diff mbox series

[2/2] net/mlx5: E-Switch, Implement devlink port function cmds to control roce

Message ID 20221102163954.279266-3-danielj@nvidia.com (mailing list archive)
State Changes Requested
Delegated to: Netdev Maintainers
Headers show
Series devlink: Add port function attribute to enable/disable roce | expand

Checks

Context Check Description
netdev/tree_selection success Guessed tree name to be net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 1 this patch: 1
netdev/cc_maintainers warning 6 maintainers not CCed: linux-rdma@vger.kernel.org leon@kernel.org linux-doc@vger.kernel.org corbet@lwn.net edumazet@google.com pabeni@redhat.com
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 1 this patch: 1
netdev/checkpatch warning WARNING: line length of 89 exceeds 80 columns WARNING: line length of 90 exceeds 80 columns WARNING: line length of 95 exceeds 80 columns WARNING: line length of 98 exceeds 80 columns WARNING: line length of 99 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 1 this patch: 1
netdev/source_inline success Was 0 now: 0

Commit Message

Dan Jurgens Nov. 2, 2022, 4:39 p.m. UTC
From: Yishai Hadas <yishaih@nvidia.com>

Implement devlink port function commands to enable / disable roce.
This is used to control the roce device capabilities.

Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Daniel Jurgens <danielj@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../device_drivers/ethernet/mellanox/mlx5.rst |  32 ++++++
 .../net/ethernet/mellanox/mlx5/core/devlink.c |   2 +
 .../net/ethernet/mellanox/mlx5/core/eswitch.c |  34 ++++++
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |   8 +-
 .../mellanox/mlx5/core/eswitch_offloads.c     | 105 ++++++++++++++++++
 .../ethernet/mellanox/mlx5/core/mlx5_core.h   |   2 +
 .../net/ethernet/mellanox/mlx5/core/vport.c   |  23 ++++
 7 files changed, 205 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
index 5edf50d7dbd5..2ffdc103571e 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
@@ -388,6 +388,38 @@  device created for the PCI VF/SF.
       function:
         hw_addr 00:00:00:00:88:88
 
+RoCE capability setup
+---------------------
+Not all mlx5 PCI VFs/SFs require RoCE capability.
+
+When RoCE capability is disabled, it saves 1 Mbytes worth of system memory per
+PCI VF/SF.
+
+mlx5 driver provides mechanism to setup RoCE capability.
+
+When user disables RoCE capability for a VF/SF, user application cannot send or
+receive any RoCE packets through this VF/SF and RoCE GID table for this PCI
+will be empty.
+
+When RoCE capability is disabled in the device using port function attribute,
+VF/SF driver cannot override it.
+
+- Get RoCE capability of the VF device::
+
+    $ devlink port show pci/0000:06:00.0/2
+    pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1
+        function:
+            hw_addr 00:00:00:00:00:00 roce on
+
+- Set RoCE capability of the VF device::
+
+    $ devlink port function set pci/0000:06:00.0/2 roce off
+
+    $ devlink port show pci/0000:06:00.0/2
+    pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1
+        function:
+            hw_addr 00:00:00:00:00:00 roce off
+
 SF state setup
 --------------
 To use the SF, the user must active 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 66c6a7017695..69d103694ac2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -318,6 +318,8 @@  static const struct devlink_ops mlx5_devlink_ops = {
 	.rate_node_new = mlx5_esw_devlink_rate_node_new,
 	.rate_node_del = mlx5_esw_devlink_rate_node_del,
 	.rate_leaf_parent_set = mlx5_esw_devlink_rate_parent_set,
+	.port_function_roce_get = mlx5_devlink_port_function_roce_get,
+	.port_function_roce_set = mlx5_devlink_port_function_roce_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 c59107fa9e6d..035240587163 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -772,6 +772,32 @@  static void esw_vport_cleanup_acl(struct mlx5_eswitch *esw,
 		esw_vport_destroy_offloads_acl_tables(esw, vport);
 }
 
+static int mlx5_esw_vport_roce_cap_get(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+{
+	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *query_ctx;
+	void *hca_caps;
+	int err;
+
+	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
+		return 0;
+
+	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
+	if (!query_ctx)
+		return -ENOMEM;
+
+	err = mlx5_vport_get_other_func_cap(esw->dev, vport->vport, query_ctx);
+	if (err)
+		goto out_free;
+
+	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
+	vport->info.roce_enabled = MLX5_GET(cmd_hca_cap, hca_caps, roce);
+
+out_free:
+	kfree(query_ctx);
+	return err;
+}
+
 static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
 	u16 vport_num = vport->vport;
@@ -785,6 +811,10 @@  static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 	if (mlx5_esw_is_manager_vport(esw, vport_num))
 		return 0;
 
