i40e/i40evf: improve Tx performance with a small tweak

Add a prefetch for the next Tx descriptor to be used when we know
there are more coming.

Change-ID: Ibb9acab11d508eec2db7da795df74debc16eeacb
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Jim Young <james.m.young@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -2616,6 +2616,8 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	    netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
 						   tx_ring->queue_index)))
 		writel(i, tx_ring->tail);
+	else
+		prefetchw(tx_desc + 1);
 
 	return;
 

drivers/net/ethernet/intel/i40evf/i40e_txrx.c

@@ -1841,6 +1841,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	    netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
 						   tx_ring->queue_index)))
 		writel(i, tx_ring->tail);
+	else
+		prefetchw(tx_desc + 1);
 
 	return;