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>

18 files changed, 1425 insertions, 59 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 12b764f4c93c..e45682745263 100644
--- a/MAINTAINERS
+++ b/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
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 1c7ab6cabbb8..a15a7b37d386 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/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);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 96d95cb36c52..e26b110e27da 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/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;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 0472941af820..dec77d6f0ac9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/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);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 2cc3c626c3fe..b8a51515e73c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/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 @@ no_msi:
 
 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 @@ err_disable_pdev:
 	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);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 7baef52db6b7..ef9683101ead 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/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 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 22379eb8e924..f69f6280519f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/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 @@ err_bus_init:
 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);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index a01723600f0a..c73d1c0792a6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/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;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index ae65b9940aed..f33b997f2b61 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/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,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 09ce451c283b..53487d3eb9f6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -49,6 +49,7 @@
 #include <linux/jiffies.h>
 #include <linux/bitops.h>
 #include <linux/list.h>
+#include <net/devlink.h>
 #include <net/switchdev.h>
 #include <generated/utsrelease.h>
 
@@ -304,21 +305,47 @@ mlxsw_sp_port_system_port_mapping_set(struct mlxsw_sp_port *mlxsw_sp_port)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sspr), sspr_pl);
 }
 
-static int mlxsw_sp_port_module_check(struct mlxsw_sp_port *mlxsw_sp_port,
-				      bool *p_usable)
+static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
+					 u8 local_port, u8 *p_module,
+					 u8 *p_width)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char pmlp_pl[MLXSW_REG_PMLP_LEN];
 	int err;
 
-	mlxsw_reg_pmlp_pack(pmlp_pl, mlxsw_sp_port->local_port);
+	mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl);
 	if (err)
 		return err;
-	*p_usable = mlxsw_reg_pmlp_width_get(pmlp_pl) ? true : false;
+	*p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
+	*p_width = mlxsw_reg_pmlp_width_get(pmlp_pl);
 	return 0;
 }
 
+static int mlxsw_sp_port_module_map(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				    u8 module, u8 width, u8 lane)
+{
+	char pmlp_pl[MLXSW_REG_PMLP_LEN];
+	int i;
+
+	mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
+	mlxsw_reg_pmlp_width_set(pmlp_pl, width);
+	for (i = 0; i < width; i++) {
+		mlxsw_reg_pmlp_module_set(pmlp_pl, i, module);
+		mlxsw_reg_pmlp_tx_lane_set(pmlp_pl, i, lane + i);  /* Rx & Tx */
+	}
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl);
+}
+
+static int mlxsw_sp_port_module_unmap(struct mlxsw_sp *mlxsw_sp, u8 local_port)
+{
+	char pmlp_pl[MLXSW_REG_PMLP_LEN];
+
+	mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
+	mlxsw_reg_pmlp_width_set(pmlp_pl, 0);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl);
+}
+
 static int mlxsw_sp_port_open(struct net_device *dev)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
@@ -1273,6 +1300,18 @@ static u32 mlxsw_sp_to_ptys_speed(u32 speed)
 	return ptys_proto;
 }
 
+static u32 mlxsw_sp_to_ptys_upper_speed(u32 upper_speed)
+{
+	u32 ptys_proto = 0;
+	int i;
+
+	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
+		if (mlxsw_sp_port_link_mode[i].speed <= upper_speed)
+			ptys_proto |= mlxsw_sp_port_link_mode[i].mask;
+	}
+	return ptys_proto;
+}
+
 static int mlxsw_sp_port_set_settings(struct net_device *dev,
 				      struct ethtool_cmd *cmd)
 {
@@ -1349,11 +1388,27 @@ static const struct ethtool_ops mlxsw_sp_port_ethtool_ops = {
 	.set_settings		= mlxsw_sp_port_set_settings,
 };
 
