[Devel] [PATCH 1/1] vhost/vsock: suppress EHOSTUNREACH fast-fail during CPR pause

[Denis V. Lunev]

The companion commit preserves ring state across VHOST_RESET_OWNER,
but QEMU still issues VHOST_VSOCK_SET_RUNNING(0) before RESET_OWNER,
nulling vq->private_data via vhost_vsock_drop_backends(). The
fast-fail in vhost_transport_send_pkt() from 4ff28534c799 then
rejects every host send with -EHOSTUNREACH until the destination
calls SET_RUNNING(1) -- the entire CPR window becomes a hard
outage for host AF_VSOCK clients (VSTOR-131956).

Add a cpr_paused flag set by vhost_vsock_stop() when the backend
was previously live, cleared by vhost_vsock_start(). When set,
vhost_transport_send_pkt() queues the skb instead of fast-failing;
the existing kick of send_pkt_work in vhost_vsock_start() drains
it on resume. A device that has never run keeps cpr_paused == false
and the boot-time fast-fail behaviour is preserved.

Set the flag before dropping backends so a concurrent sender never
observes (NULL, !paused).

https://virtuozzo.atlassian.net/browse/VSTOR-131956
Signed-off-by: Denis V. Lunev <den at openvz.org>

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply at anthropic.com>
---
 drivers/vhost/vsock.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 0a518c3d1596..82671fcc6769 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -57,6 +57,7 @@ struct vhost_vsock {
 
 	u32 guest_cid;
 	bool seqpacket_allow;
+	bool cpr_paused;	/* between stop and next start; queues sends */
 };
 
 static u32 vhost_transport_get_local_cid(void)
@@ -295,7 +296,9 @@ vhost_transport_send_pkt(struct sk_buff *skb)
 	 * 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.
 	 */
-	if (unlikely(!data_race(vhost_vq_get_backend(&vsock->vqs[VSOCK_VQ_RX])))) {
+	/* cpr_paused: queue across CPR; else NULL backend means not ready. */
+	if (unlikely(!data_race(vhost_vq_get_backend(&vsock->vqs[VSOCK_VQ_RX])) &&
+		     !READ_ONCE(vsock->cpr_paused))) {
 		rcu_read_unlock();
 		kfree_skb(skb);
 		return -EHOSTUNREACH;
@@ -610,9 +613,9 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 		mutex_unlock(&vq->mutex);
 	}
 
-	/* Some packets may have been queued before the device was started,
-	 * let's kick the send worker to send them.
-	 */
+	WRITE_ONCE(vsock->cpr_paused, false);
+
+	/* Drain anything queued while paused or before first start. */
 	vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work);
 
 	mutex_unlock(&vsock->dev.mutex);
@@ -653,6 +656,7 @@ static void vhost_vsock_drop_backends(struct vhost_vsock *vsock)
 static int vhost_vsock_stop(struct vhost_vsock *vsock, bool check_owner)
 {
 	int ret = 0;
+	bool was_running;
 
 	mutex_lock(&vsock->dev.mutex);
 
@@ -662,6 +666,12 @@ static int vhost_vsock_stop(struct vhost_vsock *vsock, bool check_owner)
 			goto err;
 	}
 
+	/* Set cpr_paused before dropping backends so concurrent senders
+	 * see (backend, !paused) or (NULL, paused), never (NULL, !paused).
+	 */
+	was_running = !!vhost_vq_get_backend(&vsock->vqs[VSOCK_VQ_RX]);
+	if (was_running)
+		WRITE_ONCE(vsock->cpr_paused, true);
 	vhost_vsock_drop_backends(vsock);
 err:
 	mutex_unlock(&vsock->dev.mutex);
-- 
2.51.0