summaryrefslogtreecommitdiff
path: root/net/ipv4/ip_gre.c
blob: 10e9b5aea07030c47f7f1dd880013b47685231ac (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
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
/*
 *	Linux NET3:	GRE over IP protocol decoder.
 *
 *	Authors: Alexey Kuznetsov (kuznet@ms2.inr.ac.ru)
 *
 *	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/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <asm/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 <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ipip.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/gre.h>

#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#endif

/*
   Problems & solutions
   --------------------

   1. The most important issue is detecting local dead loops.
   They would cause complete host lockup in transmit, which
   would be "resolved" by stack overflow or, if queueing is enabled,
   with infinite looping in net_bh.

   We cannot track such dead loops during route installation,
   it is infeasible task. The most general solutions would be
   to keep skb->encapsulation counter (sort of local ttl),
   and silently drop packet when it expires. It is a good
   solution, but it supposes maintaing new variable in ALL
   skb, even if no tunneling is used.

   Current solution: xmit_recursion breaks dead loops. This is a percpu
   counter, since when we enter the first ndo_xmit(), cpu migration is
   forbidden. We force an exit if this counter reaches RECURSION_LIMIT

   2. Networking dead loops would not kill routers, but would really
   kill network. IP hop limit plays role of "t->recursion" in this case,
   if we copy it from packet being encapsulated to upper header.
   It is very good solution, but it introduces two problems:

   - Routing protocols, using packets with ttl=1 (OSPF, RIP2),
     do not work over tunnels.
   - traceroute does not work. I planned to relay ICMP from tunnel,
     so that this problem would be solved and traceroute output
     would even more informative. This idea appeared to be wrong:
     only Linux complies to rfc1812 now (yes, guys, Linux is the only
     true router now :-)), all routers (at least, in neighbourhood of mine)
     return only 8 bytes of payload. It is the end.

   Hence, if we want that OSPF worked or traceroute said something reasonable,
   we should search for another solution.

   One of them is to parse packet trying to detect inner encapsulation
   made by our node. It is difficult or even impossible, especially,
   taking into account fragmentation. TO be short, tt is not solution at all.

   Current solution: The solution was UNEXPECTEDLY SIMPLE.
   We force DF flag on tunnels with preconfigured hop limit,
   that is ALL. :-) Well, it does not remove the problem completely,
   but exponential growth of network traffic is changed to linear
   (branches, that exceed pmtu are pruned) and tunnel mtu
   fastly degrades to value <68, where looping stops.
   Yes, it is not good if there exists a router in the loop,
   which does not force DF, even when encapsulating packets have DF set.
   But it is not our problem! Nobody could accuse us, we made
   all that we could make. Even if it is your gated who injected
   fatal route to network, even if it were you who configured
   fatal static route: you are innocent. :-)



   3. Really, ipv4/ipip.c, ipv4/ip_gre.c and ipv6/sit.c contain
   practically identical code. It would be good to glue them
   together, but it is not very evident, how to make them modular.
   sit is integral part of IPv6, ipip and gre are naturally modular.
   We could extract common parts (hash table, ioctl etc)
   to a separate module (ip_tunnel.c).

   Alexey Kuznetsov.
 */

static struct rtnl_link_ops ipgre_link_ops __read_mostly;
static int ipgre_tunnel_init(struct net_device *dev);
static void ipgre_tunnel_setup(struct net_device *dev);
static int ipgre_tunnel_bind_dev(struct net_device *dev);

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

#define HASH_SIZE  16

static int ipgre_net_id __read_mostly;
struct ipgre_net {
	struct ip_tunnel __rcu *tunnels[4][HASH_SIZE];

	struct net_device *fb_tunnel_dev;
};

/* Tunnel hash table */

/*
   4 hash tables:

   3: (remote,local)
   2: (remote,*)
   1: (*,local)
   0: (*,*)

   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.
 */

#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)

#define tunnels_r_l	tunnels[3]
#define tunnels_r	tunnels[2]
#define tunnels_l	tunnels[1]
#define tunnels_wc	tunnels[0]
/*
 * Locking : hash tables are protected by RCU and RTNL
 */

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

/* 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 *ipgre_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;
}

/* Given src, dst and key, find appropriate for input tunnel. */

static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
					      __be32 remote, __be32 local,
					      __be32 key, __be16 gre_proto)
{
	struct net *net = dev_net(dev);
	int link = dev->ifindex;
	unsigned int h0 = HASH(remote);
	unsigned int h1 = HASH(key);
	struct ip_tunnel *t, *cand = NULL;
	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
	int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
		       ARPHRD_ETHER : ARPHRD_IPGRE;
	int score, cand_score = 4;

	for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) {
		if (local != t->parms.iph.saddr ||
		    remote != t->parms.iph.daddr ||
		    key != t->parms.i_key ||
		    !(t->dev->flags & IFF_UP))
			continue;

		if (t->dev->type != ARPHRD_IPGRE &&
		    t->dev->type != dev_type)
			continue;

		score = 0;
		if (t->parms.link != link)
			score |= 1;
		if (t->dev->type != dev_type)
			score |= 2;
		if (score == 0)
			return t;

		if (score < cand_score) {
			cand = t;
			cand_score = score;
		}
	}

	for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) {
		if (remote != t->parms.iph.daddr ||
		    key != t->parms.i_key ||
		    !(t->dev->flags & IFF_UP))
			continue;

		if (t->dev->type != ARPHRD_IPGRE &&
		    t->dev->type != dev_type)
			continue;

