Merge branch 'devlink'

Jiri Pirko says:

====================
Introduce devlink interface and first drivers to use it

There a is need for some userspace API that would allow to expose things
that are not directly related to any device class like net_device of
ib_device, but rather chip-wide/switch-ASIC-wide stuff.

Use cases:
1) get/set of port type (Ethernet/InfiniBand)
2) setting up port splitters - split port into multiple ones and squash again,
   enables usage of splitter cable
3) setting up shared buffers - shared among multiple ports within
   one chip (work in progress)
4) configuration of switch wide properties - resources division etc - This will
   allow to pass configuration that is unacceptable to be passed as
   a module option.

First patch of this set introduces a new generic Netlink based interface,
called "devlink". It is similar to nl80211 model and it is heavily
influenced by it, including the API definition. The devlink introduction patch
implements use cases 1) and 2). Other 2 are in development atm and will
be addressed by follow-ups.

It is very convenient for drivers to use devlink, as you can see in other
patches in this set.

Counterpart for devlink is userspace tool for now called "dl". Command line
interface and outputs are derived from "ip" tool so it should be easy
for users to get used to it.

It is available here as a standalone tool for now:
https://github.com/jpirko/devlink
After this is merge in kernel, I will include the "dl" or "devlink" tool
into iproute2 toolset.

Port type setting example:
	myhost:~$ dl help
	Usage: dl [ OPTIONS ] OBJECT { COMMAND | help }
	where  OBJECT := { dev | port | monitor }
	       OPTIONS := { -v/--verbose }

	myhost:~$ dl dev help
	Usage: dl dev show [DEV]

	myhost:~$ dl dev show
	pci/0000:01:00.0

	myhost:~$ dl port help
	Usage: dl port show [DEV/PORT_INDEX]
	Usage: dl port set DEV/PORT_INDEX [ type { eth | ib | auto} ]
	Usage: dl port split DEV/PORT_INDEX count
	Usage: dl port unsplit DEV/PORT_INDEX

	myhost:~$ dl port show
	pci/0000:01:00.0/1: type ib ibdev mlx4_0
	pci/0000:01:00.0/2: type ib ibdev mlx4_0

	myhost:~$ sudo dl port set pci/0000:01:00.0/1 type eth

	myhost:~$ dl port show
	pci/0000:01:00.0/1: type eth netdev ens4
	pci/0000:01:00.0/2: type ib ibdev mlx4_0

	myhost:~$ sudo dl port set ens4 type auto

	myhost:~$ dl port show
	pci/0000:01:00.0/1: type eth(auto) netdev ens4
	pci/0000:01:00.0/2: type ib ibdev mlx4_0

Port splitting example:
	myswitch:~$ sudo modprobe mlxsw_pci
	myswitch:~$ dl port
	pci/0000:03:00.0/1: type eth netdev eth0
	pci/0000:03:00.0/3: type eth netdev eth1
	pci/0000:03:00.0/5: type eth netdev eth2
	...
	pci/0000:03:00.0/63: type eth netdev eth31

	myswitch:~$ sudo dl port split pci/0000:03:00.0/1 2   (or "sudo dl port split eth0 2")

	myswitch:~$ dl port
	pci/0000:03:00.0/3: type eth netdev eth1
	pci/0000:03:00.0/5: type eth netdev eth2
	...
	pci/0000:03:00.0/63: type eth netdev eth31
	pci/0000:03:00.0/1: type eth netdev eth0 split_group 16
	pci/0000:03:00.0/2: type eth netdev eth32 split_group 16

	myswitch:~$ sudo dl port unsplit pci/0000:03:00.0/1

	myswitch:~$ dl port
	pci/0000:03:00.0/3: type eth netdev eth1
	pci/0000:03:00.0/5: type eth netdev eth2
	pci/0000:03:00.0/63: type eth netdev eth31
	pci/0000:03:00.0/1: type eth netdev eth0

v2->v3:
patch 1/9
 -removed generated devlink index and name, use bus name and dev name as
  a handle for all userspace originated commands. Along with that,
  remove sysfs stub. Requested by Hannes Sowa.
patch 2/9
 -add dev param to devlink_register (api change)
patch 4/9
 -add dev param to devlink_register (api change)
patch 9/9
 -set port's speed according to width fix by Ido
v1->v2:
patch 1/9
 -removed no longer used "devlink_dev" helper
 -fix couple of typos and misspells
patch 4/9:
 -removed SET_NETDEV_DEV set to devlink dev
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

