net/mlx5e: TX, Separate cachelines of xmit and completion stats

Avoid false sharing of cachelines by separating the cachelines of
TX stats that are dertied in xmit flow and in completion flow.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

drivers/net/ethernet/mellanox/mlx5/core/en_stats.c

@@ -64,11 +64,11 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
@@ -1137,11 +1137,11 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, recover) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) },
 };
 
 static const struct counter_desc ch_stats_desc[] = {

drivers/net/ethernet/mellanox/mlx5/core/en_stats.h

@@ -75,11 +75,11 @@ struct mlx5e_sw_stats {
 	u64 tx_csum_partial;
 	u64 tx_csum_partial_inner;
 	u64 tx_queue_stopped;
-	u64 tx_queue_wake;
 	u64 tx_queue_dropped;
 	u64 tx_xmit_more;
-	u64 tx_cqe_err;
 	u64 tx_recover;
+	u64 tx_queue_wake;
+	u64 tx_cqe_err;
 	u64 rx_wqe_err;
 	u64 rx_mpwqe_filler;
 	u64 rx_buff_alloc_err;
@@ -203,10 +203,11 @@ struct mlx5e_sq_stats {
 	/* less likely accessed in data path */
 	u64 csum_none;
 	u64 stopped;
-	u64 wake;
 	u64 dropped;
-	u64 cqe_err;
 	u64 recover;
+	/* dirtied @completion */
+	u64 wake ____cacheline_aligned_in_smp;
+	u64 cqe_err;
 };
 
 struct mlx5e_ch_stats {