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

Pull networking updates from David Miller:

 1) New offloading infrastructure and example 'rocker' driver for
    offloading of switching and routing to hardware.

    This work was done by a large group of dedicated individuals, not
    limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
    Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu

 2) Start making the networking operate on IOV iterators instead of
    modifying iov objects in-situ during transfers.  Thanks to Al Viro
    and Herbert Xu.

 3) A set of new netlink interfaces for the TIPC stack, from Richard
    Alpe.

 4) Remove unnecessary looping during ipv6 routing lookups, from Martin
    KaFai Lau.

 5) Add PAUSE frame generation support to gianfar driver, from Matei
    Pavaluca.

 6) Allow for larger reordering levels in TCP, which are easily
    achievable in the real world right now, from Eric Dumazet.

 7) Add a variable of napi_schedule that doesn't need to disable cpu
    interrupts, from Eric Dumazet.

 8) Use a doubly linked list to optimize neigh_parms_release(), from
    Nicolas Dichtel.

 9) Various enhancements to the kernel BPF verifier, and allow eBPF
    programs to actually be attached to sockets.  From Alexei
    Starovoitov.

10) Support TSO/LSO in sunvnet driver, from David L Stevens.

11) Allow controlling ECN usage via routing metrics, from Florian
    Westphal.

12) Remote checksum offload, from Tom Herbert.

13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
    driver, from Thomas Lendacky.

14) Add MPLS support to openvswitch, from Simon Horman.

15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
    Klassert.

16) Do gro flushes on a per-device basis using a timer, from Eric
    Dumazet.  This tries to resolve the conflicting goals between the
    desired handling of bulk vs.  RPC-like traffic.

17) Allow userspace to ask for the CPU upon what a packet was
    received/steered, via SO_INCOMING_CPU.  From Eric Dumazet.

18) Limit GSO packets to half the current congestion window, from Eric
    Dumazet.

19) Add a generic helper so that all drivers set their RSS keys in a
    consistent way, from Eric Dumazet.

20) Add xmit_more support to enic driver, from Govindarajulu
    Varadarajan.

21) Add VLAN packet scheduler action, from Jiri Pirko.

22) Support configurable RSS hash functions via ethtool, from Eyal
    Perry.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
  Fix race condition between vxlan_sock_add and vxlan_sock_release
  net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
  net/mlx4: Add support for A0 steering
  net/mlx4: Refactor QUERY_PORT
  net/mlx4_core: Add explicit error message when rule doesn't meet configuration
  net/mlx4: Add A0 hybrid steering
  net/mlx4: Add mlx4_bitmap zone allocator
  net/mlx4: Add a check if there are too many reserved QPs
  net/mlx4: Change QP allocation scheme
  net/mlx4_core: Use tasklet for user-space CQ completion events
  net/mlx4_core: Mask out host side virtualization features for guests
  net/mlx4_en: Set csum level for encapsulated packets
  be2net: Export tunnel offloads only when a VxLAN tunnel is created
  gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
  cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
  net: fec: only enable mdio interrupt before phy device link up
  net: fec: clear all interrupt events to support i.MX6SX
  net: fec: reset fep link status in suspend function
  net: sock: fix access via invalid file descriptor
  net: introduce helper macro for_each_cmsghdr
  ...

1 files changed, 137 insertions, 17 deletions

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 88e8de3b59b0..d06107d36ec8 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -36,6 +36,7 @@
 #include <linux/mutex.h>
 #include <linux/if_addr.h>
 #include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
 
