提交 489ce7a4 编写于 作者: J Jesse Brandeburg 提交者: Jeff Kirsher

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: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
上级 c78b953e
......@@ -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;
......
......@@ -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;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册