		score = 0;
		if (t->parms.link != link)
			score |= 1;
		if (t->dev->type != dev_type)
			score |= 2;
		if (score == 0)
			return t;

		if (score < cand_score) {
			cand = t;
			cand_score = score;
		}
	}

	for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) {
		if ((local != t->parms.iph.saddr &&
		     (local != t->parms.iph.daddr ||
		      !ipv4_is_multicast(local))) ||
		    key != t->parms.i_key ||
		    !(t->dev->flags & IFF_UP))
			continue;

		if (t->dev->type != ARPHRD_IPGRE &&
		    t->dev->type != dev_type)
			continue;

		score = 0;
		if (t->parms.link != link)
			score |= 1;
		if (t->dev->type != dev_type)
			score |= 2;
		if (score == 0)
			return t;

		if (score < cand_score) {
			cand = t;
			cand_score = score;
		}
	}

	for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) {
		if (t->parms.i_key != key ||
		    !(t->dev->flags & IFF_UP))
			continue;

		if (t->dev->type != ARPHRD_IPGRE &&
		    t->dev->type != dev_type)
			continue;

		score = 0;
		if (t->parms.link != link)
			score |= 1;
		if (t->dev->type != dev_type)
			score |= 2;
		if (score == 0)
			return t;

		if (score < cand_score) {
			cand = t;
			cand_score = score;
		}
	}

	if (cand != NULL)
		return cand;

	dev = ign->fb_tunnel_dev;
	if (dev->flags & IFF_UP)
		return netdev_priv(dev);

	return NULL;
}

static struct ip_tunnel __rcu **__ipgre_bucket(struct ipgre_net *ign,
		struct ip_tunnel_parm *parms)
{
	__be32 remote = parms->iph.daddr;
	__be32 local = parms->iph.saddr;
	__be32 key = parms->i_key;
	unsigned int h = HASH(key);
	int prio = 0;

	if (local)
		prio |= 1;
	if (remote && !ipv4_is_multicast(remote)) {
		prio |= 2;
		h ^= HASH(remote);
	}

	return &ign->tunnels[prio][h];
}

static inline struct ip_tunnel __rcu **ipgre_bucket(struct ipgre_net *ign,
		struct ip_tunnel *t)
{
	return __ipgre_bucket(ign, &t->parms);
}

static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t)
{
	struct ip_tunnel __rcu **tp = ipgre_bucket(ign, t);

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

static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
{
	struct ip_tunnel __rcu **tp;
	struct ip_tunnel *iter;

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

static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
					   struct ip_tunnel_parm *parms,
					   int type)
{
	__be32 remote = parms->iph.daddr;
	__be32 local = parms->iph.saddr;
	__be32 key = parms->i_key;
	int link = parms->link;
	struct ip_tunnel *t;
	struct ip_tunnel __rcu **tp;
	struct ipgre_net *ign = net_generic(net, ipgre_net_id);

	for (tp = __ipgre_bucket(ign, parms);
	     (t = rtnl_dereference(*tp)) != NULL;
	     tp = &t->next)
		if (local == t->parms.iph.saddr &&
		    remote == t->parms.iph.daddr &&
		    key == t->parms.i_key &&
		    link == t->parms.link &&
		    type == t->dev->type)
			break;

	return t;
}

static struct ip_tunnel *ipgre_tunnel_locate(struct net *net,
		struct ip_tunnel_parm *parms, int create)
{
	struct ip_tunnel *t, *nt;
	struct net_device *dev;
	char name[IFNAMSIZ];
	struct ipgre_net *ign = net_generic(net, ipgre_net_id);

	t = ipgre_tunnel_find(net, parms, ARPHRD_IPGRE);
	if (t || !create)
		return t;

	if (parms->name[0])
		strlcpy(name, parms->name, IFNAMSIZ);
	else
		strcpy(name, "gre%d");

	dev = alloc_netdev(sizeof(*t), name, ipgre_tunnel_setup);
	if (!dev)
		return NULL;

	dev_net_set(dev, net);

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

	nt = netdev_priv(dev);
	nt->parms = *parms;
	dev->rtnl_link_ops = &ipgre_link_ops;

	dev->mtu = ipgre_tunnel_bind_dev(dev);

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

	dev_hold(dev);
	ipgre_tunnel_link(ign, nt);
	return nt;

failed_free:
	free_netdev(dev);
	return NULL;
}

static void ipgre_tunnel_uninit(struct net_device *dev)
{
	struct net *net = dev_net(dev);
	struct ipgre_net *ign = net_generic(net, ipgre_net_id);

	ipgre_tunnel_unlink(ign, netdev_priv(dev));
	dev_put(dev);
}


static void ipgre_err(struct sk_buff *skb, u32 info)
{

/* All the routers (except for Linux) return only
   8 bytes of packet payload. It means, that precise relaying of
   ICMP in the real Internet is absolutely infeasible.

   Moreover, Cisco "wise men" put GRE key to the third word
   in GRE header. It makes impossible maintaining even soft state for keyed
   GRE tunnels with enabled checksum. Tell them "thank you".

