Merge branch 'devlink-resource'

Jiri Pirko says:

====================
devlink: Add support for resource abstraction

Arkadi says:

Many of the ASIC's internal resources are limited and are shared between
several hardware procedures. For example, unified hash-based memory can
be used for many lookup purposes, like FDB and LPM. In many cases the user
can provide a partitioning scheme for such a resource in order to perform
fine tuning for his application. In such cases performing driver reload is
needed for the changes to take place, thus this patchset also adds support
for hot reload.

Such an abstraction can be coupled with devlink's dpipe interface, which
models the ASIC's pipeline as a graph of match/action tables. By modeling
the hardware resource object, and by coupling it to several dpipe tables,
further visibility can be achieved in order to debug ASIC-wide issues.

The proposed interface will provide the user the ability to understand the
limitations of the hardware, and receive notification regarding its occupancy.
Furthermore, monitoring the resource occupancy can be done in real-time and
can be useful in many cases.

---
v2->v3
- Mix/Max/Gran attributes.
- Add resource consumption per table.
- Change basic resource unit to 'entry'.
- ABI documentation.

v1->v2
- Add resource size attribute.
- Fix split bug.
====================

Signed-off-by: David S. Miller <[email protected]>

Documentation/ABI/testing/devlink-resource-mlxsw

@@ -0,0 +1,33 @@
+What: 		/kvd/
+Date:		08-Jan-2018
+KernelVersion:	v4.16
+Contact:	[email protected]
+Description:	The main database in the Spectrum device is a centralized
+		KVD database used for many of the tables used to configure
+		the chip including L2 FDB, L3 LPM, ECMP and more. The KVD
+		is divided into two sections, the first is hash-based table
+		and the second is a linear access table. The division
+		between the linear and hash-based sections is static and
+		require reload before the changes take effect.
+
+What: 		/kvd/linear
+Date:		08-Jan-2018
+KernelVersion:	v4.16
+Contact:	[email protected]
+Description:	The linear section of the KVD is managed by software as a
+		flat memory accessed using an index.
+
+What: 		/kvd/hash_single
+Date:		08-Jan-2018
+KernelVersion:	v4.16
+Contact:	[email protected]
+Description:	The hash based section of the KVD is managed by the switch
+		device. Used in case the key size is smaller or equal to
+		64bit.
+
+What: 		/kvd/hash_double
+Date:		08-Jan-2018
+KernelVersion:	v4.16
+Contact:	[email protected]
+Description:	The hash based section of the KVD is managed by the switch
+		device. Used in case the key is larger than 64 bit.

drivers/net/ethernet/mellanox/mlxsw/core.c

@@ -113,6 +113,7 @@ struct mlxsw_core {
 	struct mlxsw_thermal *thermal;
 	struct mlxsw_core_port *ports;
 	unsigned int max_ports;
+	bool reload_fail;
 	unsigned long driver_priv[0];
 	/* driver_priv has to be always the last item */
 };
@@ -962,7 +963,28 @@ mlxsw_devlink_sb_occ_tc_port_bind_get(struct devlink_port *devlink_port,
 						     pool_type, p_cur, p_max);
 }
 
+static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	const struct mlxsw_bus *mlxsw_bus = mlxsw_core->bus;
+	int err;
+
+	if (!mlxsw_bus->reset)
+		return -EOPNOTSUPP;
+
+	mlxsw_core_bus_device_unregister(mlxsw_core, true);
+	mlxsw_bus->reset(mlxsw_core->bus_priv);
+	err = mlxsw_core_bus_device_register(mlxsw_core->bus_info,
+					     mlxsw_core->bus,
+					     mlxsw_core->bus_priv, true,
+					     devlink);
+	if (err)
+		mlxsw_core->reload_fail = true;
+	return err;
+}
+
 static const struct devlink_ops mlxsw_devlink_ops = {
+	.reload				= mlxsw_devlink_core_bus_device_reload,
 	.port_type_set			= mlxsw_devlink_port_type_set,
 	.port_split			= mlxsw_devlink_port_split,
 	.port_unsplit			= mlxsw_devlink_port_unsplit,
@@ -980,23 +1002,26 @@ static const struct devlink_ops mlxsw_devlink_ops = {
 
