summaryrefslogtreecommitdiff
path: root/net/ipv4/ip_tunnel.c
blob: afed1aac2638398c472de6504f7f4a43e5b2d502 (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
/*
 * Copyright (c) 2013 Nicira, Inc.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301, USA
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_arp.h>
#include <linux/mroute.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/rculist.h>
#include <linux/err.h>

#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ip_tunnels.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>

#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#endif

static unsigned int ip_tunnel_hash(__be32 key, __be32 remote)
{
	return hash_32((__force u32)key ^ (__force u32)remote,
			 IP_TNL_HASH_BITS);
}

static void __tunnel_dst_set(struct ip_tunnel_dst *idst,
			     struct dst_entry *dst, __be32 saddr)
{
	struct dst_entry *old_dst;

	dst_clone(dst);
	old_dst = xchg((__force struct dst_entry **)&idst->dst, dst);
	dst_release(old_dst);
	idst->saddr = saddr;
}

static void tunnel_dst_set(struct ip_tunnel *t,
			   struct dst_entry *dst, __be32 saddr)
{
	__tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst, saddr);
}

static void tunnel_dst_reset(struct ip_tunnel *t)
{
	tunnel_dst_set(t, NULL, 0);
}

void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
{
	int i;

	for_each_possible_cpu(i)
		__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL, 0);
}
EXPORT_SYMBOL(ip_tunnel_dst_reset_all);

static struct rtable *tunnel_rtable_get(struct ip_tunnel *t,
					u32 cookie, __be32 *saddr)
{
	struct ip_tunnel_dst *idst;
	struct dst_entry *dst;

	rcu_read_lock();
	idst = this_cpu_ptr(t->dst_cache);
	dst = rcu_dereference(idst->dst);
	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
		dst = NULL;
	if (dst) {
		if (!dst->obsolete || dst->ops->check(dst, cookie)) {
			*saddr = idst->saddr;
		} else {
			tunnel_dst_reset(t);
			dst_release(dst);
			dst = NULL;
		}
	}
	rcu_read_unlock();
	return (struct rtable *)dst;
}

static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
				__be16 flags, __be32 key)
{
	if (p->i_flags & TUNNEL_KEY) {
		if (flags & TUNNEL_KEY)
			return key == p->i_key;
		else
			/* key expected, none present */
			return false;
	} else
		return !(flags & TUNNEL_KEY);
}

/* Fallback tunnel: no source, no destination, no key, no options

   Tunnel hash table:
   We require exact key match i.e. if a key is present in packet
   it will match only tunnel with the same key; if it is not present,
   it will match only keyless tunnel.

   All keysless packets, if not matched configured keyless tunnels
   will match fallback tunnel.
   Given src, dst and key, find appropriate for input tunnel.
*/
struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
				   int link, __be16 flags,
				   __be32 remote, __be32 local,
				   __be32 key)
{
	unsigned int hash;
	struct ip_tunnel *t, *cand = NULL;
	struct hlist_head *head;

	hash = ip_tunnel_hash(key, remote);
	head = &itn->tunnels[hash];

	hlist_for_each_entry_rcu(t, head, hash_node) {
		if (local != t->parms.iph.saddr ||
		    remote != t->parms.iph.daddr ||
		    !(t->dev->flags & IFF_UP))
			continue;

		if (!ip_tunnel_key_match(&t->parms, flags, key))
			continue;

		if (t->parms.link == link)
			return t;
		else
			cand = t;
	}

	hlist_for_each_entry_rcu(t, head, hash_node) {
		if (remote != t->parms.iph.daddr ||
		    t->parms.iph.saddr != 0 ||
		    !(t->dev->flags & IFF_UP))
			continue;

		if (!ip_tunnel_key_match(&t->parms, flags, key))
			continue;

		if (t->parms.link == link)
			return t;
		else if (!cand)
			cand = t;
	}

	hash = ip_tunnel_hash(key, 0);
	head = &itn->tunnels[hash];

