Re: [net-next 10/16] net/mlx5: Support PCIe buffer congestion handling via Devlink

[Jiri Pirko <jiri@resnulli.us>]

Thu, Jul 19, 2018 at 03:01:01AM CEST, saeedm@mellanox.com wrote:
>From: Eran Ben Elisha <eranbe@mellanox.com>
>
>Add support for two driver parameters via devlink params interface:
>- Congestion action
>	HW mechanism in the PCIe buffer which monitors the amount of
>	consumed PCIe buffer per host.  This mechanism supports the
>	following actions in case of threshold overflow:
>	- Disabled - NOP (Default)
>	- Drop
>	- Mark - Mark CE bit in the CQE of received packet
>- Congestion mode
>	- Aggressive - Aggressive static trigger threshold (Default)
>	- Dynamic - Dynamically change the trigger threshold
>
>Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
>Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
>Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
>---
> .../net/ethernet/mellanox/mlx5/core/devlink.c | 105 +++++++++++++++++-
> 1 file changed, 104 insertions(+), 1 deletion(-)
>
>diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
>index 9800c98b01d3..1f04decef043 100644
>--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
>+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
>@@ -153,12 +153,115 @@ static int mlx5_devlink_query_tx_overflow_sense(struct mlx5_core_dev *mdev,
> 	return 0;
> }
> 
>+static int mlx5_devlink_set_congestion_action(struct devlink *devlink, u32 id,
>+					      struct devlink_param_gset_ctx *ctx)
>+{
>+	struct mlx5_core_dev *dev = devlink_priv(devlink);
>+	u8 max = MLX5_DEVLINK_CONGESTION_ACTION_MAX;
>+	u8 sense;
>+	int err;
>+
>+	if (!MLX5_CAP_MCAM_FEATURE(dev, mark_tx_action_cqe) &&
>+	    !MLX5_CAP_MCAM_FEATURE(dev, mark_tx_action_cnp))
>+		max = MLX5_DEVLINK_CONGESTION_ACTION_MARK - 1;
>+
>+	if (ctx->val.vu8 > max)

This should not be num. It should be a string. Same for "mode".


>+		return -ERANGE;
>+
>+	err = mlx5_devlink_query_tx_overflow_sense(dev, &sense);
>+	if (err)
>+		return err;
>+
>+	if (ctx->val.vu8 == MLX5_DEVLINK_CONGESTION_ACTION_DISABLED &&
>+	    sense != MLX5_DEVLINK_CONGESTION_MODE_AGGRESSIVE)
>+		return -EINVAL;
>+
>+	return mlx5_devlink_set_tx_lossy_overflow(dev, ctx->val.vu8);
>+}
>+
>+static int mlx5_devlink_get_congestion_action(struct devlink *devlink, u32 id,
>+					      struct devlink_param_gset_ctx *ctx)
>+{
>+	struct mlx5_core_dev *dev = devlink_priv(devlink);
>+
>+	return mlx5_devlink_query_tx_lossy_overflow(dev, &ctx->val.vu8);
>+}
>+
>+static int mlx5_devlink_set_congestion_mode(struct devlink *devlink, u32 id,
>+					    struct devlink_param_gset_ctx *ctx)
>+{
>+	struct mlx5_core_dev *dev = devlink_priv(devlink);
>+	u8 tx_lossy_overflow;
>+	int err;
>+
>+	if (ctx->val.vu8 > MLX5_DEVLINK_CONGESTION_MODE_MAX)
>+		return -ERANGE;
>+
>+	err = mlx5_devlink_query_tx_lossy_overflow(dev, &tx_lossy_overflow);
>+	if (err)
>+		return err;
>+
>+	if (ctx->val.vu8 != MLX5_DEVLINK_CONGESTION_MODE_AGGRESSIVE &&
>+	    tx_lossy_overflow == MLX5_DEVLINK_CONGESTION_ACTION_DISABLED)
>+		return -EINVAL;
>+
>+	return mlx5_devlink_set_tx_overflow_sense(dev, ctx->val.vu8);
>+}
>+
>+static int mlx5_devlink_get_congestion_mode(struct devlink *devlink, u32 id,
>+					    struct devlink_param_gset_ctx *ctx)
>+{
>+	struct mlx5_core_dev *dev = devlink_priv(devlink);
>+
>+	return mlx5_devlink_query_tx_overflow_sense(dev, &ctx->val.vu8);
>+}
>+
>+enum mlx5_devlink_param_id {
>+	MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
>+	MLX5_DEVLINK_PARAM_ID_CONGESTION_ACTION,
>+	MLX5_DEVLINK_PARAM_ID_CONGESTION_MODE,
>+};
>+
>+static const struct devlink_param mlx5_devlink_params[] = {
>+	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_CONGESTION_ACTION,
>+			     "congestion_action",
>+			     DEVLINK_PARAM_TYPE_U8,
>+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
>+			     mlx5_devlink_get_congestion_action,
>+			     mlx5_devlink_set_congestion_action, NULL),
>+	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_CONGESTION_MODE,
>+			     "congestion_mode",
>+			     DEVLINK_PARAM_TYPE_U8,
>+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
>+			     mlx5_devlink_get_congestion_mode,
>+			     mlx5_devlink_set_congestion_mode, NULL),
>+};
>+
> int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
> {
>-	return devlink_register(devlink, dev);
>+	int err;
>+
>+	err = devlink_register(devlink, dev);
>+	if (err)
>+		return err;
>+
>+	err = devlink_params_register(devlink, mlx5_devlink_params,
>+				      ARRAY_SIZE(mlx5_devlink_params));
>+	if (err) {
>+		dev_err(dev, "devlink_params_register failed, err = %d\n", err);
>+		goto unregister;
>+	}
>+
>+	return 0;
>+
>+unregister:
>+	devlink_unregister(devlink);
>+	return err;
> }
> 
> void mlx5_devlink_unregister(struct devlink *devlink)
> {
>+	devlink_params_unregister(devlink, mlx5_devlink_params,
>+				  ARRAY_SIZE(mlx5_devlink_params));
> 	devlink_unregister(devlink);
> }
>-- 
>2.17.0
>