tcp: purge write queue upon aborting the connection
Subsystems (3)
PATCH 1/1 tcp: purge write queue upon aborting the connection
From: Soheil Hassas Yeganeh <[email protected]>
When the connection is aborted, there is no point in keeping the packets on the write queue until the connection is closed.
Similar to a27fd7a8ed38 ('tcp: purge write queue upon RST'), this is essential for a correct MSG_ZEROCOPY implementation, because userspace cannot call close(fd) before receiving zerocopy signals even when the connection is aborted.
--- net/ipv4/tcp.c | 1 + net/ipv4/tcp_timer.c | 1 + 2 files changed, 2 insertions(+)
net/ipv4/tcp.c +1 -0
@@ -3566,6 +3566,7 @@ int tcp_abort(struct sock *sk, int err)bh_unlock_sock (sk);local_bh_enable (); +tcp_write_queue_purge (sk);release_sock (sk);return 0 ; }
net/ipv4/tcp_timer.c +1 -0
@@ -34,6 +34,7 @@ static void tcp_write_err(struct sock *sk) sk->sk_err = sk->sk_err_soft ? :ETIMEDOUT ; sk->sk_error_report (sk); +tcp_write_queue_purge (sk);tcp_done (sk);__NET_INC_STATS (sock_net (sk),LINUX_MIB_TCPABORTONTIMEOUT ); }
Signature · 1 line
2.16.2.395.g2e18187dfd-goog
David Miller
maintainerFrom: Soheil Hassas Yeganeh <[email protected]>
Date: Tue, 6 Mar 2018 17:15:12 -0500
Quoted 11 lines
From: Soheil Hassas Yeganeh <[email protected]>
When the connection is aborted, there is no point in keeping the packets on the write queue until the connection is closed.
Similar to
a27fd7a8ed38('tcp: purge write queue upon RST'), this is essential for a correctMSG_ZEROCOPYimplementation, because userspace cannot call close(fd) before receiving zerocopy signals even when the connection is aborted.
Quoted 5 lines
Fixes f214f915e7db ("tcp: enable MSG_ZEROCOPY")Signed-off-by Soheil Hassas Yeganeh <[email protected]>Signed-off-by Neal Cardwell <[email protected]>Reviewed-by Eric Dumazet <[email protected]>Signed-off-by Yuchung Cheng <[email protected]>
Applied and queued up for -stable, thanks.