net/mlx4_en: Move queue stopped/waked counters to be per ring

Give accurate counters and avoids cache misses when several rings
update the counters of stop/wake queue.
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: NAmir Vadai <amirv@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx4/en_port.c

@@ -148,10 +148,16 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	stats->tx_packets = 0;
 	stats->tx_bytes = 0;
 	priv->port_stats.tx_chksum_offload = 0;
+	priv->port_stats.queue_stopped = 0;
+	priv->port_stats.wake_queue = 0;
+
 	for (i = 0; i < priv->tx_ring_num; i++) {
 		stats->tx_packets += priv->tx_ring[i]->packets;
 		stats->tx_bytes += priv->tx_ring[i]->bytes;
 		priv->port_stats.tx_chksum_offload += priv->tx_ring[i]->tx_csum;
+		priv->port_stats.queue_stopped +=
+			priv->tx_ring[i]->queue_stopped;
+		priv->port_stats.wake_queue += priv->tx_ring[i]->wake_queue;
 	}
 
 	stats->rx_errors = be64_to_cpu(mlx4_en_stats->PCS) +

drivers/net/ethernet/mellanox/mlx4/en_tx.c

@@ -445,7 +445,7 @@ static int mlx4_en_process_tx_cq(struct net_device *dev,
 	 */
 	if (netif_tx_queue_stopped(ring->tx_queue) && txbbs_skipped > 0) {
 		netif_tx_wake_queue(ring->tx_queue);
-		priv->port_stats.wake_queue++;
+		ring->wake_queue++;
 	}
 	return done;
 }
@@ -691,7 +691,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		     ring->size - HEADROOM - MAX_DESC_TXBBS)) {
 		/* every full Tx ring stops queue */
 		netif_tx_stop_queue(ring->tx_queue);
-		priv->port_stats.queue_stopped++;
+		ring->queue_stopped++;
 
 		/* If queue was emptied after the if, and before the
 		 * stop_queue - need to wake the queue, or else it will remain
@@ -704,7 +704,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (unlikely(((int)(ring->prod - ring->cons)) <=
 			     ring->size - HEADROOM - MAX_DESC_TXBBS)) {
 			netif_tx_wake_queue(ring->tx_queue);
-			priv->port_stats.wake_queue++;
+			ring->wake_queue++;
 		} else {
 			return NETDEV_TX_BUSY;
 		}

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -274,6 +274,8 @@ struct mlx4_en_tx_ring {
 	unsigned long bytes;
 	unsigned long packets;
 	unsigned long tx_csum;
+	unsigned long queue_stopped;
+	unsigned long wake_queue;
 	struct mlx4_bf bf;
 	bool bf_enabled;
 	struct netdev_queue *tx_queue;