-static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port)
+static int
+mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 width)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	u32 upper_speed = MLXSW_SP_PORT_BASE_SPEED * width;
+	char ptys_pl[MLXSW_REG_PTYS_LEN];
+	u32 eth_proto_admin;
+
+	eth_proto_admin = mlxsw_sp_to_ptys_upper_speed(upper_speed);
+	mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port,
+			    eth_proto_admin);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
+}
+
+static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				  bool split, u8 module, u8 width)
 {
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
+	struct devlink_port *devlink_port;
 	struct net_device *dev;
-	bool usable;
 	size_t bytes;
 	int err;
 
@@ -1364,6 +1419,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 	mlxsw_sp_port->dev = dev;
 	mlxsw_sp_port->mlxsw_sp = mlxsw_sp;
 	mlxsw_sp_port->local_port = local_port;
+	mlxsw_sp_port->split = split;
 	bytes = DIV_ROUND_UP(VLAN_N_VID, BITS_PER_BYTE);
 	mlxsw_sp_port->active_vlans = kzalloc(bytes, GFP_KERNEL);
 	if (!mlxsw_sp_port->active_vlans) {
@@ -1404,17 +1460,14 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 	 */
 	dev->hard_header_len += MLXSW_TXHDR_LEN;
 
-	err = mlxsw_sp_port_module_check(mlxsw_sp_port, &usable);
+	devlink_port = &mlxsw_sp_port->devlink_port;
+	if (mlxsw_sp_port->split)
+		devlink_port_split_set(devlink_port, module);
+	err = devlink_port_register(devlink, devlink_port, local_port);
 	if (err) {
-		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to check module\n",
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to register devlink port\n",
 			mlxsw_sp_port->local_port);
-		goto err_port_module_check;
-	}
-
-	if (!usable) {
-		dev_dbg(mlxsw_sp->bus_info->dev, "Port %d: Not usable, skipping initialization\n",
-			mlxsw_sp_port->local_port);
-		goto port_not_usable;
+		goto err_devlink_port_register;
 	}
 
 	err = mlxsw_sp_port_system_port_mapping_set(mlxsw_sp_port);
@@ -1431,6 +1484,13 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 		goto err_port_swid_set;
 	}
 
+	err = mlxsw_sp_port_speed_by_width_set(mlxsw_sp_port, width);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to enable speeds\n",
+			mlxsw_sp_port->local_port);
+		goto err_port_speed_by_width_set;
+	}
+
 	err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, ETH_DATA_LEN);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set MTU\n",
@@ -1457,6 +1517,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 		goto err_register_netdev;
 	}
 
+	devlink_port_type_eth_set(devlink_port, dev);
+
 	err = mlxsw_sp_port_vlan_init(mlxsw_sp_port);
 	if (err)
 		goto err_port_vlan_init;
@@ -1470,10 +1532,11 @@ err_register_netdev:
 err_port_buffers_init:
 err_port_admin_status_set:
 err_port_mtu_set:
+err_port_speed_by_width_set:
 err_port_swid_set:
 err_port_system_port_mapping_set:
-port_not_usable:
-err_port_module_check:
+	devlink_port_unregister(&mlxsw_sp_port->devlink_port);
+err_devlink_port_register:
 err_dev_addr_init:
 	free_percpu(mlxsw_sp_port->pcpu_stats);
 err_alloc_stats:
@@ -1485,6 +1548,28 @@ err_port_active_vlans_alloc:
 	return err;
 }
 
+static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				bool split, u8 module, u8 width, u8 lane)
+{
+	int err;
+
+	err = mlxsw_sp_port_module_map(mlxsw_sp, local_port, module, width,
+				       lane);
+	if (err)
+		return err;
+
+	err = __mlxsw_sp_port_create(mlxsw_sp, local_port, split, module,
+				     width);
+	if (err)
+		goto err_port_create;
+
+	return 0;
+
+err_port_create:
+	mlxsw_sp_port_module_unmap(mlxsw_sp, local_port);
+	return err;
+}
+
 static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 {
 	struct net_device *dev = mlxsw_sp_port->dev;
@@ -1505,12 +1590,19 @@ static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	struct devlink_port *devlink_port;
 
