summaryrefslogtreecommitdiff
path: root/net/ipv4/ip_tunnel_core.c
blob: cc1caab4a654921a267bac1cca56bb91244b9ea9 (plain)
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
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2013 Nicira, Inc.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/netfilter_ipv4.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/static_key.h>

#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ip_tunnels.h>
#include <net/ip6_tunnel.h>
#include <net/ip6_checksum.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/dst_metadata.h>
#include <net/geneve.h>
#include <net/vxlan.h>
#include <net/erspan.h>

const struct ip_tunnel_encap_ops __rcu *
		iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
EXPORT_SYMBOL(iptun_encaps);

const struct ip6_tnl_encap_ops __rcu *
		ip6tun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
EXPORT_SYMBOL(ip6tun_encaps);

void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
		   __be32 src, __be32 dst, __u8 proto,
		   __u8 tos, __u8 ttl, __be16 df, bool xnet)
{
	int pkt_len = skb->len - skb_inner_network_offset(skb);
	struct net *net = dev_net(rt->dst.dev);
	struct net_device *dev = skb->dev;
	struct iphdr *iph;
	int err;

	skb_scrub_packet(skb, xnet);

	skb_clear_hash_if_not_l4(skb);
	skb_dst_set(skb, &rt->dst);
	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));

	/* Push down and install the IP header. */
	skb_push(skb, sizeof(struct iphdr));
	skb_reset_network_header(skb);

	iph = ip_hdr(skb);

	iph->version	=	4;
	iph->ihl	=	sizeof(struct iphdr) >> 2;
	iph->frag_off	=	ip_mtu_locked(&rt->dst) ? 0 : df;
	iph->protocol	=	proto;
	iph->tos	=	tos;
	iph->daddr	=	dst;
	iph->saddr	=	src;
	iph->ttl	=	ttl;
	__ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1);

	err = ip_local_out(net, sk, skb);

	if (dev) {
		if (unlikely(net_xmit_eval(err)))
			pkt_len = 0;
		iptunnel_xmit_stats(dev, pkt_len);
	}
}
EXPORT_SYMBOL_GPL(iptunnel_xmit);

int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
			   __be16 inner_proto, bool raw_proto, bool xnet)
{
	if (unlikely(!pskb_may_pull(skb, hdr_len)))
		return -ENOMEM;

	skb_pull_rcsum(skb, hdr_len);

	if (!raw_proto && inner_proto == htons(ETH_P_TEB)) {
		struct ethhdr *eh;

		if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
			return -ENOMEM;

		eh = (struct ethhdr *)skb->data;
		if (likely(eth_proto_is_802_3(eh->h_proto)))
			skb->protocol = eh->h_proto;
		else
			skb->protocol = htons(ETH_P_802_2);

	} else {
		skb->protocol = inner_proto;
	}

	skb_clear_hash_if_not_l4(skb);
	__vlan_hwaccel_clear_tag(skb);
	skb_set_queue_mapping(skb, 0);
	skb_scrub_packet(skb, xnet);

	return iptunnel_pull_offloads(skb);
}
EXPORT_SYMBOL_GPL(__iptunnel_pull_header);

struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
					     gfp_t flags)
{
	struct metadata_dst *res;
	struct ip_tunnel_info *dst, *src;

	if (!md || md->type != METADATA_IP_TUNNEL ||
	    md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
		return NULL;

	src = &md->u.tun_info;
	res = metadata_dst_alloc(src->options_len, METADATA_IP_TUNNEL, flags);
	if (!res)
		return NULL;

	dst = &res->u.tun_info;
	dst->key.tun_id = src->key.tun_id;
	if (src->mode & IP_TUNNEL_INFO_IPV6)
		memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src,
		       sizeof(struct in6_addr));
	else
		dst->key.u.ipv4.dst = src->key.u.ipv4.src;
	dst->key.tun_flags = src->key.tun_flags;
	dst->mode = src->mode | IP_TUNNEL_INFO_TX;
	ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src),
				src->options_len, 0);

	return res;
}
EXPORT_SYMBOL_GPL(iptunnel_metadata_reply);

int iptunnel_handle_offloads(struct sk_buff *skb,
			     int gso_type_mask)
{
	int err;

	if (likely(!skb->encapsulation)) {
		skb_reset_inner_headers(skb);
		skb->encapsulation = 1;
	}

	if (skb_is_gso(skb)) {
		err = skb_header_unclone(skb, GFP_ATOMIC);
		if (unlikely(err))
			return err;
		skb_shinfo(skb)->gso_type |= gso_type_mask;
		return 0;
	}

	if (skb->ip_summed != CHECKSUM_PARTIAL) {
		skb->ip_summed = CHECKSUM_NONE;
		/* We clear encapsulation here to prevent badly-written
		 * drivers potentially deciding to offload an inner checksum
		 * if we set CHECKSUM_PARTIAL on the outer header.
		 * This should go away when the drivers are all fixed.
		 */
		skb->encapsulation = 0;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);

