aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv6/reassembly.c
blob: 0b97230a32517b599e26ab2bed4a405ec0f67f99 (plain) (blame)
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
/*
 *	IPv6 fragment reassembly
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	Based on: net/ipv4/ip_fragment.c
 *
 *	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:
 *	Andi Kleen	Make it work with multiple hosts.
 *			More RFC compliance.
 *
 *      Horst von Brand Add missing #include <linux/string.h>
 *	Alexey Kuznetsov	SMP races, threading, cleanup.
 *	Patrick McHardy		LRU queue of frag heads for evictor.
 *	Mitsuru KANDA @USAGI	Register inet6_protocol{}.
 *	David Stevens and
 *	YOSHIFUJI,H. @USAGI	Always remove fragment header to
 *				calculate ICV correctly.
 */
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/jiffies.h>
#include <linux/net.h>
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/skbuff.h>
#include <linux/slab.h>

#include <net/sock.h>
#include <net/snmp.h>

#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/inet_frag.h>

struct ip6frag_skb_cb
{
	struct inet6_skb_parm	h;
	int			offset;
};

#define FRAG6_CB(skb)	((struct ip6frag_skb_cb*)((skb)->cb))


/*
 *	Equivalent of ipv4 struct ipq
 */

struct frag_queue
{
	struct inet_frag_queue	q;

	__be32			id;		/* fragment id		*/
	u32			user;
	struct in6_addr		saddr;
	struct in6_addr		daddr;

	int			iif;
	unsigned int		csum;
	__u16			nhoffset;
};

static struct inet_frags ip6_frags;

int ip6_frag_nqueues(struct net *net)
{
	return net->ipv6.frags.nqueues;
}

int ip6_frag_mem(struct net *net)
{
	return atomic_read(&net->ipv6.frags.mem);
}

static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
			  struct net_device *dev);

/*
 * callers should be careful not to use the hash value outside the ipfrag_lock
 * as doing so could race with ipfrag_hash_rnd being recalculated.
 */
unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
			     const struct in6_addr *daddr, u32 rnd)
{
	u32 a, b, c;

	a = (__force u32)saddr->s6_addr32[0];
	b = (__force u32)saddr->s6_addr32[1];
	c = (__force u32)saddr->s6_addr32[2];

	a += JHASH_GOLDEN_RATIO;
	b += JHASH_GOLDEN_RATIO;
	c += rnd;
	__jhash_mix(a, b, c);

	a += (__force u32)saddr->s6_addr32[3];
	b += (__force u32)daddr->s6_addr32[0];
	c += (__force u32)daddr->s6_addr32[1];
	__jhash_mix(a, b, c);

	a += (__force u32)daddr->s6_addr32[2];
	b += (__force u32)daddr->s6_addr32[3];
	c += (__force u32)id;
	__jhash_mix(a, b, c);

	return c & (INETFRAGS_HASHSZ - 1);
}
EXPORT_SYMBOL_GPL(inet6_hash_frag);

static unsigned int ip6_hashfn(struct inet_frag_queue *q)
{
	struct frag_queue *fq;

	fq = container_of(q, struct frag_queue, q);
	return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr, ip6_frags.rnd);
}

int ip6_frag_match(struct inet_frag_queue *q, void *a)
{
	struct frag_queue *fq;
	struct ip6_create_arg *arg = a;

	fq = container_of(q, struct frag_queue, q);
	return (fq->id == arg->id && fq->user == arg->user &&
			ipv6_addr_equal(&fq->saddr, arg->src) &&
			ipv6_addr_equal(&fq->daddr, arg->dst));
}
EXPORT_SYMBOL(ip6_frag_match);

/* Memory Tracking Functions. */
static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb)
{
	atomic_sub(skb->truesize, &nf->mem);
	kfree_skb(skb);
}

void ip6_frag_init(struct inet_frag_queue *q, void *a)
{
	struct frag_queue *fq = container_of(q, struct frag_queue, q);
	struct ip6_create_arg *arg = a;

	fq->id = arg->id;
	fq->user = arg->user;
	ipv6_addr_copy(&fq->saddr, arg->src);
	ipv6_addr_copy(&fq->daddr, arg->dst);
}
EXPORT_SYMBOL(ip6_frag_init);

