net/mlx5: E-Switch, Implement devlink port function cmds to control migratable

Implement devlink port function commands to enable / disable migratable.
This is used to control the migratable capability of the device.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Acked-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 124 insertions, 0 deletions

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
index 8b8f95d1293a..6969652f593c 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
@@ -364,6 +364,14 @@ PCI devices/SF.
 mlx5 driver support devlink port function attr mechanism to setup RoCE
 capability. (refer to Documentation/networking/devlink/devlink-port.rst)
 
+migratable capability setup
+---------------------------
+User who wants mlx5 PCI VFs to be able to perform live migration need to
+explicitly enable the VF migratable capability.
+
+mlx5 driver support devlink port function attr mechanism to setup migratable
+capability. (refer to Documentation/networking/devlink/devlink-port.rst)
+
 SF state setup
 --------------
 To use the SF, the user must activate the SF using the SF function state
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 336c7b7fa494..ddb197970c22 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -316,6 +316,8 @@ static const struct devlink_ops mlx5_devlink_ops = {
 	.rate_leaf_parent_set = mlx5_esw_devlink_rate_parent_set,
 	.port_fn_roce_get = mlx5_devlink_port_fn_roce_get,
 	.port_fn_roce_set = mlx5_devlink_port_fn_roce_set,
+	.port_fn_migratable_get = mlx5_devlink_port_fn_migratable_get,
+	.port_fn_migratable_set = mlx5_devlink_port_fn_migratable_set,
 #endif
 #ifdef CONFIG_MLX5_SF_MANAGER
 	.port_new = mlx5_devlink_sf_port_new,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 001fb1e62135..527e4bffda8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -794,6 +794,14 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *
 	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
 	vport->info.roce_enabled = MLX5_GET(cmd_hca_cap, hca_caps, roce);
 
+	memset(query_ctx, 0, query_out_sz);
+	err = mlx5_vport_get_other_func_cap(esw->dev, vport->vport, query_ctx,
+					    MLX5_CAP_GENERAL_2);
+	if (err)
+		goto out_free;
+
+	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
+	vport->info.mig_enabled = MLX5_GET(cmd_hca_cap_2, hca_caps, migratable);
 out_free:
 	kfree(query_ctx);
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index eea0521729df..5a85a5d32be7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -154,6 +154,7 @@ struct mlx5_vport_info {
 	u8                      spoofchk: 1;
 	u8                      trusted: 1;
 	u8                      roce_enabled: 1;
+	u8                      mig_enabled: 1;
 };
 
 /* Vport context events */
@@ -513,6 +514,10 @@ int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled,
 				  struct netlink_ext_ack *extack);
 int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable,
 				  struct netlink_ext_ack *extack);
+int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enabled,
+					struct netlink_ext_ack *extack);
+int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
+					struct netlink_ext_ack *extack);
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type);
 
 int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 7618c51351ca..c6a14202c62c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4038,6 +4038,107 @@ mlx5_devlink_port_fn_get_vport(struct devlink_port *port, struct mlx5_eswitch *e
 	return mlx5_eswitch_get_vport(esw, vport_num);
 }
 
+int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enabled,
+					struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	int err = -EOPNOTSUPP;
+
+	esw = mlx5_devlink_eswitch_get(port->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	if (!MLX5_CAP_GEN(esw->dev, migration)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support migration");
+		return err;
+	}
+
+	vport = mlx5_devlink_port_fn_get_vport(port, esw);
+	if (IS_ERR(vport)) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
+		return PTR_ERR(vport);
+	}
+
+	mutex_lock(&esw->state_lock);
+	if (vport->enabled) {
+		*is_enabled = vport->info.mig_enabled;
+		err = 0;
+	}
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
+					struct netlink_ext_ack *extack)
+{
+	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	void *query_ctx;
+	void *hca_caps;
+	int err = -EOPNOTSUPP;
+
+	esw = mlx5_devlink_eswitch_get(port->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	if (!MLX5_CAP_GEN(esw->dev, migration)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support migration");
+		return err;
+	}
+
+	vport = mlx5_devlink_port_fn_get_vport(port, esw);
+	if (IS_ERR(vport)) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid port");
+		return PTR_ERR(vport);
+	}
+
+	mutex_lock(&esw->state_lock);
+	if (!vport->enabled) {
+		NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
+		goto out;
+	}
+
+	if (vport->info.mig_enabled == enable) {
+		err = 0;
+		goto out;
+	}
+
+	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
+	if (!query_ctx) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = mlx5_vport_get_other_func_cap(esw->dev, vport->vport, query_ctx,
+					    MLX5_CAP_GENERAL_2);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed getting HCA caps");
+		goto out_free;
+	}
+
+	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
+	memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability),
+	       MLX5_UN_SZ_BYTES(hca_cap_union));
+	MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, 1);
+
+	err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport->vport,
+					    MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed setting HCA migratable cap");
+		goto out_free;
+	}
+
+	vport->info.mig_enabled = enable;
+
+out_free:
+	kfree(query_ctx);
+out:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
 int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled,
 				  struct netlink_ext_ack *extack)
 {