Free Electrons

Embedded Linux Experts

  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
971
972
973
974
975
976
977
978
979
980
981
/*
 *	Internet Control Message Protocol (ICMPv6)
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	Based on net/ipv4/icmp.c
 *
 *	RFC 1885
 *
 *	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:
 *
 *	Andi Kleen		:	exception handling
 *	Andi Kleen			add rate limits. never reply to a icmp.
 *					add more length checks and other fixes.
 *	yoshfuji		:	ensure to sent parameter problem for
 *					fragments.
 *	YOSHIFUJI Hideaki @USAGI:	added sysctl for icmp rate limit.
 *	Randy Dunlap and
 *	YOSHIFUJI Hideaki @USAGI:	Per-interface statistics support
 *	Kazunori MIYAZAWA @USAGI:       change output process to use ip6_append_data
 */

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/netfilter.h>
#include <linux/slab.h>

#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/icmpv6.h>

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

#include <net/ipv6.h>
#include <net/ip6_checksum.h>
#include <net/protocol.h>
#include <net/raw.h>
#include <net/rawv6.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/inet_common.h>

#include <asm/uaccess.h>

/*
 *	The ICMP socket(s). This is the most convenient way to flow control
 *	our ICMP output as well as maintain a clean interface throughout
 *	all layers. All Socketless IP sends will soon be gone.
 *
 *	On SMP we have one ICMP socket per-cpu.
 */
static inline struct sock *icmpv6_sk(struct net *net)
{
	return net->ipv6.icmp_sk[smp_processor_id()];
}

static int icmpv6_rcv(struct sk_buff *skb);

static const struct inet6_protocol icmpv6_protocol = {
	.handler	=	icmpv6_rcv,
	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};

static __inline__ struct sock *icmpv6_xmit_lock(struct net *net)
{
	struct sock *sk;

	local_bh_disable();

	sk = icmpv6_sk(net);
	if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
		/* This can happen if the output path (f.e. SIT or
		 * ip6ip6 tunnel) signals dst_link_failure() for an
		 * outgoing ICMP6 packet.
		 */
		local_bh_enable();
		return NULL;
	}
	return sk;
}

static __inline__ void icmpv6_xmit_unlock(struct sock *sk)
{
	spin_unlock_bh(&sk->sk_lock.slock);
}

/*
 * Slightly more convenient version of icmpv6_send.
 */
void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
{
	icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos);
	kfree_skb(skb);
}

/*
 * Figure out, may we reply to this packet with icmp error.
 *
 * We do not reply, if:
 *	- it was icmp error message.
 *	- it is truncated, so that it is known, that protocol is ICMPV6
 *	  (i.e. in the middle of some exthdr)
 *
 *	--ANK (980726)
 */

static int is_ineligible(struct sk_buff *skb)
{
	int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data;
	int len = skb->len - ptr;
	__u8 nexthdr = ipv6_hdr(skb)->nexthdr;
	__be16 frag_off;

	if (len < 0)
		return 1;

	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off);
	if (ptr < 0)
		return 0;
	if (nexthdr == IPPROTO_ICMPV6) {
		u8 _type, *tp;
		tp = skb_header_pointer(skb,
			ptr+offsetof(struct icmp6hdr, icmp6_type),
			sizeof(_type), &_type);
		if (tp == NULL ||
		    !(*tp & ICMPV6_INFOMSG_MASK))
			return 1;
	}
	return 0;
}

/*
 * Check the ICMP output rate limit
 */
static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
				      struct flowi6 *fl6)
{
	struct dst_entry *dst;
	struct net *net = sock_net(sk);
	bool res = false;

	/* Informational messages are not limited. */
	if (type & ICMPV6_INFOMSG_MASK)
		return true;

	/* Do not limit pmtu discovery, it would break it. */
	if (type == ICMPV6_PKT_TOOBIG)
		return true;

	/*
	 * Look up the output route.
	 * XXX: perhaps the expire for routing entries cloned by
	 * this lookup should be more aggressive (not longer than timeout).
	 */
	dst = ip6_route_output(net, sk, fl6);
	if (dst->error) {
		IP6_INC_STATS(net, ip6_dst_idev(dst),
			      IPSTATS_MIB_OUTNOROUTES);
	} else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) {
		res = true;
	} else {
		struct rt6_info *rt = (struct rt6_info *)dst;
		int tmo = net->ipv6.sysctl.icmpv6_time;

