net/mlx4_en: Configure the XPS queue mapping on driver load

Only TX rings of User Piority 0 are mapped.
TX rings of other UP's are using UP 0 mapping.
XPS is not in use when num_tc is set.

Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -1910,8 +1910,10 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 				      prof->tx_ring_size, i, TX, node))
 			goto err;
 
-		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i], priv->base_tx_qpn + i,
-					   prof->tx_ring_size, TXBB_SIZE, node))
+		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i],
+					   priv->base_tx_qpn + i,
+					   prof->tx_ring_size, TXBB_SIZE,
+					   node, i))
 			goto err;
 	}
 

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

@@ -55,7 +55,7 @@ MODULE_PARM_DESC(inline_thold, "threshold for using inline data");
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring, int qpn, u32 size,
-			   u16 stride, int node)
+			   u16 stride, int node, int queue_index)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_tx_ring *ring;
@@ -140,6 +140,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 		ring->bf_enabled = true;
 
 	ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type;
+	ring->queue_index = queue_index;
+
+	if (queue_index < priv->num_tx_rings_p_up && cpu_online(queue_index))
+		cpumask_set_cpu(queue_index, &ring->affinity_mask);
 
 	*pring = ring;
 	return 0;
@@ -206,6 +210,9 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
 			       &ring->qp, &ring->qp_state);
+	if (!user_prio && cpu_online(ring->queue_index))
+		netif_set_xps_queue(priv->dev, &ring->affinity_mask,
+				    ring->queue_index);
 
 	return err;
 }

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

@@ -255,6 +255,8 @@ struct mlx4_en_tx_ring {
 	u16 poll_cnt;
 	struct mlx4_en_tx_info *tx_info;
 	u8 *bounce_buf;
+	u8 queue_index;
+	cpumask_t affinity_mask;
 	u32 last_nr_txbb;
 	struct mlx4_qp qp;
 	struct mlx4_qp_context context;
@@ -719,7 +721,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring,
-			   int qpn, u32 size, u16 stride, int node);
+			   int qpn, u32 size, u16 stride,
+			   int node, int queue_index);
 void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_tx_ring **pring);
 int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,