summaryrefslogtreecommitdiffstats
path: root/net/ipv6/ip6_tunnel.c
blob: 02730ef26b0fc173e05a96b1bbdbdc69e8321aa1 (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
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
/*
 *	IPv6 tunneling device
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Ville Nuorvala		<vnuorval@tcs.hut.fi>
 *	Yasuyuki Kozakai	<kozakai@linux-ipv6.org>
 *
 *      Based on:
 *      linux/net/ipv6/sit.c and linux/net/ipv4/ipip.c
 *
 *      RFC 2473
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 *
 */

#include <linux/module.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/sockios.h>
#include <linux/icmp.h>
#include <linux/if.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/if_tunnel.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <linux/route.h>
#include <linux/rtnetlink.h>
#include <linux/netfilter_ipv6.h>
#include <linux/slab.h>

#include <asm/uaccess.h>
#include <asm/atomic.h>

#include <net/icmp.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/ip6_tunnel.h>
#include <net/xfrm.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>

MODULE_AUTHOR("Ville Nuorvala");
MODULE_DESCRIPTION("IPv6 tunneling device");
MODULE_LICENSE("GPL");

#ifdef IP6_TNL_DEBUG
#define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __func__)
#else
#define IP6_TNL_TRACE(x...) do {;} while(0)
#endif

#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
#define IPV6_TCLASS_SHIFT 20

#define HASH_SIZE  32

#define HASH(addr) ((__force u32)((addr)->s6_addr32[0] ^ (addr)->s6_addr32[1] ^ \
		     (addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \
		    (HASH_SIZE - 1))

static int ip6_tnl_dev_init(struct net_device *dev);
static void ip6_tnl_dev_setup(struct net_device *dev);

static int ip6_tnl_net_id __read_mostly;
struct ip6_tnl_net {
	/* the IPv6 tunnel fallback device */
	struct net_device *fb_tnl_dev;
	/* lists for storing tunnels in use */
	struct ip6_tnl __rcu *tnls_r_l[HASH_SIZE];
	struct ip6_tnl __rcu *tnls_wc[1];
	struct ip6_tnl __rcu **tnls[2];
};

/* often modified stats are per cpu, other are shared (netdev->stats) */
struct pcpu_tstats {
	unsigned long	rx_packets;
	unsigned long	rx_bytes;
	unsigned long	tx_packets;
	unsigned long	tx_bytes;
};

static struct net_device_stats *ip6_get_stats(struct net_device *dev)
{
	struct pcpu_tstats sum = { 0 };
	int i;

	for_each_possible_cpu(i) {
		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);

		sum.rx_packets += tstats->rx_packets;
		sum.rx_bytes   += tstats->rx_bytes;
		sum.tx_packets += tstats->tx_packets;
		sum.tx_bytes   += tstats->tx_bytes;
	}
	dev->stats.rx_packets = sum.rx_packets;
	dev->stats.rx_bytes   = sum.rx_bytes;
	dev->stats.tx_packets = sum.tx_packets;
	dev->stats.tx_bytes   = sum.tx_bytes;
	return &dev->stats;
}

/*
 * Locking : hash tables are protected by RCU and RTNL
 */

static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
{
	struct dst_entry *dst = t->dst_cache;

	if (dst && dst->obsolete &&
	    dst->ops->check(dst, t->dst_cookie) == NULL) {
		t->dst_cache = NULL;
		dst_release(dst);
		return NULL;
	}

	return dst;
}

static inline void ip6_tnl_dst_reset(struct ip6_tnl *t)
{
	dst_release(t->dst_cache);
	t->dst_cache = NULL;
}

static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
{
	struct rt6_info *rt = (struct rt6_info *) dst;
	t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
	dst_release(t->dst_cache);
	t->dst_cache = dst;
}

/**
 * ip6_tnl_lookup - fetch tunnel matching the end-point addresses
 *   @remote: the address of the tunnel exit-point
 *   @local: the address of the tunnel entry-point
 *
 * Return:
 *   tunnel matching given end-points if found,
 *   else fallback tunnel if its device is up,
 *   else %NULL
 **/

#define for_each_ip6_tunnel_rcu(start) \
	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))

static struct ip6_tnl *
ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local)
{
	unsigned int h0 = HASH(remote);
	unsigned int h1 = HASH(local);
	struct ip6_tnl *t;
	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);

	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[h0 ^ h1]) {
		if (ipv6_addr_equal(local, &t->parms.laddr) &&
		    ipv6_addr_equal(remote, &t->parms.raddr) &&
		    (t->dev->flags & IFF_UP))
			return t;
	}
	t = rcu_dereference(ip6n->tnls_wc[0]);
	if (t && (t->dev->flags & IFF_UP))
		return t;

	return NULL;
}

/**
 * ip6_tnl_bucket - get head of list matching given tunnel parameters
 *   @p: parameters containing tunnel end-points
 *
 * Description:
 *   ip6_tnl_bucket() returns the head of the list matching the
 *   &struct in6_addr entries laddr and raddr in @p.
 *
 * Return: head of IPv6 tunnel list
 **/

static struct ip6_tnl __rcu **
ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p)
{
	struct in6_addr *remote = &p->raddr;
	struct in6_addr *local = &p->laddr;
	unsigned h = 0;
	int prio = 0;

	if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) {
		prio = 1;
		h = HASH(remote) ^ HASH(local);
	}
	return &ip6n->tnls[prio][h];
}