   Well, I wonder, rfc1812 was written by Cisco employee,
   what the hell these idiots break standrads established
   by themself???
 */

	const struct iphdr *iph = (const struct iphdr *)skb->data;
	__be16	     *p = (__be16*)(skb->data+(iph->ihl<<2));
	int grehlen = (iph->ihl<<2) + 4;
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;
	struct ip_tunnel *t;
	__be16 flags;

	flags = p[0];
	if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
		if (flags&(GRE_VERSION|GRE_ROUTING))
			return;
		if (flags&GRE_KEY) {
			grehlen += 4;
			if (flags&GRE_CSUM)
				grehlen += 4;
		}
	}

	/* If only 8 bytes returned, keyed message will be dropped here */
	if (skb_headlen(skb) < grehlen)
		return;

	switch (type) {
	default:
	case ICMP_PARAMETERPROB:
		return;

	case ICMP_DEST_UNREACH:
		switch (code) {
		case ICMP_SR_FAILED:
		case ICMP_PORT_UNREACH:
			/* Impossible event. */
			return;
		case ICMP_FRAG_NEEDED:
			/* Soft state for pmtu is maintained by IP core. */
			return;
		default:
			/* All others are translated to HOST_UNREACH.
			   rfc2003 contains "deep thoughts" about NET_UNREACH,
			   I believe they are just ether pollution. --ANK
			 */
			break;
		}
		break;
	case ICMP_TIME_EXCEEDED:
		if (code != ICMP_EXC_TTL)
			return;
		break;
	}

	rcu_read_lock();
	t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
				flags & GRE_KEY ?
				*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
				p[1]);
	if (t == NULL || t->parms.iph.daddr == 0 ||
	    ipv4_is_multicast(t->parms.iph.daddr))
		goto out;

	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
		goto out;

	if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
		t->err_count++;
	else
		t->err_count = 1;
	t->err_time = jiffies;
out:
	rcu_read_unlock();
}

static inline void ipgre_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb)
{
	if (INET_ECN_is_ce(iph->tos)) {
		if (skb->protocol == htons(ETH_P_IP)) {
			IP_ECN_set_ce(ip_hdr(skb));
		} else if (skb->protocol == htons(ETH_P_IPV6)) {
			IP6_ECN_set_ce(ipv6_hdr(skb));
		}
	}
}

static inline u8
ipgre_ecn_encapsulate(u8 tos, const struct iphdr *old_iph, struct sk_buff *skb)
{
	u8 inner = 0;
	if (skb->protocol == htons(ETH_P_IP))
		inner = old_iph->tos;
	else if (skb->protocol == htons(ETH_P_IPV6))
		inner = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
	return INET_ECN_encapsulate(tos, inner);
}

static int ipgre_rcv(struct sk_buff *skb)
{
	const struct iphdr *iph;
	u8     *h;
	__be16    flags;
	__sum16   csum = 0;
	__be32 key = 0;
	u32    seqno = 0;
	struct ip_tunnel *tunnel;
	int    offset = 4;
	__be16 gre_proto;

	if (!pskb_may_pull(skb, 16))
		goto drop_nolock;

	iph = ip_hdr(skb);
	h = skb->data;
	flags = *(__be16*)h;

	if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
		/* - Version must be 0.
		   - We do not support routing headers.
		 */
		if (flags&(GRE_VERSION|GRE_ROUTING))
			goto drop_nolock;

		if (flags&GRE_CSUM) {
			switch (skb->ip_summed) {
			case CHECKSUM_COMPLETE:
				csum = csum_fold(skb->csum);
				if (!csum)
					break;
				/* fall through */
			case CHECKSUM_NONE:
				skb->csum = 0;
				csum = __skb_checksum_complete(skb);
				skb->ip_summed = CHECKSUM_COMPLETE;
			}
			offset += 4;
		}
		if (flags&GRE_KEY) {
			key = *(__be32*)(h + offset);
			offset += 4;
		}
		if (flags&GRE_SEQ) {
			seqno = ntohl(*(__be32*)(h + offset));
			offset += 4;
		}
	}

	gre_proto = *(__be16 *)(h + 2);

	rcu_read_lock();
	if ((tunnel = ipgre_tunnel_lookup(skb->dev,
					  iph->saddr, iph->daddr, key,
					  gre_proto))) {
		struct pcpu_tstats *tstats;

		secpath_reset(skb);

		skb->protocol = gre_proto;
		/* WCCP version 1 and 2 protocol decoding.
		 * - Change protocol to IP
		 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
		 */
		if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
			skb->protocol = htons(ETH_P_IP);
			if ((*(h + offset) & 0xF0) != 0x40)
				offset += 4;
		}

		skb->mac_header = skb->network_header;
		__pskb_pull(skb, offset);
		skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
		skb->pkt_type = PACKET_HOST;
#ifdef CONFIG_NET_IPGRE_BROADCAST
		if (ipv4_is_multicast(iph->daddr)) {
			/* Looped back packet, drop it! */
			if (rt_is_output_route(skb_rtable(skb)))
				goto drop;
			tunnel->dev->stats.multicast++;
			skb->pkt_type = PACKET_BROADCAST;
		}
#endif

		if (((flags&GRE_CSUM) && csum) ||
		    (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
			tunnel->dev->stats.rx_crc_errors++;
			tunnel->dev->stats.rx_errors++;
			goto drop;
		}
		if (tunnel->parms.i_flags&GRE_SEQ) {
			if (!(flags&GRE_SEQ) ||
			    (tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
				tunnel->dev->stats.rx_fifo_errors++;
				tunnel->dev->stats.rx_errors++;
				goto drop;
			}
			tunnel->i_seqno = seqno + 1;
		}

		/* Warning: All skb pointers will be invalidated! */
		if (tunnel->dev->type == ARPHRD_ETHER) {
			if (!pskb_may_pull(skb, ETH_HLEN)) {
				tunnel->dev->stats.rx_length_errors++;
				tunnel->dev->stats.rx_errors++;
				goto drop;
			}

			iph = ip_hdr(skb);
			skb->protocol = eth_type_trans(skb, tunnel->dev);
			skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
		}