@@ -43,6 +44,7 @@
 
 #include <linux/inet.h>
 #include <linux/netdevice.h>
+#include <net/switchdev.h>
 #include <net/ip.h>
 #include <net/protocol.h>
 #include <net/arp.h>
@@ -868,7 +870,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
 	       + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
 	       + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
-	       + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */
+	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
+	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */
 }
 
 static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -952,7 +955,7 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
 static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
 {
 	int err;
-	struct netdev_phys_port_id ppid;
+	struct netdev_phys_item_id ppid;
 
 	err = dev_get_phys_port_id(dev, &ppid);
 	if (err) {
@@ -967,6 +970,24 @@ static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
+static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
+{
+	int err;
+	struct netdev_phys_item_id psid;
+
+	err = netdev_switch_parent_id_get(dev, &psid);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	if (nla_put(skb, IFLA_PHYS_SWITCH_ID, psid.id_len, psid.id))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    int type, u32 pid, u32 seq, u32 change,
 			    unsigned int flags, u32 ext_filter_mask)
@@ -1039,6 +1060,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	if (rtnl_phys_port_id_fill(skb, dev))
 		goto nla_put_failure;
 
+	if (rtnl_phys_switch_id_fill(skb, dev))
+		goto nla_put_failure;
+
 	attr = nla_reserve(skb, IFLA_STATS,
 			sizeof(struct rtnl_link_stats));
 	if (attr == NULL)
@@ -1196,8 +1220,9 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_PROMISCUITY]	= { .type = NLA_U32 },
 	[IFLA_NUM_TX_QUEUES]	= { .type = NLA_U32 },
 	[IFLA_NUM_RX_QUEUES]	= { .type = NLA_U32 },
-	[IFLA_PHYS_PORT_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
+	[IFLA_PHYS_PORT_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
 	[IFLA_CARRIER_CHANGES]	= { .type = NLA_U32 },  /* ignored */
+	[IFLA_PHYS_SWITCH_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2221,8 +2246,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
-		  gfp_t flags)
+struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
+				       unsigned int change, gfp_t flags)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
@@ -2240,11 +2265,28 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
 		kfree_skb(skb);
 		goto errout;
 	}
-	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
-	return;
+	return skb;
 errout:
 	if (err < 0)
 		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	return NULL;
+}
+
+void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
+{
+	struct net *net = dev_net(dev);
+
+	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
+}
+
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+		  gfp_t flags)
+{
+	struct sk_buff *skb;
+
+	skb = rtmsg_ifinfo_build_skb(type, dev, change, flags);
+	if (skb)
+		rtmsg_ifinfo_send(skb, dev, flags);
 }
 EXPORT_SYMBOL(rtmsg_ifinfo);
 
@@ -2313,7 +2355,7 @@ errout:
 int ndo_dflt_fdb_add(struct ndmsg *ndm,
 		     struct nlattr *tb[],
 		     struct net_device *dev,
-		     const unsigned char *addr,
+		     const unsigned char *addr, u16 vid,
 		     u16 flags)
 {
 	int err = -EINVAL;
@@ -2339,6 +2381,28 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm,
 }
 EXPORT_SYMBOL(ndo_dflt_fdb_add);
 
+static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid)
+{
+	u16 vid = 0;
+
+	if (vlan_attr) {
+		if (nla_len(vlan_attr) != sizeof(u16)) {
+			pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n");
+			return -EINVAL;
+		}
+
+		vid = nla_get_u16(vlan_attr);
+
+		if (!vid || vid >= VLAN_VID_MASK) {
+			pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n",
+				vid);
+			return -EINVAL;
+		}
+	}
+	*p_vid = vid;
+	return 0;
+}
+
 static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
@@ -2346,6 +2410,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[NDA_MAX+1];
 	struct net_device *dev;
 	u8 *addr;
+	u16 vid;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
@@ -2371,6 +2436,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	addr = nla_data(tb[NDA_LLADDR]);
 
+	err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+	if (err)
+		return err;
+
 	err = -EOPNOTSUPP;
 
 	/* Support fdb on master device the net/bridge default case */
@@ -2379,7 +2448,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 		struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 		const struct net_device_ops *ops = br_dev->netdev_ops;
 