		/* Give more bandwidth to wider prefixes. */
		if (rt->rt6i_dst.plen < 128)
			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);

		if (!rt->rt6i_peer)
			rt6_bind_peer(rt, 1);
		res = inet_peer_xrlim_allow(rt->rt6i_peer, tmo);
	}
	dst_release(dst);
	return res;
}

/*
 *	an inline helper for the "simple" if statement below
 *	checks if parameter problem report is caused by an
 *	unrecognized IPv6 option that has the Option Type
 *	highest-order two bits set to 10
 */

static __inline__ int opt_unrec(struct sk_buff *skb, __u32 offset)
{
	u8 _optval, *op;

	offset += skb_network_offset(skb);
	op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval);
	if (op == NULL)
		return 1;
	return (*op & 0xC0) == 0x80;
}

static int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len)
{
	struct sk_buff *skb;
	struct icmp6hdr *icmp6h;
	int err = 0;

	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
		goto out;

	icmp6h = icmp6_hdr(skb);
	memcpy(icmp6h, thdr, sizeof(struct icmp6hdr));
	icmp6h->icmp6_cksum = 0;

	if (skb_queue_len(&sk->sk_write_queue) == 1) {
		skb->csum = csum_partial(icmp6h,
					sizeof(struct icmp6hdr), skb->csum);
		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr,
						      &fl6->daddr,
						      len, fl6->flowi6_proto,
						      skb->csum);
	} else {
		__wsum tmp_csum = 0;

		skb_queue_walk(&sk->sk_write_queue, skb) {
			tmp_csum = csum_add(tmp_csum, skb->csum);
		}

		tmp_csum = csum_partial(icmp6h,
					sizeof(struct icmp6hdr), tmp_csum);
		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr,
						      &fl6->daddr,
						      len, fl6->flowi6_proto,
						      tmp_csum);
	}
	ip6_push_pending_frames(sk);
out:
	return err;
}

struct icmpv6_msg {
	struct sk_buff	*skb;
	int		offset;
	uint8_t		type;
};

static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
{
	struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
	struct sk_buff *org_skb = msg->skb;
	__wsum csum = 0;

	csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
				      to, len, csum);
	skb->csum = csum_block_add(skb->csum, csum, odd);
	if (!(msg->type & ICMPV6_INFOMSG_MASK))
		nf_ct_attach(skb, org_skb);
	return 0;
}

#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
static void mip6_addr_swap(struct sk_buff *skb)
{
	struct ipv6hdr *iph = ipv6_hdr(skb);
	struct inet6_skb_parm *opt = IP6CB(skb);
	struct ipv6_destopt_hao *hao;
	struct in6_addr tmp;
	int off;

	if (opt->dsthao) {
		off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO);
		if (likely(off >= 0)) {
			hao = (struct ipv6_destopt_hao *)
					(skb_network_header(skb) + off);
			tmp = iph->saddr;
			iph->saddr = hao->addr;
			hao->addr = tmp;
		}
	}
}
#else
static inline void mip6_addr_swap(struct sk_buff *skb) {}
#endif

static struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
					     struct sock *sk, struct flowi6 *fl6)
{
	struct dst_entry *dst, *dst2;
	struct flowi6 fl2;
	int err;

	err = ip6_dst_lookup(sk, &dst, fl6);
	if (err)
		return ERR_PTR(err);

	/*
	 * We won't send icmp if the destination is known
	 * anycast.
	 */
	if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: acast source\n");
		dst_release(dst);
		return ERR_PTR(-EINVAL);
	}

	/* No need to clone since we're just using its address. */
	dst2 = dst;

	dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), sk, 0);
	if (!IS_ERR(dst)) {
		if (dst != dst2)
			return dst;
	} else {
		if (PTR_ERR(dst) == -EPERM)
			dst = NULL;
		else
			return dst;
	}

	err = xfrm_decode_session_reverse(skb, flowi6_to_flowi(&fl2), AF_INET6);
	if (err)
		goto relookup_failed;

	err = ip6_dst_lookup(sk, &dst2, &fl2);
	if (err)
		goto relookup_failed;