MAINTAINERS

@@ -3499,6 +3499,14 @@ F:	include/linux/device-mapper.h
 F:	include/linux/dm-*.h
 F:	include/uapi/linux/dm-*.h
 
+DEVLINK
+M:	Jiri Pirko <jiri@mellanox.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	net/core/devlink.c
+F:	include/net/devlink.h
+F:	include/uapi/linux/devlink.h
+
 DIALOG SEMICONDUCTOR DRIVERS
 M:	Support Opensource <support.opensource@diasemi.com>
 W:	http://www.dialog-semiconductor.com/products

drivers/infiniband/hw/mlx4/main.c

@@ -41,6 +41,7 @@
 #include <linux/if_vlan.h>
 #include <net/ipv6.h>
 #include <net/addrconf.h>
+#include <net/devlink.h>
 
 #include <rdma/ib_smi.h>
 #include <rdma/ib_user_verbs.h>
@@ -2519,6 +2520,9 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	}
 
 	ibdev->ib_active = true;
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+		devlink_port_type_ib_set(mlx4_get_devlink_port(dev, i),
+					 &ibdev->ib_dev);
 
 	if (mlx4_is_mfunc(ibdev->dev))
 		init_pkeys(ibdev);
@@ -2643,7 +2647,10 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 {
 	struct mlx4_ib_dev *ibdev = ibdev_ptr;
 	int p;
+	int i;
 
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+		devlink_port_type_clear(mlx4_get_devlink_port(dev, i));
 	ibdev->ib_active = false;
 	flush_workqueue(wq);
 

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -40,6 +40,7 @@
 #include <net/ip.h>
 #include <net/busy_poll.h>
 #include <net/vxlan.h>
+#include <net/devlink.h>
 
 #include <linux/mlx4/driver.h>
 #include <linux/mlx4/device.h>
@@ -2033,8 +2034,11 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
 	en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port);
 
 	/* Unregister device - this will close the port if it was up */
-	if (priv->registered)
+	if (priv->registered) {
+		devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev,
+							      priv->port));
 		unregister_netdev(dev);
+	}
 
 	if (priv->allocated)
 		mlx4_free_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE);
@@ -3051,6 +3055,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	}
 
 	priv->registered = 1;
+	devlink_port_type_eth_set(mlx4_get_devlink_port(mdev->dev, priv->port),
+				  dev);
 
 	return 0;
 

drivers/net/ethernet/mellanox/mlx4/intf.c

@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/errno.h>
+#include <net/devlink.h>
 
 #include "mlx4.h"
 
@@ -249,3 +250,11 @@ void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int
 	return result;
 }
 EXPORT_SYMBOL_GPL(mlx4_get_protocol_dev);
+
+struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port)
+{
+	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+
+	return &info->devlink_port;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_devlink_port);

drivers/net/ethernet/mellanox/mlx4/main.c

@@ -42,6 +42,7 @@
 #include <linux/io-mapping.h>
 #include <linux/delay.h>
 #include <linux/kmod.h>
+#include <net/devlink.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
@@ -1081,36 +1082,20 @@ static ssize_t show_port_type(struct device *dev,
 	return strlen(buf);
 }
 
