aboutsummaryrefslogblamecommitdiffstats
path: root/net/core/neighbour.c
blob: 0c8666872d10fdf0d90fea6b327952c6f6493051 (plain) (tree)
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270

































                                                                          
                         



























                                                                          
                     
                                                  
      














































































































                                                                          
                                                                            


              


































                                                                         
 
 










                                                                      






































































































































































































































































































































































                                                                                  

                                                        

























































































































                                                                              




                                                                           
                             

         































                                                                                          
                                                 




                                                                         
                                                 






                                                                                        
                                                 




                                                                               
                                                 












                                                                     
                                         


















                                                                                

                                                      

                                                    







































                                                                               
                                                 
                                          
                                                        

                                                      
                                                 









                                                               
                                         

                                                                          
















































































































































                                                                                
                                                          
                                                                         

                                                                               







































































































































































































                                                                               
                                                             





























                                                                         


                                                 


























                                                                              







                                                                           





























                                                                            

                                                    












































































































































































































































                                                                                

                                                                              


                                         































                                                                            

                                                                               
 
                                 


                                          

                                
































                                                                                
                                   

                                                    






































                                                                                

                                                                               
 
                                 


                                          

                                














































































































































































                                                                                

                                                                    
                                                                           





                                     

                                                                      

                                            
                                          

                             















































                                                                                

                                                                






















































































































































































































































































































































                                                                                                               
                                                                                                                                                                       































































                                                                       
                                                                 




                                                                  

                                                                   










                                                           
                                                                 



                                                                  

                                                                   












































































































































































































































                                                                        
                                                        





































































                                                                       

                                  







                                       
/*
 *	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/config.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/sched.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/times.h>
#include <net/neighbour.h>
#include <net/dst.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/random.h>
#include <linux/string.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);
#ifdef CONFIG_ARPD
static void neigh_app_notify(struct neighbour *n);
#endif
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 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;
}

/*
 * 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_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_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_alloc(tbl->kmem_cachep, SLAB_ATOMIC);
	if (!n)
		goto out_entries;

	memset(n, 0, tbl->entry_size);

	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 = kmalloc(size, GFP_ATOMIC);
	} else {
		ret = (struct neighbour **)
			__get_free_pages(GFP_ATOMIC, get_order(size));
	}
	if (ret)
		memset(ret, 0, 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(new_entries & (new_entries - 1));
	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) & tbl->hash_mask;
	
	NEIGH_CACHE_STAT_INC(tbl, lookups);

	read_lock_bh(&tbl->lock);
	for (n = tbl->hash_buckets[hash_val]; 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) & tbl->hash_mask;

	NEIGH_CACHE_STAT_INC(tbl, lookups);

	read_lock_bh(&tbl->lock);
	for (n = tbl->hash_buckets[hash_val]; 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;

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

	if (neigh->parms->neigh_destructor)
		(neigh->parms->neigh_destructor)(neigh);

	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_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;

 	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);
		}
	} 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);
			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);
	}

#ifdef CONFIG_ARPD
	if (notify && neigh->parms->app_probes)
		neigh_app_notify(neigh);
#endif
	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 __inline__ void neigh_update_hhs(struct neighbour *neigh)
{
	struct hh_cache *hh;
	void (*update)(struct hh_cache*, struct net_device*, unsigned char *) =
		neigh->dev->header_cache_update;

	if (update) {
		for (hh = neigh->hh; hh; hh = hh->hh_next) {
			write_lock_bh(&hh->hh_lock);
			update(hh, neigh->dev, neigh->ha);
			write_unlock_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;
#ifdef CONFIG_ARPD
	int notify = 0;
#endif
	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;
#ifdef CONFIG_ARPD
		notify = old & NUD_VALID;
#endif
		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);
#ifdef CONFIG_ARPD
		notify = 1;
#endif
	}
	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);
#ifdef CONFIG_ARPD
	if (notify && neigh->parms->app_probes)
		neigh_app_notify(neigh);
#endif
	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,
			  u16 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 = kmalloc(sizeof(*hh), GFP_ATOMIC)) != NULL) {
		memset(hh, 0, sizeof(struct hh_cache));
		rwlock_init(&hh->hh_lock);
		hh->hh_type = protocol;
		atomic_set(&hh->hh_refcnt, 0);
		hh->hh_next = NULL;
		if (dev->hard_header_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->nh.raw - skb->data);

	if (dev->hard_header &&
	    dev->hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
		    	     skb->len) < 0 &&
	    dev->rebuild_header(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->nh.raw - skb->data);

	if (!neigh_event_send(neigh, skb)) {
		int err;
		struct net_device *dev = neigh->dev;
		if (dev->hard_header_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->nh.raw - skb->data);

