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

Pull networking fixes from David Miller:

 1) There was a simplification in the ipv6 ndisc packet sending
    attempted here, which avoided using memory accounting on the
    per-netns ndisc socket for sending NDISC packets.  It did fix some
    important issues, but it causes regressions so it gets reverted here
    too.  Specifically, the problem with this change is that the IPV6
    output path really depends upon there being a valid skb->sk
    attached.

    The reason we want to do this change in some form when we figure out
    how to do it right, is that if a device goes down the ndisc_sk
    socket send queue will fill up and block NDISC packets that we want
    to send to other devices too.  That's really bad behavior.

    Hopefully Thomas can come up with a better version of this change.

 2) Fix a severe TCP performance regression by reverting a change made
    to dev_pick_tx() quite some time ago.  From Eric Dumazet.

 3) TIPC returns wrongly signed error codes, fix from Erik Hugne.

 4) Fix OOPS when doing IPSEC over ipv4 tunnels due to orphaning the
    skb->sk too early.  Fix from Li Hongjun.

 5) RAW ipv4 sockets can use the wrong routing key during lookup, from
    Chris Clark.

 6) Similar to #1 revert an older change that tried to use plain
    alloc_skb() for SYN/ACK TCP packets, this broke the netfilter owner
    mark which needs to see the skb->sk for such frames.  From Phil
    Oester.

 7) BNX2x driver bug fixes from Ariel Elior and Yuval Mintz,
    specifically in the handling of virtual functions.

 8) IPSEC path error propagations to sockets is not done properly when
    we have v4 in v6, and v6 in v4 type rules.  Fix from Hannes Frederic
    Sowa.

 9) Fix missing channel context release in mac80211, from Johannes Berg.

10) Fix network namespace handing wrt.  SCM_RIGHTS, from Andy
    Lutomirski.

11) Fix usage of bogus NAPI weight in jme, netxen, and ps3_gelic
    drivers.  From Michal Schmidt.

12) Hopefully a complete and correct fix for the genetlink dump locking
    and module reference counting.  From Pravin B Shelar.

13) sk_busy_loop() must do a cpu_relax(), from Eliezer Tamir.

14) Fix handling of timestamp offset when restoring a snapshotted TCP
    socket.  From Andrew Vagin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (44 commits)
  net: fec: fix time stamping logic after napi conversion
  net: bridge: convert MLDv2 Query MRC into msecs_to_jiffies for max_delay
  mISDN: return -EINVAL on error in dsp_control_req()
  net: revert 8728c544a9c ("net: dev_pick_tx() fix")
  Revert "ipv6: Don't depend on per socket memory for neighbour discovery messages"
  ipv4 tunnels: fix an oops when using ipip/sit with IPsec
  tipc: set sk_err correctly when connection fails
  tcp: tcp_make_synack() should use sock_wmalloc
  bridge: separate querier and query timer into IGMP/IPv4 and MLD/IPv6 ones
  ipv6: Don't depend on per socket memory for neighbour discovery messages
  ipv4: sendto/hdrincl: don't use destination address found in header
  tcp: don't apply tsoffset if rcv_tsecr is zero
  tcp: initialize rcv_tstamp for restored sockets
  net: xilinx: fix memleak
  net: usb: Add HP hs2434 device to ZLP exception table
  net: add cpu_relax to busy poll loop
  net: stmmac: fixed the pbl setting with DT
  genl: Hold reference on correct module while netlink-dump.
  genl: Fix genl dumpit() locking.
  xfrm: Fix potential null pointer dereference in xdst_queue_output
  ...

7 files changed, 38 insertions, 10 deletions

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index ecd60733e5e2..90747f1973fe 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -724,6 +724,11 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 		ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
 	}
 
+	if (likely(!skb->encapsulation)) {
+		skb_reset_inner_headers(skb);
+		skb->encapsulation = 1;
+	}
+
 	skb_push(skb, gre_hlen);
 	skb_reset_network_header(skb);
 	skb_set_transport_header(skb, sizeof(*ipv6h));
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6e3ddf806ec2..e7ceb6c871d1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -238,6 +238,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	hdr->saddr = fl6->saddr;
 	hdr->daddr = *first_hop;
 
+	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 
@@ -1057,6 +1058,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		/* initialize protocol header pointer */
 		skb->transport_header = skb->network_header + fragheaderlen;
 
