summaryrefslogtreecommitdiff
path: root/net/ipv6/exthdrs.c
blob: a6a275db88cdd8aa315f2e5a7b14911342ee7345 (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
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
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
/*
 *	Extension Header handling for IPv6
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *	Andi Kleen		<ak@muc.de>
 *	Alexey Kuznetsov	<kuznet@ms2.inr.ac.ru>
 *
 *	$Id: exthdrs.c,v 1.13 2001/06/19 15:58:56 davem Exp $
 *
 *	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.
 */

/* Changes:
 *	yoshfuji		: ensure not to overrun while parsing
 *				  tlv options.
 *	Mitsuru KANDA @USAGI and: Remove ipv6_parse_exthdrs().
 *	YOSHIFUJI Hideaki @USAGI  Register inbound extension header
 *				  handlers as inet6_protocol{}.
 */

#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/icmpv6.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/ip6_route.h>
#include <net/addrconf.h>
#ifdef CONFIG_IPV6_MIP6
#include <net/xfrm.h>
#endif

#include <asm/uaccess.h>

int ipv6_find_tlv(struct sk_buff *skb, int offset, int type)
{
	const unsigned char *nh = skb_network_header(skb);
	int packet_len = skb->tail - nh;
	struct ipv6_opt_hdr *hdr;
	int len;

	if (offset + 2 > packet_len)
		goto bad;
	hdr = (struct ipv6_opt_hdr *)(nh + offset);
	len = ((hdr->hdrlen + 1) << 3);

	if (offset + len > packet_len)
		goto bad;

	offset += 2;
	len -= 2;

	while (len > 0) {
		int opttype = nh[offset];
		int optlen;

		if (opttype == type)
			return offset;

		switch (opttype) {
		case IPV6_TLV_PAD0:
			optlen = 1;
			break;
		default:
			optlen = nh[offset + 1] + 2;
			if (optlen > len)
				goto bad;
			break;
		}
		offset += optlen;
		len -= optlen;
	}
	/* not_found */
 bad:
	return -1;
}

/*
 *	Parsing tlv encoded headers.
 *
 *	Parsing function "func" returns 1, if parsing succeed
 *	and 0, if it failed.
 *	It MUST NOT touch skb->h.
 */

struct tlvtype_proc {
	int	type;
	int	(*func)(struct sk_buff **skbp, int offset);
};

/*********************
  Generic functions
 *********************/

/* An unknown option is detected, decide what to do */

static int ip6_tlvopt_unknown(struct sk_buff **skbp, int optoff)
{
	struct sk_buff *skb = *skbp;

	switch ((skb_network_header(skb)[optoff] & 0xC0) >> 6) {
	case 0: /* ignore */
		return 1;

	case 1: /* drop packet */
		break;

	case 3: /* Send ICMP if not a multicast address and drop packet */
		/* Actually, it is redundant check. icmp_send
		   will recheck in any case.
		 */
		if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr))
			break;
	case 2: /* send ICMP PARM PROB regardless and drop packet */
		icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff);
		return 0;
	};

	kfree_skb(skb);
	return 0;
}

/* Parse tlv encoded option header (hop-by-hop or destination) */

static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff **skbp)
{
	struct sk_buff *skb = *skbp;
	struct tlvtype_proc *curr;
	const unsigned char *nh = skb_network_header(skb);
	int off = skb_network_header_len(skb);
	int len = (skb_transport_header(skb)[1] + 1) << 3;

	if (skb_transport_offset(skb) + len > skb_headlen(skb))
		goto bad;

	off += 2;
	len -= 2;

	while (len > 0) {
		int optlen = nh[off + 1] + 2;

		switch (nh[off]) {
		case IPV6_TLV_PAD0:
			optlen = 1;
			break;

		case IPV6_TLV_PADN:
			break;

		default: /* Other TLV code so scan list */
			if (optlen > len)
				goto bad;
			for (curr=procs; curr->type >= 0; curr++) {
				if (curr->type == nh[off]) {
					/* type specific length/alignment
					   checks will be performed in the
					   func(). */
					if (curr->func(skbp, off) == 0)
						return 0;
					break;
				}
			}
			if (curr->type < 0) {
				if (ip6_tlvopt_unknown(skbp, off) == 0)
					return 0;
			}
			break;
		}
		off += optlen;
		len -= optlen;
	}
	if (len == 0)
		return 1;
bad:
	kfree_skb(skb);
	return 0;
}

