[PATCH v3 0/4] vhost/vsock: add support for VHOST_RESET_OWNER and CPR migration

[PATCH v3 0/4] vhost/vsock: add support for VHOST_RESET_OWNER and CPR migration

[Andrey Drobyshev]

v2 -> v3:

  * Patch 4: skip the kick of TX VQ worker once backend is gone - add
    to cancel_pkt() the same guard as in send_pkt().
    (Reported by Sashiko AI)

v2: https://lore.kernel.org/virtualization/20260622175808.508084-1-andrey.drobyshev@virtuozzo.com

Andrey Drobyshev (2):
  vhost/vsock: suppress EHOSTUNREACH fast-fail during CPR pause
  vhost/vsock: re-scan TX virtqueue on device start

Pavel Tikhomirov (2):
  vhost/vsock: split out vhost_vsock_drop_backends helper
  vhost/vsock: add VHOST_RESET_OWNER ioctl

 drivers/vhost/vsock.c | 106 +++++++++++++++++++++++++++++++++---------
 1 file changed, 85 insertions(+), 21 deletions(-)

-- 
2.47.1

[PATCH v3 1/4] vhost/vsock: split out vhost_vsock_drop_backends helper

[Andrey Drobyshev]

From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>

Split the actual backend dropping part from vhost_vsock_stop.  We're
going to need it for the VHOST_RESET_OWNER implementation in the
following patch, when vsock->dev.mutex is already taken and owner is
checked.

Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
Reviewed-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
---
 drivers/vhost/vsock.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 9aaab6bb8061..b12221ce6faf 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -664,9 +664,24 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 	return ret;
 }
 
-static int vhost_vsock_stop(struct vhost_vsock *vsock, bool check_owner)
+static void vhost_vsock_drop_backends(struct vhost_vsock *vsock)
 {
+	struct vhost_virtqueue *vq;
 	size_t i;
+
+	lockdep_assert_held(&vsock->dev.mutex);
+
+	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
+		vq = &vsock->vqs[i];
+
+		mutex_lock(&vq->mutex);
+		vhost_vq_set_backend(vq, NULL);
+		mutex_unlock(&vq->mutex);
+	}
+}
+
+static int vhost_vsock_stop(struct vhost_vsock *vsock, bool check_owner)
+{
 	int ret = 0;
 
 	mutex_lock(&vsock->dev.mutex);
@@ -677,14 +692,7 @@ static int vhost_vsock_stop(struct vhost_vsock *vsock, bool check_owner)
 			goto err;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
-		struct vhost_virtqueue *vq = &vsock->vqs[i];
-
-		mutex_lock(&vq->mutex);
-		vhost_vq_set_backend(vq, NULL);
-		mutex_unlock(&vq->mutex);
-	}
-
+	vhost_vsock_drop_backends(vsock);
 err:
 	mutex_unlock(&vsock->dev.mutex);
 	return ret;
-- 
2.47.1

[PATCH v3 2/4] vhost/vsock: suppress EHOSTUNREACH fast-fail during CPR pause

[Andrey Drobyshev]

Earlier commit bb26ed5f3a8b ("vhost/vsock: Refuse the connection
immediately when guest isn't ready") added a fast-fail in
vhost_transport_send_pkt().  It rejects every host send with -EHOSTUNREACH
until the destination calls SET_RUNNING(1).  The fast-fail condition checks
whether device's backends are dropped, and if they're, the guest is
considered to be not ready.

However, there might be other reasons for backends to be nulled.  In
particular, when QEMU is performing CPR (checkpoint-restore) migration,
device ownership is being RESET and SET again, which leads to backends
drop and reattach.  If we end up connecting during this window, an
AF_VSOCK client gets -EHOSTUNREACH, which is wrong.

Add a 'started' flag which is set once in vhost_vsock_start() and is
never cleared.  The behaviour changes to:

  * When device was never started -> flag is unset -> no listener can
    exist yet -> fast-fail;
  * Once the device starts -> flag is set -> we don't fast-fail ->
    we queue and preserve during any later stop / CPR pause.

Important caveat: after the first start, a connect during any stopped
window is queued instead of fast-failed.  That was the behaviour before
the patch bb26ed5f3a8b, and we're restoring it now.  However we still
keep the behaviour originally intended by that commit (i.e. fast-fail if
there's no real listener yet) while fixing the CPR path.