/**
 * ip6_tnl_link - add tunnel to hash table
 *   @t: tunnel to be added
 **/

static void
ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
	struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms);

	rcu_assign_pointer(t->next , rtnl_dereference(*tp));
	rcu_assign_pointer(*tp, t);
}

/**
 * ip6_tnl_unlink - remove tunnel from hash table
 *   @t: tunnel to be removed
 **/

static void
ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
	struct ip6_tnl __rcu **tp;
	struct ip6_tnl *iter;

	for (tp = ip6_tnl_bucket(ip6n, &t->parms);
	     (iter = rtnl_dereference(*tp)) != NULL;
	     tp = &iter->next) {
		if (t == iter) {
			rcu_assign_pointer(*tp, t->next);
			break;
		}
	}
}

static void ip6_dev_free(struct net_device *dev)
{
	free_percpu(dev->tstats);
	free_netdev(dev);
}

/**
 * ip6_tnl_create() - create a new tunnel
 *   @p: tunnel parameters
 *   @pt: pointer to new tunnel
 *
 * Description:
 *   Create tunnel matching given parameters.
 *
 * Return:
 *   created tunnel or NULL
 **/

static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p)
{
	struct net_device *dev;
	struct ip6_tnl *t;
	char name[IFNAMSIZ];
	int err;
	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);

	if (p->name[0])
		strlcpy(name, p->name, IFNAMSIZ);
	else
		sprintf(name, "ip6tnl%%d");

	dev = alloc_netdev(sizeof (*t), name, ip6_tnl_dev_setup);
	if (dev == NULL)
		goto failed;

	dev_net_set(dev, net);

	if (strchr(name, '%')) {
		if (dev_alloc_name(dev, name) < 0)
			goto failed_free;
	}

	t = netdev_priv(dev);
	t->parms = *p;
	err = ip6_tnl_dev_init(dev);
	if (err < 0)
		goto failed_free;

	if ((err = register_netdevice(dev)) < 0)
		goto failed_free;

	dev_hold(dev);
	ip6_tnl_link(ip6n, t);
	return t;

failed_free:
	ip6_dev_free(dev);
failed:
	return NULL;
}

/**
 * ip6_tnl_locate - find or create tunnel matching given parameters
 *   @p: tunnel parameters
 *   @create: != 0 if allowed to create new tunnel if no match found
 *
 * Description:
 *   ip6_tnl_locate() first tries to locate an existing tunnel
 *   based on @parms. If this is unsuccessful, but @create is set a new
 *   tunnel device is created and registered for use.
 *
 * Return:
 *   matching tunnel or NULL
 **/

static struct ip6_tnl *ip6_tnl_locate(struct net *net,
		struct ip6_tnl_parm *p, int create)
{
	struct in6_addr *remote = &p->raddr;
	struct in6_addr *local = &p->laddr;
	struct ip6_tnl __rcu **tp;
	struct ip6_tnl *t;
	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);

	for (tp = ip6_tnl_bucket(ip6n, p);
	     (t = rtnl_dereference(*tp)) != NULL;
	     tp = &t->next) {
		if (ipv6_addr_equal(local, &t->parms.laddr) &&
		    ipv6_addr_equal(remote, &t->parms.raddr))
			return t;
	}
	if (!create)
		return NULL;
	return ip6_tnl_create(net, p);
}

/**
 * ip6_tnl_dev_uninit - tunnel device uninitializer
 *   @dev: the device to be destroyed
 *
 * Description:
 *   ip6_tnl_dev_uninit() removes tunnel from its list
 **/

static void
ip6_tnl_dev_uninit(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct net *net = dev_net(dev);
	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);

	if (dev == ip6n->fb_tnl_dev)
		rcu_assign_pointer(ip6n->tnls_wc[0], NULL);
	else
		ip6_tnl_unlink(ip6n, t);
	ip6_tnl_dst_reset(t);
	dev_put(dev);
}

/**
 * parse_tvl_tnl_enc_lim - handle encapsulation limit option
 *   @skb: received socket buffer
 *
 * Return:
 *   0 if none was found,
 *   else index to encapsulation limit
 **/

static __u16
parse_tlv_tnl_enc_lim(struct sk_buff *skb, __u8 * raw)
{
	struct ipv6hdr *ipv6h = (struct ipv6hdr *) raw;
	__u8 nexthdr = ipv6h->nexthdr;
	__u16 off = sizeof (*ipv6h);

	while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
		__u16 optlen = 0;
		struct ipv6_opt_hdr *hdr;
		if (raw + off + sizeof (*hdr) > skb->data &&
		    !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
			break;

		hdr = (struct ipv6_opt_hdr *) (raw + off);
		if (nexthdr == NEXTHDR_FRAGMENT) {
			struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
			if (frag_hdr->frag_off)
				break;
			optlen = 8;
		} else if (nexthdr == NEXTHDR_AUTH) {
			optlen = (hdr->hdrlen + 2) << 2;
		} else {
			optlen = ipv6_optlen(hdr);
		}
		if (nexthdr == NEXTHDR_DEST) {
			__u16 i = off + 2;
			while (1) {
				struct ipv6_tlv_tnl_enc_lim *tel;

				/* No more room for encapsulation limit */
				if (i + sizeof (*tel) > off + optlen)
					break;

				tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i];
				/* return index of option if found and valid */
				if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
				    tel->length == 1)
					return i;
				/* else jump to next option */
				if (tel->type)
					i += tel->length + 2;
				else
					i++;
			}
		}
		nexthdr = hdr->nexthdr;
		off += optlen;
	}
	return 0;
}

