New training

Linux graphics course

New training

Linux graphics course

Bootlin logo

Elixir Cross Referencer

  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
/*
 * IPv6 fragment reassembly for connection tracking
 *
 * Copyright (C)2004 USAGI/WIDE Project
 *
 * Author:
 *	Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
 *
 * Based on: net/ipv6/reassembly.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.
 */

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

#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/rawv6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <linux/sysctl.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
#include <linux/kernel.h>
#include <linux/module.h>

#if 0
#define DEBUGP printk
#else
#define DEBUGP(format, args...)
#endif

#define NF_CT_FRAG6_HIGH_THRESH 262144 /* == 256*1024 */
#define NF_CT_FRAG6_LOW_THRESH 196608  /* == 192*1024 */
#define NF_CT_FRAG6_TIMEOUT IPV6_FRAG_TIMEOUT

unsigned int nf_ct_frag6_high_thresh = 256*1024;
unsigned int nf_ct_frag6_low_thresh = 192*1024;
unsigned long nf_ct_frag6_timeout = IPV6_FRAG_TIMEOUT;

struct nf_ct_frag6_skb_cb
{
	struct inet6_skb_parm	h;
	int			offset;
	struct sk_buff		*orig;
};

#define NFCT_FRAG6_CB(skb)	((struct nf_ct_frag6_skb_cb*)((skb)->cb))

struct nf_ct_frag6_queue
{
	struct hlist_node	list;
	struct list_head	lru_list;	/* lru list member	*/

	__u32			id;		/* fragment id		*/
	struct in6_addr		saddr;
	struct in6_addr		daddr;

	spinlock_t		lock;
	atomic_t		refcnt;
	struct timer_list	timer;		/* expire timer		*/
	struct sk_buff		*fragments;
	int			len;
	int			meat;
	struct timeval		stamp;
	unsigned int		csum;
	__u8			last_in;	/* has first/last segment arrived? */
#define COMPLETE		4
#define FIRST_IN		2
#define LAST_IN			1
	__u16			nhoffset;
};

/* Hash table. */

#define FRAG6Q_HASHSZ	64

static struct hlist_head nf_ct_frag6_hash[FRAG6Q_HASHSZ];
static DEFINE_RWLOCK(nf_ct_frag6_lock);
static u32 nf_ct_frag6_hash_rnd;
static LIST_HEAD(nf_ct_frag6_lru_list);
int nf_ct_frag6_nqueues = 0;

static __inline__ void __fq_unlink(struct nf_ct_frag6_queue *fq)
{
	hlist_del(&fq->list);
	list_del(&fq->lru_list);
	nf_ct_frag6_nqueues--;
}

static __inline__ void fq_unlink(struct nf_ct_frag6_queue *fq)
{
	write_lock(&nf_ct_frag6_lock);
	__fq_unlink(fq);
	write_unlock(&nf_ct_frag6_lock);
}

static unsigned int ip6qhashfn(u32 id, struct in6_addr *saddr,
			       struct in6_addr *daddr)
{
	u32 a, b, c;

	a = saddr->s6_addr32[0];
	b = saddr->s6_addr32[1];
	c = saddr->s6_addr32[2];

	a += JHASH_GOLDEN_RATIO;
	b += JHASH_GOLDEN_RATIO;
	c += nf_ct_frag6_hash_rnd;
	__jhash_mix(a, b, c);

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

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

	return c & (FRAG6Q_HASHSZ - 1);
}

static struct timer_list nf_ct_frag6_secret_timer;
int nf_ct_frag6_secret_interval = 10 * 60 * HZ;

static void nf_ct_frag6_secret_rebuild(unsigned long dummy)
{
	unsigned long now = jiffies;
	int i;

	write_lock(&nf_ct_frag6_lock);
	get_random_bytes(&nf_ct_frag6_hash_rnd, sizeof(u32));
	for (i = 0; i < FRAG6Q_HASHSZ; i++) {
		struct nf_ct_frag6_queue *q;
		struct hlist_node *p, *n;