/*****************************
  Destination options header.
 *****************************/

#ifdef CONFIG_IPV6_MIP6
static int ipv6_dest_hao(struct sk_buff **skbp, int optoff)
{
	struct sk_buff *skb = *skbp;
	struct ipv6_destopt_hao *hao;
	struct inet6_skb_parm *opt = IP6CB(skb);
	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
	struct in6_addr tmp_addr;
	int ret;

	if (opt->dsthao) {
		LIMIT_NETDEBUG(KERN_DEBUG "hao duplicated\n");
		goto discard;
	}
	opt->dsthao = opt->dst1;
	opt->dst1 = 0;

	hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff);

	if (hao->length != 16) {
		LIMIT_NETDEBUG(
			KERN_DEBUG "hao invalid option length = %d\n", hao->length);
		goto discard;
	}

	if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) {
		LIMIT_NETDEBUG(
			KERN_DEBUG "hao is not an unicast addr: " NIP6_FMT "\n", NIP6(hao->addr));
		goto discard;
	}

	ret = xfrm6_input_addr(skb, (xfrm_address_t *)&ipv6h->daddr,
			       (xfrm_address_t *)&hao->addr, IPPROTO_DSTOPTS);
	if (unlikely(ret < 0))
		goto discard;

	if (skb_cloned(skb)) {
		struct sk_buff *skb2 = skb_copy(skb, GFP_ATOMIC);
		struct inet6_skb_parm *opt2;

		if (skb2 == NULL)
			goto discard;

		opt2 = IP6CB(skb2);
		memcpy(opt2, opt, sizeof(*opt2));

		kfree_skb(skb);

		/* update all variable using below by copied skbuff */
		*skbp = skb = skb2;
		hao = (struct ipv6_destopt_hao *)(skb_network_header(skb2) +
						  optoff);
		ipv6h = ipv6_hdr(skb2);
	}

	if (skb->ip_summed == CHECKSUM_COMPLETE)
		skb->ip_summed = CHECKSUM_NONE;

	ipv6_addr_copy(&tmp_addr, &ipv6h->saddr);
	ipv6_addr_copy(&ipv6h->saddr, &hao->addr);
	ipv6_addr_copy(&hao->addr, &tmp_addr);

	if (skb->tstamp.tv64 == 0)
		__net_timestamp(skb);

	return 1;

 discard:
	kfree_skb(skb);
	return 0;
}
#endif

static struct tlvtype_proc tlvprocdestopt_lst[] = {
#ifdef CONFIG_IPV6_MIP6
	{
		.type	= IPV6_TLV_HAO,
		.func	= ipv6_dest_hao,
	},
#endif
	{-1,			NULL}
};

static int ipv6_destopt_rcv(struct sk_buff **skbp)
{
	struct sk_buff *skb = *skbp;
	struct inet6_skb_parm *opt = IP6CB(skb);
#ifdef CONFIG_IPV6_MIP6
	__u16 dstbuf;
#endif
	struct dst_entry *dst;

	if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) ||
	    !pskb_may_pull(skb, (skb_transport_offset(skb) +
				 ((skb_transport_header(skb)[1] + 1) << 3)))) {
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
				 IPSTATS_MIB_INHDRERRORS);
		kfree_skb(skb);
		return -1;
	}

	opt->lastopt = opt->dst1 = skb_network_header_len(skb);
#ifdef CONFIG_IPV6_MIP6
	dstbuf = opt->dst1;
#endif

	dst = dst_clone(skb->dst);
	if (ip6_parse_tlv(tlvprocdestopt_lst, skbp)) {
		dst_release(dst);
		skb = *skbp;
		skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3;
		opt = IP6CB(skb);
#ifdef CONFIG_IPV6_MIP6
		opt->nhoff = dstbuf;
#else
		opt->nhoff = opt->dst1;
#endif
		return 1;
	}

	IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);
	dst_release(dst);
	return -1;
}

static struct inet6_protocol destopt_protocol = {
	.handler	=	ipv6_destopt_rcv,
	.flags		=	INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR,
};

void __init ipv6_destopt_init(void)
{
	if (inet6_add_protocol(&destopt_protocol, IPPROTO_DSTOPTS) < 0)
		printk(KERN_ERR "ipv6_destopt_init: Could not register protocol\n");
}

/********************************
  NONE header. No data in packet.
 ********************************/

static int ipv6_nodata_rcv(struct sk_buff **skbp)
{
	struct sk_buff *skb = *skbp;

	kfree_skb(skb);
	return 0;
}

static struct inet6_protocol nodata_protocol = {
	.handler	=	ipv6_nodata_rcv,
	.flags		=	INET6_PROTO_NOPOLICY,
};

void __init ipv6_nodata_init(void)
{
	if (inet6_add_protocol(&nodata_protocol, IPPROTO_NONE) < 0)
		printk(KERN_ERR "ipv6_nodata_init: Could not register protocol\n");
}

/********************************
  Routing header.
 ********************************/

static int ipv6_rthdr_rcv(struct sk_buff **skbp)
{
	struct sk_buff *skb = *skbp;
	struct inet6_skb_parm *opt = IP6CB(skb);
	struct in6_addr *addr = NULL;
	struct in6_addr daddr;
	struct inet6_dev *idev;
	int n, i;
	struct ipv6_rt_hdr *hdr;
	struct rt0_hdr *rthdr;
	int accept_source_route = ipv6_devconf.accept_source_route;

	if (accept_source_route < 0 ||
	    ((idev = in6_dev_get(skb->dev)) == NULL)) {
		kfree_skb(skb);
		return -1;
	}
	if (idev->cnf.accept_source_route < 0) {
		in6_dev_put(idev);
		kfree_skb(skb);
		return -1;
	}

	if (accept_source_route > idev->cnf.accept_source_route)
		accept_source_route = idev->cnf.accept_source_route;

	in6_dev_put(idev);

	if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) ||
	    !pskb_may_pull(skb, (skb_transport_offset(skb) +
				 ((skb_transport_header(skb)[1] + 1) << 3)))) {
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
				 IPSTATS_MIB_INHDRERRORS);
		kfree_skb(skb);
		return -1;
	}

	hdr = (struct ipv6_rt_hdr *)skb_transport_header(skb);

	switch (hdr->type) {
#ifdef CONFIG_IPV6_MIP6
		break;
#endif
	case IPV6_SRCRT_TYPE_0:
		if (accept_source_route > 0)
			break;
		kfree_skb(skb);
		return -1;
	default:
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
				 IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
				  (&hdr->type) - skb_network_header(skb));
		return -1;
	}

	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) ||
	    skb->pkt_type != PACKET_HOST) {
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
				 IPSTATS_MIB_INADDRERRORS);
		kfree_skb(skb);
		return -1;
	}

looped_back:
	if (hdr->segments_left == 0) {
		switch (hdr->type) {
#ifdef CONFIG_IPV6_MIP6
		case IPV6_SRCRT_TYPE_2:
			/* Silently discard type 2 header unless it was
			 * processed by own
			 */
			if (!addr) {
				IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
						 IPSTATS_MIB_INADDRERRORS);
				kfree_skb(skb);
				return -1;
			}
			break;
#endif
		default:
			break;
		}

		opt->lastopt = opt->srcrt = skb_network_header_len(skb);
		skb->transport_header += (hdr->hdrlen + 1) << 3;
		opt->dst0 = opt->dst1;
		opt->dst1 = 0;
		opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb);
		return 1;
	}

