/*
 *      Generic address resolution entity
 *
 *      Authors:
 *      Pedro Roque             <roque@di.fc.ul.pt>
 *      Alexey Kuznetsov        <kuznet@ms2.inr.ac.ru>
 *
 *      This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 *
 *      Fixes:
 *      Vitaly E. Lavrov        releasing NULL neighbor in neigh_add.
 *      Harald Welte            Add neighbour cache statistics like rtstat
 */

#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/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>

#define NEIGH_DEBUG 1

#define NEIGH_PRINTK(x...) printk(x)
#define NEIGH_NOPRINTK(x...) do { ; } while(0)
#define NEIGH_PRINTK0 NEIGH_PRINTK
#define NEIGH_PRINTK1 NEIGH_NOPRINTK
#define NEIGH_PRINTK2 NEIGH_NOPRINTK

#if NEIGH_DEBUG >= 1
#undef NEIGH_PRINTK1
#define NEIGH_PRINTK1 NEIGH_PRINTK
#endif
#if NEIGH_DEBUG >= 2
#undef NEIGH_PRINTK2
#define NEIGH_PRINTK2 NEIGH_PRINTK
#endif

#define PNEIGH_HASHMASK         0xF

static void neigh_timer_handler(unsigned long arg);
static void __neigh_notify(struct neighbour *n, int type, int flags);
static void neigh_update_notify(struct neighbour *neigh);
static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev);

static struct neigh_table *neigh_tables;
#ifdef CONFIG_PROC_FS
static const struct file_operations neigh_stat_seq_fops;
#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.

   The last lock is neigh_tbl_lock. It is pure SMP lock, protecting
   list of neighbour tables. This list is used only in process context,
 */

static DEFINE_RWLOCK(neigh_tbl_lock);

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

static void neigh_cleanup_and_release(struct neighbour *neigh)
{
        if (neigh->parms->neigh_cleanup)
                neigh->parms->neigh_cleanup(neigh);

        __neigh_notify(neigh, RTM_DELNEIGH, 0);
        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 ? (net_random() % base) + (base >> 1) : 0);
}


static int neigh_forced_gc(struct neigh_table *tbl)
{
        int shrunk = 0;
        int i;

        NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);

        write_lock_bh(&tbl->lock);
        for (i = 0; i <= tbl->hash_mask; i++) {
                struct neighbour *n, **np;

                np = &tbl->hash_buckets[i];
                while ((n = *np) != NULL) {
                        /* Neighbour record may be discarded if:
                         * - nobody refers to it.
                         * - it is not permanent
                         */
                        write_lock(&n->lock);
                        if (atomic_read(&n->refcnt) == 1 &&
                            !(n->nud_state & NUD_PERMANENT)) {
                                *np     = n->next;
                                n->dead = 1;
                                shrunk  = 1;
                                write_unlock(&n->lock);
                                neigh_cleanup_and_release(n);
                                continue;
                        }
                        write_unlock(&n->lock);
                        np = &n->next;
                }
        }

        tbl->last_flush = jiffies;

        write_unlock_bh(&tbl->lock);

        return shrunk;
}

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)
{
        int i;

        for (i = 0; i <= tbl->hash_mask; i++) {
                struct neighbour *n, **np = &tbl->hash_buckets[i];

                while ((n = *np) != NULL) {
                        if (dev && n->dev != dev) {
                                np = &n->next;
                                continue;
                        }
                        *np = n->next;
                        write_lock(&n->lock);
                        neigh_del_timer(n);
                        n->dead = 1;

                        if (atomic_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->output = neigh_blackhole;
                                if (n->nud_state & NUD_VALID)
                                        n->nud_state = NUD_NOARP;
                                else
                                        n->nud_state = NUD_NONE;
                                NEIGH_PRINTK2("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);
        write_unlock_bh(&tbl->lock);
}

int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
{
        write_lock_bh(&tbl->lock);
        neigh_flush_dev(tbl, dev);
        pneigh_ifdown(tbl, dev);
        write_unlock_bh(&tbl->lock);

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

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

        entries = atomic_inc_return(&tbl->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)
                        goto out_entries;
        }

        n = kmem_cache_zalloc(tbl->kmem_cachep, GFP_ATOMIC);
        if (!n)
                goto out_entries;

        skb_queue_head_init(&n->arp_queue);
        rwlock_init(&n->lock);
        n->updated        = n->used = now;
        n->nud_state      = NUD_NONE;
        n->output         = neigh_blackhole;
        n->parms          = neigh_parms_clone(&tbl->parms);
        init_timer(&n->timer);
        n->timer.function = neigh_timer_handler;
        n->timer.data     = (unsigned long)n;

        NEIGH_CACHE_STAT_INC(tbl, allocs);
        n->tbl            = tbl;
        atomic_set(&n->refcnt, 1);
        n->dead           = 1;
out:
        return n;

out_entries:
        atomic_dec(&tbl->entries);
        goto out;
}

static struct neighbour **neigh_hash_alloc(unsigned int entries)
{
        unsigned long size = entries * sizeof(struct neighbour *);
        struct neighbour **ret;

        if (size <= PAGE_SIZE) {
                ret = kzalloc(size, GFP_ATOMIC);
        } else {
                ret = (struct neighbour **)
                      __get_free_pages(GFP_ATOMIC|__GFP_ZERO, get_order(size));
        }
        return ret;
}

static void neigh_hash_free(struct neighbour **hash, unsigned int entries)
{
        unsigned long size = entries * sizeof(struct neighbour *);

        if (size <= PAGE_SIZE)
                kfree(hash);
        else
                free_pages((unsigned long)hash, get_order(size));
}

static void neigh_hash_grow(struct neigh_table *tbl, unsigned long new_entries)
{
        struct neighbour **new_hash, **old_hash;
        unsigned int i, new_hash_mask, old_entries;

