// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *      Generic address resolution entity
 *
 *      Authors:
 *      Pedro Roque             <roque@di.fc.ul.pt>
 *      Alexey Kuznetsov        <kuznet@ms2.inr.ac.ru>
 *
 *      Fixes:
 *      Vitaly E. Lavrov        releasing NULL neighbor in neigh_add.
 *      Harald Welte            Add neighbour cache statistics like rtstat
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/slab.h>
#include <linux/kmemleak.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/times.h>
#include <net/net_namespace.h>
#include <net/neighbour.h>
#include <net/arp.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/netevent.h>
#include <net/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/random.h>
#include <linux/string.h>
#include <linux/log2.h>
#include <linux/inetdevice.h>
#include <net/addrconf.h>

#include <trace/events/neigh.h>

#define NEIGH_DEBUG 1
#define neigh_dbg(level, fmt, ...)              \
do {                                            \
        if (level <= NEIGH_DEBUG)               \
                pr_debug(fmt, ##__VA_ARGS__);   \
} while (0)

#define PNEIGH_HASHMASK         0xF

static void neigh_timer_handler(struct timer_list *t);
static void __neigh_notify(struct neighbour *n, int type, int flags,
                           u32 pid);
static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
                                    struct net_device *dev);

#ifdef CONFIG_PROC_FS
static const struct seq_operations neigh_stat_seq_ops;
#endif

/*
   Neighbour hash table buckets are protected with rwlock tbl->lock.

   - All the scans/updates to hash buckets MUST be made under this lock.
   - NOTHING clever should be made under this lock: no callbacks
     to protocol backends, no attempts to send something to network.
     It will result in deadlocks, if backend/driver wants to use neighbour
     cache.
   - If the entry requires some non-trivial actions, increase
     its reference count and release table lock.

   Neighbour entries are protected:
   - with reference count.
   - with rwlock neigh->lock

   Reference count prevents destruction.

   neigh->lock mainly serializes ll address data and its validity state.
   However, the same lock is used to protect another entry fields:
    - timer
    - resolution queue

   Again, nothing clever shall be made under neigh->lock,
   the most complicated procedure, which we allow is dev->hard_header.
   It is supposed, that dev->hard_header is simplistic and does
   not make callbacks to neighbour tables.
 */

static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb)
{
        kfree_skb(skb);
        return -ENETDOWN;
}

static void neigh_cleanup_and_release(struct neighbour *neigh)
{
        trace_neigh_cleanup_and_release(neigh, 0);
        __neigh_notify(neigh, RTM_DELNEIGH, 0, 0);
        call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
        neigh_release(neigh);
}

/*
 * It is random distribution in the interval (1/2)*base...(3/2)*base.
 * It corresponds to default IPv6 settings and is not overridable,
 * because it is really reasonable choice.
 */

unsigned long neigh_rand_reach_time(unsigned long base)
{
        return base ? (prandom_u32() % base) + (base >> 1) : 0;
}
EXPORT_SYMBOL(neigh_rand_reach_time);

static void neigh_mark_dead(struct neighbour *n)
{
        n->dead = 1;
        if (!list_empty(&n->gc_list)) {
                list_del_init(&n->gc_list);
                atomic_dec(&n->tbl->gc_entries);
        }
}

static void neigh_update_gc_list(struct neighbour *n)
{
        bool on_gc_list, exempt_from_gc;

        write_lock_bh(&n->tbl->lock);
        write_lock(&n->lock);

        if (n->dead)
                goto out;

        /* remove from the gc list if new state is permanent or if neighbor
         * is externally learned; otherwise entry should be on the gc list
         */
        exempt_from_gc = n->nud_state & NUD_PERMANENT ||
                         n->flags & NTF_EXT_LEARNED;
        on_gc_list = !list_empty(&n->gc_list);

        if (exempt_from_gc && on_gc_list) {
                list_del_init(&n->gc_list);
                atomic_dec(&n->tbl->gc_entries);
        } else if (!exempt_from_gc && !on_gc_list) {
                /* add entries to the tail; cleaning removes from the front */
                list_add_tail(&n->gc_list, &n->tbl->gc_list);
                atomic_inc(&n->tbl->gc_entries);
        }

out:
        write_unlock(&n->lock);
        write_unlock_bh(&n->tbl->lock);
}

static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags,
                                     int *notify)
{
        bool rc = false;
        u8 ndm_flags;

        if (!(flags & NEIGH_UPDATE_F_ADMIN))
                return rc;

        ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0;
        if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) {
                if (ndm_flags & NTF_EXT_LEARNED)
                        neigh->flags |= NTF_EXT_LEARNED;
                else
                        neigh->flags &= ~NTF_EXT_LEARNED;
                rc = true;
                *notify = 1;
        }

        return rc;
}

static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np,
                      struct neigh_table *tbl)
{
        bool retval = false;

        write_lock(&n->lock);
        if (refcount_read(&n->refcnt) == 1) {
                struct neighbour *neigh;

                neigh = rcu_dereference_protected(n->next,
                                                  lockdep_is_held(&tbl->lock));
                rcu_assign_pointer(*np, neigh);
                neigh_mark_dead(n);
                retval = true;
        }
        write_unlock(&n->lock);
        if (retval)
                neigh_cleanup_and_release(n);
        return retval;
}

bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl)
{
        struct neigh_hash_table *nht;
        void *pkey = ndel->primary_key;
        u32 hash_val;
        struct neighbour *n;
        struct neighbour __rcu **np;

        nht = rcu_dereference_protected(tbl->nht,
                                        lockdep_is_held(&tbl->lock));
        hash_val = tbl->hash(pkey, ndel->dev, nht->hash_rnd);
        hash_val = hash_val >> (32 - nht->hash_shift);

        np = &nht->hash_buckets[hash_val];
        while ((n = rcu_dereference_protected(*np,
                                              lockdep_is_held(&tbl->lock)))) {
                if (n == ndel)
                        return neigh_del(n, np, tbl);
                np = &n->next;
        }
        return false;
}

static int neigh_forced_gc(struct neigh_table *tbl)
{
        int max_clean = atomic_read(&tbl->gc_entries) - tbl->gc_thresh2;
        unsigned long tref = jiffies - 5 * HZ;
        struct neighbour *n, *tmp;
        int shrunk = 0;

        NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);

        write_lock_bh(&tbl->lock);

        list_for_each_entry_safe(n, tmp, &tbl->gc_list, gc_list) {
                if (refcount_read(&n->refcnt) == 1) {
                        bool remove = false;

                        write_lock(&n->lock);
                        if ((n->nud_state == NUD_FAILED) ||
                            (n->nud_state == NUD_NOARP) ||
                            (tbl->is_multicast &&
                             tbl->is_multicast(n->primary_key)) ||
                            time_after(tref, n->updated))
                                remove = true;
                        write_unlock(&n->lock);

