summaryrefslogtreecommitdiff
path: root/pfinet/linux-src/net/ipv4/fib_hash.c
blob: d9e029cef55cee88b0939386018c7cee892ac956 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		IPv4 FIB: lookup engine and maintenance routines.
 *
 * Version:	$Id: fib_hash.c,v 1.8 1999/03/25 10:04:17 davem Exp $
 *
 * Authors:	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.
 */

#include <linux/config.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/init.h>

#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/ip_fib.h>

#define FTprint(a...)
/*
   printk(KERN_DEBUG a)
 */

/*
   These bizarre types are just to force strict type checking.
   When I reversed order of bytes and changed to natural mask lengths,
   I forgot to make fixes in several places. Now I am lazy to return
   it back.
 */

typedef struct {
	u32	datum;
} fn_key_t;

typedef struct {
	u32	datum;
} fn_hash_idx_t;

struct fib_node
{
	struct fib_node		*fn_next;
	struct fib_info		*fn_info;
#define FIB_INFO(f)	((f)->fn_info)
	fn_key_t		fn_key;
	u8			fn_tos;
	u8			fn_type;
	u8			fn_scope;
	u8			fn_state;
};

#define FN_S_ZOMBIE	1
#define FN_S_ACCESSED	2

static int fib_hash_zombies;

struct fn_zone
{
	struct fn_zone	*fz_next;	/* Next not empty zone	*/
	struct fib_node	**fz_hash;	/* Hash table pointer	*/
	int		fz_nent;	/* Number of entries	*/

	int		fz_divisor;	/* Hash divisor		*/
	u32		fz_hashmask;	/* (1<<fz_divisor) - 1	*/
#define FZ_HASHMASK(fz)	((fz)->fz_hashmask)

	int		fz_order;	/* Zone order		*/
	u32		fz_mask;
#define FZ_MASK(fz)	((fz)->fz_mask)
};

/* NOTE. On fast computers evaluation of fz_hashmask and fz_mask
   can be cheaper than memory lookup, so that FZ_* macros are used.
 */

struct fn_hash
{
	struct fn_zone	*fn_zones[33];
	struct fn_zone	*fn_zone_list;
};

static __inline__ fn_hash_idx_t fn_hash(fn_key_t key, struct fn_zone *fz)
{
	u32 h = ntohl(key.datum)>>(32 - fz->fz_order);
	h ^= (h>>20);
	h ^= (h>>10);
	h ^= (h>>5);
	h &= FZ_HASHMASK(fz);
	return *(fn_hash_idx_t*)&h;
}

#define fz_key_0(key)		((key).datum = 0)
#define fz_prefix(key,fz)	((key).datum)

static __inline__ fn_key_t fz_key(u32 dst, struct fn_zone *fz)
{
	fn_key_t k;
	k.datum = dst & FZ_MASK(fz);
	return k;
}

static __inline__ struct fib_node ** fz_chain_p(fn_key_t key, struct fn_zone *fz)
{
	return &fz->fz_hash[fn_hash(key, fz).datum];
}

static __inline__ struct fib_node * fz_chain(fn_key_t key, struct fn_zone *fz)
{
	return fz->fz_hash[fn_hash(key, fz).datum];
}

extern __inline__ int fn_key_eq(fn_key_t a, fn_key_t b)
{
	return a.datum == b.datum;
}

extern __inline__ int fn_key_leq(fn_key_t a, fn_key_t b)
{
	return a.datum <= b.datum;
}

#define FZ_MAX_DIVISOR 1024

#ifdef CONFIG_IP_ROUTE_LARGE_TABLES

static __inline__ void fn_rebuild_zone(struct fn_zone *fz,
					struct fib_node **old_ht,
					int old_divisor)
{
	int i;
	struct fib_node *f, **fp, *next;

	for (i=0; i<old_divisor; i++) {
		for (f=old_ht[i]; f; f=next) {
			next = f->fn_next;
			for (fp = fz_chain_p(f->fn_key, fz);
			     *fp && fn_key_leq((*fp)->fn_key, f->fn_key);
			     fp = &(*fp)->fn_next)
				/* NONE */;
			f->fn_next = *fp;
			*fp = f;
		}
	}
}

static void fn_rehash_zone(struct fn_zone *fz)
{
	struct fib_node **ht, **old_ht;
	int old_divisor, new_divisor;
	u32 new_hashmask;
		
	old_divisor = fz->fz_divisor;

