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

Pull networking fixes from David Miller:

 1) Fix route leak in xfrm_bundle_create().

 2) In mac80211, validate user rate mask before configuring it. From
    Johannes Berg.

 3) Properly enforce memory limits in fair queueing code, from Toke
    Hoiland-Jorgensen.

 4) Fix lockdep splat in inet_csk_route_req(), from Eric Dumazet.

 5) Fix TSO header allocation and management in mvpp2 driver, from Yan
    Markman.

 6) Don't take socket lock in BH handler in strparser code, from Tom
    Herbert.

 7) Don't show sockets from other namespaces in AF_UNIX code, from
    Andrei Vagin.

 8) Fix double free in error path of tap_open(), from Girish Moodalbail.

 9) Fix TX map failure path in igb and ixgbe, from Jean-Philippe Brucker
    and Alexander Duyck.

10) Fix DCB mode programming in stmmac driver, from Jose Abreu.

11) Fix err_count handling in various tunnels (ipip, ip6_gre). From Xin
    Long.

12) Properly align SKB head before building SKB in tuntap, from Jason
    Wang.

13) Avoid matching qdiscs with a zero handle during lookups, from Cong
    Wang.

14) Fix various endianness bugs in sctp, from Xin Long.

15) Fix tc filter callback races and add selftests which trigger the
    problem, from Cong Wang.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (73 commits)
  selftests: Introduce a new test case to tc testsuite
  selftests: Introduce a new script to generate tc batch file
  net_sched: fix call_rcu() race on act_sample module removal
  net_sched: add rtnl assertion to tcf_exts_destroy()
  net_sched: use tcf_queue_work() in tcindex filter
  net_sched: use tcf_queue_work() in rsvp filter
  net_sched: use tcf_queue_work() in route filter
  net_sched: use tcf_queue_work() in u32 filter
  net_sched: use tcf_queue_work() in matchall filter
  net_sched: use tcf_queue_work() in fw filter
  net_sched: use tcf_queue_work() in flower filter
  net_sched: use tcf_queue_work() in flow filter
  net_sched: use tcf_queue_work() in cgroup filter
  net_sched: use tcf_queue_work() in bpf filter
  net_sched: use tcf_queue_work() in basic filter
  net_sched: introduce a workqueue for RCU callbacks of tc filter
  sctp: fix some type cast warnings introduced since very beginning
  sctp: fix a type cast warnings that causes a_rwnd gets the wrong value
  sctp: fix some type cast warnings introduced by transport rhashtable
  sctp: fix some type cast warnings introduced by stream reconf
  ...

4 files changed, 52 insertions, 22 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5ec9136a7c36..b47a59cb3573 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -543,7 +543,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
-	opt = rcu_dereference(ireq->ireq_opt);
+	opt = ireq_opt_deref(ireq);
+
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index fb1ad22b5e29..cdd627355ed1 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -128,43 +128,68 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly;
 
 static int ipip_err(struct sk_buff *skb, u32 info)
 {
-
-/* All the routers (except for Linux) return only
-   8 bytes of packet payload. It means, that precise relaying of
-   ICMP in the real Internet is absolutely infeasible.
- */
+	/* All the routers (except for Linux) return only
+	 * 8 bytes of packet payload. It means, that precise relaying of
+	 * ICMP in the real Internet is absolutely infeasible.
+	 */
 	struct net *net = dev_net(skb->dev);
 	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
-	struct ip_tunnel *t;
-	int err;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	struct ip_tunnel *t;
+	int err = 0;
+
+	switch (type) {
+	case ICMP_DEST_UNREACH:
+		switch (code) {
+		case ICMP_SR_FAILED:
+			/* Impossible event. */
+			goto out;
+		default:
+			/* All others are translated to HOST_UNREACH.
+			 * rfc2003 contains "deep thoughts" about NET_UNREACH,
+			 * I believe they are just ether pollution. --ANK
+			 */
+			break;
+		}
+		break;
+
+	case ICMP_TIME_EXCEEDED:
+		if (code != ICMP_EXC_TTL)
+			goto out;
+		break;
+
+	case ICMP_REDIRECT:
+		break;
+
+	default:
+		goto out;
+	}
 
-	err = -ENOENT;
 	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 			     iph->daddr, iph->saddr, 0);
-	if (!t)
+	if (!t) {
+		err = -ENOENT;
 		goto out;
+	}
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
-		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, iph->protocol, 0);
-		err = 0;
+		ipv4_update_pmtu(skb, net, info, t->parms.link, 0,
+				 iph->protocol, 0);
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
-			      iph->protocol, 0);
-		err = 0;
+		ipv4_redirect(skb, net, t->parms.link, 0, iph->protocol, 0);
 		goto out;
 	}
 
-	if (t->parms.iph.daddr == 0)
+	if (t->parms.iph.daddr == 0) {
+		err = -ENOENT;
 		goto out;
+	}
 
-	err = 0;
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
 		goto out;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4c43365c374c..5b027c69cbc5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -877,7 +877,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    rcu_dereference(ireq->ireq_opt));
+					    ireq_opt_deref(ireq));
 		err = net_xmit_eval(err);
 	}
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0bc9e46a5369..ae60dd3faed0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -739,8 +739,10 @@ static void tcp_tsq_handler(struct sock *sk)
 		struct tcp_sock *tp = tcp_sk(sk);
 
 		if (tp->lost_out > tp->retrans_out &&
-		    tp->snd_cwnd > tcp_packets_in_flight(tp))
+		    tp->snd_cwnd > tcp_packets_in_flight(tp)) {
+			tcp_mstamp_refresh(tp);
 			tcp_xmit_retransmit_queue(sk);
+		}
 
 		tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle,
 			       0, GFP_ATOMIC);
@@ -2237,6 +2239,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 	sent_pkts = 0;
 
+	tcp_mstamp_refresh(tp);
 	if (!push_one) {
 		/* Do MTU probing. */
 		result = tcp_mtu_probe(sk);
@@ -2248,7 +2251,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	}
 
 	max_segs = tcp_tso_segs(sk, mss_now);
-	tcp_mstamp_refresh(tp);
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
@@ -2841,8 +2843,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
-		if (!err)
+		if (!err) {
 			skb->skb_mstamp = tp->tcp_mstamp;
+			tcp_rate_skb_sent(sk, skb);
+		}
 	} else {
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}