net/core/devlink.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * 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>
 */

#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 <linux/spinlock.h>
#include <linux/refcount.h>
#include <linux/workqueue.h>
#include <linux/u64_stats_sync.h>
#include <linux/timekeeping.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>
#define CREATE_TRACE_POINTS
#include <trace/events/devlink.h>

static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = {
	{
		.name = "destination mac",
		.id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC,
		.bitwidth = 48,
	},
};

struct devlink_dpipe_header devlink_dpipe_header_ethernet = {
	.name = "ethernet",
	.id = DEVLINK_DPIPE_HEADER_ETHERNET,
	.fields = devlink_dpipe_fields_ethernet,
	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ethernet),
	.global = true,
};
EXPORT_SYMBOL(devlink_dpipe_header_ethernet);

static struct devlink_dpipe_field devlink_dpipe_fields_ipv4[] = {
	{
		.name = "destination ip",
		.id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP,
		.bitwidth = 32,
	},
};

struct devlink_dpipe_header devlink_dpipe_header_ipv4 = {
	.name = "ipv4",
	.id = DEVLINK_DPIPE_HEADER_IPV4,
	.fields = devlink_dpipe_fields_ipv4,
	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv4),
	.global = true,
};
EXPORT_SYMBOL(devlink_dpipe_header_ipv4);

static struct devlink_dpipe_field devlink_dpipe_fields_ipv6[] = {
	{
		.name = "destination ip",
		.id = DEVLINK_DPIPE_FIELD_IPV6_DST_IP,
		.bitwidth = 128,
	},
};

struct devlink_dpipe_header devlink_dpipe_header_ipv6 = {
	.name = "ipv6",
	.id = DEVLINK_DPIPE_HEADER_IPV6,
	.fields = devlink_dpipe_fields_ipv6,
	.fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv6),
	.global = true,
};
EXPORT_SYMBOL(devlink_dpipe_header_ipv6);

EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);

static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = {
	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY },
	[DEVLINK_PORT_FN_ATTR_STATE] =
		NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE,
				 DEVLINK_PORT_FN_STATE_ACTIVE),
};

static DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC);
#define DEVLINK_REGISTERED XA_MARK_1

/* 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);

struct net *devlink_net(const struct devlink *devlink)
{
	return read_pnet(&devlink->_net);
}
EXPORT_SYMBOL_GPL(devlink_net);

static void devlink_put(struct devlink *devlink)
{
	if (refcount_dec_and_test(&devlink->refcount))
		complete(&devlink->comp);
}

static bool __must_check devlink_try_get(struct devlink *devlink)
{
	return refcount_inc_not_zero(&devlink->refcount);
}

static struct devlink *devlink_get_from_attrs(struct net *net,
					      struct nlattr **attrs)
{
	struct devlink *devlink;
	unsigned long index;
	bool found = false;
	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]);

	lockdep_assert_held(&devlink_mutex);

	xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) {
		if (strcmp(devlink->dev->bus->name, busname) == 0 &&
		    strcmp(dev_name(devlink->dev), devname) == 0 &&
		    net_eq(devlink_net(devlink), net)) {
			found = true;
			break;
		}
	}

	if (!found || !devlink_try_get(devlink))
		devlink = ERR_PTR(-ENODEV);

	return devlink;
}

static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink,
						      unsigned 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,
				      unsigned 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);
}

static inline bool
devlink_rate_is_leaf(struct devlink_rate *devlink_rate)
{
	return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF;
}

static inline bool
devlink_rate_is_node(struct devlink_rate *devlink_rate)
{
	return devlink_rate->type == DEVLINK_RATE_TYPE_NODE;
}

static struct devlink_rate *
devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info)
{
	struct devlink_rate *devlink_rate;
	struct devlink_port *devlink_port;

	devlink_port = devlink_port_get_from_attrs(devlink, info->attrs);
	if (IS_ERR(devlink_port))
		return ERR_CAST(devlink_port);
	devlink_rate = devlink_port->devlink_rate;
	return devlink_rate ?: ERR_PTR(-ENODEV);
}

static struct devlink_rate *
devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name)
{
	static struct devlink_rate *devlink_rate;

	list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
		if (devlink_rate_is_node(devlink_rate) &&
		    !strcmp(node_name, devlink_rate->name))
			return devlink_rate;
	}
	return ERR_PTR(-ENODEV);
}

static struct devlink_rate *
devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
{
	const char *rate_node_name;
	size_t len;

	if (!attrs[DEVLINK_ATTR_RATE_NODE_NAME])
		return ERR_PTR(-EINVAL);
	rate_node_name = nla_data(attrs[DEVLINK_ATTR_RATE_NODE_NAME]);
	len = strlen(rate_node_name);
	/* Name cannot be empty or decimal number */
	if (!len || strspn(rate_node_name, "0123456789") == len)
		return ERR_PTR(-EINVAL);

	return devlink_rate_node_get_by_name(devlink, rate_node_name);
}

static struct devlink_rate *
devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info)
{
	return devlink_rate_node_get_from_attrs(devlink, info->attrs);
}

static struct devlink_rate *
devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info)
{
	struct nlattr **attrs = info->attrs;

	if (attrs[DEVLINK_ATTR_PORT_INDEX])
		return devlink_rate_leaf_get_from_info(devlink, info);
	else if (attrs[DEVLINK_ATTR_RATE_NODE_NAME])
		return devlink_rate_node_get_from_info(devlink, info);
	else
		return ERR_PTR(-EINVAL);
}

struct devlink_sb {
	struct list_head list;
	unsigned int index;
	u32 size;
	u16 ingress_pools_count;
	u16 egress_pools_count;
	u16 ingress_tc_count;
	u16 egress_tc_count;
};

static u16 devlink_sb_pool_count(struct devlink_sb *devlink_sb)
{
	return devlink_sb->ingress_pools_count + devlink_sb->egress_pools_count;
}

static struct devlink_sb *devlink_sb_get_by_index(struct devlink *devlink,
						  unsigned int sb_index)
{
	struct devlink_sb *devlink_sb;

	list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
		if (devlink_sb->index == sb_index)
			return devlink_sb;
	}
	return NULL;
}

static bool devlink_sb_index_exists(struct devlink *devlink,
				    unsigned int sb_index)
{
	return devlink_sb_get_by_index(devlink, sb_index);
}

static struct devlink_sb *devlink_sb_get_from_attrs(struct devlink *devlink,
						    struct nlattr **attrs)
{
	if (attrs[DEVLINK_ATTR_SB_INDEX]) {
		u32 sb_index = nla_get_u32(attrs[DEVLINK_ATTR_SB_INDEX]);
		struct devlink_sb *devlink_sb;

		devlink_sb = devlink_sb_get_by_index(devlink, sb_index);
		if (!devlink_sb)
			return ERR_PTR(-ENODEV);
		return devlink_sb;
	}
	return ERR_PTR(-EINVAL);
}

static struct devlink_sb *devlink_sb_get_from_info(struct devlink *devlink,
						   struct genl_info *info)
{
	return devlink_sb_get_from_attrs(devlink, info->attrs);
}

static int devlink_sb_pool_index_get_from_attrs(struct devlink_sb *devlink_sb,
						struct nlattr **attrs,
						u16 *p_pool_index)
{
	u16 val;

	if (!attrs[DEVLINK_ATTR_SB_POOL_INDEX])
		return -EINVAL;

	val = nla_get_u16(attrs[DEVLINK_ATTR_SB_POOL_INDEX]);
	if (val >= devlink_sb_pool_count(devlink_sb))
		return -EINVAL;
	*p_pool_index = val;
	return 0;
}

static int devlink_sb_pool_index_get_from_info(struct devlink_sb *devlink_sb,
					       struct genl_info *info,
					       u16 *p_pool_index)
{
	return devlink_sb_pool_index_get_from_attrs(devlink_sb, info->attrs,
						    p_pool_index);
}

static int
devlink_sb_pool_type_get_from_attrs(struct nlattr **attrs,
				    enum devlink_sb_pool_type *p_pool_type)
{
	u8 val;

	if (!attrs[DEVLINK_ATTR_SB_POOL_TYPE])
		return -EINVAL;

	val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_TYPE]);
	if (val != DEVLINK_SB_POOL_TYPE_INGRESS &&
	    val != DEVLINK_SB_POOL_TYPE_EGRESS)
		return -EINVAL;
	*p_pool_type = val;
	return 0;
}

static int
devlink_sb_pool_type_get_from_info(struct genl_info *info,
				   enum devlink_sb_pool_type *p_pool_type)
{
	return devlink_sb_pool_type_get_from_attrs(info->attrs, p_pool_type);
}

static int
devlink_sb_th_type_get_from_attrs(struct nlattr **attrs,
				  enum devlink_sb_threshold_type *p_th_type)
{
	u8 val;

	if (!attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE])
		return -EINVAL;

	val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]);
	if (val != DEVLINK_SB_THRESHOLD_TYPE_STATIC &&
	    val != DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC)
		return -EINVAL;
	*p_th_type = val;
	return 0;
}