	hlist_for_each_entry_rcu(t, head, hash_node) {
		if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) &&
		    (local != t->parms.iph.daddr || !ipv4_is_multicast(local)))
			continue;

		if (!(t->dev->flags & IFF_UP))
			continue;

		if (!ip_tunnel_key_match(&t->parms, flags, key))
			continue;

		if (t->parms.link == link)
			return t;
		else if (!cand)
			cand = t;
	}

	if (flags & TUNNEL_NO_KEY)
		goto skip_key_lookup;

	hlist_for_each_entry_rcu(t, head, hash_node) {
		if (t->parms.i_key != key ||
		    t->parms.iph.saddr != 0 ||
		    t->parms.iph.daddr != 0 ||
		    !(t->dev->flags & IFF_UP))
			continue;

		if (t->parms.link == link)
			return t;
		else if (!cand)
			cand = t;
	}

skip_key_lookup:
	if (cand)
		return cand;

	if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
		return netdev_priv(itn->fb_tunnel_dev);


	return NULL;
}
EXPORT_SYMBOL_GPL(ip_tunnel_lookup);

static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn,
				    struct ip_tunnel_parm *parms)
{
	unsigned int h;
	__be32 remote;
	__be32 i_key = parms->i_key;

	if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr))
		remote = parms->iph.daddr;
	else
		remote = 0;

	if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI))
		i_key = 0;

	h = ip_tunnel_hash(i_key, remote);
	return &itn->tunnels[h];
}

static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t)
{
	struct hlist_head *head = ip_bucket(itn, &t->parms);

	hlist_add_head_rcu(&t->hash_node, head);
}

static void ip_tunnel_del(struct ip_tunnel *t)
{
	hlist_del_init_rcu(&t->hash_node);
}

static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
					struct ip_tunnel_parm *parms,
					int type)
{
	__be32 remote = parms->iph.daddr;
	__be32 local = parms->iph.saddr;
	__be32 key = parms->i_key;
	__be16 flags = parms->i_flags;
	int link = parms->link;
	struct ip_tunnel *t = NULL;
	struct hlist_head *head = ip_bucket(itn, parms);

	hlist_for_each_entry_rcu(t, head, hash_node) {
		if (local == t->parms.iph.saddr &&
		    remote == t->parms.iph.daddr &&
		    link == t->parms.link &&
		    type == t->dev->type &&
		    ip_tunnel_key_match(&t->parms, flags, key))
			break;
	}
	return t;
}

static struct net_device *__ip_tunnel_create(struct net *net,
					     const struct rtnl_link_ops *ops,
					     struct ip_tunnel_parm *parms)
{
	int err;
	struct ip_tunnel *tunnel;
	struct net_device *dev;
	char name[IFNAMSIZ];

	if (parms->name[0])
		strlcpy(name, parms->name, IFNAMSIZ);
	else {
		if (strlen(ops->kind) > (IFNAMSIZ - 3)) {
			err = -E2BIG;
			goto failed;
		}
		strlcpy(name, ops->kind, IFNAMSIZ);
		strncat(name, "%d", 2);
	}

	ASSERT_RTNL();
	dev = alloc_netdev(ops->priv_size, name, NET_NAME_UNKNOWN, ops->setup);
	if (!dev) {
		err = -ENOMEM;
		goto failed;
	}
	dev_net_set(dev, net);

	dev->rtnl_link_ops = ops;

	tunnel = netdev_priv(dev);
	tunnel->parms = *parms;
	tunnel->net = net;

	err = register_netdevice(dev);
	if (err)
		goto failed_free;

	return dev;

