net/mlx4_en: Datapath structures are allocated per NUMA node

For each RX/TX ring and its CQ, allocation is done on a NUMA node that
corresponds to the core that the data structure should operate on.
The assumption is that the core number is reflected by the ring index.
The affected allocations are the ring/CQ data structures,
the TX/RX info and the shared HW/SW buffer.
For TX rings, each core has rings of all UPs.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c
index 00f223a..84cfb40 100644
--- a/drivers/net/ethernet/mellanox/mlx4/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/pd.c
@@ -168,7 +168,7 @@
 }
 EXPORT_SYMBOL_GPL(mlx4_uar_free);
 
-int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf)
+int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf, int node)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_uar *uar;
@@ -186,10 +186,13 @@
 			err = -ENOMEM;
 			goto out;
 		}
-		uar = kmalloc(sizeof *uar, GFP_KERNEL);
+		uar = kmalloc_node(sizeof(*uar), GFP_KERNEL, node);
 		if (!uar) {
-			err = -ENOMEM;
-			goto out;
+			uar = kmalloc(sizeof(*uar), GFP_KERNEL);
+			if (!uar) {
+				err = -ENOMEM;
+				goto out;
+			}
 		}
 		err = mlx4_uar_alloc(dev, uar);
 		if (err)