	dst2 = xfrm_lookup(net, dst2, flowi6_to_flowi(&fl2), sk, XFRM_LOOKUP_ICMP);
	if (!IS_ERR(dst2)) {
		dst_release(dst);
		dst = dst2;
	} else {
		err = PTR_ERR(dst2);
		if (err == -EPERM) {
			dst_release(dst);
			return dst2;
		} else
			goto relookup_failed;
	}

relookup_failed:
	if (dst)
		return dst;
	return ERR_PTR(err);
}

/*
 *	Send an ICMP message in response to a packet in error
 */
void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
{
	struct net *net = dev_net(skb->dev);
	struct inet6_dev *idev = NULL;
	struct ipv6hdr *hdr = ipv6_hdr(skb);
	struct sock *sk;
	struct ipv6_pinfo *np;
	const struct in6_addr *saddr = NULL;
	struct dst_entry *dst;
	struct icmp6hdr tmp_hdr;
	struct flowi6 fl6;
	struct icmpv6_msg msg;
	int iif = 0;
	int addr_type = 0;
	int len;
	int hlimit;
	int err = 0;

	if ((u8 *)hdr < skb->head ||
	    (skb->network_header + sizeof(*hdr)) > skb->tail)
		return;

	/*
	 *	Make sure we respect the rules
	 *	i.e. RFC 1885 2.4(e)
	 *	Rule (e.1) is enforced by not using icmpv6_send
	 *	in any code that processes icmp errors.
	 */
	addr_type = ipv6_addr_type(&hdr->daddr);

	if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0))
		saddr = &hdr->daddr;

	/*
	 *	Dest addr check
	 */

	if ((addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST)) {
		if (type != ICMPV6_PKT_TOOBIG &&
		    !(type == ICMPV6_PARAMPROB &&
		      code == ICMPV6_UNK_OPTION &&
		      (opt_unrec(skb, info))))
			return;

		saddr = NULL;
	}

	addr_type = ipv6_addr_type(&hdr->saddr);

	/*
	 *	Source addr check
	 */

	if (addr_type & IPV6_ADDR_LINKLOCAL)
		iif = skb->dev->ifindex;

	/*
	 *	Must not send error if the source does not uniquely
	 *	identify a single node (RFC2463 Section 2.4).
	 *	We check unspecified / multicast addresses here,
	 *	and anycast addresses will be checked later.
	 */
	if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n");
		return;
	}

	/*
	 *	Never answer to a ICMP packet.
	 */
	if (is_ineligible(skb)) {
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: no reply to icmp error\n");
		return;
	}

	mip6_addr_swap(skb);

	memset(&fl6, 0, sizeof(fl6));
	fl6.flowi6_proto = IPPROTO_ICMPV6;
	fl6.daddr = hdr->saddr;
	if (saddr)
		fl6.saddr = *saddr;
	fl6.flowi6_oif = iif;
	fl6.fl6_icmp_type = type;
	fl6.fl6_icmp_code = code;
	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));

	sk = icmpv6_xmit_lock(net);
	if (sk == NULL)
		return;
	np = inet6_sk(sk);

	if (!icmpv6_xrlim_allow(sk, type, &fl6))
		goto out;

	tmp_hdr.icmp6_type = type;
	tmp_hdr.icmp6_code = code;
	tmp_hdr.icmp6_cksum = 0;
	tmp_hdr.icmp6_pointer = htonl(info);

	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
		fl6.flowi6_oif = np->mcast_oif;
	else if (!fl6.flowi6_oif)
		fl6.flowi6_oif = np->ucast_oif;

	dst = icmpv6_route_lookup(net, skb, sk, &fl6);
	if (IS_ERR(dst))
		goto out;

	if (ipv6_addr_is_multicast(&fl6.daddr))
		hlimit = np->mcast_hops;
	else
		hlimit = np->hop_limit;
	if (hlimit < 0)
		hlimit = ip6_dst_hoplimit(dst);

	msg.skb = skb;
	msg.offset = skb_network_offset(skb);
	msg.type = type;

	len = skb->len - msg.offset;
	len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr));
	if (len < 0) {
		LIMIT_NETDEBUG(KERN_DEBUG "icmp: len problem\n");
		goto out_dst_release;
	}

	rcu_read_lock();
	idev = __in6_dev_get(skb->dev);

