[PATCH 4/4] net/mlx4_en: Use atomic counter to decide when queue is full

@@ -165,6 +165,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 	ring->last_nr_txbb = 1;
 	ring->poll_cnt = 0;
 	ring->blocked = 0;
+	atomic_set(&ring->inflight, 0);
 	memset(ring->tx_info, 0, ring->size * sizeof(struct mlx4_en_tx_info));
 	memset(ring->buf, 0, ring->buf_size);
 

@@ -364,15 +365,13 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 	wmb();
 	ring->cons += txbbs_skipped;
 	netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
+	atomic_sub(txbbs_skipped, &ring->inflight);
 
 	/* Wakeup Tx queue if this ring stopped it */
-	if (unlikely(ring->blocked)) {
-		if ((u32) (ring->prod - ring->cons) <=
-		     ring->size - HEADROOM - MAX_DESC_TXBBS) {
-			ring->blocked = 0;
-			netif_tx_wake_queue(ring->tx_queue);
-			priv->port_stats.wake_queue++;
-		}
+	if (unlikely(ring->blocked && txbbs_skipped > 0)) {
+		ring->blocked = 0;
+		netif_tx_wake_queue(ring->tx_queue);
+		priv->port_stats.wake_queue++;
 	}
 }
 

@@ -588,7 +587,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		vlan_tag = vlan_tx_tag_get(skb);
 
 	/* Check available TXBBs And 2K spare for prefetch */
-	if (unlikely(((int)(ring->prod - ring->cons)) >
+	if (unlikely(atomic_read(&ring->inflight) >
 		     ring->size - HEADROOM - MAX_DESC_TXBBS)) {
 		/* every full Tx ring stops queue */
 		netif_tx_stop_queue(ring->tx_queue);

@@ -710,6 +709,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	ring->prod += nr_txbb;
+	atomic_add(nr_txbb, &ring->inflight);
 
 	/* If we used a bounce buffer then copy descriptor back into place */
 	if (bounce)

@@ -257,6 +257,7 @@ struct mlx4_en_tx_ring {
 	struct mlx4_bf bf;
 	bool bf_enabled;
 	struct netdev_queue *tx_queue;
+	atomic_t inflight;
 };
 
 struct mlx4_en_rx_desc {