	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 = kmalloc(sizeof(*p), GFP_KERNEL);

	if (p) {
		memcpy(p, &tbl->parms, sizeof(*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);
}


void neigh_table_init(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,
						     NULL, NULL);

	if (!tbl->kmem_cachep)
		panic("cannot create neighbour cache");

	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, 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 = kmalloc(phsize, GFP_KERNEL);

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

	memset(tbl->phash_buckets, 0, phsize);

	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(&tbl->proxy_queue);

	tbl->last_flush = now;
	tbl->last_rand	= now + tbl->parms.reachable_time * 20;
	write_lock(&neigh_tbl_lock);
	tbl->next	= neigh_tables;
	neigh_tables	= tbl;
	write_unlock(&neigh_tbl_lock);
}

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;

	return 0;
}

int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct ndmsg *ndm = NLMSG_DATA(nlh);
	struct rtattr **nda = arg;
	struct neigh_table *tbl;
	struct net_device *dev = NULL;
	int err = -ENODEV;

	if (ndm->ndm_ifindex &&
	    (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL)
		goto out;

	read_lock(&neigh_tbl_lock);
	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
		struct rtattr *dst_attr = nda[NDA_DST - 1];
		struct neighbour *n;

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

		err = -EINVAL;
		if (!dst_attr || RTA_PAYLOAD(dst_attr) < tbl->key_len)
			goto out_dev_put;

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

		if (!dev)
			goto out;

		n = neigh_lookup(tbl, RTA_DATA(dst_attr), dev);
		if (n) {
			err = neigh_update(n, NULL, NUD_FAILED, 
					   NEIGH_UPDATE_F_OVERRIDE|
					   NEIGH_UPDATE_F_ADMIN);
			neigh_release(n);
		}
		goto out_dev_put;
	}
	read_unlock(&neigh_tbl_lock);
	err = -EADDRNOTAVAIL;
out_dev_put:
	if (dev)
		dev_put(dev);
out:
	return err;
}

int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct ndmsg *ndm = NLMSG_DATA(nlh);
	struct rtattr **nda = arg;
	struct neigh_table *tbl;
	struct net_device *dev = NULL;
	int err = -ENODEV;

	if (ndm->ndm_ifindex &&
	    (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL)
		goto out;

	read_lock(&neigh_tbl_lock);
	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
		struct rtattr *lladdr_attr = nda[NDA_LLADDR - 1];
		struct rtattr *dst_attr = nda[NDA_DST - 1];
		int override = 1;
		struct neighbour *n;

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

		err = -EINVAL;
		if (!dst_attr || RTA_PAYLOAD(dst_attr) < tbl->key_len)
			goto out_dev_put;

		if (ndm->ndm_flags & NTF_PROXY) {
			err = -ENOBUFS;
			if (pneigh_lookup(tbl, RTA_DATA(dst_attr), dev, 1))
				err = 0;
			goto out_dev_put;
		}

		err = -EINVAL;
		if (!dev)
			goto out;
		if (lladdr_attr && RTA_PAYLOAD(lladdr_attr) < dev->addr_len)
			goto out_dev_put;
	
		n = neigh_lookup(tbl, RTA_DATA(dst_attr), dev);
		if (n) {
			if (nlh->nlmsg_flags & NLM_F_EXCL) {
				err = -EEXIST;
				neigh_release(n);
				goto out_dev_put;
			}
			
			override = nlh->nlmsg_flags & NLM_F_REPLACE;
		} else if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
			err = -ENOENT;
			goto out_dev_put;
		} else {
			n = __neigh_lookup_errno(tbl, RTA_DATA(dst_attr), dev);
			if (IS_ERR(n)) {
				err = PTR_ERR(n);
				goto out_dev_put;
			}
		}

		err = neigh_update(n,
				   lladdr_attr ? RTA_DATA(lladdr_attr) : NULL,
				   ndm->ndm_state,
				   (override ? NEIGH_UPDATE_F_OVERRIDE : 0) |
				   NEIGH_UPDATE_F_ADMIN);

		neigh_release(n);
		goto out_dev_put;
	}

	read_unlock(&neigh_tbl_lock);
	err = -EADDRNOTAVAIL;
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 rtattr *nest = NULL;
	
	nest = RTA_NEST(skb, NDTA_PARMS);

	if (parms->dev)
		RTA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex);

	RTA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt));
	RTA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len);
	RTA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen);
	RTA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes);
	RTA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes);
	RTA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes);
	RTA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time);
	RTA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME,
		      parms->base_reachable_time);
	RTA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime);
	RTA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time);
	RTA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time);
	RTA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay);
	RTA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay);
	RTA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime);

	return RTA_NEST_END(skb, nest);

rtattr_failure:
	return RTA_NEST_CANCEL(skb, nest);
}

static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb,
			      struct netlink_callback *cb)
{
	struct nlmsghdr *nlh;
	struct ndtmsg *ndtmsg;

	nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg),
			       NLM_F_MULTI);

	ndtmsg = NLMSG_DATA(nlh);