        NEIGH_CACHE_STAT_INC(tbl, hash_grows);

        BUG_ON(!is_power_of_2(new_entries));
        new_hash = neigh_hash_alloc(new_entries);
        if (!new_hash)
                return;

        old_entries = tbl->hash_mask + 1;
        new_hash_mask = new_entries - 1;
        old_hash = tbl->hash_buckets;

        get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd));
        for (i = 0; i < old_entries; i++) {
                struct neighbour *n, *next;

                for (n = old_hash[i]; n; n = next) {
                        unsigned int hash_val = tbl->hash(n->primary_key, n->dev);

                        hash_val &= new_hash_mask;
                        next = n->next;

                        n->next = new_hash[hash_val];
                        new_hash[hash_val] = n;
                }
        }
        tbl->hash_buckets = new_hash;
        tbl->hash_mask = new_hash_mask;

        neigh_hash_free(old_hash, old_entries);
}

struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
                               struct net_device *dev)
{
        struct neighbour *n;
        int key_len = tbl->key_len;
        u32 hash_val = tbl->hash(pkey, dev);

        NEIGH_CACHE_STAT_INC(tbl, lookups);

        read_lock_bh(&tbl->lock);
        for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) {
                if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) {
                        neigh_hold(n);
                        NEIGH_CACHE_STAT_INC(tbl, hits);
                        break;
                }
        }
        read_unlock_bh(&tbl->lock);
        return n;
}

struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, const void *pkey)
{
        struct neighbour *n;
        int key_len = tbl->key_len;
        u32 hash_val = tbl->hash(pkey, NULL);

        NEIGH_CACHE_STAT_INC(tbl, lookups);

        read_lock_bh(&tbl->lock);
        for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) {
                if (!memcmp(n->primary_key, pkey, key_len)) {
                        neigh_hold(n);
                        NEIGH_CACHE_STAT_INC(tbl, hits);
                        break;
                }
        }
        read_unlock_bh(&tbl->lock);
        return n;
}

struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey,
                               struct net_device *dev)
{
        u32 hash_val;
        int key_len = tbl->key_len;
        int error;
        struct neighbour *n1, *rc, *n = neigh_alloc(tbl);

        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;
        }

        /* 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 - (n->parms->base_reachable_time << 1);

        write_lock_bh(&tbl->lock);

        if (atomic_read(&tbl->entries) > (tbl->hash_mask + 1))
                neigh_hash_grow(tbl, (tbl->hash_mask + 1) << 1);

        hash_val = tbl->hash(pkey, dev) & tbl->hash_mask;

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

        for (n1 = tbl->hash_buckets[hash_val]; n1; n1 = n1->next) {
                if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) {
                        neigh_hold(n1);
                        rc = n1;
                        goto out_tbl_unlock;
                }
        }

        n->next = tbl->hash_buckets[hash_val];
        tbl->hash_buckets[hash_val] = n;
        n->dead = 0;
        neigh_hold(n);
        write_unlock_bh(&tbl->lock);
        NEIGH_PRINTK2("neigh %p is created.\n", n);
        rc = n;
out:
        return rc;
out_tbl_unlock:
        write_unlock_bh(&tbl->lock);
out_neigh_release:
        neigh_release(n);
        goto out;
}

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

        read_lock_bh(&tbl->lock);

        for (n = tbl->phash_buckets[hash_val]; n; n = n->next) {
                if (!memcmp(n->key, pkey, key_len) &&
                    (n->dev == dev || !n->dev)) {
                        read_unlock_bh(&tbl->lock);
                        goto out;
                }
        }
        read_unlock_bh(&tbl->lock);
        n = NULL;
        if (!creat)
                goto out;

        ASSERT_RTNL();

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

        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;
}


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

        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) {
                        *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(struct neigh_table *tbl, struct net_device *dev)
{
        struct pneigh_entry *n, **np;
        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;
                                if (tbl->pdestructor)
                                        tbl->pdestructor(n);
                                if (n->dev)
                                        dev_put(n->dev);
                                kfree(n);
                                continue;
                        }
                        np = &n->next;
                }
        }
        return -ENOENT;
}


/*
 *      neighbour must already be out of the table;
 *
 */
void neigh_destroy(struct neighbour *neigh)
{
        struct hh_cache *hh;

        NEIGH_CACHE_STAT_INC(neigh->tbl, destroys);

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

        if (neigh_del_timer(neigh))
                printk(KERN_WARNING "Impossible event.\n");

        while ((hh = neigh->hh) != NULL) {
                neigh->hh = hh->hh_next;
                hh->hh_next = NULL;

                write_seqlock_bh(&hh->hh_lock);
                hh->hh_output = neigh_blackhole;
                write_sequnlock_bh(&hh->hh_lock);
                if (atomic_dec_and_test(&hh->hh_refcnt))
                        kfree(hh);
        }

        skb_queue_purge(&neigh->arp_queue);

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

        NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh);

        atomic_dec(&neigh->tbl->entries);
        kmem_cache_free(neigh->tbl->kmem_cachep, neigh);
}

/* Neighbour state is suspicious;
   disable fast path.

   Called with write_locked neigh.
 */
static void neigh_suspect(struct neighbour *neigh)
{
        struct hh_cache *hh;

        NEIGH_PRINTK2("neigh %p is suspected.\n", neigh);

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

        for (hh = neigh->hh; hh; hh = hh->hh_next)
                hh->hh_output = neigh->ops->output;
}

/* Neighbour state is OK;
   enable fast path.