failed_free:
	free_netdev(dev);
failed:
	return ERR_PTR(err);
}

static inline void init_tunnel_flow(struct flowi4 *fl4,
				    int proto,
				    __be32 daddr, __be32 saddr,
				    __be32 key, __u8 tos, int oif)
{
	memset(fl4, 0, sizeof(*fl4));
	fl4->flowi4_oif = oif;
	fl4->daddr = daddr;
	fl4->saddr = saddr;
	fl4->flowi4_tos = tos;
	fl4->flowi4_proto = proto;
	fl4->fl4_gre_key = key;
}

static int ip_tunnel_bind_dev(struct net_device *dev)
{
	struct net_device *tdev = NULL;
	struct ip_tunnel *tunnel = netdev_priv(dev);
	const struct iphdr *iph;
	int hlen = LL_MAX_HEADER;
	int mtu = ETH_DATA_LEN;
	int t_hlen = tunnel->hlen + sizeof(struct iphdr);

	iph = &tunnel->parms.iph;

	/* Guess output device to choose reasonable mtu and needed_headroom */
	if (iph->daddr) {
		struct flowi4 fl4;
		struct rtable *rt;

		init_tunnel_flow(&fl4, iph->protocol, iph->daddr,
				 iph->saddr, tunnel->parms.o_key,
				 RT_TOS(iph->tos), tunnel->parms.link);
		rt = ip_route_output_key(tunnel->net, &fl4);

		if (!IS_ERR(rt)) {
			tdev = rt->dst.dev;
			tunnel_dst_set(tunnel, &rt->dst, fl4.saddr);
			ip_rt_put(rt);
		}
		if (dev->type != ARPHRD_ETHER)
			dev->flags |= IFF_POINTOPOINT;
	}

	if (!tdev && tunnel->parms.link)
		tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);

	if (tdev) {
		hlen = tdev->hard_header_len + tdev->needed_headroom;
		mtu = tdev->mtu;
	}
	dev->iflink = tunnel->parms.link;

	dev->needed_headroom = t_hlen + hlen;
	mtu -= (dev->hard_header_len + t_hlen);

	if (mtu < 68)
		mtu = 68;

	return mtu;
}

static struct ip_tunnel *ip_tunnel_create(struct net *net,
					  struct ip_tunnel_net *itn,
					  struct ip_tunnel_parm *parms)
{
	struct ip_tunnel *nt;
	struct net_device *dev;

	BUG_ON(!itn->fb_tunnel_dev);
	dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
	if (IS_ERR(dev))
		return ERR_CAST(dev);

	dev->mtu = ip_tunnel_bind_dev(dev);

	nt = netdev_priv(dev);
	ip_tunnel_add(itn, nt);
	return nt;
}

int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
		  const struct tnl_ptk_info *tpi, bool log_ecn_error)
{
	struct pcpu_sw_netstats *tstats;
	const struct iphdr *iph = ip_hdr(skb);
	int err;

#ifdef CONFIG_NET_IPGRE_BROADCAST
	if (ipv4_is_multicast(iph->daddr)) {
		tunnel->dev->stats.multicast++;
		skb->pkt_type = PACKET_BROADCAST;
	}
#endif

	if ((!(tpi->flags&TUNNEL_CSUM) &&  (tunnel->parms.i_flags&TUNNEL_CSUM)) ||
	     ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) {
		tunnel->dev->stats.rx_crc_errors++;
		tunnel->dev->stats.rx_errors++;
		goto drop;
	}

	if (tunnel->parms.i_flags&TUNNEL_SEQ) {
		if (!(tpi->flags&TUNNEL_SEQ) ||
		    (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) {
			tunnel->dev->stats.rx_fifo_errors++;
			tunnel->dev->stats.rx_errors++;
			goto drop;
		}
		tunnel->i_seqno = ntohl(tpi->seq) + 1;
	}

	skb_reset_network_header(skb);

	err = IP_ECN_decapsulate(iph, skb);
	if (unlikely(err)) {
		if (log_ecn_error)
			net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
					&iph->saddr, iph->tos);
		if (err > 1) {
			++tunnel->dev->stats.rx_frame_errors;
			++tunnel->dev->stats.rx_errors;
			goto drop;
		}
	}

	tstats = this_cpu_ptr(tunnel->dev->tstats);
	u64_stats_update_begin(&tstats->syncp);
	tstats->rx_packets++;
	tstats->rx_bytes += skb->len;
	u64_stats_update_end(&tstats->syncp);

