diff options
| author |   Jason Wang <jasowang@redhat.com> | 2017-09-05 09:22:05 +0800 |
|---|---|---|
| committer |   Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2017-09-20 08:22:10 +0200 |
| commit | 88f6c6f254bf414cf135acc1d5d6edf106a02ab4 (patch) | |
| tree | 352e3cd53c6410d8c893f98ba5f696ea7d4cc434 | |
| parent | gianfar: Fix Tx flow control deactivation (diff) | |
| download | linux-stable-88f6c6f254bf414cf135acc1d5d6edf106a02ab4.tar.xz linux-stable-88f6c6f254bf414cf135acc1d5d6edf106a02ab4.zip | |
vhost_net: correctly check tx avail during rx busy polling
[ Upstream commit 8b949bef9172ca69d918e93509a4ecb03d0355e0 ]
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: 030881372460 ("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>
| -rw-r--r-- | drivers/vhost/net.c | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index f61f852d6cfd..83ad2ac0cbea 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -557,8 +557,13 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk) preempt_enable(); - if (vhost_enable_notify(&net->dev, vq)) + if (!vhost_vq_avail_empty(&net->dev, vq)) vhost_poll_queue(&vq->poll); + else if (unlikely(vhost_enable_notify(&net->dev, vq))) { + vhost_disable_notify(&net->dev, vq); + vhost_poll_queue(&vq->poll); + } + mutex_unlock(&vq->mutex); len = peek_head_len(sk); |