 	if (!mlxsw_sp_port)
 		return;
+	mlxsw_sp->ports[local_port] = NULL;
+	devlink_port = &mlxsw_sp_port->devlink_port;
+	devlink_port_type_clear(devlink_port);
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
+	devlink_port_unregister(devlink_port);
 	mlxsw_sp_port_vports_fini(mlxsw_sp_port);
 	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
+	mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
+	mlxsw_sp_port_module_unmap(mlxsw_sp, mlxsw_sp_port->local_port);
 	free_percpu(mlxsw_sp_port->pcpu_stats);
 	kfree(mlxsw_sp_port->untagged_vlans);
 	kfree(mlxsw_sp_port->active_vlans);
@@ -1529,6 +1621,7 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp)
 static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
 {
 	size_t alloc_size;
+	u8 module, width;
 	int i;
 	int err;
 
@@ -1538,19 +1631,158 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
 		return -ENOMEM;
 
 	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
-		err = mlxsw_sp_port_create(mlxsw_sp, i);
+		err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &module,
+						    &width);
+		if (err)
+			goto err_port_module_info_get;
+		if (!width)
+			continue;
+		mlxsw_sp->port_to_module[i] = module;
+		err = __mlxsw_sp_port_create(mlxsw_sp, i, false, module, width);
 		if (err)
 			goto err_port_create;
 	}
 	return 0;
 
 err_port_create:
+err_port_module_info_get:
 	for (i--; i >= 1; i--)
 		mlxsw_sp_port_remove(mlxsw_sp, i);
 	kfree(mlxsw_sp->ports);
 	return err;
 }
 
