IB/mlx5: Support padded 128B CQE feature

In some benchmarks and some CPU architectures, writing the CQE on a full
cache line size improves performance by saving memory access operations
(read-modify-write) relative to partial cache line change. This patch
lets the user to configure the device to pad the CQE up to 128B in case
its content is less than 128B. Currently the driver supports only padding
for a CQE size of 128B.

Signed-off-by: Guy Levi <guyle@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -444,6 +444,10 @@ struct mlx5_shared_mr_info {
 	struct ib_umem		*umem;
 };
 
+enum mlx5_ib_cq_pr_flags {
+	MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD	= 1 << 0,
+};
+
 struct mlx5_ib_cq {
 	struct ib_cq		ibcq;
 	struct mlx5_core_cq	mcq;
@@ -466,6 +470,7 @@ struct mlx5_ib_cq {
 	struct list_head	wc_list;
 	enum ib_cq_notify_flags notify_flags;
 	struct work_struct	notify_work;
+	u16			private_flags; /* Use mlx5_ib_cq_pr_flags */
 };
 
 struct mlx5_ib_wc {