-static ssize_t set_port_type(struct device *dev,
-			     struct device_attribute *attr,
-			     const char *buf, size_t count)
+static int __set_port_type(struct mlx4_port_info *info,
+			   enum mlx4_port_type port_type)
 {
-	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
-						   port_attr);
 	struct mlx4_dev *mdev = info->dev;
 	struct mlx4_priv *priv = mlx4_priv(mdev);
 	enum mlx4_port_type types[MLX4_MAX_PORTS];
 	enum mlx4_port_type new_types[MLX4_MAX_PORTS];
-	static DEFINE_MUTEX(set_port_type_mutex);
 	int i;
 	int err = 0;
 
-	mutex_lock(&set_port_type_mutex);
-
-	if (!strcmp(buf, "ib\n"))
-		info->tmp_type = MLX4_PORT_TYPE_IB;
-	else if (!strcmp(buf, "eth\n"))
-		info->tmp_type = MLX4_PORT_TYPE_ETH;
-	else if (!strcmp(buf, "auto\n"))
-		info->tmp_type = MLX4_PORT_TYPE_AUTO;
-	else {
-		mlx4_err(mdev, "%s is not supported port type\n", buf);
-		err = -EINVAL;
-		goto err_out;
-	}
-
 	mlx4_stop_sense(mdev);
 	mutex_lock(&priv->port_mutex);
+	info->tmp_type = port_type;
+
 	/* Possible type is always the one that was delivered */
 	mdev->caps.possible_type[info->port] = info->tmp_type;
 
@@ -1152,6 +1137,37 @@ static ssize_t set_port_type(struct device *dev,
 out:
 	mlx4_start_sense(mdev);
 	mutex_unlock(&priv->port_mutex);
+
+	return err;
+}
+
+static ssize_t set_port_type(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
+						   port_attr);
+	struct mlx4_dev *mdev = info->dev;
+	enum mlx4_port_type port_type;
+	static DEFINE_MUTEX(set_port_type_mutex);
+	int err;
+
+	mutex_lock(&set_port_type_mutex);
+
+	if (!strcmp(buf, "ib\n")) {
+		port_type = MLX4_PORT_TYPE_IB;
+	} else if (!strcmp(buf, "eth\n")) {
+		port_type = MLX4_PORT_TYPE_ETH;
+	} else if (!strcmp(buf, "auto\n")) {
+		port_type = MLX4_PORT_TYPE_AUTO;
+	} else {
+		mlx4_err(mdev, "%s is not supported port type\n", buf);
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	err = __set_port_type(info, port_type);
+
 err_out:
 	mutex_unlock(&set_port_type_mutex);
 
@@ -2881,8 +2897,13 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 
 static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 {
+	struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
 	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
-	int err = 0;
+	int err;
+
+	err = devlink_port_register(devlink, &info->devlink_port, port);
+	if (err)
+		return err;
 
 	info->dev = dev;
 	info->port = port;
@@ -2907,6 +2928,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 	err = device_create_file(&dev->persist->pdev->dev, &info->port_attr);
 	if (err) {
 		mlx4_err(dev, "Failed to create file for port %d\n", port);
+		devlink_port_unregister(&info->devlink_port);
 		info->port = -1;
 	}
 
@@ -3678,23 +3700,54 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 	return err;
 }
 
+static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port,
+				      enum devlink_port_type port_type)
+{
+	struct mlx4_port_info *info = container_of(devlink_port,
+						   struct mlx4_port_info,
+						   devlink_port);
+	enum mlx4_port_type mlx4_port_type;
+
+	switch (port_type) {
+	case DEVLINK_PORT_TYPE_AUTO:
+		mlx4_port_type = MLX4_PORT_TYPE_AUTO;
+		break;
+	case DEVLINK_PORT_TYPE_ETH:
+		mlx4_port_type = MLX4_PORT_TYPE_ETH;
+		break;
+	case DEVLINK_PORT_TYPE_IB:
+		mlx4_port_type = MLX4_PORT_TYPE_IB;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return __set_port_type(info, mlx4_port_type);
+}
+
+static const struct devlink_ops mlx4_devlink_ops = {
+	.port_type_set	= mlx4_devlink_port_type_set,
+};
+
 static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct devlink *devlink;
 	struct mlx4_priv *priv;
 	struct mlx4_dev *dev;
 	int ret;
 