+static u8 mlxsw_sp_cluster_base_port_get(u8 local_port)
+{
+	u8 offset = (local_port - 1) % MLXSW_SP_PORTS_PER_CLUSTER_MAX;
+
+	return local_port - offset;
+}
+
+static int mlxsw_sp_port_split(void *priv, u8 local_port, unsigned int count)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count;
+	u8 module, cur_width, base_port;
+	int i;
+	int err;
+
+	mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	if (!mlxsw_sp_port) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n",
+			local_port);
+		return -EINVAL;
+	}
+
+	if (count != 2 && count != 4) {
+		netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n");
+		return -EINVAL;
+	}
+
+	err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module,
+					    &cur_width);
+	if (err) {
+		netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n");
+		return err;
+	}
+
+	if (cur_width != MLXSW_PORT_MODULE_MAX_WIDTH) {
+		netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n");
+		return -EINVAL;
+	}
+
+	/* Make sure we have enough slave (even) ports for the split. */
+	if (count == 2) {
+		base_port = local_port;
+		if (mlxsw_sp->ports[base_port + 1]) {
+			netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n");
+			return -EINVAL;
+		}
+	} else {
+		base_port = mlxsw_sp_cluster_base_port_get(local_port);
+		if (mlxsw_sp->ports[base_port + 1] ||
+		    mlxsw_sp->ports[base_port + 3]) {
+			netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n");
+			return -EINVAL;
+		}
+	}
+
+	for (i = 0; i < count; i++)
+		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+
+	for (i = 0; i < count; i++) {
+		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true,
+					   module, width, i * width);
+		if (err) {
+			dev_err(mlxsw_sp->bus_info->dev, "Failed to create split port\n");
+			goto err_port_create;
+		}
+	}
+
+	return 0;
+
+err_port_create:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+	for (i = 0; i < count / 2; i++) {
+		module = mlxsw_sp->port_to_module[base_port + i * 2];
+		mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false,
+				     module, MLXSW_PORT_MODULE_MAX_WIDTH, 0);
+	}
+	return err;
+}
+
+static int mlxsw_sp_port_unsplit(void *priv, u8 local_port)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	u8 module, cur_width, base_port;
+	unsigned int count;
+	int i;
+	int err;
+
+	mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	if (!mlxsw_sp_port) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n",
+			local_port);
+		return -EINVAL;
+	}
+
+	if (!mlxsw_sp_port->split) {
+		netdev_err(mlxsw_sp_port->dev, "Port wasn't split\n");
+		return -EINVAL;
+	}
+
+	err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module,
+					    &cur_width);
+	if (err) {
+		netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n");
+		return err;
+	}
+	count = cur_width == 1 ? 4 : 2;
+
+	base_port = mlxsw_sp_cluster_base_port_get(local_port);
+
+	/* Determine which ports to remove. */
+	if (count == 2 && local_port >= base_port + 2)
+		base_port = base_port + 2;
+
+	for (i = 0; i < count; i++)
+		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+
+	for (i = 0; i < count / 2; i++) {
+		module = mlxsw_sp->port_to_module[base_port + i * 2];
+		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false,
+					   module, MLXSW_PORT_MODULE_MAX_WIDTH,
+					   0);
+		if (err)
+			dev_err(mlxsw_sp->bus_info->dev, "Failed to reinstantiate port\n");
+	}
+
+	return 0;
+}
+
 static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
 				     char *pude_pl, void *priv)
 {
@@ -1974,6 +2206,8 @@ static struct mlxsw_driver mlxsw_sp_driver = {
 	.priv_size		= sizeof(struct mlxsw_sp),
 	.init			= mlxsw_sp_init,
 	.fini			= mlxsw_sp_fini,
+	.port_split		= mlxsw_sp_port_split,
+	.port_unsplit		= mlxsw_sp_port_unsplit,
 	.txhdr_construct	= mlxsw_sp_txhdr_construct,
 	.txhdr_len		= MLXSW_TXHDR_LEN,
 	.profile		= &mlxsw_sp_config_profile,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 3b89ed2f3c76..1b691d7e4a2a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/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 *
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index d85960cfb694..7a60a26759b6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/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 @@ err_port_mtu_set:
 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 @@ err_alloc_stats:
 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);
 }
