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

Pull networking updates from David Miller:

 1) Add VF IPSEC offload support in ixgbe, from Shannon Nelson.

 2) Add zero-copy AF_XDP support to i40e, from Björn Töpel.

 3) All in-tree drivers are converted to {g,s}et_link_ksettings() so we
    can get rid of the {g,s}et_settings ethtool callbacks, from Michal
    Kubecek.

 4) Add software timestamping to veth driver, from Michael Walle.

 5) More work to make packet classifiers and actions lockless, from Vlad
    Buslov.

 6) Support sticky FDB entries in bridge, from Nikolay Aleksandrov.

 7) Add ipv6 version of IP_MULTICAST_ALL sockopt, from Andre Naujoks.

 8) Support batching of XDP buffers in vhost_net, from Jason Wang.

 9) Add flow dissector BPF hook, from Petar Penkov.

10) i40e vf --> generic iavf conversion, from Jesse Brandeburg.

11) Add NLA_REJECT netlink attribute policy type, to signal when users
    provide attributes in situations which don't make sense. From
    Johannes Berg.

12) Switch TCP and fair-queue scheduler over to earliest departure time
    model. From Eric Dumazet.

13) Improve guest receive performance by doing rx busy polling in tx
    path of vhost networking driver, from Tonghao Zhang.

14) Add per-cgroup local storage to bpf

15) Add reference tracking to BPF, from Joe Stringer. The verifier can
    now make sure that references taken to objects are properly released
    by the program.

16) Support in-place encryption in TLS, from Vakul Garg.

17) Add new taprio packet scheduler, from Vinicius Costa Gomes.

18) Lots of selftests additions, too numerous to mention one by one here
    but all of which are very much appreciated.

19) Support offloading of eBPF programs containing BPF to BPF calls in
    nfp driver, frm Quentin Monnet.

20) Move dpaa2_ptp driver out of staging, from Yangbo Lu.

21) Lots of u32 classifier cleanups and simplifications, from Al Viro.

22) Add new strict versions of netlink message parsers, and enable them
    for some situations. From David Ahern.

23) Evict neighbour entries on carrier down, also from David Ahern.

24) Support BPF sk_msg verdict programs with kTLS, from Daniel Borkmann
    and John Fastabend.

25) Add support for filtering route dumps, from David Ahern.

26) New igc Intel driver for 2.5G parts, from Sasha Neftin et al.

27) Allow vxlan enslavement to bridges in mlxsw driver, from Ido
    Schimmel.

28) Add queue and stack map types to eBPF, from Mauricio Vasquez B.

29) Add back byte-queue-limit support to r8169, with all the bug fixes
    in other areas of the driver it works now! From Florian Westphal and
    Heiner Kallweit.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2147 commits)
  tcp: add tcp_reset_xmit_timer() helper
  qed: Fix static checker warning
  Revert "be2net: remove desc field from be_eq_obj"
  Revert "net: simplify sock_poll_wait"
  net: socionext: Reset tx queue in ndo_stop
  net: socionext: Add dummy PHY register read in phy_write()
  net: socionext: Stop PHY before resetting netsec
  net: stmmac: Set OWN bit for jumbo frames
  arm64: dts: stratix10: Support Ethernet Jumbo frame
  tls: Add maintainers
  net: ethernet: ti: cpsw: unsync mcast entries while switch promisc mode
  octeontx2-af: Support for NIXLF's UCAST/PROMISC/ALLMULTI modes
  octeontx2-af: Support for setting MAC address
  octeontx2-af: Support for changing RSS algorithm
  octeontx2-af: NIX Rx flowkey configuration for RSS
  octeontx2-af: Install ucast and bcast pkt forwarding rules
  octeontx2-af: Add LMAC channel info to NIXLF_ALLOC response
  octeontx2-af: NPC MCAM and LDATA extract minimal configuration
  octeontx2-af: Enable packet length and csum validation
  octeontx2-af: Support for VTAG strip and capture
  ...

1 files changed, 26 insertions, 33 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 47e08c1b5bc3..2868ef28ce52 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -426,26 +426,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-/* 3. Tuning rcvbuf, when connection enters established state. */
-static void tcp_fixup_rcvbuf(struct sock *sk)
-{
-	u32 mss = tcp_sk(sk)->advmss;
-	int rcvmem;
-
-	rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER) *
-		 tcp_default_init_rwnd(mss);
-
-	/* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
-	 * Allow enough cushion so that sender is not limited by our window
-	 */
-	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)
-		rcvmem <<= 2;
-
-	if (sk->sk_rcvbuf < rcvmem)
-		sk->sk_rcvbuf = min(rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
-}
-
-/* 4. Try to fixup all. It is made immediately after connection enters
+/* 3. Try to fixup all. It is made immediately after connection enters
  *    established state.
  */
 void tcp_init_buffer_space(struct sock *sk)
@@ -454,12 +435,10 @@ void tcp_init_buffer_space(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	int maxwin;
 