		hlist_for_each_entry_safe(q, p, n, &nf_ct_frag6_hash[i], list) {
			unsigned int hval = ip6qhashfn(q->id,
						       &q->saddr,
						       &q->daddr);
			if (hval != i) {
				hlist_del(&q->list);
				/* Relink to new hash chain. */
				hlist_add_head(&q->list,
					       &nf_ct_frag6_hash[hval]);
			}
		}
	}
	write_unlock(&nf_ct_frag6_lock);

	mod_timer(&nf_ct_frag6_secret_timer, now + nf_ct_frag6_secret_interval);
}

atomic_t nf_ct_frag6_mem = ATOMIC_INIT(0);

/* Memory Tracking Functions. */
static inline void frag_kfree_skb(struct sk_buff *skb, unsigned int *work)
{
	if (work)
		*work -= skb->truesize;
	atomic_sub(skb->truesize, &nf_ct_frag6_mem);
	if (NFCT_FRAG6_CB(skb)->orig)
		kfree_skb(NFCT_FRAG6_CB(skb)->orig);

	kfree_skb(skb);
}

static inline void frag_free_queue(struct nf_ct_frag6_queue *fq,
				   unsigned int *work)
{
	if (work)
		*work -= sizeof(struct nf_ct_frag6_queue);
	atomic_sub(sizeof(struct nf_ct_frag6_queue), &nf_ct_frag6_mem);
	kfree(fq);
}

static inline struct nf_ct_frag6_queue *frag_alloc_queue(void)
{
	struct nf_ct_frag6_queue *fq = kmalloc(sizeof(struct nf_ct_frag6_queue), GFP_ATOMIC);

	if (!fq)
		return NULL;
	atomic_add(sizeof(struct nf_ct_frag6_queue), &nf_ct_frag6_mem);
	return fq;
}

/* Destruction primitives. */

/* Complete destruction of fq. */
static void nf_ct_frag6_destroy(struct nf_ct_frag6_queue *fq,
				unsigned int *work)
{
	struct sk_buff *fp;

	BUG_TRAP(fq->last_in&COMPLETE);
	BUG_TRAP(del_timer(&fq->timer) == 0);

	/* Release all fragment data. */
	fp = fq->fragments;
	while (fp) {
		struct sk_buff *xp = fp->next;

		frag_kfree_skb(fp, work);
		fp = xp;
	}

	frag_free_queue(fq, work);
}

static __inline__ void fq_put(struct nf_ct_frag6_queue *fq, unsigned int *work)
{
	if (atomic_dec_and_test(&fq->refcnt))
		nf_ct_frag6_destroy(fq, work);
}

/* Kill fq entry. It is not destroyed immediately,
 * because caller (and someone more) holds reference count.
 */
static __inline__ void fq_kill(struct nf_ct_frag6_queue *fq)
{
	if (del_timer(&fq->timer))
		atomic_dec(&fq->refcnt);

	if (!(fq->last_in & COMPLETE)) {
		fq_unlink(fq);
		atomic_dec(&fq->refcnt);
		fq->last_in |= COMPLETE;
	}
}

static void nf_ct_frag6_evictor(void)
{
	struct nf_ct_frag6_queue *fq;
	struct list_head *tmp;
	unsigned int work;

	work = atomic_read(&nf_ct_frag6_mem);
	if (work <= nf_ct_frag6_low_thresh)
		return;

	work -= nf_ct_frag6_low_thresh;
	while (work > 0) {
		read_lock(&nf_ct_frag6_lock);
		if (list_empty(&nf_ct_frag6_lru_list)) {
			read_unlock(&nf_ct_frag6_lock);
			return;
		}
		tmp = nf_ct_frag6_lru_list.next;
		BUG_ON(tmp == NULL);
		fq = list_entry(tmp, struct nf_ct_frag6_queue, lru_list);
		atomic_inc(&fq->refcnt);
		read_unlock(&nf_ct_frag6_lock);