/* Destruction primitives. */

static __inline__ void fq_put(struct frag_queue *fq)
{
	inet_frag_put(&fq->q, &ip6_frags);
}

/* Kill fq entry. It is not destroyed immediately,
 * because caller (and someone more) holds reference count.
 */
static __inline__ void fq_kill(struct frag_queue *fq)
{
	inet_frag_kill(&fq->q, &ip6_frags);
}

static void ip6_evictor(struct net *net, struct inet6_dev *idev)
{
	int evicted;

	evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags);
	if (evicted)
		IP6_ADD_STATS_BH(net, idev, IPSTATS_MIB_REASMFAILS, evicted);
}

static void ip6_frag_expire(unsigned long data)
{
	struct frag_queue *fq;
	struct net_device *dev = NULL;
	struct net *net;

	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);

	spin_lock(&fq->q.lock);

	if (fq->q.last_in & INET_FRAG_COMPLETE)
		goto out;

	fq_kill(fq);

	net = container_of(fq->q.net, struct net, ipv6.frags);
	rcu_read_lock();
	dev = dev_get_by_index_rcu(net, fq->iif);
	if (!dev)
		goto out_rcu_unlock;

	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);

	/* Don't send error if the first segment did not arrive. */
	if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments)
		goto out_rcu_unlock;

	/*
	   But use as source device on which LAST ARRIVED
	   segment was received. And do not use fq->dev
	   pointer directly, device might already disappeared.
	 */
	fq->q.fragments->dev = dev;
	icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
out_rcu_unlock:
	rcu_read_unlock();
out:
	spin_unlock(&fq->q.lock);
	fq_put(fq);
}

static __inline__ struct frag_queue *
fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst)
{
	struct inet_frag_queue *q;
	struct ip6_create_arg arg;
	unsigned int hash;

	arg.id = id;
	arg.user = IP6_DEFRAG_LOCAL_DELIVER;
	arg.src = src;
	arg.dst = dst;

	read_lock(&ip6_frags.lock);
	hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd);

	q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
	if (q == NULL)
		return NULL;

	return container_of(q, struct frag_queue, q);
}

static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
			   struct frag_hdr *fhdr, int nhoff)
{
	struct sk_buff *prev, *next;
	struct net_device *dev;
	int offset, end;
	struct net *net = dev_net(skb_dst(skb)->dev);

	if (fq->q.last_in & INET_FRAG_COMPLETE)
		goto err;

	offset = ntohs(fhdr->frag_off) & ~0x7;
	end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
			((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));

	if ((unsigned int)end > IPV6_MAXPLEN) {
		IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
				 IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
				  ((u8 *)&fhdr->frag_off -
				   skb_network_header(skb)));
		return -1;
	}

	if (skb->ip_summed == CHECKSUM_COMPLETE) {
		const unsigned char *nh = skb_network_header(skb);
		skb->csum = csum_sub(skb->csum,
				     csum_partial(nh, (u8 *)(fhdr + 1) - nh,
						  0));
	}

	/* Is this the final fragment? */
	if (!(fhdr->frag_off & htons(IP6_MF))) {
		/* If we already have some bits beyond end
		 * or have different end, the segment is corrupted.
		 */
		if (end < fq->q.len ||
		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
			goto err;
		fq->q.last_in |= INET_FRAG_LAST_IN;
		fq->q.len = end;
	} else {
		/* Check if the fragment is rounded to 8 bytes.
		 * Required by the RFC.
		 */
		if (end & 0x7) {
			/* RFC2460 says always send parameter problem in
			 * this case. -DaveM
			 */
			IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
					 IPSTATS_MIB_INHDRERRORS);
			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
					  offsetof(struct ipv6hdr, payload_len));
			return -1;
		}
		if (end > fq->q.len) {
			/* Some bits beyond end -> corruption. */
			if (fq->q.last_in & INET_FRAG_LAST_IN)
				goto err;
			fq->q.len = end;
		}
	}

	if (end == offset)
		goto err;

	/* Point into the IP datagram 'data' part. */
	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data))
		goto err;

	if (pskb_trim_rcsum(skb, end - offset))
		goto err;