	switch (hdr->type) {
	case IPV6_SRCRT_TYPE_0:
		if (hdr->hdrlen & 0x01) {
			IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
					 IPSTATS_MIB_INHDRERRORS);
			icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
					  ((&hdr->hdrlen) -
					   skb_network_header(skb)));
			return -1;
		}
		break;
#ifdef CONFIG_IPV6_MIP6
	case IPV6_SRCRT_TYPE_2:
		/* Silently discard invalid RTH type 2 */
		if (hdr->hdrlen != 2 || hdr->segments_left != 1) {
			IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
					 IPSTATS_MIB_INHDRERRORS);
			kfree_skb(skb);
			return -1;
		}
		break;
#endif
	}

	/*
	 *	This is the routing header forwarding algorithm from
	 *	RFC 2460, page 16.
	 */

	n = hdr->hdrlen >> 1;

	if (hdr->segments_left > n) {
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
				 IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
				  ((&hdr->segments_left) -
				   skb_network_header(skb)));
		return -1;
	}

	/* We are about to mangle packet header. Be careful!
	   Do not damage packets queued somewhere.
	 */
	if (skb_cloned(skb)) {
		struct sk_buff *skb2 = skb_copy(skb, GFP_ATOMIC);
		/* the copy is a forwarded packet */
		if (skb2 == NULL) {
			IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
					 IPSTATS_MIB_OUTDISCARDS);
			kfree_skb(skb);
			return -1;
		}
		kfree_skb(skb);
		*skbp = skb = skb2;
		opt = IP6CB(skb2);
		hdr = (struct ipv6_rt_hdr *)skb_transport_header(skb2);
	}

	if (skb->ip_summed == CHECKSUM_COMPLETE)
		skb->ip_summed = CHECKSUM_NONE;

	i = n - --hdr->segments_left;

	rthdr = (struct rt0_hdr *) hdr;
	addr = rthdr->addr;
	addr += i - 1;

	switch (hdr->type) {
#ifdef CONFIG_IPV6_MIP6
	case IPV6_SRCRT_TYPE_2:
		if (xfrm6_input_addr(skb, (xfrm_address_t *)addr,
				     (xfrm_address_t *)&ipv6_hdr(skb)->saddr,
				     IPPROTO_ROUTING) < 0) {
			IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
					 IPSTATS_MIB_INADDRERRORS);
			kfree_skb(skb);
			return -1;
		}
		if (!ipv6_chk_home_addr(addr)) {
			IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
					 IPSTATS_MIB_INADDRERRORS);
			kfree_skb(skb);
			return -1;
		}
		break;
#endif
	default:
		break;
	}

	if (ipv6_addr_is_multicast(addr)) {
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
				 IPSTATS_MIB_INADDRERRORS);
		kfree_skb(skb);
		return -1;
	}

	ipv6_addr_copy(&daddr, addr);
	ipv6_addr_copy(addr, &ipv6_hdr(skb)->daddr);
	ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &daddr);

	dst_release(xchg(&skb->dst, NULL));
	ip6_route_input(skb);
	if (skb->dst->error) {
		skb_push(skb, skb->data - skb_network_header(skb));
		dst_input(skb);
		return -1;
	}

	if (skb->dst->dev->flags&IFF_LOOPBACK) {
		if (ipv6_hdr(skb)->hop_limit <= 1) {
			IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
					 IPSTATS_MIB_INHDRERRORS);
			icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
				    0, skb->dev);
			kfree_skb(skb);
			return -1;
		}
		ipv6_hdr(skb)->hop_limit--;
		goto looped_back;
	}

	skb_push(skb, skb->data - skb_network_header(skb));
	dst_input(skb);
	return -1;
}

static struct inet6_protocol rthdr_protocol = {
	.handler	=	ipv6_rthdr_rcv,
	.flags		=	INET6_PROTO_NOPOLICY | INET6_PROTO_GSO_EXTHDR,
};

void __init ipv6_rthdr_init(void)
{
	if (inet6_add_protocol(&rthdr_protocol, IPPROTO_ROUTING) < 0)
		printk(KERN_ERR "ipv6_rthdr_init: Could not register protocol\n");
};

/*
   This function inverts received rthdr.
   NOTE: specs allow to make it automatically only if
   packet authenticated.