                        if (remove && neigh_remove_one(n, tbl))
                                shrunk++;
                        if (shrunk >= max_clean)
                                break;
                }
        }

        tbl->last_flush = jiffies;

        write_unlock_bh(&tbl->lock);

        return shrunk;
}

static void neigh_add_timer(struct neighbour *n, unsigned long when)
{
        neigh_hold(n);
        if (unlikely(mod_timer(&n->timer, when))) {
                printk("NEIGH: BUG, double timer add, state is %x\n",
                       n->nud_state);
                dump_stack();
        }
}

static int neigh_del_timer(struct neighbour *n)
{
        if ((n->nud_state & NUD_IN_TIMER) &&
            del_timer(&n->timer)) {
                neigh_release(n);
                return 1;
        }
        return 0;
}

static void pneigh_queue_purge(struct sk_buff_head *list)
{
        struct sk_buff *skb;

        while ((skb = skb_dequeue(list)) != NULL) {
                dev_put(skb->dev);
                kfree_skb(skb);
        }
}

static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev,
                            bool skip_perm)
{
        int i;
        struct neigh_hash_table *nht;

        nht = rcu_dereference_protected(tbl->nht,
                                        lockdep_is_held(&tbl->lock));

        for (i = 0; i < (1 << nht->hash_shift); i++) {
                struct neighbour *n;
                struct neighbour __rcu **np = &nht->hash_buckets[i];

                while ((n = rcu_dereference_protected(*np,
                                        lockdep_is_held(&tbl->lock))) != NULL) {
                        if (dev && n->dev != dev) {
                                np = &n->next;
                                continue;
                        }
                        if (skip_perm && n->nud_state & NUD_PERMANENT) {
                                np = &n->next;
                                continue;
                        }
                        rcu_assign_pointer(*np,
                                   rcu_dereference_protected(n->next,
                                                lockdep_is_held(&tbl->lock)));
                        write_lock(&n->lock);
                        neigh_del_timer(n);
                        neigh_mark_dead(n);
                        if (refcount_read(&n->refcnt) != 1) {
                                /* The most unpleasant situation.
                                   We must destroy neighbour entry,
                                   but someone still uses it.

                                   The destroy will be delayed until
                                   the last user releases us, but
                                   we must kill timers etc. and move
                                   it to safe state.
                                 */
                                __skb_queue_purge(&n->arp_queue);
                                n->arp_queue_len_bytes = 0;
                                n->output = neigh_blackhole;
                                if (n->nud_state & NUD_VALID)
                                        n->nud_state = NUD_NOARP;
                                else
                                        n->nud_state = NUD_NONE;
                                neigh_dbg(2, "neigh %p is stray\n", n);
                        }
                        write_unlock(&n->lock);
                        neigh_cleanup_and_release(n);
                }
        }
}

void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev)
{
        write_lock_bh(&tbl->lock);
        neigh_flush_dev(tbl, dev, false);
        write_unlock_bh(&tbl->lock);
}
EXPORT_SYMBOL(neigh_changeaddr);

static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev,
                          bool skip_perm)
{
        write_lock_bh(&tbl->lock);
        neigh_flush_dev(tbl, dev, skip_perm);
        pneigh_ifdown_and_unlock(tbl, dev);

        del_timer_sync(&tbl->proxy_timer);
        pneigh_queue_purge(&tbl->proxy_queue);
        return 0;
}

int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev)
{
        __neigh_ifdown(tbl, dev, true);
        return 0;
}
EXPORT_SYMBOL(neigh_carrier_down);

int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
{
        __neigh_ifdown(tbl, dev, false);
        return 0;
}
EXPORT_SYMBOL(neigh_ifdown);

static struct neighbour *neigh_alloc(struct neigh_table *tbl,
                                     struct net_device *dev,
                                     bool exempt_from_gc)
{
        struct neighbour *n = NULL;
        unsigned long now = jiffies;
        int entries;

        if (exempt_from_gc)
                goto do_alloc;

        entries = atomic_inc_return(&tbl->gc_entries) - 1;
        if (entries >= tbl->gc_thresh3 ||
            (entries >= tbl->gc_thresh2 &&
             time_after(now, tbl->last_flush + 5 * HZ))) {
                if (!neigh_forced_gc(tbl) &&
                    entries >= tbl->gc_thresh3) {
                        net_info_ratelimited("%s: neighbor table overflow!\n",
                                             tbl->id);
                        NEIGH_CACHE_STAT_INC(tbl, table_fulls);
                        goto out_entries;
                }
        }

do_alloc:
        n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC);
        if (!n)
                goto out_entries;

        __skb_queue_head_init(&n->arp_queue);
        rwlock_init(&n->lock);
        seqlock_init(&n->ha_lock);
        n->updated        = n->used = now;
        n->nud_state      = NUD_NONE;
        n->output         = neigh_blackhole;
        seqlock_init(&n->hh.hh_lock);
        n->parms          = neigh_parms_clone(&tbl->parms);
        timer_setup(&n->timer, neigh_timer_handler, 0);

        NEIGH_CACHE_STAT_INC(tbl, allocs);
        n->tbl            = tbl;
        refcount_set(&n->refcnt, 1);
        n->dead           = 1;
        INIT_LIST_HEAD(&n->gc_list);

        atomic_inc(&tbl->entries);
out:
        return n;

out_entries:
        if (!exempt_from_gc)
                atomic_dec(&tbl->gc_entries);
        goto out;
}

static void neigh_get_hash_rnd(u32 *x)
{
        *x = get_random_u32() | 1;
}

static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift)
{
        size_t size = (1 << shift) * sizeof(struct neighbour *);
        struct neigh_hash_table *ret;
        struct neighbour __rcu **buckets;
        int i;

        ret = kmalloc(sizeof(*ret), GFP_ATOMIC);
        if (!ret)
                return NULL;
        if (size <= PAGE_SIZE) {
                buckets = kzalloc(size, GFP_ATOMIC);
        } else {
                buckets = (struct neighbour __rcu **)
                          __get_free_pages(GFP_ATOMIC | __GFP_ZERO,
                                           get_order(size));
                kmemleak_alloc(buckets, size, 1, GFP_ATOMIC);
        }
        if (!buckets) {
                kfree(ret);
                return NULL;
        }
        ret->hash_buckets = buckets;
        ret->hash_shift = shift;
        for (i = 0; i < NEIGH_NUM_HASH_RND; i++)
                neigh_get_hash_rnd(&ret->hash_rnd[i]);
        return ret;
}

static void neigh_hash_free_rcu(struct rcu_head *head)
{
        struct neigh_hash_table *nht = container_of(head,
                                                    struct neigh_hash_table,
                                                    rcu);
        size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *);
        struct neighbour __rcu **buckets = nht->hash_buckets;

        if (size <= PAGE_SIZE) {
                kfree(buckets);
        } else {
                kmemleak_free(buckets);
                free_pages((unsigned long)buckets, get_order(size));
        }
        kfree(nht);
}

static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl,
                                                unsigned long new_shift)
{
        unsigned int i, hash;
        struct neigh_hash_table *new_nht, *old_nht;

        NEIGH_CACHE_STAT_INC(tbl, hash_grows);

        old_nht = rcu_dereference_protected(tbl->nht,
                                            lockdep_is_held(&tbl->lock));
        new_nht = neigh_hash_alloc(new_shift);
        if (!new_nht)
                return old_nht;

        for (i = 0; i < (1 << old_nht->hash_shift); i++) {
                struct neighbour *n, *next;

                for (n = rcu_dereference_protected(old_nht->hash_buckets[i],
                                                   lockdep_is_held(&tbl->lock));
                     n != NULL;
                     n = next) {
                        hash = tbl->hash(n->primary_key, n->dev,
                                         new_nht->hash_rnd);

                        hash >>= (32 - new_nht->hash_shift);
                        next = rcu_dereference_protected(n->next,
                                                lockdep_is_held(&tbl->lock));