	/* Find out which fragments are in front and at the back of us
	 * in the chain of fragments so far.  We must know where to put
	 * this fragment, right?
	 */
	prev = NULL;
	for(next = fq->q.fragments; next != NULL; next = next->next) {
		if (FRAG6_CB(next)->offset >= offset)
			break;	/* bingo! */
		prev = next;
	}

	/* We found where to put this one.  Check for overlap with
	 * preceding fragment, and, if needed, align things so that
	 * any overlaps are eliminated.
	 */
	if (prev) {
		int i = (FRAG6_CB(prev)->offset + prev->len) - offset;

		if (i > 0) {
			offset += i;
			if (end <= offset)
				goto err;
			if (!pskb_pull(skb, i))
				goto err;
			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
				skb->ip_summed = CHECKSUM_NONE;
		}
	}

	/* Look for overlap with succeeding segments.
	 * If we can merge fragments, do it.
	 */
	while (next && FRAG6_CB(next)->offset < end) {
		int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */

		if (i < next->len) {
			/* Eat head of the next overlapped fragment
			 * and leave the loop. The next ones cannot overlap.
			 */
			if (!pskb_pull(next, i))
				goto err;
			FRAG6_CB(next)->offset += i;	/* next fragment */
			fq->q.meat -= i;
			if (next->ip_summed != CHECKSUM_UNNECESSARY)
				next->ip_summed = CHECKSUM_NONE;
			break;
		} else {
			struct sk_buff *free_it = next;

			/* Old fragment is completely overridden with
			 * new one drop it.
			 */
			next = next->next;

			if (prev)
				prev->next = next;
			else
				fq->q.fragments = next;

			fq->q.meat -= free_it->len;
			frag_kfree_skb(fq->q.net, free_it);
		}
	}

	FRAG6_CB(skb)->offset = offset;

	/* Insert this fragment in the chain of fragments. */
	skb->next = next;
	if (prev)
		prev->next = skb;
	else
		fq->q.fragments = skb;

	dev = skb->dev;
	if (dev) {
		fq->iif = dev->ifindex;
		skb->dev = NULL;
	}
	fq->q.stamp = skb->tstamp;
	fq->q.meat += skb->len;
	atomic_add(skb->truesize, &fq->q.net->mem);

	/* The first fragment.
	 * nhoffset is obtained from the first fragment, of course.
	 */
	if (offset == 0) {
		fq->nhoffset = nhoff;
		fq->q.last_in |= INET_FRAG_FIRST_IN;
	}

	if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
	    fq->q.meat == fq->q.len)
		return ip6_frag_reasm(fq, prev, dev);

	write_lock(&ip6_frags.lock);
	list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
	write_unlock(&ip6_frags.lock);
	return -1;

err:
	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
		      IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
	return -1;
}

/*
 *	Check if this packet is complete.
 *	Returns NULL on failure by any reason, and pointer
 *	to current nexthdr field in reassembled frame.
 *
 *	It is called with locked fq, and caller must check that
 *	queue is eligible for reassembly i.e. it is not COMPLETE,
 *	the last and the first frames arrived and all the bits are here.
 */
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
			  struct net_device *dev)
{
	struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
	struct sk_buff *fp, *head = fq->q.fragments;
	int    payload_len;
	unsigned int nhoff;

	fq_kill(fq);

	/* Make the one we just received the head. */
	if (prev) {
		head = prev->next;
		fp = skb_clone(head, GFP_ATOMIC);

		if (!fp)
			goto out_oom;

		fp->next = head->next;
		prev->next = fp;

		skb_morph(head, fq->q.fragments);
		head->next = fq->q.fragments->next;

		kfree_skb(fq->q.fragments);
		fq->q.fragments = head;
	}

	WARN_ON(head == NULL);
	WARN_ON(FRAG6_CB(head)->offset != 0);

	/* Unfragmented part is taken from the first segment. */
	payload_len = ((head->data - skb_network_header(head)) -
		       sizeof(struct ipv6hdr) + fq->q.len -
		       sizeof(struct frag_hdr));
	if (payload_len > IPV6_MAXPLEN)
		goto out_oversize;

	/* Head of list must not be cloned. */
	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
		goto out_oom;

