// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * INET         An implementation of the TCP/IP protocol suite for the LINUX
 *              operating system.  INET is implemented using the  BSD Socket
 *              interface as the means of communication with the user level.
 *
 *              Routing netlink socket interface: protocol independent part.
 *
 * Authors:     Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 *      Fixes:
 *      Vitaly E. Lavrov                RTA_OK arithmetics was wrong.
 */

#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/kernel.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/security.h>
#include <linux/mutex.h>
#include <linux/if_addr.h>
#include <linux/if_bridge.h>
#include <linux/if_vlan.h>
#include <linux/pci.h>
#include <linux/etherdevice.h>
#include <linux/bpf.h>

#include <linux/uaccess.h>

#include <linux/inet.h>
#include <linux/netdevice.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/udp.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/pkt_sched.h>
#include <net/fib_rules.h>
#include <net/rtnetlink.h>
#include <net/net_namespace.h>

#define RTNL_MAX_TYPE           50
#define RTNL_SLAVE_MAX_TYPE     36

struct rtnl_link {
        rtnl_doit_func          doit;
        rtnl_dumpit_func        dumpit;
        struct module           *owner;
        unsigned int            flags;
        struct rcu_head         rcu;
};

static DEFINE_MUTEX(rtnl_mutex);

void rtnl_lock(void)
{
        mutex_lock(&rtnl_mutex);
}
EXPORT_SYMBOL(rtnl_lock);

int rtnl_lock_killable(void)
{
        return mutex_lock_killable(&rtnl_mutex);
}
EXPORT_SYMBOL(rtnl_lock_killable);

static struct sk_buff *defer_kfree_skb_list;
void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail)
{
        if (head && tail) {
                tail->next = defer_kfree_skb_list;
                defer_kfree_skb_list = head;
        }
}
EXPORT_SYMBOL(rtnl_kfree_skbs);

void __rtnl_unlock(void)
{
        struct sk_buff *head = defer_kfree_skb_list;

        defer_kfree_skb_list = NULL;

        mutex_unlock(&rtnl_mutex);

        while (head) {
                struct sk_buff *next = head->next;

                kfree_skb(head);
                cond_resched();
                head = next;
        }
}

void rtnl_unlock(void)
{
        /* This fellow will unlock it for us. */
        netdev_run_todo();
}
EXPORT_SYMBOL(rtnl_unlock);

int rtnl_trylock(void)
{
        return mutex_trylock(&rtnl_mutex);
}
EXPORT_SYMBOL(rtnl_trylock);

int rtnl_is_locked(void)
{
        return mutex_is_locked(&rtnl_mutex);
}
EXPORT_SYMBOL(rtnl_is_locked);

bool refcount_dec_and_rtnl_lock(refcount_t *r)
{
        return refcount_dec_and_mutex_lock(r, &rtnl_mutex);
}
EXPORT_SYMBOL(refcount_dec_and_rtnl_lock);

#ifdef CONFIG_PROVE_LOCKING
bool lockdep_rtnl_is_held(void)
{
        return lockdep_is_held(&rtnl_mutex);
}
EXPORT_SYMBOL(lockdep_rtnl_is_held);
#endif /* #ifdef CONFIG_PROVE_LOCKING */

static struct rtnl_link *__rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];

static inline int rtm_msgindex(int msgtype)
{
        int msgindex = msgtype - RTM_BASE;

        /*
         * msgindex < 0 implies someone tried to register a netlink
         * control code. msgindex >= RTM_NR_MSGTYPES may indicate that
         * the message type has not been added to linux/rtnetlink.h
         */
        BUG_ON(msgindex < 0 || msgindex >= RTM_NR_MSGTYPES);

        return msgindex;
}

static struct rtnl_link *rtnl_get_link(int protocol, int msgtype)
{
        struct rtnl_link **tab;

        if (protocol >= ARRAY_SIZE(rtnl_msg_handlers))
                protocol = PF_UNSPEC;

        tab = rcu_dereference_rtnl(rtnl_msg_handlers[protocol]);
        if (!tab)
                tab = rcu_dereference_rtnl(rtnl_msg_handlers[PF_UNSPEC]);

        return tab[msgtype];
}

static int rtnl_register_internal(struct module *owner,
                                  int protocol, int msgtype,
                                  rtnl_doit_func doit, rtnl_dumpit_func dumpit,
                                  unsigned int flags)
{
        struct rtnl_link *link, *old;
        struct rtnl_link __rcu **tab;
        int msgindex;
        int ret = -ENOBUFS;

        BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
        msgindex = rtm_msgindex(msgtype);

        rtnl_lock();
        tab = rtnl_msg_handlers[protocol];
        if (tab == NULL) {
                tab = kcalloc(RTM_NR_MSGTYPES, sizeof(void *), GFP_KERNEL);
                if (!tab)
                        goto unlock;

                /* ensures we see the 0 stores */
                rcu_assign_pointer(rtnl_msg_handlers[protocol], tab);
        }

        old = rtnl_dereference(tab[msgindex]);
        if (old) {
                link = kmemdup(old, sizeof(*old), GFP_KERNEL);
                if (!link)
                        goto unlock;
        } else {
                link = kzalloc(sizeof(*link), GFP_KERNEL);
                if (!link)
                        goto unlock;
        }

        WARN_ON(link->owner && link->owner != owner);
        link->owner = owner;

        WARN_ON(doit && link->doit && link->doit != doit);
        if (doit)
                link->doit = doit;
        WARN_ON(dumpit && link->dumpit && link->dumpit != dumpit);
        if (dumpit)
                link->dumpit = dumpit;

        link->flags |= flags;

        /* publish protocol:msgtype */
        rcu_assign_pointer(tab[msgindex], link);
        ret = 0;
        if (old)
                kfree_rcu(old, rcu);
unlock:
        rtnl_unlock();
        return ret;
}

/**
 * rtnl_register_module - Register a rtnetlink message type
 *
 * @owner: module registering the hook (THIS_MODULE)
 * @protocol: Protocol family or PF_UNSPEC
 * @msgtype: rtnetlink message type
 * @doit: Function pointer called for each request message
 * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
 * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions
 *
 * Like rtnl_register, but for use by removable modules.
 */
int rtnl_register_module(struct module *owner,
                         int protocol, int msgtype,
                         rtnl_doit_func doit, rtnl_dumpit_func dumpit,
                         unsigned int flags)
{
        return rtnl_register_internal(owner, protocol, msgtype,
                                      doit, dumpit, flags);
}
EXPORT_SYMBOL_GPL(rtnl_register_module);

/**
 * rtnl_register - Register a rtnetlink message type
 * @protocol: Protocol family or PF_UNSPEC
 * @msgtype: rtnetlink message type
 * @doit: Function pointer called for each request message
 * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
 * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions
 *
 * Registers the specified function pointers (at least one of them has
 * to be non-NULL) to be called whenever a request message for the
 * specified protocol family and message type is received.
 *
 * The special protocol family PF_UNSPEC may be used to define fallback
 * function pointers for the case when no entry for the specific protocol
 * family exists.
 */
void rtnl_register(int protocol, int msgtype,
                   rtnl_doit_func doit, rtnl_dumpit_func dumpit,
                   unsigned int flags)
{
        int err;

        err = rtnl_register_internal(NULL, protocol, msgtype, doit, dumpit,
                                     flags);
        if (err)
                pr_err("Unable to register rtnetlink message handler, "
                       "protocol = %d, message type = %d\n", protocol, msgtype);
}

/**
 * rtnl_unregister - Unregister a rtnetlink message type
 * @protocol: Protocol family or PF_UNSPEC
 * @msgtype: rtnetlink message type
 *
 * Returns 0 on success or a negative error code.
 */
int rtnl_unregister(int protocol, int msgtype)
{
        struct rtnl_link **tab, *link;
        int msgindex;

        BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
        msgindex = rtm_msgindex(msgtype);

        rtnl_lock();
        tab = rtnl_dereference(rtnl_msg_handlers[protocol]);
        if (!tab) {
                rtnl_unlock();
                return -ENOENT;
        }

        link = tab[msgindex];
        rcu_assign_pointer(tab[msgindex], NULL);
        rtnl_unlock();

        kfree_rcu(link, rcu);

        return 0;
}
EXPORT_SYMBOL_GPL(rtnl_unregister);

/**
 * rtnl_unregister_all - Unregister all rtnetlink message type of a protocol
 * @protocol : Protocol family or PF_UNSPEC
 *
 * Identical to calling rtnl_unregster() for all registered message types
 * of a certain protocol family.
 */
void rtnl_unregister_all(int protocol)
{
        struct rtnl_link **tab, *link;
        int msgindex;

        BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);

        rtnl_lock();
        tab = rtnl_msg_handlers[protocol];
        if (!tab) {
                rtnl_unlock();
                return;
        }
        RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL);
        for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) {
                link = tab[msgindex];
                if (!link)
                        continue;

                rcu_assign_pointer(tab[msgindex], NULL);
                kfree_rcu(link, rcu);
        }
        rtnl_unlock();

        synchronize_net();

        kfree(tab);
}
EXPORT_SYMBOL_GPL(rtnl_unregister_all);

static LIST_HEAD(link_ops);

static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind)
{
        const struct rtnl_link_ops *ops;

        list_for_each_entry(ops, &link_ops, list) {
                if (!strcmp(ops->kind, kind))
                        return ops;
        }
        return NULL;
}

/**
 * __rtnl_link_register - Register rtnl_link_ops with rtnetlink.
 * @ops: struct rtnl_link_ops * to register
 *
 * The caller must hold the rtnl_mutex. This function should be used
 * by drivers that create devices during module initialization. It
 * must be called before registering the devices.
 *
 * Returns 0 on success or a negative error code.
 */
int __rtnl_link_register(struct rtnl_link_ops *ops)
{
        if (rtnl_link_ops_get(ops->kind))
                return -EEXIST;

        /* The check for setup is here because if ops
         * does not have that filled up, it is not possible
         * to use the ops for creating device. So do not
         * fill up dellink as well. That disables rtnl_dellink.
         */
        if (ops->setup && !ops->dellink)
                ops->dellink = unregister_netdevice_queue;

        list_add_tail(&ops->list, &link_ops);
        return 0;
}
EXPORT_SYMBOL_GPL(__rtnl_link_register);

/**
 * rtnl_link_register - Register rtnl_link_ops with rtnetlink.
 * @ops: struct rtnl_link_ops * to register
 *
 * Returns 0 on success or a negative error code.
 */
int rtnl_link_register(struct rtnl_link_ops *ops)
{
        int err;

        /* Sanity-check max sizes to avoid stack buffer overflow. */
        if (WARN_ON(ops->maxtype > RTNL_MAX_TYPE ||
                    ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE))
                return -EINVAL;

        rtnl_lock();
        err = __rtnl_link_register(ops);
        rtnl_unlock();
        return err;
}
EXPORT_SYMBOL_GPL(rtnl_link_register);

static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops)
{
        struct net_device *dev;
        LIST_HEAD(list_kill);

        for_each_netdev(net, dev) {
                if (dev->rtnl_link_ops == ops)
                        ops->dellink(dev, &list_kill);
        }
        unregister_netdevice_many(&list_kill);
}