   I will not discuss it here (though, I am really pissed off at
   this stupid requirement making rthdr idea useless)

   Actually, it creates severe problems  for us.
   Embryonic requests has no associated sockets,
   so that user have no control over it and
   cannot not only to set reply options, but
   even to know, that someone wants to connect
   without success. :-(

   For now we need to test the engine, so that I created
   temporary (or permanent) backdoor.
   If listening socket set IPV6_RTHDR to 2, then we invert header.
						   --ANK (980729)
 */

struct ipv6_txoptions *
ipv6_invert_rthdr(struct sock *sk, struct ipv6_rt_hdr *hdr)
{
	/* Received rthdr:

	   [ H1 -> H2 -> ... H_prev ]  daddr=ME

	   Inverted result:
	   [ H_prev -> ... -> H1 ] daddr =sender

	   Note, that IP output engine will rewrite this rthdr
	   by rotating it left by one addr.
	 */

	int n, i;
	struct rt0_hdr *rthdr = (struct rt0_hdr*)hdr;
	struct rt0_hdr *irthdr;
	struct ipv6_txoptions *opt;
	int hdrlen = ipv6_optlen(hdr);

	if (hdr->segments_left ||
	    hdr->type != IPV6_SRCRT_TYPE_0 ||
	    hdr->hdrlen & 0x01)
		return NULL;

	n = hdr->hdrlen >> 1;
	opt = sock_kmalloc(sk, sizeof(*opt) + hdrlen, GFP_ATOMIC);
	if (opt == NULL)
		return NULL;
	memset(opt, 0, sizeof(*opt));
	opt->tot_len = sizeof(*opt) + hdrlen;
	opt->srcrt = (void*)(opt+1);
	opt->opt_nflen = hdrlen;

	memcpy(opt->srcrt, hdr, sizeof(*hdr));
	irthdr = (struct rt0_hdr*)opt->srcrt;
	irthdr->reserved = 0;
	opt->srcrt->segments_left = n;
	for (i=0; i<n; i++)
		memcpy(irthdr->addr+i, rthdr->addr+(n-1-i), 16);
	return opt;
}

EXPORT_SYMBOL_GPL(ipv6_invert_rthdr);

/**********************************
  Hop-by-hop options.
 **********************************/

/* Router Alert as of RFC 2711 */

static int ipv6_hop_ra(struct sk_buff **skbp, int optoff)
{
	struct sk_buff *skb = *skbp;
	const unsigned char *nh = skb_network_header(skb);

	if (nh[optoff + 1] == 2) {
		IP6CB(skb)->ra = optoff;
		return 1;
	}
	LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n",
		       nh[optoff + 1]);
	kfree_skb(skb);
	return 0;
}

/* Jumbo payload */

static int ipv6_hop_jumbo(struct sk_buff **skbp, int optoff)
{
	struct sk_buff *skb = *skbp;
	const unsigned char *nh = skb_network_header(skb);
	u32 pkt_len;

	if (nh[optoff + 1] != 4 || (optoff & 3) != 2) {
		LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n",
			       nh[optoff+1]);
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst),
				 IPSTATS_MIB_INHDRERRORS);
		goto drop;
	}

	pkt_len = ntohl(*(__be32 *)(nh + optoff + 2));
	if (pkt_len <= IPV6_MAXPLEN) {
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff+2);
		return 0;
	}
	if (ipv6_hdr(skb)->payload_len) {
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS);
		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff);
		return 0;
	}

	if (pkt_len > skb->len - sizeof(struct ipv6hdr)) {
		IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INTRUNCATEDPKTS);
		goto drop;
	}

	if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
		goto drop;

	return 1;

drop:
	kfree_skb(skb);
	return 0;
}

static struct tlvtype_proc tlvprochopopt_lst[] = {
	{
		.type	= IPV6_TLV_ROUTERALERT,
		.func	= ipv6_hop_ra,
	},
	{
		.type	= IPV6_TLV_JUMBO,
		.func	= ipv6_hop_jumbo,
	},
	{ -1, }
};

int ipv6_parse_hopopts(struct sk_buff **skbp)
{
	struct sk_buff *skb = *skbp;
	struct inet6_skb_parm *opt = IP6CB(skb);