	switch (old_divisor) {
	case 16:
		new_divisor = 256;
		new_hashmask = 0xFF;
		break;
	case 256:
		new_divisor = 1024;
		new_hashmask = 0x3FF;
		break;
	default:
		printk(KERN_CRIT "route.c: bad divisor %d!\n", old_divisor);
		return;
	}
#if RT_CACHE_DEBUG >= 2
	printk("fn_rehash_zone: hash for zone %d grows from %d\n", fz->fz_order, old_divisor);
#endif

	ht = kmalloc(new_divisor*sizeof(struct fib_node*), GFP_KERNEL);

	if (ht)	{
		memset(ht, 0, new_divisor*sizeof(struct fib_node*));
		start_bh_atomic();
		old_ht = fz->fz_hash;
		fz->fz_hash = ht;
		fz->fz_hashmask = new_hashmask;
		fz->fz_divisor = new_divisor;
		fn_rebuild_zone(fz, old_ht, old_divisor);
		end_bh_atomic();
		kfree(old_ht);
	}
}
#endif /* CONFIG_IP_ROUTE_LARGE_TABLES */

static void fn_free_node(struct fib_node * f)
{
	fib_release_info(FIB_INFO(f));
	kfree_s(f, sizeof(struct fib_node));
}


static struct fn_zone *
fn_new_zone(struct fn_hash *table, int z)
{
	int i;
	struct fn_zone *fz = kmalloc(sizeof(struct fn_zone), GFP_KERNEL);
	if (!fz)
		return NULL;

	memset(fz, 0, sizeof(struct fn_zone));
	if (z) {
		fz->fz_divisor = 16;
		fz->fz_hashmask = 0xF;
	} else {
		fz->fz_divisor = 1;
		fz->fz_hashmask = 0;
	}
	fz->fz_hash = kmalloc(fz->fz_divisor*sizeof(struct fib_node*), GFP_KERNEL);
	if (!fz->fz_hash) {
		kfree(fz);
		return NULL;
	}
	memset(fz->fz_hash, 0, fz->fz_divisor*sizeof(struct fib_node*));
	fz->fz_order = z;
	fz->fz_mask = inet_make_mask(z);

	/* Find the first not empty zone with more specific mask */
	for (i=z+1; i<=32; i++)
		if (table->fn_zones[i])
			break;
	if (i>32) {
		/* No more specific masks, we are the first. */
		fz->fz_next = table->fn_zone_list;
		table->fn_zone_list = fz;
	} else {
		fz->fz_next = table->fn_zones[i]->fz_next;
		table->fn_zones[i]->fz_next = fz;
	}
	table->fn_zones[z] = fz;
	return fz;
}

static int
fn_hash_lookup(struct fib_table *tb, const struct rt_key *key, struct fib_result *res)
{
	int err;
	struct fn_zone *fz;
	struct fn_hash *t = (struct fn_hash*)tb->tb_data;

	for (fz = t->fn_zone_list; fz; fz = fz->fz_next) {
		struct fib_node *f;
		fn_key_t k = fz_key(key->dst, fz);

		for (f = fz_chain(k, fz); f; f = f->fn_next) {
			if (!fn_key_eq(k, f->fn_key)) {
				if (fn_key_leq(k, f->fn_key))
					break;
				else
					continue;
			}
#ifdef CONFIG_IP_ROUTE_TOS
			if (f->fn_tos && f->fn_tos != key->tos)
				continue;
#endif
			f->fn_state |= FN_S_ACCESSED;

			if (f->fn_state&FN_S_ZOMBIE)
				continue;
			if (f->fn_scope < key->scope)
				continue;

			err = fib_semantic_match(f->fn_type, FIB_INFO(f), key, res);
			if (err == 0) {
				res->type = f->fn_type;
				res->scope = f->fn_scope;
				res->prefixlen = fz->fz_order;
				res->prefix = &fz_prefix(f->fn_key, fz);
				return 0;
			}
			if (err < 0)
				return err;
		}
	}
	return 1;
}

static int fn_hash_last_dflt=-1;

static int fib_detect_death(struct fib_info *fi, int order,
			    struct fib_info **last_resort, int *last_idx)
{
	struct neighbour *n;
	int state = NUD_NONE;

	n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].nh_gw, fi->fib_dev);
	if (n) {
		state = n->nud_state;
		neigh_release(n);
	}
	if (state==NUD_REACHABLE)
		return 0;
	if ((state&NUD_VALID) && order != fn_hash_last_dflt)
		return 0;
	if ((state&NUD_VALID) ||
	    (*last_idx<0 && order > fn_hash_last_dflt)) {
		*last_resort = fi;
		*last_idx = order;
	}
	return 1;
}