+		skb->protocol = htons(ETH_P_IPV6);
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		skb->csum = 0;
 	}
@@ -1359,6 +1361,7 @@ alloc_new_skb:
 			/*
 			 *	Fill in the control structures
 			 */
+			skb->protocol = htons(ETH_P_IPV6);
 			skb->ip_summed = CHECKSUM_NONE;
 			skb->csum = 0;
 			/* reserve for fragmentation and ipsec header */
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1e55866cead7..46ba243605a3 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1027,6 +1027,12 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 		init_tel_txopt(&opt, encap_limit);
 		ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
 	}
+
+	if (likely(!skb->encapsulation)) {
+		skb_reset_inner_headers(skb);
+		skb->encapsulation = 1;
+	}
+
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index c45f7a5c36e9..cdaed47ba932 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -628,6 +628,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
 		goto error;
 	skb_reserve(skb, hlen);
 
+	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 	skb_dst_set(skb, &rt->dst);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a3437a4cd07e..21b25dd8466b 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -645,11 +645,7 @@ static int ipip_rcv(struct sk_buff *skb)
 	const struct iphdr *iph;
 	struct ip_tunnel *tunnel;
 
-	if (iptunnel_pull_header(skb, 0, tpi.proto))
-		goto drop;
-
 	iph = ip_hdr(skb);
-
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
 				     iph->saddr, iph->daddr);
 	if (tunnel != NULL) {
@@ -659,6 +655,8 @@ static int ipip_rcv(struct sk_buff *skb)
 
 		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 			goto drop;
+		if (iptunnel_pull_header(skb, 0, tpi.proto))
+			goto drop;
 		return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
 	}
 
@@ -888,6 +886,11 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		ttl = iph6->hop_limit;
 	tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
 
+	if (likely(!skb->encapsulation)) {
+		skb_reset_inner_headers(skb);
+		skb->encapsulation = 1;
+	}
+
 	err = iptunnel_xmit(dev_net(dev), rt, skb, fl4.saddr, fl4.daddr,
 			    IPPROTO_IPV6, tos, ttl, df);
 	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 8755a3079d0f..6cd625e37706 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -34,8 +34,10 @@ static int xfrm6_local_dontfrag(struct sk_buff *skb)
 	struct sock *sk = skb->sk;
 
 	if (sk) {
-		proto = sk->sk_protocol;
+		if (sk->sk_family != AF_INET6)
+			return 0;
 
+		proto = sk->sk_protocol;
 		if (proto == IPPROTO_UDP || proto == IPPROTO_RAW)
 			return inet6_sk(sk)->dontfrag;
 	}
@@ -54,13 +56,15 @@ static void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu)
 	ipv6_local_rxpmtu(sk, &fl6, mtu);
 }
 
-static void xfrm6_local_error(struct sk_buff *skb, u32 mtu)
+void xfrm6_local_error(struct sk_buff *skb, u32 mtu)
 {
 	struct flowi6 fl6;
+	const struct ipv6hdr *hdr;
 	struct sock *sk = skb->sk;
 
+	hdr = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
 	fl6.fl6_dport = inet_sk(sk)->inet_dport;
-	fl6.daddr = ipv6_hdr(skb)->daddr;
+	fl6.daddr = hdr->daddr;
 
 	ipv6_local_error(sk, EMSGSIZE, &fl6, mtu);
 }
@@ -80,7 +84,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 		if (xfrm6_local_dontfrag(skb))
 			xfrm6_local_rxpmtu(skb, mtu);
 		else if (skb->sk)
-			xfrm6_local_error(skb, mtu);
+			xfrm_local_error(skb, mtu);
 		else
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 		ret = -EMSGSIZE;
@@ -136,13 +140,18 @@ static int __xfrm6_output(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct xfrm_state *x = dst->xfrm;
-	int mtu = ip6_skb_dst_mtu(skb);
+	int mtu;
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		mtu = ip6_skb_dst_mtu(skb);
+	else
+		mtu = dst_mtu(skb_dst(skb));
 
 	if (skb->len > mtu && xfrm6_local_dontfrag(skb)) {
 		xfrm6_local_rxpmtu(skb, mtu);
 		return -EMSGSIZE;
 	} else if (!skb->local_df && skb->len > mtu && skb->sk) {
-		xfrm6_local_error(skb, mtu);
+		xfrm_local_error(skb, mtu);
 		return -EMSGSIZE;
 	}
 
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index d8c70b8efc24..3fc970135fc6 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -183,6 +183,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = {
 	.extract_input		= xfrm6_extract_input,
 	.extract_output		= xfrm6_extract_output,
 	.transport_finish	= xfrm6_transport_finish,
+	.local_error		= xfrm6_local_error,
 };
 
 int __init xfrm6_state_init(void)