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 2e8af001c5da..bd0e7075ea6d 100644
--- a/include/linux/mlx4/driver.h
+++ b/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;
diff --git a/include/net/devlink.h b/include/net/devlink.h
new file mode 100644
index 000000000000..c37d257891d6
--- /dev/null
+++ b/include/net/devlink.h
@@ -0,0 +1,140 @@
+/*
+ * 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_ */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
new file mode 100644
index 000000000000..c9fee5781eb1
--- /dev/null
+++ b/include/uapi/linux/devlink.h
@@ -0,0 +1,72 @@
+/*
+ * 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_ */
diff --git a/net/Kconfig b/net/Kconfig
index b80efecfc1a0..6c9cfb0d7639 100644
--- a/net/Kconfig
+++ b/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
diff --git a/net/core/Makefile b/net/core/Makefile
index 7a8fb8aef992..014422e2561f 100644
--- a/net/core/Makefile
+++ b/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
diff --git a/net/core/devlink.c b/net/core/devlink.c
new file mode 100644
index 000000000000..590fa561cb7f
--- /dev/null
+++ b/net/core/devlink.c
@@ -0,0 +1,738 @@
+/*
+ * net/core/devlink.c - Network physical/parent device Netlink interface
+ *
+ * Heavily inspired by net/wireless/
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/gfp.h>
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <rdma/ib_verbs.h>
+#include <net/netlink.h>
+#include <net/genetlink.h>
+#include <net/rtnetlink.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+#include <net/devlink.h>
+
+static LIST_HEAD(devlink_list);
+
+/* devlink_mutex
+ *
+ * An overall lock guarding every operation coming from userspace.
+ * It also guards devlink devices list and it is taken when
+ * driver registers/unregisters it.
+ */
+static DEFINE_MUTEX(devlink_mutex);
+
+/* devlink_port_mutex
+ *
+ * Shared lock to guard lists of ports in all devlink devices.
+ */
+static DEFINE_MUTEX(devlink_port_mutex);
+
+static struct net *devlink_net(const struct devlink *devlink)
+{
+	return read_pnet(&devlink->_net);
+}
+
+static void devlink_net_set(struct devlink *devlink, struct net *net)
+{
+	write_pnet(&devlink->_net, net);
+}
+
+static struct devlink *devlink_get_from_attrs(struct net *net,
+					      struct nlattr **attrs)
+{
+	struct devlink *devlink;
+	char *busname;
+	char *devname;
+
+	if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME])
+		return ERR_PTR(-EINVAL);
+
+	busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]);
+	devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]);
+
+	list_for_each_entry(devlink, &devlink_list, list) {
+		if (strcmp(devlink->dev->bus->name, busname) == 0 &&
+		    strcmp(dev_name(devlink->dev), devname) == 0 &&
+		    net_eq(devlink_net(devlink), net))
+			return devlink;
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
+static struct devlink *devlink_get_from_info(struct genl_info *info)
+{
+	return devlink_get_from_attrs(genl_info_net(info), info->attrs);
+}
+
+static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink,
+						      int port_index)
+{
+	struct devlink_port *devlink_port;
+
+	list_for_each_entry(devlink_port, &devlink->port_list, list) {
+		if (devlink_port->index == port_index)
+			return devlink_port;
+	}
+	return NULL;
+}
+
+static bool devlink_port_index_exists(struct devlink *devlink, int port_index)
+{
+	return devlink_port_get_by_index(devlink, port_index);
+}
+
+static struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink,
+							struct nlattr **attrs)
+{
+	if (attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]);
+		struct devlink_port *devlink_port;
+
+		devlink_port = devlink_port_get_by_index(devlink, port_index);
+		if (!devlink_port)
+			return ERR_PTR(-ENODEV);
+		return devlink_port;
+	}
+	return ERR_PTR(-EINVAL);
+}
+
+static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink,
+						       struct genl_info *info)
+{
+	return devlink_port_get_from_attrs(devlink, info->attrs);
+}
+
+#define DEVLINK_NL_FLAG_NEED_PORT	BIT(0)
+
+static int devlink_nl_pre_doit(const struct genl_ops *ops,
+			       struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink;
+
+	mutex_lock(&devlink_mutex);
+	devlink = devlink_get_from_info(info);
+	if (IS_ERR(devlink)) {
+		mutex_unlock(&devlink_mutex);
+		return PTR_ERR(devlink);
+	}
+	info->user_ptr[0] = devlink;
+	if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) {