   Called with write_locked neigh.
 */
static void neigh_connect(struct neighbour *neigh)
{
        struct hh_cache *hh;

        NEIGH_PRINTK2("neigh %p is connected.\n", neigh);

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

        for (hh = neigh->hh; hh; hh = hh->hh_next)
                hh->hh_output = neigh->ops->hh_output;
}

static void neigh_periodic_timer(unsigned long arg)
{
        struct neigh_table *tbl = (struct neigh_table *)arg;
        struct neighbour *n, **np;
        unsigned long expire, now = jiffies;

        NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs);

        write_lock(&tbl->lock);

        /*
         *      periodically recompute ReachableTime from random function
         */

        if (time_after(now, tbl->last_rand + 300 * HZ)) {
                struct neigh_parms *p;
                tbl->last_rand = now;
                for (p = &tbl->parms; p; p = p->next)
                        p->reachable_time =
                                neigh_rand_reach_time(p->base_reachable_time);
        }

        np = &tbl->hash_buckets[tbl->hash_chain_gc];
        tbl->hash_chain_gc = ((tbl->hash_chain_gc + 1) & tbl->hash_mask);

        while ((n = *np) != NULL) {
                unsigned int state;

                write_lock(&n->lock);

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

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

                if (atomic_read(&n->refcnt) == 1 &&
                    (state == NUD_FAILED ||
                     time_after(now, n->used + n->parms->gc_staletime))) {
                        *np = n->next;
                        n->dead = 1;
                        write_unlock(&n->lock);
                        neigh_cleanup_and_release(n);
                        continue;
                }
                write_unlock(&n->lock);

next_elt:
                np = &n->next;
        }

        /* 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.
         */
        expire = tbl->parms.base_reachable_time >> 1;
        expire /= (tbl->hash_mask + 1);
        if (!expire)
                expire = 1;

        if (expire>HZ)
                mod_timer(&tbl->gc_timer, round_jiffies(now + expire));
        else
                mod_timer(&tbl->gc_timer, now + expire);

        write_unlock(&tbl->lock);
}

static __inline__ int neigh_max_probes(struct neighbour *n)
{
        struct neigh_parms *p = n->parms;
        return (n->nud_state & NUD_PROBE ?
                p->ucast_probes :
                p->ucast_probes + p->app_probes + p->mcast_probes);
}

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

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

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

        write_lock(&neigh->lock);

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

        if (!(state & NUD_IN_TIMER)) {
#ifndef CONFIG_SMP
                printk(KERN_WARNING "neigh: timer & !nud_in_timer\n");
#endif
                goto out;
        }

        if (state & NUD_REACHABLE) {
                if (time_before_eq(now,
                                   neigh->confirmed + neigh->parms->reachable_time)) {
                        NEIGH_PRINTK2("neigh %p is still alive.\n", neigh);
                        next = neigh->confirmed + neigh->parms->reachable_time;
                } else if (time_before_eq(now,
                                          neigh->used + neigh->parms->delay_probe_time)) {
                        NEIGH_PRINTK2("neigh %p is delayed.\n", neigh);
                        neigh->nud_state = NUD_DELAY;
                        neigh->updated = jiffies;
                        neigh_suspect(neigh);
                        next = now + neigh->parms->delay_probe_time;
                } else {
                        NEIGH_PRINTK2("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->parms->delay_probe_time)) {
                        NEIGH_PRINTK2("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_PRINTK2("neigh %p is probed.\n", neigh);
                        neigh->nud_state = NUD_PROBE;
                        neigh->updated = jiffies;
                        atomic_set(&neigh->probes, 0);
                        next = now + neigh->parms->retrans_time;
                }
        } else {
                /* NUD_PROBE|NUD_INCOMPLETE */
                next = now + neigh->parms->retrans_time;
        }

        if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) &&
            atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) {
                struct sk_buff *skb;

                neigh->nud_state = NUD_FAILED;
                neigh->updated = jiffies;
                notify = 1;
                NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed);
                NEIGH_PRINTK2("neigh %p is failed.\n", neigh);

                /* 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);
        }

        if (neigh->nud_state & NUD_IN_TIMER) {
                if (time_before(next, jiffies + HZ/2))
                        next = jiffies + HZ/2;
                if (!mod_timer(&neigh->timer, next))
                        neigh_hold(neigh);
        }
        if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) {
                struct sk_buff *skb = skb_peek(&neigh->arp_queue);
                /* keep skb alive even if arp_queue overflows */
                if (skb)
                        skb_get(skb);
                write_unlock(&neigh->lock);
                neigh->ops->solicit(neigh, skb);
                atomic_inc(&neigh->probes);
                if (skb)
                        kfree_skb(skb);
        } else {
out:
                write_unlock(&neigh->lock);
        }

        if (notify)
                neigh_update_notify(neigh);

        neigh_release(neigh);
}

int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
{
        int rc;
        unsigned long now;

        write_lock_bh(&neigh->lock);

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

        now = jiffies;

        if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
                if (neigh->parms->mcast_probes + neigh->parms->app_probes) {
                        atomic_set(&neigh->probes, neigh->parms->ucast_probes);
                        neigh->nud_state     = NUD_INCOMPLETE;
                        neigh->updated = jiffies;
                        neigh_hold(neigh);
                        neigh_add_timer(neigh, now + 1);
                } else {
                        neigh->nud_state = NUD_FAILED;
                        neigh->updated = jiffies;
                        write_unlock_bh(&neigh->lock);

