aboutsummaryrefslogtreecommitdiffstats
path: root/net/netfilter/nf_nat_proto.c
blob: 8284ed1b31735da0c30d3b7341164246d6e59ace (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
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
/* (C) 1999-2001 Paul `Rusty' Russell
 * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/types.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>

#include <linux/dccp.h>
#include <linux/sctp.h>
#include <net/sctp/checksum.h>

#include <linux/netfilter.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_l3proto.h>

#include <linux/ipv6.h>
#include <linux/netfilter_ipv6.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <net/ip6_route.h>
#include <net/xfrm.h>
#include <net/ipv6.h>

#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack.h>
#include <linux/netfilter/nfnetlink_conntrack.h>

static const struct nf_nat_l3proto nf_nat_l3proto_ipv4;
#if IS_ENABLED(CONFIG_IPV6)
static const struct nf_nat_l3proto nf_nat_l3proto_ipv6;
#endif

static void nf_csum_update(struct sk_buff *skb,
			   unsigned int iphdroff, __sum16 *check,
			   const struct nf_conntrack_tuple *t,
			   enum nf_nat_manip_type maniptype);

static void
__udp_manip_pkt(struct sk_buff *skb,
	        unsigned int iphdroff, struct udphdr *hdr,
	        const struct nf_conntrack_tuple *tuple,
	        enum nf_nat_manip_type maniptype, bool do_csum)
{
	__be16 *portptr, newport;

	if (maniptype == NF_NAT_MANIP_SRC) {
		/* Get rid of src port */
		newport = tuple->src.u.udp.port;
		portptr = &hdr->source;
	} else {
		/* Get rid of dst port */
		newport = tuple->dst.u.udp.port;
		portptr = &hdr->dest;
	}
	if (do_csum) {
		nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype);
		inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport,
					 false);
		if (!hdr->check)
			hdr->check = CSUM_MANGLED_0;
	}
	*portptr = newport;
}

static bool udp_manip_pkt(struct sk_buff *skb,
			  unsigned int iphdroff, unsigned int hdroff,
			  const struct nf_conntrack_tuple *tuple,
			  enum nf_nat_manip_type maniptype)
{
	struct udphdr *hdr;
	bool do_csum;

	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
		return false;

	hdr = (struct udphdr *)(skb->data + hdroff);
	do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL;

	__udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, do_csum);
	return true;
}

static bool udplite_manip_pkt(struct sk_buff *skb,
			      unsigned int iphdroff, unsigned int hdroff,
			      const struct nf_conntrack_tuple *tuple,
			      enum nf_nat_manip_type maniptype)
{
#ifdef CONFIG_NF_CT_PROTO_UDPLITE
	struct udphdr *hdr;

	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
		return false;

	hdr = (struct udphdr *)(skb->data + hdroff);
	__udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, true);
#endif
	return true;
}

static bool
sctp_manip_pkt(struct sk_buff *skb,
	       unsigned int iphdroff, unsigned int hdroff,
	       const struct nf_conntrack_tuple *tuple,
	       enum nf_nat_manip_type maniptype)
{
#ifdef CONFIG_NF_CT_PROTO_SCTP
	struct sctphdr *hdr;
	int hdrsize = 8;

	/* This could be an inner header returned in imcp packet; in such
	 * cases we cannot update the checksum field since it is outside
	 * of the 8 bytes of transport layer headers we are guaranteed.
	 */
	if (skb->len >= hdroff + sizeof(*hdr))
		hdrsize = sizeof(*hdr);

	if (!skb_make_writable(skb, hdroff + hdrsize))
		return false;

	hdr = (struct sctphdr *)(skb->data + hdroff);

	if (maniptype == NF_NAT_MANIP_SRC) {
		/* Get rid of src port */
		hdr->source = tuple->src.u.sctp.port;
	} else {
		/* Get rid of dst port */
		hdr->dest = tuple->dst.u.sctp.port;
	}

	if (hdrsize < sizeof(*hdr))
		return true;

	if (skb->ip_summed != CHECKSUM_PARTIAL) {
		hdr->checksum = sctp_compute_cksum(skb, hdroff);
		skb->ip_summed = CHECKSUM_NONE;
	}