Signed-off-by: Denis V. Lunev <den@openvz.org>
Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
Reviewed-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
---
 drivers/vhost/vsock.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index b12221ce6faf..bec6bcfd885f 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -61,6 +61,7 @@ struct vhost_vsock {
 
 	u32 guest_cid;
 	bool seqpacket_allow;
+	bool started;		/* set on first SET_RUNNING(1); never cleared */
 };
 
 static u32 vhost_transport_get_local_cid(void)
@@ -302,17 +303,12 @@ vhost_transport_send_pkt(struct sk_buff *skb, struct net *net)
 		return -ENODEV;
 	}
 
-	/* Fast-fail if the guest hasn't enabled the RX vq yet. Queuing the packet
-	 * and making the caller wait is pointless: even if the guest manages to init
-	 * within the timeout, it'll immediately reply with RST, because there's no
-	 * listener on the port yet.
-	 *
-	 * vhost_vq_get_backend() without vq->mutex is acceptable here: locking
-	 * the mutex would be too expensive in this hot path, and we already have
-	 * all the outcomes covered: if the backend becomes NULL right after the check,
-	 * vhost_transport_do_send_pkt() will check it under the mutex anyway.
+	/* Fast-fail until the guest first enables the device (SET_RUNNING(1)).
+	 * Before that there is no listener, so queuing is pointless. 'started'
+	 * is never cleared, so once we're up we keep queuing across later
+	 * stop / CPR-pause windows.
 	 */
-	if (unlikely(!data_race(vhost_vq_get_backend(&vsock->vqs[VSOCK_VQ_RX])))) {
+	if (unlikely(!READ_ONCE(vsock->started))) {
 		rcu_read_unlock();
 		kfree_skb(skb);
 		return -EHOSTUNREACH;
@@ -640,6 +636,11 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 		mutex_unlock(&vq->mutex);
 	}
 
+	/* Set 'started' flag on the first start; never cleared, so send_pkt
+	 * keeps queuing (instead of fast-failing) on later stop / CPR pauses.
+	 */
+	WRITE_ONCE(vsock->started, true);
+
 	/* Some packets may have been queued before the device was started,
 	 * let's kick the send worker to send them.
 	 */
@@ -728,6 +729,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 
 	vsock->guest_cid = 0; /* no CID assigned yet */
 	vsock->seqpacket_allow = false;
+	vsock->started = false;
 
 	atomic_set(&vsock->queued_replies, 0);
 
-- 
2.47.1

[PATCH v3 3/4] vhost/vsock: re-scan TX virtqueue on device start

[Andrey Drobyshev]

During QEMU CPR live-update (and VHOST_RESET_OWNER in general) the guest
keeps running while the host drops and later re-attaches vhost backends.
If the guest adds a buffer to the TX virtqueue (guest->host) and kicks
while the backend is temporarily NULL (between vhost_vsock_drop_backends()
and the next vhost_vsock_start()), then the kick is delivered to the
vhost worker, handle_tx_kick() sees a NULL backend and returns, and the
kick signal is consumed.  The buffer is then left in the ring.

Then upon device start vhost_vsock_start() only re-kicks the RX send
worker, never the TX VQ, so the buffer is processed only if the guest
happens to kick again.  But if the guest itself is now waiting for data
from the host, it will never kick TX VQ again, and we end up in a
deadlock.

The issue itself is pre-existing, but it only manifests during a brief
pause caused by VHOST_RESET_OWNER.  Namely, the deadlock is reproduced
during active host->guest socat data transfer under multiple consecutive
CPR live-update's.

To fix this, in vhost_vsock_start(), after kicking the RX send worker, also
queue the TX vq poll so any buffers the guest enqueued while we were paused
get scanned.

Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
Reviewed-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
---
 drivers/vhost/vsock.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index bec6bcfd885f..81d4f7209719 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -646,6 +646,13 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 	 */
 	vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work);
 
+	/*
+	 * Some packets might've also been queued in TX VQ.  That is the case
+	 * during the brief device pause caused by VHOST_RESET_OWNER.  Re-scan
+	 * the TX VQ here, mirroring the RX send-worker kick above.
+	 */
+	vhost_poll_queue(&vsock->vqs[VSOCK_VQ_TX].poll);
+
 	mutex_unlock(&vsock->dev.mutex);
 	return 0;
 
-- 
2.47.1

[PATCH v3 4/4] vhost/vsock: add VHOST_RESET_OWNER ioctl

[Andrey Drobyshev]

From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>

This ioctl is needed for QEMU's CPR (checkpoint-restore) migration of
the guest with vhost-vsock device.  For this to work, we need to reset
the device ownership on the source side by calling RESET_OWNER, and then
claim it on the dest side by calling SET_OWNER.  We expect not to lose any
AF_VSOCK connection while this happens.

