vhost_net: stop polling socket during rx processing

We don't stop rx polling socket during rx processing, this will lead
unnecessary wakeups from under layer net devices (E.g
sock_def_readable() form tun). Rx will be slowed down in this
way. This patch avoids this by stop polling socket during rx
processing. A small drawback is that this introduces some overheads in
light load case because of the extra start/stop polling, but single
netperf TCP_RR does not notice any change. In a super heavy load case,
e.g using pktgen to inject packet to guest, we get about ~8.8%
improvement on pps:

before: ~1240000 pkt/s
after:  ~1350000 pkt/s

Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f744eeb3e2b47ec0abbfa908e81e4cc108097145..1d3e45f84549beb85c9bfbe1fc87a283ec164611 100644 (file)
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -301,6 +301,32 @@ static bool vhost_can_busy_poll(struct vhost_dev *dev,
               !vhost_has_work(dev);
 }
 
+static void vhost_net_disable_vq(struct vhost_net *n,
+                                struct vhost_virtqueue *vq)
+{
+       struct vhost_net_virtqueue *nvq =
+               container_of(vq, struct vhost_net_virtqueue, vq);
+       struct vhost_poll *poll = n->poll + (nvq - n->vqs);
+       if (!vq->private_data)
+               return;
+       vhost_poll_stop(poll);
+}
+
+static int vhost_net_enable_vq(struct vhost_net *n,
+                               struct vhost_virtqueue *vq)
+{
+       struct vhost_net_virtqueue *nvq =
+               container_of(vq, struct vhost_net_virtqueue, vq);
+       struct vhost_poll *poll = n->poll + (nvq - n->vqs);
+       struct socket *sock;
+
+       sock = vq->private_data;
+       if (!sock)
+               return 0;
+
+       return vhost_poll_start(poll, sock->file);
+}
+
 static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
                                    struct vhost_virtqueue *vq,
                                    struct iovec iov[], unsigned int iov_size,
@@ -613,6 +639,7 @@ static void handle_rx(struct vhost_net *net)
        if (!sock)
                goto out;
        vhost_disable_notify(&net->dev, vq);
+       vhost_net_disable_vq(net, vq);
 
        vhost_hlen = nvq->vhost_hlen;
        sock_hlen = nvq->sock_hlen;
@@ -629,7 +656,7 @@ static void handle_rx(struct vhost_net *net)
                                        likely(mergeable) ? UIO_MAXIOV : 1);
                /* On error, stop handling until the next kick. */
                if (unlikely(headcount < 0))
-                       break;
+                       goto out;
                /* On overrun, truncate and discard */
                if (unlikely(headcount > UIO_MAXIOV)) {
                        iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
@@ -648,7 +675,7 @@ static void handle_rx(struct vhost_net *net)
                        }
                        /* Nothing new?  Wait for eventfd to tell us
                         * they refilled. */
-                       break;
+                       goto out;
                }
                /* We don't need to be notified again. */
                iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len);
@@ -676,7 +703,7 @@ static void handle_rx(struct vhost_net *net)
                                         &fixup) != sizeof(hdr)) {
                                vq_err(vq, "Unable to write vnet_hdr "
                                       "at addr %p\n", vq->iov->iov_base);
-                               break;
+                               goto out;
                        }
                } else {
                        /* Header came from socket; we'll need to patch
@@ -692,7 +719,7 @@ static void handle_rx(struct vhost_net *net)
                                 &fixup) != sizeof num_buffers) {
                        vq_err(vq, "Failed num_buffers write");
                        vhost_discard_vq_desc(vq, headcount);
-                       break;
+                       goto out;
                }
                vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
                                            headcount);
@@ -701,9 +728,10 @@ static void handle_rx(struct vhost_net *net)
                total_len += vhost_len;
                if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
                        vhost_poll_queue(&vq->poll);
-                       break;
+                       goto out;
                }
        }
+       vhost_net_enable_vq(net, vq);
 out:
        mutex_unlock(&vq->mutex);
 }
@@ -782,32 +810,6 @@ static int vhost_net_open(struct inode *inode, struct file *f)
        return 0;
 }
 
-static void vhost_net_disable_vq(struct vhost_net *n,
-                                struct vhost_virtqueue *vq)
-{
-       struct vhost_net_virtqueue *nvq =
-               container_of(vq, struct vhost_net_virtqueue, vq);
-       struct vhost_poll *poll = n->poll + (nvq - n->vqs);
-       if (!vq->private_data)
-               return;
-       vhost_poll_stop(poll);
-}
-
-static int vhost_net_enable_vq(struct vhost_net *n,
-                               struct vhost_virtqueue *vq)
-{
-       struct vhost_net_virtqueue *nvq =
-               container_of(vq, struct vhost_net_virtqueue, vq);
-       struct vhost_poll *poll = n->poll + (nvq - n->vqs);
-       struct socket *sock;
-
-       sock = vq->private_data;
-       if (!sock)
-               return 0;
-
-       return vhost_poll_start(poll, sock->file);
-}
-
 static struct socket *vhost_net_stop_vq(struct vhost_net *n,
                                        struct vhost_virtqueue *vq)
 {