tcp: reset timer after any SYNACK retransmit

[ Upstream commit cd75eff64dae8856afbf6ef0f0ca3c145465d8e0 ]

Linux immediately returns SYNACK on (spurious) SYN retransmits, but
keeps the SYNACK timer running independently. Thus the timer may
fire right after the SYNACK retransmit and causes a SYN-SYNACK
cross-fire burst.

Adopt the fast retransmit/recovery idea in established state by
re-arming the SYNACK timer after the fast (SYNACK) retransmit. The
timer may fire late up to 500ms due to the current SYNACK timer wheel,
but it's OK to be conservative when network is congested. Eric's new
listener design should address this issue.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b83a49cc38169a654a14b94581f72eae09466c52..2f672e7ab6eb86679c8f6623e555093f7ab84b48 100644 (file)
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -583,8 +583,13 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
                 *
                 * Note that even if there is new data in the SYN packet
                 * they will be thrown away too.
+                *
+                * Reset timer after retransmitting SYNACK, similar to
+                * the idea of fast retransmit in recovery.
                 */
-               inet_rtx_syn_ack(sk, req);
+               if (!inet_rtx_syn_ack(sk, req))
+                       req->expires = min(TCP_TIMEOUT_INIT << req->num_timeout,
+                                          TCP_RTO_MAX) + jiffies;
                return NULL;
        }