#endif
	return true;
}

static bool
tcp_manip_pkt(struct sk_buff *skb,
	      unsigned int iphdroff, unsigned int hdroff,
	      const struct nf_conntrack_tuple *tuple,
	      enum nf_nat_manip_type maniptype)
{
	struct tcphdr *hdr;
	__be16 *portptr, newport, oldport;
	int hdrsize = 8; /* TCP connection tracking guarantees this much */

	/* this could be a inner header returned in icmp packet; in such
	   cases we cannot update the checksum field since it is outside of
	   the 8 bytes of transport layer headers we are guaranteed */
	if (skb->len >= hdroff + sizeof(struct tcphdr))
		hdrsize = sizeof(struct tcphdr);

	if (!skb_make_writable(skb, hdroff + hdrsize))
		return false;

	hdr = (struct tcphdr *)(skb->data + hdroff);

	if (maniptype == NF_NAT_MANIP_SRC) {
		/* Get rid of src port */
		newport = tuple->src.u.tcp.port;
		portptr = &hdr->source;
	} else {
		/* Get rid of dst port */
		newport = tuple->dst.u.tcp.port;
		portptr = &hdr->dest;
	}

	oldport = *portptr;
	*portptr = newport;

	if (hdrsize < sizeof(*hdr))
		return true;

	nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype);
	inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, false);
	return true;
}

static bool
dccp_manip_pkt(struct sk_buff *skb,
	       unsigned int iphdroff, unsigned int hdroff,
	       const struct nf_conntrack_tuple *tuple,
	       enum nf_nat_manip_type maniptype)
{
#ifdef CONFIG_NF_CT_PROTO_DCCP
	struct dccp_hdr *hdr;
	__be16 *portptr, oldport, newport;
	int hdrsize = 8; /* DCCP connection tracking guarantees this much */

	if (skb->len >= hdroff + sizeof(struct dccp_hdr))
		hdrsize = sizeof(struct dccp_hdr);

	if (!skb_make_writable(skb, hdroff + hdrsize))
		return false;

	hdr = (struct dccp_hdr *)(skb->data + hdroff);

	if (maniptype == NF_NAT_MANIP_SRC) {
		newport = tuple->src.u.dccp.port;
		portptr = &hdr->dccph_sport;
	} else {
		newport = tuple->dst.u.dccp.port;
		portptr = &hdr->dccph_dport;
	}

	oldport = *portptr;
	*portptr = newport;

	if (hdrsize < sizeof(*hdr))
		return true;

	nf_csum_update(skb, iphdroff, &hdr->dccph_checksum, tuple, maniptype);
	inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport,
				 false);
#endif
	return true;
}

static bool
icmp_manip_pkt(struct sk_buff *skb,
	       unsigned int iphdroff, unsigned int hdroff,
	       const struct nf_conntrack_tuple *tuple,
	       enum nf_nat_manip_type maniptype)
{
	struct icmphdr *hdr;

	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
		return false;

	hdr = (struct icmphdr *)(skb->data + hdroff);
	inet_proto_csum_replace2(&hdr->checksum, skb,
				 hdr->un.echo.id, tuple->src.u.icmp.id, false);
	hdr->un.echo.id = tuple->src.u.icmp.id;
	return true;
}

static bool
icmpv6_manip_pkt(struct sk_buff *skb,
		 unsigned int iphdroff, unsigned int hdroff,
		 const struct nf_conntrack_tuple *tuple,
		 enum nf_nat_manip_type maniptype)
{
	struct icmp6hdr *hdr;

	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
		return false;

	hdr = (struct icmp6hdr *)(skb->data + hdroff);
	nf_csum_update(skb, iphdroff, &hdr->icmp6_cksum, tuple, maniptype);
	if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST ||
	    hdr->icmp6_type == ICMPV6_ECHO_REPLY) {
		inet_proto_csum_replace2(&hdr->icmp6_cksum, skb,
					 hdr->icmp6_identifier,
					 tuple->src.u.icmp.id, false);
		hdr->icmp6_identifier = tuple->src.u.icmp.id;
	}
	return true;
}

/* manipulate a GRE packet according to maniptype */
static bool
gre_manip_pkt(struct sk_buff *skb,
	      unsigned int iphdroff, unsigned int hdroff,
	      const struct nf_conntrack_tuple *tuple,
	      enum nf_nat_manip_type maniptype)
{
#if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE)
	const struct gre_base_hdr *greh;
	struct pptp_gre_header *pgreh;