		spin_lock(&fq->lock);
		if (!(fq->last_in&COMPLETE))
			fq_kill(fq);
		spin_unlock(&fq->lock);

		fq_put(fq, &work);
	}
}

static void nf_ct_frag6_expire(unsigned long data)
{
	struct nf_ct_frag6_queue *fq = (struct nf_ct_frag6_queue *) data;

	spin_lock(&fq->lock);

	if (fq->last_in & COMPLETE)
		goto out;

	fq_kill(fq);

out:
	spin_unlock(&fq->lock);
	fq_put(fq, NULL);
}

/* Creation primitives. */

static struct nf_ct_frag6_queue *nf_ct_frag6_intern(unsigned int hash,
					  struct nf_ct_frag6_queue *fq_in)
{
	struct nf_ct_frag6_queue *fq;
#ifdef CONFIG_SMP
	struct hlist_node *n;
#endif

	write_lock(&nf_ct_frag6_lock);
#ifdef CONFIG_SMP
	hlist_for_each_entry(fq, n, &nf_ct_frag6_hash[hash], list) {
		if (fq->id == fq_in->id && 
		    ipv6_addr_equal(&fq_in->saddr, &fq->saddr) &&
		    ipv6_addr_equal(&fq_in->daddr, &fq->daddr)) {
			atomic_inc(&fq->refcnt);
			write_unlock(&nf_ct_frag6_lock);
			fq_in->last_in |= COMPLETE;
			fq_put(fq_in, NULL);
			return fq;
		}
	}
#endif
	fq = fq_in;

	if (!mod_timer(&fq->timer, jiffies + nf_ct_frag6_timeout))
		atomic_inc(&fq->refcnt);

	atomic_inc(&fq->refcnt);
	hlist_add_head(&fq->list, &nf_ct_frag6_hash[hash]);
	INIT_LIST_HEAD(&fq->lru_list);
	list_add_tail(&fq->lru_list, &nf_ct_frag6_lru_list);
	nf_ct_frag6_nqueues++;
	write_unlock(&nf_ct_frag6_lock);
	return fq;
}


static struct nf_ct_frag6_queue *
nf_ct_frag6_create(unsigned int hash, u32 id, struct in6_addr *src,				   struct in6_addr *dst)
{
	struct nf_ct_frag6_queue *fq;

	if ((fq = frag_alloc_queue()) == NULL) {
		DEBUGP("Can't alloc new queue\n");
		goto oom;
	}

	memset(fq, 0, sizeof(struct nf_ct_frag6_queue));

	fq->id = id;
	ipv6_addr_copy(&fq->saddr, src);
	ipv6_addr_copy(&fq->daddr, dst);

	init_timer(&fq->timer);
	fq->timer.function = nf_ct_frag6_expire;
	fq->timer.data = (long) fq;
	spin_lock_init(&fq->lock);
	atomic_set(&fq->refcnt, 1);

	return nf_ct_frag6_intern(hash, fq);

oom:
	return NULL;
}

static __inline__ struct nf_ct_frag6_queue *
fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst)
{
	struct nf_ct_frag6_queue *fq;
	struct hlist_node *n;
	unsigned int hash = ip6qhashfn(id, src, dst);

	read_lock(&nf_ct_frag6_lock);
	hlist_for_each_entry(fq, n, &nf_ct_frag6_hash[hash], list) {
		if (fq->id == id && 
		    ipv6_addr_equal(src, &fq->saddr) &&
		    ipv6_addr_equal(dst, &fq->daddr)) {
			atomic_inc(&fq->refcnt);
			read_unlock(&nf_ct_frag6_lock);
			return fq;
		}
	}
	read_unlock(&nf_ct_frag6_lock);

	return nf_ct_frag6_create(hash, id, src, dst);
}


static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb, 
			     struct frag_hdr *fhdr, int nhoff)
{
	struct sk_buff *prev, *next;
	int offset, end;