/**
 * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
 * @ops: struct rtnl_link_ops * to unregister
 *
 * The caller must hold the rtnl_mutex and guarantee net_namespace_list
 * integrity (hold pernet_ops_rwsem for writing to close the race
 * with setup_net() and cleanup_net()).
 */
void __rtnl_link_unregister(struct rtnl_link_ops *ops)
{
        struct net *net;

        for_each_net(net) {
                __rtnl_kill_links(net, ops);
        }
        list_del(&ops->list);
}
EXPORT_SYMBOL_GPL(__rtnl_link_unregister);

/* Return with the rtnl_lock held when there are no network
 * devices unregistering in any network namespace.
 */
static void rtnl_lock_unregistering_all(void)
{
        struct net *net;
        bool unregistering;
        DEFINE_WAIT_FUNC(wait, woken_wake_function);

        add_wait_queue(&netdev_unregistering_wq, &wait);
        for (;;) {
                unregistering = false;
                rtnl_lock();
                /* We held write locked pernet_ops_rwsem, and parallel
                 * setup_net() and cleanup_net() are not possible.
                 */
                for_each_net(net) {
                        if (net->dev_unreg_count > 0) {
                                unregistering = true;
                                break;
                        }
                }
                if (!unregistering)
                        break;
                __rtnl_unlock();

                wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
        }
        remove_wait_queue(&netdev_unregistering_wq, &wait);
}

/**
 * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
 * @ops: struct rtnl_link_ops * to unregister
 */
void rtnl_link_unregister(struct rtnl_link_ops *ops)
{
        /* Close the race with setup_net() and cleanup_net() */
        down_write(&pernet_ops_rwsem);
        rtnl_lock_unregistering_all();
        __rtnl_link_unregister(ops);
        rtnl_unlock();
        up_write(&pernet_ops_rwsem);
}
EXPORT_SYMBOL_GPL(rtnl_link_unregister);

static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev)
{
        struct net_device *master_dev;
        const struct rtnl_link_ops *ops;
        size_t size = 0;

        rcu_read_lock();

        master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev);
        if (!master_dev)
                goto out;

        ops = master_dev->rtnl_link_ops;
        if (!ops || !ops->get_slave_size)
                goto out;
        /* IFLA_INFO_SLAVE_DATA + nested data */
        size = nla_total_size(sizeof(struct nlattr)) +
               ops->get_slave_size(master_dev, dev);

out:
        rcu_read_unlock();
        return size;
}

static size_t rtnl_link_get_size(const struct net_device *dev)
{
        const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
        size_t size;

        if (!ops)
                return 0;

        size = nla_total_size(sizeof(struct nlattr)) + /* IFLA_LINKINFO */
               nla_total_size(strlen(ops->kind) + 1);  /* IFLA_INFO_KIND */

        if (ops->get_size)
                /* IFLA_INFO_DATA + nested data */
                size += nla_total_size(sizeof(struct nlattr)) +
                        ops->get_size(dev);

        if (ops->get_xstats_size)
                /* IFLA_INFO_XSTATS */
                size += nla_total_size(ops->get_xstats_size(dev));

        size += rtnl_link_get_slave_info_data_size(dev);

        return size;
}

static LIST_HEAD(rtnl_af_ops);

static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
{
        const struct rtnl_af_ops *ops;

        list_for_each_entry_rcu(ops, &rtnl_af_ops, list) {
                if (ops->family == family)
                        return ops;
        }

        return NULL;
}

/**
 * rtnl_af_register - Register rtnl_af_ops with rtnetlink.
 * @ops: struct rtnl_af_ops * to register
 *
 * Returns 0 on success or a negative error code.
 */
void rtnl_af_register(struct rtnl_af_ops *ops)
{
        rtnl_lock();
        list_add_tail_rcu(&ops->list, &rtnl_af_ops);
        rtnl_unlock();
}
EXPORT_SYMBOL_GPL(rtnl_af_register);

/**
 * rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink.
 * @ops: struct rtnl_af_ops * to unregister
 */
void rtnl_af_unregister(struct rtnl_af_ops *ops)
{
        rtnl_lock();
        list_del_rcu(&ops->list);
        rtnl_unlock();

        synchronize_rcu();
}
EXPORT_SYMBOL_GPL(rtnl_af_unregister);

static size_t rtnl_link_get_af_size(const struct net_device *dev,
                                    u32 ext_filter_mask)
{
        struct rtnl_af_ops *af_ops;
        size_t size;

        /* IFLA_AF_SPEC */
        size = nla_total_size(sizeof(struct nlattr));

        rcu_read_lock();
        list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
                if (af_ops->get_link_af_size) {
                        /* AF_* + nested data */
                        size += nla_total_size(sizeof(struct nlattr)) +
                                af_ops->get_link_af_size(dev, ext_filter_mask);
                }
        }
        rcu_read_unlock();

        return size;
}

static bool rtnl_have_link_slave_info(const struct net_device *dev)
{
        struct net_device *master_dev;
        bool ret = false;

        rcu_read_lock();

        master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev);
        if (master_dev && master_dev->rtnl_link_ops)
                ret = true;
        rcu_read_unlock();
        return ret;
}

static int rtnl_link_slave_info_fill(struct sk_buff *skb,
                                     const struct net_device *dev)
{
        struct net_device *master_dev;
        const struct rtnl_link_ops *ops;
        struct nlattr *slave_data;
        int err;

        master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
        if (!master_dev)
                return 0;
        ops = master_dev->rtnl_link_ops;
        if (!ops)
                return 0;
        if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0)
                return -EMSGSIZE;
        if (ops->fill_slave_info) {
                slave_data = nla_nest_start_noflag(skb, IFLA_INFO_SLAVE_DATA);
                if (!slave_data)
                        return -EMSGSIZE;
                err = ops->fill_slave_info(skb, master_dev, dev);
                if (err < 0)
                        goto err_cancel_slave_data;
                nla_nest_end(skb, slave_data);
        }
        return 0;

err_cancel_slave_data:
        nla_nest_cancel(skb, slave_data);
        return err;
}

static int rtnl_link_info_fill(struct sk_buff *skb,
                               const struct net_device *dev)
{
        const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
        struct nlattr *data;
        int err;

        if (!ops)
                return 0;
        if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0)
                return -EMSGSIZE;
        if (ops->fill_xstats) {
                err = ops->fill_xstats(skb, dev);
                if (err < 0)
                        return err;
        }
        if (ops->fill_info) {
                data = nla_nest_start_noflag(skb, IFLA_INFO_DATA);
                if (data == NULL)
                        return -EMSGSIZE;
                err = ops->fill_info(skb, dev);
                if (err < 0)
                        goto err_cancel_data;
                nla_nest_end(skb, data);
        }
        return 0;

err_cancel_data:
        nla_nest_cancel(skb, data);
        return err;
}

static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev)
{
        struct nlattr *linkinfo;
        int err = -EMSGSIZE;

        linkinfo = nla_nest_start_noflag(skb, IFLA_LINKINFO);
        if (linkinfo == NULL)
                goto out;

        err = rtnl_link_info_fill(skb, dev);
        if (err < 0)
                goto err_cancel_link;

        err = rtnl_link_slave_info_fill(skb, dev);
        if (err < 0)
                goto err_cancel_link;

        nla_nest_end(skb, linkinfo);
        return 0;

err_cancel_link:
        nla_nest_cancel(skb, linkinfo);
out:
        return err;
}

int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo)
{
        struct sock *rtnl = net->rtnl;
        int err = 0;

        NETLINK_CB(skb).dst_group = group;
        if (echo)
                refcount_inc(&skb->users);
        netlink_broadcast(rtnl, skb, pid, group, GFP_KERNEL);
        if (echo)
                err = netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT);
        return err;
}

int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid)
{
        struct sock *rtnl = net->rtnl;

        return nlmsg_unicast(rtnl, skb, pid);
}
EXPORT_SYMBOL(rtnl_unicast);

void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
                 struct nlmsghdr *nlh, gfp_t flags)
{
        struct sock *rtnl = net->rtnl;
        int report = 0;

        if (nlh)
                report = nlmsg_report(nlh);

        nlmsg_notify(rtnl, skb, pid, group, report, flags);
}
EXPORT_SYMBOL(rtnl_notify);

void rtnl_set_sk_err(struct net *net, u32 group, int error)
{
        struct sock *rtnl = net->rtnl;

        netlink_set_err(rtnl, 0, group, error);
}
EXPORT_SYMBOL(rtnl_set_sk_err);

int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
{
        struct nlattr *mx;
        int i, valid = 0;

        /* nothing is dumped for dst_default_metrics, so just skip the loop */
        if (metrics == dst_default_metrics.metrics)
                return 0;

        mx = nla_nest_start_noflag(skb, RTA_METRICS);
        if (mx == NULL)
                return -ENOBUFS;

        for (i = 0; i < RTAX_MAX; i++) {
                if (metrics[i]) {
                        if (i == RTAX_CC_ALGO - 1) {
                                char tmp[TCP_CA_NAME_MAX], *name;

                                name = tcp_ca_get_name_by_key(metrics[i], tmp);
                                if (!name)
                                        continue;
                                if (nla_put_string(skb, i + 1, name))
                                        goto nla_put_failure;
                        } else if (i == RTAX_FEATURES - 1) {
                                u32 user_features = metrics[i] & RTAX_FEATURE_MASK;

                                if (!user_features)
                                        continue;
                                BUILD_BUG_ON(RTAX_FEATURE_MASK & DST_FEATURE_MASK);
                                if (nla_put_u32(skb, i + 1, user_features))
                                        goto nla_put_failure;
                        } else {
                                if (nla_put_u32(skb, i + 1, metrics[i]))
                                        goto nla_put_failure;
                        }
                        valid++;
                }
        }

        if (!valid) {
                nla_nest_cancel(skb, mx);
                return 0;
        }

        return nla_nest_end(skb, mx);

nla_put_failure:
        nla_nest_cancel(skb, mx);
        return -EMSGSIZE;
}
EXPORT_SYMBOL(rtnetlink_put_metrics);

int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
                       long expires, u32 error)
{
        struct rta_cacheinfo ci = {
                .rta_error = error,
                .rta_id =  id,
        };

        if (dst) {
                ci.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse);
                ci.rta_used = dst->__use;
                ci.rta_clntref = atomic_read(&dst->__refcnt);
        }
        if (expires) {
                unsigned long clock;

                clock = jiffies_to_clock_t(abs(expires));
                clock = min_t(unsigned long, clock, INT_MAX);
                ci.rta_expires = (expires > 0) ? clock : -clock;
        }
        return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci);
}
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);

static void set_operstate(struct net_device *dev, unsigned char transition)
{
        unsigned char operstate = dev->operstate;

        switch (transition) {
        case IF_OPER_UP:
                if ((operstate == IF_OPER_DORMANT ||
                     operstate == IF_OPER_UNKNOWN) &&
                    !netif_dormant(dev))
                        operstate = IF_OPER_UP;
                break;

        case IF_OPER_DORMANT:
                if (operstate == IF_OPER_UP ||
                    operstate == IF_OPER_UNKNOWN)
                        operstate = IF_OPER_DORMANT;
                break;
        }

        if (dev->operstate != operstate) {
                write_lock_bh(&dev_base_lock);
                dev->operstate = operstate;
                write_unlock_bh(&dev_base_lock);
                netdev_state_change(dev);
        }
}

static unsigned int rtnl_dev_get_flags(const struct net_device *dev)
{
        return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) |
               (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI));
}

static unsigned int rtnl_dev_combine_flags(const struct net_device *dev,
                                           const struct ifinfomsg *ifm)
{
        unsigned int flags = ifm->ifi_flags;

