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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 65 insertions, 37 deletions

diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index be8ef1e5dfef..d3ea89020c69 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -2,8 +2,6 @@
 #include <linux/tcp.h>
 #include <net/tcp.h>
 
-int sysctl_tcp_recovery __read_mostly = TCP_RACK_LOSS_DETECTION;
-
 static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -46,7 +44,8 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
 static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb;
+	u32 min_rtt = tcp_min_rtt(tp);
+	struct sk_buff *skb, *n;
 	u32 reo_wnd;
 
 	*reo_timeout = 0;
@@ -56,48 +55,36 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 	 * to queuing or delayed ACKs.
 	 */
 	reo_wnd = 1000;
-	if ((tp->rack.reord || !tp->lost_out) && tcp_min_rtt(tp) != ~0U)
-		reo_wnd = max(tcp_min_rtt(tp) >> 2, reo_wnd);
+	if ((tp->rack.reord || !tp->lost_out) && min_rtt != ~0U) {
+		reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd);
+		reo_wnd = min(reo_wnd, tp->srtt_us >> 3);
+	}
 
-	tcp_for_write_queue(skb, sk) {
+	list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue,
+				 tcp_tsorted_anchor) {
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+		s32 remaining;
 
-		if (skb == tcp_send_head(sk))
-			break;
-
-		/* Skip ones already (s)acked */
-		if (!after(scb->end_seq, tp->snd_una) ||
-		    scb->sacked & TCPCB_SACKED_ACKED)
+		/* Skip ones marked lost but not yet retransmitted */
+		if ((scb->sacked & TCPCB_LOST) &&
+		    !(scb->sacked & TCPCB_SACKED_RETRANS))
 			continue;
 
-		if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp,
-					tp->rack.end_seq, scb->end_seq)) {
-			/* Step 3 in draft-cheng-tcpm-rack-00.txt:
-			 * A packet is lost if its elapsed time is beyond
-			 * the recent RTT plus the reordering window.
-			 */
-			u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp,
-							 skb->skb_mstamp);
-			s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed;
-
-			if (remaining < 0) {
-				tcp_rack_mark_skb_lost(sk, skb);
-				continue;
-			}
-
-			/* Skip ones marked lost but not yet retransmitted */
-			if ((scb->sacked & TCPCB_LOST) &&
-			    !(scb->sacked & TCPCB_SACKED_RETRANS))
-				continue;
+		if (!tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp,
+					 tp->rack.end_seq, scb->end_seq))
+			break;
 
+		/* A packet is lost if it has not been s/acked beyond
+		 * the recent RTT plus the reordering window.
+		 */
+		remaining = tp->rack.rtt_us + reo_wnd -
+			    tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp);
+		if (remaining < 0) {
+			tcp_rack_mark_skb_lost(sk, skb);
+			list_del_init(&skb->tcp_tsorted_anchor);
+		} else {
 			/* Record maximum wait time (+1 to avoid 0) */
 			*reo_timeout = max_t(u32, *reo_timeout, 1 + remaining);
-
-		} else if (!(scb->sacked & TCPCB_RETRANS)) {
-			/* Original data are sent sequentially so stop early
-			 * b/c the rest are all sent after rack_sent
-			 */
-			break;
 		}
 	}
 }
@@ -176,3 +163,44 @@ void tcp_rack_reo_timeout(struct sock *sk)
 	if (inet_csk(sk)->icsk_pending != ICSK_TIME_RETRANS)
 		tcp_rearm_rto(sk);
 }
+
+/* Updates the RACK's reo_wnd based on DSACK and no. of recoveries.
+ *
+ * If DSACK is received, increment reo_wnd by min_rtt/4 (upper bounded
+ * by srtt), since there is possibility that spurious retransmission was
+ * due to reordering delay longer than reo_wnd.
+ *
+ * Persist the current reo_wnd value for TCP_RACK_RECOVERY_THRESH (16)
+ * no. of successful recoveries (accounts for full DSACK-based loss
+ * recovery undo). After that, reset it to default (min_rtt/4).
+ *
+ * At max, reo_wnd is incremented only once per rtt. So that the new
+ * DSACK on which we are reacting, is due to the spurious retx (approx)
+ * after the reo_wnd has been updated last time.
+ *
+ * reo_wnd is tracked in terms of steps (of min_rtt/4), rather than
+ * absolute value to account for change in rtt.
+ */
+void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND ||
+	    !rs->prior_delivered)
+		return;
+
+	/* Disregard DSACK if a rtt has not passed since we adjusted reo_wnd */
+	if (before(rs->prior_delivered, tp->rack.last_delivered))
+		tp->rack.dsack_seen = 0;
+
+	/* Adjust the reo_wnd if update is pending */
+	if (tp->rack.dsack_seen) {
+		tp->rack.reo_wnd_steps = min_t(u32, 0xFF,
+					       tp->rack.reo_wnd_steps + 1);
+		tp->rack.dsack_seen = 0;
+		tp->rack.last_delivered = tp->delivered;
+		tp->rack.reo_wnd_persist = TCP_RACK_RECOVERY_THRESH;
+	} else if (!tp->rack.reo_wnd_persist) {
+		tp->rack.reo_wnd_steps = 1;
+	}
+}