/**
 * iptunnel_pmtud_build_icmp() - Build ICMP error message for PMTUD
 * @skb:	Original packet with L2 header
 * @mtu:	MTU value for ICMP error
 *
 * Return: length on success, negative error code if message couldn't be built.
 */
static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct icmphdr *icmph;
	struct iphdr *niph;
	struct ethhdr eh;
	int len, err;

	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr)))
		return -EINVAL;

	skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
	pskb_pull(skb, ETH_HLEN);
	skb_reset_network_header(skb);

	err = pskb_trim(skb, 576 - sizeof(*niph) - sizeof(*icmph));
	if (err)
		return err;

	len = skb->len + sizeof(*icmph);
	err = skb_cow(skb, sizeof(*niph) + sizeof(*icmph) + ETH_HLEN);
	if (err)
		return err;

	icmph = skb_push(skb, sizeof(*icmph));
	*icmph = (struct icmphdr) {
		.type			= ICMP_DEST_UNREACH,
		.code			= ICMP_FRAG_NEEDED,
		.checksum		= 0,
		.un.frag.__unused	= 0,
		.un.frag.mtu		= htons(mtu),
	};
	icmph->checksum = ip_compute_csum(icmph, len);
	skb_reset_transport_header(skb);

	niph = skb_push(skb, sizeof(*niph));
	*niph = (struct iphdr) {
		.ihl			= sizeof(*niph) / 4u,
		.version 		= 4,
		.tos 			= 0,
		.tot_len		= htons(len + sizeof(*niph)),
		.id			= 0,
		.frag_off		= htons(IP_DF),
		.ttl			= iph->ttl,
		.protocol		= IPPROTO_ICMP,
		.saddr			= iph->daddr,
		.daddr			= iph->saddr,
	};
	ip_send_check(niph);
	skb_reset_network_header(skb);

	skb->ip_summed = CHECKSUM_NONE;

	eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0);
	skb_reset_mac_header(skb);

	return skb->len;
}

/**
 * iptunnel_pmtud_check_icmp() - Trigger ICMP reply if needed and allowed
 * @skb:	Buffer being sent by encapsulation, L2 headers expected
 * @mtu:	Network MTU for path
 *
 * Return: 0 for no ICMP reply, length if built, negative value on error.
 */
static int iptunnel_pmtud_check_icmp(struct sk_buff *skb, int mtu)
{
	const struct icmphdr *icmph = icmp_hdr(skb);
	const struct iphdr *iph = ip_hdr(skb);

	if (mtu < 576 || iph->frag_off != htons(IP_DF))
		return 0;

	if (ipv4_is_lbcast(iph->daddr)  || ipv4_is_multicast(iph->daddr) ||
	    ipv4_is_zeronet(iph->saddr) || ipv4_is_loopback(iph->saddr)  ||
	    ipv4_is_lbcast(iph->saddr)  || ipv4_is_multicast(iph->saddr))
		return 0;

	if (iph->protocol == IPPROTO_ICMP && icmp_is_err(icmph->type))
		return 0;

	return iptunnel_pmtud_build_icmp(skb, mtu);
}

#if IS_ENABLED(CONFIG_IPV6)
/**
 * iptunnel_pmtud_build_icmpv6() - Build ICMPv6 error message for PMTUD
 * @skb:	Original packet with L2 header
 * @mtu:	MTU value for ICMPv6 error
 *
 * Return: length on success, negative error code if message couldn't be built.
 */
static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
{
	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
	struct icmp6hdr *icmp6h;
	struct ipv6hdr *nip6h;
	struct ethhdr eh;
	int len, err;
	__wsum csum;