-		err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags);
+		err = ops->ndo_fdb_add(ndm, tb, dev, addr, vid,
+				       nlh->nlmsg_flags);
 		if (err)
 			goto out;
 		else
@@ -2390,9 +2460,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if ((ndm->ndm_flags & NTF_SELF)) {
 		if (dev->netdev_ops->ndo_fdb_add)
 			err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr,
+							   vid,
 							   nlh->nlmsg_flags);
 		else
-			err = ndo_dflt_fdb_add(ndm, tb, dev, addr,
+			err = ndo_dflt_fdb_add(ndm, tb, dev, addr, vid,
 					       nlh->nlmsg_flags);
 
 		if (!err) {
@@ -2410,7 +2481,7 @@ out:
 int ndo_dflt_fdb_del(struct ndmsg *ndm,
 		     struct nlattr *tb[],
 		     struct net_device *dev,
-		     const unsigned char *addr)
+		     const unsigned char *addr, u16 vid)
 {
 	int err = -EINVAL;
 
@@ -2439,6 +2510,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct net_device *dev;
 	int err = -EINVAL;
 	__u8 *addr;
+	u16 vid;
 
 	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
@@ -2466,6 +2538,10 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	addr = nla_data(tb[NDA_LLADDR]);
 
+	err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+	if (err)
+		return err;
+
 	err = -EOPNOTSUPP;
 
 	/* Support fdb on master device the net/bridge default case */
@@ -2475,7 +2551,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 		const struct net_device_ops *ops = br_dev->netdev_ops;
 
 		if (ops->ndo_fdb_del)
-			err = ops->ndo_fdb_del(ndm, tb, dev, addr);
+			err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
 
 		if (err)
 			goto out;
@@ -2486,9 +2562,10 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	/* Embedded bridge, macvlan, and any other device support */
 	if (ndm->ndm_flags & NTF_SELF) {
 		if (dev->netdev_ops->ndo_fdb_del)
-			err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
+			err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr,
+							   vid);
 		else
-			err = ndo_dflt_fdb_del(ndm, tb, dev, addr);
+			err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
 
 		if (!err) {
 			rtnl_fdb_notify(dev, addr, RTM_DELNEIGH);
@@ -2628,12 +2705,22 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask,
+			       unsigned int attrnum, unsigned int flag)
+{
+	if (mask & flag)
+		return nla_put_u8(skb, attrnum, !!(flags & flag));
+	return 0;
+}
+
 int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
-			    struct net_device *dev, u16 mode)
+			    struct net_device *dev, u16 mode,
+			    u32 flags, u32 mask)
 {
 	struct nlmsghdr *nlh;
 	struct ifinfomsg *ifm;
 	struct nlattr *br_afspec;
+	struct nlattr *protinfo;
 	u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
 	struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 
@@ -2665,13 +2752,46 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	if (!br_afspec)
 		goto nla_put_failure;
 
-	if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF) ||
-	    nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) {
+	if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF)) {
 		nla_nest_cancel(skb, br_afspec);
 		goto nla_put_failure;
 	}
+
+	if (mode != BRIDGE_MODE_UNDEF) {
+		if (nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) {
+			nla_nest_cancel(skb, br_afspec);
+			goto nla_put_failure;
+		}
+	}
 	nla_nest_end(skb, br_afspec);
 
+	protinfo = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
+	if (!protinfo)
+		goto nla_put_failure;
+
+	if (brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_MODE, BR_HAIRPIN_MODE) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_GUARD, BR_BPDU_GUARD) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_FAST_LEAVE,
+				BR_MULTICAST_FAST_LEAVE) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_LEARNING, BR_LEARNING) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_LEARNING_SYNC, BR_LEARNING_SYNC) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD) ||
+	    brport_nla_put_flag(skb, flags, mask,
+				IFLA_BRPORT_PROXYARP, BR_PROXYARP)) {
+		nla_nest_cancel(skb, protinfo);
+		goto nla_put_failure;
+	}
+
+	nla_nest_end(skb, protinfo);
+
 	return nlmsg_end(skb, nlh);
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);