aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorMenglong Dong <imagedong@tencent.com>2023-08-11 10:55:29 +0800
committerDavid S. Miller <davem@davemloft.net>2023-08-13 12:21:37 +0100
commite89688e3e97868451a5d05b38a9d2633d6785cd4 (patch)
tree1225317dcd3fbb6641b83478ee977aa3e46afe08
parent800a666141de75baebb59b347b9c9e43d963e4da (diff)
downloadnf-next-e89688e3e97868451a5d05b38a9d2633d6785cd4.tar.gz
net: tcp: fix unexcepted socket die when snd_wnd is 0
In tcp_retransmit_timer(), a window shrunk connection will be regarded as timeout if 'tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX'. This is not right all the time. The retransmits will become zero-window probes in tcp_retransmit_timer() if the 'snd_wnd==0'. Therefore, the icsk->icsk_rto will come up to TCP_RTO_MAX sooner or later. However, the timer can be delayed and be triggered after 122877ms, not TCP_RTO_MAX, as I tested. Therefore, 'tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX' is always true once the RTO come up to TCP_RTO_MAX, and the socket will die. Fix this by replacing the 'tcp_jiffies32' with '(u32)icsk->icsk_timeout', which is exact the timestamp of the timeout. However, "tp->rcv_tstamp" can restart from idle, then tp->rcv_tstamp could already be a long time (minutes or hours) in the past even on the first RTO. So we double check the timeout with the duration of the retransmission. Meanwhile, making "2 * TCP_RTO_MAX" as the timeout to avoid the socket dying too soon. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://lore.kernel.org/netdev/CADxym3YyMiO+zMD4zj03YPM3FBi-1LHi6gSD2XT8pyAMM096pg@mail.gmail.com/ Signed-off-by: Menglong Dong <imagedong@tencent.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--net/ipv4/tcp_timer.c18
1 files changed, 17 insertions, 1 deletions
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index d45c96c7f5a447..f2a52c11e044e9 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -454,6 +454,22 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
req->timeout << req->num_timeout, TCP_RTO_MAX);
}
+static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
+ const struct sk_buff *skb)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ const int timeout = TCP_RTO_MAX * 2;
+ u32 rcv_delta, rtx_delta;
+
+ rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp;
+ if (rcv_delta <= timeout)
+ return false;
+
+ rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) -
+ (tp->retrans_stamp ?: tcp_skb_timestamp(skb)));
+
+ return rtx_delta > timeout;
+}
/**
* tcp_retransmit_timer() - The TCP retransmit timeout handler
@@ -519,7 +535,7 @@ void tcp_retransmit_timer(struct sock *sk)
tp->snd_una, tp->snd_nxt);
}
#endif
- if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) {
+ if (tcp_rtx_probe0_timed_out(sk, skb)) {
tcp_write_err(sk);
goto out;
}