static void
fn_hash_select_default(struct fib_table *tb, const struct rt_key *key, struct fib_result *res)
{
	int order, last_idx;
	struct fib_node *f;
	struct fib_info *fi = NULL;
	struct fib_info *last_resort;
	struct fn_hash *t = (struct fn_hash*)tb->tb_data;
	struct fn_zone *fz = t->fn_zones[0];

	if (fz == NULL)
		return;

	last_idx = -1;
	last_resort = NULL;
	order = -1;

	for (f = fz->fz_hash[0]; f; f = f->fn_next) {
		struct fib_info *next_fi = FIB_INFO(f);

		if ((f->fn_state&FN_S_ZOMBIE) ||
		    f->fn_scope != res->scope ||
		    f->fn_type != RTN_UNICAST)
			continue;

		if (next_fi->fib_priority > res->fi->fib_priority)
			break;
		if (!next_fi->fib_nh[0].nh_gw || next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
			continue;
		f->fn_state |= FN_S_ACCESSED;

		if (fi == NULL) {
			if (next_fi != res->fi)
				break;
		} else if (!fib_detect_death(fi, order, &last_resort, &last_idx)) {
			res->fi = fi;
			fn_hash_last_dflt = order;
			return;
		}
		fi = next_fi;
		order++;
	}

	if (order<=0 || fi==NULL) {
		fn_hash_last_dflt = -1;
		return;
	}

	if (!fib_detect_death(fi, order, &last_resort, &last_idx)) {
		res->fi = fi;
		fn_hash_last_dflt = order;
		return;
	}

	if (last_idx >= 0)
		res->fi = last_resort;
	fn_hash_last_dflt = last_idx;
}

#define FIB_SCAN(f, fp) \
for ( ; ((f) = *(fp)) != NULL; (fp) = &(f)->fn_next)

#define FIB_SCAN_KEY(f, fp, key) \
for ( ; ((f) = *(fp)) != NULL && fn_key_eq((f)->fn_key, (key)); (fp) = &(f)->fn_next)

#ifndef CONFIG_IP_ROUTE_TOS
#define FIB_SCAN_TOS(f, fp, key, tos) FIB_SCAN_KEY(f, fp, key)
#else
#define FIB_SCAN_TOS(f, fp, key, tos) \
for ( ; ((f) = *(fp)) != NULL && fn_key_eq((f)->fn_key, (key)) && \
     (f)->fn_tos == (tos) ; (fp) = &(f)->fn_next)
#endif


#ifdef CONFIG_RTNETLINK
static void rtmsg_fib(int, struct fib_node*, int, int,
		      struct nlmsghdr *n,
		      struct netlink_skb_parms *);
#else
#define rtmsg_fib(a, b, c, d, e, f)
#endif


static int
fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta,
		struct nlmsghdr *n, struct netlink_skb_parms *req)
{
	struct fn_hash *table = (struct fn_hash*)tb->tb_data;
	struct fib_node *new_f, *f, **fp, **del_fp;
	struct fn_zone *fz;
	struct fib_info *fi;

	int z = r->rtm_dst_len;
	int type = r->rtm_type;
#ifdef CONFIG_IP_ROUTE_TOS
	u8 tos = r->rtm_tos;
#endif
	fn_key_t key;
	int err;

FTprint("tb(%d)_insert: %d %08x/%d %d %08x\n", tb->tb_id, r->rtm_type, rta->rta_dst ?
*(u32*)rta->rta_dst : 0, z, rta->rta_oif ? *rta->rta_oif : -1,
rta->rta_prefsrc ? *(u32*)rta->rta_prefsrc : 0);
	if (z > 32)
		return -EINVAL;
	fz = table->fn_zones[z];
	if (!fz && !(fz = fn_new_zone(table, z)))
		return -ENOBUFS;

	fz_key_0(key);
	if (rta->rta_dst) {
		u32 dst;
		memcpy(&dst, rta->rta_dst, 4);
		if (dst & ~FZ_MASK(fz))
			return -EINVAL;
		key = fz_key(dst, fz);
	}

	if  ((fi = fib_create_info(r, rta, n, &err)) == NULL)
		return err;

#ifdef CONFIG_IP_ROUTE_LARGE_TABLES
	if (fz->fz_nent > (fz->fz_divisor<<2) &&
	    fz->fz_divisor < FZ_MAX_DIVISOR &&
	    (z==32 || (1<<z) > fz->fz_divisor))
		fn_rehash_zone(fz);
#endif

	fp = fz_chain_p(key, fz);

