tcp: purge write queue upon RST
Subsystems (3)
PATCH 1/1 tcp: purge write queue upon RST
From: Soheil Hassas Yeganeh <[email protected]>
When the connection is reset, there is no point in keeping the packets on the write queue until the connection is closed.
RFC 793 (page 70) and RFC 793-bis (page 64) both suggest purging the write queue upon RST:
https://tools.ietf.org/html/draft-ietf-tcpm-rfc793bis-07
Moreover, this is essential for a correct MSG_ZEROCOPY implementation, because userspace cannot call close(fd) before receiving zerocopy signals even when the connection is reset.
--- net/ipv4/tcp_input.c | 1 + 1 file changed, 1 insertion(+)
net/ipv4/tcp_input.c +1 -0
@@ -3998,6 +3998,7 @@ void tcp_reset(struct sock *sk)/* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb (); +tcp_write_queue_purge (sk);tcp_done (sk);if (!sock_flag (sk,SOCK_DEAD ))
Signature · 1 line
2.16.2.395.g2e18187dfd-goog
David Miller
maintainerFrom: Soheil Hassas Yeganeh <[email protected]>
Date: Tue, 27 Feb 2018 18:32:18 -0500
Quoted 15 lines
From: Soheil Hassas Yeganeh <[email protected]>
When the connection is reset, there is no point in keeping the packets on the write queue until the connection is closed.
RFC 793 (page 70) and RFC 793-bis (page 64) both suggest purging the write queue upon RST:
https://tools.ietf.org/html/draft-ietf-tcpm-rfc793bis-07Moreover, this is essential for a correct
MSG_ZEROCOPYimplementation, because userspace cannot call close(fd) before receiving zerocopy signals even when the connection is reset.
Quoted 5 lines
Fixes f214f915e7db ("tcp: enable MSG_ZEROCOPY")Signed-off-by Soheil Hassas Yeganeh <[email protected]>Reviewed-by Eric Dumazet <[email protected]>Signed-off-by Yuchung Cheng <[email protected]>Signed-off-by Neal Cardwell <[email protected]>
This is one of those "yeah, why have we been doing this all of this time?" kind of situation.
Let's hope there isn't some subtle side effect, but indeed this current behavior is broken for MSG_ZEROCOPY.
Applied and queued up for -stable, thanks!
Quoted 24 lines · David Miller
From: Soheil Hassas Yeganeh <[email protected]>
Date: Tue, 27 Feb 2018 18:32:18 -0500Quoted 15 lines
From: Soheil Hassas Yeganeh <[email protected]>
When the connection is reset, there is no point in keeping the packets on the write queue until the connection is closed.
RFC 793 (page 70) and RFC 793-bis (page 64) both suggest purging the write queue upon RST:
https://tools.ietf.org/html/draft-ietf-tcpm-rfc793bis-07Moreover, this is essential for a correct
MSG_ZEROCOPYimplementation, because userspace cannot call close(fd) before receiving zerocopy signals even when the connection is reset.Quoted 5 lines
Fixes f214f915e7db ("tcp: enable MSG_ZEROCOPY")Signed-off-by Soheil Hassas Yeganeh <[email protected]>Reviewed-by Eric Dumazet <[email protected]>Signed-off-by Yuchung Cheng <[email protected]>Signed-off-by Neal Cardwell <[email protected]>
Quoted 6 lines
This is one of those "yeah, why have we been doing this all of this time?" kind of situation.
Let's hope there isn't some subtle side effect, but indeed this current behavior is broken for
MSG_ZEROCOPY.
One of the effect is that for very large queues (more than 100 MB), queue purge might take a lot of time, in BH context (while handling one RST)
But even before the patch, this could also happen from BH context anyway.
We might use work queue (s) in the future to handle the purge in the background in process context.
But really this is not urgent.
Quoted 1 line
Applied and queued up for -stable, thanks!
Thanks David.