	/* pgreh includes two optional 32bit fields which are not required
	 * to be there.  That's where the magic '8' comes from */
	if (!skb_make_writable(skb, hdroff + sizeof(*pgreh) - 8))
		return false;

	greh = (void *)skb->data + hdroff;
	pgreh = (struct pptp_gre_header *)greh;

	/* we only have destination manip of a packet, since 'source key'
	 * is not present in the packet itself */
	if (maniptype != NF_NAT_MANIP_DST)
		return true;

	switch (greh->flags & GRE_VERSION) {
	case GRE_VERSION_0:
		/* We do not currently NAT any GREv0 packets.
		 * Try to behave like "nf_nat_proto_unknown" */
		break;
	case GRE_VERSION_1:
		pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key));
		pgreh->call_id = tuple->dst.u.gre.key;
		break;
	default:
		pr_debug("can't nat unknown GRE version\n");
		return false;
	}
#endif
	return true;
}

static bool l4proto_manip_pkt(struct sk_buff *skb,
			      unsigned int iphdroff, unsigned int hdroff,
			      const struct nf_conntrack_tuple *tuple,
			      enum nf_nat_manip_type maniptype)
{
	switch (tuple->dst.protonum) {
	case IPPROTO_TCP:
		return tcp_manip_pkt(skb, iphdroff, hdroff,
				     tuple, maniptype);
	case IPPROTO_UDP:
		return udp_manip_pkt(skb, iphdroff, hdroff,
				     tuple, maniptype);
	case IPPROTO_UDPLITE:
		return udplite_manip_pkt(skb, iphdroff, hdroff,
					 tuple, maniptype);
	case IPPROTO_SCTP:
		return sctp_manip_pkt(skb, iphdroff, hdroff,
				      tuple, maniptype);
	case IPPROTO_ICMP:
		return icmp_manip_pkt(skb, iphdroff, hdroff,
				      tuple, maniptype);
	case IPPROTO_ICMPV6:
		return icmpv6_manip_pkt(skb, iphdroff, hdroff,
					tuple, maniptype);
	case IPPROTO_DCCP:
		return dccp_manip_pkt(skb, iphdroff, hdroff,
				      tuple, maniptype);
	case IPPROTO_GRE:
		return gre_manip_pkt(skb, iphdroff, hdroff,
				     tuple, maniptype);
	}

	/* If we don't know protocol -- no error, pass it unmodified. */
	return true;
}

static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb,
				  unsigned int iphdroff,
				  const struct nf_conntrack_tuple *target,
				  enum nf_nat_manip_type maniptype)
{
	struct iphdr *iph;
	unsigned int hdroff;

	if (!skb_make_writable(skb, iphdroff + sizeof(*iph)))
		return false;

	iph = (void *)skb->data + iphdroff;
	hdroff = iphdroff + iph->ihl * 4;

	if (!l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype))
		return false;
	iph = (void *)skb->data + iphdroff;

	if (maniptype == NF_NAT_MANIP_SRC) {
		csum_replace4(&iph->check, iph->saddr, target->src.u3.ip);
		iph->saddr = target->src.u3.ip;
	} else {
		csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip);
		iph->daddr = target->dst.u3.ip;
	}
	return true;
}

static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
				  unsigned int iphdroff,
				  const struct nf_conntrack_tuple *target,
				  enum nf_nat_manip_type maniptype)
{
#if IS_ENABLED(CONFIG_IPV6)
	struct ipv6hdr *ipv6h;
	__be16 frag_off;
	int hdroff;
	u8 nexthdr;

	if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h)))
		return false;

	ipv6h = (void *)skb->data + iphdroff;
	nexthdr = ipv6h->nexthdr;
	hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h),
				  &nexthdr, &frag_off);
	if (hdroff < 0)
		goto manip_addr;

	if ((frag_off & htons(~0x7)) == 0 &&
	    !l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype))
		return false;

	/* must reload, offset might have changed */
	ipv6h = (void *)skb->data + iphdroff;

manip_addr:
	if (maniptype == NF_NAT_MANIP_SRC)
		ipv6h->saddr = target->src.u3.in6;
	else
		ipv6h->daddr = target->dst.u3.in6;

