virtio_net: flush uncompleted TX on reset

If the backend could not transmit a packet right away for some reason,
the packet is queued for asynchronous sending. The corresponding vq
element is tracked in the async_tx.elem field of the VirtIONetQueue,
for later freeing when the transmission is complete.

If a reset happens before completion, virtio_net_tx_complete() will push
async_tx.elem back to the guest anyway, and we end up with the inuse flag
of the vq being equal to -1. The next call to virtqueue_pop() is then
likely to fail with "Virtqueue size exceeded".

This can be reproduced easily by starting a guest with an hubport backend
that is not connected to a functional network, eg,

 -device virtio-net-pci,netdev=hub0 -netdev hubport,id=hub0,hubid=0

and no other -netdev hubport,hubid=0 on the command line.

The appropriate fix is to ensure that such an asynchronous transmission
cannot survive a device reset. So for all queues, we first try to send
the packet again, and eventually we purge it if the backend still could
not deliver it.

CC: qemu-stable@nongnu.org
Reported-by: R. Nageswara Sastry <nasastry@in.ibm.com>
Buglink: https://github.com/open-power-host-os/qemu/issues/37
Signed-off-by: Greg Kurz <groug@kaod.org>
Tested-by: R. Nageswara Sastry <nasastry@in.ibm.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>

hw/net/virtio-net.c

@@ -427,6 +427,7 @@ static RxFilterInfo *virtio_net_query_rxfilter(NetClientState *nc)
 static void virtio_net_reset(VirtIODevice *vdev)
 {
     VirtIONet *n = VIRTIO_NET(vdev);
+    int i;
 
     /* Reset back to compatibility mode */
     n->promisc = 1;
@@ -450,6 +451,16 @@ static void virtio_net_reset(VirtIODevice *vdev)
     memcpy(&n->mac[0], &n->nic->conf->macaddr, sizeof(n->mac));
     qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);
     memset(n->vlans, 0, MAX_VLAN >> 3);
+
+    /* Flush any async TX */
+    for (i = 0;  i < n->max_queues; i++) {
+        NetClientState *nc = qemu_get_subqueue(n->nic, i);
+
+        if (nc->peer) {
+            qemu_flush_or_purge_queued_packets(nc->peer, true);
+            assert(!virtio_net_get_subqueue(nc)->async_tx.elem);
+        }
+    }
 }
 
 static void peer_test_vnet_hdr(VirtIONet *n)

include/net/net.h

@@ -153,6 +153,7 @@ ssize_t qemu_send_packet_async(NetClientState *nc, const uint8_t *buf,
                                int size, NetPacketSent *sent_cb);
 void qemu_purge_queued_packets(NetClientState *nc);
 void qemu_flush_queued_packets(NetClientState *nc);
+void qemu_flush_or_purge_queued_packets(NetClientState *nc, bool purge);
 void qemu_format_nic_info_str(NetClientState *nc, uint8_t macaddr[6]);
 bool qemu_has_ufo(NetClientState *nc);
 bool qemu_has_vnet_hdr(NetClientState *nc);

net/net.c

@@ -595,7 +595,6 @@ void qemu_purge_queued_packets(NetClientState *nc)
     qemu_net_queue_purge(nc->peer->incoming_queue, nc);
 }
 
-static
 void qemu_flush_or_purge_queued_packets(NetClientState *nc, bool purge)
 {
     nc->receive_disabled = 0;