        /* bugwards compatibility: ifi_change == 0 is treated as ~0 */
        if (ifm->ifi_change)
                flags = (flags & ifm->ifi_change) |
                        (rtnl_dev_get_flags(dev) & ~ifm->ifi_change);

        return flags;
}

static void copy_rtnl_link_stats(struct rtnl_link_stats *a,
                                 const struct rtnl_link_stats64 *b)
{
        a->rx_packets = b->rx_packets;
        a->tx_packets = b->tx_packets;
        a->rx_bytes = b->rx_bytes;
        a->tx_bytes = b->tx_bytes;
        a->rx_errors = b->rx_errors;
        a->tx_errors = b->tx_errors;
        a->rx_dropped = b->rx_dropped;
        a->tx_dropped = b->tx_dropped;

        a->multicast = b->multicast;
        a->collisions = b->collisions;

        a->rx_length_errors = b->rx_length_errors;
        a->rx_over_errors = b->rx_over_errors;
        a->rx_crc_errors = b->rx_crc_errors;
        a->rx_frame_errors = b->rx_frame_errors;
        a->rx_fifo_errors = b->rx_fifo_errors;
        a->rx_missed_errors = b->rx_missed_errors;

        a->tx_aborted_errors = b->tx_aborted_errors;
        a->tx_carrier_errors = b->tx_carrier_errors;
        a->tx_fifo_errors = b->tx_fifo_errors;
        a->tx_heartbeat_errors = b->tx_heartbeat_errors;
        a->tx_window_errors = b->tx_window_errors;

        a->rx_compressed = b->rx_compressed;
        a->tx_compressed = b->tx_compressed;

        a->rx_nohandler = b->rx_nohandler;
}

/* All VF info */
static inline int rtnl_vfinfo_size(const struct net_device *dev,
                                   u32 ext_filter_mask)
{
        if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF)) {
                int num_vfs = dev_num_vf(dev->dev.parent);
                size_t size = nla_total_size(0);
                size += num_vfs *
                        (nla_total_size(0) +
                         nla_total_size(sizeof(struct ifla_vf_mac)) +
                         nla_total_size(sizeof(struct ifla_vf_broadcast)) +
                         nla_total_size(sizeof(struct ifla_vf_vlan)) +
                         nla_total_size(0) + /* nest IFLA_VF_VLAN_LIST */
                         nla_total_size(MAX_VLAN_LIST_LEN *
                                        sizeof(struct ifla_vf_vlan_info)) +
                         nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
                         nla_total_size(sizeof(struct ifla_vf_tx_rate)) +
                         nla_total_size(sizeof(struct ifla_vf_rate)) +
                         nla_total_size(sizeof(struct ifla_vf_link_state)) +
                         nla_total_size(sizeof(struct ifla_vf_rss_query_en)) +
                         nla_total_size(0) + /* nest IFLA_VF_STATS */
                         /* IFLA_VF_STATS_RX_PACKETS */
                         nla_total_size_64bit(sizeof(__u64)) +
                         /* IFLA_VF_STATS_TX_PACKETS */
                         nla_total_size_64bit(sizeof(__u64)) +
                         /* IFLA_VF_STATS_RX_BYTES */
                         nla_total_size_64bit(sizeof(__u64)) +
                         /* IFLA_VF_STATS_TX_BYTES */
                         nla_total_size_64bit(sizeof(__u64)) +
                         /* IFLA_VF_STATS_BROADCAST */
                         nla_total_size_64bit(sizeof(__u64)) +
                         /* IFLA_VF_STATS_MULTICAST */
                         nla_total_size_64bit(sizeof(__u64)) +
                         /* IFLA_VF_STATS_RX_DROPPED */
                         nla_total_size_64bit(sizeof(__u64)) +
                         /* IFLA_VF_STATS_TX_DROPPED */
                         nla_total_size_64bit(sizeof(__u64)) +
                         nla_total_size(sizeof(struct ifla_vf_trust)));
                return size;
        } else
                return 0;
}

static size_t rtnl_port_size(const struct net_device *dev,
                             u32 ext_filter_mask)
{
        size_t port_size = nla_total_size(4)            /* PORT_VF */
                + nla_total_size(PORT_PROFILE_MAX)      /* PORT_PROFILE */
                + nla_total_size(PORT_UUID_MAX)         /* PORT_INSTANCE_UUID */
                + nla_total_size(PORT_UUID_MAX)         /* PORT_HOST_UUID */
                + nla_total_size(1)                     /* PROT_VDP_REQUEST */
                + nla_total_size(2);                    /* PORT_VDP_RESPONSE */
        size_t vf_ports_size = nla_total_size(sizeof(struct nlattr));
        size_t vf_port_size = nla_total_size(sizeof(struct nlattr))
                + port_size;
        size_t port_self_size = nla_total_size(sizeof(struct nlattr))
                + port_size;

        if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
            !(ext_filter_mask & RTEXT_FILTER_VF))
                return 0;
        if (dev_num_vf(dev->dev.parent))
                return port_self_size + vf_ports_size +
                        vf_port_size * dev_num_vf(dev->dev.parent);
        else
                return port_self_size;
}

static size_t rtnl_xdp_size(void)
{
        size_t xdp_size = nla_total_size(0) +   /* nest IFLA_XDP */
                          nla_total_size(1) +   /* XDP_ATTACHED */
                          nla_total_size(4) +   /* XDP_PROG_ID (or 1st mode) */
                          nla_total_size(4);    /* XDP_<mode>_PROG_ID */

        return xdp_size;
}

static noinline size_t if_nlmsg_size(const struct net_device *dev,
                                     u32 ext_filter_mask)
{
        return NLMSG_ALIGN(sizeof(struct ifinfomsg))
               + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
               + nla_total_size(IFALIASZ) /* IFLA_IFALIAS */
               + nla_total_size(IFNAMSIZ) /* IFLA_QDISC */
               + nla_total_size_64bit(sizeof(struct rtnl_link_ifmap))
               + nla_total_size(sizeof(struct rtnl_link_stats))
               + nla_total_size_64bit(sizeof(struct rtnl_link_stats64))
               + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
               + nla_total_size(MAX_ADDR_LEN) /* IFLA_BROADCAST */
               + nla_total_size(4) /* IFLA_TXQLEN */
               + nla_total_size(4) /* IFLA_WEIGHT */
               + nla_total_size(4) /* IFLA_MTU */
               + nla_total_size(4) /* IFLA_LINK */
               + nla_total_size(4) /* IFLA_MASTER */
               + nla_total_size(1) /* IFLA_CARRIER */

               + nla_total_size(4) /* IFLA_PROMISCUITY */
               + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */
               + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */
               + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */
               + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */
               + nla_total_size(1) /* IFLA_OPERSTATE */
               + nla_total_size(1) /* IFLA_LINKMODE */
               + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
               + nla_total_size(4) /* IFLA_LINK_NETNSID */
               + nla_total_size(4) /* IFLA_GROUP */
               + nla_total_size(ext_filter_mask
                                & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
               + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
               + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
               + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
               + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */
               + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
               + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
               + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
               + rtnl_xdp_size() /* IFLA_XDP */
               + nla_total_size(4)  /* IFLA_EVENT */
               + nla_total_size(4)  /* IFLA_NEW_NETNSID */
               + nla_total_size(4)  /* IFLA_NEW_IFINDEX */
               + nla_total_size(1)  /* IFLA_PROTO_DOWN */
               + nla_total_size(4)  /* IFLA_TARGET_NETNSID */
               + nla_total_size(4)  /* IFLA_CARRIER_UP_COUNT */
               + nla_total_size(4)  /* IFLA_CARRIER_DOWN_COUNT */
               + nla_total_size(4)  /* IFLA_MIN_MTU */
               + nla_total_size(4)  /* IFLA_MAX_MTU */
               + 0;
}

static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
{
        struct nlattr *vf_ports;
        struct nlattr *vf_port;
        int vf;
        int err;

        vf_ports = nla_nest_start_noflag(skb, IFLA_VF_PORTS);
        if (!vf_ports)
                return -EMSGSIZE;

        for (vf = 0; vf < dev_num_vf(dev->dev.parent); vf++) {
                vf_port = nla_nest_start_noflag(skb, IFLA_VF_PORT);
                if (!vf_port)
                        goto nla_put_failure;
                if (nla_put_u32(skb, IFLA_PORT_VF, vf))
                        goto nla_put_failure;
                err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb);
                if (err == -EMSGSIZE)
                        goto nla_put_failure;
                if (err) {
                        nla_nest_cancel(skb, vf_port);
                        continue;
                }
                nla_nest_end(skb, vf_port);
        }

        nla_nest_end(skb, vf_ports);

        return 0;

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

static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
{
        struct nlattr *port_self;
        int err;

        port_self = nla_nest_start_noflag(skb, IFLA_PORT_SELF);
        if (!port_self)
                return -EMSGSIZE;

        err = dev->netdev_ops->ndo_get_vf_port(dev, PORT_SELF_VF, skb);
        if (err) {
                nla_nest_cancel(skb, port_self);
                return (err == -EMSGSIZE) ? err : 0;
        }

        nla_nest_end(skb, port_self);

        return 0;
}

static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
                          u32 ext_filter_mask)
{
        int err;

        if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
            !(ext_filter_mask & RTEXT_FILTER_VF))
                return 0;

        err = rtnl_port_self_fill(skb, dev);
        if (err)
                return err;

        if (dev_num_vf(dev->dev.parent)) {
                err = rtnl_vf_ports_fill(skb, dev);
                if (err)
                        return err;
        }

        return 0;
}

static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
{
        int err;
        struct netdev_phys_item_id ppid;

        err = dev_get_phys_port_id(dev, &ppid);
        if (err) {
                if (err == -EOPNOTSUPP)
                        return 0;
                return err;
        }

        if (nla_put(skb, IFLA_PHYS_PORT_ID, ppid.id_len, ppid.id))
                return -EMSGSIZE;

        return 0;
}

static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev)
{
        char name[IFNAMSIZ];
        int err;

        err = dev_get_phys_port_name(dev, name, sizeof(name));
        if (err) {
                if (err == -EOPNOTSUPP)
                        return 0;
                return err;
        }

        if (nla_put_string(skb, IFLA_PHYS_PORT_NAME, name))
                return -EMSGSIZE;

        return 0;
}

static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
{
        struct netdev_phys_item_id ppid = { };
        int err;

        err = dev_get_port_parent_id(dev, &ppid, false);
        if (err) {
                if (err == -EOPNOTSUPP)
                        return 0;
                return err;
        }

        if (nla_put(skb, IFLA_PHYS_SWITCH_ID, ppid.id_len, ppid.id))
                return -EMSGSIZE;

        return 0;
}

static noinline_for_stack int rtnl_fill_stats(struct sk_buff *skb,
                                              struct net_device *dev)
{
        struct rtnl_link_stats64 *sp;
        struct nlattr *attr;

        attr = nla_reserve_64bit(skb, IFLA_STATS64,
                                 sizeof(struct rtnl_link_stats64), IFLA_PAD);
        if (!attr)
                return -EMSGSIZE;

        sp = nla_data(attr);
        dev_get_stats(dev, sp);

        attr = nla_reserve(skb, IFLA_STATS,
                           sizeof(struct rtnl_link_stats));
        if (!attr)
                return -EMSGSIZE;

        copy_rtnl_link_stats(nla_data(attr), sp);

        return 0;
}

static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
                                               struct net_device *dev,
                                               int vfs_num,
                                               struct nlattr *vfinfo)
{
        struct ifla_vf_rss_query_en vf_rss_query_en;
        struct nlattr *vf, *vfstats, *vfvlanlist;
        struct ifla_vf_link_state vf_linkstate;
        struct ifla_vf_vlan_info vf_vlan_info;
        struct ifla_vf_spoofchk vf_spoofchk;
        struct ifla_vf_tx_rate vf_tx_rate;
        struct ifla_vf_stats vf_stats;
        struct ifla_vf_trust vf_trust;
        struct ifla_vf_vlan vf_vlan;
        struct ifla_vf_rate vf_rate;
        struct ifla_vf_mac vf_mac;
        struct ifla_vf_broadcast vf_broadcast;
        struct ifla_vf_info ivi;

        memset(&ivi, 0, sizeof(ivi));