	/* If the first fragment is fragmented itself, we split
	 * it to two chunks: the first with data and paged part
	 * and the second, holding only fragments. */
	if (skb_has_frags(head)) {
		struct sk_buff *clone;
		int i, plen = 0;

		if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL)
			goto out_oom;
		clone->next = head->next;
		head->next = clone;
		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
		skb_frag_list_init(head);
		for (i=0; i<skb_shinfo(head)->nr_frags; i++)
			plen += skb_shinfo(head)->frags[i].size;
		clone->len = clone->data_len = head->data_len - plen;
		head->data_len -= clone->len;
		head->len -= clone->len;
		clone->csum = 0;
		clone->ip_summed = head->ip_summed;
		atomic_add(clone->truesize, &fq->q.net->mem);
	}

	/* We have to remove fragment header from datagram and to relocate
	 * header in order to calculate ICV correctly. */
	nhoff = fq->nhoffset;
	skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
	memmove(head->head + sizeof(struct frag_hdr), head->head,
		(head->data - head->head) - sizeof(struct frag_hdr));
	head->mac_header += sizeof(struct frag_hdr);
	head->network_header += sizeof(struct frag_hdr);

	skb_shinfo(head)->frag_list = head->next;
	skb_reset_transport_header(head);
	skb_push(head, head->data - skb_network_header(head));

	for (fp=head->next; fp; fp = fp->next) {
		head->data_len += fp->len;
		head->len += fp->len;
		if (head->ip_summed != fp->ip_summed)
			head->ip_summed = CHECKSUM_NONE;
		else if (head->ip_summed == CHECKSUM_COMPLETE)
			head->csum = csum_add(head->csum, fp->csum);
		head->truesize += fp->truesize;
	}
	atomic_sub(head->truesize, &fq->q.net->mem);

	head->next = NULL;
	head->dev = dev;
	head->tstamp = fq->q.stamp;
	ipv6_hdr(head)->payload_len = htons(payload_len);
	IP6CB(head)->nhoff = nhoff;

	/* Yes, and fold redundant checksum back. 8) */
	if (head->ip_summed == CHECKSUM_COMPLETE)
		head->csum = csum_partial(skb_network_header(head),
					  skb_network_header_len(head),
					  head->csum);

	rcu_read_lock();
	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
	rcu_read_unlock();
	fq->q.fragments = NULL;
	return 1;

out_oversize:
	if (net_ratelimit())
		printk(KERN_DEBUG "ip6_frag_reasm: payload len = %d\n", payload_len);
	goto out_fail;
out_oom:
	if (net_ratelimit())
		printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
out_fail:
	rcu_read_lock();
	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
	rcu_read_unlock();
	return -1;
}

static int ipv6_frag_rcv(struct sk_buff *skb)
{
	struct frag_hdr *fhdr;
	struct frag_queue *fq;
	struct ipv6hdr *hdr = ipv6_hdr(skb);
	struct net *net = dev_net(skb_dst(skb)->dev);

	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);

	/* Jumbo payload inhibits frag. header */
	if (hdr->payload_len==0)
		goto fail_hdr;

	if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
				 sizeof(struct frag_hdr))))
		goto fail_hdr;

	hdr = ipv6_hdr(skb);
	fhdr = (struct frag_hdr *)skb_transport_header(skb);

	if (!(fhdr->frag_off & htons(0xFFF9))) {
		/* It is not a fragmented frame */
		skb->transport_header += sizeof(struct frag_hdr);
		IP6_INC_STATS_BH(net,
				 ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);

		IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
		return 1;
	}

	if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh)
		ip6_evictor(net, ip6_dst_idev(skb_dst(skb)));

	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr);
	if (fq != NULL) {
		int ret;

		spin_lock(&fq->q.lock);

		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);

		spin_unlock(&fq->q.lock);
		fq_put(fq);
		return ret;
	}

	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
	kfree_skb(skb);
	return -1;

fail_hdr:
	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS);
	icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb));
	return -1;
}

static const struct inet6_protocol frag_protocol =
{
	.handler	=	ipv6_frag_rcv,
	.flags		=	INET6_PROTO_NOPOLICY,
};

