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

Pull networking updates from David Miller:
 "Highlights:

   1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.

   2) Add fib_sync_mem to control the amount of dirty memory we allow to
      queue up between synchronize RCU calls, from David Ahern.

   3) Make flow classifier more lockless, from Vlad Buslov.

   4) Add PHY downshift support to aquantia driver, from Heiner
      Kallweit.

   5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
      contention on SLAB spinlocks in heavy RPC workloads.

   6) Partial GSO offload support in XFRM, from Boris Pismenny.

   7) Add fast link down support to ethtool, from Heiner Kallweit.

   8) Use siphash for IP ID generator, from Eric Dumazet.

   9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
      entries, from David Ahern.

  10) Move skb->xmit_more into a per-cpu variable, from Florian
      Westphal.

  11) Improve eBPF verifier speed and increase maximum program size,
      from Alexei Starovoitov.

  12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
      spinlocks. From Neil Brown.

  13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.

  14) Improve link partner cap detection in generic PHY code, from
      Heiner Kallweit.

  15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
      Maguire.

  16) Remove SKB list implementation assumptions in SCTP, your's truly.

  17) Various cleanups, optimizations, and simplifications in r8169
      driver. From Heiner Kallweit.

  18) Add memory accounting on TX and RX path of SCTP, from Xin Long.

  19) Switch PHY drivers over to use dynamic featue detection, from
      Heiner Kallweit.

  20) Support flow steering without masking in dpaa2-eth, from Ioana
      Ciocoi.

  21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
      Pirko.

  22) Increase the strict parsing of current and future netlink
      attributes, also export such policies to userspace. From Johannes
      Berg.

  23) Allow DSA tag drivers to be modular, from Andrew Lunn.

  24) Remove legacy DSA probing support, also from Andrew Lunn.

  25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
      Haabendal.

  26) Add a generic tracepoint for TX queue timeouts to ease debugging,
      from Cong Wang.

  27) More indirect call optimizations, from Paolo Abeni"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
  cxgb4: Fix error path in cxgb4_init_module
  net: phy: improve pause mode reporting in phy_print_status
  dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
  net: macb: Change interrupt and napi enable order in open
  net: ll_temac: Improve error message on error IRQ
  net/sched: remove block pointer from common offload structure
  net: ethernet: support of_get_mac_address new ERR_PTR error
  net: usb: smsc: fix warning reported by kbuild test robot
  staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
  net: dsa: support of_get_mac_address new ERR_PTR error
  net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
  vrf: sit mtu should not be updated when vrf netdev is the link
  net: dsa: Fix error cleanup path in dsa_init_module
  l2tp: Fix possible NULL pointer dereference
  taprio: add null check on sched_nest to avoid potential null pointer dereference
  net: mvpp2: cls: fix less than zero check on a u32 variable
  net_sched: sch_fq: handle non connected flows
  net_sched: sch_fq: do not assume EDT packets are ordered
  net: hns3: use devm_kcalloc when allocating desc_cb
  net: hns3: some cleanup for struct hns3_enet_ring
  ...

1 files changed, 80 insertions, 31 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 731d3045b50a..077d9abdfcf5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2252,7 +2252,7 @@ static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp,
  */
 static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
 {
-	return !tp->retrans_stamp ||
+	return tp->retrans_stamp &&
 	       tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
 }
 
@@ -3521,7 +3521,7 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (rexmit == REXMIT_NONE)
+	if (rexmit == REXMIT_NONE || sk->sk_state == TCP_SYN_SENT)
 		return;
 
 	if (unlikely(rexmit == 2)) {
@@ -5647,6 +5647,32 @@ discard:
 }
 EXPORT_SYMBOL(tcp_rcv_established);
 
+void tcp_init_transfer(struct sock *sk, int bpf_op)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	tcp_mtup_init(sk);
+	icsk->icsk_af_ops->rebuild_header(sk);
+	tcp_init_metrics(sk);
+
+	/* Initialize the congestion window to start the transfer.
+	 * Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
+	 * retransmitted. In light of RFC6298 more aggressive 1sec
+	 * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK
+	 * retransmission has occurred.
+	 */
+	if (tp->total_retrans > 1 && tp->undo_marker)
+		tp->snd_cwnd = 1;
+	else
+		tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
+	tp->snd_cwnd_stamp = tcp_jiffies32;
+
+	tcp_call_bpf(sk, bpf_op, 0, NULL);
+	tcp_init_congestion_control(sk);
+	tcp_init_buffer_space(sk);
+}
+
 void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -5748,6 +5774,21 @@ static void smc_check_reset_syn(struct tcp_sock *tp)
 #endif
 }
 