	if (fq->last_in & COMPLETE) {
		DEBUGP("Allready completed\n");
		goto err;
	}

	offset = ntohs(fhdr->frag_off) & ~0x7;
	end = offset + (ntohs(skb->nh.ipv6h->payload_len) -
			((u8 *) (fhdr + 1) - (u8 *) (skb->nh.ipv6h + 1)));

	if ((unsigned int)end > IPV6_MAXPLEN) {
		DEBUGP("offset is too large.\n");
 		return -1;
	}

 	if (skb->ip_summed == CHECKSUM_HW)
 		skb->csum = csum_sub(skb->csum,
 				     csum_partial(skb->nh.raw,
						  (u8*)(fhdr + 1) - skb->nh.raw,
						  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->len ||
		    ((fq->last_in & LAST_IN) && end != fq->len)) {
			DEBUGP("already received last fragment\n");
			goto err;
		}
		fq->last_in |= LAST_IN;
		fq->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
			 */
			DEBUGP("the end of this fragment is not rounded to 8 bytes.\n");
			return -1;
		}
		if (end > fq->len) {
			/* Some bits beyond end -> corruption. */
			if (fq->last_in & LAST_IN) {
				DEBUGP("last packet already reached.\n");
				goto err;
			}
			fq->len = end;
		}
	}

	if (end == offset)
		goto err;

	/* Point into the IP datagram 'data' part. */
	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) {
		DEBUGP("queue: message is too short.\n");
		goto err;
	}
	if (pskb_trim_rcsum(skb, end - offset)) {
		DEBUGP("Can't trim\n");
		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->fragments; next != NULL; next = next->next) {
		if (NFCT_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 = (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset;

		if (i > 0) {
			offset += i;
			if (end <= offset) {
				DEBUGP("overlap\n");
				goto err;
			}
			if (!pskb_pull(skb, i)) {
				DEBUGP("Can't pull\n");
				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 && NFCT_FRAG6_CB(next)->offset < end) {
		/* overlap is 'i' bytes */
		int i = end - NFCT_FRAG6_CB(next)->offset;

		if (i < next->len) {
			/* Eat head of the next overlapped fragment
			 * and leave the loop. The next ones cannot overlap.
			 */
			DEBUGP("Eat head of the overlapped parts.: %d", i);
			if (!pskb_pull(next, i))
				goto err;

			/* next fragment */
			NFCT_FRAG6_CB(next)->offset += i;
			fq->meat -= i;
			if (next->ip_summed != CHECKSUM_UNNECESSARY)
				next->ip_summed = CHECKSUM_NONE;
			break;
		} else {
			struct sk_buff *free_it = next;

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

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

			fq->meat -= free_it->len;
			frag_kfree_skb(free_it, NULL);
		}
	}

	NFCT_FRAG6_CB(skb)->offset = offset;

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

	skb->dev = NULL;
	skb_get_timestamp(skb, &fq->stamp);
	fq->meat += skb->len;
	atomic_add(skb->truesize, &nf_ct_frag6_mem);

	/* The first fragment.
	 * nhoffset is obtained from the first fragment, of course.
	 */
	if (offset == 0) {
		fq->nhoffset = nhoff;
		fq->last_in |= FIRST_IN;
	}
	write_lock(&nf_ct_frag6_lock);
	list_move_tail(&fq->lru_list, &nf_ct_frag6_lru_list);
	write_unlock(&nf_ct_frag6_lock);
	return 0;

err:
	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 struct sk_buff *
nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
{
	struct sk_buff *fp, *op, *head = fq->fragments;
	int    payload_len;

	fq_kill(fq);

	BUG_TRAP(head != NULL);
	BUG_TRAP(NFCT_FRAG6_CB(head)->offset == 0);

	/* Unfragmented part is taken from the first segment. */
	payload_len = (head->data - head->nh.raw) - sizeof(struct ipv6hdr) + fq->len - sizeof(struct frag_hdr);
	if (payload_len > IPV6_MAXPLEN) {
		DEBUGP("payload len is too large.\n");
		goto out_oversize;
	}