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

	RTA_PUT_STRING(skb, NDTA_NAME, tbl->id);
	RTA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval);
	RTA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1);
	RTA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2);
	RTA_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,
		};

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

	{
		int cpu;
		struct ndt_stats ndst;

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

		for_each_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;
		}

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

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

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

rtattr_failure:
	read_unlock_bh(&tbl->lock);
	return NLMSG_CANCEL(skb, nlh);
 
nlmsg_failure:
	return -1;
}

static int neightbl_fill_param_info(struct neigh_table *tbl,
				    struct neigh_parms *parms,
				    struct sk_buff *skb,
				    struct netlink_callback *cb)
{
	struct ndtmsg *ndtmsg;
	struct nlmsghdr *nlh;

	nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg),
			       NLM_F_MULTI);

	ndtmsg = NLMSG_DATA(nlh);

	read_lock_bh(&tbl->lock);
	ndtmsg->ndtm_family = tbl->family;
	ndtmsg->ndtm_pad1   = 0;
	ndtmsg->ndtm_pad2   = 0;
	RTA_PUT_STRING(skb, NDTA_NAME, tbl->id);

	if (neightbl_fill_parms(skb, parms) < 0)
		goto rtattr_failure;

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

rtattr_failure:
	read_unlock_bh(&tbl->lock);
	return NLMSG_CANCEL(skb, nlh);

nlmsg_failure:
	return -1;
}
 
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;
}

int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct neigh_table *tbl;
	struct ndtmsg *ndtmsg = NLMSG_DATA(nlh);
	struct rtattr **tb = arg;
	int err = -EINVAL;

	if (!tb[NDTA_NAME - 1] || !RTA_PAYLOAD(tb[NDTA_NAME - 1]))
		return -EINVAL;

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

		if (!rtattr_strcmp(tb[NDTA_NAME - 1], tbl->id))
			break;
	}

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

	/* 
	 * 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_THRESH1 - 1])
		tbl->gc_thresh1 = RTA_GET_U32(tb[NDTA_THRESH1 - 1]);

	if (tb[NDTA_THRESH2 - 1])
		tbl->gc_thresh2 = RTA_GET_U32(tb[NDTA_THRESH2 - 1]);

	if (tb[NDTA_THRESH3 - 1])
		tbl->gc_thresh3 = RTA_GET_U32(tb[NDTA_THRESH3 - 1]);

	if (tb[NDTA_GC_INTERVAL - 1])
		tbl->gc_interval = RTA_GET_MSECS(tb[NDTA_GC_INTERVAL - 1]);

	if (tb[NDTA_PARMS - 1]) {
		struct rtattr *tbp[NDTPA_MAX];
		struct neigh_parms *p;
		u32 ifindex = 0;

		if (rtattr_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS - 1]) < 0)
			goto rtattr_failure;

		if (tbp[NDTPA_IFINDEX - 1])
			ifindex = RTA_GET_U32(tbp[NDTPA_IFINDEX - 1]);

		p = lookup_neigh_params(tbl, ifindex);
		if (p == NULL) {
			err = -ENOENT;
			goto rtattr_failure;
		}
	
		if (tbp[NDTPA_QUEUE_LEN - 1])
			p->queue_len = RTA_GET_U32(tbp[NDTPA_QUEUE_LEN - 1]);

		if (tbp[NDTPA_PROXY_QLEN - 1])
			p->proxy_qlen = RTA_GET_U32(tbp[NDTPA_PROXY_QLEN - 1]);

		if (tbp[NDTPA_APP_PROBES - 1])
			p->app_probes = RTA_GET_U32(tbp[NDTPA_APP_PROBES - 1]);

		if (tbp[NDTPA_UCAST_PROBES - 1])
			p->ucast_probes =
			   RTA_GET_U32(tbp[NDTPA_UCAST_PROBES - 1]);

		if (tbp[NDTPA_MCAST_PROBES - 1])
			p->mcast_probes =
			   RTA_GET_U32(tbp[NDTPA_MCAST_PROBES - 1]);

		if (tbp[NDTPA_BASE_REACHABLE_TIME - 1])
			p->base_reachable_time =
			   RTA_GET_MSECS(tbp[NDTPA_BASE_REACHABLE_TIME - 1]);

		if (tbp[NDTPA_GC_STALETIME - 1])
			p->gc_staletime =
			   RTA_GET_MSECS(tbp[NDTPA_GC_STALETIME - 1]);

		if (tbp[NDTPA_DELAY_PROBE_TIME - 1])
			p->delay_probe_time =
			   RTA_GET_MSECS(tbp[NDTPA_DELAY_PROBE_TIME - 1]);