                        rcu_assign_pointer(n->next,
                                           rcu_dereference_protected(
                                                new_nht->hash_buckets[hash],
                                                lockdep_is_held(&tbl->lock)));
                        rcu_assign_pointer(new_nht->hash_buckets[hash], n);
                }
        }

        rcu_assign_pointer(tbl->nht, new_nht);
        call_rcu(&old_nht->rcu, neigh_hash_free_rcu);
        return new_nht;
}

struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
                               struct net_device *dev)
{
        struct neighbour *n;

        NEIGH_CACHE_STAT_INC(tbl, lookups);

        rcu_read_lock_bh();
        n = __neigh_lookup_noref(tbl, pkey, dev);
        if (n) {
                if (!refcount_inc_not_zero(&n->refcnt))
                        n = NULL;
                NEIGH_CACHE_STAT_INC(tbl, hits);
        }

        rcu_read_unlock_bh();
        return n;
}
EXPORT_SYMBOL(neigh_lookup);

struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
                                     const void *pkey)
{
        struct neighbour *n;
        unsigned int key_len = tbl->key_len;
        u32 hash_val;
        struct neigh_hash_table *nht;

        NEIGH_CACHE_STAT_INC(tbl, lookups);

        rcu_read_lock_bh();
        nht = rcu_dereference_bh(tbl->nht);
        hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) >> (32 - nht->hash_shift);

        for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
             n != NULL;
             n = rcu_dereference_bh(n->next)) {
                if (!memcmp(n->primary_key, pkey, key_len) &&
                    net_eq(dev_net(n->dev), net)) {
                        if (!refcount_inc_not_zero(&n->refcnt))
                                n = NULL;
                        NEIGH_CACHE_STAT_INC(tbl, hits);
                        break;
                }
        }

        rcu_read_unlock_bh();
        return n;
}
EXPORT_SYMBOL(neigh_lookup_nodev);

static struct neighbour *___neigh_create(struct neigh_table *tbl,
                                         const void *pkey,
                                         struct net_device *dev,
                                         bool exempt_from_gc, bool want_ref)
{
        struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev, exempt_from_gc);
        u32 hash_val;
        unsigned int key_len = tbl->key_len;
        int error;
        struct neigh_hash_table *nht;

        trace_neigh_create(tbl, dev, pkey, n, exempt_from_gc);

        if (!n) {
                rc = ERR_PTR(-ENOBUFS);
                goto out;
        }

        memcpy(n->primary_key, pkey, key_len);
        n->dev = dev;
        dev_hold(dev);

        /* Protocol specific setup. */
        if (tbl->constructor && (error = tbl->constructor(n)) < 0) {
                rc = ERR_PTR(error);
                goto out_neigh_release;
        }

        if (dev->netdev_ops->ndo_neigh_construct) {
                error = dev->netdev_ops->ndo_neigh_construct(dev, n);
                if (error < 0) {
                        rc = ERR_PTR(error);
                        goto out_neigh_release;
                }
        }

        /* Device specific setup. */
        if (n->parms->neigh_setup &&
            (error = n->parms->neigh_setup(n)) < 0) {
                rc = ERR_PTR(error);
                goto out_neigh_release;
        }

        n->confirmed = jiffies - (NEIGH_VAR(n->parms, BASE_REACHABLE_TIME) << 1);

        write_lock_bh(&tbl->lock);
        nht = rcu_dereference_protected(tbl->nht,
                                        lockdep_is_held(&tbl->lock));

        if (atomic_read(&tbl->entries) > (1 << nht->hash_shift))
                nht = neigh_hash_grow(tbl, nht->hash_shift + 1);

        hash_val = tbl->hash(n->primary_key, dev, nht->hash_rnd) >> (32 - nht->hash_shift);

        if (n->parms->dead) {
                rc = ERR_PTR(-EINVAL);
                goto out_tbl_unlock;
        }

        for (n1 = rcu_dereference_protected(nht->hash_buckets[hash_val],
                                            lockdep_is_held(&tbl->lock));
             n1 != NULL;
             n1 = rcu_dereference_protected(n1->next,
                        lockdep_is_held(&tbl->lock))) {
                if (dev == n1->dev && !memcmp(n1->primary_key, n->primary_key, key_len)) {
                        if (want_ref)
                                neigh_hold(n1);
                        rc = n1;
                        goto out_tbl_unlock;
                }
        }

        n->dead = 0;
        if (!exempt_from_gc)
                list_add_tail(&n->gc_list, &n->tbl->gc_list);

        if (want_ref)
                neigh_hold(n);
        rcu_assign_pointer(n->next,
                           rcu_dereference_protected(nht->hash_buckets[hash_val],
                                                     lockdep_is_held(&tbl->lock)));
        rcu_assign_pointer(nht->hash_buckets[hash_val], n);
        write_unlock_bh(&tbl->lock);
        neigh_dbg(2, "neigh %p is created\n", n);
        rc = n;
out:
        return rc;
out_tbl_unlock:
        write_unlock_bh(&tbl->lock);
out_neigh_release:
        if (!exempt_from_gc)
                atomic_dec(&tbl->gc_entries);
        neigh_release(n);
        goto out;
}

struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
                                 struct net_device *dev, bool want_ref)
{
        return ___neigh_create(tbl, pkey, dev, false, want_ref);
}
EXPORT_SYMBOL(__neigh_create);

static u32 pneigh_hash(const void *pkey, unsigned int key_len)
{
        u32 hash_val = *(u32 *)(pkey + key_len - 4);
        hash_val ^= (hash_val >> 16);
        hash_val ^= hash_val >> 8;
        hash_val ^= hash_val >> 4;
        hash_val &= PNEIGH_HASHMASK;
        return hash_val;
}

static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n,
                                              struct net *net,
                                              const void *pkey,
                                              unsigned int key_len,
                                              struct net_device *dev)
{
        while (n) {
                if (!memcmp(n->key, pkey, key_len) &&
                    net_eq(pneigh_net(n), net) &&
                    (n->dev == dev || !n->dev))
                        return n;
                n = n->next;
        }
        return NULL;
}

struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl,
                struct net *net, const void *pkey, struct net_device *dev)
{
        unsigned int key_len = tbl->key_len;
        u32 hash_val = pneigh_hash(pkey, key_len);

        return __pneigh_lookup_1(tbl->phash_buckets[hash_val],
                                 net, pkey, key_len, dev);
}
EXPORT_SYMBOL_GPL(__pneigh_lookup);

struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
                                    struct net *net, const void *pkey,
                                    struct net_device *dev, int creat)
{
        struct pneigh_entry *n;
        unsigned int key_len = tbl->key_len;
        u32 hash_val = pneigh_hash(pkey, key_len);

        read_lock_bh(&tbl->lock);
        n = __pneigh_lookup_1(tbl->phash_buckets[hash_val],
                              net, pkey, key_len, dev);
        read_unlock_bh(&tbl->lock);

        if (n || !creat)
                goto out;