	/*
	 * skb_network_header(skb) is equal to skb->data, and
	 * skb_network_header_len(skb) is always equal to
	 * sizeof(struct ipv6hdr) by definition of
	 * hop-by-hop options.
	 */
	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + 8) ||
	    !pskb_may_pull(skb, (sizeof(struct ipv6hdr) +
				 ((skb_transport_header(skb)[1] + 1) << 3)))) {
		kfree_skb(skb);
		return -1;
	}

	opt->hop = sizeof(struct ipv6hdr);
	if (ip6_parse_tlv(tlvprochopopt_lst, skbp)) {
		skb = *skbp;
		skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3;
		opt = IP6CB(skb);
		opt->nhoff = sizeof(struct ipv6hdr);
		return 1;
	}
	return -1;
}

/*
 *	Creating outbound headers.
 *
 *	"build" functions work when skb is filled from head to tail (datagram)
 *	"push"	functions work when headers are added from tail to head (tcp)
 *
 *	In both cases we assume, that caller reserved enough room
 *	for headers.
 */

static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
			    struct ipv6_rt_hdr *opt,
			    struct in6_addr **addr_p)
{
	struct rt0_hdr *phdr, *ihdr;
	int hops;

	ihdr = (struct rt0_hdr *) opt;

	phdr = (struct rt0_hdr *) skb_push(skb, (ihdr->rt_hdr.hdrlen + 1) << 3);
	memcpy(phdr, ihdr, sizeof(struct rt0_hdr));

	hops = ihdr->rt_hdr.hdrlen >> 1;

	if (hops > 1)
		memcpy(phdr->addr, ihdr->addr + 1,
		       (hops - 1) * sizeof(struct in6_addr));

	ipv6_addr_copy(phdr->addr + (hops - 1), *addr_p);
	*addr_p = ihdr->addr;

	phdr->rt_hdr.nexthdr = *proto;
	*proto = NEXTHDR_ROUTING;
}

static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv6_opt_hdr *opt)
{
	struct ipv6_opt_hdr *h = (struct ipv6_opt_hdr *)skb_push(skb, ipv6_optlen(opt));

	memcpy(h, opt, ipv6_optlen(opt));
	h->nexthdr = *proto;
	*proto = type;
}

void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
			  u8 *proto,
			  struct in6_addr **daddr)
{
	if (opt->srcrt) {
		ipv6_push_rthdr(skb, proto, opt->srcrt, daddr);
		/*
		 * IPV6_RTHDRDSTOPTS is ignored
		 * unless IPV6_RTHDR is set (RFC3542).
		 */
		if (opt->dst0opt)
			ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst0opt);
	}
	if (opt->hopopt)
		ipv6_push_exthdr(skb, proto, NEXTHDR_HOP, opt->hopopt);
}

EXPORT_SYMBOL(ipv6_push_nfrag_opts);

void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto)
{
	if (opt->dst1opt)
		ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst1opt);
}

struct ipv6_txoptions *
ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
{
	struct ipv6_txoptions *opt2;

	opt2 = sock_kmalloc(sk, opt->tot_len, GFP_ATOMIC);
	if (opt2) {
		long dif = (char*)opt2 - (char*)opt;
		memcpy(opt2, opt, opt->tot_len);
		if (opt2->hopopt)
			*((char**)&opt2->hopopt) += dif;
		if (opt2->dst0opt)
			*((char**)&opt2->dst0opt) += dif;
		if (opt2->dst1opt)
			*((char**)&opt2->dst1opt) += dif;
		if (opt2->srcrt)
			*((char**)&opt2->srcrt) += dif;
	}
	return opt2;
}