 int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 				   const struct mlxsw_bus *mlxsw_bus,
-				   void *bus_priv)
+				   void *bus_priv, bool reload,
+				   struct devlink *devlink)
 {
 	const char *device_kind = mlxsw_bus_info->device_kind;
 	struct mlxsw_core *mlxsw_core;
 	struct mlxsw_driver *mlxsw_driver;
-	struct devlink *devlink;
 	size_t alloc_size;
 	int err;
 
 	mlxsw_driver = mlxsw_core_driver_get(device_kind);
 	if (!mlxsw_driver)
 		return -EINVAL;
-	alloc_size = sizeof(*mlxsw_core) + mlxsw_driver->priv_size;
-	devlink = devlink_alloc(&mlxsw_devlink_ops, alloc_size);
-	if (!devlink) {
-		err = -ENOMEM;
-		goto err_devlink_alloc;
+
+	if (!reload) {
+		alloc_size = sizeof(*mlxsw_core) + mlxsw_driver->priv_size;
+		devlink = devlink_alloc(&mlxsw_devlink_ops, alloc_size);
+		if (!devlink) {
+			err = -ENOMEM;
+			goto err_devlink_alloc;
+		}
 	}
 
 	mlxsw_core = devlink_priv(devlink);
@@ -1012,6 +1037,12 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_bus_init;
 
+	if (mlxsw_driver->resources_register && !reload) {
+		err = mlxsw_driver->resources_register(mlxsw_core);
+		if (err)
+			goto err_register_resources;
+	}
+
 	err = mlxsw_ports_init(mlxsw_core);
 	if (err)
 		goto err_ports_init;
@@ -1032,9 +1063,11 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_emad_init;
 
-	err = devlink_register(devlink, mlxsw_bus_info->dev);
-	if (err)
-		goto err_devlink_register;
+	if (!reload) {
+		err = devlink_register(devlink, mlxsw_bus_info->dev);
+		if (err)
+			goto err_devlink_register;
+	}
 
 	err = mlxsw_hwmon_init(mlxsw_core, mlxsw_bus_info, &mlxsw_core->hwmon);
 	if (err)
@@ -1057,7 +1090,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 err_thermal_init:
 err_hwmon_init:
-	devlink_unregister(devlink);
+	if (!reload)
+		devlink_unregister(devlink);
 err_devlink_register:
 	mlxsw_emad_fini(mlxsw_core);
 err_emad_init:
@@ -1067,26 +1101,40 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 err_ports_init:
 	mlxsw_bus->fini(bus_priv);
 err_bus_init:
-	devlink_free(devlink);
+	if (!reload)
+		devlink_resources_unregister(devlink, NULL);
+err_register_resources:
+	if (!reload)
+		devlink_free(devlink);
 err_devlink_alloc:
 	mlxsw_core_driver_put(device_kind);
 	return err;
 }
 EXPORT_SYMBOL(mlxsw_core_bus_device_register);
 
-void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
+void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
+				      bool reload)
 {
 	const char *device_kind = mlxsw_core->bus_info->device_kind;
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
+	if (mlxsw_core->reload_fail)
+		goto reload_fail;
+
 	if (mlxsw_core->driver->fini)
 		mlxsw_core->driver->fini(mlxsw_core);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
-	devlink_unregister(devlink);
+	if (!reload)
+		devlink_unregister(devlink);
 	mlxsw_emad_fini(mlxsw_core);
 	kfree(mlxsw_core->lag.mapping);
 	mlxsw_ports_fini(mlxsw_core);
+	if (!reload)
+		devlink_resources_unregister(devlink, NULL);
 	mlxsw_core->bus->fini(mlxsw_core->bus_priv);
+	if (reload)
+		return;
+reload_fail:
 	devlink_free(devlink);
 	mlxsw_core_driver_put(device_kind);
 }
@@ -1791,6 +1839,22 @@ void mlxsw_core_flush_owq(void)
 }
 EXPORT_SYMBOL(mlxsw_core_flush_owq);
 