#endif
	return true;
}

unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct,
			      enum nf_nat_manip_type mtype,
			      enum ip_conntrack_dir dir)
{
	struct nf_conntrack_tuple target;

	/* We are aiming to look like inverse of other direction. */
	nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple);

	switch (target.src.l3num) {
	case NFPROTO_IPV6:
		if (nf_nat_ipv6_manip_pkt(skb, 0, &target, mtype))
			return NF_ACCEPT;
		break;
	case NFPROTO_IPV4:
		if (nf_nat_ipv4_manip_pkt(skb, 0, &target, mtype))
			return NF_ACCEPT;
		break;
	default:
		WARN_ON_ONCE(1);
		break;
	}

	return NF_DROP;
}

static void nf_nat_ipv4_csum_update(struct sk_buff *skb,
				    unsigned int iphdroff, __sum16 *check,
				    const struct nf_conntrack_tuple *t,
				    enum nf_nat_manip_type maniptype)
{
	struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff);
	__be32 oldip, newip;

	if (maniptype == NF_NAT_MANIP_SRC) {
		oldip = iph->saddr;
		newip = t->src.u3.ip;
	} else {
		oldip = iph->daddr;
		newip = t->dst.u3.ip;
	}
	inet_proto_csum_replace4(check, skb, oldip, newip, true);
}

static void nf_nat_ipv6_csum_update(struct sk_buff *skb,
				    unsigned int iphdroff, __sum16 *check,
				    const struct nf_conntrack_tuple *t,
				    enum nf_nat_manip_type maniptype)
{
#if IS_ENABLED(CONFIG_IPV6)
	const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff);
	const struct in6_addr *oldip, *newip;

	if (maniptype == NF_NAT_MANIP_SRC) {
		oldip = &ipv6h->saddr;
		newip = &t->src.u3.in6;
	} else {
		oldip = &ipv6h->daddr;
		newip = &t->dst.u3.in6;
	}
	inet_proto_csum_replace16(check, skb, oldip->s6_addr32,
				  newip->s6_addr32, true);
#endif
}

static void nf_csum_update(struct sk_buff *skb,
			   unsigned int iphdroff, __sum16 *check,
			   const struct nf_conntrack_tuple *t,
			   enum nf_nat_manip_type maniptype)
{
	switch (t->src.l3num) {
	case NFPROTO_IPV4:
		nf_nat_ipv4_csum_update(skb, iphdroff, check, t, maniptype);
		return;
	case NFPROTO_IPV6:
		nf_nat_ipv6_csum_update(skb, iphdroff, check, t, maniptype);
		return;
	}
}

static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb,
				    u8 proto, void *data, __sum16 *check,
				    int datalen, int oldlen)
{
	if (skb->ip_summed != CHECKSUM_PARTIAL) {
		const struct iphdr *iph = ip_hdr(skb);

		skb->ip_summed = CHECKSUM_PARTIAL;
		skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) +
			ip_hdrlen(skb);
		skb->csum_offset = (void *)check - data;
		*check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen,
					    proto, 0);
	} else {
		inet_proto_csum_replace2(check, skb,
					 htons(oldlen), htons(datalen), true);
	}
}

#if IS_ENABLED(CONFIG_IPV6)
static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb,
				    u8 proto, void *data, __sum16 *check,
				    int datalen, int oldlen)
{
	if (skb->ip_summed != CHECKSUM_PARTIAL) {
		const struct ipv6hdr *ipv6h = ipv6_hdr(skb);

		skb->ip_summed = CHECKSUM_PARTIAL;
		skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) +
			(data - (void *)skb->data);
		skb->csum_offset = (void *)check - data;
		*check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
					  datalen, proto, 0);
	} else {
		inet_proto_csum_replace2(check, skb,
					 htons(oldlen), htons(datalen), true);
	}
}
#endif

void nf_nat_csum_recalc(struct sk_buff *skb,
			u8 nfproto, u8 proto, void *data, __sum16 *check,
			int datalen, int oldlen)
{
	switch (nfproto) {
	case NFPROTO_IPV4:
		nf_nat_ipv4_csum_recalc(skb, proto, data, check,
					datalen, oldlen);
		return;
#if IS_ENABLED(CONFIG_IPV6)
	case NFPROTO_IPV6:
		nf_nat_ipv6_csum_recalc(skb, proto, data, check,
					datalen, oldlen);
		return;
#endif
	}