		if (tbp[NDTPA_RETRANS_TIME - 1])
			p->retrans_time =
			   RTA_GET_MSECS(tbp[NDTPA_RETRANS_TIME - 1]);

		if (tbp[NDTPA_ANYCAST_DELAY - 1])
			p->anycast_delay =
			   RTA_GET_MSECS(tbp[NDTPA_ANYCAST_DELAY - 1]);

		if (tbp[NDTPA_PROXY_DELAY - 1])
			p->proxy_delay =
			   RTA_GET_MSECS(tbp[NDTPA_PROXY_DELAY - 1]);

		if (tbp[NDTPA_LOCKTIME - 1])
			p->locktime = RTA_GET_MSECS(tbp[NDTPA_LOCKTIME - 1]);
	}

	err = 0;

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

int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
{
	int idx, family;
	int s_idx = cb->args[0];
	struct neigh_table *tbl;

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

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

		if (idx < s_idx || (family && tbl->family != family))
			continue;

		if (neightbl_fill_info(tbl, skb, cb) <= 0)
			break;

		for (++idx, p = tbl->parms.next; p; p = p->next, idx++) {
			if (idx < s_idx)
				continue;

			if (neightbl_fill_param_info(tbl, p, skb, cb) <= 0)
				goto out;
		}

	}
out:
	read_unlock(&neigh_tbl_lock);
	cb->args[0] = idx;

	return skb->len;
}

static int neigh_fill_info(struct sk_buff *skb, struct neighbour *n,
			   u32 pid, u32 seq, int event, unsigned int flags)
{
	unsigned long now = jiffies;
	unsigned char *b = skb->tail;
	struct nda_cacheinfo ci;
	int locked = 0;
	u32 probes;
	struct nlmsghdr *nlh = NLMSG_NEW(skb, pid, seq, event,
					 sizeof(struct ndmsg), flags);
	struct ndmsg *ndm = NLMSG_DATA(nlh);

	ndm->ndm_family	 = n->ops->family;
	ndm->ndm_pad1    = 0;
	ndm->ndm_pad2    = 0;
	ndm->ndm_flags	 = n->flags;
	ndm->ndm_type	 = n->type;
	ndm->ndm_ifindex = n->dev->ifindex;
	RTA_PUT(skb, NDA_DST, n->tbl->key_len, n->primary_key);
	read_lock_bh(&n->lock);
	locked		 = 1;
	ndm->ndm_state	 = n->nud_state;
	if (n->nud_state & NUD_VALID)
		RTA_PUT(skb, NDA_LLADDR, n->dev->addr_len, n->ha);
	ci.ndm_used	 = now - n->used;
	ci.ndm_confirmed = now - n->confirmed;
	ci.ndm_updated	 = now - n->updated;
	ci.ndm_refcnt	 = atomic_read(&n->refcnt) - 1;
	probes = atomic_read(&n->probes);
	read_unlock_bh(&n->lock);
	locked		 = 0;
	RTA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci);
	RTA_PUT(skb, NDA_PROBES, sizeof(probes), &probes);
	nlh->nlmsg_len	 = skb->tail - b;
	return skb->len;

nlmsg_failure:
rtattr_failure:
	if (locked)
		read_unlock_bh(&n->lock);
	skb_trim(skb, b - skb->data);
	return -1;
}


static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
			    struct netlink_callback *cb)
{
	struct neighbour *n;
	int rc, h, s_h = cb->args[1];
	int idx, s_idx = idx = cb->args[2];

	for (h = 0; h <= tbl->hash_mask; h++) {
		if (h < s_h)
			continue;
		if (h > s_h)
			s_idx = 0;
		read_lock_bh(&tbl->lock);
		for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next, idx++) {
			if (idx < s_idx)
				continue;
			if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid,
					    cb->nlh->nlmsg_seq,
					    RTM_NEWNEIGH,
					    NLM_F_MULTI) <= 0) {
				read_unlock_bh(&tbl->lock);
				rc = -1;
				goto out;
			}
		}
		read_unlock_bh(&tbl->lock);
	}
	rc = skb->len;
out:
	cb->args[1] = h;
	cb->args[2] = idx;
	return rc;
}

int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct neigh_table *tbl;
	int t, family, s_t;

	read_lock(&neigh_tbl_lock);
	family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family;
	s_t = cb->args[0];

	for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) {
		if (t < s_t || (family && tbl->family != family))
			continue;
		if (t > s_t)
			memset(&cb->args[1], 0, sizeof(cb->args) -
						sizeof(cb->args[0]));
		if (neigh_dump_table(tbl, skb, cb) < 0)
			break;
	}
	read_unlock(&neigh_tbl_lock);

	cb->args[0] = t;
	return skb->len;
}

void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie)
{
	int chain;

	read_lock_bh(&tbl->lock);
	for (chain = 0; chain <= tbl->hash_mask; chain++) {
		struct neighbour *n;

		for (n = tbl->hash_buckets[chain]; n; n = n->next)
			cb(n, cookie);
	}
	read_unlock_bh(&tbl->lock);
}
EXPORT_SYMBOL(neigh_for_each);

