net: dont update dev->trans_start in 10GB drivers

Followup of commits 9d21493b4beb8f918ba248032fefa393074a5e2b
and 08baf561083bc27a953aa087dd8a664bb2b88e8e
(net: tx scalability works : trans_start)
(net: txq_trans_update() helper)

Now that core network takes care of trans_start updates, dont do it
in drivers themselves, if possible. Multi queue drivers can
avoid one cache miss (on dev->trans_start) in their start_xmit()
handler.

Exceptions are NETIF_F_LLTX drivers (vxge & tehuti)

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 0 insertions, 1 deletions

diff --git a/drivers/net/mlx4/en_tx.c b/drivers/net/mlx4/en_tx.c
index ac6fc499b28..1c83a96fde3 100644
--- a/drivers/net/mlx4/en_tx.c
+++ b/drivers/net/mlx4/en_tx.c
@@ -819,7 +819,6 @@ int mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
         /* Ring doorbell! */
         wmb();
         writel(ring->doorbell_qpn, mdev->uar_map + MLX4_SEND_DOORBELL);
-        dev->trans_start = jiffies;
 
         /* Poll CQ here */
         mlx4_en_xmit_poll(priv, tx_ind);