tcp: pause Fast Open globally after third consecutive timeout

Prior to this patch, active Fast Open is paused on a specific
destination IP address if the previous connections to the
IP address have experienced recurring timeouts . But recent
experiments by Microsoft (https://goo.gl/cykmn7) and Mozilla
browsers indicate the isssue is often caused by broken middle-boxes
sitting close to the client. Therefore it is much better user
experience if Fast Open is disabled out-right globally to avoid
experiencing further timeouts on connections toward other
destinations.

This patch changes the destination-IP disablement to global
disablement if a connection experiencing recurring timeouts
or aborts due to timeout.  Repeated incidents would still
exponentially increase the pause time, starting from an hour.
This is extremely conservative but an unfortunate compromise to
minimize bad experience due to broken middle-boxes.

Reported-by: Dragana Damjanovic <ddamjanovic@mozilla.com>
Reported-by: Patrick McManus <mcmanus@ducksong.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Wei Wang <weiwan@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 1 insertions, 16 deletions

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 16df6dd44b98..c9a63417af48 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -183,11 +183,6 @@ static int tcp_write_timeout(struct sock *sk)
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits) {
 			dst_negative_advice(sk);
-			if (tp->syn_fastopen || tp->syn_data)
-				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
-			if (tp->syn_data && icsk->icsk_retransmits == 1)
-				NET_INC_STATS(sock_net(sk),
-					      LINUX_MIB_TCPFASTOPENACTIVEFAIL);
 		} else if (!tp->syn_data && !tp->syn_fastopen) {
 			sk_rethink_txhash(sk);
 		}
@@ -195,17 +190,6 @@ static int tcp_write_timeout(struct sock *sk)
 		expired = icsk->icsk_retransmits >= retry_until;
 	} else {
 		if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) {
-			/* Some middle-boxes may black-hole Fast Open _after_
-			 * the handshake. Therefore we conservatively disable
-			 * Fast Open on this path on recurring timeouts after
-			 * successful Fast Open.
-			 */
-			if (tp->syn_data_acked) {
-				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
-				if (icsk->icsk_retransmits == net->ipv4.sysctl_tcp_retries1)
-					NET_INC_STATS(sock_net(sk),
-						      LINUX_MIB_TCPFASTOPENACTIVEFAIL);
-			}
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
@@ -228,6 +212,7 @@ static int tcp_write_timeout(struct sock *sk)
 		expired = retransmits_timed_out(sk, retry_until,
 						icsk->icsk_user_timeout);
 	}
+	tcp_fastopen_active_detect_blackhole(sk, expired);
 	if (expired) {
 		/* Has it gone just too far? */
 		tcp_write_err(sk);