        ASSERT_RTNL();

        n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL);
        if (!n)
                goto out;

        n->protocol = 0;
        write_pnet(&n->net, net);
        memcpy(n->key, pkey, key_len);
        n->dev = dev;
        if (dev)
                dev_hold(dev);

        if (tbl->pconstructor && tbl->pconstructor(n)) {
                if (dev)
                        dev_put(dev);
                kfree(n);
                n = NULL;
                goto out;
        }

        write_lock_bh(&tbl->lock);
        n->next = tbl->phash_buckets[hash_val];
        tbl->phash_buckets[hash_val] = n;
        write_unlock_bh(&tbl->lock);
out:
        return n;
}
EXPORT_SYMBOL(pneigh_lookup);


int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
                  struct net_device *dev)
{
        struct pneigh_entry *n, **np;
        unsigned int key_len = tbl->key_len;
        u32 hash_val = pneigh_hash(pkey, key_len);

        write_lock_bh(&tbl->lock);
        for (np = &tbl->phash_buckets[hash_val]; (n = *np) != NULL;
             np = &n->next) {
                if (!memcmp(n->key, pkey, key_len) && n->dev == dev &&
                    net_eq(pneigh_net(n), net)) {
                        *np = n->next;
                        write_unlock_bh(&tbl->lock);
                        if (tbl->pdestructor)
                                tbl->pdestructor(n);
                        if (n->dev)
                                dev_put(n->dev);
                        kfree(n);
                        return 0;
                }
        }
        write_unlock_bh(&tbl->lock);
        return -ENOENT;
}

static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
                                    struct net_device *dev)
{
        struct pneigh_entry *n, **np, *freelist = NULL;
        u32 h;

        for (h = 0; h <= PNEIGH_HASHMASK; h++) {
                np = &tbl->phash_buckets[h];
                while ((n = *np) != NULL) {
                        if (!dev || n->dev == dev) {
                                *np = n->next;
                                n->next = freelist;
                                freelist = n;
                                continue;
                        }
                        np = &n->next;
                }
        }
        write_unlock_bh(&tbl->lock);
        while ((n = freelist)) {
                freelist = n->next;
                n->next = NULL;
                if (tbl->pdestructor)
                        tbl->pdestructor(n);
                if (n->dev)
                        dev_put(n->dev);
                kfree(n);
        }
        return -ENOENT;
}

static void neigh_parms_destroy(struct neigh_parms *parms);

static inline void neigh_parms_put(struct neigh_parms *parms)
{
        if (refcount_dec_and_test(&parms->refcnt))
                neigh_parms_destroy(parms);
}

/*
 *      neighbour must already be out of the table;
 *
 */
void neigh_destroy(struct neighbour *neigh)
{
        struct net_device *dev = neigh->dev;

        NEIGH_CACHE_STAT_INC(neigh->tbl, destroys);

        if (!neigh->dead) {
                pr_warn("Destroying alive neighbour %p\n", neigh);
                dump_stack();
                return;
        }

        if (neigh_del_timer(neigh))
                pr_warn("Impossible event\n");

        write_lock_bh(&neigh->lock);
        __skb_queue_purge(&neigh->arp_queue);
        write_unlock_bh(&neigh->lock);
        neigh->arp_queue_len_bytes = 0;

        if (dev->netdev_ops->ndo_neigh_destroy)
                dev->netdev_ops->ndo_neigh_destroy(dev, neigh);

        dev_put(dev);
        neigh_parms_put(neigh->parms);

        neigh_dbg(2, "neigh %p is destroyed\n", neigh);

        atomic_dec(&neigh->tbl->entries);
        kfree_rcu(neigh, rcu);
}
EXPORT_SYMBOL(neigh_destroy);

/* Neighbour state is suspicious;
   disable fast path.

   Called with write_locked neigh.
 */
static void neigh_suspect(struct neighbour *neigh)
{
        neigh_dbg(2, "neigh %p is suspected\n", neigh);

        neigh->output = neigh->ops->output;
}

/* Neighbour state is OK;
   enable fast path.

   Called with write_locked neigh.
 */
static void neigh_connect(struct neighbour *neigh)
{
        neigh_dbg(2, "neigh %p is connected\n", neigh);

        neigh->output = neigh->ops->connected_output;
}

static void neigh_periodic_work(struct work_struct *work)
{
        struct neigh_table *tbl = container_of(work, struct neigh_table, gc_work.work);
        struct neighbour *n;
        struct neighbour __rcu **np;
        unsigned int i;
        struct neigh_hash_table *nht;

        NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs);

        write_lock_bh(&tbl->lock);
        nht = rcu_dereference_protected(tbl->nht,
                                        lockdep_is_held(&tbl->lock));

        /*
         *      periodically recompute ReachableTime from random function
         */

        if (time_after(jiffies, tbl->last_rand + 300 * HZ)) {
                struct neigh_parms *p;
                tbl->last_rand = jiffies;
                list_for_each_entry(p, &tbl->parms_list, list)
                        p->reachable_time =
                                neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
        }

        if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
                goto out;

        for (i = 0 ; i < (1 << nht->hash_shift); i++) {
                np = &nht->hash_buckets[i];

                while ((n = rcu_dereference_protected(*np,
                                lockdep_is_held(&tbl->lock))) != NULL) {
                        unsigned int state;

                        write_lock(&n->lock);

                        state = n->nud_state;
                        if ((state & (NUD_PERMANENT | NUD_IN_TIMER)) ||
                            (n->flags & NTF_EXT_LEARNED)) {
                                write_unlock(&n->lock);
                                goto next_elt;
                        }

                        if (time_before(n->used, n->confirmed))
                                n->used = n->confirmed;

                        if (refcount_read(&n->refcnt) == 1 &&
                            (state == NUD_FAILED ||
                             time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) {
                                *np = n->next;
                                neigh_mark_dead(n);
                                write_unlock(&n->lock);
                                neigh_cleanup_and_release(n);
                                continue;
                        }
                        write_unlock(&n->lock);

next_elt:
                        np = &n->next;
                }
                /*
                 * It's fine to release lock here, even if hash table
                 * grows while we are preempted.
                 */
                write_unlock_bh(&tbl->lock);
                cond_resched();
                write_lock_bh(&tbl->lock);
                nht = rcu_dereference_protected(tbl->nht,
                                                lockdep_is_held(&tbl->lock));
        }
out:
        /* Cycle through all hash buckets every BASE_REACHABLE_TIME/2 ticks.
         * ARP entry timeouts range from 1/2 BASE_REACHABLE_TIME to 3/2
         * BASE_REACHABLE_TIME.
         */
        queue_delayed_work(system_power_efficient_wq, &tbl->gc_work,
                              NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1);
        write_unlock_bh(&tbl->lock);
}

static __inline__ int neigh_max_probes(struct neighbour *n)
{
        struct neigh_parms *p = n->parms;
        return NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) +
               (n->nud_state & NUD_PROBE ? NEIGH_VAR(p, MCAST_REPROBES) :
                NEIGH_VAR(p, MCAST_PROBES));
}

static void neigh_invalidate(struct neighbour *neigh)
        __releases(neigh->lock)
        __acquires(neigh->lock)
{
        struct sk_buff *skb;

        NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed);
        neigh_dbg(2, "neigh %p is failed\n", neigh);
        neigh->updated = jiffies;

        /* It is very thin place. report_unreachable is very complicated
           routine. Particularly, it can hit the same neighbour entry!

