net/mlx5e: Enable adaptive-TX moderation

Add support for adaptive TX moderation. This greatly reduces TX interrupt
rate and increases bandwidth, mostly for TCP bandwidth over ARM
architecture (below). There is a slight single stream TCP with very large
message sizes degradation (x86). In this case if there's any moderation on
transmitted packets the bandwidth would reduce due to hitting TCP output limit.
Since this is a synthetic case, this is still worth doing.

Performance improvement (ConnectX-4Lx 40GbE, ARM)
TCP 64B bandwidth with 1-50 streams increased 6-35%.
TCP 64B bandwidth with 100-500 streams increased 20-70%.

Performance improvement (ConnectX-5 100GbE, x86)
Bandwidth: increased up to 40% (1024B with 10s of streams).
Interrupt rate: reduced up to 50% (1024B with 1000s of streams).

Performance degradation (ConnectX-5 100GbE, x86)
Bandwidth: up to 10% decrease single stream TCP (1MB message size from
51Gb/s to 47Gb/s).

Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 50 insertions, 31 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a69cc1cc7bfb..f1fe490ed794 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1025,6 +1025,9 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	if (err)
 		goto err_sq_wq_destroy;
 
+	INIT_WORK(&sq->dim.work, mlx5e_tx_dim_work);
+	sq->dim.mode = params->tx_cq_moderation.cq_period_mode;
+
 	sq->edge = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS;
 
 	return 0;
@@ -1188,6 +1191,9 @@ static int mlx5e_open_txqsq(struct mlx5e_channel *c,
 	if (tx_rate)
 		mlx5e_set_sq_maxrate(c->netdev, sq, tx_rate);
 
+	if (params->tx_dim_enabled)
+		sq->state |= BIT(MLX5E_SQ_STATE_AM);
+
 	return 0;
 
 err_free_txqsq:
@@ -4084,18 +4090,48 @@ static bool slow_pci_heuristic(struct mlx5_core_dev *mdev)
 		link_speed > MLX5E_SLOW_PCI_RATIO * pci_bw;
 }
 
-void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+static struct net_dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
 {
-	params->tx_cq_moderation.cq_period_mode = cq_period_mode;
+	struct net_dim_cq_moder moder;
+
+	moder.cq_period_mode = cq_period_mode;
+	moder.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
+	moder.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
+	if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
+		moder.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE;
+
+	return moder;
+}
 
-	params->tx_cq_moderation.pkts =
-		MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
-	params->tx_cq_moderation.usec =
-		MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
+static struct net_dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
+{
+	struct net_dim_cq_moder moder;
 
+	moder.cq_period_mode = cq_period_mode;
+	moder.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
+	moder.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC;
 	if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
-		params->tx_cq_moderation.usec =
-			MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE;
+		moder.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE;
+
+	return moder;
+}
+
+static u8 mlx5_to_net_dim_cq_period_mode(u8 cq_period_mode)
+{
+	return cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE ?
+		NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE :
+		NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+}
+
+void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+{
+	if (params->tx_dim_enabled) {
+		u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode);
+
+		params->tx_cq_moderation = net_dim_get_def_tx_moderation(dim_period_mode);
+	} else {
+		params->tx_cq_moderation = mlx5e_get_def_tx_moderation(cq_period_mode);
+	}
 
 	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER,
 			params->tx_cq_moderation.cq_period_mode ==
@@ -4104,30 +4140,12 @@ void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
 
 void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
 {
-	params->rx_cq_moderation.cq_period_mode = cq_period_mode;
-
-	params->rx_cq_moderation.pkts =
-		MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
-	params->rx_cq_moderation.usec =
-		MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC;
-
-	if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE)
-		params->rx_cq_moderation.usec =
-			MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE;
-
 	if (params->rx_dim_enabled) {
-		switch (cq_period_mode) {
-		case MLX5_CQ_PERIOD_MODE_START_FROM_CQE:
-			params->rx_cq_moderation =
-				net_dim_get_def_rx_moderation(
-					NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE);
-			break;
-		case MLX5_CQ_PERIOD_MODE_START_FROM_EQE:
-		default:
-			params->rx_cq_moderation =
-				net_dim_get_def_rx_moderation(
-					NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE);
-		}
+		u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode);
+
+		params->rx_cq_moderation = net_dim_get_def_rx_moderation(dim_period_mode);
+	} else {
+		params->rx_cq_moderation = mlx5e_get_def_rx_moderation(cq_period_mode);
 	}
 
 	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER,
@@ -4191,6 +4209,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 			MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 			MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	params->tx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
 	mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode);
 	mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);