+	err = mlx5_esw_vport_roce_cap_get(esw, vport);
+	if (err)
+		goto err_roce;
+
 	mlx5_modify_vport_admin_state(esw->dev,
 				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 				      vport_num, 1,
@@ -804,6 +834,10 @@  static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 			       vport->info.qos, flags);
 
 	return 0;
+
+err_roce:
+	esw_vport_cleanup_acl(esw, vport);
+	return err;
 }
 
 /* Don't cleanup vport->info, it's needed to restore vport configuration */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index f68dc2d0dbe6..83e125d13b7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -153,6 +153,7 @@  struct mlx5_vport_info {
 	u8                      qos;
 	u8                      spoofchk: 1;
 	u8                      trusted: 1;
+	u8                      roce_enabled: 1;
 };
 
 /* Vport context events */
@@ -508,7 +509,12 @@  int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port,
 int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port,
 					   const u8 *hw_addr, int hw_addr_len,
 					   struct netlink_ext_ack *extack);
-
+int mlx5_devlink_port_function_roce_get(struct devlink_port *port,
+					bool *is_enabled,
+					struct netlink_ext_ack *extack);
+int mlx5_devlink_port_function_roce_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 4e50df3139c6..446488687a1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4024,3 +4024,108 @@  int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port,
 
 	return mlx5_eswitch_set_vport_mac(esw, vport_num, hw_addr);
 }
+
+int mlx5_devlink_port_function_roce_get(struct devlink_port *port,
+					bool *is_enabled,
+					struct netlink_ext_ack *extack)
+{
+	struct mlx5_eswitch *esw;
+	struct mlx5_vport *vport;
+	int err = -EOPNOTSUPP;
+	u16 vport_num;
+
+	esw = mlx5_devlink_eswitch_get(port->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
+		return -EOPNOTSUPP;
+
+	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
+	if (!is_port_function_supported(esw, vport_num))
+		return -EOPNOTSUPP;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	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.roce_enabled;
+		err = 0;
+	}
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_devlink_port_function_roce_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;
+	int err = -EOPNOTSUPP;
+	void *query_ctx;
+	void *hca_caps;
+	u16 vport_num;
+
+	esw = mlx5_devlink_eswitch_get(port->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
+		return -EOPNOTSUPP;
+
+	vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
+	if (!is_port_function_supported(esw, vport_num))
+		return -EOPNOTSUPP;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	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.roce_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_num, query_ctx);
+	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);
+	MLX5_SET(cmd_hca_cap, hca_caps, roce, enable);
+
+	err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport_num);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed setting HCA roce cap");
+		goto out_free;
+	}
+
+	vport->info.roce_enabled = enable;
+
+out_free:
+	kfree(query_ctx);
+out:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index a806e3de7b7c..9f717f3fff98 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -309,6 +309,8 @@  enum {
 
 u8 mlx5_get_nic_state(struct mlx5_core_dev *dev);
 void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state);
+int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out);
+int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap, u16 function_id);
 
 static inline bool mlx5_core_is_sf(const struct mlx5_core_dev *dev)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index d5c317325030..75c876712992 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -1171,3 +1171,26 @@  int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, vo
 	MLX5_SET(query_hca_cap_in, in, other_function, true);
 	return mlx5_cmd_exec_inout(dev, query_hca_cap, in, out);
 }
+
+int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap, u16 function_id)
+{
+	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	void *set_hca_cap;
+	void *set_ctx;
+	int ret;
+
+	set_ctx = kzalloc(set_sz, GFP_KERNEL);
+	if (!set_ctx)
+		return -ENOMEM;
+
+	MLX5_SET(set_hca_cap_in, set_ctx, opcode, MLX5_CMD_OP_SET_HCA_CAP);
+	MLX5_SET(set_hca_cap_in, set_ctx, op_mod, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1);
+	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
+	memcpy(set_hca_cap, hca_cap, MLX5_ST_SZ_BYTES(cmd_hca_cap));
+	MLX5_SET(set_hca_cap_in, set_ctx, function_id, function_id);
+	MLX5_SET(set_hca_cap_in, set_ctx, other_function, true);
+	ret = mlx5_cmd_exec_in(dev, set_hca_cap, set_ctx);
+
+	kfree(set_ctx);
+	return ret;
+}