	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr)))
		return -EINVAL;

	skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
	pskb_pull(skb, ETH_HLEN);
	skb_reset_network_header(skb);

	err = pskb_trim(skb, IPV6_MIN_MTU - sizeof(*nip6h) - sizeof(*icmp6h));
	if (err)
		return err;

	len = skb->len + sizeof(*icmp6h);
	err = skb_cow(skb, sizeof(*nip6h) + sizeof(*icmp6h) + ETH_HLEN);
	if (err)
		return err;

	icmp6h = skb_push(skb, sizeof(*icmp6h));
	*icmp6h = (struct icmp6hdr) {
		.icmp6_type		= ICMPV6_PKT_TOOBIG,
		.icmp6_code		= 0,
		.icmp6_cksum		= 0,
		.icmp6_mtu		= htonl(mtu),
	};
	skb_reset_transport_header(skb);

	nip6h = skb_push(skb, sizeof(*nip6h));
	*nip6h = (struct ipv6hdr) {
		.priority		= 0,
		.version		= 6,
		.flow_lbl		= { 0 },
		.payload_len		= htons(len),
		.nexthdr		= IPPROTO_ICMPV6,
		.hop_limit		= ip6h->hop_limit,
		.saddr			= ip6h->daddr,
		.daddr			= ip6h->saddr,
	};
	skb_reset_network_header(skb);

	csum = csum_partial(icmp6h, len, 0);
	icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len,
					      IPPROTO_ICMPV6, csum);

	skb->ip_summed = CHECKSUM_NONE;

	eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0);
	skb_reset_mac_header(skb);

	return skb->len;
}

/**
 * iptunnel_pmtud_check_icmpv6() - Trigger ICMPv6 reply if needed and allowed
 * @skb:	Buffer being sent by encapsulation, L2 headers expected
 * @mtu:	Network MTU for path
 *
 * Return: 0 for no ICMPv6 reply, length if built, negative value on error.
 */
static int iptunnel_pmtud_check_icmpv6(struct sk_buff *skb, int mtu)
{
	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
	int stype = ipv6_addr_type(&ip6h->saddr);
	u8 proto = ip6h->nexthdr;
	__be16 frag_off;
	int offset;

	if (mtu < IPV6_MIN_MTU)
		return 0;

	if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST ||
	    stype == IPV6_ADDR_LOOPBACK)
		return 0;

	offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto,
				  &frag_off);
	if (offset < 0 || (frag_off & htons(~0x7)))
		return 0;

	if (proto == IPPROTO_ICMPV6) {
		struct icmp6hdr *icmp6h;

		if (!pskb_may_pull(skb, skb_network_header(skb) +
					offset + 1 - skb->data))
			return 0;

		icmp6h = (struct icmp6hdr *)(skb_network_header(skb) + offset);
		if (icmpv6_is_err(icmp6h->icmp6_type) ||
		    icmp6h->icmp6_type == NDISC_REDIRECT)
			return 0;
	}

	return iptunnel_pmtud_build_icmpv6(skb, mtu);
}
#endif /* IS_ENABLED(CONFIG_IPV6) */

/**
 * skb_tunnel_check_pmtu() - Check, update PMTU and trigger ICMP reply as needed
 * @skb:	Buffer being sent by encapsulation, L2 headers expected
 * @encap_dst:	Destination for tunnel encapsulation (outer IP)
 * @headroom:	Encapsulation header size, bytes
 * @reply:	Build matching ICMP or ICMPv6 message as a result
 *
 * L2 tunnel implementations that can carry IP and can be directly bridged
 * (currently UDP tunnels) can't always rely on IP forwarding paths to handle
 * PMTU discovery. In the bridged case, ICMP or ICMPv6 messages need to be built
 * based on payload and sent back by the encapsulation itself.
 *
 * For routable interfaces, we just need to update the PMTU for the destination.
 *
 * Return: 0 if ICMP error not needed, length if built, negative value on error
 */
int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
			  int headroom, bool reply)
{
	u32 mtu = dst_mtu(encap_dst) - headroom;

	if ((skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) ||
	    (!skb_is_gso(skb) && (skb->len - skb_network_offset(skb)) <= mtu))
		return 0;

	skb_dst_update_pmtu_no_confirm(skb, mtu);

	if (!reply || skb->pkt_type == PACKET_HOST)
		return 0;

	if (skb->protocol == htons(ETH_P_IP))
		return iptunnel_pmtud_check_icmp(skb, mtu);