+int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
+			     const struct mlxsw_config_profile *profile,
+			     u64 *p_single_size, u64 *p_double_size,
+			     u64 *p_linear_size)
+{
+	struct mlxsw_driver *driver = mlxsw_core->driver;
+
+	if (!driver->kvd_sizes_get)
+		return -EINVAL;
+
+	return driver->kvd_sizes_get(mlxsw_core, profile,
+				     p_single_size, p_double_size,
+				     p_linear_size);
+}
+EXPORT_SYMBOL(mlxsw_core_kvd_sizes_get);
+
 static int __init mlxsw_core_module_init(void)
 {
 	int err;

drivers/net/ethernet/mellanox/mlxsw/core.h

@@ -66,8 +66,9 @@ void mlxsw_core_driver_unregister(struct mlxsw_driver *mlxsw_driver);
 
 int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 				   const struct mlxsw_bus *mlxsw_bus,
-				   void *bus_priv);
-void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core);
+				   void *bus_priv, bool reload,
+				   struct devlink *devlink);
+void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, bool reload);
 
 struct mlxsw_tx_info {
 	u8 local_port;
@@ -308,10 +309,20 @@ struct mlxsw_driver {
 				       u32 *p_cur, u32 *p_max);
 	void (*txhdr_construct)(struct sk_buff *skb,
 				const struct mlxsw_tx_info *tx_info);
+	int (*resources_register)(struct mlxsw_core *mlxsw_core);
+	int (*kvd_sizes_get)(struct mlxsw_core *mlxsw_core,
+			     const struct mlxsw_config_profile *profile,
+			     u64 *p_single_size, u64 *p_double_size,
+			     u64 *p_linear_size);
 	u8 txhdr_len;
 	const struct mlxsw_config_profile *profile;
 };
 
+int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
+			     const struct mlxsw_config_profile *profile,
+			     u64 *p_single_size, u64 *p_double_size,
+			     u64 *p_linear_size);
+
 bool mlxsw_core_res_valid(struct mlxsw_core *mlxsw_core,
 			  enum mlxsw_res_id res_id);
 
@@ -332,6 +343,7 @@ struct mlxsw_bus {
 		    const struct mlxsw_config_profile *profile,
 		    struct mlxsw_res *res);
 	void (*fini)(void *bus_priv);
+	void (*reset)(void *bus_priv);
 	bool (*skb_transmit_busy)(void *bus_priv,
 				  const struct mlxsw_tx_info *tx_info);
 	int (*skb_transmit)(void *bus_priv, struct sk_buff *skb,

drivers/net/ethernet/mellanox/mlxsw/i2c.c

@@ -539,7 +539,8 @@ static int mlxsw_i2c_probe(struct i2c_client *client,
 	mlxsw_i2c->dev = &client->dev;
 
 	err = mlxsw_core_bus_device_register(&mlxsw_i2c->bus_info,
-					     &mlxsw_i2c_bus, mlxsw_i2c);
+					     &mlxsw_i2c_bus, mlxsw_i2c, false,
+					     NULL);
 	if (err) {
 		dev_err(&client->dev, "Fail to register core bus\n");
 		return err;
@@ -557,7 +558,7 @@ static int mlxsw_i2c_remove(struct i2c_client *client)
 {
 	struct mlxsw_i2c *mlxsw_i2c = i2c_get_clientdata(client);
 
-	mlxsw_core_bus_device_unregister(mlxsw_i2c->core);
+	mlxsw_core_bus_device_unregister(mlxsw_i2c->core, false);
 	mutex_destroy(&mlxsw_i2c->cmd.lock);
 
 	return 0;