1 files changed, 27 insertions, 12 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 454d9fea640e..5980d3fe597c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -66,6 +66,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->size = size;
 	ring->size_mask = size - 1;
 	ring->stride = stride;
+	ring->full_size = ring->size - HEADROOM - MAX_DESC_TXBBS;
 
 	tmp = size * sizeof(struct mlx4_en_tx_info);
 	ring->tx_info = kmalloc_node(tmp, GFP_KERNEL | __GFP_NOWARN, node);
@@ -137,8 +138,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	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);
+	if (queue_index < priv->num_tx_rings_p_up)
+		cpumask_set_cpu_local_first(queue_index,
+					    priv->mdev->dev->numa_node,
+					    &ring->affinity_mask);
 
 	*pring = ring;
 	return 0;
@@ -205,7 +208,7 @@ 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))
+	if (!cpumask_empty(&ring->affinity_mask))
 		netif_set_xps_queue(priv->dev, &ring->affinity_mask,
 				    ring->queue_index);
 
@@ -221,6 +224,11 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 		       MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp);
 }
 
+static inline bool mlx4_en_is_tx_ring_full(struct mlx4_en_tx_ring *ring)
+{
+	return ring->prod - ring->cons > ring->full_size;
+}
+
 static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 			      struct mlx4_en_tx_ring *ring, int index,
 			      u8 owner)
@@ -463,11 +471,10 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 
 	netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
 
-	/*
-	 * Wakeup Tx queue if this stopped, and at least 1 packet
-	 * was completed
+	/* Wakeup Tx queue if this stopped, and ring is not full.
 	 */
-	if (netif_tx_queue_stopped(ring->tx_queue) && txbbs_skipped > 0) {
+	if (netif_tx_queue_stopped(ring->tx_queue) &&
+	    !mlx4_en_is_tx_ring_full(ring)) {
 		netif_tx_wake_queue(ring->tx_queue);
 		ring->wake_queue++;
 	}
@@ -911,8 +918,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 
 	/* Check available TXBBs And 2K spare for prefetch */
-	stop_queue = (int)(ring->prod - ring_cons) >
-		      ring->size - HEADROOM - MAX_DESC_TXBBS;
+	stop_queue = mlx4_en_is_tx_ring_full(ring);
 	if (unlikely(stop_queue)) {
 		netif_tx_stop_queue(ring->tx_queue);
 		ring->queue_stopped++;
@@ -954,7 +960,17 @@ 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();
-			iowrite32(ring->doorbell_qpn,
+			/* Since there is no iowrite*_native() that writes the
+			 * value as is, without byteswapping - using the one
+			 * the doesn't do byteswapping in the relevant arch
+			 * endianness.
+			 */
+#if defined(__LITTLE_ENDIAN)
+			iowrite32(
+#else
+			iowrite32be(
+#endif
+				  ring->doorbell_qpn,
 				  ring->bf.uar->map + MLX4_SEND_DOORBELL);
 		} else {
 			ring->xmit_more++;
@@ -971,8 +987,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		smp_rmb();
 
 		ring_cons = ACCESS_ONCE(ring->cons);
-		if (unlikely(((int)(ring->prod - ring_cons)) <=
-			     ring->size - HEADROOM - MAX_DESC_TXBBS)) {
+		if (unlikely(!mlx4_en_is_tx_ring_full(ring))) {
 			netif_tx_wake_queue(ring->tx_queue);
 			ring->wake_queue++;
 		}