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

		__skb_tunnel_rx(skb, tunnel->dev);

		skb_reset_network_header(skb);
		ipgre_ecn_decapsulate(iph, skb);

		netif_rx(skb);

		rcu_read_unlock();
		return 0;
	}
	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);

drop:
	rcu_read_unlock();
drop_nolock:
	kfree_skb(skb);
	return 0;
}

static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct pcpu_tstats *tstats;
	const struct iphdr  *old_iph = ip_hdr(skb);
	const struct iphdr  *tiph;
	struct flowi4 fl4;
	u8     tos;
	__be16 df;
	struct rtable *rt;     			/* Route to the other host */
	struct net_device *tdev;		/* Device to other host */
	struct iphdr  *iph;			/* Our new IP header */
	unsigned int max_headroom;		/* The extra header space needed */
	int    gre_hlen;
	__be32 dst;
	int    mtu;

	if (dev->type == ARPHRD_ETHER)
		IPCB(skb)->flags = 0;

	if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
		gre_hlen = 0;
		tiph = (const struct iphdr *)skb->data;
	} else {
		gre_hlen = tunnel->hlen;
		tiph = &tunnel->parms.iph;
	}

	if ((dst = tiph->daddr) == 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);
			if ((dst = rt->rt_gateway) == 0)
				goto tx_error_icmp;
		}
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
		else if (skb->protocol == htons(ETH_P_IPV6)) {
			const struct in6_addr *addr6;
			int addr_type;
			struct neighbour *neigh = skb_dst(skb)->neighbour;

			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)
				goto tx_error_icmp;

			dst = addr6->s6_addr32[3];
		}
#endif
		else
			goto tx_error;
	}

	tos = tiph->tos;
	if (tos == 1) {
		tos = 0;
		if (skb->protocol == htons(ETH_P_IP))
			tos = old_iph->tos;
		else if (skb->protocol == htons(ETH_P_IPV6))
			tos = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
	}

	rt = ip_route_output_gre(dev_net(dev), &fl4, dst, tiph->saddr,
				 tunnel->parms.o_key, RT_TOS(tos),
				 tunnel->parms.link);
	if (IS_ERR(rt)) {
		dev->stats.tx_carrier_errors++;
		goto tx_error;
	}
	tdev = rt->dst.dev;

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

	df = tiph->frag_off;
	if (df)
		mtu = dst_mtu(&rt->dst) - dev->hard_header_len - 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), mtu);

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

		if ((old_iph->frag_off&htons(IP_DF)) &&
		    mtu < ntohs(old_iph->tot_len)) {
			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
			ip_rt_put(rt);
			goto tx_error;
		}
	}
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
	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 (mtu >= IPV6_MIN_MTU && mtu < skb->len - tunnel->hlen + gre_hlen) {
			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
			ip_rt_put(rt);
			goto tx_error;
		}
	}
#endif

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

			dst_link_failure(skb);
		} else
			tunnel->err_count = 0;
	}

	max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->dst.header_len;

	if (skb_headroom(skb) < max_headroom || skb_shared(skb)||
	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
		if (max_headroom > dev->needed_headroom)
			dev->needed_headroom = max_headroom;
		if (!new_skb) {
			ip_rt_put(rt);
			dev->stats.tx_dropped++;
			dev_kfree_skb(skb);
			return NETDEV_TX_OK;
		}
		if (skb->sk)
			skb_set_owner_w(new_skb, skb->sk);
		dev_kfree_skb(skb);
		skb = new_skb;
		old_iph = ip_hdr(skb);
	}

	skb_reset_transport_header(skb);
	skb_push(skb, gre_hlen);
	skb_reset_network_header(skb);
	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
			      IPSKB_REROUTED);
	skb_dst_drop(skb);
	skb_dst_set(skb, &rt->dst);

	/*
	 *	Push down and install the IPIP header.
	 */

	iph 			=	ip_hdr(skb);
	iph->version		=	4;
	iph->ihl		=	sizeof(struct iphdr) >> 2;
	iph->frag_off		=	df;
	iph->protocol		=	IPPROTO_GRE;
	iph->tos		=	ipgre_ecn_encapsulate(tos, old_iph, skb);
	iph->daddr		=	fl4.daddr;
	iph->saddr		=	fl4.saddr;

	if ((iph->ttl = tiph->ttl) == 0) {
		if (skb->protocol == htons(ETH_P_IP))
			iph->ttl = old_iph->ttl;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
		else if (skb->protocol == htons(ETH_P_IPV6))
			iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit;
#endif
		else
			iph->ttl = ip4_dst_hoplimit(&rt->dst);
	}

	((__be16 *)(iph + 1))[0] = tunnel->parms.o_flags;
	((__be16 *)(iph + 1))[1] = (dev->type == ARPHRD_ETHER) ?
				   htons(ETH_P_TEB) : skb->protocol;

	if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) {
		__be32 *ptr = (__be32*)(((u8*)iph) + tunnel->hlen - 4);

		if (tunnel->parms.o_flags&GRE_SEQ) {
			++tunnel->o_seqno;
			*ptr = htonl(tunnel->o_seqno);
			ptr--;
		}
		if (tunnel->parms.o_flags&GRE_KEY) {
			*ptr = tunnel->parms.o_key;
			ptr--;
		}
		if (tunnel->parms.o_flags&GRE_CSUM) {
			*ptr = 0;
			*(__sum16*)ptr = ip_compute_csum((void*)(iph+1), skb->len - sizeof(struct iphdr));
		}
	}

	nf_reset(skb);
	tstats = this_cpu_ptr(dev->tstats);
	__IPTUNNEL_XMIT(tstats, &dev->stats);
	return NETDEV_TX_OK;

tx_error_icmp:
	dst_link_failure(skb);

tx_error:
	dev->stats.tx_errors++;
	dev_kfree_skb(skb);
	return NETDEV_TX_OK;
}

static int ipgre_tunnel_bind_dev(struct net_device *dev)
{
	struct net_device *tdev = NULL;
	struct ip_tunnel *tunnel;
	const struct iphdr *iph;
	int hlen = LL_MAX_HEADER;
	int mtu = ETH_DATA_LEN;
	int addend = sizeof(struct iphdr) + 4;

	tunnel = netdev_priv(dev);
	iph = &tunnel->parms.iph;

