net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers

Add two helpers so that drivers do not have to care of BQL being
available or not.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jim Davis <jim.epost@gmail.com>
Fixes: 29d40c903247 ("net/mlx4_en: Use prefetch in tx path")
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -392,7 +392,8 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 	if (!priv->port_up)
 		return true;
 
-	prefetchw(&ring->tx_queue->dql.limit);
+	netdev_txq_bql_complete_prefetchw(ring->tx_queue);
+
 	index = cons_index & size_mask;
 	cqe = mlx4_en_get_cqe(buf, index, priv->cqe_size) + factor;
 	last_nr_txbb = ACCESS_ONCE(ring->last_nr_txbb);
@@ -737,7 +738,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		vlan_tag = vlan_tx_tag_get(skb);
 
 
-	prefetchw(&ring->tx_queue->dql);
+	netdev_txq_bql_enqueue_prefetchw(ring->tx_queue);
 
 	/* Track current inflight packets for performance analysis */
 	AVG_PERF_COUNTER(priv->pstats.inflight_avg,

include/linux/netdevice.h

@@ -30,6 +30,7 @@
 #include <linux/bug.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
+#include <linux/prefetch.h>
 #include <asm/cache.h>
 #include <asm/byteorder.h>
 
@@ -2480,6 +2481,34 @@ netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue)
 	return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN;
 }
 
+/**
+ *	netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write
+ *	@dev_queue: pointer to transmit queue
+ *
+ * BQL enabled drivers might use this helper in their ndo_start_xmit(),
+ * to give appropriate hint to the cpu.
+ */
+static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue)
+{
+#ifdef CONFIG_BQL
+	prefetchw(&dev_queue->dql.num_queued);
+#endif
+}
+
+/**
+ *	netdev_txq_bql_complete_prefetchw - prefetch bql data for write
+ *	@dev_queue: pointer to transmit queue
+ *
+ * BQL enabled drivers might use this helper in their TX completion path,
+ * to give appropriate hint to the cpu.
+ */
+static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue)
+{
+#ifdef CONFIG_BQL
+	prefetchw(&dev_queue->dql.limit);
+#endif
+}
+
 static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
 					unsigned int bytes)
 {