+static void tcp_try_undo_spurious_syn(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 syn_stamp;
+
+	/* undo_marker is set when SYN or SYNACK times out. The timeout is
+	 * spurious if the ACK's timestamp option echo value matches the
+	 * original SYN timestamp.
+	 */
+	syn_stamp = tp->retrans_stamp;
+	if (tp->undo_marker && syn_stamp && tp->rx_opt.saw_tstamp &&
+	    syn_stamp == tp->rx_opt.rcv_tsecr)
+		tp->undo_marker = 0;
+}
+
 static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 					 const struct tcphdr *th)
 {
@@ -5815,6 +5856,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		tcp_ecn_rcv_synack(tp, th);
 
 		tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
+		tcp_try_undo_spurious_syn(sk);
 		tcp_ack(sk, skb, FLAG_SLOWPATH);
 
 		/* Ok.. it's good. Set up sequence numbers and
@@ -5973,6 +6015,27 @@ reset_and_undo:
 	return 1;
 }
 
+static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
+{
+	tcp_try_undo_loss(sk, false);
+	inet_csk(sk)->icsk_retransmits = 0;
+
+	/* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1,
+	 * we no longer need req so release it.
+	 */
+	reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false);
+
+	/* Re-arm the timer because data may have been sent out.
+	 * This is similar to the regular data transmission case
+	 * when new data has just been ack'ed.
+	 *
+	 * (TFO) - we could try to be more aggressive and
+	 * retransmitting any data sooner based on when they
+	 * are sent out.
+	 */
+	tcp_rearm_rto(sk);
+}
+
 /*
  *	This function implements the receiving procedure of RFC 793 for
  *	all states except ESTABLISHED and TIME_WAIT.
@@ -6069,22 +6132,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (!tp->srtt_us)
 			tcp_synack_rtt_meas(sk, req);
 
-		/* Once we leave TCP_SYN_RECV, we no longer need req
-		 * so release it.
-		 */
 		if (req) {
-			inet_csk(sk)->icsk_retransmits = 0;
-			reqsk_fastopen_remove(sk, req, false);
-			/* Re-arm the timer because data may have been sent out.
-			 * This is similar to the regular data transmission case
-			 * when new data has just been ack'ed.
-			 *
-			 * (TFO) - we could try to be more aggressive and
-			 * retransmitting any data sooner based on when they
-			 * are sent out.
-			 */
-			tcp_rearm_rto(sk);
+			tcp_rcv_synrecv_state_fastopen(sk);
 		} else {
+			tcp_try_undo_spurious_syn(sk);
+			tp->retrans_stamp = 0;
 			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
 			tp->copied_seq = tp->rcv_nxt;
 		}
@@ -6119,16 +6171,9 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	case TCP_FIN_WAIT1: {
 		int tmo;
 
-		/* If we enter the TCP_FIN_WAIT1 state and we are a
-		 * Fast Open socket and this is the first acceptable
-		 * ACK we have received, this would have acknowledged
-		 * our SYNACK so stop the SYNACK timer.
-		 */
-		if (req) {
-			/* We no longer need the request sock. */
-			reqsk_fastopen_remove(sk, req, false);
-			tcp_rearm_rto(sk);
-		}
+		if (req)
+			tcp_rcv_synrecv_state_fastopen(sk);
+
 		if (tp->snd_una != tp->write_seq)
 			break;
 
@@ -6263,6 +6308,11 @@ static inline void pr_drop_req(struct request_sock *req, __u16 port, int family)
  * congestion control: Linux DCTCP asserts ECT on all packets,
  * including SYN, which is most optimal solution; however,
  * others, such as FreeBSD do not.
+ *
+ * Exception: At least one of the reserved bits of the TCP header (th->res1) is
+ * set, indicating the use of a future TCP extension (such as AccECN). See
+ * RFC8311 §4.3 which updates RFC3168 to allow the development of such
+ * extensions.
  */
 static void tcp_ecn_create_request(struct request_sock *req,
 				   const struct sk_buff *skb,
@@ -6282,7 +6332,7 @@ static void tcp_ecn_create_request(struct request_sock *req,
 	ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK);
 	ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst;
 
-	if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
+	if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
 	    (ecn_ok_dst & DST_FEATURE_ECN_CA) ||
 	    tcp_bpf_ca_needs_ecn((struct sock *)req))
 		inet_rsk(req)->ecn_ok = 1;
@@ -6298,7 +6348,7 @@ static void tcp_openreq_init(struct request_sock *req,
 	req->cookie_ts = 0;
 	tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
 	tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
-	tcp_rsk(req)->snt_synack = tcp_clock_us();
+	tcp_rsk(req)->snt_synack = 0;
 	tcp_rsk(req)->last_oow_ack_time = 0;
 	req->mss = rx_opt->mss_clamp;
 	req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
@@ -6502,8 +6552,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			reqsk_fastopen_remove(fastopen_sk, req, false);
 			bh_unlock_sock(fastopen_sk);
 			sock_put(fastopen_sk);
-			reqsk_put(req);
-			goto drop;
+			goto drop_and_free;
 		}
 		sk->sk_data_ready(sk);
 		bh_unlock_sock(fastopen_sk);
@@ -6527,7 +6576,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 drop_and_release:
 	dst_release(dst);
 drop_and_free:
-	reqsk_free(req);
+	__reqsk_free(req);
 drop:
 	tcp_listendrop(sk);
 	return 0;