        /* Not all SR-IOV capable drivers support the
         * spoofcheck and "RSS query enable" query.  Preset to
         * -1 so the user space tool can detect that the driver
         * didn't report anything.
         */
        ivi.spoofchk = -1;
        ivi.rss_query_en = -1;
        ivi.trusted = -1;
        /* The default value for VF link state is "auto"
         * IFLA_VF_LINK_STATE_AUTO which equals zero
         */
        ivi.linkstate = 0;
        /* VLAN Protocol by default is 802.1Q */
        ivi.vlan_proto = htons(ETH_P_8021Q);
        if (dev->netdev_ops->ndo_get_vf_config(dev, vfs_num, &ivi))
                return 0;

        memset(&vf_vlan_info, 0, sizeof(vf_vlan_info));

        vf_mac.vf =
                vf_vlan.vf =
                vf_vlan_info.vf =
                vf_rate.vf =
                vf_tx_rate.vf =
                vf_spoofchk.vf =
                vf_linkstate.vf =
                vf_rss_query_en.vf =
                vf_trust.vf = ivi.vf;

        memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
        memcpy(vf_broadcast.broadcast, dev->broadcast, dev->addr_len);
        vf_vlan.vlan = ivi.vlan;
        vf_vlan.qos = ivi.qos;
        vf_vlan_info.vlan = ivi.vlan;
        vf_vlan_info.qos = ivi.qos;
        vf_vlan_info.vlan_proto = ivi.vlan_proto;
        vf_tx_rate.rate = ivi.max_tx_rate;
        vf_rate.min_tx_rate = ivi.min_tx_rate;
        vf_rate.max_tx_rate = ivi.max_tx_rate;
        vf_spoofchk.setting = ivi.spoofchk;
        vf_linkstate.link_state = ivi.linkstate;
        vf_rss_query_en.setting = ivi.rss_query_en;
        vf_trust.setting = ivi.trusted;
        vf = nla_nest_start_noflag(skb, IFLA_VF_INFO);
        if (!vf)
                goto nla_put_vfinfo_failure;
        if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) ||
            nla_put(skb, IFLA_VF_BROADCAST, sizeof(vf_broadcast), &vf_broadcast) ||
            nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) ||
            nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate),
                    &vf_rate) ||
            nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
                    &vf_tx_rate) ||
            nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
                    &vf_spoofchk) ||
            nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate),
                    &vf_linkstate) ||
            nla_put(skb, IFLA_VF_RSS_QUERY_EN,
                    sizeof(vf_rss_query_en),
                    &vf_rss_query_en) ||
            nla_put(skb, IFLA_VF_TRUST,
                    sizeof(vf_trust), &vf_trust))
                goto nla_put_vf_failure;
        vfvlanlist = nla_nest_start_noflag(skb, IFLA_VF_VLAN_LIST);
        if (!vfvlanlist)
                goto nla_put_vf_failure;
        if (nla_put(skb, IFLA_VF_VLAN_INFO, sizeof(vf_vlan_info),
                    &vf_vlan_info)) {
                nla_nest_cancel(skb, vfvlanlist);
                goto nla_put_vf_failure;
        }
        nla_nest_end(skb, vfvlanlist);
        memset(&vf_stats, 0, sizeof(vf_stats));
        if (dev->netdev_ops->ndo_get_vf_stats)
                dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num,
                                                &vf_stats);
        vfstats = nla_nest_start_noflag(skb, IFLA_VF_STATS);
        if (!vfstats)
                goto nla_put_vf_failure;
        if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS,
                              vf_stats.rx_packets, IFLA_VF_STATS_PAD) ||
            nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS,
                              vf_stats.tx_packets, IFLA_VF_STATS_PAD) ||
            nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_BYTES,
                              vf_stats.rx_bytes, IFLA_VF_STATS_PAD) ||
            nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_BYTES,
                              vf_stats.tx_bytes, IFLA_VF_STATS_PAD) ||
            nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST,
                              vf_stats.broadcast, IFLA_VF_STATS_PAD) ||
            nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST,
                              vf_stats.multicast, IFLA_VF_STATS_PAD) ||
            nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_DROPPED,
                              vf_stats.rx_dropped, IFLA_VF_STATS_PAD) ||
            nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_DROPPED,
                              vf_stats.tx_dropped, IFLA_VF_STATS_PAD)) {
                nla_nest_cancel(skb, vfstats);
                goto nla_put_vf_failure;
        }
        nla_nest_end(skb, vfstats);
        nla_nest_end(skb, vf);
        return 0;

nla_put_vf_failure:
        nla_nest_cancel(skb, vf);
nla_put_vfinfo_failure:
        nla_nest_cancel(skb, vfinfo);
        return -EMSGSIZE;
}

static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb,
                                           struct net_device *dev,
                                           u32 ext_filter_mask)
{
        struct nlattr *vfinfo;
        int i, num_vfs;

        if (!dev->dev.parent || ((ext_filter_mask & RTEXT_FILTER_VF) == 0))
                return 0;

        num_vfs = dev_num_vf(dev->dev.parent);
        if (nla_put_u32(skb, IFLA_NUM_VF, num_vfs))
                return -EMSGSIZE;

        if (!dev->netdev_ops->ndo_get_vf_config)
                return 0;

        vfinfo = nla_nest_start_noflag(skb, IFLA_VFINFO_LIST);
        if (!vfinfo)
                return -EMSGSIZE;

        for (i = 0; i < num_vfs; i++) {
                if (rtnl_fill_vfinfo(skb, dev, i, vfinfo))
                        return -EMSGSIZE;
        }

        nla_nest_end(skb, vfinfo);
        return 0;
}

static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
{
        struct rtnl_link_ifmap map;

        memset(&map, 0, sizeof(map));
        map.mem_start   = dev->mem_start;
        map.mem_end     = dev->mem_end;
        map.base_addr   = dev->base_addr;
        map.irq         = dev->irq;
        map.dma         = dev->dma;
        map.port        = dev->if_port;

        if (nla_put_64bit(skb, IFLA_MAP, sizeof(map), &map, IFLA_PAD))
                return -EMSGSIZE;

        return 0;
}

static u32 rtnl_xdp_prog_skb(struct net_device *dev)
{
        const struct bpf_prog *generic_xdp_prog;

        ASSERT_RTNL();

        generic_xdp_prog = rtnl_dereference(dev->xdp_prog);
        if (!generic_xdp_prog)
                return 0;
        return generic_xdp_prog->aux->id;
}

static u32 rtnl_xdp_prog_drv(struct net_device *dev)
{
        return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf, XDP_QUERY_PROG);
}

static u32 rtnl_xdp_prog_hw(struct net_device *dev)
{
        return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf,
                               XDP_QUERY_PROG_HW);
}

static int rtnl_xdp_report_one(struct sk_buff *skb, struct net_device *dev,
                               u32 *prog_id, u8 *mode, u8 tgt_mode, u32 attr,
                               u32 (*get_prog_id)(struct net_device *dev))
{
        u32 curr_id;
        int err;

        curr_id = get_prog_id(dev);
        if (!curr_id)
                return 0;

        *prog_id = curr_id;
        err = nla_put_u32(skb, attr, curr_id);
        if (err)
                return err;

        if (*mode != XDP_ATTACHED_NONE)
                *mode = XDP_ATTACHED_MULTI;
        else
                *mode = tgt_mode;

        return 0;
}

static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
{
        struct nlattr *xdp;
        u32 prog_id;
        int err;
        u8 mode;

        xdp = nla_nest_start_noflag(skb, IFLA_XDP);
        if (!xdp)
                return -EMSGSIZE;

        prog_id = 0;
        mode = XDP_ATTACHED_NONE;
        err = rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_SKB,
                                  IFLA_XDP_SKB_PROG_ID, rtnl_xdp_prog_skb);
        if (err)
                goto err_cancel;
        err = rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_DRV,
                                  IFLA_XDP_DRV_PROG_ID, rtnl_xdp_prog_drv);
        if (err)
                goto err_cancel;
        err = rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_HW,
                                  IFLA_XDP_HW_PROG_ID, rtnl_xdp_prog_hw);
        if (err)
                goto err_cancel;

        err = nla_put_u8(skb, IFLA_XDP_ATTACHED, mode);
        if (err)
                goto err_cancel;

        if (prog_id && mode != XDP_ATTACHED_MULTI) {
                err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id);
                if (err)
                        goto err_cancel;
        }

        nla_nest_end(skb, xdp);
        return 0;

err_cancel:
        nla_nest_cancel(skb, xdp);
        return err;
}

static u32 rtnl_get_event(unsigned long event)
{
        u32 rtnl_event_type = IFLA_EVENT_NONE;

        switch (event) {
        case NETDEV_REBOOT:
                rtnl_event_type = IFLA_EVENT_REBOOT;
                break;
        case NETDEV_FEAT_CHANGE:
                rtnl_event_type = IFLA_EVENT_FEATURES;
                break;
        case NETDEV_BONDING_FAILOVER:
                rtnl_event_type = IFLA_EVENT_BONDING_FAILOVER;
                break;
        case NETDEV_NOTIFY_PEERS:
                rtnl_event_type = IFLA_EVENT_NOTIFY_PEERS;
                break;
        case NETDEV_RESEND_IGMP:
                rtnl_event_type = IFLA_EVENT_IGMP_RESEND;
                break;
        case NETDEV_CHANGEINFODATA:
                rtnl_event_type = IFLA_EVENT_BONDING_OPTIONS;
                break;
        default:
                break;
        }

        return rtnl_event_type;
}

static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev)
{
        const struct net_device *upper_dev;
        int ret = 0;

        rcu_read_lock();

        upper_dev = netdev_master_upper_dev_get_rcu(dev);
        if (upper_dev)
                ret = nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex);

        rcu_read_unlock();
        return ret;
}

static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev,
                          bool force)
{
        int ifindex = dev_get_iflink(dev);

        if (force || dev->ifindex != ifindex)
                return nla_put_u32(skb, IFLA_LINK, ifindex);

        return 0;
}

static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
                                              struct net_device *dev)
{
        char buf[IFALIASZ];
        int ret;

        ret = dev_get_alias(dev, buf, sizeof(buf));
        return ret > 0 ? nla_put_string(skb, IFLA_IFALIAS, buf) : 0;
}

static int rtnl_fill_link_netnsid(struct sk_buff *skb,
                                  const struct net_device *dev,
                                  struct net *src_net, gfp_t gfp)
{
        bool put_iflink = false;

        if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) {
                struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);

                if (!net_eq(dev_net(dev), link_net)) {
                        int id = peernet2id_alloc(src_net, link_net, gfp);