static int
devlink_sb_th_type_get_from_info(struct genl_info *info,
				 enum devlink_sb_threshold_type *p_th_type)
{
	return devlink_sb_th_type_get_from_attrs(info->attrs, p_th_type);
}

static int
devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb,
				   struct nlattr **attrs,
				   enum devlink_sb_pool_type pool_type,
				   u16 *p_tc_index)
{
	u16 val;

	if (!attrs[DEVLINK_ATTR_SB_TC_INDEX])
		return -EINVAL;

	val = nla_get_u16(attrs[DEVLINK_ATTR_SB_TC_INDEX]);
	if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS &&
	    val >= devlink_sb->ingress_tc_count)
		return -EINVAL;
	if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS &&
	    val >= devlink_sb->egress_tc_count)
		return -EINVAL;
	*p_tc_index = val;
	return 0;
}

static int
devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,
				  struct genl_info *info,
				  enum devlink_sb_pool_type pool_type,
				  u16 *p_tc_index)
{
	return devlink_sb_tc_index_get_from_attrs(devlink_sb, info->attrs,
						  pool_type, p_tc_index);
}

struct devlink_region {
	struct devlink *devlink;
	struct devlink_port *port;
	struct list_head list;
	union {
		const struct devlink_region_ops *ops;
		const struct devlink_port_region_ops *port_ops;
	};
	struct list_head snapshot_list;
	u32 max_snapshots;
	u32 cur_snapshots;
	u64 size;
};

struct devlink_snapshot {
	struct list_head list;
	struct devlink_region *region;
	u8 *data;
	u32 id;
};

static struct devlink_region *
devlink_region_get_by_name(struct devlink *devlink, const char *region_name)
{
	struct devlink_region *region;

	list_for_each_entry(region, &devlink->region_list, list)
		if (!strcmp(region->ops->name, region_name))
			return region;

	return NULL;
}

static struct devlink_region *
devlink_port_region_get_by_name(struct devlink_port *port,
				const char *region_name)
{
	struct devlink_region *region;

	list_for_each_entry(region, &port->region_list, list)
		if (!strcmp(region->ops->name, region_name))
			return region;

	return NULL;
}

static struct devlink_snapshot *
devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
{
	struct devlink_snapshot *snapshot;

	list_for_each_entry(snapshot, &region->snapshot_list, list)
		if (snapshot->id == id)
			return snapshot;

	return NULL;
}

#define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
#define DEVLINK_NL_FLAG_NEED_RATE		BIT(2)
#define DEVLINK_NL_FLAG_NEED_RATE_NODE		BIT(3)

/* The per devlink instance lock is taken by default in the pre-doit
 * operation, yet several commands do not require this. The global
 * devlink lock is taken and protects from disruption by user-calls.
 */
#define DEVLINK_NL_FLAG_NO_LOCK			BIT(4)

static int devlink_nl_pre_doit(const struct genl_ops *ops,
			       struct sk_buff *skb, struct genl_info *info)
{
	struct devlink_port *devlink_port;
	struct devlink *devlink;
	int err;

	mutex_lock(&devlink_mutex);
	devlink = devlink_get_from_attrs(genl_info_net(info), info->attrs);
	if (IS_ERR(devlink)) {
		mutex_unlock(&devlink_mutex);
		return PTR_ERR(devlink);
	}
	if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK)
		mutex_lock(&devlink->lock);
	info->user_ptr[0] = devlink;
	if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) {
		devlink_port = devlink_port_get_from_info(devlink, info);
		if (IS_ERR(devlink_port)) {
			err = PTR_ERR(devlink_port);
			goto unlock;
		}
		info->user_ptr[1] = devlink_port;
	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT) {
		devlink_port = devlink_port_get_from_info(devlink, info);
		if (!IS_ERR(devlink_port))
			info->user_ptr[1] = devlink_port;
	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) {
		struct devlink_rate *devlink_rate;

		devlink_rate = devlink_rate_get_from_info(devlink, info);
		if (IS_ERR(devlink_rate)) {
			err = PTR_ERR(devlink_rate);
			goto unlock;
		}
		info->user_ptr[1] = devlink_rate;
	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) {
		struct devlink_rate *rate_node;

		rate_node = devlink_rate_node_get_from_info(devlink, info);
		if (IS_ERR(rate_node)) {
			err = PTR_ERR(rate_node);
			goto unlock;
		}
		info->user_ptr[1] = rate_node;
	}
	return 0;

unlock:
	if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK)
		mutex_unlock(&devlink->lock);
	devlink_put(devlink);
	mutex_unlock(&devlink_mutex);
	return err;
}

static void devlink_nl_post_doit(const struct genl_ops *ops,
				 struct sk_buff *skb, struct genl_info *info)
{
	struct devlink *devlink;

	devlink = info->user_ptr[0];
	if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK)
		mutex_unlock(&devlink->lock);
	devlink_put(devlink);
	mutex_unlock(&devlink_mutex);
}

static struct genl_family devlink_nl_family;

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;
}

struct devlink_reload_combination {
	enum devlink_reload_action action;
	enum devlink_reload_limit limit;
};

static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = {
	{
		/* can't reinitialize driver with no down time */
		.action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
		.limit = DEVLINK_RELOAD_LIMIT_NO_RESET,
	},
};

static bool
devlink_reload_combination_is_invalid(enum devlink_reload_action action,
				      enum devlink_reload_limit limit)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++)
		if (devlink_reload_invalid_combinations[i].action == action &&
		    devlink_reload_invalid_combinations[i].limit == limit)
			return true;
	return false;
}

static bool
devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action)
{
	return test_bit(action, &devlink->ops->reload_actions);
}

static bool
devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit)
{
	return test_bit(limit, &devlink->ops->reload_limits);
}

static int devlink_reload_stat_put(struct sk_buff *msg,
				   enum devlink_reload_limit limit, u32 value)
{
	struct nlattr *reload_stats_entry;

	reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY);
	if (!reload_stats_entry)
		return -EMSGSIZE;

	if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) ||
	    nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value))
		goto nla_put_failure;
	nla_nest_end(msg, reload_stats_entry);
	return 0;

nla_put_failure:
	nla_nest_cancel(msg, reload_stats_entry);
	return -EMSGSIZE;
}

static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote)
{
	struct nlattr *reload_stats_attr, *act_info, *act_stats;
	int i, j, stat_idx;
	u32 value;

	if (!is_remote)
		reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS);
	else
		reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS);

	if (!reload_stats_attr)
		return -EMSGSIZE;

	for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) {
		if ((!is_remote &&
		     !devlink_reload_action_is_supported(devlink, i)) ||
		    i == DEVLINK_RELOAD_ACTION_UNSPEC)
			continue;
		act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO);
		if (!act_info)
			goto nla_put_failure;

		if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i))
			goto action_info_nest_cancel;
		act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS);
		if (!act_stats)
			goto action_info_nest_cancel;

		for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) {
			/* Remote stats are shown even if not locally supported.
			 * Stats of actions with unspecified limit are shown
			 * though drivers don't need to register unspecified
			 * limit.
			 */
			if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC &&
			     !devlink_reload_limit_is_supported(devlink, j)) ||
			    devlink_reload_combination_is_invalid(i, j))
				continue;

			stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i;
			if (!is_remote)
				value = devlink->stats.reload_stats[stat_idx];
			else
				value = devlink->stats.remote_reload_stats[stat_idx];
			if (devlink_reload_stat_put(msg, j, value))
				goto action_stats_nest_cancel;
		}
		nla_nest_end(msg, act_stats);
		nla_nest_end(msg, act_info);
	}
	nla_nest_end(msg, reload_stats_attr);
	return 0;

action_stats_nest_cancel:
	nla_nest_cancel(msg, act_stats);
action_info_nest_cancel:
	nla_nest_cancel(msg, act_info);
nla_put_failure:
	nla_nest_cancel(msg, reload_stats_attr);
	return -EMSGSIZE;
}

static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
			   enum devlink_command cmd, u32 portid,
			   u32 seq, int flags)
{
	struct nlattr *dev_stats;
	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_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed))
		goto nla_put_failure;

	dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS);
	if (!dev_stats)
		goto nla_put_failure;

	if (devlink_reload_stats_put(msg, devlink, false))
		goto dev_stats_nest_cancel;
	if (devlink_reload_stats_put(msg, devlink, true))
		goto dev_stats_nest_cancel;

	nla_nest_end(msg, dev_stats);
	genlmsg_end(msg, hdr);
	return 0;

dev_stats_nest_cancel:
	nla_nest_cancel(msg, dev_stats);
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_attrs_put(struct sk_buff *msg,
				     struct devlink_port *devlink_port)
{
	struct devlink_port_attrs *attrs = &devlink_port->attrs;

