tcp: avoid reducing cwnd when ACK+DSACK is received

With TLP, the peer may reply to a probe with an
ACK+D-SACK, with ack value set to tlp_high_seq. In the current code,
such ACK+DSACK will be missed and only at next, higher ack will the TLP
episode be considered done. Since the DSACK is not present anymore,
this will cost a cwnd reduction.

This patch ensures that this scenario does not cause a cwnd reduction, since
receiving an ACK+DSACK indicates that both the initial segment and the probe
have been received by the peer.

The following packetdrill test, from Neal Cardwell, validates this patch:

// Establish a connection.
0     socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0     setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0    bind(3, ..., ...) = 0
+0    listen(3, 1) = 0

+0    < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+0    > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 6>
+.020 < . 1:1(0) ack 1 win 257
+0    accept(3, ..., ...) = 4

// Send 1 packet.
+0    write(4, ..., 1000) = 1000
+0    > P. 1:1001(1000) ack 1

// Loss probe retransmission.
// packets_out == 1 => schedule PTO in max(2*RTT, 1.5*RTT + 200ms)
// In this case, this means: 1.5*RTT + 200ms = 230ms
+.230 > P. 1:1001(1000) ack 1
+0    %{ assert tcpi_snd_cwnd == 10 }%

// Receiver ACKs at tlp_high_seq with a DSACK,
// indicating they received the original packet and probe.
+.020 < . 1:1(0) ack 1001 win 257 <sack 1:1001,nop,nop>
+0    %{ assert tcpi_snd_cwnd == 10 }%

// Send another packet.
+0    write(4, ..., 1000) = 1000
+0    > P. 1001:2001(1000) ack 1

// Receiver ACKs above tlp_high_seq, which should end the TLP episode
// if we haven't already. We should not reduce cwnd.
+.020 < . 1:1(0) ack 2001 win 257
+0    %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%

Credits:
-Gregory helped in finding that tcp_process_tlp_ack was where the cwnd
got reduced in our MPTCP tests.
-Neal wrote the packetdrill test above
-Yuchung reworked the patch to make it more readable.

Cc: Gregory Detal <gregory.detal@uclouvain.be>
Cc: Nandita Dukkipati <nanditad@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Sébastien Barré <sebastien.barre@uclouvain.be>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/tcp_input.c

@@ -3358,34 +3358,34 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
 }
 
 /* This routine deals with acks during a TLP episode.
+ * We mark the end of a TLP episode on receiving TLP dupack or when
+ * ack is after tlp_high_seq.
  * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
  */
 static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	bool is_tlp_dupack = (ack == tp->tlp_high_seq) &&
-			     !(flag & (FLAG_SND_UNA_ADVANCED |
-				       FLAG_NOT_DUP | FLAG_DATA_SACKED));
 
-	/* Mark the end of TLP episode on receiving TLP dupack or when
-	 * ack is after tlp_high_seq.
-	 */
-	if (is_tlp_dupack) {
-		tp->tlp_high_seq = 0;
+	if (before(ack, tp->tlp_high_seq))
 		return;
-	}
 
-	if (after(ack, tp->tlp_high_seq)) {
+	if (flag & FLAG_DSACKING_ACK) {
+		/* This DSACK means original and TLP probe arrived; no loss */
+		tp->tlp_high_seq = 0;
+	} else if (after(ack, tp->tlp_high_seq)) {
+		/* ACK advances: there was a loss, so reduce cwnd. Reset
+		 * tlp_high_seq in tcp_init_cwnd_reduction()
+		 */
+		tcp_init_cwnd_reduction(sk);
+		tcp_set_ca_state(sk, TCP_CA_CWR);
+		tcp_end_cwnd_reduction(sk);
+		tcp_try_keep_open(sk);
+		NET_INC_STATS_BH(sock_net(sk),
+				 LINUX_MIB_TCPLOSSPROBERECOVERY);
+	} else if (!(flag & (FLAG_SND_UNA_ADVANCED |
+			     FLAG_NOT_DUP | FLAG_DATA_SACKED))) {
+		/* Pure dupack: original and TLP probe arrived; no loss */
 		tp->tlp_high_seq = 0;
-		/* Don't reduce cwnd if DSACK arrives for TLP retrans. */
-		if (!(flag & FLAG_DSACKING_ACK)) {
-			tcp_init_cwnd_reduction(sk);
-			tcp_set_ca_state(sk, TCP_CA_CWR);
-			tcp_end_cwnd_reduction(sk);
-			tcp_try_keep_open(sk);
-			NET_INC_STATS_BH(sock_net(sk),
-					 LINUX_MIB_TCPLOSSPROBERECOVERY);
-		}
 	}
 }