Skip to contentSkip to conversation

tcp: purge write queue upon RST

PATCH In review Soheil Hassas Yeganeh 3 participants 3 messages Feb 27, 2018 – Feb 28, 2018

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

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.

Fixes f214f915e7db ("tcp: enable MSG_ZEROCOPY")
---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)
net/ipv4/tcp_input.c +1 -0
index 06b9c4765f42..b17fac2629c3 100644
@@ -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
maintainer
#1 lore raw

From: 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-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.

Quoted 5 lines
Fixes f214f915e7db ("tcp: enable MSG_ZEROCOPY")

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!

#2 lore raw
Quoted 24 lines · David Miller

From: 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-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.

Quoted 5 lines
Fixes f214f915e7db ("tcp: enable MSG_ZEROCOPY")
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.