	if (!devlink_port->attrs_set)
		return 0;
	if (attrs->lanes) {
		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_LANES, attrs->lanes))
			return -EMSGSIZE;
	}
	if (nla_put_u8(msg, DEVLINK_ATTR_PORT_SPLITTABLE, attrs->splittable))
		return -EMSGSIZE;
	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour))
		return -EMSGSIZE;
	switch (devlink_port->attrs.flavour) {
	case DEVLINK_PORT_FLAVOUR_PCI_PF:
		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
				attrs->pci_pf.controller) ||
		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf))
			return -EMSGSIZE;
		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external))
			return -EMSGSIZE;
		break;
	case DEVLINK_PORT_FLAVOUR_PCI_VF:
		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
				attrs->pci_vf.controller) ||
		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) ||
		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf))
			return -EMSGSIZE;
		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external))
			return -EMSGSIZE;
		break;
	case DEVLINK_PORT_FLAVOUR_PCI_SF:
		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
				attrs->pci_sf.controller) ||
		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
				attrs->pci_sf.pf) ||
		    nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER,
				attrs->pci_sf.sf))
			return -EMSGSIZE;
		break;
	case DEVLINK_PORT_FLAVOUR_PHYSICAL:
	case DEVLINK_PORT_FLAVOUR_CPU:
	case DEVLINK_PORT_FLAVOUR_DSA:
		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER,
				attrs->phys.port_number))
			return -EMSGSIZE;
		if (!attrs->split)
			return 0;
		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP,
				attrs->phys.port_number))
			return -EMSGSIZE;
		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER,
				attrs->phys.split_subport_number))
			return -EMSGSIZE;
		break;
	default:
		break;
	}
	return 0;
}

static int devlink_port_fn_hw_addr_fill(const struct devlink_ops *ops,
					struct devlink_port *port,
					struct sk_buff *msg,
					struct netlink_ext_ack *extack,
					bool *msg_updated)
{
	u8 hw_addr[MAX_ADDR_LEN];
	int hw_addr_len;
	int err;

	if (!ops->port_function_hw_addr_get)
		return 0;

	err = ops->port_function_hw_addr_get(port, hw_addr, &hw_addr_len,
					     extack);
	if (err) {
		if (err == -EOPNOTSUPP)
			return 0;
		return err;
	}
	err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr);
	if (err)
		return err;
	*msg_updated = true;
	return 0;
}

static int devlink_nl_rate_fill(struct sk_buff *msg,
				struct devlink_rate *devlink_rate,
				enum devlink_command cmd, u32 portid, u32 seq,
				int flags, struct netlink_ext_ack *extack)
{
	struct devlink *devlink = devlink_rate->devlink;
	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_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type))
		goto nla_put_failure;

	if (devlink_rate_is_leaf(devlink_rate)) {
		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
				devlink_rate->devlink_port->index))
			goto nla_put_failure;
	} else if (devlink_rate_is_node(devlink_rate)) {
		if (nla_put_string(msg, DEVLINK_ATTR_RATE_NODE_NAME,
				   devlink_rate->name))
			goto nla_put_failure;
	}

	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE,
			      devlink_rate->tx_share, DEVLINK_ATTR_PAD))
		goto nla_put_failure;

	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_MAX,
			      devlink_rate->tx_max, DEVLINK_ATTR_PAD))
		goto nla_put_failure;

	if (devlink_rate->parent)
		if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME,
				   devlink_rate->parent->name))
			goto nla_put_failure;

	genlmsg_end(msg, hdr);
	return 0;

nla_put_failure:
	genlmsg_cancel(msg, hdr);
	return -EMSGSIZE;
}

static bool
devlink_port_fn_state_valid(enum devlink_port_fn_state state)
{
	return state == DEVLINK_PORT_FN_STATE_INACTIVE ||
	       state == DEVLINK_PORT_FN_STATE_ACTIVE;
}

static bool
devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate)
{
	return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED ||
	       opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED;
}

static int devlink_port_fn_state_fill(const struct devlink_ops *ops,
				      struct devlink_port *port,
				      struct sk_buff *msg,
				      struct netlink_ext_ack *extack,
				      bool *msg_updated)
{
	enum devlink_port_fn_opstate opstate;
	enum devlink_port_fn_state state;
	int err;

	if (!ops->port_fn_state_get)
		return 0;

	err = ops->port_fn_state_get(port, &state, &opstate, extack);
	if (err) {
		if (err == -EOPNOTSUPP)
			return 0;
		return err;
	}
	if (!devlink_port_fn_state_valid(state)) {
		WARN_ON_ONCE(1);
		NL_SET_ERR_MSG_MOD(extack, "Invalid state read from driver");
		return -EINVAL;
	}
	if (!devlink_port_fn_opstate_valid(opstate)) {
		WARN_ON_ONCE(1);
		NL_SET_ERR_MSG_MOD(extack,
				   "Invalid operational state read from driver");
		return -EINVAL;
	}
	if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) ||
	    nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate))
		return -EMSGSIZE;
	*msg_updated = true;
	return 0;
}

static int
devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port,
				   struct netlink_ext_ack *extack)
{
	const struct devlink_ops *ops;
	struct nlattr *function_attr;
	bool msg_updated = false;
	int err;

	function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION);
	if (!function_attr)
		return -EMSGSIZE;

	ops = port->devlink->ops;
	err = devlink_port_fn_hw_addr_fill(ops, port, msg, extack,
					   &msg_updated);
	if (err)
		goto out;
	err = devlink_port_fn_state_fill(ops, port, msg, extack, &msg_updated);
out:
	if (err || !msg_updated)
		nla_nest_cancel(msg, function_attr);
	else
		nla_nest_end(msg, function_attr);
	return err;
}

static int devlink_nl_port_fill(struct sk_buff *msg,
				struct devlink_port *devlink_port,
				enum devlink_command cmd, u32 portid, u32 seq,
				int flags, struct netlink_ext_ack *extack)
{
	struct devlink *devlink = devlink_port->devlink;
	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;

	/* Hold rtnl lock while accessing port's netdev attributes. */
	rtnl_lock();
	spin_lock_bh(&devlink_port->type_lock);
	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))
		goto nla_put_failure_type_locked;
	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_type_locked;
	if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
		struct net *net = devlink_net(devlink_port->devlink);
		struct net_device *netdev = devlink_port->type_dev;

		if (netdev && net_eq(net, dev_net(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_type_locked;
	}
	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_type_locked;
	}
	spin_unlock_bh(&devlink_port->type_lock);
	rtnl_unlock();
	if (devlink_nl_port_attrs_put(msg, devlink_port))
		goto nla_put_failure;
	if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack))
		goto nla_put_failure;

	genlmsg_end(msg, hdr);
	return 0;

nla_put_failure_type_locked:
	spin_unlock_bh(&devlink_port->type_lock);
	rtnl_unlock();
nla_put_failure:
	genlmsg_cancel(msg, hdr);
	return -EMSGSIZE;
}

static void devlink_port_notify(struct devlink_port *devlink_port,
				enum devlink_command cmd)
{
	struct sk_buff *msg;
	int err;

	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_port, cmd, 0, 0, 0, NULL);
	if (err) {
		nlmsg_free(msg);
		return;
	}

	genlmsg_multicast_netns(&devlink_nl_family,
				devlink_net(devlink_port->devlink), msg, 0,
				DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
}

static void devlink_rate_notify(struct devlink_rate *devlink_rate,
				enum devlink_command cmd)
{
	struct sk_buff *msg;
	int err;

	WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && cmd != DEVLINK_CMD_RATE_DEL);

	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return;

	err = devlink_nl_rate_fill(msg, devlink_rate, cmd, 0, 0, 0, NULL);
	if (err) {
		nlmsg_free(msg);
		return;
	}

	genlmsg_multicast_netns(&devlink_nl_family,
				devlink_net(devlink_rate->devlink), msg, 0,
				DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
}

static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg,
					  struct netlink_callback *cb)
{
	struct devlink_rate *devlink_rate;
	struct devlink *devlink;
	int start = cb->args[0];
	unsigned long index;
	int idx = 0;
	int err = 0;

	mutex_lock(&devlink_mutex);
	xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) {
		if (!devlink_try_get(devlink))
			continue;

		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
			goto retry;

		mutex_lock(&devlink->lock);
		list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
			enum devlink_command cmd = DEVLINK_CMD_RATE_NEW;
			u32 id = NETLINK_CB(cb->skb).portid;

			if (idx < start) {
				idx++;
				continue;
			}
			err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id,
						   cb->nlh->nlmsg_seq,
						   NLM_F_MULTI, NULL);
			if (err) {
				mutex_unlock(&devlink->lock);
				devlink_put(devlink);
				goto out;
			}
			idx++;
		}
		mutex_unlock(&devlink->lock);
retry:
		devlink_put(devlink);
	}
out:
	mutex_unlock(&devlink_mutex);
	if (err != -EMSGSIZE)
		return err;

	cb->args[0] = idx;
	return msg->len;
}

static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb,
					struct genl_info *info)
{
	struct devlink_rate *devlink_rate = 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_rate_fill(msg, devlink_rate, DEVLINK_CMD_RATE_NEW,
				   info->snd_portid, info->snd_seq, 0,
				   info->extack);
	if (err) {
		nlmsg_free(msg);
		return err;
	}

	return genlmsg_reply(msg, info);
}

static bool
devlink_rate_is_parent_node(struct devlink_rate *devlink_rate,
			    struct devlink_rate *parent)
{
	while (parent) {
		if (parent == devlink_rate)
			return true;
		parent = parent->parent;
	}
	return false;
}