	WARN_ON_ONCE(1);
}

static const struct nf_nat_l3proto nf_nat_l3proto_ipv4 = {
	.l3proto		= NFPROTO_IPV4,
};

int nf_nat_icmp_reply_translation(struct sk_buff *skb,
				  struct nf_conn *ct,
				  enum ip_conntrack_info ctinfo,
				  unsigned int hooknum)
{
	struct {
		struct icmphdr	icmp;
		struct iphdr	ip;
	} *inside;
	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
	enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
	unsigned int hdrlen = ip_hdrlen(skb);
	struct nf_conntrack_tuple target;
	unsigned long statusbit;

	WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY);

	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
		return 0;
	if (nf_ip_checksum(skb, hooknum, hdrlen, 0))
		return 0;

	inside = (void *)skb->data + hdrlen;
	if (inside->icmp.type == ICMP_REDIRECT) {
		if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK)
			return 0;
		if (ct->status & IPS_NAT_MASK)
			return 0;
	}

	if (manip == NF_NAT_MANIP_SRC)
		statusbit = IPS_SRC_NAT;
	else
		statusbit = IPS_DST_NAT;

	/* Invert if this is reply direction */
	if (dir == IP_CT_DIR_REPLY)
		statusbit ^= IPS_NAT_MASK;

	if (!(ct->status & statusbit))
		return 1;

	if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp),
				   &ct->tuplehash[!dir].tuple, !manip))
		return 0;

	if (skb->ip_summed != CHECKSUM_PARTIAL) {
		/* Reloading "inside" here since manip_pkt may reallocate */
		inside = (void *)skb->data + hdrlen;
		inside->icmp.checksum = 0;
		inside->icmp.checksum =
			csum_fold(skb_checksum(skb, hdrlen,
					       skb->len - hdrlen, 0));
	}

	/* Change outer to look like the reply to an incoming packet */
	nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple);
	target.dst.protonum = IPPROTO_ICMP;
	if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip))
		return 0;

	return 1;
}
EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);

static unsigned int
nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
	       const struct nf_hook_state *state)
{
	struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;

	ct = nf_ct_get(skb, &ctinfo);
	if (!ct)
		return NF_ACCEPT;

	if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) {
		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
							   state->hook))
				return NF_DROP;
			else
				return NF_ACCEPT;
		}
	}

	return nf_nat_inet_fn(priv, skb, state);
}

static unsigned int
nf_nat_ipv4_in(void *priv, struct sk_buff *skb,
	       const struct nf_hook_state *state)
{
	unsigned int ret;
	__be32 daddr = ip_hdr(skb)->daddr;

	ret = nf_nat_ipv4_fn(priv, skb, state);
	if (ret == NF_ACCEPT && daddr != ip_hdr(skb)->daddr)
		skb_dst_drop(skb);

	return ret;
}

static unsigned int
nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
		const struct nf_hook_state *state)
{
#ifdef CONFIG_XFRM
	const struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;
	int err;
#endif
	unsigned int ret;

	ret = nf_nat_ipv4_fn(priv, skb, state);
#ifdef CONFIG_XFRM
	if (ret != NF_ACCEPT)
		return ret;

	if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
		return ret;

	ct = nf_ct_get(skb, &ctinfo);
	if (ct) {
		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);

		if (ct->tuplehash[dir].tuple.src.u3.ip !=
		     ct->tuplehash[!dir].tuple.dst.u3.ip ||
		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
		     ct->tuplehash[dir].tuple.src.u.all !=
		     ct->tuplehash[!dir].tuple.dst.u.all)) {
			err = nf_xfrm_me_harder(state->net, skb, AF_INET);
			if (err < 0)
				ret = NF_DROP_ERR(err);
		}
	}
#endif
	return ret;
}

static unsigned int
nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
		     const struct nf_hook_state *state)
{
	const struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;
	unsigned int ret;
	int err;

	ret = nf_nat_ipv4_fn(priv, skb, state);
	if (ret != NF_ACCEPT)
		return ret;

	ct = nf_ct_get(skb, &ctinfo);
	if (ct) {
		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);

