neighbour.c

/*
 *	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/slab.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/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);

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;
}
EXPORT_SYMBOL(neigh_rand_reach_time);


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

	NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);

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

		np = &nht->hash_buckets[i];
		while ((n = rcu_dereference_protected(*np,
					lockdep_is_held(&tbl->lock))) != 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)) {
				rcu_assign_pointer(*np,
					rcu_dereference_protected(n->next,
						  lockdep_is_held(&tbl->lock)));
				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 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)
{
	int i;
	struct neigh_hash_table *nht;

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

	for (i = 0; i <= nht->hash_mask; 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;
			}
			rcu_assign_pointer(*np,
				   rcu_dereference_protected(n->next,
						lockdep_is_held(&tbl->lock)));
			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);
}
EXPORT_SYMBOL(neigh_changeaddr);

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;
}
EXPORT_SYMBOL(neigh_ifdown);

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);
	seqlock_init(&n->ha_lock);
	n->updated	  = n->used = now;
	n->nud_state	  = NUD_NONE;
	n->output	  = neigh_blackhole;
	n->parms	  = neigh_parms_clone(&tbl->parms);
	setup_timer(&n->timer, neigh_timer_handler, (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 neigh_hash_table *neigh_hash_alloc(unsigned int entries)
{
	size_t size = entries * sizeof(struct neighbour *);
	struct neigh_hash_table *ret;
	struct neighbour **buckets;

	ret = kmalloc(sizeof(*ret), GFP_ATOMIC);
	if (!ret)
		return NULL;
	if (size <= PAGE_SIZE)
		buckets = kzalloc(size, GFP_ATOMIC);
	else
		buckets = (struct neighbour **)
			  __get_free_pages(GFP_ATOMIC | __GFP_ZERO,
					   get_order(size));
	if (!buckets) {
		kfree(ret);
		return NULL;
	}
	rcu_assign_pointer(ret->hash_buckets, buckets);
	ret->hash_mask = entries - 1;
	get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd));
	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 = (nht->hash_mask + 1) * sizeof(struct neighbour *);
	struct neighbour **buckets = nht->hash_buckets;

	if (size <= PAGE_SIZE)
		kfree(buckets);
	else
		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_entries)
{
	unsigned int i, hash;
	struct neigh_hash_table *new_nht, *old_nht;

	NEIGH_CACHE_STAT_INC(tbl, hash_grows);

	BUG_ON(!is_power_of_2(new_entries));
	old_nht = rcu_dereference_protected(tbl->nht,
					    lockdep_is_held(&tbl->lock));
	new_nht = neigh_hash_alloc(new_entries);
	if (!new_nht)
		return old_nht;

	for (i = 0; i <= old_nht->hash_mask; 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 &= new_nht->hash_mask;
			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;
	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, dev, nht->hash_rnd) & nht->hash_mask;

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

	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;
	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) & nht->hash_mask;

	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 (!atomic_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);

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);
	struct neigh_hash_table *nht;

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

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

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

	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, pkey, key_len)) {
			neigh_hold(n1);
			rc = n1;
			goto out_tbl_unlock;
		}
	}

	n->dead = 0;
	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_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;
}
EXPORT_SYMBOL(neigh_create);

static u32 pneigh_hash(const void *pkey, 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,
					      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)
{
	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;
	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;

	write_pnet(&n->net, hold_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);
		release_net(net);
		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;
	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);
			release_net(pneigh_net(n));
			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);
				release_net(pneigh_net(n));
				kfree(n);
				continue;
			}
			np = &n->next;
		}
	}
	return -ENOENT;
}

static void neigh_parms_destroy(struct neigh_parms *parms);

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

static void neigh_destroy_rcu(struct rcu_head *head)
{
	struct neighbour *neigh = container_of(head, struct neighbour, rcu);

	kmem_cache_free(neigh->tbl->kmem_cachep, neigh);
}
/*
 *	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);
		hh_cache_put(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);
	call_rcu(&neigh->rcu, neigh_destroy_rcu);
}
EXPORT_SYMBOL(neigh_destroy);

/* 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_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;
		for (p = &tbl->parms; p; p = p->next)
			p->reachable_time =
				neigh_rand_reach_time(p->base_reachable_time);
	}

	for (i = 0 ; i <= nht->hash_mask; 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)) {
				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(jiffies, 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;
		}
		/*
		 * 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);
	}
	/* 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.
	 */
	schedule_delayed_work(&tbl->gc_work,
			      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 (n->nud_state & NUD_PROBE) ?
		p->ucast_probes :
		p->ucast_probes + p->app_probes + 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_PRINTK2("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);
}

/* 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)) {
		neigh->nud_state = NUD_FAILED;
		notify = 1;
		neigh_invalidate(neigh);
	}

	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 = skb_copy(skb, GFP_ATOMIC);
		write_unlock(&neigh->lock);
		neigh->ops->solicit(neigh, skb);
		atomic_inc(&neigh->probes);
		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_add_timer(neigh, now + 1);
		} 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_PRINTK2("neigh %p is delayed.\n", 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) {