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];
	unsigned long index;
	int idx = 0;
	int err;

	mutex_lock(&devlink_mutex);
	xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) {
		if (!devlink_try_get(devlink))
			continue;

		if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) {
			devlink_put(devlink);
			continue;
		}

		if (idx < start) {
			idx++;
			devlink_put(devlink);
			continue;
		}

		err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW,
				      NETLINK_CB(cb->skb).portid,
				      cb->nlh->nlmsg_seq, NLM_F_MULTI);
		devlink_put(devlink);
		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_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_port, DEVLINK_CMD_PORT_NEW,
				   info->snd_portid, info->snd_seq, 0,
				   info->extack);
	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];
	unsigned long index;
	int idx = 0;
	int err;

	mutex_lock(&devlink_mutex);
	xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) {
		if (!devlink_try_get(devlink))
			continue;

		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
			goto retry;

		mutex_lock(&devlink->lock);
		list_for_each_entry(devlink_port, &devlink->port_list, list) {
			if (idx < start) {
				idx++;
				continue;
			}
			err = devlink_nl_port_fill(msg, devlink_port,
						   DEVLINK_CMD_NEW,
						   NETLINK_CB(cb->skb).portid,
						   cb->nlh->nlmsg_seq,
						   NLM_F_MULTI, cb->extack);
			if (err) {
				mutex_unlock(&devlink->lock);
				devlink_put(devlink);
				goto out;
			}
			idx++;
		}
		mutex_unlock(&devlink->lock);
retry:
		devlink_put(devlink);
	}
out:
	mutex_unlock(&devlink_mutex);

	cb->args[0] = idx;
	return msg->len;
}

static int devlink_port_type_set(struct devlink_port *devlink_port,
				 enum devlink_port_type port_type)

{
	int err;

	if (!devlink_port->devlink->ops->port_type_set)
		return -EOPNOTSUPP;

	if (port_type == devlink_port->type)
		return 0;

	err = devlink_port->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;
}

static int devlink_port_function_hw_addr_set(struct devlink_port *port,
					     const struct nlattr *attr,
					     struct netlink_ext_ack *extack)
{
	const struct devlink_ops *ops = port->devlink->ops;
	const u8 *hw_addr;
	int hw_addr_len;

	hw_addr = nla_data(attr);
	hw_addr_len = nla_len(attr);
	if (hw_addr_len > MAX_ADDR_LEN) {
		NL_SET_ERR_MSG_MOD(extack, "Port function hardware address too long");
		return -EINVAL;
	}
	if (port->type == DEVLINK_PORT_TYPE_ETH) {
		if (hw_addr_len != ETH_ALEN) {
			NL_SET_ERR_MSG_MOD(extack, "Address must be 6 bytes for Ethernet device");
			return -EINVAL;
		}
		if (!is_unicast_ether_addr(hw_addr)) {
			NL_SET_ERR_MSG_MOD(extack, "Non-unicast hardware address unsupported");
			return -EINVAL;
		}
	}

	if (!ops->port_function_hw_addr_set) {
		NL_SET_ERR_MSG_MOD(extack, "Port doesn't support function attributes");
		return -EOPNOTSUPP;
	}

	return ops->port_function_hw_addr_set(port, hw_addr, hw_addr_len,
					      extack);
}

static int devlink_port_fn_state_set(struct devlink_port *port,
				     const struct nlattr *attr,
				     struct netlink_ext_ack *extack)
{
	enum devlink_port_fn_state state;
	const struct devlink_ops *ops;

	state = nla_get_u8(attr);
	ops = port->devlink->ops;
	if (!ops->port_fn_state_set) {
		NL_SET_ERR_MSG_MOD(extack,
				   "Function does not support state setting");
		return -EOPNOTSUPP;
	}
	return ops->port_fn_state_set(port, state, extack);
}

static int devlink_port_function_set(struct devlink_port *port,
				     const struct nlattr *attr,
				     struct netlink_ext_ack *extack)
{
	struct nlattr *tb[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1];
	int err;

	err = nla_parse_nested(tb, DEVLINK_PORT_FUNCTION_ATTR_MAX, attr,
			       devlink_function_nl_policy, extack);
	if (err < 0) {
		NL_SET_ERR_MSG_MOD(extack, "Fail to parse port function attributes");
		return err;
	}

	attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR];
	if (attr) {
		err = devlink_port_function_hw_addr_set(port, attr, extack);
		if (err)
			return err;
	}
	/* Keep this as the last function attribute set, so that when
	 * multiple port function attributes are set along with state,
	 * Those can be applied first before activating the state.
	 */
	attr = tb[DEVLINK_PORT_FN_ATTR_STATE];
	if (attr)
		err = devlink_port_fn_state_set(port, attr, extack);

	if (!err)
		devlink_port_notify(port, DEVLINK_CMD_PORT_NEW);
	return err;
}

static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb,
					struct genl_info *info)
{
	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_port, port_type);
		if (err)
			return err;
	}

	if (info->attrs[DEVLINK_ATTR_PORT_FUNCTION]) {
		struct nlattr *attr = info->attrs[DEVLINK_ATTR_PORT_FUNCTION];
		struct netlink_ext_ack *extack = info->extack;

		err = devlink_port_function_set(devlink_port, attr, extack);
		if (err)
			return err;
	}

	return 0;
}

static int devlink_port_split(struct devlink *devlink, u32 port_index,
			      u32 count, struct netlink_ext_ack *extack)

{
	if (devlink->ops->port_split)
		return devlink->ops->port_split(devlink, port_index, count,
						extack);
	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];
	struct devlink_port *devlink_port;
	u32 port_index;
	u32 count;

	if (!info->attrs[DEVLINK_ATTR_PORT_INDEX] ||
	    !info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT])
		return -EINVAL;

	devlink_port = devlink_port_get_from_info(devlink, info);
	port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
	count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]);

	if (IS_ERR(devlink_port))
		return -EINVAL;

	if (!devlink_port->attrs.splittable) {
		/* Split ports cannot be split. */
		if (devlink_port->attrs.split)
			NL_SET_ERR_MSG_MOD(info->extack, "Port cannot be split further");
		else
			NL_SET_ERR_MSG_MOD(info->extack, "Port cannot be split");
		return -EINVAL;
	}

	if (count < 2 || !is_power_of_2(count) || count > devlink_port->attrs.lanes) {
		NL_SET_ERR_MSG_MOD(info->extack, "Invalid split count");
		return -EINVAL;
	}

	return devlink_port_split(devlink, port_index, count, info->extack);
}

static int devlink_port_unsplit(struct devlink *devlink, u32 port_index,
				struct netlink_ext_ack *extack)

{
	if (devlink->ops->port_unsplit)
		return devlink->ops->port_unsplit(devlink, port_index, extack);
	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, info->extack);
}

static int devlink_port_new_notifiy(struct devlink *devlink,
				    unsigned int port_index,
				    struct genl_info *info)
{
	struct devlink_port *devlink_port;
	struct sk_buff *msg;
	int err;

	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	mutex_lock(&devlink->lock);
	devlink_port = devlink_port_get_by_index(devlink, port_index);
	if (!devlink_port) {
		err = -ENODEV;
		goto out;
	}

	err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW,
				   info->snd_portid, info->snd_seq, 0, NULL);
	if (err)
		goto out;

	err = genlmsg_reply(msg, info);
	mutex_unlock(&devlink->lock);
	return err;

out:
	mutex_unlock(&devlink->lock);
	nlmsg_free(msg);
	return err;
}

static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb,
					struct genl_info *info)
{
	struct netlink_ext_ack *extack = info->extack;
	struct devlink_port_new_attrs new_attrs = {};
	struct devlink *devlink = info->user_ptr[0];
	unsigned int new_port_index;
	int err;

	if (!devlink->ops->port_new || !devlink->ops->port_del)
		return -EOPNOTSUPP;

	if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] ||
	    !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) {
		NL_SET_ERR_MSG_MOD(extack, "Port flavour or PCI PF are not specified");
		return -EINVAL;
	}
	new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]);
	new_attrs.pfnum =
		nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]);