                        if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
                                return -EMSGSIZE;

                        put_iflink = true;
                }
        }

        return nla_put_iflink(skb, dev, put_iflink);
}

static int rtnl_fill_link_af(struct sk_buff *skb,
                             const struct net_device *dev,
                             u32 ext_filter_mask)
{
        const struct rtnl_af_ops *af_ops;
        struct nlattr *af_spec;

        af_spec = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
        if (!af_spec)
                return -EMSGSIZE;

        list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) {
                struct nlattr *af;
                int err;

                if (!af_ops->fill_link_af)
                        continue;

                af = nla_nest_start_noflag(skb, af_ops->family);
                if (!af)
                        return -EMSGSIZE;

                err = af_ops->fill_link_af(skb, dev, ext_filter_mask);
                /*
                 * Caller may return ENODATA to indicate that there
                 * was no data to be dumped. This is not an error, it
                 * means we should trim the attribute header and
                 * continue.
                 */
                if (err == -ENODATA)
                        nla_nest_cancel(skb, af);
                else if (err < 0)
                        return -EMSGSIZE;

                nla_nest_end(skb, af);
        }

        nla_nest_end(skb, af_spec);
        return 0;
}

static int rtnl_fill_ifinfo(struct sk_buff *skb,
                            struct net_device *dev, struct net *src_net,
                            int type, u32 pid, u32 seq, u32 change,
                            unsigned int flags, u32 ext_filter_mask,
                            u32 event, int *new_nsid, int new_ifindex,
                            int tgt_netnsid, gfp_t gfp)
{
        struct ifinfomsg *ifm;
        struct nlmsghdr *nlh;

        ASSERT_RTNL();
        nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
        if (nlh == NULL)
                return -EMSGSIZE;

        ifm = nlmsg_data(nlh);
        ifm->ifi_family = AF_UNSPEC;
        ifm->__ifi_pad = 0;
        ifm->ifi_type = dev->type;
        ifm->ifi_index = dev->ifindex;
        ifm->ifi_flags = dev_get_flags(dev);
        ifm->ifi_change = change;

        if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid))
                goto nla_put_failure;

        if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
            nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) ||
            nla_put_u8(skb, IFLA_OPERSTATE,
                       netif_running(dev) ? dev->operstate : IF_OPER_DOWN) ||
            nla_put_u8(skb, IFLA_LINKMODE, dev->link_mode) ||
            nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
            nla_put_u32(skb, IFLA_MIN_MTU, dev->min_mtu) ||
            nla_put_u32(skb, IFLA_MAX_MTU, dev->max_mtu) ||
            nla_put_u32(skb, IFLA_GROUP, dev->group) ||
            nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) ||
            nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) ||
            nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) ||
            nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) ||
#ifdef CONFIG_RPS
            nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
#endif
            put_master_ifindex(skb, dev) ||
            nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
            (dev->qdisc &&
             nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
            nla_put_ifalias(skb, dev) ||
            nla_put_u32(skb, IFLA_CARRIER_CHANGES,
                        atomic_read(&dev->carrier_up_count) +
                        atomic_read(&dev->carrier_down_count)) ||
            nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down) ||
            nla_put_u32(skb, IFLA_CARRIER_UP_COUNT,
                        atomic_read(&dev->carrier_up_count)) ||
            nla_put_u32(skb, IFLA_CARRIER_DOWN_COUNT,
                        atomic_read(&dev->carrier_down_count)))
                goto nla_put_failure;

        if (event != IFLA_EVENT_NONE) {
                if (nla_put_u32(skb, IFLA_EVENT, event))
                        goto nla_put_failure;
        }

        if (rtnl_fill_link_ifmap(skb, dev))
                goto nla_put_failure;

        if (dev->addr_len) {
                if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) ||
                    nla_put(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast))
                        goto nla_put_failure;
        }

        if (rtnl_phys_port_id_fill(skb, dev))
                goto nla_put_failure;

        if (rtnl_phys_port_name_fill(skb, dev))
                goto nla_put_failure;

        if (rtnl_phys_switch_id_fill(skb, dev))
                goto nla_put_failure;

        if (rtnl_fill_stats(skb, dev))
                goto nla_put_failure;

        if (rtnl_fill_vf(skb, dev, ext_filter_mask))
                goto nla_put_failure;

        if (rtnl_port_fill(skb, dev, ext_filter_mask))
                goto nla_put_failure;

        if (rtnl_xdp_fill(skb, dev))
                goto nla_put_failure;

        if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) {
                if (rtnl_link_fill(skb, dev) < 0)
                        goto nla_put_failure;
        }

        if (rtnl_fill_link_netnsid(skb, dev, src_net, gfp))
                goto nla_put_failure;

        if (new_nsid &&
            nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0)
                goto nla_put_failure;
        if (new_ifindex &&
            nla_put_s32(skb, IFLA_NEW_IFINDEX, new_ifindex) < 0)
                goto nla_put_failure;


        rcu_read_lock();
        if (rtnl_fill_link_af(skb, dev, ext_filter_mask))
                goto nla_put_failure_rcu;
        rcu_read_unlock();

        nlmsg_end(skb, nlh);
        return 0;

nla_put_failure_rcu:
        rcu_read_unlock();
nla_put_failure:
        nlmsg_cancel(skb, nlh);
        return -EMSGSIZE;
}

static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
        [IFLA_IFNAME]           = { .type = NLA_STRING, .len = IFNAMSIZ-1 },
        [IFLA_ADDRESS]          = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
        [IFLA_BROADCAST]        = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
        [IFLA_MAP]              = { .len = sizeof(struct rtnl_link_ifmap) },
        [IFLA_MTU]              = { .type = NLA_U32 },
        [IFLA_LINK]             = { .type = NLA_U32 },
        [IFLA_MASTER]           = { .type = NLA_U32 },
        [IFLA_CARRIER]          = { .type = NLA_U8 },
        [IFLA_TXQLEN]           = { .type = NLA_U32 },
        [IFLA_WEIGHT]           = { .type = NLA_U32 },
        [IFLA_OPERSTATE]        = { .type = NLA_U8 },
        [IFLA_LINKMODE]         = { .type = NLA_U8 },
        [IFLA_LINKINFO]         = { .type = NLA_NESTED },
        [IFLA_NET_NS_PID]       = { .type = NLA_U32 },
        [IFLA_NET_NS_FD]        = { .type = NLA_U32 },
        /* IFLA_IFALIAS is a string, but policy is set to NLA_BINARY to
         * allow 0-length string (needed to remove an alias).
         */
        [IFLA_IFALIAS]          = { .type = NLA_BINARY, .len = IFALIASZ - 1 },
        [IFLA_VFINFO_LIST]      = {. type = NLA_NESTED },
        [IFLA_VF_PORTS]         = { .type = NLA_NESTED },
        [IFLA_PORT_SELF]        = { .type = NLA_NESTED },
        [IFLA_AF_SPEC]          = { .type = NLA_NESTED },
        [IFLA_EXT_MASK]         = { .type = NLA_U32 },
        [IFLA_PROMISCUITY]      = { .type = NLA_U32 },
        [IFLA_NUM_TX_QUEUES]    = { .type = NLA_U32 },
        [IFLA_NUM_RX_QUEUES]    = { .type = NLA_U32 },
        [IFLA_GSO_MAX_SEGS]     = { .type = NLA_U32 },
        [IFLA_GSO_MAX_SIZE]     = { .type = NLA_U32 },
        [IFLA_PHYS_PORT_ID]     = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
        [IFLA_CARRIER_CHANGES]  = { .type = NLA_U32 },  /* ignored */
        [IFLA_PHYS_SWITCH_ID]   = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
        [IFLA_LINK_NETNSID]     = { .type = NLA_S32 },
        [IFLA_PROTO_DOWN]       = { .type = NLA_U8 },
        [IFLA_XDP]              = { .type = NLA_NESTED },
        [IFLA_EVENT]            = { .type = NLA_U32 },
        [IFLA_GROUP]            = { .type = NLA_U32 },
        [IFLA_TARGET_NETNSID]   = { .type = NLA_S32 },
        [IFLA_CARRIER_UP_COUNT] = { .type = NLA_U32 },
        [IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 },
        [IFLA_MIN_MTU]          = { .type = NLA_U32 },
        [IFLA_MAX_MTU]          = { .type = NLA_U32 },
};

static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
        [IFLA_INFO_KIND]        = { .type = NLA_STRING },
        [IFLA_INFO_DATA]        = { .type = NLA_NESTED },
        [IFLA_INFO_SLAVE_KIND]  = { .type = NLA_STRING },
        [IFLA_INFO_SLAVE_DATA]  = { .type = NLA_NESTED },
};

static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
        [IFLA_VF_MAC]           = { .len = sizeof(struct ifla_vf_mac) },
        [IFLA_VF_BROADCAST]     = { .type = NLA_REJECT },
        [IFLA_VF_VLAN]          = { .len = sizeof(struct ifla_vf_vlan) },
        [IFLA_VF_VLAN_LIST]     = { .type = NLA_NESTED },
        [IFLA_VF_TX_RATE]       = { .len = sizeof(struct ifla_vf_tx_rate) },
        [IFLA_VF_SPOOFCHK]      = { .len = sizeof(struct ifla_vf_spoofchk) },
        [IFLA_VF_RATE]          = { .len = sizeof(struct ifla_vf_rate) },
        [IFLA_VF_LINK_STATE]    = { .len = sizeof(struct ifla_vf_link_state) },
        [IFLA_VF_RSS_QUERY_EN]  = { .len = sizeof(struct ifla_vf_rss_query_en) },
        [IFLA_VF_STATS]         = { .type = NLA_NESTED },
        [IFLA_VF_TRUST]         = { .len = sizeof(struct ifla_vf_trust) },
        [IFLA_VF_IB_NODE_GUID]  = { .len = sizeof(struct ifla_vf_guid) },
        [IFLA_VF_IB_PORT_GUID]  = { .len = sizeof(struct ifla_vf_guid) },
};

static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
        [IFLA_PORT_VF]          = { .type = NLA_U32 },
        [IFLA_PORT_PROFILE]     = { .type = NLA_STRING,
                                    .len = PORT_PROFILE_MAX },
        [IFLA_PORT_INSTANCE_UUID] = { .type = NLA_BINARY,
                                      .len = PORT_UUID_MAX },
        [IFLA_PORT_HOST_UUID]   = { .type = NLA_STRING,
                                    .len = PORT_UUID_MAX },
        [IFLA_PORT_REQUEST]     = { .type = NLA_U8, },
        [IFLA_PORT_RESPONSE]    = { .type = NLA_U16, },