#if IS_ENABLED(CONFIG_IPV6)
	if (skb->protocol == htons(ETH_P_IPV6))
		return iptunnel_pmtud_check_icmpv6(skb, mtu);
#endif
	return 0;
}
EXPORT_SYMBOL(skb_tunnel_check_pmtu);

static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
	[LWTUNNEL_IP_UNSPEC]	= { .strict_start_type = LWTUNNEL_IP_OPTS },
	[LWTUNNEL_IP_ID]	= { .type = NLA_U64 },
	[LWTUNNEL_IP_DST]	= { .type = NLA_U32 },
	[LWTUNNEL_IP_SRC]	= { .type = NLA_U32 },
	[LWTUNNEL_IP_TTL]	= { .type = NLA_U8 },
	[LWTUNNEL_IP_TOS]	= { .type = NLA_U8 },
	[LWTUNNEL_IP_FLAGS]	= { .type = NLA_U16 },
	[LWTUNNEL_IP_OPTS]	= { .type = NLA_NESTED },
};

static const struct nla_policy ip_opts_policy[LWTUNNEL_IP_OPTS_MAX + 1] = {
	[LWTUNNEL_IP_OPTS_GENEVE]	= { .type = NLA_NESTED },
	[LWTUNNEL_IP_OPTS_VXLAN]	= { .type = NLA_NESTED },
	[LWTUNNEL_IP_OPTS_ERSPAN]	= { .type = NLA_NESTED },
};

static const struct nla_policy
geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = {
	[LWTUNNEL_IP_OPT_GENEVE_CLASS]	= { .type = NLA_U16 },
	[LWTUNNEL_IP_OPT_GENEVE_TYPE]	= { .type = NLA_U8 },
	[LWTUNNEL_IP_OPT_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 128 },
};

static const struct nla_policy
vxlan_opt_policy[LWTUNNEL_IP_OPT_VXLAN_MAX + 1] = {
	[LWTUNNEL_IP_OPT_VXLAN_GBP]	= { .type = NLA_U32 },
};

static const struct nla_policy
erspan_opt_policy[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1] = {
	[LWTUNNEL_IP_OPT_ERSPAN_VER]	= { .type = NLA_U8 },
	[LWTUNNEL_IP_OPT_ERSPAN_INDEX]	= { .type = NLA_U32 },
	[LWTUNNEL_IP_OPT_ERSPAN_DIR]	= { .type = NLA_U8 },
	[LWTUNNEL_IP_OPT_ERSPAN_HWID]	= { .type = NLA_U8 },
};

static int ip_tun_parse_opts_geneve(struct nlattr *attr,
				    struct ip_tunnel_info *info, int opts_len,
				    struct netlink_ext_ack *extack)
{
	struct nlattr *tb[LWTUNNEL_IP_OPT_GENEVE_MAX + 1];
	int data_len, err;

	err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_GENEVE_MAX, attr,
			       geneve_opt_policy, extack);
	if (err)
		return err;

	if (!tb[LWTUNNEL_IP_OPT_GENEVE_CLASS] ||
	    !tb[LWTUNNEL_IP_OPT_GENEVE_TYPE] ||
	    !tb[LWTUNNEL_IP_OPT_GENEVE_DATA])
		return -EINVAL;

	attr = tb[LWTUNNEL_IP_OPT_GENEVE_DATA];
	data_len = nla_len(attr);
	if (data_len % 4)
		return -EINVAL;

	if (info) {
		struct geneve_opt *opt = ip_tunnel_info_opts(info) + opts_len;

		memcpy(opt->opt_data, nla_data(attr), data_len);
		opt->length = data_len / 4;
		attr = tb[LWTUNNEL_IP_OPT_GENEVE_CLASS];
		opt->opt_class = nla_get_be16(attr);
		attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE];
		opt->type = nla_get_u8(attr);
		info->key.tun_flags |= TUNNEL_GENEVE_OPT;
	}

	return sizeof(struct geneve_opt) + data_len;
}

static int ip_tun_parse_opts_vxlan(struct nlattr *attr,
				   struct ip_tunnel_info *info, int opts_len,
				   struct netlink_ext_ack *extack)
{
	struct nlattr *tb[LWTUNNEL_IP_OPT_VXLAN_MAX + 1];
	int err;

	err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_VXLAN_MAX, attr,
			       vxlan_opt_policy, extack);
	if (err)
		return err;

	if (!tb[LWTUNNEL_IP_OPT_VXLAN_GBP])
		return -EINVAL;

	if (info) {
		struct vxlan_metadata *md =
			ip_tunnel_info_opts(info) + opts_len;

		attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP];
		md->gbp = nla_get_u32(attr);
		md->gbp &= VXLAN_GBP_MASK;
		info->key.tun_flags |= TUNNEL_VXLAN_OPT;
	}

