summaryrefslogtreecommitdiff
path: root/drivers/net/tun.c
blob: 457f2d7430cf13684f6ac4c5c971530d029d8b46 (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
/*
 *  TUN - Universal TUN/TAP device driver.
 *  Copyright (C) 1999-2002 Maxim Krasnyansky <maxk@qualcomm.com>
 *
 *  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.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 *  GNU General Public License for more details.
 *
 *  $Id: tun.c,v 1.15 2002/03/01 02:44:24 maxk Exp $
 */

/*
 *  Changes:
 *
 *  Mike Kershaw <dragorn@kismetwireless.net> 2005/08/14
 *    Add TUNSETLINK ioctl to set the link encapsulation
 *
 *  Mark Smith <markzzzsmith@yahoo.com.au>
 *    Use random_ether_addr() for tap MAC address.
 *
 *  Harald Roelle <harald.roelle@ifi.lmu.de>  2004/04/20
 *    Fixes in packet dropping, queue length setting and queue wakeup.
 *    Increased default tx queue length.
 *    Added ethtool API.
 *    Minor cleanups
 *
 *  Daniel Podlejski <underley@underley.eu.org>
 *    Modifications for 2.3.99-pre5 kernel.
 */

#define DRV_NAME	"tun"
#define DRV_VERSION	"1.6"
#define DRV_DESCRIPTION	"Universal TUN/TAP device driver"
#define DRV_COPYRIGHT	"(C) 1999-2004 Max Krasnyansky <maxk@qualcomm.com>"

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/poll.h>
#include <linux/fcntl.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/miscdevice.h>
#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/if.h>
#include <linux/if_arp.h>
#include <linux/if_ether.h>
#include <linux/if_tun.h>
#include <linux/crc32.h>
#include <linux/nsproxy.h>
#include <linux/virtio_net.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>

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

/* Uncomment to enable debugging */
/* #define TUN_DEBUG 1 */

#ifdef TUN_DEBUG
static int debug;

#define DBG  if(tun->debug)printk
#define DBG1 if(debug==2)printk
#else
#define DBG( a... )
#define DBG1( a... )
#endif

#define FLT_EXACT_COUNT 8
struct tap_filter {
	unsigned int    count;    /* Number of addrs. Zero means disabled */
	u32             mask[2];  /* Mask of the hashed addrs */
	unsigned char	addr[FLT_EXACT_COUNT][ETH_ALEN];
};

struct tun_file {
	atomic_t count;
	struct tun_struct *tun;
	struct net *net;
	wait_queue_head_t	read_wait;
};

struct tun_struct {
	struct tun_file		*tfile;
	unsigned int 		flags;
	uid_t			owner;
	gid_t			group;

	struct sk_buff_head	readq;

	struct net_device	*dev;
	struct fasync_struct	*fasync;

	struct tap_filter       txflt;

#ifdef TUN_DEBUG
	int debug;
#endif
};

static int tun_attach(struct tun_struct *tun, struct file *file)
{
	struct tun_file *tfile = file->private_data;
	const struct cred *cred = current_cred();
	int err;

	ASSERT_RTNL();

	/* Check permissions */
	if (((tun->owner != -1 && cred->euid != tun->owner) ||
	     (tun->group != -1 && cred->egid != tun->group)) &&
		!capable(CAP_NET_ADMIN))
		return -EPERM;

	netif_tx_lock_bh(tun->dev);

	err = -EINVAL;
	if (tfile->tun)
		goto out;

	err = -EBUSY;
	if (tun->tfile)
		goto out;

	err = 0;
	tfile->tun = tun;
	tun->tfile = tfile;
	dev_hold(tun->dev);
	atomic_inc(&tfile->count);

out:
	netif_tx_unlock_bh(tun->dev);
	return err;
}

static void __tun_detach(struct tun_struct *tun)
{
	struct tun_file *tfile = tun->tfile;

	/* Detach from net device */
	netif_tx_lock_bh(tun->dev);
	tfile->tun = NULL;
	tun->tfile = NULL;
	netif_tx_unlock_bh(tun->dev);

	/* Drop read queue */
	skb_queue_purge(&tun->readq);

	/* Drop the extra count on the net device */
	dev_put(tun->dev);
}

static void tun_detach(struct tun_struct *tun)
{
	rtnl_lock();
	__tun_detach(tun);
	rtnl_unlock();
}

static struct tun_struct *__tun_get(struct tun_file *tfile)
{
	struct tun_struct *tun = NULL;

	if (atomic_inc_not_zero(&tfile->count))
		tun = tfile->tun;

	return tun;
}

static struct tun_struct *tun_get(struct file *file)
{
	return __tun_get(file->private_data);
}

static void tun_put(struct tun_struct *tun)
{
	struct tun_file *tfile = tun->tfile;

	if (atomic_dec_and_test(&tfile->count))
		tun_detach(tfile->tun);
}

/* TAP filterting */
static void addr_hash_set(u32 *mask, const u8 *addr)
{
	int n = ether_crc(ETH_ALEN, addr) >> 26;
	mask[n >> 5] |= (1 << (n & 31));
}

static unsigned int addr_hash_test(const u32 *mask, const u8 *addr)
{
	int n = ether_crc(ETH_ALEN, addr) >> 26;
	return mask[n >> 5] & (1 << (n & 31));
}

static int update_filter(struct tap_filter *filter, void __user *arg)
{
	struct { u8 u[ETH_ALEN]; } *addr;
	struct tun_filter uf;
	int err, alen, n, nexact;

	if (copy_from_user(&uf, arg, sizeof(uf)))
		return -EFAULT;

	if (!uf.count) {
		/* Disabled */
		filter->count = 0;
		return 0;
	}

	alen = ETH_ALEN * uf.count;
	addr = kmalloc(alen, GFP_KERNEL);
	if (!addr)
		return -ENOMEM;

	if (copy_from_user(addr, arg + sizeof(uf), alen)) {
		err = -EFAULT;
		goto done;
	}