                        if (skb)
                                kfree_skb(skb);
                        return 1;
                }
        } else if (neigh->nud_state & NUD_STALE) {
                NEIGH_PRINTK2("neigh %p is delayed.\n", neigh);
                neigh_hold(neigh);
                neigh->nud_state = NUD_DELAY;
                neigh->updated = jiffies;
                neigh_add_timer(neigh,
                                jiffies + neigh->parms->delay_probe_time);
        }

        if (neigh->nud_state == NUD_INCOMPLETE) {
                if (skb) {
                        if (skb_queue_len(&neigh->arp_queue) >=
                            neigh->parms->queue_len) {
                                struct sk_buff *buff;
                                buff = neigh->arp_queue.next;
                                __skb_unlink(buff, &neigh->arp_queue);
                                kfree_skb(buff);
                        }
                        __skb_queue_tail(&neigh->arp_queue, skb);
                }
                rc = 1;
        }
out_unlock_bh:
        write_unlock_bh(&neigh->lock);
        return rc;
}

static void neigh_update_hhs(struct neighbour *neigh)
{
        struct hh_cache *hh;
        void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *)
                = neigh->dev->header_ops->cache_update;

        if (update) {
                for (hh = neigh->hh; hh; hh = hh->hh_next) {
                        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.
                                It also allows to retain current state
                                if lladdr is unchanged.
        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.
 */

int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
                 u32 flags)
{
        u8 old;
        int err;
        int notify = 0;
        struct net_device *dev;
        int update_isrouter = 0;

        write_lock_bh(&neigh->lock);

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

        if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
            (old & (NUD_NOARP | NUD_PERMANENT)))
                goto out;

        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;
                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))
                        goto out;
                lladdr = neigh->ha;
        }

        if (new & NUD_CONNECTED)
                neigh->confirmed = jiffies;
        neigh->updated = 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_WEAK_OVERRIDE) ||
                             (old & NUD_CONNECTED))
                            )
                                new = old;
                }
        }

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

        if (lladdr != neigh->ha) {
                memcpy(&neigh->ha, lladdr, dev->addr_len);
                neigh_update_hhs(neigh);
                if (!(new & NUD_CONNECTED))
                        neigh->confirmed = jiffies -
                                      (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 neighbour *n1 = neigh;
                        write_unlock_bh(&neigh->lock);
                        /* On shaper/eql skb->dst->neighbour != neigh :( */
                        if (skb->dst && skb->dst->neighbour)
                                n1 = skb->dst->neighbour;
                        n1->output(skb);
                        write_lock_bh(&neigh->lock);
                }
                skb_queue_purge(&neigh->arp_queue);
        }
out:
        if (update_isrouter) {
                neigh->flags = (flags & NEIGH_UPDATE_F_ISROUTER) ?
                        (neigh->flags | NTF_ROUTER) :
                        (neigh->flags & ~NTF_ROUTER);
        }
        write_unlock_bh(&neigh->lock);

        if (notify)
                neigh_update_notify(neigh);

        return err;
}

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);
        return neigh;
}

static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst,
                          __be16 protocol)
{
        struct hh_cache *hh;
        struct net_device *dev = dst->dev;

        for (hh = n->hh; hh; hh = hh->hh_next)
                if (hh->hh_type == protocol)
                        break;

        if (!hh && (hh = kzalloc(sizeof(*hh), GFP_ATOMIC)) != NULL) {
                seqlock_init(&hh->hh_lock);
                hh->hh_type = protocol;
                atomic_set(&hh->hh_refcnt, 0);
                hh->hh_next = NULL;

                if (dev->header_ops->cache(n, hh)) {
                        kfree(hh);
                        hh = NULL;
                } else {
                        atomic_inc(&hh->hh_refcnt);
                        hh->hh_next = n->hh;
                        n->hh       = hh;
                        if (n->nud_state & NUD_CONNECTED)
                                hh->hh_output = n->ops->hh_output;
                        else
                                hh->hh_output = n->ops->output;
                }
        }
        if (hh) {
                atomic_inc(&hh->hh_refcnt);
                dst->hh = hh;
        }
}

/* This function can be used in contexts, where only old dev_queue_xmit
   worked, f.e. if you want to override normal output path (eql, shaper),
   but resolution is not made yet.
 */

int neigh_compat_output(struct sk_buff *skb)
{
        struct net_device *dev = skb->dev;

        __skb_pull(skb, skb_network_offset(skb));

        if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
                            skb->len) < 0 &&
            dev->header_ops->rebuild(skb))
                return 0;

        return dev_queue_xmit(skb);
}

/* Slow and careful. */

int neigh_resolve_output(struct sk_buff *skb)
{
        struct dst_entry *dst = skb->dst;
        struct neighbour *neigh;
        int rc = 0;

        if (!dst || !(neigh = dst->neighbour))
                goto discard;

        __skb_pull(skb, skb_network_offset(skb));

        if (!neigh_event_send(neigh, skb)) {
                int err;
                struct net_device *dev = neigh->dev;
                if (dev->header_ops->cache && !dst->hh) {
                        write_lock_bh(&neigh->lock);
                        if (!dst->hh)
                                neigh_hh_init(neigh, dst, dst->ops->protocol);
                        err = dev_hard_header(skb, dev, ntohs(skb->protocol),
                                              neigh->ha, NULL, skb->len);
                        write_unlock_bh(&neigh->lock);
                } else {
                        read_lock_bh(&neigh->lock);
                        err = dev_hard_header(skb, dev, ntohs(skb->protocol),
                                              neigh->ha, NULL, skb->len);
                        read_unlock_bh(&neigh->lock);
                }
                if (err >= 0)
                        rc = neigh->ops->queue_xmit(skb);
                else
                        goto out_kfree_skb;
        }
out:
        return rc;
discard:
        NEIGH_PRINTK1("neigh_resolve_output: dst=%p neigh=%p\n",
                      dst, dst ? dst->neighbour : NULL);
out_kfree_skb:
        rc = -EINVAL;
        kfree_skb(skb);
        goto out;
}