RESET_OWNER keeps the guest CID hashed, so that connections survive. That
leaves the device reachable by a lockless send/cancel path while the worker
is being torn down: a concurrent vhost_transport_send_pkt() or
vhost_transport_cancel_pkt() can call vhost_vq_work_queue() as
vhost_workers_free() frees the worker.  That might cause a use-after-free
of vq->worker.  In addition, any work queued onto the dying worker leaves
VHOST_WORK_QUEUED stuck, stalling send_pkt_queue after resume.

Fence the send/cancel paths around the teardown: send_pkt()/cancel_pkt()
only kick the worker while the backend is alive.  And reset_owner() calls
synchronize_rcu() after drop_backends() so in-flight send/cancel finish
before the worker is freed.

Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
---
 drivers/vhost/vsock.c | 51 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 49 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 81d4f7209719..f0a0aa7d3200 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -318,7 +318,14 @@ vhost_transport_send_pkt(struct sk_buff *skb, struct net *net)
 		atomic_inc(&vsock->queued_replies);
 
 	virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb);
-	vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work);
+
+	/* Skip the kick once the backend is gone (stop/RESET_OWNER); the skb
+	 * stays queued and vhost_vsock_start() drains it. Pairs with the
+	 * synchronize_rcu() in vhost_vsock_reset_owner().
+	 */
+	if (data_race(vhost_vq_get_backend(&vsock->vqs[VSOCK_VQ_RX])))
+		vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX],
+				    &vsock->send_pkt_work);
 
 	rcu_read_unlock();
 	return len;
@@ -346,7 +353,15 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
 		int new_cnt;
 
 		new_cnt = atomic_sub_return(cnt, &vsock->queued_replies);
-		if (new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num)
+
+		/* Skip the kick once the backend is gone (stop/RESET_OWNER):
+		 * vhost_poll_queue() would touch the worker which is being freed
+		 * by teardown, e.g. on RESET_OWNER.  Pairs with the
+		 * synchronize_rcu() in vhost_vsock_reset_owner().  The TX VQ is
+		 * re-kicked by vhost_vsock_start().
+		 */
+		if (data_race(vhost_vq_get_backend(tx_vq)) &&
+		    new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num)
 			vhost_poll_queue(&tx_vq->poll);
 	}
 
@@ -903,6 +918,36 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
 	return -EFAULT;
 }
 
+static int vhost_vsock_reset_owner(struct vhost_vsock *vsock)
+{
+	struct vhost_iotlb *umem;
+	long err;
+
+	mutex_lock(&vsock->dev.mutex);
+	err = vhost_dev_check_owner(&vsock->dev);
+	if (err)
+		goto done;
+	umem = vhost_dev_reset_owner_prepare();
+	if (!umem) {
+		err = -ENOMEM;
+		goto done;
+	}
+	vhost_vsock_drop_backends(vsock);
+
+	/* Let in-flight send_pkt() callers stop touching the worker before the
+	 * flush + free below. Pairs with the backend check in
+	 * vhost_transport_send_pkt().
+	 */
+	synchronize_rcu();
+
+	vhost_vsock_flush(vsock);
+	vhost_dev_stop(&vsock->dev);
+	vhost_dev_reset_owner(&vsock->dev, umem);
+done:
+	mutex_unlock(&vsock->dev.mutex);
+	return err;
+}
+
 static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
 				  unsigned long arg)
 {
@@ -946,6 +991,8 @@ static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
 			return -EOPNOTSUPP;
 		vhost_set_backend_features(&vsock->dev, features);
 		return 0;
+	case VHOST_RESET_OWNER:
+		return vhost_vsock_reset_owner(vsock);
 	default:
 		mutex_lock(&vsock->dev.mutex);
 		r = vhost_dev_ioctl(&vsock->dev, ioctl, argp);
-- 
2.47.1

Re: [PATCH v3 4/4] vhost/vsock: add VHOST_RESET_OWNER ioctl

[Pavel Tikhomirov]