           So that, we try to be accurate and avoid dead loop. --ANK
         */
        while (neigh->nud_state == NUD_FAILED &&
               (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) {
                write_unlock(&neigh->lock);
                neigh->ops->error_report(neigh, skb);
                write_lock(&neigh->lock);

        }
        __skb_queue_purge(&neigh->arp_queue);
        neigh->arp_queue_len_bytes = 0;
}

static void neigh_probe(struct neighbour *neigh)
        __releases(neigh->lock)
{
        struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue);
        /* keep skb alive even if arp_queue overflows */
        if (skb)
                skb = skb_clone(skb, GFP_ATOMIC);
        write_unlock(&neigh->lock);
        if (neigh->ops->solicit)
                neigh->ops->solicit(neigh, skb);
        atomic_inc(&neigh->probes);
        consume_skb(skb);
}

/* Called when a timer expires for a neighbour entry. */

static void neigh_timer_handler(struct timer_list *t)
{
        unsigned long now, next;
        struct neighbour *neigh = from_timer(neigh, t, timer);
        unsigned int state;
        int notify = 0;

        write_lock(&neigh->lock);

        state = neigh->nud_state;
        now = jiffies;
        next = now + HZ;

        if (!(state & NUD_IN_TIMER))
                goto out;

        if (state & NUD_REACHABLE) {
                if (time_before_eq(now,
                                   neigh->confirmed + neigh->parms->reachable_time)) {
                        neigh_dbg(2, "neigh %p is still alive\n", neigh);
                        next = neigh->confirmed + neigh->parms->reachable_time;
                } else if (time_before_eq(now,
                                          neigh->used +
                                          NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) {
                        neigh_dbg(2, "neigh %p is delayed\n", neigh);
                        neigh->nud_state = NUD_DELAY;
                        neigh->updated = jiffies;
                        neigh_suspect(neigh);
                        next = now + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME);
                } else {
                        neigh_dbg(2, "neigh %p is suspected\n", neigh);
                        neigh->nud_state = NUD_STALE;
                        neigh->updated = jiffies;
                        neigh_suspect(neigh);
                        notify = 1;
                }
        } else if (state & NUD_DELAY) {
                if (time_before_eq(now,
                                   neigh->confirmed +
                                   NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) {
                        neigh_dbg(2, "neigh %p is now reachable\n", neigh);
                        neigh->nud_state = NUD_REACHABLE;
                        neigh->updated = jiffies;
                        neigh_connect(neigh);
                        notify = 1;
                        next = neigh->confirmed + neigh->parms->reachable_time;
                } else {
                        neigh_dbg(2, "neigh %p is probed\n", neigh);
                        neigh->nud_state = NUD_PROBE;
                        neigh->updated = jiffies;
                        atomic_set(&neigh->probes, 0);
                        notify = 1;
                        next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
                                         HZ/100);
                }
        } else {
                /* NUD_PROBE|NUD_INCOMPLETE */
                next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), HZ/100);
        }

        if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) &&
            atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) {
                neigh->nud_state = NUD_FAILED;
                notify = 1;
                neigh_invalidate(neigh);
                goto out;
        }

        if (neigh->nud_state & NUD_IN_TIMER) {
                if (time_before(next, jiffies + HZ/100))
                        next = jiffies + HZ/100;
                if (!mod_timer(&neigh->timer, next))
                        neigh_hold(neigh);
        }
        if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) {
                neigh_probe(neigh);
        } else {
out:
                write_unlock(&neigh->lock);
        }

        if (notify)
                neigh_update_notify(neigh, 0);

        trace_neigh_timer_handler(neigh, 0);

        neigh_release(neigh);
}

int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
{
        int rc;
        bool immediate_probe = false;

        write_lock_bh(&neigh->lock);

        rc = 0;
        if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
                goto out_unlock_bh;
        if (neigh->dead)
                goto out_dead;

        if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
                if (NEIGH_VAR(neigh->parms, MCAST_PROBES) +
                    NEIGH_VAR(neigh->parms, APP_PROBES)) {
                        unsigned long next, now = jiffies;

                        atomic_set(&neigh->probes,
                                   NEIGH_VAR(neigh->parms, UCAST_PROBES));
                        neigh_del_timer(neigh);
                        neigh->nud_state     = NUD_INCOMPLETE;
                        neigh->updated = now;
                        next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
                                         HZ/100);
                        neigh_add_timer(neigh, next);
                        immediate_probe = true;
                } else {
                        neigh->nud_state = NUD_FAILED;
                        neigh->updated = jiffies;
                        write_unlock_bh(&neigh->lock);

                        kfree_skb(skb);
                        return 1;
                }
        } else if (neigh->nud_state & NUD_STALE) {
                neigh_dbg(2, "neigh %p is delayed\n", neigh);
                neigh_del_timer(neigh);
                neigh->nud_state = NUD_DELAY;
                neigh->updated = jiffies;
                neigh_add_timer(neigh, jiffies +
                                NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME));
        }

        if (neigh->nud_state == NUD_INCOMPLETE) {
                if (skb) {
                        while (neigh->arp_queue_len_bytes + skb->truesize >
                               NEIGH_VAR(neigh->parms, QUEUE_LEN_BYTES)) {
                                struct sk_buff *buff;

                                buff = __skb_dequeue(&neigh->arp_queue);
                                if (!buff)
                                        break;
                                neigh->arp_queue_len_bytes -= buff->truesize;
                                kfree_skb(buff);
                                NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards);
                        }
                        skb_dst_force(skb);
                        __skb_queue_tail(&neigh->arp_queue, skb);
                        neigh->arp_queue_len_bytes += skb->truesize;
                }
                rc = 1;
        }
out_unlock_bh:
        if (immediate_probe)
                neigh_probe(neigh);
        else
                write_unlock(&neigh->lock);
        local_bh_enable();
        trace_neigh_event_send_done(neigh, rc);
        return rc;

out_dead:
        if (neigh->nud_state & NUD_STALE)
                goto out_unlock_bh;
        write_unlock_bh(&neigh->lock);
        kfree_skb(skb);
        trace_neigh_event_send_dead(neigh, 1);
        return 1;
}
EXPORT_SYMBOL(__neigh_event_send);

static void neigh_update_hhs(struct neighbour *neigh)
{
        struct hh_cache *hh;
        void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *)
                = NULL;

        if (neigh->dev->header_ops)
                update = neigh->dev->header_ops->cache_update;

        if (update) {
                hh = &neigh->hh;
                if (READ_ONCE(hh->hh_len)) {
                        write_seqlock_bh(&hh->hh_lock);
                        update(hh, neigh->dev, neigh->ha);
                        write_sequnlock_bh(&hh->hh_lock);
                }
        }
}



/* Generic update routine.
   -- lladdr is new lladdr or NULL, if it is not supplied.
   -- new    is new state.
   -- flags
        NEIGH_UPDATE_F_OVERRIDE allows to override existing lladdr,
                                if it is different.
        NEIGH_UPDATE_F_WEAK_OVERRIDE will suspect existing "connected"
                                lladdr instead of overriding it
                                if it is different.
        NEIGH_UPDATE_F_ADMIN    means that the change is administrative.

        NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing
                                NTF_ROUTER flag.
        NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as
                                a router.

