net/mlx4_en: Avoid calling bswap in tx fast path

- doorbell_qpn is stored in the cpu_to_be32() way to avoid bswap() in fast
  path.
- mdev->mr.key stored in ring->mr_key to also avoid bswap() and access to
  cold cache line.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -195,7 +195,8 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 	memset(ring->buf, 0, ring->buf_size);
 
 	ring->qp_state = MLX4_QP_STATE_RST;
-	ring->doorbell_qpn = ring->qp.qpn << 8;
+	ring->doorbell_qpn = cpu_to_be32(ring->qp.qpn << 8);
+	ring->mr_key = cpu_to_be32(mdev->mr.key);
 
 	mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn,
 				ring->cqn, user_prio, &ring->context);
@@ -654,7 +655,6 @@ static void mlx4_bf_copy(void __iomem *dst, const void *src,
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	struct mlx4_en_dev *mdev = priv->mdev;
 	struct device *ddev = priv->ddev;
 	struct mlx4_en_tx_ring *ring;
 	struct mlx4_en_tx_desc *tx_desc;
@@ -769,7 +769,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 				goto tx_drop_unmap;
 
 			data->addr = cpu_to_be64(dma);
-			data->lkey = cpu_to_be32(mdev->mr.key);
+			data->lkey = ring->mr_key;
 			wmb();
 			data->byte_count = cpu_to_be32(skb_frag_size(frag));
 			--data;
@@ -787,7 +787,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 				goto tx_drop_unmap;
 
 			data->addr = cpu_to_be64(dma);
-			data->lkey = cpu_to_be32(mdev->mr.key);
+			data->lkey = ring->mr_key;
 			wmb();
 			data->byte_count = cpu_to_be32(byte_count);
 		}
@@ -879,9 +879,12 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	send_doorbell = !skb->xmit_more || netif_xmit_stopped(ring->tx_queue);
 
+	real_size = (real_size / 16) & 0x3f;
+
 	if (ring->bf_enabled && desc_size <= MAX_BF && !bounce &&
 	    !vlan_tx_tag_present(skb) && send_doorbell) {
-		tx_desc->ctrl.bf_qpn |= cpu_to_be32(ring->doorbell_qpn);
+		tx_desc->ctrl.bf_qpn = ring->doorbell_qpn |
+				       cpu_to_be32(real_size);
 
 		op_own |= htonl((bf_index & 0xffff) << 8);
 		/* Ensure new descriptor hits memory
@@ -911,7 +914,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		tx_desc->ctrl.owner_opcode = op_own;
 		if (send_doorbell) {
 			wmb();
-			iowrite32be(ring->doorbell_qpn,
+			iowrite32(ring->doorbell_qpn,
 				  ring->bf.uar->map + MLX4_SEND_DOORBELL);
 		} else {
 			ring->xmit_more++;

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

@@ -279,7 +279,8 @@ struct mlx4_en_tx_ring {
 	u16			stride;
 	u16			cqn;	/* index of port CQ associated with this ring */
 	u32			buf_size;
-	u32			doorbell_qpn;
+	__be32			doorbell_qpn;
+	__be32			mr_key;
 	void			*buf;
 	struct mlx4_en_tx_info	*tx_info;
 	u8			*bounce_buf;