/* As fast as possible without hh cache */

int neigh_connected_output(struct sk_buff *skb)
{
        int err;
        struct dst_entry *dst = skb->dst;
        struct neighbour *neigh = dst->neighbour;
        struct net_device *dev = neigh->dev;

        __skb_pull(skb, skb_network_offset(skb));

        read_lock_bh(&neigh->lock);
        err = dev_hard_header(skb, dev, ntohs(skb->protocol),
                              neigh->ha, NULL, skb->len);
        read_unlock_bh(&neigh->lock);
        if (err >= 0)
                err = neigh->ops->queue_xmit(skb);
        else {
                err = -EINVAL;
                kfree_skb(skb);
        }
        return err;
}

static void neigh_proxy_process(unsigned long arg)
{
        struct neigh_table *tbl = (struct neigh_table *)arg;
        long sched_next = 0;
        unsigned long now = jiffies;
        struct sk_buff *skb;

        spin_lock(&tbl->proxy_queue.lock);

        skb = tbl->proxy_queue.next;

        while (skb != (struct sk_buff *)&tbl->proxy_queue) {
                struct sk_buff *back = skb;
                long tdif = NEIGH_CB(back)->sched_next - now;

                skb = skb->next;
                if (tdif <= 0) {
                        struct net_device *dev = back->dev;
                        __skb_unlink(back, &tbl->proxy_queue);
                        if (tbl->proxy_redo && netif_running(dev))
                                tbl->proxy_redo(back);
                        else
                                kfree_skb(back);

                        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 now = jiffies;
        unsigned long sched_next = now + (net_random() % p->proxy_delay);

        if (tbl->proxy_queue.qlen > 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;
        }
        dst_release(skb->dst);
        skb->dst = NULL;
        dev_hold(skb->dev);
        __skb_queue_tail(&tbl->proxy_queue, skb);
        mod_timer(&tbl->proxy_timer, sched_next);
        spin_unlock(&tbl->proxy_queue.lock);
}


struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
                                      struct neigh_table *tbl)
{
        struct neigh_parms *p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL);

        if (p) {
                p->tbl            = tbl;
                atomic_set(&p->refcnt, 1);
                INIT_RCU_HEAD(&p->rcu_head);
                p->reachable_time =
                                neigh_rand_reach_time(p->base_reachable_time);
                if (dev) {
                        if (dev->neigh_setup && dev->neigh_setup(dev, p)) {
                                kfree(p);
                                return NULL;
                        }

                        dev_hold(dev);
                        p->dev = dev;
                }
                p->sysctl_table = NULL;
                write_lock_bh(&tbl->lock);
                p->next         = tbl->parms.next;
                tbl->parms.next = p;
                write_unlock_bh(&tbl->lock);
        }
        return p;
}

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)
{
        struct neigh_parms **p;

        if (!parms || parms == &tbl->parms)
                return;
        write_lock_bh(&tbl->lock);
        for (p = &tbl->parms.next; *p; p = &(*p)->next) {
                if (*p == parms) {
                        *p = parms->next;
                        parms->dead = 1;
                        write_unlock_bh(&tbl->lock);
                        if (parms->dev)
                                dev_put(parms->dev);
                        call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
                        return;
                }
        }
        write_unlock_bh(&tbl->lock);
        NEIGH_PRINTK1("neigh_parms_release: not found\n");
}

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

static struct lock_class_key neigh_table_proxy_queue_class;

void neigh_table_init_no_netlink(struct neigh_table *tbl)
{
        unsigned long now = jiffies;
        unsigned long phsize;

        atomic_set(&tbl->parms.refcnt, 1);
        INIT_RCU_HEAD(&tbl->parms.rcu_head);
        tbl->parms.reachable_time =
                          neigh_rand_reach_time(tbl->parms.base_reachable_time);

        if (!tbl->kmem_cachep)
                tbl->kmem_cachep =
                        kmem_cache_create(tbl->id, tbl->entry_size, 0,
                                          SLAB_HWCACHE_ALIGN|SLAB_PANIC,
                                          NULL);
        tbl->stats = alloc_percpu(struct neigh_statistics);
        if (!tbl->stats)
                panic("cannot create neighbour cache statistics");

#ifdef CONFIG_PROC_FS
        tbl->pde = create_proc_entry(tbl->id, 0, init_net.proc_net_stat);
        if (!tbl->pde)
                panic("cannot create neighbour proc dir entry");
        tbl->pde->proc_fops = &neigh_stat_seq_fops;
        tbl->pde->data = tbl;
#endif

        tbl->hash_mask = 1;
        tbl->hash_buckets = neigh_hash_alloc(tbl->hash_mask + 1);