	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev)));

	if (tunnel->dev->type == ARPHRD_ETHER) {
		skb->protocol = eth_type_trans(skb, tunnel->dev);
		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
	} else {
		skb->dev = tunnel->dev;
	}

	gro_cells_receive(&tunnel->gro_cells, skb);
	return 0;

drop:
	kfree_skb(skb);
	return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_rcv);

static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
			    struct rtable *rt, __be16 df)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
	int mtu;

	if (df)
		mtu = dst_mtu(&rt->dst) - dev->hard_header_len
					- sizeof(struct iphdr) - tunnel->hlen;
	else
		mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;

	if (skb_dst(skb))
		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);

	if (skb->protocol == htons(ETH_P_IP)) {
		if (!skb_is_gso(skb) &&
		    (df & htons(IP_DF)) && mtu < pkt_size) {
			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
			return -E2BIG;
		}
	}
#if IS_ENABLED(CONFIG_IPV6)
	else if (skb->protocol == htons(ETH_P_IPV6)) {
		struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);

		if (rt6 && mtu < dst_mtu(skb_dst(skb)) &&
			   mtu >= IPV6_MIN_MTU) {
			if ((tunnel->parms.iph.daddr &&
			    !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
			    rt6->rt6i_dst.plen == 128) {
				rt6->rt6i_flags |= RTF_MODIFIED;
				dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
			}
		}

		if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
					mtu < pkt_size) {
			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
			return -E2BIG;
		}
	}
#endif
	return 0;
}

void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
		    const struct iphdr *tnl_params, const u8 protocol)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	const struct iphdr *inner_iph;
	struct flowi4 fl4;
	u8     tos, ttl;
	__be16 df;
	struct rtable *rt;		/* Route to the other host */
	unsigned int max_headroom;	/* The extra header space needed */
	__be32 dst;
	int err;
	bool connected;

	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
	connected = (tunnel->parms.iph.daddr != 0);

	dst = tnl_params->daddr;
	if (dst == 0) {
		/* NBMA tunnel */

		if (skb_dst(skb) == NULL) {
			dev->stats.tx_fifo_errors++;
			goto tx_error;
		}

		if (skb->protocol == htons(ETH_P_IP)) {
			rt = skb_rtable(skb);
			dst = rt_nexthop(rt, inner_iph->daddr);
		}
#if IS_ENABLED(CONFIG_IPV6)
		else if (skb->protocol == htons(ETH_P_IPV6)) {
			const struct in6_addr *addr6;
			struct neighbour *neigh;
			bool do_tx_error_icmp;
			int addr_type;

			neigh = dst_neigh_lookup(skb_dst(skb),
						 &ipv6_hdr(skb)->daddr);
			if (neigh == NULL)
				goto tx_error;

			addr6 = (const struct in6_addr *)&neigh->primary_key;
			addr_type = ipv6_addr_type(addr6);

			if (addr_type == IPV6_ADDR_ANY) {
				addr6 = &ipv6_hdr(skb)->daddr;
				addr_type = ipv6_addr_type(addr6);
			}

			if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
				do_tx_error_icmp = true;
			else {
				do_tx_error_icmp = false;
				dst = addr6->s6_addr32[3];
			}
			neigh_release(neigh);
			if (do_tx_error_icmp)
				goto tx_error_icmp;
		}
#endif
		else
			goto tx_error;

