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

Pull networking fixes from David Miller:
 "I'm sending this out, in particular, to get the iwlwifi fix
  propagated:

   1) Fix build due to missing include in i40e driver, from Lucas
      Tanure.

   2) Memory leak in openvswitch port allocation, from Chirstoph Jaeger.

   3) Check DMA mapping errors in myri10ge, from Stanislaw Gruszka.

   4) Fix various deadlock scenerios in sunvnet driver, from Sowmini
      Varadhan.

   5) Fix cxgb4i build failures with incompatible Kconfig settings of
      the driver vs ipv6, from Anish Bhatt.

   6) Fix generation of ACK packet timestamps in the presence of TSO
      which will be split up, from Willem de Bruijn.

   7) Don't enable sched scan in iwlwifi driver, it causes firmware
      crashes in some revisions.  From Emmanuel Grumbach.

   8) Revert a macvlan simplification that causes crashes.

   9) Handle RTT calculations properly in the presence of repair'd SKBs,
      from Andrey Vagin.

  10) SIT tunnel lookup uses wrong device index in compares, from
      Shmulik Ladkani.

  11) Handle MTU reductions in TCP properly for ipv4 mapped ipv6
      sockets, from Neal Cardwell.

  12) Add missing annotations in rhashtable code, from Thomas Graf.

  13) Fix false interpretation of two RTOs as being from the same TCP
      loss event in the FRTO code, from Neal Cardwell"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (42 commits)
  netlink: Annotate RCU locking for seq_file walker
  rhashtable: fix annotations for rht_for_each_entry_rcu()
  rhashtable: unexport and make rht_obj() static
  rhashtable: RCU annotations for next pointers
  tcp: fix ssthresh and undo for consecutive short FRTO episodes
  tcp: don't allow syn packets without timestamps to pass tcp_tw_recycle logic
  tcp: fix tcp_release_cb() to dispatch via address family for mtu_reduced()
  sit: Fix ipip6_tunnel_lookup device matching criteria
  net: ethernet: ibm: ehea: Remove duplicate object from Makefile
  net: xgene: Check negative return value of xgene_enet_get_ring_size()
  tcp: don't use timestamp from repaired skb-s to calculate RTT (v2)
  net: xilinx: Remove .owner field for driver
  Revert "macvlan: simplify the structure port"
  iwlwifi: mvm: disable scheduled scan to prevent firmware crash
  xen-netback: remove loop waiting function
  xen-netback: don't stop dealloc kthread too early
  xen-netback: move NAPI add/remove calls
  xen-netback: fix debugfs entry creation
  xen-netback: fix debugfs write length check
  net-timestamp: fix missing tcp fragmentation cases
  ...

1 files changed, 14 insertions, 13 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a3d47af01906..a906e0200ff2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2687,7 +2687,6 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
  */
 static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
 {
-	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
@@ -2713,12 +2712,9 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
 
 	if (recovered) {
 		/* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */
-		icsk->icsk_retransmits = 0;
 		tcp_try_undo_recovery(sk);
 		return;
 	}
-	if (flag & FLAG_DATA_ACKED)
-		icsk->icsk_retransmits = 0;
 	if (tcp_is_reno(tp)) {
 		/* A Reno DUPACK means new data in F-RTO step 2.b above are
 		 * delivered. Lower inflight to clock out (re)tranmissions.
@@ -3050,10 +3046,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 	first_ackt.v64 = 0;
 
 	while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
+		struct skb_shared_info *shinfo = skb_shinfo(skb);
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
 		u8 sacked = scb->sacked;
 		u32 acked_pcount;
 
+		if (unlikely(shinfo->tx_flags & SKBTX_ACK_TSTAMP) &&
+		    between(shinfo->tskey, prior_snd_una, tp->snd_una - 1))
+			__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+
 		/* Determine how many packets and what bytes were acked, tso and else */
 		if (after(scb->end_seq, tp->snd_una)) {
 			if (tcp_skb_pcount(skb) == 1 ||
@@ -3107,11 +3108,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			tp->retrans_stamp = 0;
 		}
 
-		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_ACK_TSTAMP) &&
-		    between(skb_shinfo(skb)->tskey, prior_snd_una,
-			    tp->snd_una + 1))
-			__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
-
 		if (!fully_acked)
 			break;
 
@@ -3405,8 +3401,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
 
-	if (after(ack, prior_snd_una))
+	if (after(ack, prior_snd_una)) {
 		flag |= FLAG_SND_UNA_ADVANCED;
+		icsk->icsk_retransmits = 0;
+	}
 
 	prior_fackets = tp->fackets_out;
 
@@ -5979,12 +5977,14 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		 * timewait bucket, so that all the necessary checks
 		 * are made in the function processing timewait state.
 		 */
-		if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle) {
+		if (tcp_death_row.sysctl_tw_recycle) {
 			bool strict;
 
 			dst = af_ops->route_req(sk, &fl, req, &strict);
+
 			if (dst && strict &&
-			    !tcp_peer_is_proven(req, dst, true)) {
+			    !tcp_peer_is_proven(req, dst, true,
+						tmp_opt.saw_tstamp)) {
 				NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
 				goto drop_and_release;
 			}
@@ -5993,7 +5993,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		else if (!sysctl_tcp_syncookies &&
 			 (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
 			  (sysctl_max_syn_backlog >> 2)) &&
-			 !tcp_peer_is_proven(req, dst, false)) {
+			 !tcp_peer_is_proven(req, dst, false,
+					     tmp_opt.saw_tstamp)) {
 			/* Without syncookies last quarter of
 			 * backlog is filled with destinations,
 			 * proven to be alive.