	/*
	 * Scan list to find the first route with the same destination
	 */
	FIB_SCAN(f, fp) {
		if (fn_key_leq(key,f->fn_key))
			break;
	}

#ifdef CONFIG_IP_ROUTE_TOS
	/*
	 * Find route with the same destination and tos.
	 */
	FIB_SCAN_KEY(f, fp, key) {
		if (f->fn_tos <= tos)
			break;
	}
#endif

	del_fp = NULL;

	if (f && (f->fn_state&FN_S_ZOMBIE) &&
#ifdef CONFIG_IP_ROUTE_TOS
	    f->fn_tos == tos &&
#endif
	    fn_key_eq(f->fn_key, key)) {
		del_fp = fp;
		fp = &f->fn_next;
		f = *fp;
		goto create;
	}

	FIB_SCAN_TOS(f, fp, key, tos) {
		if (fi->fib_priority <= FIB_INFO(f)->fib_priority)
			break;
	}

	/* Now f==*fp points to the first node with the same
	   keys [prefix,tos,priority], if such key already
	   exists or to the node, before which we will insert new one.
	 */

	if (f && 
#ifdef CONFIG_IP_ROUTE_TOS
	    f->fn_tos == tos &&
#endif
	    fn_key_eq(f->fn_key, key) &&
	    fi->fib_priority == FIB_INFO(f)->fib_priority) {
		struct fib_node **ins_fp;

		err = -EEXIST;
		if (n->nlmsg_flags&NLM_F_EXCL)
			goto out;

		if (n->nlmsg_flags&NLM_F_REPLACE) {
			del_fp = fp;
			fp = &f->fn_next;
			f = *fp;
			goto replace;
		}

		ins_fp = fp;
		err = -EEXIST;

		FIB_SCAN_TOS(f, fp, key, tos) {
			if (fi->fib_priority != FIB_INFO(f)->fib_priority)
				break;
			if (f->fn_type == type && f->fn_scope == r->rtm_scope
			    && FIB_INFO(f) == fi)
				goto out;
		}

		if (!(n->nlmsg_flags&NLM_F_APPEND)) {
			fp = ins_fp;
			f = *fp;
		}
	}

create:
	err = -ENOENT;
	if (!(n->nlmsg_flags&NLM_F_CREATE))
		goto out;

replace:
	err = -ENOBUFS;
	new_f = (struct fib_node *) kmalloc(sizeof(struct fib_node), GFP_KERNEL);
	if (new_f == NULL)
		goto out;

	memset(new_f, 0, sizeof(struct fib_node));

	new_f->fn_key = key;
#ifdef CONFIG_IP_ROUTE_TOS
	new_f->fn_tos = tos;
#endif
	new_f->fn_type = type;
	new_f->fn_scope = r->rtm_scope;
	FIB_INFO(new_f) = fi;

	/*
	 * Insert new entry to the list.
	 */

	new_f->fn_next = f;
	*fp = new_f;
	fz->fz_nent++;

	if (del_fp) {
		f = *del_fp;
		/* Unlink replaced node */
		*del_fp = f->fn_next;
		synchronize_bh();

		if (!(f->fn_state&FN_S_ZOMBIE))
			rtmsg_fib(RTM_DELROUTE, f, z, tb->tb_id, n, req);
		if (f->fn_state&FN_S_ACCESSED)
			rt_cache_flush(-1);
		fn_free_node(f);
		fz->fz_nent--;
	} else {
		rt_cache_flush(-1);
	}
	rtmsg_fib(RTM_NEWROUTE, new_f, z, tb->tb_id, n, req);
	return 0;

out:
	fib_release_info(fi);
	return err;
}


static int
fn_hash_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta,
		struct nlmsghdr *n, struct netlink_skb_parms *req)
{
	struct fn_hash *table = (struct fn_hash*)tb->tb_data;
	struct fib_node **fp, **del_fp, *f;
	int z = r->rtm_dst_len;
	struct fn_zone *fz;
	fn_key_t key;
	int matched;
#ifdef CONFIG_IP_ROUTE_TOS
	u8 tos = r->rtm_tos;
#endif

