virtio_net: move tx vq operation under tx queue lock

It's unsafe to operate a vq from multiple threads.
Unfortunately this is exactly what we do when invoking
clean tx poll from rx napi.
Same happens with napi-tx even without the
opportunistic cleaning from the receive interrupt: that races
with processing the vq in start_xmit.

As a fix move everything that deals with the vq to under tx lock.

Fixes: b92f1e67 ("virtio-net: transmit napi")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

drivers/net/virtio_net.c

@@ -1592,6 +1592,8 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 	struct virtnet_info *vi = sq->vq->vdev->priv;
 	unsigned int index = vq2txq(sq->vq);
 	struct netdev_queue *txq;
+	int opaque;
+	bool done;
 
 	if (unlikely(is_xdp_raw_buffer_queue(vi, index))) {
 		/* We don't need to enable cb for XDP */
@@ -1601,10 +1603,28 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 
 	txq = netdev_get_tx_queue(vi->dev, index);
 	__netif_tx_lock(txq, raw_smp_processor_id());
+	virtqueue_disable_cb(sq->vq);
 	free_old_xmit_skbs(sq, true);
+
+	opaque = virtqueue_enable_cb_prepare(sq->vq);
+
+	done = napi_complete_done(napi, 0);
+
+	if (!done)
+		virtqueue_disable_cb(sq->vq);
+
 	__netif_tx_unlock(txq);
 
-	virtqueue_napi_complete(napi, sq->vq, 0);
+	if (done) {
+		if (unlikely(virtqueue_poll(sq->vq, opaque))) {
+			if (napi_schedule_prep(napi)) {
+				__netif_tx_lock(txq, raw_smp_processor_id());
+				virtqueue_disable_cb(sq->vq);
+				__netif_tx_unlock(txq);
+				__napi_schedule(napi);
+			}
+		}
+	}
 
 	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
 		netif_tx_wake_queue(txq);