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

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

        get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd));

        rwlock_init(&tbl->lock);
        init_timer(&tbl->gc_timer);
        tbl->gc_timer.data     = (unsigned long)tbl;
        tbl->gc_timer.function = neigh_periodic_timer;
        tbl->gc_timer.expires  = now + 1;
        add_timer(&tbl->gc_timer);

        init_timer(&tbl->proxy_timer);
        tbl->proxy_timer.data     = (unsigned long)tbl;
        tbl->proxy_timer.function = neigh_proxy_process;
        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;
}

void neigh_table_init(struct neigh_table *tbl)
{
        struct neigh_table *tmp;

        neigh_table_init_no_netlink(tbl);
        write_lock(&neigh_tbl_lock);
        for (tmp = neigh_tables; tmp; tmp = tmp->next) {
                if (tmp->family == tbl->family)
                        break;
        }
        tbl->next       = neigh_tables;
        neigh_tables    = tbl;
        write_unlock(&neigh_tbl_lock);

        if (unlikely(tmp)) {
                printk(KERN_ERR "NEIGH: Registering multiple tables for "
                       "family %d\n", tbl->family);
                dump_stack();
        }
}

int neigh_table_clear(struct neigh_table *tbl)
{
        struct neigh_table **tp;

        /* It is not clean... Fix it to unload IPv6 module safely */
        del_timer_sync(&tbl->gc_timer);
        del_timer_sync(&tbl->proxy_timer);
        pneigh_queue_purge(&tbl->proxy_queue);
        neigh_ifdown(tbl, NULL);
        if (atomic_read(&tbl->entries))
                printk(KERN_CRIT "neighbour leakage\n");
        write_lock(&neigh_tbl_lock);
        for (tp = &neigh_tables; *tp; tp = &(*tp)->next) {
                if (*tp == tbl) {
                        *tp = tbl->next;
                        break;
                }
        }
        write_unlock(&neigh_tbl_lock);

        neigh_hash_free(tbl->hash_buckets, tbl->hash_mask + 1);
        tbl->hash_buckets = 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;

        kmem_cache_destroy(tbl->kmem_cachep);
        tbl->kmem_cachep = NULL;

        return 0;
}

static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
        struct net *net = skb->sk->sk_net;
        struct ndmsg *ndm;
        struct nlattr *dst_attr;
        struct neigh_table *tbl;
        struct net_device *dev = NULL;
        int err = -EINVAL;

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

        dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST);
        if (dst_attr == NULL)
                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;
                }
        }

        read_lock(&neigh_tbl_lock);
        for (tbl = neigh_tables; tbl; tbl = tbl->next) {
                struct neighbour *neigh;

                if (tbl->family != ndm->ndm_family)
                        continue;
                read_unlock(&neigh_tbl_lock);

                if (nla_len(dst_attr) < tbl->key_len)
                        goto out_dev_put;

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

                if (dev == NULL)
                        goto out_dev_put;

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

                err = neigh_update(neigh, NULL, NUD_FAILED,
                                   NEIGH_UPDATE_F_OVERRIDE |
                                   NEIGH_UPDATE_F_ADMIN);
                neigh_release(neigh);
                goto out_dev_put;
        }
        read_unlock(&neigh_tbl_lock);
        err = -EAFNOSUPPORT;

out_dev_put:
        if (dev)
                dev_put(dev);
out:
        return err;
}

static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
        struct net *net = skb->sk->sk_net;
        struct ndmsg *ndm;
        struct nlattr *tb[NDA_MAX+1];
        struct neigh_table *tbl;
        struct net_device *dev = NULL;
        int err;

        err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
        if (err < 0)
                goto out;

        err = -EINVAL;
        if (tb[NDA_DST] == NULL)
                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)
                        goto out_dev_put;
        }

        read_lock(&neigh_tbl_lock);
        for (tbl = neigh_tables; tbl; tbl = tbl->next) {
                int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
                struct neighbour *neigh;
                void *dst, *lladdr;

                if (tbl->family != ndm->ndm_family)
                        continue;
                read_unlock(&neigh_tbl_lock);

                if (nla_len(tb[NDA_DST]) < tbl->key_len)
                        goto out_dev_put;
                dst = nla_data(tb[NDA_DST]);
                lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;

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

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

                if (dev == NULL)
                        goto out_dev_put;

                neigh = neigh_lookup(tbl, dst, dev);
                if (neigh == NULL) {
                        if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
                                err = -ENOENT;
                                goto out_dev_put;
                        }

                        neigh = __neigh_lookup_errno(tbl, dst, dev);
                        if (IS_ERR(neigh)) {
                                err = PTR_ERR(neigh);
                                goto out_dev_put;
                        }
                } else {
                        if (nlh->nlmsg_flags & NLM_F_EXCL) {
                                err = -EEXIST;
                                neigh_release(neigh);
                                goto out_dev_put;
                        }

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

                err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
                neigh_release(neigh);
                goto out_dev_put;
        }

        read_unlock(&neigh_tbl_lock);
        err = -EAFNOSUPPORT;

out_dev_put:
        if (dev)
                dev_put(dev);
out:
        return err;
}

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

        nest = nla_nest_start(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, atomic_read(&parms->refcnt));
        NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len);
        NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen);
        NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes);
        NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes);
        NLA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes);
        NLA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time);
        NLA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME,
                      parms->base_reachable_time);
        NLA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime);
        NLA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time);
        NLA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time);
        NLA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay);
        NLA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay);
        NLA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime);

        return nla_nest_end(skb, nest);

nla_put_failure:
        return nla_nest_cancel(skb, nest);
}

static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
                              u32 pid, u32 seq, int type, int flags)
{
        struct nlmsghdr *nlh;
        struct ndtmsg *ndtmsg;

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

        ndtmsg = nlmsg_data(nlh);

        read_lock_bh(&tbl->lock);
        ndtmsg->ndtm_family = tbl->family;
        ndtmsg->ndtm_pad1   = 0;
        ndtmsg->ndtm_pad2   = 0;

        NLA_PUT_STRING(skb, NDTA_NAME, tbl->id);
        NLA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval);
        NLA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1);
        NLA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2);
        NLA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3);