 	printk_once(KERN_INFO "%s", mlx4_version);
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
+	devlink = devlink_alloc(&mlx4_devlink_ops, sizeof(*priv));
+	if (!devlink)
 		return -ENOMEM;
+	priv = devlink_priv(devlink);
 
 	dev       = &priv->dev;
 	dev->persist = kzalloc(sizeof(*dev->persist), GFP_KERNEL);
 	if (!dev->persist) {
-		kfree(priv);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_devlink_free;
 	}
 	dev->persist->pdev = pdev;
 	dev->persist->dev = dev;
@@ -3703,14 +3756,23 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	mutex_init(&dev->persist->device_state_mutex);
 	mutex_init(&dev->persist->interface_state_mutex);
 
+	ret = devlink_register(devlink, &pdev->dev);
+	if (ret)
+		goto err_persist_free;
+
 	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
-	if (ret) {
-		kfree(dev->persist);
-		kfree(priv);
-	} else {
-		pci_save_state(pdev);
-	}
+	if (ret)
+		goto err_devlink_unregister;
 
+	pci_save_state(pdev);
+	return 0;
+
+err_devlink_unregister:
+	devlink_unregister(devlink);
+err_persist_free:
+	kfree(dev->persist);
+err_devlink_free:
+	devlink_free(devlink);
 	return ret;
 }
 
@@ -3811,6 +3873,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
 	struct mlx4_dev  *dev  = persist->dev;
 	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct devlink *devlink = priv_to_devlink(priv);
 	int active_vfs = 0;
 
 	mutex_lock(&persist->interface_state_mutex);
@@ -3841,8 +3904,9 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
+	devlink_unregister(devlink);
 	kfree(dev->persist);
-	kfree(priv);
+	devlink_free(devlink);
 	pci_set_drvdata(pdev, NULL);
 }
 

drivers/net/ethernet/mellanox/mlx4/mlx4.h

@@ -45,6 +45,7 @@
 #include <linux/workqueue.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
+#include <net/devlink.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/driver.h>
@@ -828,6 +829,7 @@ struct mlx4_port_info {
 	struct mlx4_roce_gid_table gid_table;
 	int			base_qpn;
 	struct cpu_rmap		*rmap;
+	struct devlink_port	devlink_port;
 };
 
 struct mlx4_sense {

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

@@ -56,6 +56,7 @@
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
 #include <asm/byteorder.h>
+#include <net/devlink.h>
 
 #include "core.h"
 #include "item.h"
@@ -784,6 +785,38 @@ static void mlxsw_core_debugfs_fini(struct mlxsw_core *mlxsw_core)
 	debugfs_remove_recursive(mlxsw_core->dbg_dir);
 }
 
+static int mlxsw_devlink_port_split(struct devlink *devlink,
+				    unsigned int port_index,
+				    unsigned int count)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+
+	if (port_index >= MLXSW_PORT_MAX_PORTS)
+		return -EINVAL;
+	if (!mlxsw_core->driver->port_split)
+		return -EOPNOTSUPP;
+	return mlxsw_core->driver->port_split(mlxsw_core->driver_priv,
+					      port_index, count);
+}
+
+static int mlxsw_devlink_port_unsplit(struct devlink *devlink,
+				      unsigned int port_index)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+
+	if (port_index >= MLXSW_PORT_MAX_PORTS)
+		return -EINVAL;
+	if (!mlxsw_core->driver->port_unsplit)
+		return -EOPNOTSUPP;
+	return mlxsw_core->driver->port_unsplit(mlxsw_core->driver_priv,
+						port_index);
+}
+
+static const struct devlink_ops mlxsw_devlink_ops = {
+	.port_split	= mlxsw_devlink_port_split,
+	.port_unsplit	= mlxsw_devlink_port_unsplit,
+};
+
 int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 				   const struct mlxsw_bus *mlxsw_bus,
 				   void *bus_priv)
@@ -791,6 +824,7 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	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;
 