   Caller MUST hold reference count on the entry.
 */

static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
                          u8 new, u32 flags, u32 nlmsg_pid,
                          struct netlink_ext_ack *extack)
{
        bool ext_learn_change = false;
        u8 old;
        int err;
        int notify = 0;
        struct net_device *dev;
        int update_isrouter = 0;

        trace_neigh_update(neigh, lladdr, new, flags, nlmsg_pid);

        write_lock_bh(&neigh->lock);

        dev    = neigh->dev;
        old    = neigh->nud_state;
        err    = -EPERM;

        if (neigh->dead) {
                NL_SET_ERR_MSG(extack, "Neighbor entry is now dead");
                new = old;
                goto out;
        }
        if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
            (old & (NUD_NOARP | NUD_PERMANENT)))
                goto out;

        ext_learn_change = neigh_update_ext_learned(neigh, flags, &notify);

        if (!(new & NUD_VALID)) {
                neigh_del_timer(neigh);
                if (old & NUD_CONNECTED)
                        neigh_suspect(neigh);
                neigh->nud_state = new;
                err = 0;
                notify = old & NUD_VALID;
                if ((old & (NUD_INCOMPLETE | NUD_PROBE)) &&
                    (new & NUD_FAILED)) {
                        neigh_invalidate(neigh);
                        notify = 1;
                }
                goto out;
        }

        /* Compare new lladdr with cached one */
        if (!dev->addr_len) {
                /* First case: device needs no address. */
                lladdr = neigh->ha;
        } else if (lladdr) {
                /* The second case: if something is already cached
                   and a new address is proposed:
                   - compare new & old
                   - if they are different, check override flag
                 */
                if ((old & NUD_VALID) &&
                    !memcmp(lladdr, neigh->ha, dev->addr_len))
                        lladdr = neigh->ha;
        } else {
                /* No address is supplied; if we know something,
                   use it, otherwise discard the request.
                 */
                err = -EINVAL;
                if (!(old & NUD_VALID)) {
                        NL_SET_ERR_MSG(extack, "No link layer address given");
                        goto out;
                }
                lladdr = neigh->ha;
        }

        /* Update confirmed timestamp for neighbour entry after we
         * received ARP packet even if it doesn't change IP to MAC binding.
         */
        if (new & NUD_CONNECTED)
                neigh->confirmed = jiffies;

        /* If entry was valid and address is not changed,
           do not change entry state, if new one is STALE.
         */
        err = 0;
        update_isrouter = flags & NEIGH_UPDATE_F_OVERRIDE_ISROUTER;
        if (old & NUD_VALID) {
                if (lladdr != neigh->ha && !(flags & NEIGH_UPDATE_F_OVERRIDE)) {
                        update_isrouter = 0;
                        if ((flags & NEIGH_UPDATE_F_WEAK_OVERRIDE) &&
                            (old & NUD_CONNECTED)) {
                                lladdr = neigh->ha;
                                new = NUD_STALE;
                        } else
                                goto out;
                } else {
                        if (lladdr == neigh->ha && new == NUD_STALE &&
                            !(flags & NEIGH_UPDATE_F_ADMIN))
                                new = old;
                }
        }

        /* Update timestamp only once we know we will make a change to the
         * neighbour entry. Otherwise we risk to move the locktime window with
         * noop updates and ignore relevant ARP updates.
         */
        if (new != old || lladdr != neigh->ha)
                neigh->updated = jiffies;

        if (new != old) {
                neigh_del_timer(neigh);
                if (new & NUD_PROBE)
                        atomic_set(&neigh->probes, 0);
                if (new & NUD_IN_TIMER)
                        neigh_add_timer(neigh, (jiffies +
                                                ((new & NUD_REACHABLE) ?
                                                 neigh->parms->reachable_time :
                                                 0)));
                neigh->nud_state = new;
                notify = 1;
        }

        if (lladdr != neigh->ha) {
                write_seqlock(&neigh->ha_lock);
                memcpy(&neigh->ha, lladdr, dev->addr_len);
                write_sequnlock(&neigh->ha_lock);
                neigh_update_hhs(neigh);
                if (!(new & NUD_CONNECTED))
                        neigh->confirmed = jiffies -
                                      (NEIGH_VAR(neigh->parms, BASE_REACHABLE_TIME) << 1);
                notify = 1;
        }
        if (new == old)
                goto out;
        if (new & NUD_CONNECTED)
                neigh_connect(neigh);
        else
                neigh_suspect(neigh);
        if (!(old & NUD_VALID)) {
                struct sk_buff *skb;

                /* Again: avoid dead loop if something went wrong */

                while (neigh->nud_state & NUD_VALID &&
                       (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) {
                        struct dst_entry *dst = skb_dst(skb);
                        struct neighbour *n2, *n1 = neigh;
                        write_unlock_bh(&neigh->lock);

                        rcu_read_lock();

                        /* Why not just use 'neigh' as-is?  The problem is that
                         * things such as shaper, eql, and sch_teql can end up
                         * using alternative, different, neigh objects to output
                         * the packet in the output path.  So what we need to do
                         * here is re-lookup the top-level neigh in the path so
                         * we can reinject the packet there.
                         */
                        n2 = NULL;
                        if (dst && dst->obsolete != DST_OBSOLETE_DEAD) {
                                n2 = dst_neigh_lookup_skb(dst, skb);
                                if (n2)
                                        n1 = n2;
                        }
                        n1->output(n1, skb);
                        if (n2)
                                neigh_release(n2);
                        rcu_read_unlock();

                        write_lock_bh(&neigh->lock);
                }
                __skb_queue_purge(&neigh->arp_queue);
                neigh->arp_queue_len_bytes = 0;
        }
out:
        if (update_isrouter)
                neigh_update_is_router(neigh, flags, &notify);
        write_unlock_bh(&neigh->lock);

        if (((new ^ old) & NUD_PERMANENT) || ext_learn_change)
                neigh_update_gc_list(neigh);

        if (notify)
                neigh_update_notify(neigh, nlmsg_pid);

        trace_neigh_update_done(neigh, err);

        return err;
}

int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
                 u32 flags, u32 nlmsg_pid)
{
        return __neigh_update(neigh, lladdr, new, flags, nlmsg_pid, NULL);
}
EXPORT_SYMBOL(neigh_update);

/* Update the neigh to listen temporarily for probe responses, even if it is
 * in a NUD_FAILED state. The caller has to hold neigh->lock for writing.
 */
void __neigh_set_probe_once(struct neighbour *neigh)
{
        if (neigh->dead)
                return;
        neigh->updated = jiffies;
        if (!(neigh->nud_state & NUD_FAILED))
                return;
        neigh->nud_state = NUD_INCOMPLETE;
        atomic_set(&neigh->probes, neigh_max_probes(neigh));
        neigh_add_timer(neigh,
                        jiffies + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
                                      HZ/100));
}
EXPORT_SYMBOL(__neigh_set_probe_once);

struct neighbour *neigh_event_ns(struct neigh_table *tbl,
                                 u8 *lladdr, void *saddr,
                                 struct net_device *dev)
{
        struct neighbour *neigh = __neigh_lookup(tbl, saddr, dev,
                                                 lladdr || !dev->addr_len);
        if (neigh)
                neigh_update(neigh, lladdr, NUD_STALE,
                             NEIGH_UPDATE_F_OVERRIDE, 0);
        return neigh;
}
EXPORT_SYMBOL(neigh_event_ns);

/* called with read_lock_bh(&n->lock); */
static void neigh_hh_init(struct neighbour *n)
{
        struct net_device *dev = n->dev;
        __be16 prot = n->tbl->protocol;
        struct hh_cache *hh = &n->hh;

        write_lock_bh(&n->lock);

        /* Only one thread can come in here and initialize the
         * hh_cache entry.
         */
        if (!hh->hh_len)
                dev->header_ops->cache(n, hh, prot);

        write_unlock_bh(&n->lock);
}

/* Slow and careful. */

int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
{
        int rc = 0;

        if (!neigh_event_send(neigh, skb)) {
                int err;
                struct net_device *dev = neigh->dev;
                unsigned int seq;

                if (dev->header_ops->cache && !READ_ONCE(neigh->hh.hh_len))
                        neigh_hh_init(neigh);

                do {
                        __skb_pull(skb, skb_network_offset(skb));
                        seq = read_seqbegin(&neigh->ha_lock);
                        err = dev_hard_header(skb, dev, ntohs(skb->protocol),
                                              neigh->ha, NULL, skb->len);
                } while (read_seqretry(&neigh->ha_lock, seq));

                if (err >= 0)
                        rc = dev_queue_xmit(skb);
                else
                        goto out_kfree_skb;
        }
out:
        return rc;
out_kfree_skb:
        rc = -EINVAL;
        kfree_skb(skb);
        goto out;
}
EXPORT_SYMBOL(neigh_resolve_output);

