Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit c7d9d6a1 authored by Yuchung Cheng's avatar Yuchung Cheng Committed by David S. Miller
Browse files

tcp: undo on DSACK during recovery 



If the receiver supports DSACK, sender can detect false recoveries and
revert cwnd reductions triggered by either severe network reordering or
concurrent reordering and loss event.

Signed-off-by: default avatarYuchung Cheng <ycheng@google.com>
Acked-by: default avatarNeal Cardwell <ncardwell@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 7026b912

net/ipv4/tcp_input.c

+7 −1
Original line number Diff line number Diff line
@@ -2315,7 +2315,7 @@ static bool tcp_try_undo_recovery(struct sock *sk) 
}



/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */

static void tcp_try_undo_dsack(struct sock *sk)

static bool tcp_try_undo_dsack(struct sock *sk)

{

	struct tcp_sock *tp = tcp_sk(sk);
@@ -2323,7 +2323,9 @@ static void tcp_try_undo_dsack(struct sock *sk) 
		DBGUNDO(sk, "D-SACK");

		tcp_undo_cwnd_reduction(sk, false);

		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);

		return true;

	}

	return false;

}



/* We can clear retrans_stamp when there are no retransmissions in the
@@ -2751,6 +2753,10 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, 
			do_lost = tcp_is_reno(tp) ||

				  tcp_fackets_out(tp) > tp->reordering;

		}

		if (tcp_try_undo_dsack(sk)) {

			tcp_try_keep_open(sk);

			return;

		}

		break;

	case TCP_CA_Loss:

		tcp_process_loss(sk, flag, is_dupack);