/* The tbl->lock must be held as a writer and BH disabled. */
void __neigh_for_each_release(struct neigh_table *tbl,
			      int (*cb)(struct neighbour *))
{
	int chain;

	for (chain = 0; chain <= tbl->hash_mask; chain++) {
		struct neighbour *n, **np;

		np = &tbl->hash_buckets[chain];
		while ((n = *np) != NULL) {
			int release;

			write_lock(&n->lock);
			release = cb(n);
			if (release) {
				*np = n->next;
				n->dead = 1;
			} else
				np = &n->next;
			write_unlock(&n->lock);
			if (release)
				neigh_release(n);
		}
	}
}
EXPORT_SYMBOL(__neigh_for_each_release);

#ifdef CONFIG_PROC_FS

static struct neighbour *neigh_get_first(struct seq_file *seq)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;
	struct neighbour *n = NULL;
	int bucket = state->bucket;

	state->flags &= ~NEIGH_SEQ_IS_PNEIGH;
	for (bucket = 0; bucket <= tbl->hash_mask; bucket++) {
		n = tbl->hash_buckets[bucket];

		while (n) {
			if (state->neigh_sub_iter) {
				loff_t fakep = 0;
				void *v;

				v = state->neigh_sub_iter(state, n, &fakep);
				if (!v)
					goto next;
			}
			if (!(state->flags & NEIGH_SEQ_SKIP_NOARP))
				break;
			if (n->nud_state & ~NUD_NOARP)
				break;
		next:
			n = n->next;
		}

		if (n)
			break;
	}
	state->bucket = bucket;

	return n;
}

static struct neighbour *neigh_get_next(struct seq_file *seq,
					struct neighbour *n,
					loff_t *pos)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;

	if (state->neigh_sub_iter) {
		void *v = state->neigh_sub_iter(state, n, pos);
		if (v)
			return n;
	}
	n = n->next;

	while (1) {
		while (n) {
			if (state->neigh_sub_iter) {
				void *v = state->neigh_sub_iter(state, n, pos);
				if (v)
					return n;
				goto next;
			}
			if (!(state->flags & NEIGH_SEQ_SKIP_NOARP))
				break;

			if (n->nud_state & ~NUD_NOARP)
				break;
		next:
			n = n->next;
		}

		if (n)
			break;

		if (++state->bucket > tbl->hash_mask)
			break;

		n = tbl->hash_buckets[state->bucket];
	}

	if (n && pos)
		--(*pos);
	return n;
}

static struct neighbour *neigh_get_idx(struct seq_file *seq, loff_t *pos)
{
	struct neighbour *n = neigh_get_first(seq);

	if (n) {
		while (*pos) {
			n = neigh_get_next(seq, n, pos);
			if (!n)
				break;
		}
	}
	return *pos ? NULL : n;
}

static struct pneigh_entry *pneigh_get_first(struct seq_file *seq)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;
	struct pneigh_entry *pn = NULL;
	int bucket = state->bucket;

	state->flags |= NEIGH_SEQ_IS_PNEIGH;
	for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) {
		pn = tbl->phash_buckets[bucket];
		if (pn)
			break;
	}
	state->bucket = bucket;

	return pn;
}

static struct pneigh_entry *pneigh_get_next(struct seq_file *seq,
					    struct pneigh_entry *pn,
					    loff_t *pos)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;

	pn = pn->next;
	while (!pn) {
		if (++state->bucket > PNEIGH_HASHMASK)
			break;
		pn = tbl->phash_buckets[state->bucket];
		if (pn)
			break;
	}

	if (pn && pos)
		--(*pos);

	return pn;
}

static struct pneigh_entry *pneigh_get_idx(struct seq_file *seq, loff_t *pos)
{
	struct pneigh_entry *pn = pneigh_get_first(seq);

	if (pn) {
		while (*pos) {
			pn = pneigh_get_next(seq, pn, pos);
			if (!pn)
				break;
		}
	}
	return *pos ? NULL : pn;
}

static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos)
{
	struct neigh_seq_state *state = seq->private;
	void *rc;

	rc = neigh_get_idx(seq, pos);
	if (!rc && !(state->flags & NEIGH_SEQ_NEIGH_ONLY))
		rc = pneigh_get_idx(seq, pos);

	return rc;
}

void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags)
{
	struct neigh_seq_state *state = seq->private;
	loff_t pos_minus_one;

	state->tbl = tbl;
	state->bucket = 0;
	state->flags = (neigh_seq_flags & ~NEIGH_SEQ_IS_PNEIGH);