	/* Guess output device to choose reasonable mtu and needed_headroom */

	if (iph->daddr) {
		struct flowi4 fl4;
		struct rtable *rt;

		rt = ip_route_output_gre(dev_net(dev), &fl4,
					 iph->daddr, iph->saddr,
					 tunnel->parms.o_key,
					 RT_TOS(iph->tos),
					 tunnel->parms.link);
		if (!IS_ERR(rt)) {
			tdev = rt->dst.dev;
			ip_rt_put(rt);
		}

		if (dev->type != ARPHRD_ETHER)
			dev->flags |= IFF_POINTOPOINT;
	}

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

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

	/* Precalculate GRE options length */
	if (tunnel->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
		if (tunnel->parms.o_flags&GRE_CSUM)
			addend += 4;
		if (tunnel->parms.o_flags&GRE_KEY)
			addend += 4;
		if (tunnel->parms.o_flags&GRE_SEQ)
			addend += 4;
	}
	dev->needed_headroom = addend + hlen;
	mtu -= dev->hard_header_len + addend;

	if (mtu < 68)
		mtu = 68;

	tunnel->hlen = addend;

	return mtu;
}

static int
ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
{
	int err = 0;
	struct ip_tunnel_parm p;
	struct ip_tunnel *t;
	struct net *net = dev_net(dev);
	struct ipgre_net *ign = net_generic(net, ipgre_net_id);

	switch (cmd) {
	case SIOCGETTUNNEL:
		t = NULL;
		if (dev == ign->fb_tunnel_dev) {
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
				err = -EFAULT;
				break;
			}
			t = ipgre_tunnel_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))
			goto done;

		err = -EFAULT;
		if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
			goto done;

		err = -EINVAL;
		if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
		    ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)))
			goto done;
		if (p.iph.ttl)
			p.iph.frag_off |= htons(IP_DF);

		if (!(p.i_flags&GRE_KEY))
			p.i_key = 0;
		if (!(p.o_flags&GRE_KEY))
			p.o_key = 0;

		t = ipgre_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);

		if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
			if (t != NULL) {
				if (t->dev != dev) {
					err = -EEXIST;
					break;
				}
			} else {
				unsigned int nflags = 0;

				t = netdev_priv(dev);

				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;
				}
				ipgre_tunnel_unlink(ign, t);
				synchronize_net();
				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;
				memcpy(dev->dev_addr, &p.iph.saddr, 4);
				memcpy(dev->broadcast, &p.iph.daddr, 4);
				ipgre_tunnel_link(ign, t);
				netdev_state_change(dev);
			}
		}

		if (t) {
			err = 0;
			if (cmd == SIOCCHGTUNNEL) {
				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) {
					t->parms.link = p.link;
					dev->mtu = ipgre_tunnel_bind_dev(dev);
					netdev_state_change(dev);
				}
			}
			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))
			goto done;

		if (dev == ign->fb_tunnel_dev) {
			err = -EFAULT;
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
				goto done;
			err = -ENOENT;
			if ((t = ipgre_tunnel_locate(net, &p, 0)) == NULL)
				goto done;
			err = -EPERM;
			if (t == netdev_priv(ign->fb_tunnel_dev))
				goto done;
			dev = t->dev;
		}
		unregister_netdevice(dev);
		err = 0;
		break;

	default:
		err = -EINVAL;
	}

done:
	return err;
}

static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	if (new_mtu < 68 ||
	    new_mtu > 0xFFF8 - dev->hard_header_len - tunnel->hlen)
		return -EINVAL;
	dev->mtu = new_mtu;
	return 0;
}

/* Nice toy. Unfortunately, useless in real life :-)
   It allows to construct virtual multiprotocol broadcast "LAN"
   over the Internet, provided multicast routing is tuned.


   I have no idea was this bicycle invented before me,
   so that I had to set ARPHRD_IPGRE to a random value.
   I have an impression, that Cisco could make something similar,
   but this feature is apparently missing in IOS<=11.2(8).

   I set up 10.66.66/24 and fec0:6666:6666::0/96 as virtual networks
   with broadcast 224.66.66.66. If you have access to mbone, play with me :-)

   ping -t 255 224.66.66.66

   If nobody answers, mbone does not work.

   ip tunnel add Universe mode gre remote 224.66.66.66 local <Your_real_addr> ttl 255
   ip addr add 10.66.66.<somewhat>/24 dev Universe
   ifconfig Universe up
   ifconfig Universe add fe80::<Your_real_addr>/10
   ifconfig Universe add fec0:6666:6666::<Your_real_addr>/96
   ftp 10.66.66.66
   ...
   ftp fec0:6666:6666::193.233.7.65
   ...