+		struct devlink_port *devlink_port;
+
+		mutex_lock(&devlink_port_mutex);
+		devlink_port = devlink_port_get_from_info(devlink, info);
+		if (IS_ERR(devlink_port)) {
+			mutex_unlock(&devlink_port_mutex);
+			mutex_unlock(&devlink_mutex);
+			return PTR_ERR(devlink_port);
+		}
+		info->user_ptr[1] = devlink_port;
+	}
+	return 0;
+}
+
+static void devlink_nl_post_doit(const struct genl_ops *ops,
+				 struct sk_buff *skb, struct genl_info *info)
+{
+	if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT)
+		mutex_unlock(&devlink_port_mutex);
+	mutex_unlock(&devlink_mutex);
+}
+
+static struct genl_family devlink_nl_family = {
+	.id		= GENL_ID_GENERATE,
+	.name		= DEVLINK_GENL_NAME,
+	.version	= DEVLINK_GENL_VERSION,
+	.maxattr	= DEVLINK_ATTR_MAX,
+	.netnsok	= true,
+	.pre_doit	= devlink_nl_pre_doit,
+	.post_doit	= devlink_nl_post_doit,
+};
+
+enum devlink_multicast_groups {
+	DEVLINK_MCGRP_CONFIG,
+};
+
+static const struct genl_multicast_group devlink_nl_mcgrps[] = {
+	[DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME },
+};
+
+static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
+{
+	if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name))
+		return -EMSGSIZE;
+	if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev)))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
+			   enum devlink_command cmd, u32 portid,
+			   u32 seq, int flags)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static void devlink_notify(struct devlink *devlink, enum devlink_command cmd)
+{
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
+				struct devlink_port *devlink_port,
+				enum devlink_command cmd, u32 portid,
+				u32 seq, int flags)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
+		goto nla_put_failure;
+	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))
+		goto nla_put_failure;
+	if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET &&
+	    nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE,
+			devlink_port->desired_type))
+		goto nla_put_failure;
+	if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
+		struct net_device *netdev = devlink_port->type_dev;
+
+		if (netdev &&
+		    (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
+				 netdev->ifindex) ||
+		     nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,
+				    netdev->name)))
+			goto nla_put_failure;
+	}
+	if (devlink_port->type == DEVLINK_PORT_TYPE_IB) {
+		struct ib_device *ibdev = devlink_port->type_dev;
+
+		if (ibdev &&
+		    nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME,
+				   ibdev->name))
+			goto nla_put_failure;
+	}
+	if (devlink_port->split &&
+	    nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP,
+			devlink_port->split_group))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static void devlink_port_notify(struct devlink_port *devlink_port,
+				enum devlink_command cmd)
+{
+	struct devlink *devlink = devlink_port->devlink;
+	struct sk_buff *msg;
+	int err;
+
+	if (!devlink_port->registered)
+		return;
+
+	WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_port_fill(msg, devlink, devlink_port, cmd, 0, 0, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct sk_buff *msg;
+	int err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW,
+			      info->snd_portid, info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_get_dumpit(struct sk_buff *msg,
+				     struct netlink_callback *cb)
+{
+	struct devlink *devlink;
+	int start = cb->args[0];
+	int idx = 0;
+	int err;
+
+	mutex_lock(&devlink_mutex);
+	list_for_each_entry(devlink, &devlink_list, list) {
+		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+			continue;
+		if (idx < start) {
+			idx++;
+			continue;
+		}
+		err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW,
+				      NETLINK_CB(cb->skb).portid,
+				      cb->nlh->nlmsg_seq, NLM_F_MULTI);
+		if (err)
+			goto out;
+		idx++;
+	}
+out:
+	mutex_unlock(&devlink_mutex);
+
+	cb->args[0] = idx;
+	return msg->len;
+}
+
+static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	struct sk_buff *msg;
+	int err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_port_fill(msg, devlink, devlink_port,
+				   DEVLINK_CMD_PORT_NEW,
+				   info->snd_portid, info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_port_get_dumpit(struct sk_buff *msg,
+					  struct netlink_callback *cb)
+{
+	struct devlink *devlink;
+	struct devlink_port *devlink_port;