	read_lock_bh(&tbl->lock);

	pos_minus_one = *pos - 1;
	return *pos ? neigh_get_idx_any(seq, &pos_minus_one) : SEQ_START_TOKEN;
}
EXPORT_SYMBOL(neigh_seq_start);

void *neigh_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct neigh_seq_state *state;
	void *rc;

	if (v == SEQ_START_TOKEN) {
		rc = neigh_get_idx(seq, pos);
		goto out;
	}

	state = seq->private;
	if (!(state->flags & NEIGH_SEQ_IS_PNEIGH)) {
		rc = neigh_get_next(seq, v, NULL);
		if (rc)
			goto out;
		if (!(state->flags & NEIGH_SEQ_NEIGH_ONLY))
			rc = pneigh_get_first(seq);
	} else {
		BUG_ON(state->flags & NEIGH_SEQ_NEIGH_ONLY);
		rc = pneigh_get_next(seq, v, NULL);
	}
out:
	++(*pos);
	return rc;
}
EXPORT_SYMBOL(neigh_seq_next);

void neigh_seq_stop(struct seq_file *seq, void *v)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;

	read_unlock_bh(&tbl->lock);
}
EXPORT_SYMBOL(neigh_seq_stop);

/* statistics via seq_file */

static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct proc_dir_entry *pde = seq->private;
	struct neigh_table *tbl = pde->data;
	int cpu;

	if (*pos == 0)
		return SEQ_START_TOKEN;
	
	for (cpu = *pos-1; cpu < NR_CPUS; ++cpu) {
		if (!cpu_possible(cpu))
			continue;
		*pos = cpu+1;
		return per_cpu_ptr(tbl->stats, cpu);
	}
	return NULL;
}

static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct proc_dir_entry *pde = seq->private;
	struct neigh_table *tbl = pde->data;
	int cpu;

	for (cpu = *pos; cpu < NR_CPUS; ++cpu) {
		if (!cpu_possible(cpu))
			continue;
		*pos = cpu+1;
		return per_cpu_ptr(tbl->stats, cpu);
	}
	return NULL;
}

static void neigh_stat_seq_stop(struct seq_file *seq, void *v)
{

}

static int neigh_stat_seq_show(struct seq_file *seq, void *v)
{
	struct proc_dir_entry *pde = seq->private;
	struct neigh_table *tbl = pde->data;
	struct neigh_statistics *st = v;

	if (v == SEQ_START_TOKEN) {
		seq_printf(seq, "entries  allocs destroys hash_grows  lookups hits  res_failed  rcv_probes_mcast rcv_probes_ucast  periodic_gc_runs forced_gc_runs\n");
		return 0;
	}

	seq_printf(seq, "%08x  %08lx %08lx %08lx  %08lx %08lx  %08lx  "
			"%08lx %08lx  %08lx %08lx\n",
		   atomic_read(&tbl->entries),

		   st->allocs,
		   st->destroys,
		   st->hash_grows,

		   st->lookups,
		   st->hits,

		   st->res_failed,

		   st->rcv_probes_mcast,
		   st->rcv_probes_ucast,

		   st->periodic_gc_runs,
		   st->forced_gc_runs
		   );

	return 0;
}

static struct seq_operations neigh_stat_seq_ops = {
	.start	= neigh_stat_seq_start,
	.next	= neigh_stat_seq_next,
	.stop	= neigh_stat_seq_stop,
	.show	= neigh_stat_seq_show,
};

static int neigh_stat_seq_open(struct inode *inode, struct file *file)
{
	int ret = seq_open(file, &neigh_stat_seq_ops);

	if (!ret) {
		struct seq_file *sf = file->private_data;
		sf->private = PDE(inode);
	}
	return ret;
};

static struct file_operations neigh_stat_seq_fops = {
	.owner	 = THIS_MODULE,
	.open 	 = neigh_stat_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release,
};

#endif /* CONFIG_PROC_FS */

#ifdef CONFIG_ARPD
void neigh_app_ns(struct neighbour *n)
{
	struct nlmsghdr  *nlh;
	int size = NLMSG_SPACE(sizeof(struct ndmsg) + 256);
	struct sk_buff *skb = alloc_skb(size, GFP_ATOMIC);

	if (!skb)
		return;

	if (neigh_fill_info(skb, n, 0, 0, RTM_GETNEIGH, 0) < 0) {
		kfree_skb(skb);
		return;
	}
	nlh			   = (struct nlmsghdr *)skb->data;
	nlh->nlmsg_flags	   = NLM_F_REQUEST;
	NETLINK_CB(skb).dst_group  = RTNLGRP_NEIGH;
	netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC);
}

static void neigh_app_notify(struct neighbour *n)
{
	struct nlmsghdr *nlh;
	int size = NLMSG_SPACE(sizeof(struct ndmsg) + 256);
	struct sk_buff *skb = alloc_skb(size, GFP_ATOMIC);

	if (!skb)
		return;

	if (neigh_fill_info(skb, n, 0, 0, RTM_NEWNEIGH, 0) < 0) {
		kfree_skb(skb);
		return;
	}
	nlh			   = (struct nlmsghdr *)skb->data;
	NETLINK_CB(skb).dst_group  = RTNLGRP_NEIGH;
	netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC);
}