	err = ip6_append_data(sk, icmpv6_getfrag, &msg,
			      len + sizeof(struct icmp6hdr),
			      sizeof(struct icmp6hdr), hlimit,
			      np->tclass, NULL, &fl6, (struct rt6_info*)dst,
			      MSG_DONTWAIT, np->dontfrag);
	if (err) {
		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
		ip6_flush_pending_frames(sk);
	} else {
		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
						 len + sizeof(struct icmp6hdr));
	}
	rcu_read_unlock();
out_dst_release:
	dst_release(dst);
out:
	icmpv6_xmit_unlock(sk);
}
EXPORT_SYMBOL(icmpv6_send);

static void icmpv6_echo_reply(struct sk_buff *skb)
{
	struct net *net = dev_net(skb->dev);
	struct sock *sk;
	struct inet6_dev *idev;
	struct ipv6_pinfo *np;
	const struct in6_addr *saddr = NULL;
	struct icmp6hdr *icmph = icmp6_hdr(skb);
	struct icmp6hdr tmp_hdr;
	struct flowi6 fl6;
	struct icmpv6_msg msg;
	struct dst_entry *dst;
	int err = 0;
	int hlimit;

	saddr = &ipv6_hdr(skb)->daddr;

	if (!ipv6_unicast_destination(skb))
		saddr = NULL;

	memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
	tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY;

	memset(&fl6, 0, sizeof(fl6));
	fl6.flowi6_proto = IPPROTO_ICMPV6;
	fl6.daddr = ipv6_hdr(skb)->saddr;
	if (saddr)
		fl6.saddr = *saddr;
	fl6.flowi6_oif = skb->dev->ifindex;
	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));

	sk = icmpv6_xmit_lock(net);
	if (sk == NULL)
		return;
	np = inet6_sk(sk);

	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
		fl6.flowi6_oif = np->mcast_oif;
	else if (!fl6.flowi6_oif)
		fl6.flowi6_oif = np->ucast_oif;

	err = ip6_dst_lookup(sk, &dst, &fl6);
	if (err)
		goto out;
	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
	if (IS_ERR(dst))
		goto out;

	if (ipv6_addr_is_multicast(&fl6.daddr))
		hlimit = np->mcast_hops;
	else
		hlimit = np->hop_limit;
	if (hlimit < 0)
		hlimit = ip6_dst_hoplimit(dst);

	idev = __in6_dev_get(skb->dev);

	msg.skb = skb;
	msg.offset = 0;
	msg.type = ICMPV6_ECHO_REPLY;

	err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
				sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl6,
				(struct rt6_info*)dst, MSG_DONTWAIT,
				np->dontfrag);

	if (err) {
		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
		ip6_flush_pending_frames(sk);
	} else {
		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
						 skb->len + sizeof(struct icmp6hdr));
	}
	dst_release(dst);
out:
	icmpv6_xmit_unlock(sk);
}

static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
{
	const struct inet6_protocol *ipprot;
	int inner_offset;
	int hash;
	u8 nexthdr;
	__be16 frag_off;

	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
		return;

	nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
	if (ipv6_ext_hdr(nexthdr)) {
		/* now skip over extension headers */
		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
						&nexthdr, &frag_off);
		if (inner_offset<0)
			return;
	} else {
		inner_offset = sizeof(struct ipv6hdr);
	}

	/* Checkin header including 8 bytes of inner protocol header. */
	if (!pskb_may_pull(skb, inner_offset+8))
		return;

	/* BUGGG_FUTURE: we should try to parse exthdrs in this packet.
	   Without this we will not able f.e. to make source routed
	   pmtu discovery.
	   Corresponding argument (opt) to notifiers is already added.
	   --ANK (980726)
	 */

	hash = nexthdr & (MAX_INET_PROTOS - 1);

	rcu_read_lock();
	ipprot = rcu_dereference(inet6_protos[hash]);
	if (ipprot && ipprot->err_handler)
		ipprot->err_handler(skb, NULL, type, code, inner_offset, info);
	rcu_read_unlock();

	raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info);
}

/*
 *	Handle icmp messages
 */

static int icmpv6_rcv(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct inet6_dev *idev = __in6_dev_get(dev);
	const struct in6_addr *saddr, *daddr;
	const struct ipv6hdr *orig_hdr;
	struct icmp6hdr *hdr;
	u8 type;

