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

Pull networking updates from David Miller:

 1) More iov_iter conversion work from Al Viro.

    [ The "crypto: switch af_alg_make_sg() to iov_iter" commit was
      wrong, and this pull actually adds an extra commit on top of the
      branch I'm pulling to fix that up, so that the pre-merge state is
      ok.   - Linus ]

 2) Various optimizations to the ipv4 forwarding information base trie
    lookup implementation.  From Alexander Duyck.

 3) Remove sock_iocb altogether, from CHristoph Hellwig.

 4) Allow congestion control algorithm selection via routing metrics.
    From Daniel Borkmann.

 5) Make ipv4 uncached route list per-cpu, from Eric Dumazet.

 6) Handle rfs hash collisions more gracefully, also from Eric Dumazet.

 7) Add xmit_more support to r8169, e1000, and e1000e drivers.  From
    Florian Westphal.

 8) Transparent Ethernet Bridging support for GRO, from Jesse Gross.

 9) Add BPF packet actions to packet scheduler, from Jiri Pirko.

10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer.

11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman
    Kwok.

12) More sanely handle out-of-window dupacks, which can result in
    serious ACK storms.  From Neal Cardwell.

13) Various rhashtable bug fixes and enhancements, from Herbert Xu,
    Patrick McHardy, and Thomas Graf.

14) Support xmit_more in be2net, from Sathya Perla.

15) Group Policy extensions for vxlan, from Thomas Graf.

16) Remove Checksum Offload support for vxlan, from Tom Herbert.

17) Like ipv4, support lockless transmit over ipv6 UDP sockets.  From
    Vlad Yasevich.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits)
  crypto: fix af_alg_make_sg() conversion to iov_iter
  ipv4: Namespecify TCP PMTU mechanism
  i40e: Fix for stats init function call in Rx setup
  tcp: don't include Fast Open option in SYN-ACK on pure SYN-data
  openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set
  ipv6: Make __ipv6_select_ident static
  ipv6: Fix fragment id assignment on LE arches.
  bridge: Fix inability to add non-vlan fdb entry
  net: Mellanox: Delete unnecessary checks before the function call "vunmap"
  cxgb4: Add support in cxgb4 to get expansion rom version via ethtool
  ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version
  net: dsa: Remove redundant phy_attach()
  IB/mlx4: Reset flow support for IB kernel ULPs
  IB/mlx4: Always use the correct port for mirrored multicast attachments
  net/bonding: Fix potential bad memory access during bonding events
  tipc: remove tipc_snprintf
  tipc: nl compat add noop and remove legacy nl framework
  tipc: convert legacy nl stats show to nl compat
  tipc: convert legacy nl net id get to nl compat
  tipc: convert legacy nl net id set to nl compat
  ...

1 files changed, 36 insertions, 15 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 52e1f2bf0ca2..ad5064362c5c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1328,14 +1328,22 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 	return ret;
 }
 
-static DEFINE_SPINLOCK(rt_uncached_lock);
-static LIST_HEAD(rt_uncached_list);
+struct uncached_list {
+	spinlock_t		lock;
+	struct list_head	head;
+};
+
+static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
 
 static void rt_add_uncached_list(struct rtable *rt)
 {
-	spin_lock_bh(&rt_uncached_lock);
-	list_add_tail(&rt->rt_uncached, &rt_uncached_list);
-	spin_unlock_bh(&rt_uncached_lock);
+	struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list);
+
+	rt->rt_uncached_list = ul;
+
+	spin_lock_bh(&ul->lock);
+	list_add_tail(&rt->rt_uncached, &ul->head);
+	spin_unlock_bh(&ul->lock);
 }
 
 static void ipv4_dst_destroy(struct dst_entry *dst)
@@ -1343,27 +1351,32 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 	struct rtable *rt = (struct rtable *) dst;
 
 	if (!list_empty(&rt->rt_uncached)) {
-		spin_lock_bh(&rt_uncached_lock);
+		struct uncached_list *ul = rt->rt_uncached_list;
+
+		spin_lock_bh(&ul->lock);
 		list_del(&rt->rt_uncached);
-		spin_unlock_bh(&rt_uncached_lock);
+		spin_unlock_bh(&ul->lock);
 	}
 }
 
 void rt_flush_dev(struct net_device *dev)
 {
-	if (!list_empty(&rt_uncached_list)) {
-		struct net *net = dev_net(dev);
-		struct rtable *rt;
+	struct net *net = dev_net(dev);
+	struct rtable *rt;
+	int cpu;
 
-		spin_lock_bh(&rt_uncached_lock);
-		list_for_each_entry(rt, &rt_uncached_list, rt_uncached) {
+	for_each_possible_cpu(cpu) {
+		struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
+
+		spin_lock_bh(&ul->lock);
+		list_for_each_entry(rt, &ul->head, rt_uncached) {
 			if (rt->dst.dev != dev)
 				continue;
 			rt->dst.dev = net->loopback_dev;
 			dev_hold(rt->dst.dev);
 			dev_put(dev);
 		}
-		spin_unlock_bh(&rt_uncached_lock);
+		spin_unlock_bh(&ul->lock);
 	}
 }
 
@@ -2381,7 +2394,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -2473,7 +2487,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	err = rt_fill_info(net, dst, src, &fl4, skb,
 			   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
 			   RTM_NEWROUTE, 0, 0);
-	if (err <= 0)
+	if (err < 0)
 		goto errout_free;
 
 	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
@@ -2721,6 +2735,7 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
 int __init ip_rt_init(void)
 {
 	int rc = 0;
+	int cpu;
 
 	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
 	if (!ip_idents)
@@ -2728,6 +2743,12 @@ int __init ip_rt_init(void)
 
 	prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
 
+	for_each_possible_cpu(cpu) {
+		struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
+
+		INIT_LIST_HEAD(&ul->head);
+		spin_lock_init(&ul->lock);
+	}
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)