	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
		/* Port index of the new port being created by driver. */
		new_attrs.port_index =
			nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
		new_attrs.port_index_valid = true;
	}
	if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) {
		new_attrs.controller =
			nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]);
		new_attrs.controller_valid = true;
	}
	if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF &&
	    info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) {
		new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]);
		new_attrs.sfnum_valid = true;
	}

	err = devlink->ops->port_new(devlink, &new_attrs, extack,
				     &new_port_index);
	if (err)
		return err;

	err = devlink_port_new_notifiy(devlink, new_port_index, info);
	if (err && err != -ENODEV) {
		/* Fail to send the response; destroy newly created port. */
		devlink->ops->port_del(devlink, new_port_index, extack);
	}
	return err;
}

static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb,
					struct genl_info *info)
{
	struct netlink_ext_ack *extack = info->extack;
	struct devlink *devlink = info->user_ptr[0];
	unsigned int port_index;

	if (!devlink->ops->port_del)
		return -EOPNOTSUPP;

	if (!info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
		NL_SET_ERR_MSG_MOD(extack, "Port index is not specified");
		return -EINVAL;
	}
	port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);

	return devlink->ops->port_del(devlink, port_index, extack);
}

static int
devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate,
				struct genl_info *info,
				struct nlattr *nla_parent)
{
	struct devlink *devlink = devlink_rate->devlink;
	const char *parent_name = nla_data(nla_parent);
	const struct devlink_ops *ops = devlink->ops;
	size_t len = strlen(parent_name);
	struct devlink_rate *parent;
	int err = -EOPNOTSUPP;

	parent = devlink_rate->parent;
	if (parent && len) {
		NL_SET_ERR_MSG_MOD(info->extack, "Rate object already has parent.");
		return -EBUSY;
	} else if (parent && !len) {
		if (devlink_rate_is_leaf(devlink_rate))
			err = ops->rate_leaf_parent_set(devlink_rate, NULL,
							devlink_rate->priv, NULL,
							info->extack);
		else if (devlink_rate_is_node(devlink_rate))
			err = ops->rate_node_parent_set(devlink_rate, NULL,
							devlink_rate->priv, NULL,
							info->extack);
		if (err)
			return err;

		refcount_dec(&parent->refcnt);
		devlink_rate->parent = NULL;
	} else if (!parent && len) {
		parent = devlink_rate_node_get_by_name(devlink, parent_name);
		if (IS_ERR(parent))
			return -ENODEV;

		if (parent == devlink_rate) {
			NL_SET_ERR_MSG_MOD(info->extack, "Parent to self is not allowed");
			return -EINVAL;
		}

		if (devlink_rate_is_node(devlink_rate) &&
		    devlink_rate_is_parent_node(devlink_rate, parent->parent)) {
			NL_SET_ERR_MSG_MOD(info->extack, "Node is already a parent of parent node.");
			return -EEXIST;
		}

		if (devlink_rate_is_leaf(devlink_rate))
			err = ops->rate_leaf_parent_set(devlink_rate, parent,
							devlink_rate->priv, parent->priv,
							info->extack);
		else if (devlink_rate_is_node(devlink_rate))
			err = ops->rate_node_parent_set(devlink_rate, parent,
							devlink_rate->priv, parent->priv,
							info->extack);
		if (err)
			return err;

		refcount_inc(&parent->refcnt);
		devlink_rate->parent = parent;
	}

	return 0;
}

static int devlink_nl_rate_set(struct devlink_rate *devlink_rate,
			       const struct devlink_ops *ops,
			       struct genl_info *info)
{
	struct nlattr *nla_parent, **attrs = info->attrs;
	int err = -EOPNOTSUPP;
	u64 rate;

	if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) {
		rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]);
		if (devlink_rate_is_leaf(devlink_rate))
			err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv,
							  rate, info->extack);
		else if (devlink_rate_is_node(devlink_rate))
			err = ops->rate_node_tx_share_set(devlink_rate, devlink_rate->priv,
							  rate, info->extack);
		if (err)
			return err;
		devlink_rate->tx_share = rate;
	}

	if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) {
		rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]);
		if (devlink_rate_is_leaf(devlink_rate))
			err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv,
							rate, info->extack);
		else if (devlink_rate_is_node(devlink_rate))
			err = ops->rate_node_tx_max_set(devlink_rate, devlink_rate->priv,
							rate, info->extack);
		if (err)
			return err;
		devlink_rate->tx_max = rate;
	}

	nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME];
	if (nla_parent) {
		err = devlink_nl_rate_parent_node_set(devlink_rate, info,
						      nla_parent);
		if (err)
			return err;
	}

	return 0;
}

static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops,
					   struct genl_info *info,
					   enum devlink_rate_type type)
{
	struct nlattr **attrs = info->attrs;

	if (type == DEVLINK_RATE_TYPE_LEAF) {
		if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_leaf_tx_share_set) {
			NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the leafs");
			return false;
		}
		if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_leaf_tx_max_set) {
			NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the leafs");
			return false;
		}
		if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
		    !ops->rate_leaf_parent_set) {
			NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs");
			return false;
		}
	} else if (type == DEVLINK_RATE_TYPE_NODE) {
		if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) {
			NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes");
			return false;
		}
		if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_node_tx_max_set) {
			NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the nodes");
			return false;
		}
		if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] &&
		    !ops->rate_node_parent_set) {
			NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes");
			return false;
		}
	} else {
		WARN(1, "Unknown type of rate object");
		return false;
	}

	return true;
}

static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb,
					struct genl_info *info)
{
	struct devlink_rate *devlink_rate = info->user_ptr[1];
	struct devlink *devlink = devlink_rate->devlink;
	const struct devlink_ops *ops = devlink->ops;
	int err;

	if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type))
		return -EOPNOTSUPP;

	err = devlink_nl_rate_set(devlink_rate, ops, info);

	if (!err)
		devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
	return err;
}

static int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb,
					struct genl_info *info)
{
	struct devlink *devlink = info->user_ptr[0];
	struct devlink_rate *rate_node;
	const struct devlink_ops *ops;
	int err;

	ops = devlink->ops;
	if (!ops || !ops->rate_node_new || !ops->rate_node_del) {
		NL_SET_ERR_MSG_MOD(info->extack, "Rate nodes aren't supported");
		return -EOPNOTSUPP;
	}

	if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE))
		return -EOPNOTSUPP;

	rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs);
	if (!IS_ERR(rate_node))
		return -EEXIST;
	else if (rate_node == ERR_PTR(-EINVAL))
		return -EINVAL;

	rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL);
	if (!rate_node)
		return -ENOMEM;

	rate_node->devlink = devlink;
	rate_node->type = DEVLINK_RATE_TYPE_NODE;
	rate_node->name = nla_strdup(info->attrs[DEVLINK_ATTR_RATE_NODE_NAME], GFP_KERNEL);
	if (!rate_node->name) {
		err = -ENOMEM;
		goto err_strdup;
	}

	err = ops->rate_node_new(rate_node, &rate_node->priv, info->extack);
	if (err)
		goto err_node_new;

	err = devlink_nl_rate_set(rate_node, ops, info);
	if (err)
		goto err_rate_set;

	refcount_set(&rate_node->refcnt, 1);
	list_add(&rate_node->list, &devlink->rate_list);
	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW);
	return 0;

err_rate_set:
	ops->rate_node_del(rate_node, rate_node->priv, info->extack);
err_node_new:
	kfree(rate_node->name);
err_strdup:
	kfree(rate_node);
	return err;
}

static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb,
					struct genl_info *info)
{
	struct devlink_rate *rate_node = info->user_ptr[1];
	struct devlink *devlink = rate_node->devlink;
	const struct devlink_ops *ops = devlink->ops;
	int err;

	if (refcount_read(&rate_node->refcnt) > 1) {
		NL_SET_ERR_MSG_MOD(info->extack, "Node has children. Cannot delete node.");
		return -EBUSY;
	}

	devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL);
	err = ops->rate_node_del(rate_node, rate_node->priv, info->extack);
	if (rate_node->parent)
		refcount_dec(&rate_node->parent->refcnt);
	list_del(&rate_node->list);
	kfree(rate_node->name);
	kfree(rate_node);
	return err;
}

static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink,
			      struct devlink_sb *devlink_sb,
			      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_SB_INDEX, devlink_sb->index))
		goto nla_put_failure;
	if (nla_put_u32(msg, DEVLINK_ATTR_SB_SIZE, devlink_sb->size))
		goto nla_put_failure;
	if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_POOL_COUNT,
			devlink_sb->ingress_pools_count))
		goto nla_put_failure;
	if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_POOL_COUNT,
			devlink_sb->egress_pools_count))
		goto nla_put_failure;
	if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_TC_COUNT,
			devlink_sb->ingress_tc_count))
		goto nla_put_failure;
	if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_TC_COUNT,
			devlink_sb->egress_tc_count))
		goto nla_put_failure;

	genlmsg_end(msg, hdr);
	return 0;

nla_put_failure:
	genlmsg_cancel(msg, hdr);
	return -EMSGSIZE;
}

static int devlink_nl_cmd_sb_get_doit(struct sk_buff *skb,
				      struct genl_info *info)
{
	struct devlink *devlink = info->user_ptr[0];
	struct devlink_sb *devlink_sb;
	struct sk_buff *msg;
	int err;

	devlink_sb = devlink_sb_get_from_info(devlink, info);
	if (IS_ERR(devlink_sb))
		return PTR_ERR(devlink_sb);

	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	err = devlink_nl_sb_fill(msg, devlink, devlink_sb,
				 DEVLINK_CMD_SB_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_sb_get_dumpit(struct sk_buff *msg,
					struct netlink_callback *cb)
{
	struct devlink *devlink;
	struct devlink_sb *devlink_sb;
	int start = cb->args[0];
	unsigned long index;
	int idx = 0;
	int err;

	mutex_lock(&devlink_mutex);
	xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) {
		if (!devlink_try_get(devlink))
			continue;