	return sizeof(struct vxlan_metadata);
}

static int ip_tun_parse_opts_erspan(struct nlattr *attr,
				    struct ip_tunnel_info *info, int opts_len,
				    struct netlink_ext_ack *extack)
{
	struct nlattr *tb[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1];
	int err;
	u8 ver;

	err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_ERSPAN_MAX, attr,
			       erspan_opt_policy, extack);
	if (err)
		return err;

	if (!tb[LWTUNNEL_IP_OPT_ERSPAN_VER])
		return -EINVAL;

	ver = nla_get_u8(tb[LWTUNNEL_IP_OPT_ERSPAN_VER]);
	if (ver == 1) {
		if (!tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX])
			return -EINVAL;
	} else if (ver == 2) {
		if (!tb[LWTUNNEL_IP_OPT_ERSPAN_DIR] ||
		    !tb[LWTUNNEL_IP_OPT_ERSPAN_HWID])
			return -EINVAL;
	} else {
		return -EINVAL;
	}

	if (info) {
		struct erspan_metadata *md =
			ip_tunnel_info_opts(info) + opts_len;

		md->version = ver;
		if (ver == 1) {
			attr = tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX];
			md->u.index = nla_get_be32(attr);
		} else {
			attr = tb[LWTUNNEL_IP_OPT_ERSPAN_DIR];
			md->u.md2.dir = nla_get_u8(attr);
			attr = tb[LWTUNNEL_IP_OPT_ERSPAN_HWID];
			set_hwid(&md->u.md2, nla_get_u8(attr));
		}

		info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
	}

	return sizeof(struct erspan_metadata);
}

static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info,
			     struct netlink_ext_ack *extack)
{
	int err, rem, opt_len, opts_len = 0;
	struct nlattr *nla;
	__be16 type = 0;

	if (!attr)
		return 0;

	err = nla_validate(nla_data(attr), nla_len(attr), LWTUNNEL_IP_OPTS_MAX,
			   ip_opts_policy, extack);
	if (err)
		return err;

	nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) {
		switch (nla_type(nla)) {
		case LWTUNNEL_IP_OPTS_GENEVE:
			if (type && type != TUNNEL_GENEVE_OPT)
				return -EINVAL;
			opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len,
							   extack);
			if (opt_len < 0)
				return opt_len;
			opts_len += opt_len;
			if (opts_len > IP_TUNNEL_OPTS_MAX)
				return -EINVAL;
			type = TUNNEL_GENEVE_OPT;
			break;
		case LWTUNNEL_IP_OPTS_VXLAN:
			if (type)
				return -EINVAL;
			opt_len = ip_tun_parse_opts_vxlan(nla, info, opts_len,
							  extack);
			if (opt_len < 0)
				return opt_len;
			opts_len += opt_len;
			type = TUNNEL_VXLAN_OPT;
			break;
		case LWTUNNEL_IP_OPTS_ERSPAN:
			if (type)
				return -EINVAL;
			opt_len = ip_tun_parse_opts_erspan(nla, info, opts_len,
							   extack);
			if (opt_len < 0)
				return opt_len;
			opts_len += opt_len;
			type = TUNNEL_ERSPAN_OPT;
			break;
		default:
			return -EINVAL;
		}
	}

	return opts_len;
}

static int ip_tun_get_optlen(struct nlattr *attr,
			     struct netlink_ext_ack *extack)
{
	return ip_tun_parse_opts(attr, NULL, extack);
}

static int ip_tun_set_opts(struct nlattr *attr, struct ip_tunnel_info *info,
			   struct netlink_ext_ack *extack)
{
	return ip_tun_parse_opts(attr, info, extack);
}

static int ip_tun_build_state(struct net *net, struct nlattr *attr,
			      unsigned int family, const void *cfg,
			      struct lwtunnel_state **ts,
			      struct netlink_ext_ack *extack)
{
	struct nlattr *tb[LWTUNNEL_IP_MAX + 1];
	struct lwtunnel_state *new_state;
	struct ip_tunnel_info *tun_info;
	int err, opt_len;

	err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_MAX, attr,
					  ip_tun_policy, extack);
	if (err < 0)
		return err;

	opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP_OPTS], extack);
	if (opt_len < 0)
		return opt_len;

	new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len);
	if (!new_state)
		return -ENOMEM;

	new_state->type = LWTUNNEL_ENCAP_IP;

	tun_info = lwt_tun_info(new_state);

	err = ip_tun_set_opts(tb[LWTUNNEL_IP_OPTS], tun_info, extack);
	if (err < 0) {
		lwtstate_free(new_state);
		return err;
	}

