[RFC,V1,6/6] tap: postload fix for cpr

Commit Message

Steven Sistare Aug. 30, 2024, 11:56 a.m. UTC

After cpr-exec of a multi-queue NIC, if any queues are unused, then
the corresponding tap is marked enabled in userland, but it is disabled
in the kernel for the fd that was preserved across exec.  One cannot call
tap_disable() during postload, because that eventually calls
IFF_DETACH_QUEUE, which fails because the queue is already detached.
Define tap_disable_postload to avoid IFF_DETACH_QUEUE.

Signed-off-by: Steve Sistare <[e-mail]>
---
 hw/net/virtio-net.c | 20 ++++++++++++++++++++
 include/net/tap.h   |  1 +
 net/tap.c           | 17 +++++++++++++++++
 3 files changed, 38 insertions(+)

Patch

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 8f30972..8dc0a02 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -728,6 +728,25 @@  static int peer_detach(VirtIONet *n, int index)
     return tap_disable(nc->peer);
 }
 
+/*
+ * Set the disabled flag on unused queue pairs after vmstate load, without
+ * calling IFF_DETACH_QUEUE, which fails because the queue is already detached.
+ */
+static void virtio_net_postload_queue_pairs(VirtIONet *n)
+{
+    int i;
+    MigMode mode = migrate_mode();
+
+    if (mode == MIG_MODE_CPR_EXEC || mode == MIG_MODE_CPR_TRANSFER) {
+        for (i = n->curr_queue_pairs; i < n->max_queue_pairs; i++) {
+            NetClientState *nc = qemu_get_subqueue(n->nic, i);
+            if (nc->peer && nc->peer->info->type == NET_CLIENT_DRIVER_TAP) {
+                tap_disable_postload(nc->peer);
+            }
+        }
+    }
+}
+
 static void virtio_net_set_queue_pairs(VirtIONet *n)
 {
     int i;
@@ -3056,6 +3075,7 @@  static int virtio_net_post_load_device(void *opaque, int version_id)
      */
     n->saved_guest_offloads = n->curr_guest_offloads;
 
+    virtio_net_postload_queue_pairs(n);
     virtio_net_set_queue_pairs(n);
 
     /* Find the first multicast entry in the saved MAC filter */
diff --git a/include/net/tap.h b/include/net/tap.h
index 5d58551..9456abe 100644
--- a/include/net/tap.h
+++ b/include/net/tap.h
@@ -30,6 +30,7 @@ 
 
 int tap_enable(NetClientState *nc);
 int tap_disable(NetClientState *nc);
+void tap_disable_postload(NetClientState *nc);
 
 int tap_get_fd(NetClientState *nc);
 
diff --git a/net/tap.c b/net/tap.c
index 4d57a53..abc4994 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -1060,3 +1060,20 @@  int tap_disable(NetClientState *nc)
         return ret;
     }
 }
+
+/*
+ * On cpr restart, the tap is marked enabled in userland, but it might be
+ * disabled in the kernel, and IFF_DETACH_QUEUE will fail because it is
+ * already detached.  This function disables without calling IFF_DETACH_QUEUE.
+ */
+void tap_disable_postload(NetClientState *nc)
+{
+    TAPState *s = DO_UPCAST(TAPState, nc, nc);
+
+    if (s->enabled == 0) {
+        return;
+    } else {
+        s->enabled = false;
+        tap_update_fd_handler(s);
+    }
+}