Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Fix refcount leak in act_ipt during replace, from Davide Caratti.

 2) Set task state properly in tun during blocking reads, from Timur
    Celik.

 3) Leaked reference in DSA, from Wen Yang.

 4) NULL deref in act_tunnel_key, from Vlad Buslov.

 5) cipso_v4_erro can reference the skb IPCB in inappropriate contexts
    thus referencing garbage, from Nazarov Sergey.

 6) Don't accept RTA_VIA and RTA_GATEWAY in contexts where those
    attributes make no sense.

 7) Fix hung sendto in tipc, from Tung Nguyen.

 8) Out-of-bounds access in netlabel, from Paul Moore.

 9) Grant reference leak in xen-netback, from Igor Druzhinin.

10) Fix tx stalls with lan743x, from Bryan Whitehead.

11) Fix interrupt storm with mv88e6xxx, from Hein Kallweit.

12) Memory leak in sit on device registry failure, from Mao Wenan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (44 commits)
  net: sit: fix memory leak in sit_init_net()
  net: dsa: mv88e6xxx: Fix statistics on mv88e6161
  geneve: correctly handle ipv6.disable module parameter
  net: dsa: mv88e6xxx: prevent interrupt storm caused by mv88e6390x_port_set_cmode
  bpf: fix sanitation rewrite in case of non-pointers
  ipv4: Add ICMPv6 support when parse route ipproto
  MIPS: eBPF: Fix icache flush end address
  lan743x: Fix TX Stall Issue
  net: phy: phylink: fix uninitialized variable in phylink_get_mac_state
  net: aquantia: regression on cpus with high cores: set mode with 8 queues
  selftests: fixes for UDP GRO
  bpf: drop refcount if bpf_map_new_fd() fails in map_create()
  net: dsa: mv88e6xxx: power serdes on/off for 10G interfaces on 6390X
  net: dsa: mv88e6xxx: Fix u64 statistics
  xen-netback: don't populate the hash cache on XenBus disconnect
  xen-netback: fix occasional leak of grant ref mappings under memory pressure
  sctp: chunk.c: correct format string for size_t in printk
  net: netem: fix skb length BUG_ON in __skb_to_sgvec
  netlabel: fix out-of-bounds memory accesses
  ipv4: Pass original device to ip_rcv_finish_core
  ...

7 files changed, 61 insertions, 20 deletions

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 777fa3b7fb13..f0165c5f376b 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -667,7 +667,8 @@ static int cipso_v4_map_lvl_valid(const struct cipso_v4_doi *doi_def, u8 level)
 	case CIPSO_V4_MAP_PASS:
 		return 0;
 	case CIPSO_V4_MAP_TRANS:
-		if (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL)
+		if ((level < doi_def->map.std->lvl.cipso_size) &&
+		    (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL))
 			return 0;
 		break;
 	}
@@ -1735,13 +1736,26 @@ validate_return:
  */
 void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway)
 {
+	unsigned char optbuf[sizeof(struct ip_options) + 40];
+	struct ip_options *opt = (struct ip_options *)optbuf;
+
 	if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES)
 		return;
 
+	/*
+	 * We might be called above the IP layer,
+	 * so we can not use icmp_send and IPCB here.
+	 */
+
+	memset(opt, 0, sizeof(struct ip_options));
+	opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+	if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL))
+		return;
+
 	if (gateway)
-		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0);
+		__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, opt);
 	else
-		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0);
+		__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, opt);
 }
 
 /**
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index fe4f6a624238..ed14ec245584 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -710,6 +710,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		case RTA_GATEWAY:
 			cfg->fc_gw = nla_get_be32(attr);
 			break;
+		case RTA_VIA:
+			NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute");
+			err = -EINVAL;
+			goto errout;
 		case RTA_PRIORITY:
 			cfg->fc_priority = nla_get_u32(attr);
 			break;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 065997f414e6..3f24414150e2 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -570,7 +570,8 @@ relookup_failed:
  *			MUST reply to only the first fragment.
  */
 
-void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
+void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+		 const struct ip_options *opt)
 {
 	struct iphdr *iph;
 	int room;
@@ -691,7 +692,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 					  iph->tos;
 	mark = IP4_REPLY_MARK(net, skb_in->mark);
 
-	if (ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in))
+	if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt))
 		goto out_unlock;
 