	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
		struct sec_path *sp = skb_sec_path(skb);
		int nh;

		if (!(sp && sp->xvec[sp->len - 1]->props.flags &
				 XFRM_STATE_ICMP))
			goto drop_no_count;

		if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(*orig_hdr)))
			goto drop_no_count;

		nh = skb_network_offset(skb);
		skb_set_network_header(skb, sizeof(*hdr));

		if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb))
			goto drop_no_count;

		skb_set_network_header(skb, nh);
	}

	ICMP6_INC_STATS_BH(dev_net(dev), idev, ICMP6_MIB_INMSGS);

	saddr = &ipv6_hdr(skb)->saddr;
	daddr = &ipv6_hdr(skb)->daddr;

	/* Perform checksum. */
	switch (skb->ip_summed) {
	case CHECKSUM_COMPLETE:
		if (!csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
				     skb->csum))
			break;
		/* fall through */
	case CHECKSUM_NONE:
		skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len,
					     IPPROTO_ICMPV6, 0));
		if (__skb_checksum_complete(skb)) {
			LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%pI6 > %pI6]\n",
				       saddr, daddr);
			goto discard_it;
		}
	}

	if (!pskb_pull(skb, sizeof(*hdr)))
		goto discard_it;

	hdr = icmp6_hdr(skb);

	type = hdr->icmp6_type;

	ICMP6MSGIN_INC_STATS_BH(dev_net(dev), idev, type);

	switch (type) {
	case ICMPV6_ECHO_REQUEST:
		icmpv6_echo_reply(skb);
		break;

	case ICMPV6_ECHO_REPLY:
		/* we couldn't care less */
		break;

	case ICMPV6_PKT_TOOBIG:
		/* BUGGG_FUTURE: if packet contains rthdr, we cannot update
		   standard destination cache. Seems, only "advanced"
		   destination cache will allow to solve this problem
		   --ANK (980726)
		 */
		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
			goto discard_it;
		hdr = icmp6_hdr(skb);
		orig_hdr = (struct ipv6hdr *) (hdr + 1);
		rt6_pmtu_discovery(&orig_hdr->daddr, &orig_hdr->saddr, dev,
				   ntohl(hdr->icmp6_mtu));

		/*
		 *	Drop through to notify
		 */

	case ICMPV6_DEST_UNREACH:
	case ICMPV6_TIME_EXCEED:
	case ICMPV6_PARAMPROB:
		icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
		break;

	case NDISC_ROUTER_SOLICITATION:
	case NDISC_ROUTER_ADVERTISEMENT:
	case NDISC_NEIGHBOUR_SOLICITATION:
	case NDISC_NEIGHBOUR_ADVERTISEMENT:
	case NDISC_REDIRECT:
		ndisc_rcv(skb);
		break;

	case ICMPV6_MGM_QUERY:
		igmp6_event_query(skb);
		break;

	case ICMPV6_MGM_REPORT:
		igmp6_event_report(skb);
		break;

	case ICMPV6_MGM_REDUCTION:
	case ICMPV6_NI_QUERY:
	case ICMPV6_NI_REPLY:
	case ICMPV6_MLD2_REPORT:
	case ICMPV6_DHAAD_REQUEST:
	case ICMPV6_DHAAD_REPLY:
	case ICMPV6_MOBILE_PREFIX_SOL:
	case ICMPV6_MOBILE_PREFIX_ADV:
		break;

	default:
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6: msg of unknown type\n");

		/* informational */
		if (type & ICMPV6_INFOMSG_MASK)
			break;

		/*
		 * error of unknown type.
		 * must pass to upper level
		 */

		icmpv6_notify(skb, type, hdr->icmp6_code, hdr->icmp6_mtu);
	}

	kfree_skb(skb);
	return 0;

discard_it:
	ICMP6_INC_STATS_BH(dev_net(dev), idev, ICMP6_MIB_INERRORS);
drop_no_count:
	kfree_skb(skb);
	return 0;
}

void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
		      u8 type,
		      const struct in6_addr *saddr,
		      const struct in6_addr *daddr,
		      int oif)
{
	memset(fl6, 0, sizeof(*fl6));
	fl6->saddr = *saddr;
	fl6->daddr = *daddr;
	fl6->flowi6_proto 	= IPPROTO_ICMPV6;
	fl6->fl6_icmp_type	= type;
	fl6->fl6_icmp_code	= 0;
	fl6->flowi6_oif		= oif;
	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
}