/**
 * ip6_tnl_err - tunnel error handler
 *
 * Description:
 *   ip6_tnl_err() should handle errors in the tunnel according
 *   to the specifications in RFC 2473.
 **/

static int
ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
	    u8 *type, u8 *code, int *msg, __u32 *info, int offset)
{
	struct ipv6hdr *ipv6h = (struct ipv6hdr *) skb->data;
	struct ip6_tnl *t;
	int rel_msg = 0;
	u8 rel_type = ICMPV6_DEST_UNREACH;
	u8 rel_code = ICMPV6_ADDR_UNREACH;
	__u32 rel_info = 0;
	__u16 len;
	int err = -ENOENT;

	/* If the packet doesn't contain the original IPv6 header we are
	   in trouble since we might need the source address for further
	   processing of the error. */

	rcu_read_lock();
	if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr,
					&ipv6h->saddr)) == NULL)
		goto out;

	if (t->parms.proto != ipproto && t->parms.proto != 0)
		goto out;

	err = 0;

	switch (*type) {
		__u32 teli;
		struct ipv6_tlv_tnl_enc_lim *tel;
		__u32 mtu;
	case ICMPV6_DEST_UNREACH:
		if (net_ratelimit())
			printk(KERN_WARNING
			       "%s: Path to destination invalid "
			       "or inactive!\n", t->parms.name);
		rel_msg = 1;
		break;
	case ICMPV6_TIME_EXCEED:
		if ((*code) == ICMPV6_EXC_HOPLIMIT) {
			if (net_ratelimit())
				printk(KERN_WARNING
				       "%s: Too small hop limit or "
				       "routing loop in tunnel!\n",
				       t->parms.name);
			rel_msg = 1;
		}
		break;
	case ICMPV6_PARAMPROB:
		teli = 0;
		if ((*code) == ICMPV6_HDR_FIELD)
			teli = parse_tlv_tnl_enc_lim(skb, skb->data);

		if (teli && teli == *info - 2) {
			tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
			if (tel->encap_limit == 0) {
				if (net_ratelimit())
					printk(KERN_WARNING
					       "%s: Too small encapsulation "
					       "limit or routing loop in "
					       "tunnel!\n", t->parms.name);
				rel_msg = 1;
			}
		} else if (net_ratelimit()) {
			printk(KERN_WARNING
			       "%s: Recipient unable to parse tunneled "
			       "packet!\n ", t->parms.name);
		}
		break;
	case ICMPV6_PKT_TOOBIG:
		mtu = *info - offset;
		if (mtu < IPV6_MIN_MTU)
			mtu = IPV6_MIN_MTU;
		t->dev->mtu = mtu;

		if ((len = sizeof (*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) {
			rel_type = ICMPV6_PKT_TOOBIG;
			rel_code = 0;
			rel_info = mtu;
			rel_msg = 1;
		}
		break;
	}

	*type = rel_type;
	*code = rel_code;
	*info = rel_info;
	*msg = rel_msg;

out:
	rcu_read_unlock();
	return err;
}

static int
ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
	   u8 type, u8 code, int offset, __be32 info)
{
	int rel_msg = 0;
	u8 rel_type = type;
	u8 rel_code = code;
	__u32 rel_info = ntohl(info);
	int err;
	struct sk_buff *skb2;
	struct iphdr *eiph;
	struct flowi fl;
	struct rtable *rt;

	err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code,
			  &rel_msg, &rel_info, offset);
	if (err < 0)
		return err;

	if (rel_msg == 0)
		return 0;

	switch (rel_type) {
	case ICMPV6_DEST_UNREACH:
		if (rel_code != ICMPV6_ADDR_UNREACH)
			return 0;
		rel_type = ICMP_DEST_UNREACH;
		rel_code = ICMP_HOST_UNREACH;
		break;
	case ICMPV6_PKT_TOOBIG:
		if (rel_code != 0)
			return 0;
		rel_type = ICMP_DEST_UNREACH;
		rel_code = ICMP_FRAG_NEEDED;
		break;
	default:
		return 0;
	}

	if (!pskb_may_pull(skb, offset + sizeof(struct iphdr)))
		return 0;

	skb2 = skb_clone(skb, GFP_ATOMIC);
	if (!skb2)
		return 0;

	skb_dst_drop(skb2);

	skb_pull(skb2, offset);
	skb_reset_network_header(skb2);
	eiph = ip_hdr(skb2);

	/* Try to guess incoming interface */
	memset(&fl, 0, sizeof(fl));
	fl.fl4_dst = eiph->saddr;
	fl.fl4_tos = RT_TOS(eiph->tos);
	fl.proto = IPPROTO_IPIP;
	rt = ip_route_output_key(dev_net(skb->dev), &fl);
	if (IS_ERR(rt))
		goto out;

	skb2->dev = rt->dst.dev;

	/* route "incoming" packet */
	if (rt->rt_flags & RTCF_LOCAL) {
		ip_rt_put(rt);
		rt = NULL;
		fl.fl4_dst = eiph->daddr;
		fl.fl4_src = eiph->saddr;
		fl.fl4_tos = eiph->tos;
		rt = ip_route_output_key(dev_net(skb->dev), &fl);
		if (IS_ERR(rt) ||
		    rt->dst.dev->type != ARPHRD_TUNNEL) {
			if (!IS_ERR(rt))
				ip_rt_put(rt);
			goto out;
		}
		skb_dst_set(skb2, &rt->dst);
	} else {
		ip_rt_put(rt);
		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
				   skb2->dev) ||
		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
			goto out;
	}