+	int start = cb->args[0];
+	int idx = 0;
+	int err;
+
+	mutex_lock(&devlink_mutex);
+	mutex_lock(&devlink_port_mutex);
+	list_for_each_entry(devlink, &devlink_list, list) {
+		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+			continue;
+		list_for_each_entry(devlink_port, &devlink->port_list, list) {
+			if (idx < start) {
+				idx++;
+				continue;
+			}
+			err = devlink_nl_port_fill(msg, devlink, devlink_port,
+						   DEVLINK_CMD_NEW,
+						   NETLINK_CB(cb->skb).portid,
+						   cb->nlh->nlmsg_seq,
+						   NLM_F_MULTI);
+			if (err)
+				goto out;
+			idx++;
+		}
+	}
+out:
+	mutex_unlock(&devlink_port_mutex);
+	mutex_unlock(&devlink_mutex);
+
+	cb->args[0] = idx;
+	return msg->len;
+}
+
+static int devlink_port_type_set(struct devlink *devlink,
+				 struct devlink_port *devlink_port,
+				 enum devlink_port_type port_type)
+
+{
+	int err;
+
+	if (devlink->ops && devlink->ops->port_type_set) {
+		if (port_type == DEVLINK_PORT_TYPE_NOTSET)
+			return -EINVAL;
+		err = devlink->ops->port_type_set(devlink_port, port_type);
+		if (err)
+			return err;
+		devlink_port->desired_type = port_type;
+		devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
+		return 0;
+	}
+	return -EOPNOTSUPP;
+}
+
+static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_port *devlink_port = info->user_ptr[1];
+	int err;
+
+	if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) {
+		enum devlink_port_type port_type;
+
+		port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]);
+		err = devlink_port_type_set(devlink, devlink_port, port_type);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int devlink_port_split(struct devlink *devlink,
+			      u32 port_index, u32 count)
+
+{
+	if (devlink->ops && devlink->ops->port_split)
+		return devlink->ops->port_split(devlink, port_index, count);
+	return -EOPNOTSUPP;
+}
+
+static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb,
+					  struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	u32 port_index;
+	u32 count;
+
+	if (!info->attrs[DEVLINK_ATTR_PORT_INDEX] ||
+	    !info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT])
+		return -EINVAL;
+
+	port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+	count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]);
+	return devlink_port_split(devlink, port_index, count);
+}
+
+static int devlink_port_unsplit(struct devlink *devlink, u32 port_index)
+
+{
+	if (devlink->ops && devlink->ops->port_unsplit)
+		return devlink->ops->port_unsplit(devlink, port_index);
+	return -EOPNOTSUPP;
+}
+
+static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	u32 port_index;
+
+	if (!info->attrs[DEVLINK_ATTR_PORT_INDEX])
+		return -EINVAL;
+
+	port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+	return devlink_port_unsplit(devlink, port_index);
+}
+
+static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 },
+};
+
+static const struct genl_ops devlink_nl_ops[] = {
+	{
+		.cmd = DEVLINK_CMD_GET,
+		.doit = devlink_nl_cmd_get_doit,
+		.dumpit = devlink_nl_cmd_get_dumpit,
+		.policy = devlink_nl_policy,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_GET,
+		.doit = devlink_nl_cmd_port_get_doit,
+		.dumpit = devlink_nl_cmd_port_get_dumpit,
+		.policy = devlink_nl_policy,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+		/* can be retrieved by unprivileged users */
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_SET,
+		.doit = devlink_nl_cmd_port_set_doit,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_SPLIT,
+		.doit = devlink_nl_cmd_port_split_doit,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_UNSPLIT,
+		.doit = devlink_nl_cmd_port_unsplit_doit,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+};
+
+/**
+ *	devlink_alloc - Allocate new devlink instance resources
+ *
+ *	@ops: ops
+ *	@priv_size: size of user private data
+ *
+ *	Allocate new devlink instance resources, including devlink index
+ *	and name.
+ */
+struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
+{
+	struct devlink *devlink;
+
+	devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
+	if (!devlink)
+		return NULL;
+	devlink->ops = ops;
+	devlink_net_set(devlink, &init_net);
+	INIT_LIST_HEAD(&devlink->port_list);
+	return devlink;
+}
+EXPORT_SYMBOL_GPL(devlink_alloc);
+
+/**
+ *	devlink_register - Register devlink instance
+ *
+ *	@devlink: devlink
+ */
+int devlink_register(struct devlink *devlink, struct device *dev)
+{
