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

Pull networking update from David Miller:

 1) Checkpoint/restarted TCP sockets now can properly propagate the TCP
    timestamp offset.  From Andrey Vagin.

 2) VMWARE VM VSOCK layer, from Andy King.

 3) Much improved support for virtual functions and SR-IOV in bnx2x,
    from Ariel ELior.

 4) All protocols on ipv4 and ipv6 are now network namespace aware, and
    all the compatability checks for initial-namespace-only protocols is
    removed.  Thanks to Tom Parkin for helping deal with the last major
    holdout, L2TP.

 5) IPV6 support in netpoll and network namespace support in pktgen,
    from Cong Wang.

 6) Multiple Registration Protocol (MRP) and Multiple VLAN Registration
    Protocol (MVRP) support, from David Ward.

 7) Compute packet lengths more accurately in the packet scheduler, from
    Eric Dumazet.

 8) Use per-task page fragment allocator in skb_append_datato_frags(),
    also from Eric Dumazet.

 9) Add support for connection tracking labels in netfilter, from
    Florian Westphal.

10) Fix default multicast group joining on ipv6, and add anti-spoofing
    checks to 6to4 and 6rd.  From Hannes Frederic Sowa.

11) Make ipv4/ipv6 fragmentation memory limits more reasonable in modern
    times, rearrange inet frag datastructures for better cacheline
    locality, and move more operations outside of locking.  From Jesper
    Dangaard Brouer.

12) Instead of strict master <--> slave relationships, allow arbitrary
    scenerios with "upper device lists".  From Jiri Pirko.

13) Improve rate limiting accuracy in TBF and act_police, also from Jiri
    Pirko.

14) Add a BPF filter netfilter match target, from Willem de Bruijn.

15) Orphan and delete a bunch of pre-historic networking drivers from
    Paul Gortmaker.

16) Add TSO support for GRE tunnels, from Pravin B SHelar.  Although
    this still needs some minor bug fixing before it's %100 correct in
    all cases.

17) Handle unresolved IPSEC states like ARP, with a resolution packet
    queue.  From Steffen Klassert.

18) Remove TCP Appropriate Byte Count support (ABC), from Stephen
    Hemminger.  This was long overdue.

19) Support SO_REUSEPORT, from Tom Herbert.

20) Allow locking a socket BPF filter, so that it cannot change after a
    process drops capabilities.

21) Add VLAN filtering to bridge, from Vlad Yasevich.

22) Bring ipv6 on-par with ipv4 and do not cache neighbour entries in
    the ipv6 routes, from YOSHIFUJI Hideaki.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1538 commits)
  ipv6: fix race condition regarding dst->expires and dst->from.
  net: fix a wrong assignment in skb_split()
  ip_gre: remove an extra dst_release()
  ppp: set qdisc_tx_busylock to avoid LOCKDEP splat
  atl1c: restore buffer state
  net: fix a build failure when !CONFIG_PROC_FS
  net: ipv4: fix waring -Wunused-variable
  net: proc: fix build failed when procfs is not configured
  Revert "xen: netback: remove redundant xenvif_put"
  net: move procfs code to net/core/net-procfs.c
  qmi_wwan, cdc-ether: add ADU960S
  bonding: set sysfs device_type to 'bond'
  bonding: fix bond_release_all inconsistencies
  b44: use netdev_alloc_skb_ip_align()
  xen: netback: remove redundant xenvif_put
  net: fec: Do a sanity check on the gpio number
  ip_gre: propogate target device GSO capability to the tunnel device
  ip_gre: allow CSUM capable devices to handle packets
  bonding: Fix initialize after use for 3ad machine state spinlock
  bonding: Fix race condition between bond_enslave() and bond_3ad_update_lacp_rate()
  ...