		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
			goto retry;

		mutex_lock(&devlink->lock);
		list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
			if (idx < start) {
				idx++;
				continue;
			}
			err = devlink_nl_sb_fill(msg, devlink, devlink_sb,
						 DEVLINK_CMD_SB_NEW,
						 NETLINK_CB(cb->skb).portid,
						 cb->nlh->nlmsg_seq,
						 NLM_F_MULTI);
			if (err) {
				mutex_unlock(&devlink->lock);
				devlink_put(devlink);
				goto out;
			}
			idx++;
		}
		mutex_unlock(&devlink->lock);
retry:
		devlink_put(devlink);
	}
out:
	mutex_unlock(&devlink_mutex);

	cb->args[0] = idx;
	return msg->len;
}

static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink,
				   struct devlink_sb *devlink_sb,
				   u16 pool_index, enum devlink_command cmd,
				   u32 portid, u32 seq, int flags)
{
	struct devlink_sb_pool_info pool_info;
	void *hdr;
	int err;

	err = devlink->ops->sb_pool_get(devlink, devlink_sb->index,
					pool_index, &pool_info);
	if (err)
		return err;

	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_SB_INDEX, devlink_sb->index))
		goto nla_put_failure;
	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
		goto nla_put_failure;
	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_info.pool_type))
		goto nla_put_failure;
	if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_SIZE, pool_info.size))
		goto nla_put_failure;
	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE,
		       pool_info.threshold_type))
		goto nla_put_failure;
	if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE,
			pool_info.cell_size))
		goto nla_put_failure;

	genlmsg_end(msg, hdr);
	return 0;

nla_put_failure:
	genlmsg_cancel(msg, hdr);
	return -EMSGSIZE;
}

static int devlink_nl_cmd_sb_pool_get_doit(struct sk_buff *skb,
					   struct genl_info *info)
{
	struct devlink *devlink = info->user_ptr[0];
	struct devlink_sb *devlink_sb;
	struct sk_buff *msg;
	u16 pool_index;
	int err;

	devlink_sb = devlink_sb_get_from_info(devlink, info);
	if (IS_ERR(devlink_sb))
		return PTR_ERR(devlink_sb);

	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
						  &pool_index);
	if (err)
		return err;

	if (!devlink->ops->sb_pool_get)
		return -EOPNOTSUPP;

	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	err = devlink_nl_sb_pool_fill(msg, devlink, devlink_sb, pool_index,
				      DEVLINK_CMD_SB_POOL_NEW,
				      info->snd_portid, info->snd_seq, 0);
	if (err) {
		nlmsg_free(msg);
		return err;
	}

	return genlmsg_reply(msg, info);
}

static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
				struct devlink *devlink,
				struct devlink_sb *devlink_sb,
				u32 portid, u32 seq)
{
	u16 pool_count = devlink_sb_pool_count(devlink_sb);
	u16 pool_index;
	int err;

	for (pool_index = 0; pool_index < pool_count; pool_index++) {
		if (*p_idx < start) {
			(*p_idx)++;
			continue;
		}
		err = devlink_nl_sb_pool_fill(msg, devlink,
					      devlink_sb,
					      pool_index,
					      DEVLINK_CMD_SB_POOL_NEW,
					      portid, seq, NLM_F_MULTI);
		if (err)
			return err;
		(*p_idx)++;
	}
	return 0;
}

static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg,
					     struct netlink_callback *cb)
{
	struct devlink *devlink;
	struct devlink_sb *devlink_sb;
	int start = cb->args[0];
	unsigned long index;
	int idx = 0;
	int err = 0;

	mutex_lock(&devlink_mutex);
	xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) {
		if (!devlink_try_get(devlink))
			continue;

		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) ||
		    !devlink->ops->sb_pool_get)
			goto retry;

		mutex_lock(&devlink->lock);
		list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
			err = __sb_pool_get_dumpit(msg, start, &idx, devlink,
						   devlink_sb,
						   NETLINK_CB(cb->skb).portid,
						   cb->nlh->nlmsg_seq);
			if (err == -EOPNOTSUPP) {
				err = 0;
			} else if (err) {
				mutex_unlock(&devlink->lock);
				devlink_put(devlink);
				goto out;
			}
		}
		mutex_unlock(&devlink->lock);
retry:
		devlink_put(devlink);
	}
out:
	mutex_unlock(&devlink_mutex);

	if (err != -EMSGSIZE)
		return err;

	cb->args[0] = idx;
	return msg->len;
}

static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index,
			       u16 pool_index, u32 size,
			       enum devlink_sb_threshold_type threshold_type,
			       struct netlink_ext_ack *extack)

{
	const struct devlink_ops *ops = devlink->ops;

	if (ops->sb_pool_set)
		return ops->sb_pool_set(devlink, sb_index, pool_index,
					size, threshold_type, extack);
	return -EOPNOTSUPP;
}

static int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb,
					   struct genl_info *info)
{
	struct devlink *devlink = info->user_ptr[0];
	enum devlink_sb_threshold_type threshold_type;
	struct devlink_sb *devlink_sb;
	u16 pool_index;
	u32 size;
	int err;

	devlink_sb = devlink_sb_get_from_info(devlink, info);
	if (IS_ERR(devlink_sb))
		return PTR_ERR(devlink_sb);

	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
						  &pool_index);
	if (err)
		return err;

	err = devlink_sb_th_type_get_from_info(info, &threshold_type);
	if (err)
		return err;

	if (!info->attrs[DEVLINK_ATTR_SB_POOL_SIZE])
		return -EINVAL;

	size = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_POOL_SIZE]);
	return devlink_sb_pool_set(devlink, devlink_sb->index,
				   pool_index, size, threshold_type,
				   info->extack);
}

static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg,
					struct devlink *devlink,
					struct devlink_port *devlink_port,
					struct devlink_sb *devlink_sb,
					u16 pool_index,
					enum devlink_command cmd,
					u32 portid, u32 seq, int flags)
{
	const struct devlink_ops *ops = devlink->ops;
	u32 threshold;
	void *hdr;
	int err;

	err = ops->sb_port_pool_get(devlink_port, devlink_sb->index,
				    pool_index, &threshold);
	if (err)
		return err;

	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_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
		goto nla_put_failure;
	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
		goto nla_put_failure;
	if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold))
		goto nla_put_failure;

	if (ops->sb_occ_port_pool_get) {
		u32 cur;
		u32 max;

		err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index,
						pool_index, &cur, &max);
		if (err && err != -EOPNOTSUPP)
			goto sb_occ_get_failure;
		if (!err) {
			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
				goto nla_put_failure;
			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max))
				goto nla_put_failure;
		}
	}

	genlmsg_end(msg, hdr);
	return 0;

nla_put_failure:
	err = -EMSGSIZE;
sb_occ_get_failure:
	genlmsg_cancel(msg, hdr);
	return err;
}

static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb,
						struct genl_info *info)
{
	struct devlink_port *devlink_port = info->user_ptr[1];
	struct devlink *devlink = devlink_port->devlink;
	struct devlink_sb *devlink_sb;
	struct sk_buff *msg;
	u16 pool_index;
	int err;

	devlink_sb = devlink_sb_get_from_info(devlink, info);
	if (IS_ERR(devlink_sb))
		return PTR_ERR(devlink_sb);

	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
						  &pool_index);
	if (err)
		return err;

	if (!devlink->ops->sb_port_pool_get)
		return -EOPNOTSUPP;

	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	err = devlink_nl_sb_port_pool_fill(msg, devlink, devlink_port,
					   devlink_sb, pool_index,
					   DEVLINK_CMD_SB_PORT_POOL_NEW,
					   info->snd_portid, info->snd_seq, 0);
	if (err) {
		nlmsg_free(msg);
		return err;
	}

	return genlmsg_reply(msg, info);
}

static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx,
				     struct devlink *devlink,
				     struct devlink_sb *devlink_sb,
				     u32 portid, u32 seq)
{
	struct devlink_port *devlink_port;
	u16 pool_count = devlink_sb_pool_count(devlink_sb);
	u16 pool_index;
	int err;

	list_for_each_entry(devlink_port, &devlink->port_list, list) {
		for (pool_index = 0; pool_index < pool_count; pool_index++) {
			if (*p_idx < start) {
				(*p_idx)++;
				continue;
			}
			err = devlink_nl_sb_port_pool_fill(msg, devlink,
							   devlink_port,
							   devlink_sb,
							   pool_index,
							   DEVLINK_CMD_SB_PORT_POOL_NEW,
							   portid, seq,
							   NLM_F_MULTI);
			if (err)
				return err;
			(*p_idx)++;
		}
	}
	return 0;
}

static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg,
						  struct netlink_callback *cb)
{
	struct devlink *devlink;
	struct devlink_sb *devlink_sb;
	int start = cb->args[0];
	unsigned long index;
	int idx = 0;
	int err = 0;

	mutex_lock(&devlink_mutex);
	xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) {
		if (!devlink_try_get(devlink))
			continue;