FTprint("tb(%d)_delete: %d %08x/%d %d\n", tb->tb_id, r->rtm_type, rta->rta_dst ?
       *(u32*)rta->rta_dst : 0, z, rta->rta_oif ? *rta->rta_oif : -1);
	if (z > 32)
		return -EINVAL;
	if ((fz  = table->fn_zones[z]) == NULL)
		return -ESRCH;

	fz_key_0(key);
	if (rta->rta_dst) {
		u32 dst;
		memcpy(&dst, rta->rta_dst, 4);
		if (dst & ~FZ_MASK(fz))
			return -EINVAL;
		key = fz_key(dst, fz);
	}

	fp = fz_chain_p(key, fz);

	FIB_SCAN(f, fp) {
		if (fn_key_eq(f->fn_key, key))
			break;
		if (fn_key_leq(key, f->fn_key))
			return -ESRCH;
	}
#ifdef CONFIG_IP_ROUTE_TOS
	FIB_SCAN_KEY(f, fp, key) {
		if (f->fn_tos == tos)
			break;
	}
#endif

	matched = 0;
	del_fp = NULL;
	FIB_SCAN_TOS(f, fp, key, tos) {
		struct fib_info * fi = FIB_INFO(f);

		if (f->fn_state&FN_S_ZOMBIE)
			return -ESRCH;

		matched++;

		if (del_fp == NULL &&
		    (!r->rtm_type || f->fn_type == r->rtm_type) &&
		    (r->rtm_scope == RT_SCOPE_NOWHERE || f->fn_scope == r->rtm_scope) &&
		    (!r->rtm_protocol || fi->fib_protocol == r->rtm_protocol) &&
		    fib_nh_match(r, n, rta, fi) == 0)
			del_fp = fp;
	}

	if (del_fp) {
		f = *del_fp;
		rtmsg_fib(RTM_DELROUTE, f, z, tb->tb_id, n, req);

		if (matched != 1) {
			*del_fp = f->fn_next;
			synchronize_bh();

			if (f->fn_state&FN_S_ACCESSED)
				rt_cache_flush(-1);
			fn_free_node(f);
			fz->fz_nent--;
		} else {
			f->fn_state |= FN_S_ZOMBIE;
			if (f->fn_state&FN_S_ACCESSED) {
				f->fn_state &= ~FN_S_ACCESSED;
				rt_cache_flush(-1);
			}
			if (++fib_hash_zombies > 128)
				fib_flush();
		}

		return 0;
	}
	return -ESRCH;
}

extern __inline__ int
fn_flush_list(struct fib_node ** fp, int z, struct fn_hash *table)
{
	int found = 0;
	struct fib_node *f;

	while ((f = *fp) != NULL) {
		struct fib_info *fi = FIB_INFO(f);

		if (fi && ((f->fn_state&FN_S_ZOMBIE) || (fi->fib_flags&RTNH_F_DEAD))) {
			*fp = f->fn_next;
			synchronize_bh();

			fn_free_node(f);
			found++;
			continue;
		}
		fp = &f->fn_next;
	}
	return found;
}

static int fn_hash_flush(struct fib_table *tb)
{
	struct fn_hash *table = (struct fn_hash*)tb->tb_data;
	struct fn_zone *fz;
	int found = 0;

	fib_hash_zombies = 0;
	for (fz = table->fn_zone_list; fz; fz = fz->fz_next) {
		int i;
		int tmp = 0;
		for (i=fz->fz_divisor-1; i>=0; i--)
			tmp += fn_flush_list(&fz->fz_hash[i], fz->fz_order, table);
		fz->fz_nent -= tmp;
		found += tmp;
	}
	return found;
}


#ifdef CONFIG_PROC_FS

static int fn_hash_get_info(struct fib_table *tb, char *buffer, int first, int count)
{
	struct fn_hash *table = (struct fn_hash*)tb->tb_data;
	struct fn_zone *fz;
	int pos = 0;
	int n = 0;

	for (fz=table->fn_zone_list; fz; fz = fz->fz_next) {
		int i;
		struct fib_node *f;
		int maxslot = fz->fz_divisor;
		struct fib_node **fp = fz->fz_hash;

		if (fz->fz_nent == 0)
			continue;

		if (pos + fz->fz_nent <= first) {
			pos += fz->fz_nent;
			continue;
		}

		for (i=0; i < maxslot; i++, fp++) {
			for (f = *fp; f; f = f->fn_next) {
				if (++pos <= first)
					continue;
				fib_node_get_info(f->fn_type,
						  f->fn_state&FN_S_ZOMBIE,
						  FIB_INFO(f),
						  fz_prefix(f->fn_key, fz),
						  FZ_MASK(fz), buffer);
				buffer += 128;
				if (++n >= count)
					return n;
			}
		}
	}
  	return n;
}
#endif