		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
		    ct->tuplehash[!dir].tuple.src.u3.ip) {
			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
			if (err < 0)
				ret = NF_DROP_ERR(err);
		}
#ifdef CONFIG_XFRM
		else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
			 ct->tuplehash[dir].tuple.dst.u.all !=
			 ct->tuplehash[!dir].tuple.src.u.all) {
			err = nf_xfrm_me_harder(state->net, skb, AF_INET);
			if (err < 0)
				ret = NF_DROP_ERR(err);
		}
#endif
	}
	return ret;
}

static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
	/* Before packet filtering, change destination */
	{
		.hook		= nf_nat_ipv4_in,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_PRE_ROUTING,
		.priority	= NF_IP_PRI_NAT_DST,
	},
	/* After packet filtering, change source */
	{
		.hook		= nf_nat_ipv4_out,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_POST_ROUTING,
		.priority	= NF_IP_PRI_NAT_SRC,
	},
	/* Before packet filtering, change destination */
	{
		.hook		= nf_nat_ipv4_local_fn,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP_PRI_NAT_DST,
	},
	/* After packet filtering, change source */
	{
		.hook		= nf_nat_ipv4_fn,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP_PRI_NAT_SRC,
	},
};

int nf_nat_l3proto_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops)
{
	return nf_nat_register_fn(net, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_register_fn);

void nf_nat_l3proto_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
{
	nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_unregister_fn);

int nf_nat_l3proto_init(void)
{
	int ret = nf_nat_l3proto_register(&nf_nat_l3proto_ipv4);

#if IS_ENABLED(CONFIG_IPV6)
	if (ret)
		return ret;

	ret = nf_nat_l3proto_register(&nf_nat_l3proto_ipv6);
	if (ret == 0)
		return ret;

	nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv4);
#endif
	return ret;
}

void nf_nat_l3proto_exit(void)
{
#if IS_ENABLED(CONFIG_IPV6)
	nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv6);
#endif
	nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv4);
}

#if IS_ENABLED(CONFIG_IPV6)
static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = {
	.l3proto		= NFPROTO_IPV6,
};

int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
				    struct nf_conn *ct,
				    enum ip_conntrack_info ctinfo,
				    unsigned int hooknum,
				    unsigned int hdrlen)
{
	struct {
		struct icmp6hdr	icmp6;
		struct ipv6hdr	ip6;
	} *inside;
	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
	enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
	struct nf_conntrack_tuple target;
	unsigned long statusbit;

	WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY);

	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
		return 0;
	if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6))
		return 0;

	inside = (void *)skb->data + hdrlen;
	if (inside->icmp6.icmp6_type == NDISC_REDIRECT) {
		if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK)
			return 0;
		if (ct->status & IPS_NAT_MASK)
			return 0;
	}

	if (manip == NF_NAT_MANIP_SRC)
		statusbit = IPS_SRC_NAT;
	else
		statusbit = IPS_DST_NAT;

	/* Invert if this is reply direction */
	if (dir == IP_CT_DIR_REPLY)
		statusbit ^= IPS_NAT_MASK;

	if (!(ct->status & statusbit))
		return 1;

	if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6),
				   &ct->tuplehash[!dir].tuple, !manip))
		return 0;

	if (skb->ip_summed != CHECKSUM_PARTIAL) {
		struct ipv6hdr *ipv6h = ipv6_hdr(skb);

		inside = (void *)skb->data + hdrlen;
		inside->icmp6.icmp6_cksum = 0;
		inside->icmp6.icmp6_cksum =
			csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
					skb->len - hdrlen, IPPROTO_ICMPV6,
					skb_checksum(skb, hdrlen,
						     skb->len - hdrlen, 0));
	}

	nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple);
	target.dst.protonum = IPPROTO_ICMPV6;
	if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip))
		return 0;

	return 1;
}
EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation);

static unsigned int
nf_nat_ipv6_fn(void *priv, struct sk_buff *skb,
	       const struct nf_hook_state *state)
{
	struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;
	__be16 frag_off;
	int hdrlen;
	u8 nexthdr;

	ct = nf_ct_get(skb, &ctinfo);
	/* Can't track?  It's not due to stress, or conntrack would
	 * have dropped it.  Hence it's the user's responsibilty to
	 * packet filter it out, or implement conntrack/NAT for that
	 * protocol. 8) --RR
	 */
	if (!ct)
		return NF_ACCEPT;

	if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) {
		nexthdr = ipv6_hdr(skb)->nexthdr;
		hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
					  &nexthdr, &frag_off);