	/* change mtu on this route */
	if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) {
		if (rel_info > dst_mtu(skb_dst(skb2)))
			goto out;

		skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info);
	}

	icmp_send(skb2, rel_type, rel_code, htonl(rel_info));

out:
	kfree_skb(skb2);
	return 0;
}

static int
ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
	   u8 type, u8 code, int offset, __be32 info)
{
	int rel_msg = 0;
	u8 rel_type = type;
	u8 rel_code = code;
	__u32 rel_info = ntohl(info);
	int err;

	err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code,
			  &rel_msg, &rel_info, offset);
	if (err < 0)
		return err;

	if (rel_msg && pskb_may_pull(skb, offset + sizeof(struct ipv6hdr))) {
		struct rt6_info *rt;
		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);

		if (!skb2)
			return 0;

		skb_dst_drop(skb2);
		skb_pull(skb2, offset);
		skb_reset_network_header(skb2);

		/* Try to guess incoming interface */
		rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr,
				NULL, 0, 0);

		if (rt && rt->rt6i_dev)
			skb2->dev = rt->rt6i_dev;

		icmpv6_send(skb2, rel_type, rel_code, rel_info);

		if (rt)
			dst_release(&rt->dst);

		kfree_skb(skb2);
	}

	return 0;
}

static void ip4ip6_dscp_ecn_decapsulate(struct ip6_tnl *t,
					struct ipv6hdr *ipv6h,
					struct sk_buff *skb)
{
	__u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK;

	if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
		ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield);

	if (INET_ECN_is_ce(dsfield))
		IP_ECN_set_ce(ip_hdr(skb));
}

static void ip6ip6_dscp_ecn_decapsulate(struct ip6_tnl *t,
					struct ipv6hdr *ipv6h,
					struct sk_buff *skb)
{
	if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
		ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb));

	if (INET_ECN_is_ce(ipv6_get_dsfield(ipv6h)))
		IP6_ECN_set_ce(ipv6_hdr(skb));
}

/* called with rcu_read_lock() */
static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t)
{
	struct ip6_tnl_parm *p = &t->parms;
	int ret = 0;
	struct net *net = dev_net(t->dev);

	if (p->flags & IP6_TNL_F_CAP_RCV) {
		struct net_device *ldev = NULL;

		if (p->link)
			ldev = dev_get_by_index_rcu(net, p->link);

		if ((ipv6_addr_is_multicast(&p->laddr) ||
		     likely(ipv6_chk_addr(net, &p->laddr, ldev, 0))) &&
		    likely(!ipv6_chk_addr(net, &p->raddr, NULL, 0)))
			ret = 1;

	}
	return ret;
}

/**
 * ip6_tnl_rcv - decapsulate IPv6 packet and retransmit it locally
 *   @skb: received socket buffer
 *   @protocol: ethernet protocol ID
 *   @dscp_ecn_decapsulate: the function to decapsulate DSCP code and ECN
 *
 * Return: 0
 **/

static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
		       __u8 ipproto,
		       void (*dscp_ecn_decapsulate)(struct ip6_tnl *t,
						    struct ipv6hdr *ipv6h,
						    struct sk_buff *skb))
{
	struct ip6_tnl *t;
	struct ipv6hdr *ipv6h = ipv6_hdr(skb);

	rcu_read_lock();

	if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr,
					&ipv6h->daddr)) != NULL) {
		struct pcpu_tstats *tstats;

		if (t->parms.proto != ipproto && t->parms.proto != 0) {
			rcu_read_unlock();
			goto discard;
		}

		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
			rcu_read_unlock();
			goto discard;
		}

		if (!ip6_tnl_rcv_ctl(t)) {
			t->dev->stats.rx_dropped++;
			rcu_read_unlock();
			goto discard;
		}
		secpath_reset(skb);
		skb->mac_header = skb->network_header;
		skb_reset_network_header(skb);
		skb->protocol = htons(protocol);
		skb->pkt_type = PACKET_HOST;
		memset(skb->cb, 0, sizeof(struct inet6_skb_parm));

		tstats = this_cpu_ptr(t->dev->tstats);
		tstats->rx_packets++;
		tstats->rx_bytes += skb->len;

		__skb_tunnel_rx(skb, t->dev);

		dscp_ecn_decapsulate(t, ipv6h, skb);

		netif_rx(skb);

		rcu_read_unlock();
		return 0;
	}
	rcu_read_unlock();
	return 1;

discard:
	kfree_skb(skb);
	return 0;
}

static int ip4ip6_rcv(struct sk_buff *skb)
{
	return ip6_tnl_rcv(skb, ETH_P_IP, IPPROTO_IPIP,
			   ip4ip6_dscp_ecn_decapsulate);
}

static int ip6ip6_rcv(struct sk_buff *skb)
{
	return ip6_tnl_rcv(skb, ETH_P_IPV6, IPPROTO_IPV6,
			   ip6ip6_dscp_ecn_decapsulate);
}

struct ipv6_tel_txoption {
	struct ipv6_txoptions ops;
	__u8 dst_opt[8];
};

static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit)
{
	memset(opt, 0, sizeof(struct ipv6_tel_txoption));

	opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT;
	opt->dst_opt[3] = 1;
	opt->dst_opt[4] = encap_limit;
	opt->dst_opt[5] = IPV6_TLV_PADN;
	opt->dst_opt[6] = 1;

	opt->ops.dst0opt = (struct ipv6_opt_hdr *) opt->dst_opt;
	opt->ops.opt_nflen = 8;
}

