Commit f698204b authored Nov 16, 2011 by Neal Cardwell Committed by David S. Miller Nov 27, 2011

tcp: allow undo from reordered DSACKs



Previously, SACK-enabled connections hung around in TCP_CA_Disorder
state while snd_una==high_seq, just waiting to accumulate DSACKs and
hopefully undo a cwnd reduction. This could and did lead to the
following unfortunate scenario: if some incoming ACKs advance snd_una
beyond high_seq then we were setting undo_marker to 0 and moving to
TCP_CA_Open, so if (due to reordering in the ACK return path) we
shortly thereafter received a DSACK then we were no longer able to
undo the cwnd reduction.

The change: Simplify the congestion avoidance state machine by
removing the behavior where SACK-enabled connections hung around in
the TCP_CA_Disorder state just waiting for DSACKs. Instead, when
snd_una advances to high_seq or beyond we typically move to
TCP_CA_Open immediately and allow an undo in either TCP_CA_Open or
TCP_CA_Disorder if we later receive enough DSACKs.

Other patches in this series will provide other changes that are
necessary to fully fix this problem.

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

parent e95ae2f2

net/ipv4/tcp_input.c

+2 −13

Original line number	Diff line number	Diff line
		@@ -2858,7 +2858,7 @@ static void tcp_try_keep_open(struct sock *sk)
		struct tcp_sock *tp = tcp_sk(sk);
		int state = TCP_CA_Open;

		if (tcp_left_out(tp) \|\| tcp_any_retrans_done(sk) \|\| tp->undo_marker)
		if (tcp_left_out(tp) \|\| tcp_any_retrans_done(sk))
		state = TCP_CA_Disorder;

		if (inet_csk(sk)->icsk_ca_state != state) {
		@@ -3066,17 +3066,6 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
		}
		break;

		case TCP_CA_Disorder:
		tcp_try_undo_dsack(sk);
		if (!tp->undo_marker \|\|
		/* For SACK case do not Open to allow to undo
		* catching for all duplicate ACKs. */
		tcp_is_reno(tp) \|\| tp->snd_una != tp->high_seq) {
		tp->undo_marker = 0;
		tcp_set_ca_state(sk, TCP_CA_Open);
		}
		break;

		case TCP_CA_Recovery:
		if (tcp_is_reno(tp))
		tcp_reset_reno_sack(tp);
		@@ -3117,7 +3106,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
		tcp_add_reno_sack(sk);
		}

		if (icsk->icsk_ca_state == TCP_CA_Disorder)
		if (icsk->icsk_ca_state <= TCP_CA_Disorder)
		tcp_try_undo_dsack(sk);

		if (!tcp_time_to_recover(sk)) {

Admin message