/*
 * Special lock-class for __icmpv6_sk:
 */
static struct lock_class_key icmpv6_socket_sk_dst_lock_key;

static int __net_init icmpv6_sk_init(struct net *net)
{
	struct sock *sk;
	int err, i, j;

	net->ipv6.icmp_sk =
		kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL);
	if (net->ipv6.icmp_sk == NULL)
		return -ENOMEM;

	for_each_possible_cpu(i) {
		err = inet_ctl_sock_create(&sk, PF_INET6,
					   SOCK_RAW, IPPROTO_ICMPV6, net);
		if (err < 0) {
			printk(KERN_ERR
			       "Failed to initialize the ICMP6 control socket "
			       "(err %d).\n",
			       err);
			goto fail;
		}

		net->ipv6.icmp_sk[i] = sk;

		/*
		 * Split off their lock-class, because sk->sk_dst_lock
		 * gets used from softirqs, which is safe for
		 * __icmpv6_sk (because those never get directly used
		 * via userspace syscalls), but unsafe for normal sockets.
		 */
		lockdep_set_class(&sk->sk_dst_lock,
				  &icmpv6_socket_sk_dst_lock_key);

		/* Enough space for 2 64K ICMP packets, including
		 * sk_buff struct overhead.
		 */
		sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024);
	}
	return 0;

 fail:
	for (j = 0; j < i; j++)
		inet_ctl_sock_destroy(net->ipv6.icmp_sk[j]);
	kfree(net->ipv6.icmp_sk);
	return err;
}

static void __net_exit icmpv6_sk_exit(struct net *net)
{
	int i;

	for_each_possible_cpu(i) {
		inet_ctl_sock_destroy(net->ipv6.icmp_sk[i]);
	}
	kfree(net->ipv6.icmp_sk);
}

static struct pernet_operations icmpv6_sk_ops = {
       .init = icmpv6_sk_init,
       .exit = icmpv6_sk_exit,
};

int __init icmpv6_init(void)
{
	int err;

	err = register_pernet_subsys(&icmpv6_sk_ops);
	if (err < 0)
		return err;

	err = -EAGAIN;
	if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0)
		goto fail;
	return 0;

fail:
	printk(KERN_ERR "Failed to register ICMP6 protocol\n");
	unregister_pernet_subsys(&icmpv6_sk_ops);
	return err;
}

void icmpv6_cleanup(void)
{
	unregister_pernet_subsys(&icmpv6_sk_ops);
	inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
}


static const struct icmp6_err {
	int err;
	int fatal;
} tab_unreach[] = {
	{	/* NOROUTE */
		.err	= ENETUNREACH,
		.fatal	= 0,
	},
	{	/* ADM_PROHIBITED */
		.err	= EACCES,
		.fatal	= 1,
	},
	{	/* Was NOT_NEIGHBOUR, now reserved */
		.err	= EHOSTUNREACH,
		.fatal	= 0,
	},
	{	/* ADDR_UNREACH	*/
		.err	= EHOSTUNREACH,
		.fatal	= 0,
	},
	{	/* PORT_UNREACH	*/
		.err	= ECONNREFUSED,
		.fatal	= 1,
	},
};

int icmpv6_err_convert(u8 type, u8 code, int *err)
{
	int fatal = 0;

	*err = EPROTO;

	switch (type) {
	case ICMPV6_DEST_UNREACH:
		fatal = 1;
		if (code <= ICMPV6_PORT_UNREACH) {
			*err  = tab_unreach[code].err;
			fatal = tab_unreach[code].fatal;
		}
		break;

	case ICMPV6_PKT_TOOBIG:
		*err = EMSGSIZE;
		break;

	case ICMPV6_PARAMPROB:
		*err = EPROTO;
		fatal = 1;
		break;

	case ICMPV6_TIME_EXCEED:
		*err = EHOSTUNREACH;
		break;
	}

	return fatal;
}

EXPORT_SYMBOL(icmpv6_err_convert);

#ifdef CONFIG_SYSCTL
ctl_table ipv6_icmp_table_template[] = {
	{
		.procname	= "ratelimit",
		.data		= &init_net.ipv6.sysctl.icmpv6_time,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_ms_jiffies,
	},
	{ },
};

struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
{
	struct ctl_table *table;

	table = kmemdup(ipv6_icmp_table_template,
			sizeof(ipv6_icmp_table_template),
			GFP_KERNEL);

	if (table)
		table[0].data = &net->ipv6.sysctl.icmpv6_time;

	return table;
}
#endif