		connected = false;
	}

	tos = tnl_params->tos;
	if (tos & 0x1) {
		tos &= ~0x1;
		if (skb->protocol == htons(ETH_P_IP)) {
			tos = inner_iph->tos;
			connected = false;
		} else if (skb->protocol == htons(ETH_P_IPV6)) {
			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
			connected = false;
		}
	}

	init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);

	rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL;

	if (!rt) {
		rt = ip_route_output_key(tunnel->net, &fl4);

		if (IS_ERR(rt)) {
			dev->stats.tx_carrier_errors++;
			goto tx_error;
		}
		if (connected)
			tunnel_dst_set(tunnel, &rt->dst, fl4.saddr);
	}

	if (rt->dst.dev == dev) {
		ip_rt_put(rt);
		dev->stats.collisions++;
		goto tx_error;
	}

	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
		ip_rt_put(rt);
		goto tx_error;
	}

	if (tunnel->err_count > 0) {
		if (time_before(jiffies,
				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
			tunnel->err_count--;

			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
			dst_link_failure(skb);
		} else
			tunnel->err_count = 0;
	}

	tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
	ttl = tnl_params->ttl;
	if (ttl == 0) {
		if (skb->protocol == htons(ETH_P_IP))
			ttl = inner_iph->ttl;
#if IS_ENABLED(CONFIG_IPV6)
		else if (skb->protocol == htons(ETH_P_IPV6))
			ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
#endif
		else
			ttl = ip4_dst_hoplimit(&rt->dst);
	}

	df = tnl_params->frag_off;
	if (skb->protocol == htons(ETH_P_IP))
		df |= (inner_iph->frag_off&htons(IP_DF));

	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
			+ rt->dst.header_len;
	if (max_headroom > dev->needed_headroom)
		dev->needed_headroom = max_headroom;

	if (skb_cow_head(skb, dev->needed_headroom)) {
		ip_rt_put(rt);
		dev->stats.tx_dropped++;
		kfree_skb(skb);
		return;
	}

	err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, protocol,
			    tos, ttl, df, !net_eq(tunnel->net, dev_net(dev)));
	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);

	return;

#if IS_ENABLED(CONFIG_IPV6)
tx_error_icmp:
	dst_link_failure(skb);
#endif
tx_error:
	dev->stats.tx_errors++;
	kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(ip_tunnel_xmit);

static void ip_tunnel_update(struct ip_tunnel_net *itn,
			     struct ip_tunnel *t,
			     struct net_device *dev,
			     struct ip_tunnel_parm *p,
			     bool set_mtu)
{
	ip_tunnel_del(t);
	t->parms.iph.saddr = p->iph.saddr;
	t->parms.iph.daddr = p->iph.daddr;
	t->parms.i_key = p->i_key;
	t->parms.o_key = p->o_key;
	if (dev->type != ARPHRD_ETHER) {
		memcpy(dev->dev_addr, &p->iph.saddr, 4);
		memcpy(dev->broadcast, &p->iph.daddr, 4);
	}
	ip_tunnel_add(itn, t);

	t->parms.iph.ttl = p->iph.ttl;
	t->parms.iph.tos = p->iph.tos;
	t->parms.iph.frag_off = p->iph.frag_off;

	if (t->parms.link != p->link) {
		int mtu;

		t->parms.link = p->link;
		mtu = ip_tunnel_bind_dev(dev);
		if (set_mtu)
			dev->mtu = mtu;
	}
	ip_tunnel_dst_reset_all(t);
	netdev_state_change(dev);
}

int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
{
	int err = 0;
	struct ip_tunnel *t = netdev_priv(dev);
	struct net *net = t->net;
	struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id);