/**
 * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own
 *   @t: the outgoing tunnel device
 *   @hdr: IPv6 header from the incoming packet
 *
 * Description:
 *   Avoid trivial tunneling loop by checking that tunnel exit-point
 *   doesn't match source of incoming packet.
 *
 * Return:
 *   1 if conflict,
 *   0 else
 **/

static inline int
ip6_tnl_addr_conflict(struct ip6_tnl *t, struct ipv6hdr *hdr)
{
	return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
}

static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
{
	struct ip6_tnl_parm *p = &t->parms;
	int ret = 0;
	struct net *net = dev_net(t->dev);

	if (p->flags & IP6_TNL_F_CAP_XMIT) {
		struct net_device *ldev = NULL;

		rcu_read_lock();
		if (p->link)
			ldev = dev_get_by_index_rcu(net, p->link);

		if (unlikely(!ipv6_chk_addr(net, &p->laddr, ldev, 0)))
			printk(KERN_WARNING
			       "%s xmit: Local address not yet configured!\n",
			       p->name);
		else if (!ipv6_addr_is_multicast(&p->raddr) &&
			 unlikely(ipv6_chk_addr(net, &p->raddr, NULL, 0)))
			printk(KERN_WARNING
			       "%s xmit: Routing loop! "
			       "Remote address found on this node!\n",
			       p->name);
		else
			ret = 1;
		rcu_read_unlock();
	}
	return ret;
}
/**
 * ip6_tnl_xmit2 - encapsulate packet and send
 *   @skb: the outgoing socket buffer
 *   @dev: the outgoing tunnel device
 *   @dsfield: dscp code for outer header
 *   @fl: flow of tunneled packet
 *   @encap_limit: encapsulation limit
 *   @pmtu: Path MTU is stored if packet is too big
 *
 * Description:
 *   Build new header and do some sanity checks on the packet before sending
 *   it.
 *
 * Return:
 *   0 on success
 *   -1 fail
 *   %-EMSGSIZE message too big. return mtu in this case.
 **/

static int ip6_tnl_xmit2(struct sk_buff *skb,
			 struct net_device *dev,
			 __u8 dsfield,
			 struct flowi *fl,
			 int encap_limit,
			 __u32 *pmtu)
{
	struct net *net = dev_net(dev);
	struct ip6_tnl *t = netdev_priv(dev);
	struct net_device_stats *stats = &t->dev->stats;
	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
	struct ipv6_tel_txoption opt;
	struct dst_entry *dst;
	struct net_device *tdev;
	int mtu;
	unsigned int max_headroom = sizeof(struct ipv6hdr);
	u8 proto;
	int err = -1;
	int pkt_len;

	if ((dst = ip6_tnl_dst_check(t)) != NULL)
		dst_hold(dst);
	else {
		dst = ip6_route_output(net, NULL, fl);

		if (dst->error)
			goto tx_err_link_failure;
		dst = xfrm_lookup(net, dst, fl, NULL, 0);
		if (IS_ERR(dst)) {
			err = PTR_ERR(dst);
			dst = NULL;
			goto tx_err_link_failure;
		}
	}

	tdev = dst->dev;

	if (tdev == dev) {
		stats->collisions++;
		if (net_ratelimit())
			printk(KERN_WARNING
			       "%s: Local routing loop detected!\n",
			       t->parms.name);
		goto tx_err_dst_release;
	}
	mtu = dst_mtu(dst) - sizeof (*ipv6h);
	if (encap_limit >= 0) {
		max_headroom += 8;
		mtu -= 8;
	}
	if (mtu < IPV6_MIN_MTU)
		mtu = IPV6_MIN_MTU;
	if (skb_dst(skb))
		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
	if (skb->len > mtu) {
		*pmtu = mtu;
		err = -EMSGSIZE;
		goto tx_err_dst_release;
	}

	/*
	 * Okay, now see if we can stuff it in the buffer as-is.
	 */
	max_headroom += LL_RESERVED_SPACE(tdev);

	if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
		struct sk_buff *new_skb;

		if (!(new_skb = skb_realloc_headroom(skb, max_headroom)))
			goto tx_err_dst_release;

		if (skb->sk)
			skb_set_owner_w(new_skb, skb->sk);
		kfree_skb(skb);
		skb = new_skb;
	}
	skb_dst_drop(skb);
	skb_dst_set(skb, dst_clone(dst));

	skb->transport_header = skb->network_header;

	proto = fl->proto;
	if (encap_limit >= 0) {
		init_tel_txopt(&opt, encap_limit);
		ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
	}
	skb_push(skb, sizeof(struct ipv6hdr));
	skb_reset_network_header(skb);
	ipv6h = ipv6_hdr(skb);
	*(__be32*)ipv6h = fl->fl6_flowlabel | htonl(0x60000000);
	dsfield = INET_ECN_encapsulate(0, dsfield);
	ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
	ipv6h->hop_limit = t->parms.hop_limit;
	ipv6h->nexthdr = proto;
	ipv6_addr_copy(&ipv6h->saddr, &fl->fl6_src);
	ipv6_addr_copy(&ipv6h->daddr, &fl->fl6_dst);
	nf_reset(skb);
	pkt_len = skb->len;
	err = ip6_local_out(skb);