        {
                unsigned long now = jiffies;
                unsigned int flush_delta = now - tbl->last_flush;
                unsigned int rand_delta = now - tbl->last_rand;

                struct ndt_config ndc = {
                        .ndtc_key_len           = tbl->key_len,
                        .ndtc_entry_size        = tbl->entry_size,
                        .ndtc_entries           = atomic_read(&tbl->entries),
                        .ndtc_last_flush        = jiffies_to_msecs(flush_delta),
                        .ndtc_last_rand         = jiffies_to_msecs(rand_delta),
                        .ndtc_hash_rnd          = tbl->hash_rnd,
                        .ndtc_hash_mask         = tbl->hash_mask,
                        .ndtc_hash_chain_gc     = tbl->hash_chain_gc,
                        .ndtc_proxy_qlen        = tbl->proxy_queue.qlen,
                };

                NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc);
        }

        {
                int cpu;
                struct ndt_stats ndst;

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

                for_each_possible_cpu(cpu) {
                        struct neigh_statistics *st;

                        st = per_cpu_ptr(tbl->stats, cpu);
                        ndst.ndts_allocs                += st->allocs;
                        ndst.ndts_destroys              += st->destroys;
                        ndst.ndts_hash_grows            += st->hash_grows;
                        ndst.ndts_res_failed            += st->res_failed;
                        ndst.ndts_lookups               += st->lookups;
                        ndst.ndts_hits                  += st->hits;
                        ndst.ndts_rcv_probes_mcast      += st->rcv_probes_mcast;
                        ndst.ndts_rcv_probes_ucast      += st->rcv_probes_ucast;
                        ndst.ndts_periodic_gc_runs      += st->periodic_gc_runs;
                        ndst.ndts_forced_gc_runs        += st->forced_gc_runs;
                }

                NLA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst);
        }

        BUG_ON(tbl->parms.dev);
        if (neightbl_fill_parms(skb, &tbl->parms) < 0)
                goto nla_put_failure;

        read_unlock_bh(&tbl->lock);
        return nlmsg_end(skb, nlh);

nla_put_failure:
        read_unlock_bh(&tbl->lock);
        nlmsg_cancel(skb, nlh);
        return -EMSGSIZE;
}

static int neightbl_fill_param_info(struct sk_buff *skb,
                                    struct neigh_table *tbl,
                                    struct neigh_parms *parms,
                                    u32 pid, u32 seq, int type,
                                    unsigned int flags)
{
        struct ndtmsg *ndtmsg;
        struct nlmsghdr *nlh;

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

        ndtmsg = nlmsg_data(nlh);

        read_lock_bh(&tbl->lock);
        ndtmsg->ndtm_family = tbl->family;
        ndtmsg->ndtm_pad1   = 0;
        ndtmsg->ndtm_pad2   = 0;

        if (nla_put_string(skb, NDTA_NAME, tbl->id) < 0 ||
            neightbl_fill_parms(skb, parms) < 0)
                goto errout;

        read_unlock_bh(&tbl->lock);
        return nlmsg_end(skb, nlh);
errout:
        read_unlock_bh(&tbl->lock);
        nlmsg_cancel(skb, nlh);
        return -EMSGSIZE;
}

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

        for (p = &tbl->parms; p; p = p->next)
                if ((p->dev && p->dev->ifindex == ifindex) ||
                    (!p->dev && !ifindex))
                        return p;

        return NULL;
}

static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = {
        [NDTA_NAME]             = { .type = NLA_STRING },
        [NDTA_THRESH1]          = { .type = NLA_U32 },
        [NDTA_THRESH2]          = { .type = NLA_U32 },
        [NDTA_THRESH3]          = { .type = NLA_U32 },
        [NDTA_GC_INTERVAL]      = { .type = NLA_U64 },
        [NDTA_PARMS]            = { .type = NLA_NESTED },
};

static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
        [NDTPA_IFINDEX]                 = { .type = NLA_U32 },
        [NDTPA_QUEUE_LEN]               = { .type = NLA_U32 },
        [NDTPA_PROXY_QLEN]              = { .type = NLA_U32 },
        [NDTPA_APP_PROBES]              = { .type = NLA_U32 },
        [NDTPA_UCAST_PROBES]            = { .type = NLA_U32 },
        [NDTPA_MCAST_PROBES]            = { .type = NLA_U32 },
        [NDTPA_BASE_REACHABLE_TIME]     = { .type = NLA_U64 },
        [NDTPA_GC_STALETIME]            = { .type = NLA_U64 },
        [NDTPA_DELAY_PROBE_TIME]        = { .type = NLA_U64 },
        [NDTPA_RETRANS_TIME]            = { .type = NLA_U64 },
        [NDTPA_ANYCAST_DELAY]           = { .type = NLA_U64 },
        [NDTPA_PROXY_DELAY]             = { .type = NLA_U64 },
        [NDTPA_LOCKTIME]                = { .type = NLA_U64 },
};

static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
        struct neigh_table *tbl;
        struct ndtmsg *ndtmsg;
        struct nlattr *tb[NDTA_MAX+1];
        int err;

        err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
                          nl_neightbl_policy);
        if (err < 0)
                goto errout;

        if (tb[NDTA_NAME] == NULL) {
                err = -EINVAL;
                goto errout;
        }

        ndtmsg = nlmsg_data(nlh);
        read_lock(&neigh_tbl_lock);
        for (tbl = neigh_tables; tbl; tbl = tbl->next) {
                if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family)
                        continue;

                if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0)
                        break;
        }

        if (tbl == NULL) {
                err = -ENOENT;
                goto errout_locked;
        }