#endif /* CONFIG_ARPD */

#ifdef CONFIG_SYSCTL

static struct neigh_sysctl_table {
	struct ctl_table_header *sysctl_header;
	ctl_table		neigh_vars[__NET_NEIGH_MAX];
	ctl_table		neigh_dev[2];
	ctl_table		neigh_neigh_dir[2];
	ctl_table		neigh_proto_dir[2];
	ctl_table		neigh_root_dir[2];
} neigh_sysctl_template = {
	.neigh_vars = {
		{
			.ctl_name	= NET_NEIGH_MCAST_SOLICIT,
			.procname	= "mcast_solicit",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_UCAST_SOLICIT,
			.procname	= "ucast_solicit",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_APP_SOLICIT,
			.procname	= "app_solicit",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_RETRANS_TIME,
			.procname	= "retrans_time",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_userhz_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_REACHABLE_TIME,
			.procname	= "base_reachable_time",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_jiffies,
			.strategy	= &sysctl_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_DELAY_PROBE_TIME,
			.procname	= "delay_first_probe_time",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_jiffies,
			.strategy	= &sysctl_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_GC_STALE_TIME,
			.procname	= "gc_stale_time",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_jiffies,
			.strategy	= &sysctl_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_UNRES_QLEN,
			.procname	= "unres_qlen",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_PROXY_QLEN,
			.procname	= "proxy_qlen",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_ANYCAST_DELAY,
			.procname	= "anycast_delay",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_userhz_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_PROXY_DELAY,
			.procname	= "proxy_delay",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_userhz_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_LOCKTIME,
			.procname	= "locktime",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_userhz_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_GC_INTERVAL,
			.procname	= "gc_interval",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_jiffies,
			.strategy	= &sysctl_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_GC_THRESH1,
			.procname	= "gc_thresh1",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_GC_THRESH2,
			.procname	= "gc_thresh2",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_GC_THRESH3,
			.procname	= "gc_thresh3",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec,
		},
		{
			.ctl_name	= NET_NEIGH_RETRANS_TIME_MS,
			.procname	= "retrans_time_ms",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_ms_jiffies,
			.strategy	= &sysctl_ms_jiffies,
		},
		{
			.ctl_name	= NET_NEIGH_REACHABLE_TIME_MS,
			.procname	= "base_reachable_time_ms",
			.maxlen		= sizeof(int),
			.mode		= 0644,
			.proc_handler	= &proc_dointvec_ms_jiffies,
			.strategy	= &sysctl_ms_jiffies,
		},
	},
	.neigh_dev = {
		{
			.ctl_name	= NET_PROTO_CONF_DEFAULT,
			.procname	= "default",
			.mode		= 0555,
		},
	},
	.neigh_neigh_dir = {
		{
			.procname	= "neigh",
			.mode		= 0555,
		},
	},
	.neigh_proto_dir = {
		{
			.mode		= 0555,
		},
	},
	.neigh_root_dir = {
		{
			.ctl_name	= CTL_NET,
			.procname	= "net",
			.mode		= 0555,
		},
	},
};

int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
			  int p_id, int pdev_id, char *p_name, 
			  proc_handler *handler, ctl_handler *strategy)
{
	struct neigh_sysctl_table *t = kmalloc(sizeof(*t), GFP_KERNEL);
	const char *dev_name_source = NULL;
	char *dev_name = NULL;
	int err = 0;

	if (!t)
		return -ENOBUFS;
	memcpy(t, &neigh_sysctl_template, sizeof(*t));
	t->neigh_vars[0].data  = &p->mcast_probes;
	t->neigh_vars[1].data  = &p->ucast_probes;
	t->neigh_vars[2].data  = &p->app_probes;
	t->neigh_vars[3].data  = &p->retrans_time;
	t->neigh_vars[4].data  = &p->base_reachable_time;
	t->neigh_vars[5].data  = &p->delay_probe_time;
	t->neigh_vars[6].data  = &p->gc_staletime;
	t->neigh_vars[7].data  = &p->queue_len;
	t->neigh_vars[8].data  = &p->proxy_qlen;
	t->neigh_vars[9].data  = &p->anycast_delay;
	t->neigh_vars[10].data = &p->proxy_delay;
	t->neigh_vars[11].data = &p->locktime;