#ifdef CONFIG_DST_CACHE
	err = dst_cache_init(&tun_info->dst_cache, GFP_KERNEL);
	if (err) {
		lwtstate_free(new_state);
		return err;
	}
#endif

	if (tb[LWTUNNEL_IP_ID])
		tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP_ID]);

	if (tb[LWTUNNEL_IP_DST])
		tun_info->key.u.ipv4.dst = nla_get_in_addr(tb[LWTUNNEL_IP_DST]);

	if (tb[LWTUNNEL_IP_SRC])
		tun_info->key.u.ipv4.src = nla_get_in_addr(tb[LWTUNNEL_IP_SRC]);

	if (tb[LWTUNNEL_IP_TTL])
		tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP_TTL]);

	if (tb[LWTUNNEL_IP_TOS])
		tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]);

	if (tb[LWTUNNEL_IP_FLAGS])
		tun_info->key.tun_flags |=
				(nla_get_be16(tb[LWTUNNEL_IP_FLAGS]) &
				 ~TUNNEL_OPTIONS_PRESENT);

	tun_info->mode = IP_TUNNEL_INFO_TX;
	tun_info->options_len = opt_len;

	*ts = new_state;

	return 0;
}

static void ip_tun_destroy_state(struct lwtunnel_state *lwtstate)
{
#ifdef CONFIG_DST_CACHE
	struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);

	dst_cache_destroy(&tun_info->dst_cache);
#endif
}

static int ip_tun_fill_encap_opts_geneve(struct sk_buff *skb,
					 struct ip_tunnel_info *tun_info)
{
	struct geneve_opt *opt;
	struct nlattr *nest;
	int offset = 0;

	nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_GENEVE);
	if (!nest)
		return -ENOMEM;

	while (tun_info->options_len > offset) {
		opt = ip_tunnel_info_opts(tun_info) + offset;
		if (nla_put_be16(skb, LWTUNNEL_IP_OPT_GENEVE_CLASS,
				 opt->opt_class) ||
		    nla_put_u8(skb, LWTUNNEL_IP_OPT_GENEVE_TYPE, opt->type) ||
		    nla_put(skb, LWTUNNEL_IP_OPT_GENEVE_DATA, opt->length * 4,
			    opt->opt_data)) {
			nla_nest_cancel(skb, nest);
			return -ENOMEM;
		}
		offset += sizeof(*opt) + opt->length * 4;
	}

	nla_nest_end(skb, nest);
	return 0;
}

static int ip_tun_fill_encap_opts_vxlan(struct sk_buff *skb,
					struct ip_tunnel_info *tun_info)
{
	struct vxlan_metadata *md;
	struct nlattr *nest;

	nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_VXLAN);
	if (!nest)
		return -ENOMEM;

	md = ip_tunnel_info_opts(tun_info);
	if (nla_put_u32(skb, LWTUNNEL_IP_OPT_VXLAN_GBP, md->gbp)) {
		nla_nest_cancel(skb, nest);
		return -ENOMEM;
	}

	nla_nest_end(skb, nest);
	return 0;
}

static int ip_tun_fill_encap_opts_erspan(struct sk_buff *skb,
					 struct ip_tunnel_info *tun_info)
{
	struct erspan_metadata *md;
	struct nlattr *nest;

	nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_ERSPAN);
	if (!nest)
		return -ENOMEM;

	md = ip_tunnel_info_opts(tun_info);
	if (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_VER, md->version))
		goto err;

	if (md->version == 1 &&
	    nla_put_be32(skb, LWTUNNEL_IP_OPT_ERSPAN_INDEX, md->u.index))
		goto err;

	if (md->version == 2 &&
	    (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_DIR, md->u.md2.dir) ||
	     nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_HWID,
			get_hwid(&md->u.md2))))
		goto err;

	nla_nest_end(skb, nest);
	return 0;
err:
	nla_nest_cancel(skb, nest);
	return -ENOMEM;
}

static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type,
				  struct ip_tunnel_info *tun_info)
{
	struct nlattr *nest;
	int err = 0;

	if (!(tun_info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))
		return 0;

	nest = nla_nest_start_noflag(skb, type);
	if (!nest)
		return -ENOMEM;

	if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT)
		err = ip_tun_fill_encap_opts_geneve(skb, tun_info);
	else if (tun_info->key.tun_flags & TUNNEL_VXLAN_OPT)
		err = ip_tun_fill_encap_opts_vxlan(skb, tun_info);
	else if (tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)
		err = ip_tun_fill_encap_opts_erspan(skb, tun_info);