#ifdef CONFIG_SYSCTL
static struct ctl_table ip6_frags_ns_ctl_table[] = {
	{
		.procname	= "ip6frag_high_thresh",
		.data		= &init_net.ipv6.frags.high_thresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec
	},
	{
		.procname	= "ip6frag_low_thresh",
		.data		= &init_net.ipv6.frags.low_thresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec
	},
	{
		.procname	= "ip6frag_time",
		.data		= &init_net.ipv6.frags.timeout,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{ }
};

static struct ctl_table ip6_frags_ctl_table[] = {
	{
		.procname	= "ip6frag_secret_interval",
		.data		= &ip6_frags.secret_interval,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{ }
};

static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
{
	struct ctl_table *table;
	struct ctl_table_header *hdr;

	table = ip6_frags_ns_ctl_table;
	if (!net_eq(net, &init_net)) {
		table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL);
		if (table == NULL)
			goto err_alloc;

		table[0].data = &net->ipv6.frags.high_thresh;
		table[1].data = &net->ipv6.frags.low_thresh;
		table[2].data = &net->ipv6.frags.timeout;
	}

	hdr = register_net_sysctl_table(net, net_ipv6_ctl_path, table);
	if (hdr == NULL)
		goto err_reg;

	net->ipv6.sysctl.frags_hdr = hdr;
	return 0;

err_reg:
	if (!net_eq(net, &init_net))
		kfree(table);
err_alloc:
	return -ENOMEM;
}

static void __net_exit ip6_frags_ns_sysctl_unregister(struct net *net)
{
	struct ctl_table *table;

	table = net->ipv6.sysctl.frags_hdr->ctl_table_arg;
	unregister_net_sysctl_table(net->ipv6.sysctl.frags_hdr);
	if (!net_eq(net, &init_net))
		kfree(table);
}

static struct ctl_table_header *ip6_ctl_header;

static int ip6_frags_sysctl_register(void)
{
	ip6_ctl_header = register_net_sysctl_rotable(net_ipv6_ctl_path,
			ip6_frags_ctl_table);
	return ip6_ctl_header == NULL ? -ENOMEM : 0;
}

static void ip6_frags_sysctl_unregister(void)
{
	unregister_net_sysctl_table(ip6_ctl_header);
}
#else
static inline int ip6_frags_ns_sysctl_register(struct net *net)
{
	return 0;
}

static inline void ip6_frags_ns_sysctl_unregister(struct net *net)
{
}

static inline int ip6_frags_sysctl_register(void)
{
	return 0;
}

static inline void ip6_frags_sysctl_unregister(void)
{
}
#endif

static int __net_init ipv6_frags_init_net(struct net *net)
{
	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;

	inet_frags_init_net(&net->ipv6.frags);

	return ip6_frags_ns_sysctl_register(net);
}

static void __net_exit ipv6_frags_exit_net(struct net *net)
{
	ip6_frags_ns_sysctl_unregister(net);
	inet_frags_exit_net(&net->ipv6.frags, &ip6_frags);
}

static struct pernet_operations ip6_frags_ops = {
	.init = ipv6_frags_init_net,
	.exit = ipv6_frags_exit_net,
};

int __init ipv6_frag_init(void)
{
	int ret;

	ret = inet6_add_protocol(&frag_protocol, IPPROTO_FRAGMENT);
	if (ret)
		goto out;

	ret = ip6_frags_sysctl_register();
	if (ret)
		goto err_sysctl;

	ret = register_pernet_subsys(&ip6_frags_ops);
	if (ret)
		goto err_pernet;

	ip6_frags.hashfn = ip6_hashfn;
	ip6_frags.constructor = ip6_frag_init;
	ip6_frags.destructor = NULL;
	ip6_frags.skb_free = NULL;
	ip6_frags.qsize = sizeof(struct frag_queue);
	ip6_frags.match = ip6_frag_match;
	ip6_frags.frag_expire = ip6_frag_expire;
	ip6_frags.secret_interval = 10 * 60 * HZ;
	inet_frags_init(&ip6_frags);
out:
	return ret;

err_pernet:
	ip6_frags_sysctl_unregister();
err_sysctl:
	inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
	goto out;
}

void ipv6_frag_exit(void)
{
	inet_frags_fini(&ip6_frags);
	ip6_frags_sysctl_unregister();
	unregister_pernet_subsys(&ip6_frags_ops);
	inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT);
}