Revert "vhost/net: Defer TX queue re-enable until after sendmsg"

This reverts commit 8c2e6b26ffe243be1e78f5a4bfb1a857d6e6f6d6. It tries
to defer the notification enabling by moving the logic out of the loop
after the vhost_tx_batch() when nothing new is spotted. This will
bring side effects as the new logic would be reused for several other
error conditions.

One example is the IOTLB: when there's an IOTLB miss, get_tx_bufs()
might return -EAGAIN and exit the loop and see there's still available
buffers, so it will queue the tx work again until userspace feed the
IOTLB entry correctly. This will slowdown the tx processing and
trigger the TX watchdog in the guest as reported in
https://lkml.org/lkml/2025/9/10/1596.

To fix, revert the change. A follow up patch will bring the performance
back in a safe way.

Reported-by: Jon Kohler <jon@nutanix.com>
Cc: stable@vger.kernel.org
Fixes: 8c2e6b26ffe2 ("vhost/net: Defer TX queue re-enable until after sendmsg")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Message-Id: <20250917063045.2042-2-jasowang@redhat.com>

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 16e39f3ab9566f9539214f678402b09f6b6a9bf6..57efd5c55f89e9e091ba73301ebd02676086722a 100644 (file)
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -765,11 +765,11 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
        int err;
        int sent_pkts = 0;
        bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX);
-       bool busyloop_intr;
        bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
 
        do {
-               busyloop_intr = false;
+               bool busyloop_intr = false;
+
                if (nvq->done_idx == VHOST_NET_BATCH)
                        vhost_tx_batch(net, nvq, sock, &msg);
 
@@ -780,10 +780,13 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
                        break;
                /* Nothing new?  Wait for eventfd to tell us they refilled. */
                if (head == vq->num) {
-                       /* Kicks are disabled at this point, break loop and
-                        * process any remaining batched packets. Queue will
-                        * be re-enabled afterwards.
-                        */
+                       if (unlikely(busyloop_intr)) {
+                               vhost_poll_queue(&vq->poll);
+                       } else if (unlikely(vhost_enable_notify(&net->dev,
+                                                               vq))) {
+                               vhost_disable_notify(&net->dev, vq);
+                               continue;
+                       }
                        break;
                }
 
@@ -839,22 +842,7 @@ done:
                ++nvq->done_idx;
        } while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len)));
 
-       /* Kicks are still disabled, dispatch any remaining batched msgs. */
        vhost_tx_batch(net, nvq, sock, &msg);
-
-       if (unlikely(busyloop_intr))
-               /* If interrupted while doing busy polling, requeue the
-                * handler to be fair handle_rx as well as other tasks
-                * waiting on cpu.
-                */
-               vhost_poll_queue(&vq->poll);
-       else
-               /* All of our work has been completed; however, before
-                * leaving the TX handler, do one last check for work,
-                * and requeue handler if necessary. If there is no work,
-                * queue will be reenabled.
-                */
-               vhost_net_busy_poll_try_queue(net, vq);
 }
 
 static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)