	if (err) {
		nla_nest_cancel(skb, nest);
		return err;
	}

	nla_nest_end(skb, nest);
	return 0;
}

static int ip_tun_fill_encap_info(struct sk_buff *skb,
				  struct lwtunnel_state *lwtstate)
{
	struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);

	if (nla_put_be64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id,
			 LWTUNNEL_IP_PAD) ||
	    nla_put_in_addr(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) ||
	    nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) ||
	    nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) ||
	    nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) ||
	    nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags) ||
	    ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info))
		return -ENOMEM;

	return 0;
}

static int ip_tun_opts_nlsize(struct ip_tunnel_info *info)
{
	int opt_len;

	if (!(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))
		return 0;

	opt_len = nla_total_size(0);		/* LWTUNNEL_IP_OPTS */
	if (info->key.tun_flags & TUNNEL_GENEVE_OPT) {
		struct geneve_opt *opt;
		int offset = 0;

		opt_len += nla_total_size(0);	/* LWTUNNEL_IP_OPTS_GENEVE */
		while (info->options_len > offset) {
			opt = ip_tunnel_info_opts(info) + offset;
			opt_len += nla_total_size(2)	/* OPT_GENEVE_CLASS */
				   + nla_total_size(1)	/* OPT_GENEVE_TYPE */
				   + nla_total_size(opt->length * 4);
							/* OPT_GENEVE_DATA */
			offset += sizeof(*opt) + opt->length * 4;
		}
	} else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) {
		opt_len += nla_total_size(0)	/* LWTUNNEL_IP_OPTS_VXLAN */
			   + nla_total_size(4);	/* OPT_VXLAN_GBP */
	} else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) {
		struct erspan_metadata *md = ip_tunnel_info_opts(info);

		opt_len += nla_total_size(0)	/* LWTUNNEL_IP_OPTS_ERSPAN */
			   + nla_total_size(1)	/* OPT_ERSPAN_VER */
			   + (md->version == 1 ? nla_total_size(4)
						/* OPT_ERSPAN_INDEX (v1) */
					       : nla_total_size(1) +
						 nla_total_size(1));
						/* OPT_ERSPAN_DIR + HWID (v2) */
	}

	return opt_len;
}

static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
	return nla_total_size_64bit(8)	/* LWTUNNEL_IP_ID */
		+ nla_total_size(4)	/* LWTUNNEL_IP_DST */
		+ nla_total_size(4)	/* LWTUNNEL_IP_SRC */
		+ nla_total_size(1)	/* LWTUNNEL_IP_TOS */
		+ nla_total_size(1)	/* LWTUNNEL_IP_TTL */
		+ nla_total_size(2)	/* LWTUNNEL_IP_FLAGS */
		+ ip_tun_opts_nlsize(lwt_tun_info(lwtstate));
					/* LWTUNNEL_IP_OPTS */
}

static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
{
	struct ip_tunnel_info *info_a = lwt_tun_info(a);
	struct ip_tunnel_info *info_b = lwt_tun_info(b);

	return memcmp(info_a, info_b, sizeof(info_a->key)) ||
	       info_a->mode != info_b->mode ||
	       info_a->options_len != info_b->options_len ||
	       memcmp(ip_tunnel_info_opts(info_a),
		      ip_tunnel_info_opts(info_b), info_a->options_len);
}

static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
	.build_state = ip_tun_build_state,
	.destroy_state = ip_tun_destroy_state,
	.fill_encap = ip_tun_fill_encap_info,
	.get_encap_size = ip_tun_encap_nlsize,
	.cmp_encap = ip_tun_cmp_encap,
	.owner = THIS_MODULE,
};

static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
	[LWTUNNEL_IP6_UNSPEC]	= { .strict_start_type = LWTUNNEL_IP6_OPTS },
	[LWTUNNEL_IP6_ID]		= { .type = NLA_U64 },
	[LWTUNNEL_IP6_DST]		= { .len = sizeof(struct in6_addr) },
	[LWTUNNEL_IP6_SRC]		= { .len = sizeof(struct in6_addr) },
	[LWTUNNEL_IP6_HOPLIMIT]		= { .type = NLA_U8 },
	[LWTUNNEL_IP6_TC]		= { .type = NLA_U8 },
	[LWTUNNEL_IP6_FLAGS]		= { .type = NLA_U16 },
	[LWTUNNEL_IP6_OPTS]		= { .type = NLA_NESTED },
};