 */

static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
			unsigned short type,
			const void *daddr, const void *saddr, unsigned int len)
{
	struct ip_tunnel *t = netdev_priv(dev);
	struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen);
	__be16 *p = (__be16*)(iph+1);

	memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
	p[0]		= t->parms.o_flags;
	p[1]		= htons(type);

	/*
	 *	Set the source hardware address.
	 */

	if (saddr)
		memcpy(&iph->saddr, saddr, 4);
	if (daddr)
		memcpy(&iph->daddr, daddr, 4);
	if (iph->daddr)
		return t->hlen;

	return -t->hlen;
}

static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
{
	const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb);
	memcpy(haddr, &iph->saddr, 4);
	return 4;
}

static const struct header_ops ipgre_header_ops = {
	.create	= ipgre_header,
	.parse	= ipgre_header_parse,
};

#ifdef CONFIG_NET_IPGRE_BROADCAST
static int ipgre_open(struct net_device *dev)
{
	struct ip_tunnel *t = netdev_priv(dev);

	if (ipv4_is_multicast(t->parms.iph.daddr)) {
		struct flowi4 fl4;
		struct rtable *rt;

		rt = ip_route_output_gre(dev_net(dev), &fl4,
					 t->parms.iph.daddr,
					 t->parms.iph.saddr,
					 t->parms.o_key,
					 RT_TOS(t->parms.iph.tos),
					 t->parms.link);
		if (IS_ERR(rt))
			return -EADDRNOTAVAIL;
		dev = rt->dst.dev;
		ip_rt_put(rt);
		if (__in_dev_get_rtnl(dev) == NULL)
			return -EADDRNOTAVAIL;
		t->mlink = dev->ifindex;
		ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr);
	}
	return 0;
}

static int ipgre_close(struct net_device *dev)
{
	struct ip_tunnel *t = netdev_priv(dev);

	if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) {
		struct in_device *in_dev;
		in_dev = inetdev_by_index(dev_net(dev), t->mlink);
		if (in_dev)
			ip_mc_dec_group(in_dev, t->parms.iph.daddr);
	}
	return 0;
}

#endif

static const struct net_device_ops ipgre_netdev_ops = {
	.ndo_init		= ipgre_tunnel_init,
	.ndo_uninit		= ipgre_tunnel_uninit,
#ifdef CONFIG_NET_IPGRE_BROADCAST
	.ndo_open		= ipgre_open,
	.ndo_stop		= ipgre_close,
#endif
	.ndo_start_xmit		= ipgre_tunnel_xmit,
	.ndo_do_ioctl		= ipgre_tunnel_ioctl,
	.ndo_change_mtu		= ipgre_tunnel_change_mtu,
	.ndo_get_stats		= ipgre_get_stats,
};

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

static void ipgre_tunnel_setup(struct net_device *dev)
{
	dev->netdev_ops		= &ipgre_netdev_ops;
	dev->destructor 	= ipgre_dev_free;

	dev->type		= ARPHRD_IPGRE;
	dev->needed_headroom 	= LL_MAX_HEADER + sizeof(struct iphdr) + 4;
	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr) - 4;
	dev->flags		= IFF_NOARP;
	dev->iflink		= 0;
	dev->addr_len		= 4;
	dev->features		|= NETIF_F_NETNS_LOCAL;
	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
}

static int ipgre_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel;
	struct iphdr *iph;

	tunnel = netdev_priv(dev);
	iph = &tunnel->parms.iph;

	tunnel->dev = dev;
	strcpy(tunnel->parms.name, dev->name);

	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);

	if (iph->daddr) {
#ifdef CONFIG_NET_IPGRE_BROADCAST
		if (ipv4_is_multicast(iph->daddr)) {
			if (!iph->saddr)
				return -EINVAL;
			dev->flags = IFF_BROADCAST;
			dev->header_ops = &ipgre_header_ops;
		}
#endif
	} else
		dev->header_ops = &ipgre_header_ops;

	dev->tstats = alloc_percpu(struct pcpu_tstats);
	if (!dev->tstats)
		return -ENOMEM;

	return 0;
}

static void ipgre_fb_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct iphdr *iph = &tunnel->parms.iph;

	tunnel->dev = dev;
	strcpy(tunnel->parms.name, dev->name);

	iph->version		= 4;
	iph->protocol		= IPPROTO_GRE;
	iph->ihl		= 5;
	tunnel->hlen		= sizeof(struct iphdr) + 4;

	dev_hold(dev);
}


static const struct gre_protocol ipgre_protocol = {
	.handler     = ipgre_rcv,
	.err_handler = ipgre_err,
};

static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
{
	int prio;

	for (prio = 0; prio < 4; prio++) {
		int h;
		for (h = 0; h < HASH_SIZE; h++) {
			struct ip_tunnel *t;

			t = rtnl_dereference(ign->tunnels[prio][h]);

			while (t != NULL) {
				unregister_netdevice_queue(t->dev, head);
				t = rtnl_dereference(t->next);
			}
		}
	}
}

static int __net_init ipgre_init_net(struct net *net)
{
	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
	int err;

	ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0",
					   ipgre_tunnel_setup);
	if (!ign->fb_tunnel_dev) {
		err = -ENOMEM;
		goto err_alloc_dev;
	}
	dev_net_set(ign->fb_tunnel_dev, net);

	ipgre_fb_tunnel_init(ign->fb_tunnel_dev);
	ign->fb_tunnel_dev->rtnl_link_ops = &ipgre_link_ops;

	if ((err = register_netdev(ign->fb_tunnel_dev)))
		goto err_reg_dev;

	rcu_assign_pointer(ign->tunnels_wc[0],
			   netdev_priv(ign->fb_tunnel_dev));
	return 0;

err_reg_dev:
	ipgre_dev_free(ign->fb_tunnel_dev);
err_alloc_dev:
	return err;
}

static void __net_exit ipgre_exit_net(struct net *net)
{
	struct ipgre_net *ign;
	LIST_HEAD(list);

	ign = net_generic(net, ipgre_net_id);
	rtnl_lock();
	ipgre_destroy_tunnels(ign, &list);
	unregister_netdevice_many(&list);
	rtnl_unlock();
}

static struct pernet_operations ipgre_net_ops = {
	.init = ipgre_init_net,
	.exit = ipgre_exit_net,
	.id   = &ipgre_net_id,
	.size = sizeof(struct ipgre_net),
};

static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
{
	__be16 flags;

	if (!data)
		return 0;

	flags = 0;
	if (data[IFLA_GRE_IFLAGS])
		flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]);
	if (data[IFLA_GRE_OFLAGS])
		flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]);
	if (flags & (GRE_VERSION|GRE_ROUTING))
		return -EINVAL;

	return 0;
}

static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[])
{
	__be32 daddr;

	if (tb[IFLA_ADDRESS]) {
		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
			return -EINVAL;
		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
			return -EADDRNOTAVAIL;
	}

	if (!data)
		goto out;

	if (data[IFLA_GRE_REMOTE]) {
		memcpy(&daddr, nla_data(data[IFLA_GRE_REMOTE]), 4);
		if (!daddr)
			return -EINVAL;
	}

out:
	return ipgre_tunnel_validate(tb, data);
}

static void ipgre_netlink_parms(struct nlattr *data[],
				struct ip_tunnel_parm *parms)
{
	memset(parms, 0, sizeof(*parms));

	parms->iph.protocol = IPPROTO_GRE;

	if (!data)
		return;

	if (data[IFLA_GRE_LINK])
		parms->link = nla_get_u32(data[IFLA_GRE_LINK]);

	if (data[IFLA_GRE_IFLAGS])
		parms->i_flags = nla_get_be16(data[IFLA_GRE_IFLAGS]);

	if (data[IFLA_GRE_OFLAGS])
		parms->o_flags = nla_get_be16(data[IFLA_GRE_OFLAGS]);

	if (data[IFLA_GRE_IKEY])
		parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]);

	if (data[IFLA_GRE_OKEY])
		parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]);

	if (data[IFLA_GRE_LOCAL])
		parms->iph.saddr = nla_get_be32(data[IFLA_GRE_LOCAL]);

	if (data[IFLA_GRE_REMOTE])
		parms->iph.daddr = nla_get_be32(data[IFLA_GRE_REMOTE]);

	if (data[IFLA_GRE_TTL])
		parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]);

	if (data[IFLA_GRE_TOS])
		parms->iph.tos = nla_get_u8(data[IFLA_GRE_TOS]);

	if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC]))
		parms->iph.frag_off = htons(IP_DF);
}

static int ipgre_tap_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel;

	tunnel = netdev_priv(dev);

	tunnel->dev = dev;
	strcpy(tunnel->parms.name, dev->name);

	ipgre_tunnel_bind_dev(dev);

	dev->tstats = alloc_percpu(struct pcpu_tstats);
	if (!dev->tstats)
		return -ENOMEM;

	return 0;
}

static const struct net_device_ops ipgre_tap_netdev_ops = {
	.ndo_init		= ipgre_tap_init,
	.ndo_uninit		= ipgre_tunnel_uninit,
	.ndo_start_xmit		= ipgre_tunnel_xmit,
	.ndo_set_mac_address 	= eth_mac_addr,
	.ndo_validate_addr	= eth_validate_addr,
	.ndo_change_mtu		= ipgre_tunnel_change_mtu,
	.ndo_get_stats		= ipgre_get_stats,
};

static void ipgre_tap_setup(struct net_device *dev)
{

	ether_setup(dev);

	dev->netdev_ops		= &ipgre_tap_netdev_ops;
	dev->destructor 	= ipgre_dev_free;

	dev->iflink		= 0;
	dev->features		|= NETIF_F_NETNS_LOCAL;
}

static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[],
			 struct nlattr *data[])
{
	struct ip_tunnel *nt;
	struct net *net = dev_net(dev);
	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
	int mtu;
	int err;

	nt = netdev_priv(dev);
	ipgre_netlink_parms(data, &nt->parms);

	if (ipgre_tunnel_find(net, &nt->parms, dev->type))
		return -EEXIST;

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

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

	/* Can use a lockless transmit, unless we generate output sequences */
	if (!(nt->parms.o_flags & GRE_SEQ))
		dev->features |= NETIF_F_LLTX;

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

	dev_hold(dev);
	ipgre_tunnel_link(ign, nt);

out:
	return err;
}

static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
			    struct nlattr *data[])
{
	struct ip_tunnel *t, *nt;
	struct net *net = dev_net(dev);
	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
	struct ip_tunnel_parm p;
	int mtu;

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

	nt = netdev_priv(dev);
	ipgre_netlink_parms(data, &p);

	t = ipgre_tunnel_locate(net, &p, 0);