	if (net_xmit_eval(err) == 0) {
		struct pcpu_tstats *tstats = this_cpu_ptr(t->dev->tstats);

		tstats->tx_bytes += pkt_len;
		tstats->tx_packets++;
	} else {
		stats->tx_errors++;
		stats->tx_aborted_errors++;
	}
	ip6_tnl_dst_store(t, dst);
	return 0;
tx_err_link_failure:
	stats->tx_carrier_errors++;
	dst_link_failure(skb);
tx_err_dst_release:
	dst_release(dst);
	return err;
}

static inline int
ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct iphdr  *iph = ip_hdr(skb);
	int encap_limit = -1;
	struct flowi fl;
	__u8 dsfield;
	__u32 mtu;
	int err;

	if ((t->parms.proto != IPPROTO_IPIP && t->parms.proto != 0) ||
	    !ip6_tnl_xmit_ctl(t))
		return -1;

	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
		encap_limit = t->parms.encap_limit;

	memcpy(&fl, &t->fl, sizeof (fl));
	fl.proto = IPPROTO_IPIP;

	dsfield = ipv4_get_dsfield(iph);

	if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
		fl.fl6_flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
					  & IPV6_TCLASS_MASK;

	err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu);
	if (err != 0) {
		/* XXX: send ICMP error even if DF is not set. */
		if (err == -EMSGSIZE)
			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
				  htonl(mtu));
		return -1;
	}

	return 0;
}

static inline int
ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
	int encap_limit = -1;
	__u16 offset;
	struct flowi fl;
	__u8 dsfield;
	__u32 mtu;
	int err;

	if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
	    !ip6_tnl_xmit_ctl(t) || ip6_tnl_addr_conflict(t, ipv6h))
		return -1;

	offset = parse_tlv_tnl_enc_lim(skb, skb_network_header(skb));
	if (offset > 0) {
		struct ipv6_tlv_tnl_enc_lim *tel;
		tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
		if (tel->encap_limit == 0) {
			icmpv6_send(skb, ICMPV6_PARAMPROB,
				    ICMPV6_HDR_FIELD, offset + 2);
			return -1;
		}
		encap_limit = tel->encap_limit - 1;
	} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
		encap_limit = t->parms.encap_limit;

	memcpy(&fl, &t->fl, sizeof (fl));
	fl.proto = IPPROTO_IPV6;

	dsfield = ipv6_get_dsfield(ipv6h);
	if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
		fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
	if ((t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL))
		fl.fl6_flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);

	err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu);
	if (err != 0) {
		if (err == -EMSGSIZE)
			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
		return -1;
	}

	return 0;
}

static netdev_tx_t
ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct net_device_stats *stats = &t->dev->stats;
	int ret;

	switch (skb->protocol) {
	case htons(ETH_P_IP):
		ret = ip4ip6_tnl_xmit(skb, dev);
		break;
	case htons(ETH_P_IPV6):
		ret = ip6ip6_tnl_xmit(skb, dev);
		break;
	default:
		goto tx_err;
	}

	if (ret < 0)
		goto tx_err;

	return NETDEV_TX_OK;

tx_err:
	stats->tx_errors++;
	stats->tx_dropped++;
	kfree_skb(skb);
	return NETDEV_TX_OK;
}

static void ip6_tnl_set_cap(struct ip6_tnl *t)
{
	struct ip6_tnl_parm *p = &t->parms;
	int ltype = ipv6_addr_type(&p->laddr);
	int rtype = ipv6_addr_type(&p->raddr);

	p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV);

	if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) &&
	    rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) &&
	    !((ltype|rtype) & IPV6_ADDR_LOOPBACK) &&
	    (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) {
		if (ltype&IPV6_ADDR_UNICAST)
			p->flags |= IP6_TNL_F_CAP_XMIT;
		if (rtype&IPV6_ADDR_UNICAST)
			p->flags |= IP6_TNL_F_CAP_RCV;
	}
}

static void ip6_tnl_link_config(struct ip6_tnl *t)
{
	struct net_device *dev = t->dev;
	struct ip6_tnl_parm *p = &t->parms;
	struct flowi *fl = &t->fl;

	memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
	memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));

	/* Set up flowi template */
	ipv6_addr_copy(&fl->fl6_src, &p->laddr);
	ipv6_addr_copy(&fl->fl6_dst, &p->raddr);
	fl->oif = p->link;
	fl->fl6_flowlabel = 0;

	if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS))
		fl->fl6_flowlabel |= IPV6_TCLASS_MASK & p->flowinfo;
	if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL))
		fl->fl6_flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo;

	ip6_tnl_set_cap(t);

	if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV)
		dev->flags |= IFF_POINTOPOINT;
	else
		dev->flags &= ~IFF_POINTOPOINT;

	dev->iflink = p->link;

	if (p->flags & IP6_TNL_F_CAP_XMIT) {
		int strict = (ipv6_addr_type(&p->raddr) &
			      (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));

		struct rt6_info *rt = rt6_lookup(dev_net(dev),
						 &p->raddr, &p->laddr,
						 p->link, strict);

		if (rt == NULL)
			return;

		if (rt->rt6i_dev) {
			dev->hard_header_len = rt->rt6i_dev->hard_header_len +
				sizeof (struct ipv6hdr);

			dev->mtu = rt->rt6i_dev->mtu - sizeof (struct ipv6hdr);
			if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
				dev->mtu-=8;

			if (dev->mtu < IPV6_MIN_MTU)
				dev->mtu = IPV6_MIN_MTU;
		}
		dst_release(&rt->dst);
	}
}

