netdev - [PATCH 4/4 net-next] tcp: undo on DSACK during recovery

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1369873214-29502-4-git-send-email-ycheng@google.com>
Date:	Wed, 29 May 2013 17:20:14 -0700
From:	Yuchung Cheng <ycheng@...gle.com>
To:	davem@...emloft.net, ncardwell@...gle.com, edumazet@...gle.com,
	nanditad@...gle.com
Cc:	aterzis@...gle.com, netdev@...r.kernel.org,
	Yuchung Cheng <ycheng@...gle.com>
Subject: [PATCH 4/4 net-next] 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: Yuchung Cheng <ycheng@...gle.com>
---
 net/ipv4/tcp_input.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c35b227..907311c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -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);
-- 
1.8.2.1

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html