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

Pull networking fixes from David Miller:

 1) Handle stations tied to AP_VLANs properly during mac80211 hw
    reconfig. From Manikanta Pubbisetty.

 2) Fix jump stack depth validation in nf_tables, from Taehee Yoo.

 3) Fix quota handling in aRFS flow expiration of mlx5 driver, from Eran
    Ben Elisha.

 4) Exit path handling fix in powerpc64 BPF JIT, from Daniel Borkmann.

 5) Use ptr_ring_consume_bh() in page pool code, from Tariq Toukan.

 6) Fix cached netdev name leak in nf_tables, from Florian Westphal.

 7) Fix memory leaks on chain rename, also from Florian Westphal.

 8) Several fixes to DCTCP congestion control ACK handling, from Yuchunk
    Cheng.

 9) Missing rcu_read_unlock() in CAIF protocol code, from Yue Haibing.

10) Fix link local address handling with VRF, from David Ahern.

11) Don't clobber 'err' on a successful call to __skb_linearize() in
    skb_segment(). From Eric Dumazet.

12) Fix vxlan fdb notification races, from Roopa Prabhu.

13) Hash UDP fragments consistently, from Paolo Abeni.

14) If TCP receives lots of out of order tiny packets, we do really
    silly stuff. Make the out-of-order queue ending more robust to this
    kind of behavior, from Eric Dumazet.

15) Don't leak netlink dump state in nf_tables, from Florian Westphal.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (76 commits)
  net: axienet: Fix double deregister of mdio
  qmi_wwan: fix interface number for DW5821e production firmware
  ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull
  bnx2x: Fix invalid memory access in rss hash config path.
  net/mlx4_core: Save the qpn from the input modifier in RST2INIT wrapper
  r8169: restore previous behavior to accept BIOS WoL settings
  cfg80211: never ignore user regulatory hint
  sock: fix sg page frag coalescing in sk_alloc_sg
  netfilter: nf_tables: move dumper state allocation into ->start
  tcp: add tcp_ooo_try_coalesce() helper
  tcp: call tcp_drop() from tcp_data_queue_ofo()
  tcp: detect malicious patterns in tcp_collapse_ofo_queue()
  tcp: avoid collapses in tcp_prune_queue() if possible
  tcp: free batches of packets in tcp_prune_ofo_queue()
  ip: hash fragments consistently
  ipv6: use fib6_info_hold_safe() when necessary
  can: xilinx_can: fix power management handling
  can: xilinx_can: fix incorrect clear of non-processed interrupts
  can: xilinx_can: fix RX overflow interrupt not being enabled
  can: xilinx_can: keep only 1-2 frames in TX FIFO to fix TX accounting
  ...

1 files changed, 24 insertions, 8 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 00e5a300ddb9..c4172c1fb198 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 }
 
 /* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+				      u32 rcv_nxt)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
 		if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
 			__sock_put(sk);
 	}
+
+	if (unlikely(rcv_nxt != tp->rcv_nxt))
+		return;  /* Special ACK sent by DCTCP to reflect ECN */
 	tcp_dec_quickack_mode(sk, pkts);
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }
@@ -1023,8 +1027,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
  * We are working here with either a clone of the original
  * SKB, or a fresh unique copy made by the retransmit engine.
  */
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
-			    gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+			      int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet;
@@ -1100,7 +1104,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	th->source		= inet->inet_sport;
 	th->dest		= inet->inet_dport;
 	th->seq			= htonl(tcb->seq);
-	th->ack_seq		= htonl(tp->rcv_nxt);
+	th->ack_seq		= htonl(rcv_nxt);
 	*(((__be16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
 					tcb->tcp_flags);
 
@@ -1141,7 +1145,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	icsk->icsk_af_ops->send_check(sk, skb);
 
 	if (likely(tcb->tcp_flags & TCPHDR_ACK))
-		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+		tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
 
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
@@ -1178,6 +1182,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	return err;
 }
 
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+			    gfp_t gfp_mask)
+{
+	return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+				  tcp_sk(sk)->rcv_nxt);
+}
+
 /* This routine just queues the buffer for sending.
  *
  * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
@@ -3571,7 +3582,7 @@ void tcp_send_delayed_ack(struct sock *sk)
 }
 
 /* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 {
 	struct sk_buff *buff;
 
@@ -3604,9 +3615,14 @@ void tcp_send_ack(struct sock *sk)
 	skb_set_tcp_pure_ack(buff);
 
 	/* Send it off, this clears delayed acks for us. */
-	tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+	__tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
+
+void tcp_send_ack(struct sock *sk)
+{
+	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
 }
-EXPORT_SYMBOL_GPL(tcp_send_ack);
 
 /* This routine sends a packet with an out of date sequence
  * number. It assumes the other end will try to ack it.