/**
 * ip6_tnl_change - update the tunnel parameters
 *   @t: tunnel to be changed
 *   @p: tunnel configuration parameters
 *
 * Description:
 *   ip6_tnl_change() updates the tunnel parameters
 **/

static int
ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p)
{
	ipv6_addr_copy(&t->parms.laddr, &p->laddr);
	ipv6_addr_copy(&t->parms.raddr, &p->raddr);
	t->parms.flags = p->flags;
	t->parms.hop_limit = p->hop_limit;
	t->parms.encap_limit = p->encap_limit;
	t->parms.flowinfo = p->flowinfo;
	t->parms.link = p->link;
	t->parms.proto = p->proto;
	ip6_tnl_dst_reset(t);
	ip6_tnl_link_config(t);
	return 0;
}

/**
 * ip6_tnl_ioctl - configure ipv6 tunnels from userspace
 *   @dev: virtual device associated with tunnel
 *   @ifr: parameters passed from userspace
 *   @cmd: command to be performed
 *
 * Description:
 *   ip6_tnl_ioctl() is used for managing IPv6 tunnels
 *   from userspace.
 *
 *   The possible commands are the following:
 *     %SIOCGETTUNNEL: get tunnel parameters for device
 *     %SIOCADDTUNNEL: add tunnel matching given tunnel parameters
 *     %SIOCCHGTUNNEL: change tunnel parameters to those given
 *     %SIOCDELTUNNEL: delete tunnel
 *
 *   The fallback device "ip6tnl0", created during module
 *   initialization, can be used for creating other tunnel devices.
 *
 * Return:
 *   0 on success,
 *   %-EFAULT if unable to copy data to or from userspace,
 *   %-EPERM if current process hasn't %CAP_NET_ADMIN set
 *   %-EINVAL if passed tunnel parameters are invalid,
 *   %-EEXIST if changing a tunnel's parameters would cause a conflict
 *   %-ENODEV if attempting to change or delete a nonexisting device
 **/

static int
ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
	int err = 0;
	struct ip6_tnl_parm p;
	struct ip6_tnl *t = NULL;
	struct net *net = dev_net(dev);
	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);

	switch (cmd) {
	case SIOCGETTUNNEL:
		if (dev == ip6n->fb_tnl_dev) {
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) {
				err = -EFAULT;
				break;
			}
			t = ip6_tnl_locate(net, &p, 0);
		}
		if (t == NULL)
			t = netdev_priv(dev);
		memcpy(&p, &t->parms, sizeof (p));
		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) {
			err = -EFAULT;
		}
		break;
	case SIOCADDTUNNEL:
	case SIOCCHGTUNNEL:
		err = -EPERM;
		if (!capable(CAP_NET_ADMIN))
			break;
		err = -EFAULT;
		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p)))
			break;
		err = -EINVAL;
		if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP &&
		    p.proto != 0)
			break;
		t = ip6_tnl_locate(net, &p, cmd == SIOCADDTUNNEL);
		if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) {
			if (t != NULL) {
				if (t->dev != dev) {
					err = -EEXIST;
					break;
				}
			} else
				t = netdev_priv(dev);

			ip6_tnl_unlink(ip6n, t);
			synchronize_net();
			err = ip6_tnl_change(t, &p);
			ip6_tnl_link(ip6n, t);
			netdev_state_change(dev);
		}
		if (t) {
			err = 0;
			if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof (p)))
				err = -EFAULT;

		} else
			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
		break;
	case SIOCDELTUNNEL:
		err = -EPERM;
		if (!capable(CAP_NET_ADMIN))
			break;

		if (dev == ip6n->fb_tnl_dev) {
			err = -EFAULT;
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p)))
				break;
			err = -ENOENT;
			if ((t = ip6_tnl_locate(net, &p, 0)) == NULL)
				break;
			err = -EPERM;
			if (t->dev == ip6n->fb_tnl_dev)
				break;
			dev = t->dev;
		}
		err = 0;
		unregister_netdevice(dev);
		break;
	default:
		err = -EINVAL;
	}
	return err;
}

/**
 * ip6_tnl_change_mtu - change mtu manually for tunnel device
 *   @dev: virtual device associated with tunnel
 *   @new_mtu: the new mtu
 *
 * Return:
 *   0 on success,
 *   %-EINVAL if mtu too small
 **/

static int
ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu < IPV6_MIN_MTU) {
		return -EINVAL;
	}
	dev->mtu = new_mtu;
	return 0;
}


static const struct net_device_ops ip6_tnl_netdev_ops = {
	.ndo_uninit	= ip6_tnl_dev_uninit,
	.ndo_start_xmit = ip6_tnl_xmit,
	.ndo_do_ioctl	= ip6_tnl_ioctl,
	.ndo_change_mtu = ip6_tnl_change_mtu,
	.ndo_get_stats	= ip6_get_stats,
};


