From: Eric Dumazet <edumazet@xxxxxxxxxx>
commit 97a9063518f198ec0adb2ecb89789de342bb8283 upstream.
If a TCP socket is using TCP_USER_TIMEOUT, and the other peer
retracted its window to zero, tcp_retransmit_timer() can
retransmit a packet every two jiffies (2 ms for HZ=1000),
for about 4 minutes after TCP_USER_TIMEOUT has 'expired'.
The fix is to make sure tcp_rtx_probe0_timed_out() takes
icsk->icsk_user_timeout into account.
Before blamed commit, the socket would not timeout after
icsk->icsk_user_timeout, but would use standard exponential
backoff for the retransmits.
Also worth noting that before commit e89688e3e978 ("net: tcp:
fix unexcepted socket die when snd_wnd is 0"), the issue
would last 2 minutes instead of 4.
Fixes: b701a99e431d ("tcp: Add tcp_clamp_rto_to_user_timeout() helper to improve accuracy")
Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Cc: Neal Cardwell <ncardwell@xxxxxxxxxx>
Reviewed-by: Jason Xing <kerneljasonxing@xxxxxxxxx>
Reviewed-by: Jon Maxwell <jmaxwell37@xxxxxxxxx>
Reviewed-by: Kuniyuki Iwashima <kuniyu@xxxxxxxxxx>
Link: https://patch.msgid.link/20240710001402.2758273-1-edumazet@xxxxxxxxxx
Signed-off-by: Jakub Kicinski <kuba@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
net/ipv4/tcp_timer.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -437,16 +437,28 @@ static void tcp_fastopen_synack_timer(st
static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
const struct sk_buff *skb)
{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
const struct tcp_sock *tp = tcp_sk(sk);
- const int timeout = TCP_RTO_MAX * 2;
+ int timeout = TCP_RTO_MAX * 2;
u32 rtx_delta;
s32 rcv_delta;
+ if (user_timeout) {
+ /* If user application specified a TCP_USER_TIMEOUT,
+ * it does not want win 0 packets to 'reset the timer'
+ * while retransmits are not making progress.
+ */
+ if (rtx_delta > user_timeout)
+ return true;
+ timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout));
+ }
+
/* Note: timer interrupt might have been delayed by at least one jiffy,
* and tp->rcv_tstamp might very well have been written recently.
* rcv_delta can thus be negative.
*/
- rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp;
+ rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp;
if (rcv_delta <= timeout)
return false;
Patches currently in stable-queue which might be from 3wdKVZggKBvgjizrf4jylttlqj.htrlwjlpmqnsz2ktzsifynts.twl@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx are
queue-5.4/tcp-avoid-too-many-retransmit-packets.patch