static int ip6_tun_build_state(struct net *net, struct nlattr *attr,
			       unsigned int family, const void *cfg,
			       struct lwtunnel_state **ts,
			       struct netlink_ext_ack *extack)
{
	struct nlattr *tb[LWTUNNEL_IP6_MAX + 1];
	struct lwtunnel_state *new_state;
	struct ip_tunnel_info *tun_info;
	int err, opt_len;

	err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP6_MAX, attr,
					  ip6_tun_policy, extack);
	if (err < 0)
		return err;

	opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP6_OPTS], extack);
	if (opt_len < 0)
		return opt_len;

	new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len);
	if (!new_state)
		return -ENOMEM;

	new_state->type = LWTUNNEL_ENCAP_IP6;

	tun_info = lwt_tun_info(new_state);

	err = ip_tun_set_opts(tb[LWTUNNEL_IP6_OPTS], tun_info, extack);
	if (err < 0) {
		lwtstate_free(new_state);
		return err;
	}

	if (tb[LWTUNNEL_IP6_ID])
		tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP6_ID]);

	if (tb[LWTUNNEL_IP6_DST])
		tun_info->key.u.ipv6.dst = nla_get_in6_addr(tb[LWTUNNEL_IP6_DST]);

	if (tb[LWTUNNEL_IP6_SRC])
		tun_info->key.u.ipv6.src = nla_get_in6_addr(tb[LWTUNNEL_IP6_SRC]);

	if (tb[LWTUNNEL_IP6_HOPLIMIT])
		tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP6_HOPLIMIT]);

	if (tb[LWTUNNEL_IP6_TC])
		tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]);

	if (tb[LWTUNNEL_IP6_FLAGS])
		tun_info->key.tun_flags |=
				(nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]) &
				 ~TUNNEL_OPTIONS_PRESENT);

	tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6;
	tun_info->options_len = opt_len;

	*ts = new_state;

	return 0;
}

static int ip6_tun_fill_encap_info(struct sk_buff *skb,
				   struct lwtunnel_state *lwtstate)
{
	struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);

	if (nla_put_be64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id,
			 LWTUNNEL_IP6_PAD) ||
	    nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) ||
	    nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) ||
	    nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) ||
	    nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) ||
	    nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags) ||
	    ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info))
		return -ENOMEM;

	return 0;
}

static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
	return nla_total_size_64bit(8)	/* LWTUNNEL_IP6_ID */
		+ nla_total_size(16)	/* LWTUNNEL_IP6_DST */
		+ nla_total_size(16)	/* LWTUNNEL_IP6_SRC */
		+ nla_total_size(1)	/* LWTUNNEL_IP6_HOPLIMIT */
		+ nla_total_size(1)	/* LWTUNNEL_IP6_TC */
		+ nla_total_size(2)	/* LWTUNNEL_IP6_FLAGS */
		+ ip_tun_opts_nlsize(lwt_tun_info(lwtstate));
					/* LWTUNNEL_IP6_OPTS */
}

static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = {
	.build_state = ip6_tun_build_state,
	.fill_encap = ip6_tun_fill_encap_info,
	.get_encap_size = ip6_tun_encap_nlsize,
	.cmp_encap = ip_tun_cmp_encap,
	.owner = THIS_MODULE,
};

void __init ip_tunnel_core_init(void)
{
	/* If you land here, make sure whether increasing ip_tunnel_info's
	 * options_len is a reasonable choice with its usage in front ends
	 * (f.e., it's part of flow keys, etc).
	 */
	BUILD_BUG_ON(IP_TUNNEL_OPTS_MAX != 255);

	lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP);
	lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6);
}

DEFINE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt);
EXPORT_SYMBOL(ip_tunnel_metadata_cnt);

void ip_tunnel_need_metadata(void)
{
	static_branch_inc(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata);

void ip_tunnel_unneed_metadata(void)
{
	static_branch_dec(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata);

/* Returns either the correct skb->protocol value, or 0 if invalid. */
__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb)
{
	if (skb_network_header(skb) >= skb->head &&
	    (skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) &&
	    ip_hdr(skb)->version == 4)
		return htons(ETH_P_IP);
	if (skb_network_header(skb) >= skb->head &&
	    (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) &&
	    ipv6_hdr(skb)->version == 6)
		return htons(ETH_P_IPV6);
	return 0;
}
EXPORT_SYMBOL(ip_tunnel_parse_protocol);

const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol };
EXPORT_SYMBOL(ip_tunnel_header_ops);