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

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

1 files changed, 20 insertions, 22 deletions

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 638af06..18cead7 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -315,14 +315,6 @@ void xfrm_policy_destroy(struct xfrm_policy *policy)
 }
 EXPORT_SYMBOL(xfrm_policy_destroy);
 
-static void xfrm_queue_purge(struct sk_buff_head *list)
-{
-	struct sk_buff *skb;
-
-	while ((skb = skb_dequeue(list)) != NULL)
-		kfree_skb(skb);
-}
-
 /* Rule must be locked. Release descentant resources, announce
  * entry dead. The rule must be unlinked from lists to the moment.
  */
@@ -335,7 +327,7 @@ static void xfrm_policy_kill(struct xfrm_policy *policy)
 
 	if (del_timer(&policy->polq.hold_timer))
 		xfrm_pol_put(policy);
-	xfrm_queue_purge(&policy->polq.hold_queue);
+	skb_queue_purge(&policy->polq.hold_queue);
 
 	if (del_timer(&policy->timer))
 		xfrm_pol_put(policy);
@@ -708,6 +700,9 @@ static void xfrm_policy_requeue(struct xfrm_policy *old,
 	struct xfrm_policy_queue *pq = &old->polq;
 	struct sk_buff_head list;
 
+	if (skb_queue_empty(&pq->hold_queue))
+		return;
+
 	__skb_queue_head_init(&list);
 
 	spin_lock_bh(&pq->hold_queue.lock);
@@ -716,9 +711,6 @@ static void xfrm_policy_requeue(struct xfrm_policy *old,
 		xfrm_pol_put(old);
 	spin_unlock_bh(&pq->hold_queue.lock);
 
-	if (skb_queue_empty(&list))
-		return;
-
 	pq = &new->polq;
 
 	spin_lock_bh(&pq->hold_queue.lock);
@@ -1012,7 +1004,9 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
 	if (list_empty(&walk->walk.all))
 		x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all);
 	else
-		x = list_entry(&walk->walk.all, struct xfrm_policy_walk_entry, all);
+		x = list_first_entry(&walk->walk.all,
+				     struct xfrm_policy_walk_entry, all);
+
 	list_for_each_entry_from(x, &net->xfrm.policy_all, all) {
 		if (x->dead)
 			continue;
@@ -1120,6 +1114,9 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 	}
 	chain = &net->xfrm.policy_inexact[dir];
 	hlist_for_each_entry(pol, chain, bydst) {
+		if ((pol->priority >= priority) && ret)
+			break;
+
 		err = xfrm_policy_match(pol, fl, type, family, dir);
 		if (err) {
 			if (err == -ESRCH)
@@ -1128,13 +1125,13 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 				ret = ERR_PTR(err);
 				goto fail;
 			}
-		} else if (pol->priority < priority) {
+		} else {
 			ret = pol;
 			break;
 		}
 	}
-	if (ret)
-		xfrm_pol_hold(ret);
+
+	xfrm_pol_hold(ret);
 fail:
 	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
@@ -1955,7 +1952,7 @@ out:
 
 purge_queue:
 	pq->timeout = 0;
-	xfrm_queue_purge(&pq->hold_queue);
+	skb_queue_purge(&pq->hold_queue);
 	xfrm_pol_put(pol);
 }
 
@@ -2814,7 +2811,7 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 		return -EAFNOSUPPORT;
 	spin_lock(&xfrm_policy_afinfo_lock);
 	if (unlikely(xfrm_policy_afinfo[afinfo->family] != NULL))
-		err = -ENOBUFS;
+		err = -EEXIST;
 	else {
 		struct dst_ops *dst_ops = afinfo->dst_ops;
 		if (likely(dst_ops->kmem_cachep == NULL))
@@ -3209,16 +3206,17 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *
 	}
 	chain = &net->xfrm.policy_inexact[dir];
 	hlist_for_each_entry(pol, chain, bydst) {
+		if ((pol->priority >= priority) && ret)
+			break;
+
 		if (xfrm_migrate_selector_match(sel, &pol->selector) &&
-		    pol->type == type &&
-		    pol->priority < priority) {
+		    pol->type == type) {
 			ret = pol;
 			break;
 		}
 	}
 
-	if (ret)
-		xfrm_pol_hold(ret);
+	xfrm_pol_hold(ret);
 
 	read_unlock_bh(&net->xfrm.xfrm_policy_lock);