net/mlx5: E-Switch, let user to enable disable metadata

Currently each packet inserted in eswitch is tagged with a internal
metadata to indicate source vport. Metadata tagging is not always
needed. Metadata insertion is needed for multi-port RoCE, failover
between representors and stacked devices. In many other cases,
metadata enablement is not needed.

Metadata insertion slows down the packet processing rate of the E-switch
when it is in switchdev mode.

Below table show performance gain with metadata disabled for VXLAN
offload rules in both SMFS and DMFS steering mode on ConnectX-5 device.

----------------------------------------------
| steering | metadata | pkt size | rx pps    |
| mode     |          |          | (million) |
----------------------------------------------
| smfs     | disabled | 128Bytes | 42        |
----------------------------------------------
| smfs     | enabled  | 128Bytes | 36        |
----------------------------------------------
| dmfs     | disabled | 128Bytes | 42        |
----------------------------------------------
| dmfs     | enabled  | 128Bytes | 36        |
----------------------------------------------

Hence, allow user to disable metadata using driver specific devlink
parameter. Metadata setting of the eswitch is applicable only for the
switchdev mode.

Example to show and disable metadata before changing eswitch mode:
$ devlink dev param show pci/0000:06:00.0 name esw_port_metadata
pci/0000:06:00.0:
  name esw_port_metadata type driver-specific
    values:
      cmode runtime value true

$ devlink dev param set pci/0000:06:00.0 \
	  name esw_port_metadata value false cmode runtime

$ devlink dev eswitch set pci/0000:06:00.0 mode switchdev

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
changelog:
v1->v2:
 - added performance numbers in commit log
 - updated commit log and documentation for switchdev mode
 - added explicit note on when user can disable metadata in
   documentation

1 files changed, 23 insertions, 7 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index ab32f685cbb7..1f58e84bdfc6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2351,8 +2351,7 @@ static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
 	mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
 }
 
-static bool
-esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
+bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
 {
 	if (!MLX5_CAP_ESW(esw->dev, esw_uplink_ingress_acl))
 		return false;
@@ -2452,6 +2451,28 @@ metadata_err:
 	return err;
 }
 
+int mlx5_esw_offloads_vport_metadata_set(struct mlx5_eswitch *esw, bool enable)
+{
+	int err = 0;
+
+	down_write(&esw->mode_lock);
+	if (esw->mode != MLX5_ESWITCH_NONE) {
+		err = -EBUSY;
+		goto done;
+	}
+	if (!mlx5_esw_vport_match_metadata_supported(esw)) {
+		err = -EOPNOTSUPP;
+		goto done;
+	}
+	if (enable)
+		esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
+	else
+		esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
+done:
+	up_write(&esw->mode_lock);
+	return err;
+}
+
 int
 esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
 				     struct mlx5_vport *vport)
@@ -2673,9 +2694,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	if (err)
 		goto err_metadata;
 
-	if (esw_check_vport_match_metadata_supported(esw))
-		esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
-
 	err = esw_offloads_metadata_init(esw);
 	if (err)
 		goto err_metadata;
@@ -2725,7 +2743,6 @@ err_pool:
 err_vport_metadata:
 	esw_offloads_metadata_uninit(esw);
 err_metadata:
-	esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
 	mlx5_rdma_disable_roce(esw->dev);
 	mutex_destroy(&esw->offloads.termtbl_mutex);
 	return err;
@@ -2761,7 +2778,6 @@ void esw_offloads_disable(struct mlx5_eswitch *esw)
 	esw_offloads_steering_cleanup(esw);
 	mapping_destroy(esw->offloads.reg_c0_obj_pool);
 	esw_offloads_metadata_uninit(esw);
-	esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
 	mlx5_rdma_disable_roce(esw->dev);
 	mutex_destroy(&esw->offloads.termtbl_mutex);
 	esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;