        /* Unused, but we need to keep it here since user space could
         * fill it. It's also broken with regard to NLA_BINARY use in
         * combination with structs.
         */
        [IFLA_PORT_VSI_TYPE]    = { .type = NLA_BINARY,
                                    .len = sizeof(struct ifla_port_vsi) },
};

static const struct nla_policy ifla_xdp_policy[IFLA_XDP_MAX + 1] = {
        [IFLA_XDP_FD]           = { .type = NLA_S32 },
        [IFLA_XDP_ATTACHED]     = { .type = NLA_U8 },
        [IFLA_XDP_FLAGS]        = { .type = NLA_U32 },
        [IFLA_XDP_PROG_ID]      = { .type = NLA_U32 },
};

static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla)
{
        const struct rtnl_link_ops *ops = NULL;
        struct nlattr *linfo[IFLA_INFO_MAX + 1];

        if (nla_parse_nested_deprecated(linfo, IFLA_INFO_MAX, nla, ifla_info_policy, NULL) < 0)
                return NULL;

        if (linfo[IFLA_INFO_KIND]) {
                char kind[MODULE_NAME_LEN];

                nla_strlcpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
                ops = rtnl_link_ops_get(kind);
        }

        return ops;
}

static bool link_master_filtered(struct net_device *dev, int master_idx)
{
        struct net_device *master;

        if (!master_idx)
                return false;

        master = netdev_master_upper_dev_get(dev);
        if (!master || master->ifindex != master_idx)
                return true;

        return false;
}

static bool link_kind_filtered(const struct net_device *dev,
                               const struct rtnl_link_ops *kind_ops)
{
        if (kind_ops && dev->rtnl_link_ops != kind_ops)
                return true;

        return false;
}

static bool link_dump_filtered(struct net_device *dev,
                               int master_idx,
                               const struct rtnl_link_ops *kind_ops)
{
        if (link_master_filtered(dev, master_idx) ||
            link_kind_filtered(dev, kind_ops))
                return true;

        return false;
}

/**
 * rtnl_get_net_ns_capable - Get netns if sufficiently privileged.
 * @sk: netlink socket
 * @netnsid: network namespace identifier
 *
 * Returns the network namespace identified by netnsid on success or an error
 * pointer on failure.
 */
struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid)
{
        struct net *net;

        net = get_net_ns_by_id(sock_net(sk), netnsid);
        if (!net)
                return ERR_PTR(-EINVAL);

        /* For now, the caller is required to have CAP_NET_ADMIN in
         * the user namespace owning the target net ns.
         */
        if (!sk_ns_capable(sk, net->user_ns, CAP_NET_ADMIN)) {
                put_net(net);
                return ERR_PTR(-EACCES);
        }
        return net;
}
EXPORT_SYMBOL_GPL(rtnl_get_net_ns_capable);

static int rtnl_valid_dump_ifinfo_req(const struct nlmsghdr *nlh,
                                      bool strict_check, struct nlattr **tb,
                                      struct netlink_ext_ack *extack)
{
        int hdrlen;

        if (strict_check) {
                struct ifinfomsg *ifm;

                if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
                        NL_SET_ERR_MSG(extack, "Invalid header for link dump");
                        return -EINVAL;
                }

                ifm = nlmsg_data(nlh);
                if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
                    ifm->ifi_change) {
                        NL_SET_ERR_MSG(extack, "Invalid values in header for link dump request");
                        return -EINVAL;
                }
                if (ifm->ifi_index) {
                        NL_SET_ERR_MSG(extack, "Filter by device index not supported for link dumps");
                        return -EINVAL;
                }

                return nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb,
                                                     IFLA_MAX, ifla_policy,
                                                     extack);
        }

        /* A hack to preserve kernel<->userspace interface.
         * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
         * However, before Linux v3.9 the code here assumed rtgenmsg and that's
         * what iproute2 < v3.9.0 used.
         * We can detect the old iproute2. Even including the IFLA_EXT_MASK
         * attribute, its netlink message is shorter than struct ifinfomsg.
         */
        hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
                 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);

        return nlmsg_parse_deprecated(nlh, hdrlen, tb, IFLA_MAX, ifla_policy,
                                      extack);
}

static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
        struct netlink_ext_ack *extack = cb->extack;
        const struct nlmsghdr *nlh = cb->nlh;
        struct net *net = sock_net(skb->sk);
        struct net *tgt_net = net;
        int h, s_h;
        int idx = 0, s_idx;
        struct net_device *dev;
        struct hlist_head *head;
        struct nlattr *tb[IFLA_MAX+1];
        u32 ext_filter_mask = 0;
        const struct rtnl_link_ops *kind_ops = NULL;
        unsigned int flags = NLM_F_MULTI;
        int master_idx = 0;
        int netnsid = -1;
        int err, i;

        s_h = cb->args[0];
        s_idx = cb->args[1];

        err = rtnl_valid_dump_ifinfo_req(nlh, cb->strict_check, tb, extack);
        if (err < 0) {
                if (cb->strict_check)
                        return err;

                goto walk_entries;
        }

        for (i = 0; i <= IFLA_MAX; ++i) {
                if (!tb[i])
                        continue;

                /* new attributes should only be added with strict checking */
                switch (i) {
                case IFLA_TARGET_NETNSID:
                        netnsid = nla_get_s32(tb[i]);
                        tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid);
                        if (IS_ERR(tgt_net)) {
                                NL_SET_ERR_MSG(extack, "Invalid target network namespace id");
                                return PTR_ERR(tgt_net);
                        }
                        break;
                case IFLA_EXT_MASK:
                        ext_filter_mask = nla_get_u32(tb[i]);
                        break;
                case IFLA_MASTER:
                        master_idx = nla_get_u32(tb[i]);
                        break;
                case IFLA_LINKINFO:
                        kind_ops = linkinfo_to_kind_ops(tb[i]);
                        break;
                default:
                        if (cb->strict_check) {
                                NL_SET_ERR_MSG(extack, "Unsupported attribute in link dump request");
                                return -EINVAL;
                        }
                }
        }

        if (master_idx || kind_ops)
                flags |= NLM_F_DUMP_FILTERED;

walk_entries:
        for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
                idx = 0;
                head = &tgt_net->dev_index_head[h];
                hlist_for_each_entry(dev, head, index_hlist) {
                        if (link_dump_filtered(dev, master_idx, kind_ops))
                                goto cont;
                        if (idx < s_idx)
                                goto cont;
                        err = rtnl_fill_ifinfo(skb, dev, net,
                                               RTM_NEWLINK,

                                               NETLINK_CB(cb->skb).portid,
                                               nlh->nlmsg_seq, 0, flags,
                                               ext_filter_mask, 0, NULL, 0,
                                               netnsid, GFP_KERNEL);

                        if (err < 0) {
                                if (likely(skb->len))
                                        goto out;

                                goto out_err;
                        }
cont:
                        idx++;
                }
        }
out:
        err = skb->len;
out_err:
        cb->args[1] = idx;
        cb->args[0] = h;
        cb->seq = net->dev_base_seq;
        nl_dump_check_consistent(cb, nlmsg_hdr(skb));
        if (netnsid >= 0)
                put_net(tgt_net);

        return err;
}

int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len,
                        struct netlink_ext_ack *exterr)
{
        return nla_parse_deprecated(tb, IFLA_MAX, head, len, ifla_policy,
                                    exterr);
}
EXPORT_SYMBOL(rtnl_nla_parse_ifla);

struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[])
{
        struct net *net;
        /* Examine the link attributes and figure out which
         * network namespace we are talking about.
         */
        if (tb[IFLA_NET_NS_PID])
                net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID]));
        else if (tb[IFLA_NET_NS_FD])
                net = get_net_ns_by_fd(nla_get_u32(tb[IFLA_NET_NS_FD]));
        else
                net = get_net(src_net);
        return net;
}
EXPORT_SYMBOL(rtnl_link_get_net);

/* Figure out which network namespace we are talking about by
 * examining the link attributes in the following order:
 *
 * 1. IFLA_NET_NS_PID
 * 2. IFLA_NET_NS_FD
 * 3. IFLA_TARGET_NETNSID
 */
static struct net *rtnl_link_get_net_by_nlattr(struct net *src_net,
                                               struct nlattr *tb[])
{
        struct net *net;

        if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD])
                return rtnl_link_get_net(src_net, tb);

        if (!tb[IFLA_TARGET_NETNSID])
                return get_net(src_net);

        net = get_net_ns_by_id(src_net, nla_get_u32(tb[IFLA_TARGET_NETNSID]));
        if (!net)
                return ERR_PTR(-EINVAL);

        return net;
}

static struct net *rtnl_link_get_net_capable(const struct sk_buff *skb,
                                             struct net *src_net,
                                             struct nlattr *tb[], int cap)
{
        struct net *net;

        net = rtnl_link_get_net_by_nlattr(src_net, tb);
        if (IS_ERR(net))
                return net;

        if (!netlink_ns_capable(skb, net->user_ns, cap)) {
                put_net(net);
                return ERR_PTR(-EPERM);
        }

        return net;
}

/* Verify that rtnetlink requests do not pass additional properties
 * potentially referring to different network namespaces.
 */
static int rtnl_ensure_unique_netns(struct nlattr *tb[],
                                    struct netlink_ext_ack *extack,
                                    bool netns_id_only)
{

        if (netns_id_only) {
                if (!tb[IFLA_NET_NS_PID] && !tb[IFLA_NET_NS_FD])
                        return 0;

                NL_SET_ERR_MSG(extack, "specified netns attribute not supported");
                return -EOPNOTSUPP;
        }

        if (tb[IFLA_TARGET_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]))
                goto invalid_attr;

        if (tb[IFLA_NET_NS_PID] && (tb[IFLA_TARGET_NETNSID] || tb[IFLA_NET_NS_FD]))
                goto invalid_attr;

        if (tb[IFLA_NET_NS_FD] && (tb[IFLA_TARGET_NETNSID] || tb[IFLA_NET_NS_PID]))
                goto invalid_attr;

        return 0;

invalid_attr:
        NL_SET_ERR_MSG(extack, "multiple netns identifying attributes specified");
        return -EINVAL;
}

static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
{
        if (dev) {
                if (tb[IFLA_ADDRESS] &&
                    nla_len(tb[IFLA_ADDRESS]) < dev->addr_len)
                        return -EINVAL;

                if (tb[IFLA_BROADCAST] &&
                    nla_len(tb[IFLA_BROADCAST]) < dev->addr_len)
                        return -EINVAL;
        }

        if (tb[IFLA_AF_SPEC]) {
                struct nlattr *af;
                int rem, err;

                nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
                        const struct rtnl_af_ops *af_ops;

                        rcu_read_lock();
                        af_ops = rtnl_af_lookup(nla_type(af));
                        if (!af_ops) {
                                rcu_read_unlock();
                                return -EAFNOSUPPORT;
                        }

                        if (!af_ops->set_link_af) {
                                rcu_read_unlock();
                                return -EOPNOTSUPP;
                        }

                        if (af_ops->validate_link_af) {
                                err = af_ops->validate_link_af(dev, af);
                                if (err < 0) {
                                        rcu_read_unlock();
                                        return err;
                                }
                        }