+	mutex_lock(&devlink_mutex);
+	devlink->dev = dev;
+	list_add_tail(&devlink->list, &devlink_list);
+	devlink_notify(devlink, DEVLINK_CMD_NEW);
+	mutex_unlock(&devlink_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_register);
+
+/**
+ *	devlink_unregister - Unregister devlink instance
+ *
+ *	@devlink: devlink
+ */
+void devlink_unregister(struct devlink *devlink)
+{
+	mutex_lock(&devlink_mutex);
+	devlink_notify(devlink, DEVLINK_CMD_DEL);
+	list_del(&devlink->list);
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_unregister);
+
+/**
+ *	devlink_free - Free devlink instance resources
+ *
+ *	@devlink: devlink
+ */
+void devlink_free(struct devlink *devlink)
+{
+	kfree(devlink);
+}
+EXPORT_SYMBOL_GPL(devlink_free);
+
+/**
+ *	devlink_port_register - Register devlink port
+ *
+ *	@devlink: devlink
+ *	@devlink_port: devlink port
+ *	@port_index
+ *
+ *	Register devlink port with provided port index. User can use
+ *	any indexing, even hw-related one. devlink_port structure
+ *	is convenient to be embedded inside user driver private structure.
+ *	Note that the caller should take care of zeroing the devlink_port
+ *	structure.
+ */
+int devlink_port_register(struct devlink *devlink,
+			  struct devlink_port *devlink_port,
+			  unsigned int port_index)
+{
+	mutex_lock(&devlink_port_mutex);
+	if (devlink_port_index_exists(devlink, port_index)) {
+		mutex_unlock(&devlink_port_mutex);
+		return -EEXIST;
+	}
+	devlink_port->devlink = devlink;
+	devlink_port->index = port_index;
+	devlink_port->type = DEVLINK_PORT_TYPE_NOTSET;
+	devlink_port->registered = true;
+	list_add_tail(&devlink_port->list, &devlink->port_list);
+	mutex_unlock(&devlink_port_mutex);
+	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_port_register);
+
+/**
+ *	devlink_port_unregister - Unregister devlink port
+ *
+ *	@devlink_port: devlink port
+ */
+void devlink_port_unregister(struct devlink_port *devlink_port)
+{
+	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL);
+	mutex_lock(&devlink_port_mutex);
+	list_del(&devlink_port->list);
+	mutex_unlock(&devlink_port_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_port_unregister);
+
+static void __devlink_port_type_set(struct devlink_port *devlink_port,
+				    enum devlink_port_type type,
+				    void *type_dev)
+{
+	devlink_port->type = type;
+	devlink_port->type_dev = type_dev;
+	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
+}
+
+/**
+ *	devlink_port_type_eth_set - Set port type to Ethernet
+ *
+ *	@devlink_port: devlink port
+ *	@netdev: related netdevice
+ */
+void devlink_port_type_eth_set(struct devlink_port *devlink_port,
+			       struct net_device *netdev)
+{
+	return __devlink_port_type_set(devlink_port,
+				       DEVLINK_PORT_TYPE_ETH, netdev);
+}
+EXPORT_SYMBOL_GPL(devlink_port_type_eth_set);
+
+/**
+ *	devlink_port_type_ib_set - Set port type to InfiniBand
+ *
+ *	@devlink_port: devlink port
+ *	@ibdev: related IB device
+ */
+void devlink_port_type_ib_set(struct devlink_port *devlink_port,
+			      struct ib_device *ibdev)
+{
+	return __devlink_port_type_set(devlink_port,
+				       DEVLINK_PORT_TYPE_IB, ibdev);
+}
+EXPORT_SYMBOL_GPL(devlink_port_type_ib_set);
+
+/**
+ *	devlink_port_type_clear - Clear port type
+ *
+ *	@devlink_port: devlink port
+ */
+void devlink_port_type_clear(struct devlink_port *devlink_port)
+{
+	return __devlink_port_type_set(devlink_port,
+				       DEVLINK_PORT_TYPE_NOTSET, NULL);
+}
+EXPORT_SYMBOL_GPL(devlink_port_type_clear);
+
+/**
+ *	devlink_port_split_set - Set port is split
+ *
+ *	@devlink_port: devlink port
+ *	@split_group: split group - identifies group split port is part of
+ */
+void devlink_port_split_set(struct devlink_port *devlink_port,
+			    u32 split_group)
+{
+	devlink_port->split = true;
+	devlink_port->split_group = split_group;
+	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
+}
+EXPORT_SYMBOL_GPL(devlink_port_split_set);
+
+static int __init devlink_module_init(void)
+{
+	return genl_register_family_with_ops_groups(&devlink_nl_family,
+						    devlink_nl_ops,
+						    devlink_nl_mcgrps);
+}
+
+static void __exit devlink_module_exit(void)
+{
+	genl_unregister_family(&devlink_nl_family);
+}
+
+module_init(devlink_module_init);
+module_exit(devlink_module_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>");
+MODULE_DESCRIPTION("Network physical device Netlink interface");
+MODULE_ALIAS_GENL_FAMILY(DEVLINK_GENL_NAME);