[Qemu-devel] [PATCH] vhost_net: stop guest notifiers after backend

[Michael S. Tsirkin]

commit a9f98bb5ebe6fb1869321dcc58e72041ae626ad8
    vhost: multiqueue support
changed the order of stopping the device.
Previously vhost_dev_stop would disable backend and only afterwards,
unset guest notifiers.  We now unset guest notifiers while vhost is
still active. This can lose interrupts causing guest networking
to fail.

In particular, this has been observed during migration.

Reported-by: "Zhangjie (HZ)" <address@hidden>
Signed-off-by: Michael S. Tsirkin <address@hidden>
---

Zhangjie could you please confirm that this fixes
the problem for you?

 hw/net/vhost_net.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index f87c798..41d5158 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -308,6 +308,12 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs,
         goto err;
     }
 
+    r = k->set_guest_notifiers(qbus->parent, total_queues * 2, true);
+    if (r < 0) {
+        error_report("Error binding guest notifier: %d", -r);
+        goto err;
+    }
+
     for (i = 0; i < total_queues; i++) {
         r = vhost_net_start_one(get_vhost_net(ncs[i].peer), dev, i * 2);
 
@@ -316,12 +322,6 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs,
         }
     }
 
-    r = k->set_guest_notifiers(qbus->parent, total_queues * 2, true);
-    if (r < 0) {
-        error_report("Error binding guest notifier: %d", -r);
-        goto err;
-    }
-
     return 0;
 
 err:
@@ -339,16 +339,16 @@ void vhost_net_stop(VirtIODevice *dev, NetClientState 
*ncs,
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus);
     int i, r;
 
+    for (i = 0; i < total_queues; i++) {
+        vhost_net_stop_one(get_vhost_net(ncs[i].peer), dev);
+    }
+
     r = k->set_guest_notifiers(qbus->parent, total_queues * 2, false);
     if (r < 0) {
         fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", r);
         fflush(stderr);
     }
     assert(r >= 0);
-
-    for (i = 0; i < total_queues; i++) {
-        vhost_net_stop_one(get_vhost_net(ncs[i].peer), dev);
-    }
 }
 
 void vhost_net_cleanup(struct vhost_net *net)
-- 
MST