@@ -798,12 +832,13 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (!mlxsw_driver)
 		return -EINVAL;
 	alloc_size = sizeof(*mlxsw_core) + mlxsw_driver->priv_size;
-	mlxsw_core = kzalloc(alloc_size, GFP_KERNEL);
-	if (!mlxsw_core) {
+	devlink = devlink_alloc(&mlxsw_devlink_ops, alloc_size);
+	if (!devlink) {
 		err = -ENOMEM;
-		goto err_core_alloc;
+		goto err_devlink_alloc;
 	}
 
+	mlxsw_core = devlink_priv(devlink);
 	INIT_LIST_HEAD(&mlxsw_core->rx_listener_list);
 	INIT_LIST_HEAD(&mlxsw_core->event_listener_list);
 	mlxsw_core->driver = mlxsw_driver;
@@ -841,6 +876,10 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_hwmon_init;
 
+	err = devlink_register(devlink, mlxsw_bus_info->dev);
+	if (err)
+		goto err_devlink_register;
+
 	err = mlxsw_driver->init(mlxsw_core->driver_priv, mlxsw_core,
 				 mlxsw_bus_info);
 	if (err)
@@ -855,6 +894,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 err_debugfs_init:
 	mlxsw_core->driver->fini(mlxsw_core->driver_priv);
 err_driver_init:
+	devlink_unregister(devlink);
+err_devlink_register:
 err_hwmon_init:
 	mlxsw_emad_fini(mlxsw_core);
 err_emad_init:
@@ -864,8 +905,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 err_alloc_lag_mapping:
 	free_percpu(mlxsw_core->pcpu_stats);
 err_alloc_stats:
-	kfree(mlxsw_core);
-err_core_alloc:
+	devlink_free(devlink);
+err_devlink_alloc:
 	mlxsw_core_driver_put(device_kind);
 	return err;
 }
@@ -874,14 +915,16 @@ EXPORT_SYMBOL(mlxsw_core_bus_device_register);
 void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
 {
 	const char *device_kind = mlxsw_core->bus_info->device_kind;
+	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
 	mlxsw_core_debugfs_fini(mlxsw_core);
 	mlxsw_core->driver->fini(mlxsw_core->driver_priv);
+	devlink_unregister(devlink);
 	mlxsw_emad_fini(mlxsw_core);
 	mlxsw_core->bus->fini(mlxsw_core->bus_priv);
 	kfree(mlxsw_core->lag.mapping);
 	free_percpu(mlxsw_core->pcpu_stats);
-	kfree(mlxsw_core);
+	devlink_free(devlink);
 	mlxsw_core_driver_put(device_kind);
 }
 EXPORT_SYMBOL(mlxsw_core_bus_device_unregister);

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

@@ -186,6 +186,8 @@ struct mlxsw_driver {
 	int (*init)(void *driver_priv, struct mlxsw_core *mlxsw_core,
 		    const struct mlxsw_bus_info *mlxsw_bus_info);
 	void (*fini)(void *driver_priv);
+	int (*port_split)(void *driver_priv, u8 local_port, unsigned int count);
+	int (*port_unsplit)(void *driver_priv, u8 local_port);
 	void (*txhdr_construct)(struct sk_buff *skb,
 				const struct mlxsw_tx_info *tx_info);
 	u8 txhdr_len;

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

@@ -59,6 +59,8 @@
 
 #define MLXSW_PORT_DONT_CARE		(MLXSW_PORT_MAX_PORTS)
 
+#define MLXSW_PORT_MODULE_MAX_WIDTH	4
+
 enum mlxsw_port_admin_status {
 	MLXSW_PORT_ADMIN_STATUS_UP = 1,
 	MLXSW_PORT_ADMIN_STATUS_DOWN = 2,

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

@@ -43,6 +43,7 @@
 #include <linux/if_vlan.h>
 #include <linux/list.h>
 #include <net/switchdev.h>
+#include <net/devlink.h>
 