	/* Head of list must not be cloned. */
	if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) {
		DEBUGP("skb is cloned but can't expand head");
		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_shinfo(head)->frag_list) {
		struct sk_buff *clone;
		int i, plen = 0;

		if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL) {
			DEBUGP("Can't alloc skb\n");
			goto out_oom;
		}
		clone->next = head->next;
		head->next = clone;
		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
		skb_shinfo(head)->frag_list = NULL;
		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;

		NFCT_FRAG6_CB(clone)->orig = NULL;
		atomic_add(clone->truesize, &nf_ct_frag6_mem);
	}

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

	skb_shinfo(head)->frag_list = head->next;
	head->h.raw = head->data;
	skb_push(head, head->data - head->nh.raw);
	atomic_sub(head->truesize, &nf_ct_frag6_mem);

	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_HW)
			head->csum = csum_add(head->csum, fp->csum);
		head->truesize += fp->truesize;
		atomic_sub(fp->truesize, &nf_ct_frag6_mem);
	}

	head->next = NULL;
	head->dev = dev;
	skb_set_timestamp(head, &fq->stamp);
	head->nh.ipv6h->payload_len = htons(payload_len);

	/* Yes, and fold redundant checksum back. 8) */
	if (head->ip_summed == CHECKSUM_HW)
		head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum);

	fq->fragments = NULL;

	/* all original skbs are linked into the NFCT_FRAG6_CB(head).orig */
	fp = skb_shinfo(head)->frag_list;
	if (NFCT_FRAG6_CB(fp)->orig == NULL)
		/* at above code, head skb is divided into two skbs. */
		fp = fp->next;

	op = NFCT_FRAG6_CB(head)->orig;
	for (; fp; fp = fp->next) {
		struct sk_buff *orig = NFCT_FRAG6_CB(fp)->orig;

		op->next = orig;
		op = orig;
		NFCT_FRAG6_CB(fp)->orig = NULL;
	}

	return head;

out_oversize:
	if (net_ratelimit())
		printk(KERN_DEBUG "nf_ct_frag6_reasm: payload len = %d\n", payload_len);
	goto out_fail;
out_oom:
	if (net_ratelimit())
		printk(KERN_DEBUG "nf_ct_frag6_reasm: no memory for reassembly\n");
out_fail:
	return NULL;
}

/*
 * find the header just before Fragment Header.
 *
 * if success return 0 and set ...
 * (*prevhdrp): the value of "Next Header Field" in the header
 *		just before Fragment Header.
 * (*prevhoff): the offset of "Next Header Field" in the header
 *		just before Fragment Header.
 * (*fhoff)   : the offset of Fragment Header.
 *
 * Based on ipv6_skip_hdr() in net/ipv6/exthdr.c
 *
 */
static int
find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
{
        u8 nexthdr = skb->nh.ipv6h->nexthdr;
	u8 prev_nhoff = (u8 *)&skb->nh.ipv6h->nexthdr - skb->data;
	int start = (u8 *)(skb->nh.ipv6h+1) - skb->data;
	int len = skb->len - start;
	u8 prevhdr = NEXTHDR_IPV6;

        while (nexthdr != NEXTHDR_FRAGMENT) {
                struct ipv6_opt_hdr hdr;
                int hdrlen;

		if (!ipv6_ext_hdr(nexthdr)) {
			return -1;
		}
                if (len < (int)sizeof(struct ipv6_opt_hdr)) {
			DEBUGP("too short\n");
			return -1;
		}
                if (nexthdr == NEXTHDR_NONE) {
			DEBUGP("next header is none\n");
			return -1;
		}
                if (skb_copy_bits(skb, start, &hdr, sizeof(hdr)))
                        BUG();
                if (nexthdr == NEXTHDR_AUTH)
                        hdrlen = (hdr.hdrlen+2)<<2;
                else
                        hdrlen = ipv6_optlen(&hdr);

		prevhdr = nexthdr;
		prev_nhoff = start;

                nexthdr = hdr.nexthdr;
                len -= hdrlen;
                start += hdrlen;
        }

	if (len < 0)
		return -1;