-	if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK))
-		tcp_fixup_rcvbuf(sk);
 	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK))
 		tcp_sndbuf_expand(sk);
 
-	tp->rcvq_space.space = tp->rcv_wnd;
+	tp->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss);
 	tcp_mstamp_refresh(tp);
 	tp->rcvq_space.time = tp->tcp_mstamp;
 	tp->rcvq_space.seq = tp->copied_seq;
@@ -485,7 +464,7 @@ void tcp_init_buffer_space(struct sock *sk)
 	tp->snd_cwnd_stamp = tcp_jiffies32;
 }
 
-/* 5. Recalculate window clamp after socket hit its memory bounds. */
+/* 4. Recalculate window clamp after socket hit its memory bounds. */
 static void tcp_clamp_window(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -1305,7 +1284,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
 	 */
 	tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
 			start_seq, end_seq, dup_sack, pcount,
-			skb->skb_mstamp);
+			tcp_skb_timestamp_us(skb));
 	tcp_rate_skb_delivered(sk, skb, state->rate);
 
 	if (skb == tp->lost_skb_hint)
@@ -1580,7 +1559,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 						TCP_SKB_CB(skb)->end_seq,
 						dup_sack,
 						tcp_skb_pcount(skb),
-						skb->skb_mstamp);
+						tcp_skb_timestamp_us(skb));
 			tcp_rate_skb_delivered(sk, skb, state->rate);
 			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
 				list_del_init(&skb->tcp_tsorted_anchor);
@@ -3000,8 +2979,8 @@ void tcp_rearm_rto(struct sock *sk)
 			 */
 			rto = usecs_to_jiffies(max_t(int, delta_us, 1));
 		}
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
-					  TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
+				     TCP_RTO_MAX, tcp_rtx_queue_head(sk));
 	}
 }
 
@@ -3103,7 +3082,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 				tp->retrans_out -= acked_pcount;
 			flag |= FLAG_RETRANS_DATA_ACKED;
 		} else if (!(sacked & TCPCB_SACKED_ACKED)) {
-			last_ackt = skb->skb_mstamp;
+			last_ackt = tcp_skb_timestamp_us(skb);
 			WARN_ON_ONCE(last_ackt == 0);
 			if (!first_ackt)
 				first_ackt = last_ackt;
@@ -3121,7 +3100,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 			tp->delivered += acked_pcount;
 			if (!tcp_skb_spurious_retrans(tp, skb))
 				tcp_rack_advance(tp, sacked, scb->end_seq,
-						 skb->skb_mstamp);
+						 tcp_skb_timestamp_us(skb));
 		}
 		if (sacked & TCPCB_LOST)
 			tp->lost_out -= acked_pcount;
@@ -3215,7 +3194,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 			tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
 		}
 	} else if (skb && rtt_update && sack_rtt_us >= 0 &&
-		   sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) {
+		   sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp,
+						    tcp_skb_timestamp_us(skb))) {
 		/* Do not re-arm RTO if the sack RTT is measured from data sent
 		 * after when the head was last (re)transmitted. Otherwise the
 		 * timeout may continue to extend in loss recovery.
@@ -3275,8 +3255,8 @@ static void tcp_ack_probe(struct sock *sk)
 	} else {
 		unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
 
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-					  when, TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
+				     when, TCP_RTO_MAX, NULL);
 	}
 }
 
@@ -4199,6 +4179,17 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq)
 		tcp_sack_extend(tp->duplicate_sack, seq, end_seq);
 }
 
+static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb)
+{
+	/* When the ACK path fails or drops most ACKs, the sender would
+	 * timeout and spuriously retransmit the same segment repeatedly.
+	 * The receiver remembers and reflects via DSACKs. Leverage the
+	 * DSACK state and change the txhash to re-route speculatively.
+	 */
+	if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq)
+		sk_rethink_txhash(sk);
+}
+
 static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -4211,6 +4202,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
 		if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
 			u32 end_seq = TCP_SKB_CB(skb)->end_seq;
 
+			tcp_rcv_spurious_retrans(sk, skb);
 			if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
 				end_seq = tp->rcv_nxt;
 			tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, end_seq);
@@ -4755,6 +4747,7 @@ queue_and_out:
 	}
 
 	if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
+		tcp_rcv_spurious_retrans(sk, skb);
 		/* A retransmit, 2nd most common case.  Force an immediate ack. */
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
 		tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);