mlx4: Fix tx ring affinity_mask creation

By default, the number of tx queues is limited by the number of online cpus
in mlx4_en_get_profile(). However, this limit no longer holds after the
ethtool .set_channels method has been called. In that situation, the driver
may access invalid bits of certain cpumask variables when queue_index >=
nr_cpu_ids.

Signed-off-by: Benjamin Poirier <[e-mail]>
Acked-by: Ido Shamay <[e-mail]>
Fixes: d03a68f ("net/mlx4_en: Configure the XPS queue mapping on driver load")
Signed-off-by: David S. Miller <[e-mail]>

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

···
 	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;
···
 
 	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);