                        rcu_read_unlock();
                }
        }

        return 0;
}

static int handle_infiniband_guid(struct net_device *dev, struct ifla_vf_guid *ivt,
                                  int guid_type)
{
        const struct net_device_ops *ops = dev->netdev_ops;

        return ops->ndo_set_vf_guid(dev, ivt->vf, ivt->guid, guid_type);
}

static int handle_vf_guid(struct net_device *dev, struct ifla_vf_guid *ivt, int guid_type)
{
        if (dev->type != ARPHRD_INFINIBAND)
                return -EOPNOTSUPP;

        return handle_infiniband_guid(dev, ivt, guid_type);
}

static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
{
        const struct net_device_ops *ops = dev->netdev_ops;
        int err = -EINVAL;

        if (tb[IFLA_VF_MAC]) {
                struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);

                if (ivm->vf >= INT_MAX)
                        return -EINVAL;
                err = -EOPNOTSUPP;
                if (ops->ndo_set_vf_mac)
                        err = ops->ndo_set_vf_mac(dev, ivm->vf,
                                                  ivm->mac);
                if (err < 0)
                        return err;
        }

        if (tb[IFLA_VF_VLAN]) {
                struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);

                if (ivv->vf >= INT_MAX)
                        return -EINVAL;
                err = -EOPNOTSUPP;
                if (ops->ndo_set_vf_vlan)
                        err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
                                                   ivv->qos,
                                                   htons(ETH_P_8021Q));
                if (err < 0)
                        return err;
        }

        if (tb[IFLA_VF_VLAN_LIST]) {
                struct ifla_vf_vlan_info *ivvl[MAX_VLAN_LIST_LEN];
                struct nlattr *attr;
                int rem, len = 0;

                err = -EOPNOTSUPP;
                if (!ops->ndo_set_vf_vlan)
                        return err;

                nla_for_each_nested(attr, tb[IFLA_VF_VLAN_LIST], rem) {
                        if (nla_type(attr) != IFLA_VF_VLAN_INFO ||
                            nla_len(attr) < NLA_HDRLEN) {
                                return -EINVAL;
                        }
                        if (len >= MAX_VLAN_LIST_LEN)
                                return -EOPNOTSUPP;
                        ivvl[len] = nla_data(attr);

                        len++;
                }
                if (len == 0)
                        return -EINVAL;

                if (ivvl[0]->vf >= INT_MAX)
                        return -EINVAL;
                err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan,
                                           ivvl[0]->qos, ivvl[0]->vlan_proto);
                if (err < 0)
                        return err;
        }

        if (tb[IFLA_VF_TX_RATE]) {
                struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
                struct ifla_vf_info ivf;

                if (ivt->vf >= INT_MAX)
                        return -EINVAL;
                err = -EOPNOTSUPP;
                if (ops->ndo_get_vf_config)
                        err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
                if (err < 0)
                        return err;

                err = -EOPNOTSUPP;
                if (ops->ndo_set_vf_rate)
                        err = ops->ndo_set_vf_rate(dev, ivt->vf,
                                                   ivf.min_tx_rate,
                                                   ivt->rate);
                if (err < 0)
                        return err;
        }

        if (tb[IFLA_VF_RATE]) {
                struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);

                if (ivt->vf >= INT_MAX)
                        return -EINVAL;
                err = -EOPNOTSUPP;
                if (ops->ndo_set_vf_rate)
                        err = ops->ndo_set_vf_rate(dev, ivt->vf,
                                                   ivt->min_tx_rate,
                                                   ivt->max_tx_rate);
                if (err < 0)
                        return err;
        }

        if (tb[IFLA_VF_SPOOFCHK]) {
                struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);

                if (ivs->vf >= INT_MAX)
                        return -EINVAL;
                err = -EOPNOTSUPP;
                if (ops->ndo_set_vf_spoofchk)
                        err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
                                                       ivs->setting);
                if (err < 0)
                        return err;
        }

        if (tb[IFLA_VF_LINK_STATE]) {
                struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);

                if (ivl->vf >= INT_MAX)
                        return -EINVAL;
                err = -EOPNOTSUPP;
                if (ops->ndo_set_vf_link_state)
                        err = ops->ndo_set_vf_link_state(dev, ivl->vf,
                                                         ivl->link_state);
                if (err < 0)
                        return err;
        }

        if (tb[IFLA_VF_RSS_QUERY_EN]) {
                struct ifla_vf_rss_query_en *ivrssq_en;

                err = -EOPNOTSUPP;
                ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]);
                if (ivrssq_en->vf >= INT_MAX)
                        return -EINVAL;
                if (ops->ndo_set_vf_rss_query_en)
                        err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf,
                                                           ivrssq_en->setting);
                if (err < 0)
                        return err;
        }

        if (tb[IFLA_VF_TRUST]) {
                struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]);

                if (ivt->vf >= INT_MAX)
                        return -EINVAL;
                err = -EOPNOTSUPP;
                if (ops->ndo_set_vf_trust)
                        err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting);
                if (err < 0)
                        return err;
        }

        if (tb[IFLA_VF_IB_NODE_GUID]) {
                struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]);

                if (ivt->vf >= INT_MAX)
                        return -EINVAL;
                if (!ops->ndo_set_vf_guid)
                        return -EOPNOTSUPP;
                return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID);
        }

        if (tb[IFLA_VF_IB_PORT_GUID]) {
                struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]);

                if (ivt->vf >= INT_MAX)
                        return -EINVAL;
                if (!ops->ndo_set_vf_guid)
                        return -EOPNOTSUPP;

                return handle_vf_guid(dev, ivt, IFLA_VF_IB_PORT_GUID);
        }

        return err;
}

static int do_set_master(struct net_device *dev, int ifindex,
                         struct netlink_ext_ack *extack)
{
        struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
        const struct net_device_ops *ops;
        int err;

        if (upper_dev) {
                if (upper_dev->ifindex == ifindex)
                        return 0;
                ops = upper_dev->netdev_ops;
                if (ops->ndo_del_slave) {
                        err = ops->ndo_del_slave(upper_dev, dev);
                        if (err)
                                return err;
                        netdev_update_lockdep_key(dev);
                } else {
                        return -EOPNOTSUPP;
                }
        }

        if (ifindex) {
                upper_dev = __dev_get_by_index(dev_net(dev), ifindex);
                if (!upper_dev)
                        return -EINVAL;
                ops = upper_dev->netdev_ops;
                if (ops->ndo_add_slave) {
                        err = ops->ndo_add_slave(upper_dev, dev, extack);
                        if (err)
                                return err;
                } else {
                        return -EOPNOTSUPP;
                }
        }
        return 0;
}

#define DO_SETLINK_MODIFIED     0x01
/* notify flag means notify + modified. */
#define DO_SETLINK_NOTIFY       0x03
static int do_setlink(const struct sk_buff *skb,
                      struct net_device *dev, struct ifinfomsg *ifm,
                      struct netlink_ext_ack *extack,
                      struct nlattr **tb, char *ifname, int status)
{
        const struct net_device_ops *ops = dev->netdev_ops;
        int err;

        err = validate_linkmsg(dev, tb);
        if (err < 0)
                return err;

        if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_TARGET_NETNSID]) {
                struct net *net = rtnl_link_get_net_capable(skb, dev_net(dev),
                                                            tb, CAP_NET_ADMIN);
                if (IS_ERR(net)) {
                        err = PTR_ERR(net);
                        goto errout;
                }

                err = dev_change_net_namespace(dev, net, ifname);
                put_net(net);
                if (err)
                        goto errout;
                status |= DO_SETLINK_MODIFIED;
        }

        if (tb[IFLA_MAP]) {
                struct rtnl_link_ifmap *u_map;
                struct ifmap k_map;

                if (!ops->ndo_set_config) {
                        err = -EOPNOTSUPP;
                        goto errout;
                }

                if (!netif_device_present(dev)) {
                        err = -ENODEV;
                        goto errout;
                }

                u_map = nla_data(tb[IFLA_MAP]);
                k_map.mem_start = (unsigned long) u_map->mem_start;
                k_map.mem_end = (unsigned long) u_map->mem_end;
                k_map.base_addr = (unsigned short) u_map->base_addr;
                k_map.irq = (unsigned char) u_map->irq;
                k_map.dma = (unsigned char) u_map->dma;
                k_map.port = (unsigned char) u_map->port;

                err = ops->ndo_set_config(dev, &k_map);
                if (err < 0)
                        goto errout;

                status |= DO_SETLINK_NOTIFY;
        }

        if (tb[IFLA_ADDRESS]) {
                struct sockaddr *sa;
                int len;

                len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len,
                                                  sizeof(*sa));
                sa = kmalloc(len, GFP_KERNEL);
                if (!sa) {
                        err = -ENOMEM;
                        goto errout;
                }
                sa->sa_family = dev->type;
                memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
                       dev->addr_len);
                err = dev_set_mac_address(dev, sa, extack);
                kfree(sa);
                if (err)
                        goto errout;
                status |= DO_SETLINK_MODIFIED;
        }

        if (tb[IFLA_MTU]) {
                err = dev_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack);
                if (err < 0)
                        goto errout;
                status |= DO_SETLINK_MODIFIED;
        }

        if (tb[IFLA_GROUP]) {
                dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
                status |= DO_SETLINK_NOTIFY;
        }

        /*
         * Interface selected by interface index but interface
         * name provided implies that a name change has been
         * requested.
         */
        if (ifm->ifi_index > 0 && ifname[0]) {
                err = dev_change_name(dev, ifname);
                if (err < 0)
                        goto errout;
                status |= DO_SETLINK_MODIFIED;
        }

        if (tb[IFLA_IFALIAS]) {
                err = dev_set_alias(dev, nla_data(tb[IFLA_IFALIAS]),
                                    nla_len(tb[IFLA_IFALIAS]));
                if (err < 0)
                        goto errout;
                status |= DO_SETLINK_NOTIFY;
        }

        if (tb[IFLA_BROADCAST]) {
                nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len);
                call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
        }

        if (ifm->ifi_flags || ifm->ifi_change) {
                err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
                                       extack);
                if (err < 0)
                        goto errout;
        }

        if (tb[IFLA_MASTER]) {
                err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
                if (err)
                        goto errout;
                status |= DO_SETLINK_MODIFIED;
        }

        if (tb[IFLA_CARRIER]) {
                err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
                if (err)
                        goto errout;
                status |= DO_SETLINK_MODIFIED;
        }

        if (tb[IFLA_TXQLEN]) {
                unsigned int value = nla_get_u32(tb[IFLA_TXQLEN]);

                err = dev_change_tx_queue_len(dev, value);
                if (err)
                        goto errout;
                status |= DO_SETLINK_MODIFIED;
        }

        if (tb[IFLA_GSO_MAX_SIZE]) {
                u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]);

                if (max_size > GSO_MAX_SIZE) {
                        err = -EINVAL;
                        goto errout;
                }

                if (dev->gso_max_size ^ max_size) {
                        netif_set_gso_max_size(dev, max_size);
                        status |= DO_SETLINK_MODIFIED;
                }
        }

        if (tb[IFLA_GSO_MAX_SEGS]) {
                u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]);

                if (max_segs > GSO_MAX_SEGS) {
                        err = -EINVAL;
                        goto errout;
                }

                if (dev->gso_max_segs ^ max_segs) {
                        dev->gso_max_segs = max_segs;
                        status |= DO_SETLINK_MODIFIED;
                }
        }

        if (tb[IFLA_OPERSTATE])
                set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));

        if (tb[IFLA_LINKMODE]) {
                unsigned char value = nla_get_u8(tb[IFLA_LINKMODE]);

                write_lock_bh(&dev_base_lock);
                if (dev->link_mode ^ value)
                        status |= DO_SETLINK_NOTIFY;
                dev->link_mode = value;
                write_unlock_bh(&dev_base_lock);
        }

        if (tb[IFLA_VFINFO_LIST]) {
                struct nlattr *vfinfo[IFLA_VF_MAX + 1];
                struct nlattr *attr;
                int rem;

                nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
                        if (nla_type(attr) != IFLA_VF_INFO ||
                            nla_len(attr) < NLA_HDRLEN) {
                                err = -EINVAL;
                                goto errout;
                        }
                        err = nla_parse_nested_deprecated(vfinfo, IFLA_VF_MAX,
                                                          attr,
                                                          ifla_vf_policy,
                                                          NULL);
                        if (err < 0)
                                goto errout;
                        err = do_setvfinfo(dev, vfinfo);
                        if (err < 0)
                                goto errout;
                        status |= DO_SETLINK_NOTIFY;
                }
        }
        err = 0;

