[PATCH net V2 1/2] vhost-net: unbreak busy polling

[PATCH net V2 1/2] vhost-net: unbreak busy polling

[Jason Wang]

Commit 67a873df0c41 ("vhost: basic in order support") pass the number
of used elem to vhost_net_rx_peek_head_len() to make sure it can
signal the used correctly before trying to do busy polling. But it
forgets to clear the count, this would cause the count run out of sync
with handle_rx() and break the busy polling.

Fixing this by passing the pointer of the count and clearing it after
the signaling the used.

Acked-by: Michael S. Tsirkin <mst@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 67a873df0c41 ("vhost: basic in order support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vhost/net.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index c6508fe0d5c8..16e39f3ab956 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1014,7 +1014,7 @@ static int peek_head_len(struct vhost_net_virtqueue *rvq, struct sock *sk)
 }
 
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
-				      bool *busyloop_intr, unsigned int count)
+				      bool *busyloop_intr, unsigned int *count)
 {
 	struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX];
 	struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX];
@@ -1024,7 +1024,8 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 
 	if (!len && rvq->busyloop_timeout) {
 		/* Flush batched heads first */
-		vhost_net_signal_used(rnvq, count);
+		vhost_net_signal_used(rnvq, *count);
+		*count = 0;
 		/* Both tx vq and rx socket were polled here */
 		vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, true);
 
@@ -1180,7 +1181,7 @@ static void handle_rx(struct vhost_net *net)
 
 	do {
 		sock_len = vhost_net_rx_peek_head_len(net, sock->sk,
-						      &busyloop_intr, count);
+						      &busyloop_intr, &count);
 		if (!sock_len)
 			break;
 		sock_len += sock_hlen;
-- 
2.34.1

[PATCH net V2 2/2] vhost-net: correctly flush batched packet before enabling notification

[Jason Wang]

Commit 8c2e6b26ffe2 ("vhost/net: Defer TX queue re-enable until after
sendmsg") 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.

Fixing this via partially reverting 8c2e6b26ffe2 and sticking the
notification enabling logic inside the loop when nothing new is
spotted and flush the batched before.

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>
---
Changes since V1:
- Tweak the commit log
- Typo fixes
---
 drivers/vhost/net.c | 33 +++++++++++++--------------------
 1 file changed, 13 insertions(+), 20 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 16e39f3ab956..3611b7537932 100644
--- 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 +780,18 @@ 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.
+			/* Flush batched packets before enabling
+			 * virqtueue notification to reduce
+			 * unnecssary virtqueue kicks.
 			 */
+			vhost_tx_batch(net, nvq, sock, &msg);
+			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 +847,7 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 		++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)
-- 
2.34.1

Re: [PATCH net V2 2/2] vhost-net: correctly flush batched packet before enabling notification

[Michael S. Tsirkin]

On Mon, Sep 15, 2025 at 10:47:03AM +0800, Jason Wang wrote:
> Commit 8c2e6b26ffe2 ("vhost/net: Defer TX queue re-enable until after
> sendmsg") 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.
> 
> Fixing this via partially reverting 8c2e6b26ffe2 and sticking the
> notification enabling logic inside the loop when nothing new is
> spotted and flush the batched before.
> 
> 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>


I still think it's better to structure this as 2 patches:
1. the revert to fix the deadlock
2. one line addition of vhost_tx_batch(net, nvq, sock, &msg);
   to get back the performance of 8c2e6b26ffe2


Not critical though



> ---
> Changes since V1:
> - Tweak the commit log
> - Typo fixes

but you didn't fix them all :(

See below

> ---
>  drivers/vhost/net.c | 33 +++++++++++++--------------------
>  1 file changed, 13 insertions(+), 20 deletions(-)
> 
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index 16e39f3ab956..3611b7537932 100644
> --- 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 +780,18 @@ 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.
> +			/* Flush batched packets before enabling
> +			 * virqtueue notification to reduce

notifications

> +			 * unnecssary virtqueue kicks.


unnecessary

>  			 */
> +			vhost_tx_batch(net, nvq, sock, &msg);
> +			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 +847,7 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
>  		++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)
> -- 
> 2.34.1