1 files changed, 29 insertions, 48 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 0c7c03d50dc0..155eccfa7760 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -56,8 +56,6 @@
 #include <net/checksum.h>
 #include <linux/mroute6.h>
 
-int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
-
 int __ip6_local_out(struct sk_buff *skb)
 {
 	int len;
@@ -88,7 +86,8 @@ static int ip6_finish_output2(struct sk_buff *skb)
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
 	struct neighbour *neigh;
-	struct rt6_info *rt;
+	struct in6_addr *nexthop;
+	int ret;
 
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->dev = dev;
@@ -121,12 +120,26 @@ static int ip6_finish_output2(struct sk_buff *skb)
 
 		IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
 				skb->len);
+
+		if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <=
+		    IPV6_ADDR_SCOPE_NODELOCAL &&
+		    !(dev->flags & IFF_LOOPBACK)) {
+			kfree_skb(skb);
+			return 0;
+		}
 	}
 
-	rt = (struct rt6_info *) dst;
-	neigh = rt->n;
-	if (neigh)
-		return dst_neigh_output(dst, neigh, skb);
+	rcu_read_lock_bh();
+	nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
+	neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
+	if (unlikely(!neigh))
+		neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
+	if (!IS_ERR(neigh)) {
+		ret = dst_neigh_output(dst, neigh, skb);
+		rcu_read_unlock_bh();
+		return ret;
+	}
+	rcu_read_unlock_bh();
 
 	IP6_INC_STATS_BH(dev_net(dst->dev),
 			 ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
@@ -216,7 +229,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	if (hlimit < 0)
 		hlimit = ip6_dst_hoplimit(dst);
 
-	*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl6->flowlabel;
+	ip6_flow_hdr(hdr, tclass, fl6->flowlabel);
 
 	hdr->payload_len = htons(seg_len);
 	hdr->nexthdr = proto;
@@ -236,9 +249,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 			       dst->dev, dst_output);
 	}
 
-	net_dbg_ratelimited("IPv6: sending pkt_too_big to self\n");
 	skb->dev = dst->dev;
-	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+	ipv6_local_error(sk, EMSGSIZE, fl6, mtu);
 	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
 	kfree_skb(skb);
 	return -EMSGSIZE;
@@ -246,39 +258,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 
 EXPORT_SYMBOL(ip6_xmit);
 
-/*
- *	To avoid extra problems ND packets are send through this
- *	routine. It's code duplication but I really want to avoid
- *	extra checks since ipv6_build_header is used by TCP (which
- *	is for us performance critical)
- */
-
-int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev,
-	       const struct in6_addr *saddr, const struct in6_addr *daddr,
-	       int proto, int len)
-{
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct ipv6hdr *hdr;
-
-	skb->protocol = htons(ETH_P_IPV6);
-	skb->dev = dev;
-
-	skb_reset_network_header(skb);
-	skb_put(skb, sizeof(struct ipv6hdr));
-	hdr = ipv6_hdr(skb);
-
-	*(__be32*)hdr = htonl(0x60000000);
-
-	hdr->payload_len = htons(len);
-	hdr->nexthdr = proto;
-	hdr->hop_limit = np->hop_limit;
-
-	hdr->saddr = *saddr;
-	hdr->daddr = *daddr;
-
-	return 0;
-}
-
 static int ip6_call_ra_chain(struct sk_buff *skb, int sel)
 {
 	struct ip6_ra_chain *ra;
@@ -913,8 +892,12 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 	 * dst entry of the nexthop router
 	 */
 	rt = (struct rt6_info *) *dst;
-	n = rt->n;
-	if (n && !(n->nud_state & NUD_VALID)) {
+	rcu_read_lock_bh();
+	n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr));
+	err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
+	rcu_read_unlock_bh();
+
+	if (err) {
 		struct inet6_ifaddr *ifp;
 		struct flowi6 fl_gw6;
 		int redirect;
@@ -1548,9 +1531,7 @@ int ip6_push_pending_frames(struct sock *sk)
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
 
-	*(__be32*)hdr = fl6->flowlabel |
-		     htonl(0x60000000 | ((int)np->cork.tclass << 20));
-
+	ip6_flow_hdr(hdr, np->cork.tclass, fl6->flowlabel);
 	hdr->hop_limit = np->cork.hop_limit;
 	hdr->nexthdr = proto;
 	hdr->saddr = fl6->saddr;