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

		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;
		}

		ipgre_tunnel_unlink(ign, t);
		t->parms.iph.saddr = p.iph.saddr;
		t->parms.iph.daddr = p.iph.daddr;
		t->parms.i_key = p.i_key;
		if (dev->type != ARPHRD_ETHER) {
			memcpy(dev->dev_addr, &p.iph.saddr, 4);
			memcpy(dev->broadcast, &p.iph.daddr, 4);
		}
		ipgre_tunnel_link(ign, t);
		netdev_state_change(dev);
	}

	t->parms.o_key = p.o_key;
	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) {
		t->parms.link = p.link;
		mtu = ipgre_tunnel_bind_dev(dev);
		if (!tb[IFLA_MTU])
			dev->mtu = mtu;
		netdev_state_change(dev);
	}

	return 0;
}

static size_t ipgre_get_size(const struct net_device *dev)
{
	return
		/* IFLA_GRE_LINK */
		nla_total_size(4) +
		/* IFLA_GRE_IFLAGS */
		nla_total_size(2) +
		/* IFLA_GRE_OFLAGS */
		nla_total_size(2) +
		/* IFLA_GRE_IKEY */
		nla_total_size(4) +
		/* IFLA_GRE_OKEY */
		nla_total_size(4) +
		/* IFLA_GRE_LOCAL */
		nla_total_size(4) +
		/* IFLA_GRE_REMOTE */
		nla_total_size(4) +
		/* IFLA_GRE_TTL */
		nla_total_size(1) +
		/* IFLA_GRE_TOS */
		nla_total_size(1) +
		/* IFLA_GRE_PMTUDISC */
		nla_total_size(1) +
		0;
}

static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
	struct ip_tunnel *t = netdev_priv(dev);
	struct ip_tunnel_parm *p = &t->parms;

	NLA_PUT_U32(skb, IFLA_GRE_LINK, p->link);
	NLA_PUT_BE16(skb, IFLA_GRE_IFLAGS, p->i_flags);
	NLA_PUT_BE16(skb, IFLA_GRE_OFLAGS, p->o_flags);
	NLA_PUT_BE32(skb, IFLA_GRE_IKEY, p->i_key);
	NLA_PUT_BE32(skb, IFLA_GRE_OKEY, p->o_key);
	NLA_PUT_BE32(skb, IFLA_GRE_LOCAL, p->iph.saddr);
	NLA_PUT_BE32(skb, IFLA_GRE_REMOTE, p->iph.daddr);
	NLA_PUT_U8(skb, IFLA_GRE_TTL, p->iph.ttl);
	NLA_PUT_U8(skb, IFLA_GRE_TOS, p->iph.tos);
	NLA_PUT_U8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF)));

	return 0;

nla_put_failure:
	return -EMSGSIZE;
}

static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
	[IFLA_GRE_LINK]		= { .type = NLA_U32 },
	[IFLA_GRE_IFLAGS]	= { .type = NLA_U16 },
	[IFLA_GRE_OFLAGS]	= { .type = NLA_U16 },
	[IFLA_GRE_IKEY]		= { .type = NLA_U32 },
	[IFLA_GRE_OKEY]		= { .type = NLA_U32 },
	[IFLA_GRE_LOCAL]	= { .len = FIELD_SIZEOF(struct iphdr, saddr) },
	[IFLA_GRE_REMOTE]	= { .len = FIELD_SIZEOF(struct iphdr, daddr) },
	[IFLA_GRE_TTL]		= { .type = NLA_U8 },
	[IFLA_GRE_TOS]		= { .type = NLA_U8 },
	[IFLA_GRE_PMTUDISC]	= { .type = NLA_U8 },
};

static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
	.kind		= "gre",
	.maxtype	= IFLA_GRE_MAX,
	.policy		= ipgre_policy,
	.priv_size	= sizeof(struct ip_tunnel),
	.setup		= ipgre_tunnel_setup,
	.validate	= ipgre_tunnel_validate,
	.newlink	= ipgre_newlink,
	.changelink	= ipgre_changelink,
	.get_size	= ipgre_get_size,
	.fill_info	= ipgre_fill_info,
};

static struct rtnl_link_ops ipgre_tap_ops __read_mostly = {
	.kind		= "gretap",
	.maxtype	= IFLA_GRE_MAX,
	.policy		= ipgre_policy,
	.priv_size	= sizeof(struct ip_tunnel),
	.setup		= ipgre_tap_setup,
	.validate	= ipgre_tap_validate,
	.newlink	= ipgre_newlink,
	.changelink	= ipgre_changelink,
	.get_size	= ipgre_get_size,
	.fill_info	= ipgre_fill_info,
};

/*
 *	And now the modules code and kernel interface.
 */

static int __init ipgre_init(void)
{
	int err;

	printk(KERN_INFO "GRE over IPv4 tunneling driver\n");

	err = register_pernet_device(&ipgre_net_ops);
	if (err < 0)
		return err;

	err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO);
	if (err < 0) {
		printk(KERN_INFO "ipgre init: can't add protocol\n");
		goto add_proto_failed;
	}

	err = rtnl_link_register(&ipgre_link_ops);
	if (err < 0)
		goto rtnl_link_failed;

	err = rtnl_link_register(&ipgre_tap_ops);
	if (err < 0)
		goto tap_ops_failed;

out:
	return err;

tap_ops_failed:
	rtnl_link_unregister(&ipgre_link_ops);
rtnl_link_failed:
	gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
add_proto_failed:
	unregister_pernet_device(&ipgre_net_ops);
	goto out;
}

static void __exit ipgre_fini(void)
{
	rtnl_link_unregister(&ipgre_tap_ops);
	rtnl_link_unregister(&ipgre_link_ops);
	if (gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0)
		printk(KERN_INFO "ipgre close: can't remove protocol\n");
	unregister_pernet_device(&ipgre_net_ops);
}

module_init(ipgre_init);
module_exit(ipgre_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("gre");
MODULE_ALIAS_RTNL_LINK("gretap");
MODULE_ALIAS_NETDEV("gre0");