/* As fast as possible without hh cache */

int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb)
{
        struct net_device *dev = neigh->dev;
        unsigned int seq;
        int err;

        do {
                __skb_pull(skb, skb_network_offset(skb));
                seq = read_seqbegin(&neigh->ha_lock);
                err = dev_hard_header(skb, dev, ntohs(skb->protocol),
                                      neigh->ha, NULL, skb->len);
        } while (read_seqretry(&neigh->ha_lock, seq));

        if (err >= 0)
                err = dev_queue_xmit(skb);
        else {
                err = -EINVAL;
                kfree_skb(skb);
        }
        return err;
}
EXPORT_SYMBOL(neigh_connected_output);

int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb)
{
        return dev_queue_xmit(skb);
}
EXPORT_SYMBOL(neigh_direct_output);

static void neigh_proxy_process(struct timer_list *t)
{
        struct neigh_table *tbl = from_timer(tbl, t, proxy_timer);
        long sched_next = 0;
        unsigned long now = jiffies;
        struct sk_buff *skb, *n;

        spin_lock(&tbl->proxy_queue.lock);

        skb_queue_walk_safe(&tbl->proxy_queue, skb, n) {
                long tdif = NEIGH_CB(skb)->sched_next - now;

                if (tdif <= 0) {
                        struct net_device *dev = skb->dev;

                        __skb_unlink(skb, &tbl->proxy_queue);
                        if (tbl->proxy_redo && netif_running(dev)) {
                                rcu_read_lock();
                                tbl->proxy_redo(skb);
                                rcu_read_unlock();
                        } else {
                                kfree_skb(skb);
                        }

                        dev_put(dev);
                } else if (!sched_next || tdif < sched_next)
                        sched_next = tdif;
        }
        del_timer(&tbl->proxy_timer);
        if (sched_next)
                mod_timer(&tbl->proxy_timer, jiffies + sched_next);
        spin_unlock(&tbl->proxy_queue.lock);
}

void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
                    struct sk_buff *skb)
{
        unsigned long sched_next = jiffies +
                        prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY));

        if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
                kfree_skb(skb);
                return;
        }

        NEIGH_CB(skb)->sched_next = sched_next;
        NEIGH_CB(skb)->flags |= LOCALLY_ENQUEUED;

        spin_lock(&tbl->proxy_queue.lock);
        if (del_timer(&tbl->proxy_timer)) {
                if (time_before(tbl->proxy_timer.expires, sched_next))
                        sched_next = tbl->proxy_timer.expires;
        }
        skb_dst_drop(skb);
        dev_hold(skb->dev);
        __skb_queue_tail(&tbl->proxy_queue, skb);
        mod_timer(&tbl->proxy_timer, sched_next);
        spin_unlock(&tbl->proxy_queue.lock);
}
EXPORT_SYMBOL(pneigh_enqueue);

static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl,
                                                      struct net *net, int ifindex)
{
        struct neigh_parms *p;

        list_for_each_entry(p, &tbl->parms_list, list) {
                if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) ||
                    (!p->dev && !ifindex && net_eq(net, &init_net)))
                        return p;
        }

        return NULL;
}

struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
                                      struct neigh_table *tbl)
{
        struct neigh_parms *p;
        struct net *net = dev_net(dev);
        const struct net_device_ops *ops = dev->netdev_ops;

        p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL);
        if (p) {
                p->tbl            = tbl;
                refcount_set(&p->refcnt, 1);
                p->reachable_time =
                                neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
                dev_hold(dev);
                p->dev = dev;
                write_pnet(&p->net, net);
                p->sysctl_table = NULL;

                if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) {
                        dev_put(dev);
                        kfree(p);
                        return NULL;
                }

                write_lock_bh(&tbl->lock);
                list_add(&p->list, &tbl->parms.list);
                write_unlock_bh(&tbl->lock);

                neigh_parms_data_state_cleanall(p);
        }
        return p;
}
EXPORT_SYMBOL(neigh_parms_alloc);

static void neigh_rcu_free_parms(struct rcu_head *head)
{
        struct neigh_parms *parms =
                container_of(head, struct neigh_parms, rcu_head);

        neigh_parms_put(parms);
}

void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms)
{
        if (!parms || parms == &tbl->parms)
                return;
        write_lock_bh(&tbl->lock);
        list_del(&parms->list);
        parms->dead = 1;
        write_unlock_bh(&tbl->lock);
        if (parms->dev)
                dev_put(parms->dev);
        call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
}
EXPORT_SYMBOL(neigh_parms_release);

static void neigh_parms_destroy(struct neigh_parms *parms)
{
        kfree(parms);
}

static struct lock_class_key neigh_table_proxy_queue_class;

static struct neigh_table *neigh_tables[NEIGH_NR_TABLES] __read_mostly;

void neigh_table_init(int index, struct neigh_table *tbl)
{
        unsigned long now = jiffies;
        unsigned long phsize;

        INIT_LIST_HEAD(&tbl->parms_list);
        INIT_LIST_HEAD(&tbl->gc_list);
        list_add(&tbl->parms.list, &tbl->parms_list);
        write_pnet(&tbl->parms.net, &init_net);
        refcount_set(&tbl->parms.refcnt, 1);
        tbl->parms.reachable_time =
                          neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME));

        tbl->stats = alloc_percpu(struct neigh_statistics);
        if (!tbl->stats)
                panic("cannot create neighbour cache statistics");

#ifdef CONFIG_PROC_FS
        if (!proc_create_seq_data(tbl->id, 0, init_net.proc_net_stat,
                              &neigh_stat_seq_ops, tbl))
                panic("cannot create neighbour proc dir entry");
#endif

        RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(3));

        phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *);
        tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL);

        if (!tbl->nht || !tbl->phash_buckets)
                panic("cannot allocate neighbour cache hashes");

        if (!tbl->entry_size)
                tbl->entry_size = ALIGN(offsetof(struct neighbour, primary_key) +
                                        tbl->key_len, NEIGH_PRIV_ALIGN);
        else
                WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN);

        rwlock_init(&tbl->lock);
        INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work);
        queue_delayed_work(system_power_efficient_wq, &tbl->gc_work,
                        tbl->parms.reachable_time);
        timer_setup(&tbl->proxy_timer, neigh_proxy_process, 0);
        skb_queue_head_init_class(&tbl->proxy_queue,
                        &neigh_table_proxy_queue_class);

        tbl->last_flush = now;
        tbl->last_rand  = now + tbl->parms.reachable_time * 20;

        neigh_tables[index] = tbl;
}
EXPORT_SYMBOL(neigh_table_init);

int neigh_table_clear(int index, struct neigh_table *tbl)
{
        neigh_tables[index] = NULL;
        /* It is not clean... Fix it to unload IPv6 module safely */
        cancel_delayed_work_sync(&tbl->gc_work);
        del_timer_sync(&tbl->proxy_timer);
        pneigh_queue_purge(&tbl->proxy_queue);
        neigh_ifdown(tbl, NULL);
        if (atomic_read(&tbl->entries))
                pr_crit("neighbour leakage\n");

        call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu,
                 neigh_hash_free_rcu);
        tbl->nht = NULL;