/**
 * ip6_tnl_dev_setup - setup virtual tunnel device
 *   @dev: virtual device associated with tunnel
 *
 * Description:
 *   Initialize function pointers and device parameters
 **/

static void ip6_tnl_dev_setup(struct net_device *dev)
{
	struct ip6_tnl *t;

	dev->netdev_ops = &ip6_tnl_netdev_ops;
	dev->destructor = ip6_dev_free;

	dev->type = ARPHRD_TUNNEL6;
	dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr);
	dev->mtu = ETH_DATA_LEN - sizeof (struct ipv6hdr);
	t = netdev_priv(dev);
	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
		dev->mtu-=8;
	dev->flags |= IFF_NOARP;
	dev->addr_len = sizeof(struct in6_addr);
	dev->features |= NETIF_F_NETNS_LOCAL;
	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
}


/**
 * ip6_tnl_dev_init_gen - general initializer for all tunnel devices
 *   @dev: virtual device associated with tunnel
 **/

static inline int
ip6_tnl_dev_init_gen(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);

	t->dev = dev;
	strcpy(t->parms.name, dev->name);
	dev->tstats = alloc_percpu(struct pcpu_tstats);
	if (!dev->tstats)
		return -ENOMEM;
	return 0;
}

/**
 * ip6_tnl_dev_init - initializer for all non fallback tunnel devices
 *   @dev: virtual device associated with tunnel
 **/

static int ip6_tnl_dev_init(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	int err = ip6_tnl_dev_init_gen(dev);

	if (err)
		return err;
	ip6_tnl_link_config(t);
	return 0;
}

/**
 * ip6_fb_tnl_dev_init - initializer for fallback tunnel device
 *   @dev: fallback device
 *
 * Return: 0
 **/

static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
{
	struct ip6_tnl *t = netdev_priv(dev);
	struct net *net = dev_net(dev);
	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
	int err = ip6_tnl_dev_init_gen(dev);

	if (err)
		return err;

	t->parms.proto = IPPROTO_IPV6;
	dev_hold(dev);
	rcu_assign_pointer(ip6n->tnls_wc[0], t);
	return 0;
}

static struct xfrm6_tunnel ip4ip6_handler __read_mostly = {
	.handler	= ip4ip6_rcv,
	.err_handler	= ip4ip6_err,
	.priority	=	1,
};

static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
	.handler	= ip6ip6_rcv,
	.err_handler	= ip6ip6_err,
	.priority	=	1,
};

static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
{
	int h;
	struct ip6_tnl *t;
	LIST_HEAD(list);

	for (h = 0; h < HASH_SIZE; h++) {
		t = rtnl_dereference(ip6n->tnls_r_l[h]);
		while (t != NULL) {
			unregister_netdevice_queue(t->dev, &list);
			t = rtnl_dereference(t->next);
		}
	}

	t = rtnl_dereference(ip6n->tnls_wc[0]);
	unregister_netdevice_queue(t->dev, &list);
	unregister_netdevice_many(&list);
}

static int __net_init ip6_tnl_init_net(struct net *net)
{
	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
	int err;

	ip6n->tnls[0] = ip6n->tnls_wc;
	ip6n->tnls[1] = ip6n->tnls_r_l;

	err = -ENOMEM;
	ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0",
				      ip6_tnl_dev_setup);

	if (!ip6n->fb_tnl_dev)
		goto err_alloc_dev;
	dev_net_set(ip6n->fb_tnl_dev, net);

	err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
	if (err < 0)
		goto err_register;

	err = register_netdev(ip6n->fb_tnl_dev);
	if (err < 0)
		goto err_register;
	return 0;

err_register:
	ip6_dev_free(ip6n->fb_tnl_dev);
err_alloc_dev:
	return err;
}

static void __net_exit ip6_tnl_exit_net(struct net *net)
{
	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);

	rtnl_lock();
	ip6_tnl_destroy_tunnels(ip6n);
	rtnl_unlock();
}

static struct pernet_operations ip6_tnl_net_ops = {
	.init = ip6_tnl_init_net,
	.exit = ip6_tnl_exit_net,
	.id   = &ip6_tnl_net_id,
	.size = sizeof(struct ip6_tnl_net),
};

/**
 * ip6_tunnel_init - register protocol and reserve needed resources
 *
 * Return: 0 on success
 **/

static int __init ip6_tunnel_init(void)
{
	int  err;

	err = register_pernet_device(&ip6_tnl_net_ops);
	if (err < 0)
		goto out_pernet;

	err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET);
	if (err < 0) {
		printk(KERN_ERR "ip6_tunnel init: can't register ip4ip6\n");
		goto out_ip4ip6;
	}

	err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6);
	if (err < 0) {
		printk(KERN_ERR "ip6_tunnel init: can't register ip6ip6\n");
		goto out_ip6ip6;
	}

	return 0;

out_ip6ip6:
	xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET);
out_ip4ip6:
	unregister_pernet_device(&ip6_tnl_net_ops);
out_pernet:
	return err;
}

/**
 * ip6_tunnel_cleanup - free resources and unregister protocol
 **/

static void __exit ip6_tunnel_cleanup(void)
{
	if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET))
		printk(KERN_INFO "ip6_tunnel close: can't deregister ip4ip6\n");

	if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6))
		printk(KERN_INFO "ip6_tunnel close: can't deregister ip6ip6\n");

	unregister_pernet_device(&ip6_tnl_net_ops);
}

module_init(ip6_tunnel_init);
module_exit(ip6_tunnel_cleanup);