[PATCH QEMU HCI-8.1 v5 31/36] VZ: migration/cpr-exec: don't exec if a vhost-net device can't be released

[Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>]

vhost_net_cpr_reset_owners() only warns when VHOST_RESET_OWNER fails for
a device, and the exec goes on.  But the new QEMU can't take such a
device: it is still owned by the old mm, so VHOST_SET_OWNER fails with
EBUSY, and the guest is left without network after the update.

Stop at the first device that can't be released and abort the cpr-exec
instead.  The VM goes on in the old QEMU, with the devices released so
far taken back.  vhost-vsock already does that in its pre_save.

Fixes: 1278e4830052 ("VZ: migration/cpr-exec: vhost-net: send RESET_OWNER before cpr-exec")
Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
---
 hw/net/vhost_net.c      | 19 +++++++++++++------
 include/net/vhost_net.h |  2 +-
 migration/cpr-exec.c    |  7 ++++++-
 3 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index fae6b060c6f..9110dc43d23 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -579,8 +579,12 @@ void vhost_net_config_mask(VHostNetState *net, VirtIODevice *dev, bool mask)
  * EBUSY.  Called right before execve(), when the VM is stopped and the
  * devices have already been stopped, so nothing is in flight.  The device is
  * fully re-initialized from the migrated state by the new QEMU.
+ *
+ * Stops at the first device that can't be released, since the new QEMU
+ * couldn't take it.  The caller then takes back the ones already released
+ * with vhost_net_cpr_set_owners().
  */
-void vhost_net_cpr_reset_owners(void)
+void vhost_net_cpr_reset_owners(Error **errp)
 {
     NetClientState *nc;
 
@@ -591,12 +595,15 @@ void vhost_net_cpr_reset_owners(void)
             net->dev.vhost_ops->backend_type == VHOST_BACKEND_TYPE_KERNEL) {
             int r = vhost_dev_reset_owner(&net->dev);
 
-            if (r < 0 && r != -ENOSYS) {
-                warn_report("cpr: failed to reset vhost-net owner for %s: %s",
-                            nc->name, strerror(-r));
-            } else if (r == 0) {
-                net->cpr_owner_reset = true;
+            if (r == -ENOSYS) {
+                continue;
+            }
+            if (r < 0) {
+                error_setg_errno(errp, -r, "cpr: failed to reset vhost-net "
+                                 "owner for %s", nc->name);
+                return;
             }
+            net->cpr_owner_reset = true;
         }
     }
 }
diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h
index cdfefa81500..679edefa1d3 100644
--- a/include/net/vhost_net.h
+++ b/include/net/vhost_net.h
@@ -89,6 +89,6 @@ int vhost_net_virtqueue_restart(VirtIODevice *vdev, NetClientState *nc,
 
 void vhost_net_save_acked_features(NetClientState *nc);
 
-void vhost_net_cpr_reset_owners(void);
+void vhost_net_cpr_reset_owners(Error **errp);
 void vhost_net_cpr_set_owners(void);
 #endif
diff --git a/migration/cpr-exec.c b/migration/cpr-exec.c
index e4ea160698c..b41dcc46494 100644
--- a/migration/cpr-exec.c
+++ b/migration/cpr-exec.c
@@ -230,7 +230,10 @@ static void cpr_exec_cb(void *opaque)
      * Hand the preserved vhost-net devices over to the new QEMU: they are
      * still owned by this mm, which is about to be replaced by execve().
      */
-    vhost_net_cpr_reset_owners();
+    vhost_net_cpr_reset_owners(&err);
+    if (err) {
+        goto fail_with_err;
+    }
 
     trace_cpr_exec();
     execvp(argv[0], argv);
@@ -240,6 +243,8 @@ static void cpr_exec_cb(void *opaque)
      * or the system is very short on resources.
      */
     error_setg_errno(&err, errno, "execvp %s failed", argv[0]);
+
+fail_with_err:
     error_report_err(error_copy(err));
     migrate_set_state(&s->state, s->state, MIGRATION_STATUS_FAILED);
     migrate_set_error(s, err);

-- 
2.47.1