summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst34
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/devlink.c62
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/devlink.h1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch.h2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c30
5 files changed, 122 insertions, 7 deletions
diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
index 1b7e32d8a61b..936a10f1942c 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
@@ -183,6 +183,40 @@ User command examples:
values:
cmode driverinit value true
+esw_port_metadata: Eswitch port metadata state
+----------------------------------------------
+When applicable, disabling Eswitch metadata can increase packet rate
+up to 20% depending on the use case and packet sizes.
+
+Eswitch port metadata state controls whether to internally tag packets with
+metadata. Metadata tagging must be enabled for multi-port RoCE, failover
+between representors and stacked devices.
+By default metadata is enabled on the supported devices in E-switch.
+Metadata is applicable only for E-switch in switchdev mode and
+users may disable it when NONE of the below use cases will be in use:
+1. HCA is in Dual/multi-port RoCE mode.
+2. VF/SF representor bonding (Usually used for Live migration)
+3. Stacked devices
+
+When metadata is disabled, the above use cases will fail to initialize if
+users try to enable them.
+
+- Show eswitch port metadata::
+
+ $ 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
+
+- Disable eswitch port metadata::
+
+ $ devlink dev param set pci/0000:06:00.0 name esw_port_metadata value false cmode runtime
+
+- Change eswitch mode to switchdev mode where after choosing the metadata value::
+
+ $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev
+
mlx5 subfunction
================
mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 38c7c44fe883..ee0f5355f120 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -456,6 +456,50 @@ static int mlx5_devlink_large_group_num_validate(struct devlink *devlink, u32 id
return 0;
}
+
+static int mlx5_devlink_esw_port_metadata_set(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+ if (!MLX5_ESWITCH_MANAGER(dev))
+ return -EOPNOTSUPP;
+
+ return mlx5_esw_offloads_vport_metadata_set(dev->priv.eswitch, ctx->val.vbool);
+}
+
+static int mlx5_devlink_esw_port_metadata_get(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+ if (!MLX5_ESWITCH_MANAGER(dev))
+ return -EOPNOTSUPP;
+
+ ctx->val.vbool = mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch);
+ return 0;
+}
+
+static int mlx5_devlink_esw_port_metadata_validate(struct devlink *devlink, u32 id,
+ union devlink_param_value val,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ u8 esw_mode;
+
+ if (!MLX5_ESWITCH_MANAGER(dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "E-Switch is unsupported");
+ return -EOPNOTSUPP;
+ }
+ esw_mode = mlx5_eswitch_mode(dev);
+ if (esw_mode == MLX5_ESWITCH_OFFLOADS) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "E-Switch must either disabled or non switchdev mode");
+ return -EBUSY;
+ }
+ return 0;
+}
+
#endif
static int mlx5_devlink_enable_remote_dev_reset_set(struct devlink *devlink, u32 id,
@@ -490,6 +534,12 @@ static const struct devlink_param mlx5_devlink_params[] = {
BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
NULL, NULL,
mlx5_devlink_large_group_num_validate),
+ DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_ESW_PORT_METADATA,
+ "esw_port_metadata", DEVLINK_PARAM_TYPE_BOOL,
+ BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+ mlx5_devlink_esw_port_metadata_get,
+ mlx5_devlink_esw_port_metadata_set,
+ mlx5_devlink_esw_port_metadata_validate),
#endif
DEVLINK_PARAM_GENERIC(ENABLE_REMOTE_DEV_RESET, BIT(DEVLINK_PARAM_CMODE_RUNTIME),
mlx5_devlink_enable_remote_dev_reset_get,
@@ -519,6 +569,18 @@ static void mlx5_devlink_set_params_init_values(struct devlink *devlink)
devlink_param_driverinit_value_set(devlink,
MLX5_DEVLINK_PARAM_ID_ESW_LARGE_GROUP_NUM,
value);
+
+ if (MLX5_ESWITCH_MANAGER(dev)) {
+ if (mlx5_esw_vport_match_metadata_supported(dev->priv.eswitch)) {
+ dev->priv.eswitch->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
+ value.vbool = true;
+ } else {
+ value.vbool = false;
+ }
+ devlink_param_driverinit_value_set(devlink,
+ MLX5_DEVLINK_PARAM_ID_ESW_PORT_METADATA,
+ value);
+ }
#endif
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
index eff107dad922..7318d44b774b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -10,6 +10,7 @@ enum mlx5_devlink_param_id {
MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE,
MLX5_DEVLINK_PARAM_ID_ESW_LARGE_GROUP_NUM,
+ MLX5_DEVLINK_PARAM_ID_ESW_PORT_METADATA,
};
struct mlx5_trap_ctx {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index deafb0e03787..c7a73dbd64b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -314,6 +314,8 @@ int esw_offloads_enable(struct mlx5_eswitch *esw);
void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw);
int esw_offloads_init_reps(struct mlx5_eswitch *esw);
+bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw);
+int mlx5_esw_offloads_vport_metadata_set(struct mlx5_eswitch *esw, bool enable);
u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw);
void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata);
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;