        if (tb[IFLA_VF_PORTS]) {
                struct nlattr *port[IFLA_PORT_MAX+1];
                struct nlattr *attr;
                int vf;
                int rem;

                err = -EOPNOTSUPP;
                if (!ops->ndo_set_vf_port)
                        goto errout;

                nla_for_each_nested(attr, tb[IFLA_VF_PORTS], rem) {
                        if (nla_type(attr) != IFLA_VF_PORT ||
                            nla_len(attr) < NLA_HDRLEN) {
                                err = -EINVAL;
                                goto errout;
                        }
                        err = nla_parse_nested_deprecated(port, IFLA_PORT_MAX,
                                                          attr,
                                                          ifla_port_policy,
                                                          NULL);
                        if (err < 0)
                                goto errout;
                        if (!port[IFLA_PORT_VF]) {
                                err = -EOPNOTSUPP;
                                goto errout;
                        }
                        vf = nla_get_u32(port[IFLA_PORT_VF]);
                        err = ops->ndo_set_vf_port(dev, vf, port);
                        if (err < 0)
                                goto errout;
                        status |= DO_SETLINK_NOTIFY;
                }
        }
        err = 0;

        if (tb[IFLA_PORT_SELF]) {
                struct nlattr *port[IFLA_PORT_MAX+1];

                err = nla_parse_nested_deprecated(port, IFLA_PORT_MAX,
                                                  tb[IFLA_PORT_SELF],
                                                  ifla_port_policy, NULL);
                if (err < 0)
                        goto errout;

                err = -EOPNOTSUPP;
                if (ops->ndo_set_vf_port)
                        err = ops->ndo_set_vf_port(dev, PORT_SELF_VF, port);
                if (err < 0)
                        goto errout;
                status |= DO_SETLINK_NOTIFY;
        }

        if (tb[IFLA_AF_SPEC]) {
                struct nlattr *af;
                int rem;

                nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
                        const struct rtnl_af_ops *af_ops;

                        rcu_read_lock();

                        BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af))));

                        err = af_ops->set_link_af(dev, af);
                        if (err < 0) {
                                rcu_read_unlock();
                                goto errout;
                        }

                        rcu_read_unlock();
                        status |= DO_SETLINK_NOTIFY;
                }
        }
        err = 0;

        if (tb[IFLA_PROTO_DOWN]) {
                err = dev_change_proto_down(dev,
                                            nla_get_u8(tb[IFLA_PROTO_DOWN]));
                if (err)
                        goto errout;
                status |= DO_SETLINK_NOTIFY;
        }

        if (tb[IFLA_XDP]) {
                struct nlattr *xdp[IFLA_XDP_MAX + 1];
                u32 xdp_flags = 0;

                err = nla_parse_nested_deprecated(xdp, IFLA_XDP_MAX,
                                                  tb[IFLA_XDP],
                                                  ifla_xdp_policy, NULL);
                if (err < 0)
                        goto errout;

                if (xdp[IFLA_XDP_ATTACHED] || xdp[IFLA_XDP_PROG_ID]) {
                        err = -EINVAL;
                        goto errout;
                }

                if (xdp[IFLA_XDP_FLAGS]) {
                        xdp_flags = nla_get_u32(xdp[IFLA_XDP_FLAGS]);
                        if (xdp_flags & ~XDP_FLAGS_MASK) {
                                err = -EINVAL;
                                goto errout;
                        }
                        if (hweight32(xdp_flags & XDP_FLAGS_MODES) > 1) {
                                err = -EINVAL;
                                goto errout;
                        }
                }

                if (xdp[IFLA_XDP_FD]) {
                        err = dev_change_xdp_fd(dev, extack,
                                                nla_get_s32(xdp[IFLA_XDP_FD]),
                                                xdp_flags);
                        if (err)
                                goto errout;
                        status |= DO_SETLINK_NOTIFY;
                }
        }

errout:
        if (status & DO_SETLINK_MODIFIED) {
                if ((status & DO_SETLINK_NOTIFY) == DO_SETLINK_NOTIFY)
                        netdev_state_change(dev);

                if (err < 0)
                        net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
                                             dev->name);
        }

        return err;
}

static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
                        struct netlink_ext_ack *extack)
{
        struct net *net = sock_net(skb->sk);
        struct ifinfomsg *ifm;
        struct net_device *dev;
        int err;
        struct nlattr *tb[IFLA_MAX+1];
        char ifname[IFNAMSIZ];

        err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFLA_MAX,
                                     ifla_policy, extack);
        if (err < 0)
                goto errout;

        err = rtnl_ensure_unique_netns(tb, extack, false);
        if (err < 0)
                goto errout;

        if (tb[IFLA_IFNAME])
                nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
        else
                ifname[0] = '\0';

        err = -EINVAL;
        ifm = nlmsg_data(nlh);
        if (ifm->ifi_index > 0)
                dev = __dev_get_by_index(net, ifm->ifi_index);
        else if (tb[IFLA_IFNAME])
                dev = __dev_get_by_name(net, ifname);
        else
                goto errout;

        if (dev == NULL) {
                err = -ENODEV;
                goto errout;
        }

        err = do_setlink(skb, dev, ifm, extack, tb, ifname, 0);
errout:
        return err;
}

static int rtnl_group_dellink(const struct net *net, int group)
{
        struct net_device *dev, *aux;
        LIST_HEAD(list_kill);
        bool found = false;

        if (!group)
                return -EPERM;

        for_each_netdev(net, dev) {
                if (dev->group == group) {
                        const struct rtnl_link_ops *ops;

                        found = true;
                        ops = dev->rtnl_link_ops;
                        if (!ops || !ops->dellink)
                                return -EOPNOTSUPP;
                }
        }

        if (!found)
                return -ENODEV;

        for_each_netdev_safe(net, dev, aux) {
                if (dev->group == group) {
                        const struct rtnl_link_ops *ops;

                        ops = dev->rtnl_link_ops;
                        ops->dellink(dev, &list_kill);
                }
        }
        unregister_netdevice_many(&list_kill);

        return 0;
}

int rtnl_delete_link(struct net_device *dev)
{
        const struct rtnl_link_ops *ops;
        LIST_HEAD(list_kill);

        ops = dev->rtnl_link_ops;
        if (!ops || !ops->dellink)
                return -EOPNOTSUPP;

        ops->dellink(dev, &list_kill);
        unregister_netdevice_many(&list_kill);

        return 0;
}
EXPORT_SYMBOL_GPL(rtnl_delete_link);

static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
                        struct netlink_ext_ack *extack)
{
        struct net *net = sock_net(skb->sk);
        struct net *tgt_net = net;
        struct net_device *dev = NULL;
        struct ifinfomsg *ifm;
        char ifname[IFNAMSIZ];
        struct nlattr *tb[IFLA_MAX+1];
        int err;
        int netnsid = -1;

        err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFLA_MAX,
                                     ifla_policy, extack);
        if (err < 0)
                return err;

        err = rtnl_ensure_unique_netns(tb, extack, true);
        if (err < 0)
                return err;

        if (tb[IFLA_IFNAME])
                nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);

        if (tb[IFLA_TARGET_NETNSID]) {
                netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]);
                tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid);
                if (IS_ERR(tgt_net))
                        return PTR_ERR(tgt_net);
        }

        err = -EINVAL;
        ifm = nlmsg_data(nlh);
        if (ifm->ifi_index > 0)
                dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
        else if (tb[IFLA_IFNAME])
                dev = __dev_get_by_name(tgt_net, ifname);
        else if (tb[IFLA_GROUP])
                err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP]));
        else
                goto out;

        if (!dev) {
                if (tb[IFLA_IFNAME] || ifm->ifi_index > 0)
                        err = -ENODEV;

                goto out;
        }

        err = rtnl_delete_link(dev);

out:
        if (netnsid >= 0)
                put_net(tgt_net);

        return err;
}

int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
{
        unsigned int old_flags;
        int err;

        old_flags = dev->flags;
        if (ifm && (ifm->ifi_flags || ifm->ifi_change)) {
                err = __dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
                                         NULL);
                if (err < 0)
                        return err;
        }

        if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
                __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags));
        } else {
                dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
                __dev_notify_flags(dev, old_flags, ~0U);
        }
        return 0;
}
EXPORT_SYMBOL(rtnl_configure_link);

struct net_device *rtnl_create_link(struct net *net, const char *ifname,
                                    unsigned char name_assign_type,
                                    const struct rtnl_link_ops *ops,
                                    struct nlattr *tb[],
                                    struct netlink_ext_ack *extack)
{
        struct net_device *dev;
        unsigned int num_tx_queues = 1;
        unsigned int num_rx_queues = 1;

        if (tb[IFLA_NUM_TX_QUEUES])
                num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]);
        else if (ops->get_num_tx_queues)
                num_tx_queues = ops->get_num_tx_queues();

        if (tb[IFLA_NUM_RX_QUEUES])
                num_rx_queues = nla_get_u32(tb[IFLA_NUM_RX_QUEUES]);
        else if (ops->get_num_rx_queues)
                num_rx_queues = ops->get_num_rx_queues();

        if (num_tx_queues < 1 || num_tx_queues > 4096) {
                NL_SET_ERR_MSG(extack, "Invalid number of transmit queues");
                return ERR_PTR(-EINVAL);
        }

        if (num_rx_queues < 1 || num_rx_queues > 4096) {
                NL_SET_ERR_MSG(extack, "Invalid number of receive queues");
                return ERR_PTR(-EINVAL);
        }

        dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
                               ops->setup, num_tx_queues, num_rx_queues);
        if (!dev)
                return ERR_PTR(-ENOMEM);

        dev_net_set(dev, net);
        dev->rtnl_link_ops = ops;
        dev->rtnl_link_state = RTNL_LINK_INITIALIZING;

        if (tb[IFLA_MTU])
                dev->mtu = nla_get_u32(tb[IFLA_MTU]);
        if (tb[IFLA_ADDRESS]) {
                memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]),
                                nla_len(tb[IFLA_ADDRESS]));
                dev->addr_assign_type = NET_ADDR_SET;
        }
        if (tb[IFLA_BROADCAST])
                memcpy(dev->broadcast, nla_data(tb[IFLA_BROADCAST]),
                                nla_len(tb[IFLA_BROADCAST]));
        if (tb[IFLA_TXQLEN])
                dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
        if (tb[IFLA_OPERSTATE])
                set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
        if (tb[IFLA_LINKMODE])
                dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
        if (tb[IFLA_GROUP])
                dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
        if (tb[IFLA_GSO_MAX_SIZE])
                netif_set_gso_max_size(dev, nla_get_u32(tb[IFLA_GSO_MAX_SIZE]));
        if (tb[IFLA_GSO_MAX_SEGS])
                dev->gso_max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]);

        return dev;
}
EXPORT_SYMBOL(rtnl_create_link);

static int rtnl_group_changelink(const struct sk_buff *skb,
                struct net *net, int group,
                struct ifinfomsg *ifm,
                struct netlink_ext_ack *extack,
                struct nlattr **tb)
{
        struct net_device *dev, *aux;
        int err;

        for_each_netdev_safe(net, dev, aux) {
                if (dev->group == group) {
                        err = do_setlink(skb, dev, ifm, extack, tb, NULL, 0);