        kfree(tbl->phash_buckets);
        tbl->phash_buckets = NULL;

        remove_proc_entry(tbl->id, init_net.proc_net_stat);

        free_percpu(tbl->stats);
        tbl->stats = NULL;

        return 0;
}
EXPORT_SYMBOL(neigh_table_clear);

static struct neigh_table *neigh_find_table(int family)
{
        struct neigh_table *tbl = NULL;

        switch (family) {
        case AF_INET:
                tbl = neigh_tables[NEIGH_ARP_TABLE];
                break;
        case AF_INET6:
                tbl = neigh_tables[NEIGH_ND_TABLE];
                break;
        case AF_DECnet:
                tbl = neigh_tables[NEIGH_DN_TABLE];
                break;
        }

        return tbl;
}

const struct nla_policy nda_policy[NDA_MAX+1] = {
        [NDA_UNSPEC]            = { .strict_start_type = NDA_NH_ID },
        [NDA_DST]               = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
        [NDA_LLADDR]            = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
        [NDA_CACHEINFO]         = { .len = sizeof(struct nda_cacheinfo) },
        [NDA_PROBES]            = { .type = NLA_U32 },
        [NDA_VLAN]              = { .type = NLA_U16 },
        [NDA_PORT]              = { .type = NLA_U16 },
        [NDA_VNI]               = { .type = NLA_U32 },
        [NDA_IFINDEX]           = { .type = NLA_U32 },
        [NDA_MASTER]            = { .type = NLA_U32 },
        [NDA_PROTOCOL]          = { .type = NLA_U8 },
        [NDA_NH_ID]             = { .type = NLA_U32 },
        [NDA_FDB_EXT_ATTRS]     = { .type = NLA_NESTED },
};

static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
                        struct netlink_ext_ack *extack)
{
        struct net *net = sock_net(skb->sk);
        struct ndmsg *ndm;
        struct nlattr *dst_attr;
        struct neigh_table *tbl;
        struct neighbour *neigh;
        struct net_device *dev = NULL;
        int err = -EINVAL;

        ASSERT_RTNL();
        if (nlmsg_len(nlh) < sizeof(*ndm))
                goto out;

        dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST);
        if (!dst_attr) {
                NL_SET_ERR_MSG(extack, "Network address not specified");
                goto out;
        }

        ndm = nlmsg_data(nlh);
        if (ndm->ndm_ifindex) {
                dev = __dev_get_by_index(net, ndm->ndm_ifindex);
                if (dev == NULL) {
                        err = -ENODEV;
                        goto out;
                }
        }

        tbl = neigh_find_table(ndm->ndm_family);
        if (tbl == NULL)
                return -EAFNOSUPPORT;

        if (nla_len(dst_attr) < (int)tbl->key_len) {
                NL_SET_ERR_MSG(extack, "Invalid network address");
                goto out;
        }

        if (ndm->ndm_flags & NTF_PROXY) {
                err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
                goto out;
        }

        if (dev == NULL)
                goto out;

        neigh = neigh_lookup(tbl, nla_data(dst_attr), dev);
        if (neigh == NULL) {
                err = -ENOENT;
                goto out;
        }

        err = __neigh_update(neigh, NULL, NUD_FAILED,
                             NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN,
                             NETLINK_CB(skb).portid, extack);
        write_lock_bh(&tbl->lock);
        neigh_release(neigh);
        neigh_remove_one(neigh, tbl);
        write_unlock_bh(&tbl->lock);

out:
        return err;
}

static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
                     struct netlink_ext_ack *extack)
{
        int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE |
                NEIGH_UPDATE_F_OVERRIDE_ISROUTER;
        struct net *net = sock_net(skb->sk);
        struct ndmsg *ndm;
        struct nlattr *tb[NDA_MAX+1];
        struct neigh_table *tbl;
        struct net_device *dev = NULL;
        struct neighbour *neigh;
        void *dst, *lladdr;
        u8 protocol = 0;
        int err;

        ASSERT_RTNL();
        err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX,
                                     nda_policy, extack);
        if (err < 0)
                goto out;

        err = -EINVAL;
        if (!tb[NDA_DST]) {
                NL_SET_ERR_MSG(extack, "Network address not specified");
                goto out;
        }

        ndm = nlmsg_data(nlh);
        if (ndm->ndm_ifindex) {
                dev = __dev_get_by_index(net, ndm->ndm_ifindex);
                if (dev == NULL) {
                        err = -ENODEV;
                        goto out;
                }

                if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) {
                        NL_SET_ERR_MSG(extack, "Invalid link address");
                        goto out;
                }
        }

        tbl = neigh_find_table(ndm->ndm_family);
        if (tbl == NULL)
                return -EAFNOSUPPORT;

        if (nla_len(tb[NDA_DST]) < (int)tbl->key_len) {
                NL_SET_ERR_MSG(extack, "Invalid network address");
                goto out;
        }

        dst = nla_data(tb[NDA_DST]);
        lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;

        if (tb[NDA_PROTOCOL])
                protocol = nla_get_u8(tb[NDA_PROTOCOL]);

        if (ndm->ndm_flags & NTF_PROXY) {
                struct pneigh_entry *pn;

                err = -ENOBUFS;
                pn = pneigh_lookup(tbl, net, dst, dev, 1);
                if (pn) {
                        pn->flags = ndm->ndm_flags;
                        if (protocol)
                                pn->protocol = protocol;
                        err = 0;
                }
                goto out;
        }

        if (!dev) {
                NL_SET_ERR_MSG(extack, "Device not specified");
                goto out;
        }

        if (tbl->allow_add && !tbl->allow_add(dev, extack)) {
                err = -EINVAL;
                goto out;
        }

        neigh = neigh_lookup(tbl, dst, dev);
        if (neigh == NULL) {
                bool exempt_from_gc;

                if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
                        err = -ENOENT;
                        goto out;
                }

                exempt_from_gc = ndm->ndm_state & NUD_PERMANENT ||
                                 ndm->ndm_flags & NTF_EXT_LEARNED;
                neigh = ___neigh_create(tbl, dst, dev, exempt_from_gc, true);
                if (IS_ERR(neigh)) {
                        err = PTR_ERR(neigh);
                        goto out;
                }
        } else {
                if (nlh->nlmsg_flags & NLM_F_EXCL) {
                        err = -EEXIST;
                        neigh_release(neigh);
                        goto out;
                }

                if (!(nlh->nlmsg_flags & NLM_F_REPLACE))
                        flags &= ~(NEIGH_UPDATE_F_OVERRIDE |
                                   NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
        }

        if (protocol)
                neigh->protocol = protocol;

        if (ndm->ndm_flags & NTF_EXT_LEARNED)
                flags |= NEIGH_UPDATE_F_EXT_LEARNED;

        if (ndm->ndm_flags & NTF_ROUTER)
                flags |= NEIGH_UPDATE_F_ISROUTER;

        if (ndm->ndm_flags & NTF_USE) {
                neigh_event_send(neigh, NULL);
                err = 0;
        } else
                err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags,
                                     NETLINK_CB(skb).portid, extack);

        neigh_release(neigh);

out:
        return err;
}

static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
{
        struct nlattr *nest;

        nest = nla_nest_start_noflag(skb, NDTA_PARMS);
        if (nest == NULL)
                return -ENOBUFS;

        if ((parms->dev &&
             nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) ||
            nla_put_u32(skb, NDTPA_REFCNT, refcount_read(&parms->refcnt)) ||
            nla_put_u32(skb, NDTPA_QUEUE_LENBYTES,