 #include "port.h"
 #include "core.h"
@@ -57,6 +58,10 @@
 
 #define MLXSW_SP_MID_MAX 7000
 
+#define MLXSW_SP_PORTS_PER_CLUSTER_MAX 4
+
+#define MLXSW_SP_PORT_BASE_SPEED 25000	/* Mb/s */
+
 struct mlxsw_sp_port;
 
 struct mlxsw_sp_upper {
@@ -122,6 +127,7 @@ struct mlxsw_sp {
 	u32 ageing_time;
 	struct mlxsw_sp_upper master_bridge;
 	struct mlxsw_sp_upper lags[MLXSW_SP_LAG_MAX];
+	u8 port_to_module[MLXSW_PORT_MAX_PORTS];
 };
 
 static inline struct mlxsw_sp_upper *
@@ -149,7 +155,8 @@ struct mlxsw_sp_port {
 	   learning_sync:1,
 	   uc_flood:1,
 	   bridged:1,
-	   lagged:1;
+	   lagged:1,
+	   split:1;
 	u16 pvid;
 	u16 lag_id;
 	struct {
@@ -162,6 +169,7 @@ struct mlxsw_sp_port {
 	unsigned long *untagged_vlans;
 	/* VLAN interfaces */
 	struct list_head vports_list;
+	struct devlink_port devlink_port;
 };
 
 static inline struct mlxsw_sp_port *

drivers/net/ethernet/mellanox/mlxsw/switchx2.c

@@ -43,6 +43,7 @@
 #include <linux/device.h>
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
+#include <net/devlink.h>
 #include <net/switchdev.h>
 #include <generated/utsrelease.h>
 
@@ -78,6 +79,7 @@ struct mlxsw_sx_port {
 	struct mlxsw_sx_port_pcpu_stats __percpu *pcpu_stats;
 	struct mlxsw_sx *mlxsw_sx;
 	u8 local_port;
+	struct devlink_port devlink_port;
 };
 
 /* tx_hdr_version
@@ -953,7 +955,9 @@ mlxsw_sx_port_mac_learning_mode_set(struct mlxsw_sx_port *mlxsw_sx_port,
 
 static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 {
+	struct devlink *devlink = priv_to_devlink(mlxsw_sx->core);
 	struct mlxsw_sx_port *mlxsw_sx_port;
+	struct devlink_port *devlink_port;
 	struct net_device *dev;
 	bool usable;
 	int err;
@@ -1007,6 +1011,14 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 		goto port_not_usable;
 	}
 
+	devlink_port = &mlxsw_sx_port->devlink_port;
+	err = devlink_port_register(devlink, devlink_port, local_port);
+	if (err) {
+		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to register devlink port\n",
+			mlxsw_sx_port->local_port);
+		goto err_devlink_port_register;
+	}
+
 	err = mlxsw_sx_port_system_port_mapping_set(mlxsw_sx_port);
 	if (err) {
 		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set system port mapping\n",
@@ -1064,6 +1076,8 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 		goto err_register_netdev;
 	}
 
+	devlink_port_type_eth_set(devlink_port, dev);
+
 	mlxsw_sx->ports[local_port] = mlxsw_sx_port;
 	return 0;
 
@@ -1075,6 +1089,8 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 err_port_speed_set:
 err_port_swid_set:
 err_port_system_port_mapping_set:
+	devlink_port_unregister(&mlxsw_sx_port->devlink_port);
+err_devlink_port_register:
 port_not_usable:
 err_port_module_check:
 err_dev_addr_get:
@@ -1087,11 +1103,15 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 static void mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
 {
 	struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port];
+	struct devlink_port *devlink_port;
 
 	if (!mlxsw_sx_port)
 		return;
+	devlink_port = &mlxsw_sx_port->devlink_port;
+	devlink_port_type_clear(devlink_port);
 	unregister_netdev(mlxsw_sx_port->dev); /* This calls ndo_stop */
 	mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
+	devlink_port_unregister(devlink_port);
 	free_percpu(mlxsw_sx_port->pcpu_stats);
 	free_netdev(mlxsw_sx_port->dev);
 }

include/linux/mlx4/driver.h

@@ -33,6 +33,7 @@
 #ifndef MLX4_DRIVER_H
 #define MLX4_DRIVER_H
 
+#include <net/devlink.h>
 #include <linux/mlx4/device.h>
 
 struct mlx4_dev;
@@ -89,6 +90,8 @@ int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p);
 
 void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port);
 
+struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port);
+
 static inline u64 mlx4_mac_to_u64(u8 *addr)
 {
 	u64 mac = 0;

include/net/devlink.h

+/*
+ * include/net/devlink.h - Network physical device Netlink interface
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef _NET_DEVLINK_H_
+#define _NET_DEVLINK_H_
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/gfp.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <net/net_namespace.h>
+#include <uapi/linux/devlink.h>
+
+struct devlink_ops;
+
+struct devlink {
+	struct list_head list;
+	struct list_head port_list;
+	const struct devlink_ops *ops;
+	struct device *dev;
+	possible_net_t _net;
+	char priv[0] __aligned(NETDEV_ALIGN);
+};
+
+struct devlink_port {
+	struct list_head list;
+	struct devlink *devlink;
+	unsigned index;
+	bool registered;
+	enum devlink_port_type type;
+	enum devlink_port_type desired_type;
+	void *type_dev;
+	bool split;
+	u32 split_group;
+};
+
+struct devlink_ops {
+	size_t priv_size;
+	int (*port_type_set)(struct devlink_port *devlink_port,
+			     enum devlink_port_type port_type);
+	int (*port_split)(struct devlink *devlink, unsigned int port_index,
+			  unsigned int count);
+	int (*port_unsplit)(struct devlink *devlink, unsigned int port_index);
+};
+
+static inline void *devlink_priv(struct devlink *devlink)
+{
+	BUG_ON(!devlink);
+	return &devlink->priv;
+}
+
+static inline struct devlink *priv_to_devlink(void *priv)
+{
+	BUG_ON(!priv);
+	return container_of(priv, struct devlink, priv);
+}
+
+struct ib_device;
+
+#if IS_ENABLED(CONFIG_NET_DEVLINK)
+
+struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size);
+int devlink_register(struct devlink *devlink, struct device *dev);
+void devlink_unregister(struct devlink *devlink);
+void devlink_free(struct devlink *devlink);
+int devlink_port_register(struct devlink *devlink,
+			  struct devlink_port *devlink_port,
+			  unsigned int port_index);
+void devlink_port_unregister(struct devlink_port *devlink_port);
+void devlink_port_type_eth_set(struct devlink_port *devlink_port,
+			       struct net_device *netdev);
+void devlink_port_type_ib_set(struct devlink_port *devlink_port,
+			      struct ib_device *ibdev);
+void devlink_port_type_clear(struct devlink_port *devlink_port);
+void devlink_port_split_set(struct devlink_port *devlink_port,
+			    u32 split_group);
+
+#else
+
+static inline struct devlink *devlink_alloc(const struct devlink_ops *ops,
+					    size_t priv_size)
+{
+	return kzalloc(sizeof(struct devlink) + priv_size, GFP_KERNEL);
+}
+
+static inline int devlink_register(struct devlink *devlink, struct device *dev)
+{
+	return 0;
+}
+
+static inline void devlink_unregister(struct devlink *devlink)
+{
+}
+
+static inline void devlink_free(struct devlink *devlink)
+{
+	kfree(devlink);
+}
+
+static inline int devlink_port_register(struct devlink *devlink,
+					struct devlink_port *devlink_port,
+					unsigned int port_index)
+{
+	return 0;
+}
+
+static inline void devlink_port_unregister(struct devlink_port *devlink_port)
+{
+}
+
+static inline void devlink_port_type_eth_set(struct devlink_port *devlink_port,
+					     struct net_device *netdev)
+{
+}
+
+static inline void devlink_port_type_ib_set(struct devlink_port *devlink_port,
+					    struct ib_device *ibdev)
+{
+}
+
+static inline void devlink_port_type_clear(struct devlink_port *devlink_port)
+{
+}
+
+static inline void devlink_port_split_set(struct devlink_port *devlink_port,
+					  u32 split_group)
+{
+}
+
+#endif
+
+#endif /* _NET_DEVLINK_H_ */

