[2/2] tcp: fix forever orphan socket caused by tcp_abort

Commit Message

Youngmin Nam March 14, 2025, 9:24 a.m. UTC

From: Xueming Feng <[e-mail]>

commit bac76cf89816bff06c4ec2f3df97dc34e150a1c4 upstream.

We have some problem closing zero-window fin-wait-1 tcp sockets in our
environment. This patch come from the investigation.

Previously tcp_abort only sends out reset and calls tcp_done when the
socket is not SOCK_DEAD, aka orphan. For orphan socket, it will only
purging the write queue, but not close the socket and left it to the
timer.

While purging the write queue, tp->packets_out and sk->sk_write_queue
is cleared along the way. However tcp_retransmit_timer have early
return based on !tp->packets_out and tcp_probe_timer have early
return based on !sk->sk_write_queue.

This caused ICSK_TIME_RETRANS and ICSK_TIME_PROBE0 not being resched
and socket not being killed by the timers, converting a zero-windowed
orphan into a forever orphan.

This patch removes the SOCK_DEAD check in tcp_abort, making it send
reset to peer and close the socket accordingly. Preventing the
timer-less orphan from happening.

According to Lorenzo's email in the v1 thread, the check was there to
prevent force-closing the same socket twice. That situation is handled
by testing for TCP_CLOSE inside lock, and returning -ENOENT if it is
already closed.

The -ENOENT code comes from the associate patch Lorenzo made for
iproute2-ss; link attached below, which also conform to RFC 9293.

At the end of the patch, tcp_write_queue_purge(sk) is removed because it
was already called in tcp_done_with_error().

p.s. This is the same patch with v2. Resent due to mis-labeled "changes
requested" on patchwork.kernel.org.

Link: https://patchwork.ozlabs.org/project/netdev/patch/[e-mail]/
Fixes: c1e64e298b8c ("net: diag: Support destroying TCP sockets.")
Signed-off-by: Xueming Feng <[e-mail]>
Tested-by: Lorenzo Colitti <[e-mail]>
Reviewed-by: Jason Xing <[e-mail]>
Reviewed-by: Eric Dumazet <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>
Cc: <[e-mail]> # v5.10+
Link: https://lore.kernel.org/lkml/Z9OZS%2Fhc+v5og6%2FU@perf/
[youngmin: Resolved minor conflict in net/ipv4/tcp.c]
Signed-off-by: Youngmin Nam <[e-mail]>
---
 net/ipv4/tcp.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

Comments

Greg KH March 14, 2025, 12:24 p.m. UTC | #1

On Fri, Mar 14, 2025 at 06:24:46PM +0900, Youngmin Nam wrote:
> From: Xueming Feng <[e-mail]>
> 
> commit bac76cf89816bff06c4ec2f3df97dc34e150a1c4 upstream.
> 
> We have some problem closing zero-window fin-wait-1 tcp sockets in our
> environment. This patch come from the investigation.
> 
> Previously tcp_abort only sends out reset and calls tcp_done when the
> socket is not SOCK_DEAD, aka orphan. For orphan socket, it will only
> purging the write queue, but not close the socket and left it to the
> timer.
> 
> While purging the write queue, tp->packets_out and sk->sk_write_queue
> is cleared along the way. However tcp_retransmit_timer have early
> return based on !tp->packets_out and tcp_probe_timer have early
> return based on !sk->sk_write_queue.
> 
> This caused ICSK_TIME_RETRANS and ICSK_TIME_PROBE0 not being resched
> and socket not being killed by the timers, converting a zero-windowed
> orphan into a forever orphan.
> 
> This patch removes the SOCK_DEAD check in tcp_abort, making it send
> reset to peer and close the socket accordingly. Preventing the
> timer-less orphan from happening.
> 
> According to Lorenzo's email in the v1 thread, the check was there to
> prevent force-closing the same socket twice. That situation is handled
> by testing for TCP_CLOSE inside lock, and returning -ENOENT if it is
> already closed.
> 
> The -ENOENT code comes from the associate patch Lorenzo made for
> iproute2-ss; link attached below, which also conform to RFC 9293.
> 
> At the end of the patch, tcp_write_queue_purge(sk) is removed because it
> was already called in tcp_done_with_error().
> 
> p.s. This is the same patch with v2. Resent due to mis-labeled "changes
> requested" on patchwork.kernel.org.
> 
> Link: https://patchwork.ozlabs.org/project/netdev/patch/[e-mail]/
> Fixes: c1e64e298b8c ("net: diag: Support destroying TCP sockets.")
> Signed-off-by: Xueming Feng <[e-mail]>
> Tested-by: Lorenzo Colitti <[e-mail]>
> Reviewed-by: Jason Xing <[e-mail]>
> Reviewed-by: Eric Dumazet <[e-mail]>
> Link: https://patch.msgid.link/[e-mail]
> Signed-off-by: Jakub Kicinski <[e-mail]>
> Cc: <[e-mail]> # v5.10+

Does not apply to 6.1.y or older, what did you want this applied to?

thanks,

greg k-h

Patch

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9fe164aa185c..ff22060f9145 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4620,6 +4620,13 @@  int tcp_abort(struct sock *sk, int err)
 		/* Don't race with userspace socket closes such as tcp_close. */
 		lock_sock(sk);
 
+	/* Avoid closing the same socket twice. */
+	if (sk->sk_state == TCP_CLOSE) {
+		if (!has_current_bpf_ctx())
+			release_sock(sk);
+		return -ENOENT;
+	}
+
 	if (sk->sk_state == TCP_LISTEN) {
 		tcp_set_state(sk, TCP_CLOSE);
 		inet_csk_listen_stop(sk);
@@ -4629,15 +4636,12 @@  int tcp_abort(struct sock *sk, int err)
 	local_bh_disable();
 	bh_lock_sock(sk);
 
-	if (!sock_flag(sk, SOCK_DEAD)) {
-		if (tcp_need_reset(sk->sk_state))
-			tcp_send_active_reset(sk, GFP_ATOMIC);
-		tcp_done_with_error(sk, err);
-	}
+	if (tcp_need_reset(sk->sk_state))
+		tcp_send_active_reset(sk, GFP_ATOMIC);
+	tcp_done_with_error(sk, err);
 
 	bh_unlock_sock(sk);
 	local_bh_enable();
-	tcp_write_queue_purge(sk);
 	if (!has_current_bpf_ctx())
 		release_sock(sk);
 	return 0;