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, 77 insertions, 28 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8d9a93ed9c59..c979dd96d82a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -283,9 +283,8 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
 
 		memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
 		rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
-		rt->rt6i_genid = rt_genid(net);
+		rt->rt6i_genid = rt_genid_ipv6(net);
 		INIT_LIST_HEAD(&rt->rt6i_siblings);
-		rt->rt6i_nsiblings = 0;
 	}
 	return rt;
 }
@@ -1062,7 +1061,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 	 * DST_OBSOLETE_FORCE_CHK which forces validation calls down
 	 * into this function always.
 	 */
-	if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev)))
+	if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev)))
 		return NULL;
 
 	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
@@ -1157,6 +1156,77 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 }
 EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
 
+/* Handle redirects */
+struct ip6rd_flowi {
+	struct flowi6 fl6;
+	struct in6_addr gateway;
+};
+
+static struct rt6_info *__ip6_route_redirect(struct net *net,
+					     struct fib6_table *table,
+					     struct flowi6 *fl6,
+					     int flags)
+{
+	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
+	struct rt6_info *rt;
+	struct fib6_node *fn;
+
+	/* Get the "current" route for this destination and
+	 * check if the redirect has come from approriate router.
+	 *
+	 * RFC 4861 specifies that redirects should only be
+	 * accepted if they come from the nexthop to the target.
+	 * Due to the way the routes are chosen, this notion
+	 * is a bit fuzzy and one might need to check all possible
+	 * routes.
+	 */
+
+	read_lock_bh(&table->tb6_lock);
+	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+restart:
+	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+		if (rt6_check_expired(rt))
+			continue;
+		if (rt->dst.error)
+			break;
+		if (!(rt->rt6i_flags & RTF_GATEWAY))
+			continue;
+		if (fl6->flowi6_oif != rt->dst.dev->ifindex)
+			continue;
+		if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
+			continue;
+		break;
+	}
+
+	if (!rt)
+		rt = net->ipv6.ip6_null_entry;
+	else if (rt->dst.error) {
+		rt = net->ipv6.ip6_null_entry;
+		goto out;
+	}
+	BACKTRACK(net, &fl6->saddr);
+out:
+	dst_hold(&rt->dst);
+
+	read_unlock_bh(&table->tb6_lock);
+
+	return rt;
+};
+
+static struct dst_entry *ip6_route_redirect(struct net *net,
+					const struct flowi6 *fl6,
+					const struct in6_addr *gateway)
+{
+	int flags = RT6_LOOKUP_F_HAS_SADDR;
+	struct ip6rd_flowi rdfl;
+
+	rdfl.fl6 = *fl6;
+	rdfl.gateway = *gateway;
+
+	return fib6_rule_lookup(net, &rdfl.fl6,
+				flags, __ip6_route_redirect);
+}
+
 void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
 {
 	const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
@@ -1171,9 +1241,8 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
 	fl6.saddr = iph->saddr;
 	fl6.flowlabel = ip6_flowinfo(iph);
 
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (!dst->error)
-		rt6_do_redirect(dst, NULL, skb);
+	dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr);
+	rt6_do_redirect(dst, NULL, skb);
 	dst_release(dst);
 }
 EXPORT_SYMBOL_GPL(ip6_redirect);
@@ -1193,9 +1262,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
 	fl6.daddr = msg->dest;
 	fl6.saddr = iph->daddr;
 
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (!dst->error)
-		rt6_do_redirect(dst, NULL, skb);
+	dst = ip6_route_redirect(net, &fl6, &iph->saddr);
+	rt6_do_redirect(dst, NULL, skb);
 	dst_release(dst);
 }
 
@@ -1355,25 +1423,6 @@ out:
 	return entries > rt_max_size;
 }
 
-int ip6_dst_hoplimit(struct dst_entry *dst)
-{
-	int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
-	if (hoplimit == 0) {
-		struct net_device *dev = dst->dev;
-		struct inet6_dev *idev;
-
-		rcu_read_lock();
-		idev = __in6_dev_get(dev);
-		if (idev)
-			hoplimit = idev->cnf.hop_limit;
-		else
-			hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit;
-		rcu_read_unlock();
-	}
-	return hoplimit;
-}
-EXPORT_SYMBOL(ip6_dst_hoplimit);
-
 /*
  *
  */