include/uapi/linux/devlink.h

+/*
+ * include/uapi/linux/devlink.h - Network physical device Netlink interface
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_DEVLINK_H_
+#define _UAPI_LINUX_DEVLINK_H_
+
+#define DEVLINK_GENL_NAME "devlink"
+#define DEVLINK_GENL_VERSION 0x1
+#define DEVLINK_GENL_MCGRP_CONFIG_NAME "config"
+
+enum devlink_command {
+	/* don't change the order or add anything between, this is ABI! */
+	DEVLINK_CMD_UNSPEC,
+
+	DEVLINK_CMD_GET,		/* can dump */
+	DEVLINK_CMD_SET,
+	DEVLINK_CMD_NEW,
+	DEVLINK_CMD_DEL,
+
+	DEVLINK_CMD_PORT_GET,		/* can dump */
+	DEVLINK_CMD_PORT_SET,
+	DEVLINK_CMD_PORT_NEW,
+	DEVLINK_CMD_PORT_DEL,
+
+	DEVLINK_CMD_PORT_SPLIT,
+	DEVLINK_CMD_PORT_UNSPLIT,
+
+	/* add new commands above here */
+
+	__DEVLINK_CMD_MAX,
+	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
+};
+
+enum devlink_port_type {
+	DEVLINK_PORT_TYPE_NOTSET,
+	DEVLINK_PORT_TYPE_AUTO,
+	DEVLINK_PORT_TYPE_ETH,
+	DEVLINK_PORT_TYPE_IB,
+};
+
+enum devlink_attr {
+	/* don't change the order or add anything between, this is ABI! */
+	DEVLINK_ATTR_UNSPEC,
+
+	/* bus name + dev name together are a handle for devlink entity */
+	DEVLINK_ATTR_BUS_NAME,			/* string */
+	DEVLINK_ATTR_DEV_NAME,			/* string */
+
+	DEVLINK_ATTR_PORT_INDEX,		/* u32 */
+	DEVLINK_ATTR_PORT_TYPE,			/* u16 */
+	DEVLINK_ATTR_PORT_DESIRED_TYPE,		/* u16 */
+	DEVLINK_ATTR_PORT_NETDEV_IFINDEX,	/* u32 */
+	DEVLINK_ATTR_PORT_NETDEV_NAME,		/* string */
+	DEVLINK_ATTR_PORT_IBDEV_NAME,		/* string */
+	DEVLINK_ATTR_PORT_SPLIT_COUNT,		/* u32 */
+	DEVLINK_ATTR_PORT_SPLIT_GROUP,		/* u32 */
+
+	/* add new attributes above here, update the policy in devlink.c */
+
+	__DEVLINK_ATTR_MAX,
+	DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1
+};
+
+#endif /* _UAPI_LINUX_DEVLINK_H_ */

net/Kconfig

@@ -396,6 +396,13 @@ config DST_CACHE
 	bool "dst cache"
 	default n
 
+config NET_DEVLINK
+	tristate "Network physical/parent device Netlink interface"
+	help
+	  Network physical/parent device Netlink interface provides
+	  infrastructure to support access to physical chip-wide config and
+	  monitoring.
+
 endif   # if NET
 
 # Used by archs to tell that they support BPF_JIT

net/core/Makefile

@@ -25,3 +25,4 @@ obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
 obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o
 obj-$(CONFIG_LWTUNNEL) += lwtunnel.o
 obj-$(CONFIG_DST_CACHE) += dst_cache.o
+obj-$(CONFIG_NET_DEVLINK) += devlink.o