		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
							     state->hook,
							     hdrlen))
				return NF_DROP;
			else
				return NF_ACCEPT;
		}
	}

	return nf_nat_inet_fn(priv, skb, state);
}

static unsigned int
nf_nat_ipv6_in(void *priv, struct sk_buff *skb,
	       const struct nf_hook_state *state)
{
	unsigned int ret;
	struct in6_addr daddr = ipv6_hdr(skb)->daddr;

	ret = nf_nat_ipv6_fn(priv, skb, state);
	if (ret != NF_DROP && ret != NF_STOLEN &&
	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
		skb_dst_drop(skb);

	return ret;
}

static unsigned int
nf_nat_ipv6_out(void *priv, struct sk_buff *skb,
		const struct nf_hook_state *state)
{
#ifdef CONFIG_XFRM
	const struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;
	int err;
#endif
	unsigned int ret;

	ret = nf_nat_ipv6_fn(priv, skb, state);
#ifdef CONFIG_XFRM
	if (ret != NF_ACCEPT)
		return ret;

	if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
		return ret;
	ct = nf_ct_get(skb, &ctinfo);
	if (ct) {
		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);

		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
				      &ct->tuplehash[!dir].tuple.dst.u3) ||
		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
		     ct->tuplehash[dir].tuple.src.u.all !=
		     ct->tuplehash[!dir].tuple.dst.u.all)) {
			err = nf_xfrm_me_harder(state->net, skb, AF_INET6);
			if (err < 0)
				ret = NF_DROP_ERR(err);
		}
	}
#endif

	return ret;
}

static int nat_route_me_harder(struct net *net, struct sk_buff *skb)
{
#ifdef CONFIG_IPV6_MODULE
	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();

	if (!v6_ops)
		return -EHOSTUNREACH;

	return v6_ops->route_me_harder(net, skb);
#else
	return ip6_route_me_harder(net, skb);
#endif
}

static unsigned int
nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
		     const struct nf_hook_state *state)
{
	const struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;
	unsigned int ret;
	int err;

	ret = nf_nat_ipv6_fn(priv, skb, state);
	if (ret != NF_ACCEPT)
		return ret;

	ct = nf_ct_get(skb, &ctinfo);
	if (ct) {
		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);

		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
				      &ct->tuplehash[!dir].tuple.src.u3)) {
			err = nat_route_me_harder(state->net, skb);
			if (err < 0)
				ret = NF_DROP_ERR(err);
		}
#ifdef CONFIG_XFRM
		else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
			 ct->tuplehash[dir].tuple.dst.u.all !=
			 ct->tuplehash[!dir].tuple.src.u.all) {
			err = nf_xfrm_me_harder(state->net, skb, AF_INET6);
			if (err < 0)
				ret = NF_DROP_ERR(err);
		}
#endif
	}

	return ret;
}

static const struct nf_hook_ops nf_nat_ipv6_ops[] = {
	/* Before packet filtering, change destination */
	{
		.hook		= nf_nat_ipv6_in,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_PRE_ROUTING,
		.priority	= NF_IP6_PRI_NAT_DST,
	},
	/* After packet filtering, change source */
	{
		.hook		= nf_nat_ipv6_out,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_POST_ROUTING,
		.priority	= NF_IP6_PRI_NAT_SRC,
	},
	/* Before packet filtering, change destination */
	{
		.hook		= nf_nat_ipv6_local_fn,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP6_PRI_NAT_DST,
	},
	/* After packet filtering, change source */
	{
		.hook		= nf_nat_ipv6_fn,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP6_PRI_NAT_SRC,
	},
};

int nf_nat_l3proto_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops)
{
	return nf_nat_register_fn(net, ops, nf_nat_ipv6_ops,
				  ARRAY_SIZE(nf_nat_ipv6_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv6_register_fn);

void nf_nat_l3proto_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
{
	nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv6_unregister_fn);
#endif /* CONFIG_IPV6 */