	*prevhdrp = prevhdr;
	*prevhoff = prev_nhoff;
	*fhoff = start;

	return 0;
}

struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb)
{
	struct sk_buff *clone; 
	struct net_device *dev = skb->dev;
	struct frag_hdr *fhdr;
	struct nf_ct_frag6_queue *fq;
	struct ipv6hdr *hdr;
	int fhoff, nhoff;
	u8 prevhdr;
	struct sk_buff *ret_skb = NULL;

	/* Jumbo payload inhibits frag. header */
	if (skb->nh.ipv6h->payload_len == 0) {
		DEBUGP("payload len = 0\n");
		return skb;
	}

	if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
		return skb;

	clone = skb_clone(skb, GFP_ATOMIC);
	if (clone == NULL) {
		DEBUGP("Can't clone skb\n");
		return skb;
	}

	NFCT_FRAG6_CB(clone)->orig = skb;

	if (!pskb_may_pull(clone, fhoff + sizeof(*fhdr))) {
		DEBUGP("message is too short.\n");
		goto ret_orig;
	}

	clone->h.raw = clone->data + fhoff;
	hdr = clone->nh.ipv6h;
	fhdr = (struct frag_hdr *)clone->h.raw;

	if (!(fhdr->frag_off & htons(0xFFF9))) {
		DEBUGP("Invalid fragment offset\n");
		/* It is not a fragmented frame */
		goto ret_orig;
	}

	if (atomic_read(&nf_ct_frag6_mem) > nf_ct_frag6_high_thresh)
		nf_ct_frag6_evictor();

	fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr);
	if (fq == NULL) {
		DEBUGP("Can't find and can't create new queue\n");
		goto ret_orig;
	}

	spin_lock(&fq->lock);

	if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) {
		spin_unlock(&fq->lock);
		DEBUGP("Can't insert skb to queue\n");
		fq_put(fq, NULL);
		goto ret_orig;
	}

	if (fq->last_in == (FIRST_IN|LAST_IN) && fq->meat == fq->len) {
		ret_skb = nf_ct_frag6_reasm(fq, dev);
		if (ret_skb == NULL)
			DEBUGP("Can't reassemble fragmented packets\n");
	}
	spin_unlock(&fq->lock);

	fq_put(fq, NULL);
	return ret_skb;

ret_orig:
	kfree_skb(clone);
	return skb;
}

void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
			struct net_device *in, struct net_device *out,
			int (*okfn)(struct sk_buff *))
{
	struct sk_buff *s, *s2;

	for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
		nf_conntrack_put_reasm(s->nfct_reasm);
		nf_conntrack_get_reasm(skb);
		s->nfct_reasm = skb;

		s2 = s->next;
		NF_HOOK_THRESH(PF_INET6, hooknum, s, in, out, okfn,
			       NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
		s = s2;
	}
	nf_conntrack_put_reasm(skb);
}

int nf_ct_frag6_kfree_frags(struct sk_buff *skb)
{
	struct sk_buff *s, *s2;

	for (s = NFCT_FRAG6_CB(skb)->orig; s; s = s2) {

		s2 = s->next;
		kfree_skb(s);
	}

	kfree_skb(skb);

	return 0;
}

int nf_ct_frag6_init(void)
{
	nf_ct_frag6_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^
				   (jiffies ^ (jiffies >> 6)));

	init_timer(&nf_ct_frag6_secret_timer);
	nf_ct_frag6_secret_timer.function = nf_ct_frag6_secret_rebuild;
	nf_ct_frag6_secret_timer.expires = jiffies
					   + nf_ct_frag6_secret_interval;
	add_timer(&nf_ct_frag6_secret_timer);

	return 0;
}

void nf_ct_frag6_cleanup(void)
{
	del_timer(&nf_ct_frag6_secret_timer);
	nf_ct_frag6_low_thresh = 0;
	nf_ct_frag6_evictor();
}