[PATCH QEMU HCI-8.1 v2 22/24] VZ: migration/cpr-exec: take the vhost-net devices back if exec fails

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

Right before execve(), cpr_exec_cb() releases the kernel vhost-net
devices with VHOST_RESET_OWNER, so that the new QEMU can take them.  If
execve() fails, the VM goes on in the old QEMU, but nobody takes the
devices back: the kernel refuses the ioctls of the next
vhost_net_start(), and the guest is left without network.

Take them back with VHOST_SET_OWNER right after the exec failure.  The
devices are stopped at that point, and vhost_net_start() sets up the
rest again when the VM resumes.  vhost-vsock does the same in its CPR
notifier.

Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com>
---
 hw/net/vhost_net.c      | 25 +++++++++++++++++++++++++
 include/net/vhost_net.h |  1 +
 migration/cpr-exec.c    |  3 +++
 3 files changed, 29 insertions(+)

diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 56c697f4bcd..58233788ebb 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -599,6 +599,31 @@ void vhost_net_cpr_reset_owners(void)
     }
 }
 
+/*
+ * Take the ownership back when the exec fails and the VM goes on in the
+ * old QEMU.  VHOST_RESET_OWNER has reset the kernel device, but the devices
+ * are stopped, and vhost_net_start() sets everything up again when the VM
+ * resumes.
+ */
+void vhost_net_cpr_set_owners(void)
+{
+    NetClientState *nc;
+
+    QTAILQ_FOREACH(nc, &net_clients, next) {
+        VHostNetState *net = get_vhost_net(nc);
+
+        if (net && net->dev.vhost_ops &&
+            net->dev.vhost_ops->backend_type == VHOST_BACKEND_TYPE_KERNEL) {
+            int r = vhost_dev_set_owner(&net->dev);
+
+            if (r < 0 && r != -ENOSYS) {
+                warn_report("cpr: failed to set vhost-net owner for %s: %s",
+                            nc->name, strerror(-r));
+            }
+        }
+    }
+}
+
 VHostNetState *get_vhost_net(NetClientState *nc)
 {
     if (!nc) {
diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h
index 39ce7ad0e3d..cdfefa81500 100644
--- a/include/net/vhost_net.h
+++ b/include/net/vhost_net.h
@@ -90,4 +90,5 @@ 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_set_owners(void);
 #endif
diff --git a/migration/cpr-exec.c b/migration/cpr-exec.c
index cb962ce7252..9a428b43093 100644
--- a/migration/cpr-exec.c
+++ b/migration/cpr-exec.c
@@ -243,6 +243,9 @@ static void cpr_exec_cb(void *opaque)
     error_free(err);
     err = NULL;
 
+    /* Still the same mm, take the vhost-net devices back */
+    vhost_net_cpr_set_owners();
+
 fail:
     g_clear_pointer(&argv, g_strfreev);
     cpr_exec_unpreserve_fds();

-- 
2.47.1