        /*
         * We acquire tbl->lock to be nice to the periodic timers and
         * make sure they always see a consistent set of values.
         */
        write_lock_bh(&tbl->lock);

        if (tb[NDTA_PARMS]) {
                struct nlattr *tbp[NDTPA_MAX+1];
                struct neigh_parms *p;
                int i, ifindex = 0;

                err = nla_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS],
                                       nl_ntbl_parm_policy);
                if (err < 0)
                        goto errout_tbl_lock;

                if (tbp[NDTPA_IFINDEX])
                        ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]);

                p = lookup_neigh_params(tbl, ifindex);
                if (p == NULL) {
                        err = -ENOENT;
                        goto errout_tbl_lock;
                }

                for (i = 1; i <= NDTPA_MAX; i++) {
                        if (tbp[i] == NULL)
                                continue;

                        switch (i) {
                        case NDTPA_QUEUE_LEN:
                                p->queue_len = nla_get_u32(tbp[i]);
                                break;
                        case NDTPA_PROXY_QLEN:
                                p->proxy_qlen = nla_get_u32(tbp[i]);
                                break;
                        case NDTPA_APP_PROBES:
                                p->app_probes = nla_get_u32(tbp[i]);
                                break;
                        case NDTPA_UCAST_PROBES:
                                p->ucast_probes = nla_get_u32(tbp[i]);
                                break;
                        case NDTPA_MCAST_PROBES:
                                p->mcast_probes = nla_get_u32(tbp[i]);
                                break;
                        case NDTPA_BASE_REACHABLE_TIME:
                                p->base_reachable_time = nla_get_msecs(tbp[i]);
                                break;
                        case NDTPA_GC_STALETIME:
                                p->gc_staletime = nla_get_msecs(tbp[i]);
                                break;
                        case NDTPA_DELAY_PROBE_TIME:
                                p->delay_probe_time = nla_get_msecs(tbp[i]);
                                break;
                        case NDTPA_RETRANS_TIME:
                                p->retrans_time = nla_get_msecs(tbp[i]);
                                break;
                        case NDTPA_ANYCAST_DELAY:
                                p->anycast_delay = nla_get_msecs(tbp[i]);
                                break;
                        case NDTPA_PROXY_DELAY:
                                p->proxy_delay = nla_get_msecs(tbp[i]);
                                break;
                        case NDTPA_LOCKTIME:
                                p->locktime = nla_get_msecs(tbp[i]);
                                break;
                        }
                }
        }

        if (tb[NDTA_THRESH1])
                tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]);

        if (tb[NDTA_THRESH2])
                tbl->gc_thresh2 = nla_get_u32(tb[NDTA_THRESH2]);

        if (tb[NDTA_THRESH3])
                tbl->gc_thresh3 = nla_get_u32(tb[NDTA_THRESH3]);

        if (tb[NDTA_GC_INTERVAL])
                tbl->gc_interval = nla_get_msecs(tb[NDTA_GC_INTERVAL]);

        err = 0;

errout_tbl_lock:
        write_unlock_bh(&tbl->lock);
errout_locked:
        read_unlock(&neigh_tbl_lock);
errout:
        return err;
}

static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
{
        int family, tidx, nidx = 0;
        int tbl_skip = cb->args[0];
        int neigh_skip = cb->args[1];
        struct neigh_table *tbl;

        family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;

        read_lock(&neigh_tbl_lock);
        for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) {
                struct neigh_parms *p;

                if (tidx < tbl_skip || (family && tbl->family != family))
                        continue;

                if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).pid,
                                       cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL,
                                       NLM_F_MULTI) <= 0)
                        break;

                for (nidx = 0, p = tbl->parms.next; p; p = p->next, nidx++) {
                        if (nidx < neigh_skip)
                                continue;

                        if (neightbl_fill_param_info(skb, tbl, p,
                                                     NETLINK_CB(cb->skb).pid,
                                                     cb->nlh->nlmsg_seq,
                                                     RTM_NEWNEIGHTBL,
                                                     NLM_F_MULTI) <= 0)
                                goto out;
                }

                neigh_skip = 0;
        }
out:
        read_unlock(&neigh_tbl_lock);
        cb->args[0] = tidx;
        cb->args[1] = nidx;

        return skb->len;
}

static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
                           u32 pid, u32 seq, int type, unsigned int flags)
{
        unsigned long now = jiffies;
        struct nda_cacheinfo ci;
        struct nlmsghdr *nlh;
        struct ndmsg *ndm;

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

        ndm = nlmsg_data(nlh);
        ndm->ndm_family  = neigh->ops->family;
        ndm->ndm_pad1    = 0;
        ndm->ndm_pad2    = 0;
        ndm->ndm_flags   = neigh->flags;
        ndm->ndm_type    = neigh->type;
        ndm->ndm_ifindex = neigh->dev->ifindex;

        NLA_PUT(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key);

        read_lock_bh(&neigh->lock);
        ndm->ndm_state   = neigh->nud_state;
        if ((neigh->nud_state & NUD_VALID) &&
            nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, neigh->ha) < 0) {
                read_unlock_bh(&neigh->lock);
                goto nla_put_failure;
        }

        ci.ndm_used      = now - neigh->used;
        ci.ndm_confirmed = now - neigh->confirmed;
        ci.ndm_updated   = now - neigh->updated;
        ci.ndm_refcnt    = atomic_read(&neigh->refcnt) - 1;
        read_unlock_bh(&neigh->lock);

        NLA_PUT_U32(skb, NDA_PROBES, atomic_read(&neigh->probes));
        NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci);