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

Pull networking changes from David Miller:
 "Noteworthy changes this time around:

   1) Multicast rejoin support for team driver, from Jiri Pirko.

   2) Centralize and simplify TCP RTT measurement handling in order to
      reduce the impact of bad RTO seeding from SYN/ACKs.  Also, when
      both timestamps and local RTT measurements are available prefer
      the later because there are broken middleware devices which
      scramble the timestamp.

      From Yuchung Cheng.

   3) Add TCP_NOTSENT_LOWAT socket option to limit the amount of kernel
      memory consumed to queue up unsend user data.  From Eric Dumazet.

   4) Add a "physical port ID" abstraction for network devices, from
      Jiri Pirko.

   5) Add a "suppress" operation to influence fib_rules lookups, from
      Stefan Tomanek.

   6) Add a networking development FAQ, from Paul Gortmaker.

   7) Extend the information provided by tcp_probe and add ipv6 support,
      from Daniel Borkmann.

   8) Use RCU locking more extensively in openvswitch data paths, from
      Pravin B Shelar.

   9) Add SCTP support to openvswitch, from Joe Stringer.

  10) Add EF10 chip support to SFC driver, from Ben Hutchings.

  11) Add new SYNPROXY netfilter target, from Patrick McHardy.

  12) Compute a rate approximation for sending in TCP sockets, and use
      this to more intelligently coalesce TSO frames.  Furthermore, add
      a new packet scheduler which takes advantage of this estimate when
      available.  From Eric Dumazet.

  13) Allow AF_PACKET fanouts with random selection, from Daniel
      Borkmann.

  14) Add ipv6 support to vxlan driver, from Cong Wang"

Resolved conflicts as per discussion.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1218 commits)
  openvswitch: Fix alignment of struct sw_flow_key.
  netfilter: Fix build errors with xt_socket.c
  tcp: Add missing braces to do_tcp_setsockopt
  caif: Add missing braces to multiline if in cfctrl_linkup_request
  bnx2x: Add missing braces in bnx2x:bnx2x_link_initialize
  vxlan: Fix kernel panic on device delete.
  net: mvneta: implement ->ndo_do_ioctl() to support PHY ioctls
  net: mvneta: properly disable HW PHY polling and ensure adjust_link() works
  icplus: Use netif_running to determine device state
  ethernet/arc/arc_emac: Fix huge delays in large file copies
  tuntap: orphan frags before trying to set tx timestamp
  tuntap: purge socket error queue on detach
  qlcnic: use standard NAPI weights
  ipv6:introduce function to find route for redirect
  bnx2x: VF RSS support - VF side
  bnx2x: VF RSS support - PF side
  vxlan: Notify drivers for listening UDP port changes
  net: usbnet: update addr_assign_type if appropriate
  driver/net: enic: update enic maintainers and driver
  driver/net: enic: Exposing symbols for Cisco's low latency driver
  ...

1 files changed, 32 insertions, 14 deletions

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 46ba243605a3..61355f7f4da5 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -41,6 +41,7 @@
 #include <linux/netfilter_ipv6.h>
 #include <linux/slab.h>
 #include <linux/hash.h>
+#include <linux/etherdevice.h>
 
 #include <asm/uaccess.h>
 #include <linux/atomic.h>
@@ -315,6 +316,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 
 	t = netdev_priv(dev);
 	t->parms = *p;
+	t->net = dev_net(dev);
 	err = ip6_tnl_create2(dev);
 	if (err < 0)
 		goto failed_free;
@@ -374,7 +376,7 @@ static void
 ip6_tnl_dev_uninit(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct net *net = dev_net(dev);
+	struct net *net = t->net;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 
 	if (dev == ip6n->fb_tnl_dev)
@@ -741,7 +743,7 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
 {
 	struct __ip6_tnl_parm *p = &t->parms;
 	int ret = 0;
-	struct net *net = dev_net(t->dev);
+	struct net *net = t->net;
 
 	if ((p->flags & IP6_TNL_F_CAP_RCV) ||
 	    ((p->flags & IP6_TNL_F_CAP_PER_PACKET) &&
@@ -800,14 +802,12 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
 			rcu_read_unlock();
 			goto discard;
 		}
-		secpath_reset(skb);
 		skb->mac_header = skb->network_header;
 		skb_reset_network_header(skb);
 		skb->protocol = htons(protocol);
-		skb->pkt_type = PACKET_HOST;
 		memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 
-		__skb_tunnel_rx(skb, t->dev);
+		__skb_tunnel_rx(skb, t->dev, t->net);
 
 		err = dscp_ecn_decapsulate(t, ipv6h, skb);
 		if (unlikely(err)) {
@@ -895,7 +895,7 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
 {
 	struct __ip6_tnl_parm *p = &t->parms;
 	int ret = 0;
-	struct net *net = dev_net(t->dev);
+	struct net *net = t->net;
 
 	if (p->flags & IP6_TNL_F_CAP_XMIT) {
 		struct net_device *ldev = NULL;
@@ -945,8 +945,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 			 int encap_limit,
 			 __u32 *pmtu)
 {
-	struct net *net = dev_net(dev);
 	struct ip6_tnl *t = netdev_priv(dev);
+	struct net *net = t->net;
 	struct net_device_stats *stats = &t->dev->stats;
 	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct ipv6_tel_txoption opt;
@@ -996,6 +996,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 		goto tx_err_dst_release;
 	}
 
+	skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
+
 	/*
 	 * Okay, now see if we can stuff it in the buffer as-is.
 	 */
@@ -1013,7 +1015,6 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 		consume_skb(skb);
 		skb = new_skb;
 	}
-	skb_dst_drop(skb);
 	if (fl6->flowi6_mark) {
 		skb_dst_set(skb, dst);
 		ndst = NULL;
@@ -1208,7 +1209,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 		int strict = (ipv6_addr_type(&p->raddr) &
 			      (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
 
-		struct rt6_info *rt = rt6_lookup(dev_net(dev),
+		struct rt6_info *rt = rt6_lookup(t->net,
 						 &p->raddr, &p->laddr,
 						 p->link, strict);
 
@@ -1257,7 +1258,7 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
 
 static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
 {
-	struct net *net = dev_net(t->dev);
+	struct net *net = t->net;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	int err;
 
@@ -1469,8 +1470,10 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
 		dev->mtu-=8;
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	/* This perm addr will be used as interface identifier by IPv6 */
+	dev->addr_assign_type = NET_ADDR_RANDOM;
+	eth_random_addr(dev->perm_addr);
 }
 
 
@@ -1485,6 +1488,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 	struct ip6_tnl *t = netdev_priv(dev);
 
 	t->dev = dev;
+	t->net = dev_net(dev);
 	dev->tstats = alloc_percpu(struct pcpu_tstats);
 	if (!dev->tstats)
 		return -ENOMEM;
@@ -1602,9 +1606,9 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
 static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
 			      struct nlattr *data[])
 {
-	struct ip6_tnl *t;
+	struct ip6_tnl *t = netdev_priv(dev);
 	struct __ip6_tnl_parm p;
-	struct net *net = dev_net(dev);
+	struct net *net = t->net;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 
 	if (dev == ip6n->fb_tnl_dev)
@@ -1705,14 +1709,24 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
 
 static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
 {
+	struct net *net = dev_net(ip6n->fb_tnl_dev);
+	struct net_device *dev, *aux;
 	int h;
 	struct ip6_tnl *t;
 	LIST_HEAD(list);
 
+	for_each_netdev_safe(net, dev, aux)
+		if (dev->rtnl_link_ops == &ip6_link_ops)
+			unregister_netdevice_queue(dev, &list);
+
 	for (h = 0; h < HASH_SIZE; h++) {
 		t = rtnl_dereference(ip6n->tnls_r_l[h]);
 		while (t != NULL) {
-			unregister_netdevice_queue(t->dev, &list);
+			/* If dev is in the same netns, it has already
+			 * been added to the list by the previous loop.
+			 */
+			if (!net_eq(dev_net(t->dev), net))
+				unregister_netdevice_queue(t->dev, &list);
 			t = rtnl_dereference(t->next);
 		}
 	}
@@ -1738,6 +1752,10 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	if (!ip6n->fb_tnl_dev)
 		goto err_alloc_dev;
 	dev_net_set(ip6n->fb_tnl_dev, net);
+	/* FB netdevice is special: we have one, and only one per netns.
+	 * Allowing to move it to another netns is clearly unsafe.
+	 */
+	ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL;
 
 	err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
 	if (err < 0)