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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 37 insertions, 21 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 45f750e..cfa51cf 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -97,6 +97,7 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 #define FLAG_SACK_RENEGING	0x2000 /* snd_una advanced to a sacked seq */
 #define FLAG_UPDATE_TS_RECENT	0x4000 /* tcp_replace_ts_recent() */
 #define FLAG_NO_CHALLENGE_ACK	0x8000 /* do not call tcp_send_challenge_ack()	*/
+#define FLAG_ACK_MAYBE_DELAYED	0x10000 /* Likely a delayed ACK */
 
 #define FLAG_ACKED		(FLAG_DATA_ACKED|FLAG_SYN_ACKED)
 #define FLAG_NOT_DUP		(FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
@@ -578,8 +579,8 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 void tcp_rcv_space_adjust(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	u32 copied;
 	int time;
-	int copied;
 
 	tcp_mstamp_refresh(tp);
 	time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
@@ -602,38 +603,31 @@ void tcp_rcv_space_adjust(struct sock *sk)
 
 	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
-		int rcvwin, rcvmem, rcvbuf;
+		int rcvmem, rcvbuf;
+		u64 rcvwin, grow;
 
 		/* minimal window to cope with packet losses, assuming
 		 * steady state. Add some cushion because of small variations.
 		 */
-		rcvwin = (copied << 1) + 16 * tp->advmss;
+		rcvwin = ((u64)copied << 1) + 16 * tp->advmss;
 
-		/* If rate increased by 25%,
-		 *	assume slow start, rcvwin = 3 * copied
-		 * If rate increased by 50%,
-		 *	assume sender can use 2x growth, rcvwin = 4 * copied
-		 */
-		if (copied >=
-		    tp->rcvq_space.space + (tp->rcvq_space.space >> 2)) {
-			if (copied >=
-			    tp->rcvq_space.space + (tp->rcvq_space.space >> 1))
-				rcvwin <<= 1;
-			else
-				rcvwin += (rcvwin >> 1);
-		}
+		/* Accommodate for sender rate increase (eg. slow start) */
+		grow = rcvwin * (copied - tp->rcvq_space.space);
+		do_div(grow, tp->rcvq_space.space);
+		rcvwin += (grow << 1);
 
 		rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
 		while (tcp_win_from_space(sk, rcvmem) < tp->advmss)
 			rcvmem += 128;
 
-		rcvbuf = min(rcvwin / tp->advmss * rcvmem,
-			     sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+		do_div(rcvwin, tp->advmss);
+		rcvbuf = min_t(u64, rcvwin * rcvmem,
+			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 		if (rcvbuf > sk->sk_rcvbuf) {
 			sk->sk_rcvbuf = rcvbuf;
 
 			/* Make the window clamp follow along.  */
-			tp->window_clamp = rcvwin;
+			tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
 		}
 	}
 	tp->rcvq_space.space = copied;
@@ -2864,11 +2858,18 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 	*rexmit = REXMIT_LOST;
 }
 
-static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
+static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
 {
 	u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
+		/* If the remote keeps returning delayed ACKs, eventually
+		 * the min filter would pick it up and overestimate the
+		 * prop. delay when it expires. Skip suspected delayed ACKs.
+		 */
+		return;
+	}
 	minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32,
 			   rtt_us ? : jiffies_to_usecs(1));
 }
@@ -2908,7 +2909,7 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	 * always taken together with ACK, SACK, or TS-opts. Any negative
 	 * values will be skipped with the seq_rtt_us < 0 check above.
 	 */
-	tcp_update_rtt_min(sk, ca_rtt_us);
+	tcp_update_rtt_min(sk, ca_rtt_us, flag);
 	tcp_rtt_estimator(sk, seq_rtt_us);
 	tcp_set_rto(sk);
 
@@ -3132,6 +3133,17 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 	if (likely(first_ackt) && !(flag & FLAG_RETRANS_DATA_ACKED)) {
 		seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt);
 		ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, last_ackt);
+
+		if (pkts_acked == 1 && last_in_flight < tp->mss_cache &&
+		    last_in_flight && !prior_sacked && fully_acked &&
+		    sack->rate->prior_delivered + 1 == tp->delivered &&
+		    !(flag & (FLAG_CA_ALERT | FLAG_SYN_ACKED))) {
+			/* Conservatively mark a delayed ACK. It's typically
+			 * from a lone runt packet over the round trip to
+			 * a receiver w/o out-of-order or CE events.
+			 */
+			flag |= FLAG_ACK_MAYBE_DELAYED;
+		}
 	}
 	if (sack->first_sackt) {
 		sack_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->first_sackt);
@@ -3621,6 +3633,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	delivered = tp->delivered - delivered;	/* freshly ACKed or SACKed */
 	lost = tp->lost - lost;			/* freshly marked lost */
+	rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED);
 	tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
 	tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
 	tcp_xmit_recovery(sk, rexmit);
@@ -5306,6 +5319,9 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 	unsigned int len = skb->len;
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	/* TCP congestion window tracking */
+	trace_tcp_probe(sk, skb);
+
 	tcp_mstamp_refresh(tp);
 	if (unlikely(!sk->sk_rx_dst))
 		inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);