On Wed, Nov 29, 2017 at 10:43:33PM +0800, Jason Wang wrote: > > > On 2017年11月29日 22:23, 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 moving checking the zero > > headcount a bit ahead. > > > > Also strengthen the small possibility of leak in case of recvmsg() > > fails by freeing the skb. > > > > Signed-off-by: Wei Xu <wexu@xxxxxxxxxx> > > Reported-by: Matthew Rosato <mjrosato@xxxxxxxxxxxxxxxxxx> > > --- > > drivers/vhost/net.c | 23 +++++++++++++---------- > > 1 file changed, 13 insertions(+), 10 deletions(-) > > > > v2: > > - add Matthew as the reporter, thanks matthew. > > - moving zero headcount check ahead instead of defer consuming skb > > due to jason and mst's comment. > > - add freeing skb in favor of recvmsg() fails. > > > > diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c > > index 8d626d7..e302e08 100644 > > --- a/drivers/vhost/net.c > > +++ b/drivers/vhost/net.c > > @@ -778,16 +778,6 @@ static void handle_rx(struct vhost_net *net) > > /* On error, stop handling until the next kick. */ > > if (unlikely(headcount < 0)) > > goto out; > > - if (nvq->rx_array) > > - msg.msg_control = vhost_net_buf_consume(&nvq->rxq); > > - /* On overrun, truncate and discard */ > > - if (unlikely(headcount > UIO_MAXIOV)) { > > - iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1); > > - err = sock->ops->recvmsg(sock, &msg, > > - 1, MSG_DONTWAIT | MSG_TRUNC); > > - pr_debug("Discarded rx packet: len %zd\n", sock_len); > > - continue; > > - } > > /* OK, now we need to know about added descriptors. */ > > if (!headcount) { > > if (unlikely(vhost_enable_notify(&net->dev, vq))) { > > @@ -800,6 +790,18 @@ static void handle_rx(struct vhost_net *net) > > * they refilled. */ > > goto out; > > } > > + if (nvq->rx_array) > > + msg.msg_control = vhost_net_buf_consume(&nvq->rxq); > > + /* On overrun, truncate and discard */ > > + if (unlikely(headcount > UIO_MAXIOV)) { > > + iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1); > > + err = sock->ops->recvmsg(sock, &msg, > > + 1, MSG_DONTWAIT | MSG_TRUNC); > > + if (unlikely(err != 1)) > > + kfree_skb((struct sk_buff *)msg.msg_control); > > I think we'd better fix this in tun/tap (better in another patch) otherwise > it lead to an odd API: some case skb were freed in recvmsg() but caller > still need to deal with the rest case. Right, it is better to handle it in recvmsg(). Wei _______________________________________________ Virtualization mailing list Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linuxfoundation.org/mailman/listinfo/virtualization