EXPORT_SYMBOL_GPL(ipv6_dup_options);

static int ipv6_renew_option(void *ohdr,
			     struct ipv6_opt_hdr __user *newopt, int newoptlen,
			     int inherit,
			     struct ipv6_opt_hdr **hdr,
			     char **p)
{
	if (inherit) {
		if (ohdr) {
			memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr));
			*hdr = (struct ipv6_opt_hdr *)*p;
			*p += CMSG_ALIGN(ipv6_optlen(*(struct ipv6_opt_hdr **)hdr));
		}
	} else {
		if (newopt) {
			if (copy_from_user(*p, newopt, newoptlen))
				return -EFAULT;
			*hdr = (struct ipv6_opt_hdr *)*p;
			if (ipv6_optlen(*(struct ipv6_opt_hdr **)hdr) > newoptlen)
				return -EINVAL;
			*p += CMSG_ALIGN(newoptlen);
		}
	}
	return 0;
}

struct ipv6_txoptions *
ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
		   int newtype,
		   struct ipv6_opt_hdr __user *newopt, int newoptlen)
{
	int tot_len = 0;
	char *p;
	struct ipv6_txoptions *opt2;
	int err;

	if (opt) {
		if (newtype != IPV6_HOPOPTS && opt->hopopt)
			tot_len += CMSG_ALIGN(ipv6_optlen(opt->hopopt));
		if (newtype != IPV6_RTHDRDSTOPTS && opt->dst0opt)
			tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst0opt));
		if (newtype != IPV6_RTHDR && opt->srcrt)
			tot_len += CMSG_ALIGN(ipv6_optlen(opt->srcrt));
		if (newtype != IPV6_DSTOPTS && opt->dst1opt)
			tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt));
	}

	if (newopt && newoptlen)
		tot_len += CMSG_ALIGN(newoptlen);

	if (!tot_len)
		return NULL;

	tot_len += sizeof(*opt2);
	opt2 = sock_kmalloc(sk, tot_len, GFP_ATOMIC);
	if (!opt2)
		return ERR_PTR(-ENOBUFS);

	memset(opt2, 0, tot_len);

	opt2->tot_len = tot_len;
	p = (char *)(opt2 + 1);

	err = ipv6_renew_option(opt ? opt->hopopt : NULL, newopt, newoptlen,
				newtype != IPV6_HOPOPTS,
				&opt2->hopopt, &p);
	if (err)
		goto out;

	err = ipv6_renew_option(opt ? opt->dst0opt : NULL, newopt, newoptlen,
				newtype != IPV6_RTHDRDSTOPTS,
				&opt2->dst0opt, &p);
	if (err)
		goto out;

	err = ipv6_renew_option(opt ? opt->srcrt : NULL, newopt, newoptlen,
				newtype != IPV6_RTHDR,
				(struct ipv6_opt_hdr **)&opt2->srcrt, &p);
	if (err)
		goto out;

	err = ipv6_renew_option(opt ? opt->dst1opt : NULL, newopt, newoptlen,
				newtype != IPV6_DSTOPTS,
				&opt2->dst1opt, &p);
	if (err)
		goto out;

	opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) +
			  (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) +
			  (opt2->srcrt ? ipv6_optlen(opt2->srcrt) : 0);
	opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0);

	return opt2;
out:
	sock_kfree_s(sk, opt2, opt2->tot_len);
	return ERR_PTR(err);
}

struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
					  struct ipv6_txoptions *opt)
{
	/*
	 * ignore the dest before srcrt unless srcrt is being included.
	 * --yoshfuji
	 */
	if (opt && opt->dst0opt && !opt->srcrt) {
		if (opt_space != opt) {
			memcpy(opt_space, opt, sizeof(*opt_space));
			opt = opt_space;
		}
		opt->opt_nflen -= ipv6_optlen(opt->dst0opt);
		opt->dst0opt = NULL;
	}

	return opt;
}