[PATCH RFC v2 2/3] virtio_net: bql

@@ -219,13 +219,15 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
 	return p;
 }
 
-static unsigned int free_old_xmit_skbs(struct send_queue *sq, int budget)
+static unsigned int free_old_xmit_skbs(struct netdev_queue *txq,
+				       struct send_queue *sq, int budget)
 {
 	struct sk_buff *skb;
 	unsigned int len;
 	struct virtnet_info *vi = sq->vq->vdev->priv;
 	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
 	unsigned int packets = 0;
+	unsigned int bytes = 0;
 
 	while (packets < budget &&
 	       (skb = virtqueue_get_buf(sq->vq, &len)) != NULL) {

@@ -233,6 +235,7 @@ static unsigned int free_old_xmit_skbs(struct send_queue *sq, int budget)
 
 		u64_stats_update_begin(&stats->tx_syncp);
 		stats->tx_bytes += skb->len;
+		bytes += skb->len;
 		stats->tx_packets++;
 		u64_stats_update_end(&stats->tx_syncp);
 

@@ -240,6 +243,8 @@ static unsigned int free_old_xmit_skbs(struct send_queue *sq, int budget)
 		packets++;
 	}
 
+	netdev_tx_completed_queue(txq, packets, bytes);
+
 	return packets;
 }
 

@@ -810,7 +815,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 again:
 	__netif_tx_lock(txq, smp_processor_id());
 	virtqueue_disable_cb(sq->vq);
-	sent += free_old_xmit_skbs(sq, budget - sent);
+	sent += free_old_xmit_skbs(txq, sq, budget - sent);
 
 	if (sent < budget) {
 		enable_done = virtqueue_enable_cb_delayed(sq->vq);

@@ -962,12 +967,13 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
 	bool kick = !skb->xmit_more;
 	bool stopped;
+	unsigned int bytes = skb->len;
 
 	virtqueue_disable_cb(sq->vq);
 
 	/* We are going to push one skb.
 	 * Try to pop one off to free space for it. */
-	free_old_xmit_skbs(sq, 1);
+	free_old_xmit_skbs(txq, sq, 1);
 
 	/* Try to transmit */
 	err = xmit_skb(sq, skb);

@@ -983,6 +989,12 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
+	netdev_tx_sent_queue(txq, bytes);
+
+	/* Kick early so device can process descriptors in parallel with us. */
+	if (kick)
+		virtqueue_kick(sq->vq);
+
 	/* Apparently nice girls don't return TX_BUSY; stop the queue
 	 * before it gets out of hand.  Naturally, this wastes entries. */
 	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {

@@ -997,7 +1009,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
 		/* More just got used, free them then recheck. */
-		free_old_xmit_skbs(sq, qsize);
+		free_old_xmit_skbs(txq, sq, qsize);
 		if (stopped && sq->vq->num_free >= 2+MAX_SKB_FRAGS)
 			netif_start_subqueue(dev, qnum);
 	}