	if (dev) {
		dev_name_source = dev->name;
		t->neigh_dev[0].ctl_name = dev->ifindex;
		t->neigh_vars[12].procname = NULL;
		t->neigh_vars[13].procname = NULL;
		t->neigh_vars[14].procname = NULL;
		t->neigh_vars[15].procname = NULL;
	} else {
 		dev_name_source = t->neigh_dev[0].procname;
		t->neigh_vars[12].data = (int *)(p + 1);
		t->neigh_vars[13].data = (int *)(p + 1) + 1;
		t->neigh_vars[14].data = (int *)(p + 1) + 2;
		t->neigh_vars[15].data = (int *)(p + 1) + 3;
	}

	t->neigh_vars[16].data  = &p->retrans_time;
	t->neigh_vars[17].data  = &p->base_reachable_time;

	if (handler || strategy) {
		/* RetransTime */
		t->neigh_vars[3].proc_handler = handler;
		t->neigh_vars[3].strategy = strategy;
		t->neigh_vars[3].extra1 = dev;
		/* ReachableTime */
		t->neigh_vars[4].proc_handler = handler;
		t->neigh_vars[4].strategy = strategy;
		t->neigh_vars[4].extra1 = dev;
		/* RetransTime (in milliseconds)*/
		t->neigh_vars[16].proc_handler = handler;
		t->neigh_vars[16].strategy = strategy;
		t->neigh_vars[16].extra1 = dev;
		/* ReachableTime (in milliseconds) */
		t->neigh_vars[17].proc_handler = handler;
		t->neigh_vars[17].strategy = strategy;
		t->neigh_vars[17].extra1 = dev;
	}

	dev_name = kstrdup(dev_name_source, GFP_KERNEL);
	if (!dev_name) {
		err = -ENOBUFS;
		goto free;
	}

 	t->neigh_dev[0].procname = dev_name;

	t->neigh_neigh_dir[0].ctl_name = pdev_id;

	t->neigh_proto_dir[0].procname = p_name;
	t->neigh_proto_dir[0].ctl_name = p_id;

	t->neigh_dev[0].child	       = t->neigh_vars;
	t->neigh_neigh_dir[0].child    = t->neigh_dev;
	t->neigh_proto_dir[0].child    = t->neigh_neigh_dir;
	t->neigh_root_dir[0].child     = t->neigh_proto_dir;

	t->sysctl_header = register_sysctl_table(t->neigh_root_dir, 0);
	if (!t->sysctl_header) {
		err = -ENOBUFS;
		goto free_procname;
	}
	p->sysctl_table = t;
	return 0;

	/* error path */
 free_procname:
	kfree(dev_name);
 free:
	kfree(t);

	return err;
}

void neigh_sysctl_unregister(struct neigh_parms *p)
{
	if (p->sysctl_table) {
		struct neigh_sysctl_table *t = p->sysctl_table;
		p->sysctl_table = NULL;
		unregister_sysctl_table(t->sysctl_header);
		kfree(t->neigh_dev[0].procname);
		kfree(t);
	}
}

#endif	/* CONFIG_SYSCTL */

EXPORT_SYMBOL(__neigh_event_send);
EXPORT_SYMBOL(neigh_add);
EXPORT_SYMBOL(neigh_changeaddr);
EXPORT_SYMBOL(neigh_compat_output);
EXPORT_SYMBOL(neigh_connected_output);
EXPORT_SYMBOL(neigh_create);
EXPORT_SYMBOL(neigh_delete);
EXPORT_SYMBOL(neigh_destroy);
EXPORT_SYMBOL(neigh_dump_info);
EXPORT_SYMBOL(neigh_event_ns);
EXPORT_SYMBOL(neigh_ifdown);
EXPORT_SYMBOL(neigh_lookup);
EXPORT_SYMBOL(neigh_lookup_nodev);
EXPORT_SYMBOL(neigh_parms_alloc);
EXPORT_SYMBOL(neigh_parms_release);
EXPORT_SYMBOL(neigh_rand_reach_time);
EXPORT_SYMBOL(neigh_resolve_output);
EXPORT_SYMBOL(neigh_table_clear);
EXPORT_SYMBOL(neigh_table_init);
EXPORT_SYMBOL(neigh_update);
EXPORT_SYMBOL(neigh_update_hhs);
EXPORT_SYMBOL(pneigh_enqueue);
EXPORT_SYMBOL(pneigh_lookup);
EXPORT_SYMBOL(neightbl_dump_info);
EXPORT_SYMBOL(neightbl_set);

#ifdef CONFIG_ARPD
EXPORT_SYMBOL(neigh_app_ns);
#endif
#ifdef CONFIG_SYSCTL
EXPORT_SYMBOL(neigh_sysctl_register);
EXPORT_SYMBOL(neigh_sysctl_unregister);
#endif