	BUG_ON(!itn->fb_tunnel_dev);
	switch (cmd) {
	case SIOCGETTUNNEL:
		if (dev == itn->fb_tunnel_dev) {
			t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
			if (t == NULL)
				t = netdev_priv(dev);
		}
		memcpy(p, &t->parms, sizeof(*p));
		break;

	case SIOCADDTUNNEL:
	case SIOCCHGTUNNEL:
		err = -EPERM;
		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
			goto done;
		if (p->iph.ttl)
			p->iph.frag_off |= htons(IP_DF);
		if (!(p->i_flags & VTI_ISVTI)) {
			if (!(p->i_flags & TUNNEL_KEY))
				p->i_key = 0;
			if (!(p->o_flags & TUNNEL_KEY))
				p->o_key = 0;
		}

		t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);

		if (!t && (cmd == SIOCADDTUNNEL)) {
			t = ip_tunnel_create(net, itn, p);
			err = PTR_ERR_OR_ZERO(t);
			break;
		}
		if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
			if (t != NULL) {
				if (t->dev != dev) {
					err = -EEXIST;
					break;
				}
			} else {
				unsigned int nflags = 0;

				if (ipv4_is_multicast(p->iph.daddr))
					nflags = IFF_BROADCAST;
				else if (p->iph.daddr)
					nflags = IFF_POINTOPOINT;

				if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) {
					err = -EINVAL;
					break;
				}

				t = netdev_priv(dev);
			}
		}

		if (t) {
			err = 0;
			ip_tunnel_update(itn, t, dev, p, true);
		} else {
			err = -ENOENT;
		}
		break;

	case SIOCDELTUNNEL:
		err = -EPERM;
		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
			goto done;

		if (dev == itn->fb_tunnel_dev) {
			err = -ENOENT;
			t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
			if (t == NULL)
				goto done;
			err = -EPERM;
			if (t == netdev_priv(itn->fb_tunnel_dev))
				goto done;
			dev = t->dev;
		}
		unregister_netdevice(dev);
		err = 0;
		break;

	default:
		err = -EINVAL;
	}

done:
	return err;
}
EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);

int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	int t_hlen = tunnel->hlen + sizeof(struct iphdr);

	if (new_mtu < 68 ||
	    new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
		return -EINVAL;
	dev->mtu = new_mtu;
	return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);

static void ip_tunnel_dev_free(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);

	gro_cells_destroy(&tunnel->gro_cells);
	free_percpu(tunnel->dst_cache);
	free_percpu(dev->tstats);
	free_netdev(dev);
}

void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct ip_tunnel_net *itn;

	itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id);

	if (itn->fb_tunnel_dev != dev) {
		ip_tunnel_del(netdev_priv(dev));
		unregister_netdevice_queue(dev, head);
	}
}
EXPORT_SYMBOL_GPL(ip_tunnel_dellink);

int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
				  struct rtnl_link_ops *ops, char *devname)
{
	struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id);
	struct ip_tunnel_parm parms;
	unsigned int i;

	for (i = 0; i < IP_TNL_HASH_SIZE; i++)
		INIT_HLIST_HEAD(&itn->tunnels[i]);

	if (!ops) {
		itn->fb_tunnel_dev = NULL;
		return 0;
	}

	memset(&parms, 0, sizeof(parms));
	if (devname)
		strlcpy(parms.name, devname, IFNAMSIZ);

	rtnl_lock();
	itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms);
	/* FB netdevice is special: we have one, and only one per netns.
	 * Allowing to move it to another netns is clearly unsafe.
	 */
	if (!IS_ERR(itn->fb_tunnel_dev)) {
		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
	}
	rtnl_unlock();

	return PTR_ERR_OR_ZERO(itn->fb_tunnel_dev);
}
EXPORT_SYMBOL_GPL(ip_tunnel_init_net);

static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
			      struct rtnl_link_ops *ops)
{
	struct net *net = dev_net(itn->fb_tunnel_dev);
	struct net_device *dev, *aux;
	int h;

	for_each_netdev_safe(net, dev, aux)
		if (dev->rtnl_link_ops == ops)
			unregister_netdevice_queue(dev, head);

