Re: [PATCH net,stable] vhost: fix skb leak in handle_rx()

[Jason Wang]

On 2017å11æ29æ 09:53, Jason Wang wrote:
> On 2017ÃÂÂ11ÃÅË29Ãâ 01:17, wexu@xxxxxxxxxx wrote:
> > From: Wei Xu <wexu@xxxxxxxxxx>
> >
> > Matthew found a roughly 40% tcp throughput regression with commit
> > c67df11f(vhost_net: try batch dequing from skb array) as discussed
> > in the following thread:
> > https://www.mail-archive.com/netdev@xxxxxxxxxxxxxxx/msg187936.html
> >
> > Eventually we figured out that it was a skb leak in handle_rx()
> > when sending packets to the VM. This usually happens when a guest
> > can not drain out vq as fast as vhost fills in, afterwards it sets
> > off the traffic jam and leaks skb(s) which occurs as no headcount
> > to send on the vq from vhost side.
> >
> > This can be avoided by making sure we have got enough headcount
> > before actually consuming a skb from the batched rx array while
> > transmitting, which is simply done by deferring it a moment later
> > in this patch.
> >
> > Signed-off-by: Wei Xu <wexu@xxxxxxxxxx>
> > ---
> > Â drivers/vhost/net.c | 4 ++--
> > Â 1 file changed, 2 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> > index 8d626d7..e76535e 100644
> > --- a/drivers/vhost/net.c
> > +++ b/drivers/vhost/net.c
> > @@ -778,8 +778,6 @@ static void handle_rx(struct vhost_net *net)
> > ÂÂÂÂÂÂÂÂÂ /* On error, stop handling until the next kick. */
> > ÂÂÂÂÂÂÂÂÂ if (unlikely(headcount < 0))
> > ÂÂÂÂÂÂÂÂÂÂÂÂÂ goto out;
> > -ÂÂÂÂÂÂÂ if (nvq->rx_array)
> > -ÂÂÂÂÂÂÂÂÂÂÂ msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
> > ÂÂÂÂÂÂÂÂÂ /* On overrun, truncate and discard */
> > ÂÂÂÂÂÂÂÂÂ if (unlikely(headcount > UIO_MAXIOV)) {
>
> You need do msg.msg_control = vhost_net_buf_consume() here too, 
> otherwise we may still get it leaked.
>
> Thanks 

Not a leak actually, but the packet won't be consumed and we will hit 
UIO_MAXIOV forever in this case.

Thanks