vhost-user: return failure if backend crash when live migration

Live migration should be terminated if the vhost-user backend crashes
before the migration completes.

Specifically, since the vhost device will be stopped when VM is stopped
before the end of the live migration, in current implementation if the
backend crashes, vhost-user device set_status() won't return failure,
live migration won't perceive the disconnection between QEMU and the
backend.

When the VM is migrated to the destination, the inflight IO will be
resubmitted, and if the IO was completed out of order before, it will
cause IO error.

To fix this issue:
1. Add the return value to set_status() for VirtioDeviceClass.
  a. For the vhost-user device, return failure when the backend crashes.
  b. For other virtio devices, always return 0.
2. Return failure if vhost_dev_stop() failed for vhost-user device.

If QEMU loses connection with the vhost-user backend, virtio set_status()
can return failure to the upper layer, migration_completion() can handle
the error, terminate the live migration, and restore the VM, so that
inflight IO can be completed normally.

Signed-off-by: Haoqian He <haoqian.he@smartx.com>
Message-Id: <20250416024729.3289157-4-haoqian.he@smartx.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

1 files changed, 14 insertions, 9 deletions

diff --git a/hw/virtio/vhost-user-base.c b/hw/virtio/vhost-user-base.c
index 77143320a2..ff67a020b4 100644
--- a/hw/virtio/vhost-user-base.c
+++ b/hw/virtio/vhost-user-base.c
@@ -66,7 +66,7 @@ err_host_notifiers:
     vhost_dev_disable_notifiers(&vub->vhost_dev, vdev);
 }
 
-static void vub_stop(VirtIODevice *vdev)
+static int vub_stop(VirtIODevice *vdev)
 {
     VHostUserBase *vub = VHOST_USER_BASE(vdev);
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
@@ -74,34 +74,39 @@ static void vub_stop(VirtIODevice *vdev)
     int ret;
 
     if (!k->set_guest_notifiers) {
-        return;
+        return 0;
     }
 
-    vhost_dev_stop(&vub->vhost_dev, vdev, true);
+    ret = vhost_dev_stop(&vub->vhost_dev, vdev, true);
 
-    ret = k->set_guest_notifiers(qbus->parent, vub->vhost_dev.nvqs, false);
-    if (ret < 0) {
+    if (k->set_guest_notifiers(qbus->parent, vub->vhost_dev.nvqs, false) < 0) {
         error_report("vhost guest notifier cleanup failed: %d", ret);
-        return;
+        return -1;
     }
 
     vhost_dev_disable_notifiers(&vub->vhost_dev, vdev);
+    return ret;
 }
 
-static void vub_set_status(VirtIODevice *vdev, uint8_t status)
+static int vub_set_status(VirtIODevice *vdev, uint8_t status)
 {
     VHostUserBase *vub = VHOST_USER_BASE(vdev);
     bool should_start = virtio_device_should_start(vdev, status);
 
     if (vhost_dev_is_started(&vub->vhost_dev) == should_start) {
-        return;
+        return 0;
     }
 
     if (should_start) {
         vub_start(vdev);
     } else {
-        vub_stop(vdev);
+        int ret;
+        ret = vub_stop(vdev);
+        if (ret < 0) {
+            return ret;
+        }
     }
+    return 0;
 }
 
 /*