Jason Wang f5755c0e87 vhost_net: correctly check tx avail during rx busy polling ...

[ Upstream commit 8b949bef91 ]

We check tx avail through vhost_enable_notify() in the past which is
wrong since it only checks whether or not guest has filled more
available buffer since last avail idx synchronization which was just
done by vhost_vq_avail_empty() before. What we really want is checking
pending buffers in the avail ring. Fix this by calling
vhost_vq_avail_empty() instead.

This issue could be noticed by doing netperf TCP_RR benchmark as
client from guest (but not host). With this fix, TCP_RR from guest to
localhost restores from 1375.91 trans per sec to 55235.28 trans per
sec on my laptop (Intel(R) Core(TM) i7-5600U CPU @ 2.60GHz).

Fixes: 0308813724 ("vhost_net: basic polling support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2017-09-20 08:19:56 +02:00

..

Kconfig

vhost: split out vringh Kconfig

2016-08-02 16:54:28 +03:00

Kconfig.vringh

vhost: split out vringh Kconfig

2016-08-02 16:54:28 +03:00

Makefile

VSOCK: Add Makefile and Kconfig

2016-08-02 02:57:30 +03:00

net.c

vhost_net: correctly check tx avail during rx busy polling

2017-09-20 08:19:56 +02:00

scsi.c

vhost/scsi: fix reuse of &vq->iov[out] in response

2016-08-23 17:16:57 +03:00

test.c

Merge 4.8-rc5 into char-misc-next

2016-09-05 08:04:07 +02:00

test.h

vhost test module

2010-12-09 16:00:21 +02:00

vhost.c

vhost: fix initialization for vq->is_le

2017-02-09 08:08:28 +01:00

vhost.h

vhost: new device IOTLB API

2016-08-02 16:53:54 +03:00

vringh.c

vringh: update for virtio 1.0 APIs

2014-12-15 23:49:28 +02:00

vsock.c

vhost/vsock: handle vhost_vq_init_access() error

2017-06-17 06:41:57 +02:00