tcp: reset reordering est. selectively on timeout

On timeout the TCP sender unconditionally resets the estimated degree
of network reordering (tp->reordering). The idea behind this is that
the estimate is too large to trigger fast recovery (e.g., due to a IP
path change).

But for example if the sender only had 2 packets outstanding, then a
timeout doesn't tell much about reordering. A sender that learns about
reordering on big writes and loses packets on small writes will end up
falsely retransmitting again and again, especially when reordering is
more likely on big writes.

Therefore the sender should only suspect that tp->reordering is too
high if it could have gone into fast recovery with the (lower) default
estimate.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 7 insertions, 2 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b61274b666f6..e965cc7b87ff 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1877,8 +1877,13 @@ void tcp_enter_loss(struct sock *sk, int how)
 	}
 	tcp_verify_left_out(tp);
 
-	tp->reordering = min_t(unsigned int, tp->reordering,
-			       sysctl_tcp_reordering);
+	/* Timeout in disordered state after receiving substantial DUPACKs
+	 * suggests that the degree of reordering is over-estimated.
+	 */
+	if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
+	    tp->sacked_out >= sysctl_tcp_reordering)
+		tp->reordering = min_t(unsigned int, tp->reordering,
+				       sysctl_tcp_reordering);
 	tcp_set_ca_state(sk, TCP_CA_Loss);
 	tp->high_seq = tp->snd_nxt;
 	TCP_ECN_queue_cwr(tp);