#ifdef CONFIG_RTNETLINK

extern __inline__ int
fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb,
		     struct fib_table *tb,
		     struct fn_zone *fz,
		     struct fib_node *f)
{
	int i, s_i;

	s_i = cb->args[3];
	for (i=0; f; i++, f=f->fn_next) {
		if (i < s_i) continue;
		if (f->fn_state&FN_S_ZOMBIE) continue;
		if (fib_dump_info(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq,
				  RTM_NEWROUTE,
				  tb->tb_id, (f->fn_state&FN_S_ZOMBIE) ? 0 : f->fn_type, f->fn_scope,
				  &f->fn_key, fz->fz_order, f->fn_tos,
				  f->fn_info) < 0) {
			cb->args[3] = i;
			return -1;
		}
	}
	cb->args[3] = i;
	return skb->len;
}

extern __inline__ int
fn_hash_dump_zone(struct sk_buff *skb, struct netlink_callback *cb,
		   struct fib_table *tb,
		   struct fn_zone *fz)
{
	int h, s_h;

	s_h = cb->args[2];
	for (h=0; h < fz->fz_divisor; h++) {
		if (h < s_h) continue;
		if (h > s_h)
			memset(&cb->args[3], 0, sizeof(cb->args) - 3*sizeof(cb->args[0]));
		if (fz->fz_hash == NULL || fz->fz_hash[h] == NULL)
			continue;
		if (fn_hash_dump_bucket(skb, cb, tb, fz, fz->fz_hash[h]) < 0) {
			cb->args[2] = h;
			return -1;
		}
	}
	cb->args[2] = h;
	return skb->len;
}

static int fn_hash_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb)
{
	int m, s_m;
	struct fn_zone *fz;
	struct fn_hash *table = (struct fn_hash*)tb->tb_data;

	s_m = cb->args[1];
	for (fz = table->fn_zone_list, m=0; fz; fz = fz->fz_next, m++) {
		if (m < s_m) continue;
		if (m > s_m)
			memset(&cb->args[2], 0, sizeof(cb->args) - 2*sizeof(cb->args[0]));
		if (fn_hash_dump_zone(skb, cb, tb, fz) < 0) {
			cb->args[1] = m;
			return -1;
		}
	}
	cb->args[1] = m;
	return skb->len;
}

static void rtmsg_fib(int event, struct fib_node* f, int z, int tb_id,
		      struct nlmsghdr *n, struct netlink_skb_parms *req)
{
	struct sk_buff *skb;
	u32 pid = req ? req->pid : 0;
	int size = NLMSG_SPACE(sizeof(struct rtmsg)+256);

	skb = alloc_skb(size, GFP_KERNEL);
	if (!skb)
		return;

	if (fib_dump_info(skb, pid, n->nlmsg_seq, event, tb_id,
			  f->fn_type, f->fn_scope, &f->fn_key, z, f->fn_tos,
			  FIB_INFO(f)) < 0) {
		kfree_skb(skb);
		return;
	}
	NETLINK_CB(skb).dst_groups = RTMGRP_IPV4_ROUTE;
	if (n->nlmsg_flags&NLM_F_ECHO)
		atomic_inc(&skb->users);
	netlink_broadcast(rtnl, skb, pid, RTMGRP_IPV4_ROUTE, GFP_KERNEL);
	if (n->nlmsg_flags&NLM_F_ECHO)
		netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT);
}

#endif /* CONFIG_RTNETLINK */

#ifdef CONFIG_IP_MULTIPLE_TABLES
struct fib_table * fib_hash_init(int id)
#else
__initfunc(struct fib_table * fib_hash_init(int id))
#endif
{
	struct fib_table *tb;
	tb = kmalloc(sizeof(struct fib_table) + sizeof(struct fn_hash), GFP_KERNEL);
	if (tb == NULL)
		return NULL;
	tb->tb_id = id;
	tb->tb_lookup = fn_hash_lookup;
	tb->tb_insert = fn_hash_insert;
	tb->tb_delete = fn_hash_delete;
	tb->tb_flush = fn_hash_flush;
	tb->tb_select_default = fn_hash_select_default;
#ifdef CONFIG_RTNETLINK
	tb->tb_dump = fn_hash_dump;
#endif
#ifdef CONFIG_PROC_FS
	tb->tb_get_info = fn_hash_get_info;
#endif
	memset(tb->tb_data, 0, sizeof(struct fn_hash));
	return tb;
}