 
@@ -742,7 +743,7 @@ out_bh_enable:
 	local_bh_enable();
 out:;
 }
-EXPORT_SYMBOL(icmp_send);
+EXPORT_SYMBOL(__icmp_send);
 
 
 static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 51d8efba6de2..1f4737b77067 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -307,11 +307,10 @@ drop:
 }
 
 static int ip_rcv_finish_core(struct net *net, struct sock *sk,
-			      struct sk_buff *skb)
+			      struct sk_buff *skb, struct net_device *dev)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	int (*edemux)(struct sk_buff *skb);
-	struct net_device *dev = skb->dev;
 	struct rtable *rt;
 	int err;
 
@@ -400,6 +399,7 @@ drop_error:
 
 static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	struct net_device *dev = skb->dev;
 	int ret;
 
 	/* if ingress device is enslaved to an L3 master device pass the
@@ -409,7 +409,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (!skb)
 		return NET_RX_SUCCESS;
 
-	ret = ip_rcv_finish_core(net, sk, skb);
+	ret = ip_rcv_finish_core(net, sk, skb, dev);
 	if (ret != NET_RX_DROP)
 		ret = dst_input(skb);
 	return ret;
@@ -545,6 +545,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 
 	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
+		struct net_device *dev = skb->dev;
 		struct dst_entry *dst;
 
 		skb_list_del_init(skb);
@@ -554,7 +555,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 		skb = l3mdev_ip_rcv(skb);
 		if (!skb)
 			continue;
-		if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP)
+		if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP)
 			continue;
 
 		dst = skb_dst(skb);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ed194d46c00e..32a35043c9f5 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -251,8 +251,9 @@ static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb)
  * If opt == NULL, then skb->data should point to IP header.
  */
 
-int ip_options_compile(struct net *net,
-		       struct ip_options *opt, struct sk_buff *skb)
+int __ip_options_compile(struct net *net,
+			 struct ip_options *opt, struct sk_buff *skb,
+			 __be32 *info)
 {
 	__be32 spec_dst = htonl(INADDR_ANY);
 	unsigned char *pp_ptr = NULL;
@@ -468,11 +469,22 @@ eol:
 		return 0;
 
 error:
-	if (skb) {
-		icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((pp_ptr-iph)<<24));
-	}
+	if (info)
+		*info = htonl((pp_ptr-iph)<<24);
 	return -EINVAL;
 }
+
+int ip_options_compile(struct net *net,
+		       struct ip_options *opt, struct sk_buff *skb)
+{
+	int ret;
+	__be32 info;
+
+	ret = __ip_options_compile(net, opt, skb, &info);
+	if (ret != 0 && skb)
+		icmp_send(skb, ICMP_PARAMETERPROB, 0, info);
+	return ret;
+}
 EXPORT_SYMBOL(ip_options_compile);
 
 /*
diff --git a/net/ipv4/netlink.c b/net/ipv4/netlink.c
index f86bb4f06609..d8e3a1fb8e82 100644
--- a/net/ipv4/netlink.c
+++ b/net/ipv4/netlink.c
@@ -3,9 +3,10 @@
 #include <linux/types.h>
 #include <net/net_namespace.h>
 #include <net/netlink.h>
+#include <linux/in6.h>
 #include <net/ip.h>
 
-int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto,
+int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
 				struct netlink_ext_ack *extack)
 {
 	*ip_proto = nla_get_u8(attr);
@@ -13,11 +14,19 @@ int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto,
 	switch (*ip_proto) {
 	case IPPROTO_TCP:
 	case IPPROTO_UDP:
+		return 0;
 	case IPPROTO_ICMP:
+		if (family != AF_INET)
+			break;
+		return 0;
+#if IS_ENABLED(CONFIG_IPV6)
+	case IPPROTO_ICMPV6:
+		if (family != AF_INET6)
+			break;
 		return 0;
-	default:
-		NL_SET_ERR_MSG(extack, "Unsupported ip proto");
-		return -EOPNOTSUPP;
+#endif
 	}
+	NL_SET_ERR_MSG(extack, "Unsupported ip proto");
+	return -EOPNOTSUPP;
 }
 EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5163b64f8fb3..7bb9128c8363 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2803,7 +2803,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 	if (tb[RTA_IP_PROTO]) {
 		err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO],
-						  &ip_proto, extack);
+						  &ip_proto, AF_INET, extack);
 		if (err)
 			return err;
 	}