		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) ||
		    !devlink->ops->sb_port_pool_get)
			goto retry;

		mutex_lock(&devlink->lock);
		list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
			err = __sb_port_pool_get_dumpit(msg, start, &idx,
							devlink, devlink_sb,
							NETLINK_CB(cb->skb).portid,
							cb->nlh->nlmsg_seq);
			if (err == -EOPNOTSUPP) {
				err = 0;
			} else if (err) {
				mutex_unlock(&devlink->lock);
				devlink_put(devlink);
				goto out;
			}
		}
		mutex_unlock(&devlink->lock);
retry:
		devlink_put(devlink);
	}
out:
	mutex_unlock(&devlink_mutex);

	if (err != -EMSGSIZE)
		return err;

	cb->args[0] = idx;
	return msg->len;
}

static int devlink_sb_port_pool_set(struct devlink_port *devlink_port,
				    unsigned int sb_index, u16 pool_index,
				    u32 threshold,
				    struct netlink_ext_ack *extack)

{
	const struct devlink_ops *ops = devlink_port->devlink->ops;

	if (ops->sb_port_pool_set)
		return ops->sb_port_pool_set(devlink_port, sb_index,
					     pool_index, threshold, extack);
	return -EOPNOTSUPP;
}

static int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb,
						struct genl_info *info)
{
	struct devlink_port *devlink_port = info->user_ptr[1];
	struct devlink *devlink = info->user_ptr[0];
	struct devlink_sb *devlink_sb;
	u16 pool_index;
	u32 threshold;
	int err;

	devlink_sb = devlink_sb_get_from_info(devlink, info);
	if (IS_ERR(devlink_sb))
		return PTR_ERR(devlink_sb);

	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
						  &pool_index);
	if (err)
		return err;

	if (!info->attrs[DEVLINK_ATTR_SB_THRESHOLD])
		return -EINVAL;

	threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]);
	return devlink_sb_port_pool_set(devlink_port, devlink_sb->index,
					pool_index, threshold, info->extack);
}

static int
devlink_nl_sb_tc_pool_bind_fill(struct sk_buff *msg, struct devlink *devlink,
				struct devlink_port *devlink_port,
				struct devlink_sb *devlink_sb, u16 tc_index,
				enum devlink_sb_pool_type pool_type,
				enum devlink_command cmd,
				u32 portid, u32 seq, int flags)
{
	const struct devlink_ops *ops = devlink->ops;
	u16 pool_index;
	u32 threshold;
	void *hdr;
	int err;

	err = ops->sb_tc_pool_bind_get(devlink_port, devlink_sb->index,
				       tc_index, pool_type,
				       &pool_index, &threshold);
	if (err)
		return err;

	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_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index))
		goto nla_put_failure;
	if (nla_put_u16(msg, DEVLINK_ATTR_SB_TC_INDEX, tc_index))
		goto nla_put_failure;
	if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_type))
		goto nla_put_failure;
	if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index))
		goto nla_put_failure;
	if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold))
		goto nla_put_failure;

	if (ops->sb_occ_tc_port_bind_get) {
		u32 cur;
		u32 max;

		err = ops->sb_occ_tc_port_bind_get(devlink_port,
						   devlink_sb->index,
						   tc_index, pool_type,
						   &cur, &max);
		if (err && err != -EOPNOTSUPP)
			return err;
		if (!err) {
			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
				goto nla_put_failure;
			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max))
				goto nla_put_failure;
		}
	}

	genlmsg_end(msg, hdr);
	return 0;

nla_put_failure:
	genlmsg_cancel(msg, hdr);
	return -EMSGSIZE;
}

static int devlink_nl_cmd_sb_tc_pool_bind_get_doit(struct sk_buff *skb,
						   struct genl_info *info)
{
	struct devlink_port *devlink_port = info->user_ptr[1];
	struct devlink *devlink = devlink_port->devlink;
	struct devlink_sb *devlink_sb;
	struct sk_buff *msg;
	enum devlink_sb_pool_type pool_type;
	u16 tc_index;
	int err;

	devlink_sb = devlink_sb_get_from_info(devlink, info);
	if (IS_ERR(devlink_sb))
		return PTR_ERR(devlink_sb);

	err = devlink_sb_pool_type_get_from_info(info, &pool_type);
	if (err)
		return err;

	err = devlink_sb_tc_index_get_from_info(devlink_sb, info,
						pool_type, &tc_index);
	if (err)
		return err;

	if (!devlink->ops->sb_tc_pool_bind_get)
		return -EOPNOTSUPP;

	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!msg)
		return -ENOMEM;

	err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port,
					      devlink_sb, tc_index, pool_type,
					      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
					      info->snd_portid,
					      info->snd_seq, 0);
	if (err) {
		nlmsg_free(msg);
		return err;
	}

	return genlmsg_reply(msg, info);
}

static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
					int start, int *p_idx,
					struct devlink *devlink,
					struct devlink_sb *devlink_sb,
					u32 portid, u32 seq)
{
	struct devlink_port *devlink_port;
	u16 tc_index;
	int err;

	list_for_each_entry(devlink_port, &devlink->port_list, list) {
		for (tc_index = 0;
		     tc_index < devlink_sb->ingress_tc_count; tc_index++) {
			if (*p_idx < start) {
				(*p_idx)++;
				continue;
			}
			err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink,
							      devlink_port,
							      devlink_sb,
							      tc_index,
							      DEVLINK_SB_POOL_TYPE_INGRESS,
							      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
							      portid, seq,
							      NLM_F_MULTI);
			if (err)
				return err;
			(*p_idx)++;
		}
		for (tc_index = 0;
		     tc_index < devlink_sb->egress_tc_count; tc_index++) {
			if (*p_idx < start) {
				(*p_idx)++;
				continue;
			}
			err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink,
							      devlink_port,
							      devlink_sb,
							      tc_index,
							      DEVLINK_SB_POOL_TYPE_EGRESS,
							      DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
							      portid, seq,
							      NLM_F_MULTI);
			if (err)
				return err;
			(*p_idx)++;
		}
	}
	return 0;
}

static int
devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
					  struct netlink_callback *cb)
{
	struct devlink *devlink;
	struct devlink_sb *devlink_sb;
	int start = cb->args[0];
	unsigned long index;
	int idx = 0;
	int err = 0;

	mutex_lock(&devlink_mutex);
	xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) {
		if (!devlink_try_get(devlink))
			continue;

		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) ||
		    !devlink->ops->sb_tc_pool_bind_get)
			goto retry;

		mutex_lock(&devlink->lock);
		list_for_each_entry(devlink_sb, &devlink->sb_list, list) {
			err = __sb_tc_pool_bind_get_dumpit(msg, start, &idx,
							   devlink,
							   devlink_sb,
							   NETLINK_CB(cb->skb).portid,
							   cb->nlh->nlmsg_seq);
			if (err == -EOPNOTSUPP) {
				err = 0;
			} else if (err) {
				mutex_unlock(&devlink->lock);
				devlink_put(devlink);
				goto out;
			}
		}
		mutex_unlock(&devlink->lock);
retry:
		devlink_put(devlink);
	}
out:
	mutex_unlock(&devlink_mutex);

	if (err != -EMSGSIZE)
		return err;

	cb->args[0] = idx;
	return msg->len;
}

static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
				       unsigned int sb_index, u16 tc_index,
				       enum devlink_sb_pool_type pool_type,
				       u16 pool_index, u32 threshold,
				       struct netlink_ext_ack *extack)

{
	const struct devlink_ops *ops = devlink_port->devlink->ops;

	if (ops->sb_tc_pool_bind_set)
		return ops->sb_tc_pool_bind_set(devlink_port, sb_index,
						tc_index, pool_type,
						pool_index, threshold, extack);
	return -EOPNOTSUPP;
}

static int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb,
						   struct genl_info *info)
{
	struct devlink_port *devlink_port = info->user_ptr[1];
	struct devlink *devlink = info->user_ptr[0];
	enum devlink_sb_pool_type pool_type;
	struct devlink_sb *devlink_sb;
	u16 tc_index;
	u16 pool_index;
	u32 threshold;
	int err;

	devlink_sb = devlink_sb_get_from_info(devlink, info);
	if (IS_ERR(devlink_sb))
		return PTR_ERR(devlink_sb);

	err = devlink_sb_pool_type_get_from_info(info, &pool_type);
	if (err)
		return err;

	err = devlink_sb_tc_index_get_from_info(devlink_sb, info,
						pool_type, &tc_index);
	if (err)
		return err;

	err = devlink_sb_pool_index_get_from_info(devlink_sb, info,
						  &pool_index);
	if (err)
		return err;

	if (!info->attrs[DEVLINK_ATTR_SB_THRESHOLD])
		return -EINVAL;

	threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]);
	return devlink_sb_tc_pool_bind_set(devlink_port, devlink_sb->index,
					   tc_index, pool_type,
					   pool_index, threshold, info->extack);
}

static int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb,
					       struct genl_info *info)
{
	struct devlink *devlink = info->user_ptr[0];
	const struct devlink_ops *ops = devlink->ops;
	struct devlink_sb *devlink_sb;

	devlink_sb = devlink_sb_get_from_info(devlink, info);
	if (IS_ERR(devlink_sb))
		return PTR_ERR(devlink_sb);

	if (ops->sb_occ_snapshot)
		return ops->sb_occ_snapshot(devlink, devlink_sb->index);
	return -EOPNOTSUPP;
}

static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb,
						struct genl_info *info)
{
	struct devlink *devlink = info->user_ptr[0];
	const struct devlink_ops *ops = devlink->ops;
	struct devlink_sb *devlink_sb;

	devlink_sb = devlink_sb_get_from_info(devlink, info);
	if (IS_ERR(devlink_sb))
		return PTR_ERR(devlink_sb);

	if (ops->sb_occ_max_clear)
		return ops->sb_occ_max_clear(devlink, devlink_sb->index);
	return -EOPNOTSUPP;
}

static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
				   enum devlink_command cmd, u32 portid,
				   u32 seq, int flags)
{
	const struct devlink_ops *ops = devlink->ops;
	enum devlink_eswitch_encap_mode encap_mode;
	u8 inline_mode;
	void *hdr;
	int err = 0;
	u16 mode;