Reviewed-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>

On 6/25/26 17:54, Andrey Drobyshev wrote:
> From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
> 
> This ioctl is needed for QEMU's CPR (checkpoint-restore) migration of
> the guest with vhost-vsock device.  For this to work, we need to reset
> the device ownership on the source side by calling RESET_OWNER, and then
> claim it on the dest side by calling SET_OWNER.  We expect not to lose any
> AF_VSOCK connection while this happens.
> 
> RESET_OWNER keeps the guest CID hashed, so that connections survive. That
> leaves the device reachable by a lockless send/cancel path while the worker
> is being torn down: a concurrent vhost_transport_send_pkt() or
> vhost_transport_cancel_pkt() can call vhost_vq_work_queue() as
> vhost_workers_free() frees the worker.  That might cause a use-after-free
> of vq->worker.  In addition, any work queued onto the dying worker leaves
> VHOST_WORK_QUEUED stuck, stalling send_pkt_queue after resume.
> 
> Fence the send/cancel paths around the teardown: send_pkt()/cancel_pkt()
> only kick the worker while the backend is alive.  And reset_owner() calls
> synchronize_rcu() after drop_backends() so in-flight send/cancel finish
> before the worker is freed.
> 
> Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
> Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
> ---
>  drivers/vhost/vsock.c | 51 +++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 49 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
> index 81d4f7209719..f0a0aa7d3200 100644
> --- a/drivers/vhost/vsock.c
> +++ b/drivers/vhost/vsock.c
> @@ -318,7 +318,14 @@ vhost_transport_send_pkt(struct sk_buff *skb, struct net *net)
>  		atomic_inc(&vsock->queued_replies);
>  
>  	virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb);
> -	vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work);
> +
> +	/* Skip the kick once the backend is gone (stop/RESET_OWNER); the skb
> +	 * stays queued and vhost_vsock_start() drains it. Pairs with the
> +	 * synchronize_rcu() in vhost_vsock_reset_owner().
> +	 */
> +	if (data_race(vhost_vq_get_backend(&vsock->vqs[VSOCK_VQ_RX])))
> +		vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX],
> +				    &vsock->send_pkt_work);
>  
>  	rcu_read_unlock();
>  	return len;
> @@ -346,7 +353,15 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
>  		int new_cnt;
>  
>  		new_cnt = atomic_sub_return(cnt, &vsock->queued_replies);
> -		if (new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num)
> +
> +		/* Skip the kick once the backend is gone (stop/RESET_OWNER):
> +		 * vhost_poll_queue() would touch the worker which is being freed
> +		 * by teardown, e.g. on RESET_OWNER.  Pairs with the
> +		 * synchronize_rcu() in vhost_vsock_reset_owner().  The TX VQ is
> +		 * re-kicked by vhost_vsock_start().
> +		 */
> +		if (data_race(vhost_vq_get_backend(tx_vq)) &&
> +		    new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num)
>  			vhost_poll_queue(&tx_vq->poll);
>  	}
>  
> @@ -903,6 +918,36 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
>  	return -EFAULT;
>  }
>  
> +static int vhost_vsock_reset_owner(struct vhost_vsock *vsock)
> +{
> +	struct vhost_iotlb *umem;
> +	long err;
> +
> +	mutex_lock(&vsock->dev.mutex);
> +	err = vhost_dev_check_owner(&vsock->dev);
> +	if (err)
> +		goto done;
> +	umem = vhost_dev_reset_owner_prepare();
> +	if (!umem) {
> +		err = -ENOMEM;
> +		goto done;
> +	}
> +	vhost_vsock_drop_backends(vsock);
> +
> +	/* Let in-flight send_pkt() callers stop touching the worker before the
> +	 * flush + free below. Pairs with the backend check in
> +	 * vhost_transport_send_pkt().
> +	 */
> +	synchronize_rcu();
> +
> +	vhost_vsock_flush(vsock);
> +	vhost_dev_stop(&vsock->dev);
> +	vhost_dev_reset_owner(&vsock->dev, umem);
> +done:
> +	mutex_unlock(&vsock->dev.mutex);
> +	return err;
> +}
> +
>  static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
>  				  unsigned long arg)
>  {
> @@ -946,6 +991,8 @@ static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
>  			return -EOPNOTSUPP;
>  		vhost_set_backend_features(&vsock->dev, features);
>  		return 0;
> +	case VHOST_RESET_OWNER:
> +		return vhost_vsock_reset_owner(vsock);
>  	default:
>  		mutex_lock(&vsock->dev.mutex);
>  		r = vhost_dev_ioctl(&vsock->dev, ioctl, argp);

-- 
Best regards, Pavel Tikhomirov
Senior Software Developer, Virtuozzo.