Skip to contentSkip to conversation

tcp: temporarily disable Fast Open on SYN timeout

PATCH Applied Yuchung Cheng 2 participants 2 messages Oct 29, 2013 – Oct 30, 2013

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 tcp: temporarily disable Fast Open on SYN timeout

Fast Open currently has a fall back feature to address SYN-data being dropped by but it requires the middle-box to pass on regular SYN retry after SYN-data. This is implemented in commit aab487435 ("net-tcp: Fast Open client - detecting SYN-data drops")

However some NAT boxes will drop all subsequent packets after first SYN-data and blackholes the entire connections. An example is incommit 356d7d8 "netfilter: nf_conntrack: fix tcp_in_window for Fast Open".

The sender should note such incidents and falls back to use regular TCP handshake on subsequent attempt temporarily as well: after the second SYN timeouts the original Fast Open SYN is most likely lost. When such an event recurs Fast Open is disabled based on the number of recurrences exponentially.

---
 net/ipv4/tcp_metrics.c | 5 +++--
 net/ipv4/tcp_timer.c   | 6 +++++-
 2 files changed, 8 insertions(+), 3 deletions(-)
net/ipv4/tcp_metrics.c +3 -2
index 4a2a841..2ab09cb 100644
@@ -671,8 +671,9 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
 		struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen;
 
 		write_seqlock_bh(&fastopen_seqlock);
-		tfom->mss = mss;
-		if (cookie->len > 0)
+		if (mss)
+			tfom->mss = mss;
+		if (cookie && cookie->len > 0)
 			tfom->cookie = *cookie;
 		if (syn_lost) {
 			++tfom->syn_loss;
net/ipv4/tcp_timer.c +5 -1
index af07b5b..64f0354 100644
@@ -156,12 +156,16 @@ static bool retransmits_timed_out(struct sock *sk,
 static int tcp_write_timeout(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 	int retry_until;
 	bool do_reset, syn_set = false;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
-		if (icsk->icsk_retransmits)
+		if (icsk->icsk_retransmits) {
 			dst_negative_advice(sk);
+			if (tp->syn_fastopen || tp->syn_data)
+				tcp_fastopen_cache_set(sk, 0, NULL, true);
+		}
 		retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
 		syn_set = true;
 	} else {
Signature · 1 line
1.8.4.1
maintainer Applied
#1 lore raw

From: Yuchung Cheng <[email protected]>
Date: Tue, 29 Oct 2013 10:09:05 -0700

Quoted 15 lines

Fast Open currently has a fall back feature to address SYN-data being dropped by but it requires the middle-box to pass on regular SYN retry after SYN-data. This is implemented in commit aab487435 ("net-tcp: Fast Open client - detecting SYN-data drops")

However some NAT boxes will drop all subsequent packets after first SYN-data and blackholes the entire connections. An example is incommit 356d7d8 "netfilter: nf_conntrack: fix tcp_in_window for Fast Open".

The sender should note such incidents and falls back to use regular TCP handshake on subsequent attempt temporarily as well: after the second SYN timeouts the original Fast Open SYN is most likely lost. When such an event recurs Fast Open is disabled based on the number of recurrences exponentially.

Quoted 3 lines

Applied, thanks.