	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
	if (!hdr)
		return -EMSGSIZE;

	err = devlink_nl_put_handle(msg, devlink);
	if (err)
		goto nla_put_failure;

	if (ops->eswitch_mode_get) {
		err = ops->eswitch_mode_get(devlink, &mode);
		if (err)
			goto nla_put_failure;
		err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode);
		if (err)
			goto nla_put_failure;
	}

	if (ops->eswitch_inline_mode_get) {
		err = ops->eswitch_inline_mode_get(devlink, &inline_mode);
		if (err)
			goto nla_put_failure;
		err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE,
				 inline_mode);
		if (err)
			goto nla_put_failure;
	}

	if (ops->eswitch_encap_mode_get) {
		err = ops->eswitch_encap_mode_get(devlink, &encap_mode);
		if (err)
			goto nla_put_failure;
		err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode);
		if (err)
			goto nla_put_failure;
	}

	genlmsg_end(msg, hdr);
	return 0;

nla_put_failure:
	genlmsg_cancel(msg, hdr);
	return err;
}

static int devlink_nl_cmd_eswitch_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_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET,
				      info->snd_portid, info->snd_seq, 0);

	if (err) {
		nlmsg_free(msg);
		return err;
	}

	return genlmsg_reply(msg, info);
}

static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode,
				    struct netlink_ext_ack *extack)
{
	struct devlink_rate *devlink_rate;

	/* Take the lock to sync with devlink_rate_nodes_destroy() */
	mutex_lock(&devlink->lock);
	list_for_each_entry(devlink_rate, &devlink->rate_list, list)
		if (devlink_rate_is_node(devlink_rate)) {
			mutex_unlock(&devlink->lock);
			NL_SET_ERR_MSG_MOD(extack, "Rate node(s) exists.");
			return -EBUSY;
		}
	mutex_unlock(&devlink->lock);
	return 0;
}

static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
					   struct genl_info *info)
{
	struct devlink *devlink = info->user_ptr[0];
	const struct devlink_ops *ops = devlink->ops;
	enum devlink_eswitch_encap_mode encap_mode;
	u8 inline_mode;
	int err = 0;
	u16 mode;

	if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) {
		if (!ops->eswitch_mode_set)
			return -EOPNOTSUPP;
		mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]);
		err = devlink_rate_nodes_check(devlink, mode, info->extack);
		if (err)
			return err;
		err = ops->eswitch_mode_set(devlink, mode, info->extack);
		if (err)
			return err;
	}

	if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) {
		if (!ops->eswitch_inline_mode_set)
			return -EOPNOTSUPP;
		inline_mode = nla_get_u8(
				info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]);
		err = ops->eswitch_inline_mode_set(devlink, inline_mode,
						   info->extack);
		if (err)
			return err;
	}

	if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) {
		if (!ops->eswitch_encap_mode_set)
			return -EOPNOTSUPP;
		encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]);
		err = ops->eswitch_encap_mode_set(devlink, encap_mode,
						  info->extack);
		if (err)
			return err;
	}

	return 0;
}

int devlink_dpipe_match_put(struct sk_buff *skb,
			    struct devlink_dpipe_match *match)
{
	struct devlink_dpipe_header *header = match->header;
	struct devlink_dpipe_field *field = &header->fields[match->field_id];
	struct nlattr *match_attr;

	match_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_MATCH);
	if (!match_attr)
		return -EMSGSIZE;

	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) ||
	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) ||
	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
		goto nla_put_failure;

	nla_nest_end(skb, match_attr);
	return 0;

nla_put_failure:
	nla_nest_cancel(skb, match_attr);
	return -EMSGSIZE;
}
EXPORT_SYMBOL_GPL(devlink_dpipe_match_put);

static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table,
				     struct sk_buff *skb)
{
	struct nlattr *matches_attr;

	matches_attr = nla_nest_start_noflag(skb,
					     DEVLINK_ATTR_DPIPE_TABLE_MATCHES);
	if (!matches_attr)
		return -EMSGSIZE;

	if (table->table_ops->matches_dump(table->priv, skb))
		goto nla_put_failure;

	nla_nest_end(skb, matches_attr);
	return 0;

nla_put_failure:
	nla_nest_cancel(skb, matches_attr);
	return -EMSGSIZE;
}

int devlink_dpipe_action_put(struct sk_buff *skb,
			     struct devlink_dpipe_action *action)
{
	struct devlink_dpipe_header *header = action->header;
	struct devlink_dpipe_field *field = &header->fields[action->field_id];
	struct nlattr *action_attr;

	action_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ACTION);
	if (!action_attr)
		return -EMSGSIZE;

	if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) ||
	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) ||
	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) ||
	    nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) ||
	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
		goto nla_put_failure;

	nla_nest_end(skb, action_attr);
	return 0;

nla_put_failure:
	nla_nest_cancel(skb, action_attr);
	return -EMSGSIZE;
}
EXPORT_SYMBOL_GPL(devlink_dpipe_action_put);

static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table,
				     struct sk_buff *skb)
{
	struct nlattr *actions_attr;

	actions_attr = nla_nest_start_noflag(skb,
					     DEVLINK_ATTR_DPIPE_TABLE_ACTIONS);
	if (!actions_attr)
		return -EMSGSIZE;

	if (table->table_ops->actions_dump(table->priv, skb))
		goto nla_put_failure;

	nla_nest_end(skb, actions_attr);
	return 0;

nla_put_failure:
	nla_nest_cancel(skb, actions_attr);
	return -EMSGSIZE;
}

static int devlink_dpipe_table_put(struct sk_buff *skb,
				   struct devlink_dpipe_table *table)
{
	struct nlattr *table_attr;
	u64 table_size;

	table_size = table->table_ops->size_get(table->priv);
	table_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLE);
	if (!table_attr)
		return -EMSGSIZE;

	if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) ||
	    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table_size,
			      DEVLINK_ATTR_PAD))
		goto nla_put_failure;
	if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED,
		       table->counters_enabled))
		goto nla_put_failure;

	if (table->resource_valid) {
		if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID,
				      table->resource_id, DEVLINK_ATTR_PAD) ||
		    nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS,
				      table->resource_units, DEVLINK_ATTR_PAD))
			goto nla_put_failure;
	}
	if (devlink_dpipe_matches_put(table, skb))
		goto nla_put_failure;

	if (devlink_dpipe_actions_put(table, skb))
		goto nla_put_failure;

	nla_nest_end(skb, table_attr);
	return 0;

nla_put_failure:
	nla_nest_cancel(skb, table_attr);
	return -EMSGSIZE;
}

static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb,
					    struct genl_info *info)
{
	int err;

	if (*pskb) {
		err = genlmsg_reply(*pskb, info);
		if (err)
			return err;
	}
	*pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!*pskb)
		return -ENOMEM;
	return 0;
}

static int devlink_dpipe_tables_fill(struct genl_info *info,
				     enum devlink_command cmd, int flags,
				     struct list_head *dpipe_tables,
				     const char *table_name)
{
	struct devlink *devlink = info->user_ptr[0];
	struct devlink_dpipe_table *table;
	struct nlattr *tables_attr;
	struct sk_buff *skb = NULL;
	struct nlmsghdr *nlh;
	bool incomplete;
	void *hdr;
	int i;
	int err;

	table = list_first_entry(dpipe_tables,
				 struct devlink_dpipe_table, list);
start_again:
	err = devlink_dpipe_send_and_alloc_skb(&skb, info);
	if (err)
		return err;

	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
			  &devlink_nl_family, NLM_F_MULTI, cmd);
	if (!hdr) {
		nlmsg_free(skb);
		return -EMSGSIZE;
	}

	if (devlink_nl_put_handle(skb, devlink))
		goto nla_put_failure;
	tables_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLES);
	if (!tables_attr)
		goto nla_put_failure;

	i = 0;
	incomplete = false;
	list_for_each_entry_from(table, dpipe_tables, list) {
		if (!table_name) {
			err = devlink_dpipe_table_put(skb, table);
			if (err) {
				if (!i)
					goto err_table_put;
				incomplete = true;
				break;
			}
		} else {
			if (!strcmp(table->name, table_name)) {
				err = devlink_dpipe_table_put(skb, table);
				if (err)
					break;
			}
		}
		i++;