When preserving a vhost fd using CPR, call VHOST_RESET_OWNER prior to CPR
in old QEMU.  Otherwise, new QEMU will fail when it calls VHOST_SET_OWNER
during vhost_dev_init.

Signed-off-by: Mark Kanda <mark.kanda@oracle.com>
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
---
 include/hw/virtio/vhost.h |  1 +
 hw/virtio/vhost.c         | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+)

diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index 38800a7..88a4838 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -132,6 +132,7 @@ struct vhost_dev {
     QLIST_ENTRY(vhost_dev) logdev_entry;
     QLIST_HEAD(, vhost_iommu) iommu_list;
     IOMMUNotifier n;
+    NotifierWithReturn cpr_transfer_notifier;
     const VhostDevConfigOps *config_ops;
 };
 
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index fc43853..a562e0c 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -24,6 +24,7 @@
 #include "standard-headers/linux/vhost_types.h"
 #include "hw/virtio/virtio-bus.h"
 #include "hw/mem/memory-device.h"
+#include "migration/misc.h"
 #include "migration/blocker.h"
 #include "migration/qemu-file-types.h"
 #include "system/dma.h"
@@ -1506,6 +1507,32 @@ static void vhost_virtqueue_cleanup(struct vhost_virtqueue *vq)
     }
 }
 
+static int vhost_cpr_notifier(NotifierWithReturn *notifier,
+                              MigrationEvent *e, Error **errp)
+{
+    struct vhost_dev *dev;
+    int r;
+
+    dev = container_of(notifier, struct vhost_dev, cpr_transfer_notifier);
+
+    if (dev->vhost_ops->backend_type != VHOST_BACKEND_TYPE_KERNEL) {
+        return 0;
+    }
+
+    if (e->type == MIG_EVENT_PRECOPY_SETUP) {
+        r = dev->vhost_ops->vhost_reset_device(dev);
+        if (r < 0) {
+            VHOST_OPS_DEBUG(r, "vhost_reset_device failed");
+        }
+    } else if (e->type == MIG_EVENT_PRECOPY_FAILED) {
+        r = dev->vhost_ops->vhost_set_owner(dev);
+        if (r < 0) {
+            VHOST_OPS_DEBUG(r, "vhost_set_owner failed");
+        }
+    }
+    return 0;
+}
+
 int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
                    VhostBackendType backend_type, uint32_t busyloop_timeout,
                    Error **errp)
@@ -1516,6 +1543,7 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
 
     hdev->vdev = NULL;
     hdev->migration_blocker = NULL;
+    hdev->cpr_transfer_notifier.notify = NULL;
 
     r = vhost_set_backend_type(hdev, backend_type);
     assert(r >= 0);
@@ -1616,6 +1644,9 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
     hdev->log_enabled = false;
     hdev->started = false;
     memory_listener_register(&hdev->memory_listener, &address_space_memory);
+    migration_add_notifier_mode(&hdev->cpr_transfer_notifier,
+                                vhost_cpr_notifier,
+                                MIG_MODE_CPR_TRANSFER);
     QLIST_INSERT_HEAD(&vhost_devices, hdev, entry);
 
     /*
@@ -1672,6 +1703,7 @@ void vhost_dev_cleanup(struct vhost_dev *hdev)
         QLIST_REMOVE(hdev, entry);
     }
     migrate_del_blocker(&hdev->migration_blocker);
+    migration_remove_notifier(&hdev->cpr_transfer_notifier);
     g_free(hdev->mem);
     g_free(hdev->mem_sections);
     if (hdev->vhost_ops) {
-- 
1.8.3.1

On 17.07.25 21:39, Steve Sistare wrote:
> When preserving a vhost fd using CPR, call VHOST_RESET_OWNER prior to CPR
> in old QEMU.  Otherwise, new QEMU will fail when it calls VHOST_SET_OWNER
> during vhost_dev_init.
> 

But, is there a benefit in passing vhostnet fd to target QEMU? As I understand,
we anyway need a full renitialization of vhost device, as it's just reset
on RESET_OWNER. So, is passing this fd better then reopen /dev/vhost-net
on target?


-- 
Best regards,
Vladimir

On 8/27/2025 7:29 AM, Vladimir Sementsov-Ogievskiy wrote:
> On 17.07.25 21:39, Steve Sistare wrote:
>> When preserving a vhost fd using CPR, call VHOST_RESET_OWNER prior to CPR
>> in old QEMU.  Otherwise, new QEMU will fail when it calls VHOST_SET_OWNER
>> during vhost_dev_init.
>>
> 
> But, is there a benefit in passing vhostnet fd to target QEMU? As I understand,
> we anyway need a full renitialization of vhost device, as it's just reset
> on RESET_OWNER. So, is passing this fd better then reopen /dev/vhost-net
> on target?

Some orchestraters pass pre-opened tap and vhost fd's on the qemu command line
when initially starting qemu.  For that model, preserving the open fd's in new
QEMU is the most natural solution.

- Steve