	for (h = 0; h < IP_TNL_HASH_SIZE; h++) {
		struct ip_tunnel *t;
		struct hlist_node *n;
		struct hlist_head *thead = &itn->tunnels[h];

		hlist_for_each_entry_safe(t, n, thead, hash_node)
			/* If dev is in the same netns, it has already
			 * been added to the list by the previous loop.
			 */
			if (!net_eq(dev_net(t->dev), net))
				unregister_netdevice_queue(t->dev, head);
	}
}

void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
{
	LIST_HEAD(list);

	rtnl_lock();
	ip_tunnel_destroy(itn, &list, ops);
	unregister_netdevice_many(&list);
	rtnl_unlock();
}
EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);

int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
		      struct ip_tunnel_parm *p)
{
	struct ip_tunnel *nt;
	struct net *net = dev_net(dev);
	struct ip_tunnel_net *itn;
	int mtu;
	int err;

	nt = netdev_priv(dev);
	itn = net_generic(net, nt->ip_tnl_net_id);

	if (ip_tunnel_find(itn, p, dev->type))
		return -EEXIST;

	nt->net = net;
	nt->parms = *p;
	err = register_netdevice(dev);
	if (err)
		goto out;

	if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
		eth_hw_addr_random(dev);

	mtu = ip_tunnel_bind_dev(dev);
	if (!tb[IFLA_MTU])
		dev->mtu = mtu;

	ip_tunnel_add(itn, nt);

out:
	return err;
}
EXPORT_SYMBOL_GPL(ip_tunnel_newlink);

int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
			 struct ip_tunnel_parm *p)
{
	struct ip_tunnel *t;
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct net *net = tunnel->net;
	struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);

	if (dev == itn->fb_tunnel_dev)
		return -EINVAL;

	t = ip_tunnel_find(itn, p, dev->type);

	if (t) {
		if (t->dev != dev)
			return -EEXIST;
	} else {
		t = tunnel;

		if (dev->type != ARPHRD_ETHER) {
			unsigned int nflags = 0;

			if (ipv4_is_multicast(p->iph.daddr))
				nflags = IFF_BROADCAST;
			else if (p->iph.daddr)
				nflags = IFF_POINTOPOINT;

			if ((dev->flags ^ nflags) &
			    (IFF_POINTOPOINT | IFF_BROADCAST))
				return -EINVAL;
		}
	}

	ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU]);
	return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_changelink);

int ip_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct iphdr *iph = &tunnel->parms.iph;
	int err;

	dev->destructor	= ip_tunnel_dev_free;
	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
	if (!dev->tstats)
		return -ENOMEM;

	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
	if (!tunnel->dst_cache) {
		free_percpu(dev->tstats);
		return -ENOMEM;
	}

	err = gro_cells_init(&tunnel->gro_cells, dev);
	if (err) {
		free_percpu(tunnel->dst_cache);
		free_percpu(dev->tstats);
		return err;
	}

	tunnel->dev = dev;
	tunnel->net = dev_net(dev);
	strcpy(tunnel->parms.name, dev->name);
	iph->version		= 4;
	iph->ihl		= 5;

	return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_init);

void ip_tunnel_uninit(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct net *net = tunnel->net;
	struct ip_tunnel_net *itn;

	itn = net_generic(net, tunnel->ip_tnl_net_id);
	/* fb_tunnel_dev will be unregisted in net-exit call. */
	if (itn->fb_tunnel_dev != dev)
		ip_tunnel_del(netdev_priv(dev));

	ip_tunnel_dst_reset_all(tunnel);
}
EXPORT_SYMBOL_GPL(ip_tunnel_uninit);

/* Do least required initialization, rest of init is done in tunnel_init call */
void ip_tunnel_setup(struct net_device *dev, int net_id)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	tunnel->ip_tnl_net_id = net_id;
}
EXPORT_SYMBOL_GPL(ip_tunnel_setup);

MODULE_LICENSE("GPL");