	/* The filter is updated without holding any locks. Which is
	 * perfectly safe. We disable it first and in the worst
	 * case we'll accept a few undesired packets. */
	filter->count = 0;
	wmb();

	/* Use first set of addresses as an exact filter */
	for (n = 0; n < uf.count && n < FLT_EXACT_COUNT; n++)
		memcpy(filter->addr[n], addr[n].u, ETH_ALEN);

	nexact = n;

	/* The rest is hashed */
	memset(filter->mask, 0, sizeof(filter->mask));
	for (; n < uf.count; n++)
		addr_hash_set(filter->mask, addr[n].u);

	/* For ALLMULTI just set the mask to all ones.
	 * This overrides the mask populated above. */
	if ((uf.flags & TUN_FLT_ALLMULTI))
		memset(filter->mask, ~0, sizeof(filter->mask));

	/* Now enable the filter */
	wmb();
	filter->count = nexact;

	/* Return the number of exact filters */
	err = nexact;

done:
	kfree(addr);
	return err;
}

/* Returns: 0 - drop, !=0 - accept */
static int run_filter(struct tap_filter *filter, const struct sk_buff *skb)
{
	/* Cannot use eth_hdr(skb) here because skb_mac_hdr() is incorrect
	 * at this point. */
	struct ethhdr *eh = (struct ethhdr *) skb->data;
	int i;

	/* Exact match */
	for (i = 0; i < filter->count; i++)
		if (!compare_ether_addr(eh->h_dest, filter->addr[i]))
			return 1;

	/* Inexact match (multicast only) */
	if (is_multicast_ether_addr(eh->h_dest))
		return addr_hash_test(filter->mask, eh->h_dest);

	return 0;
}

/*
 * Checks whether the packet is accepted or not.
 * Returns: 0 - drop, !=0 - accept
 */
static int check_filter(struct tap_filter *filter, const struct sk_buff *skb)
{
	if (!filter->count)
		return 1;

	return run_filter(filter, skb);
}

/* Network device part of the driver */

static const struct ethtool_ops tun_ethtool_ops;

/* Net device detach from fd. */
static void tun_net_uninit(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);
	struct tun_file *tfile = tun->tfile;

	/* Inform the methods they need to stop using the dev.
	 */
	if (tfile) {
		wake_up_all(&tfile->read_wait);
		if (atomic_dec_and_test(&tfile->count))
			__tun_detach(tun);
	}
}

/* Net device open. */
static int tun_net_open(struct net_device *dev)
{
	netif_start_queue(dev);
	return 0;
}

/* Net device close. */
static int tun_net_close(struct net_device *dev)
{
	netif_stop_queue(dev);
	return 0;
}

/* Net device start xmit */
static int tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);

	DBG(KERN_INFO "%s: tun_net_xmit %d\n", tun->dev->name, skb->len);

	/* Drop packet if interface is not attached */
	if (!tun->tfile)
		goto drop;

	/* Drop if the filter does not like it.
	 * This is a noop if the filter is disabled.
	 * Filter can be enabled only for the TAP devices. */
	if (!check_filter(&tun->txflt, skb))
		goto drop;

	if (skb_queue_len(&tun->readq) >= dev->tx_queue_len) {
		if (!(tun->flags & TUN_ONE_QUEUE)) {
			/* Normal queueing mode. */
			/* Packet scheduler handles dropping of further packets. */
			netif_stop_queue(dev);

			/* We won't see all dropped packets individually, so overrun
			 * error is more appropriate. */
			dev->stats.tx_fifo_errors++;
		} else {
			/* Single queue mode.
			 * Driver handles dropping of all packets itself. */
			goto drop;
		}
	}

	/* Enqueue packet */
	skb_queue_tail(&tun->readq, skb);
	dev->trans_start = jiffies;

	/* Notify and wake up reader process */
	if (tun->flags & TUN_FASYNC)
		kill_fasync(&tun->fasync, SIGIO, POLL_IN);
	wake_up_interruptible(&tun->tfile->read_wait);
	return 0;

drop:
	dev->stats.tx_dropped++;
	kfree_skb(skb);
	return 0;
}

static void tun_net_mclist(struct net_device *dev)
{
	/*
	 * This callback is supposed to deal with mc filter in
	 * _rx_ path and has nothing to do with the _tx_ path.
	 * In rx path we always accept everything userspace gives us.
	 */
	return;
}

#define MIN_MTU 68
#define MAX_MTU 65535

static int
tun_net_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu < MIN_MTU || new_mtu + dev->hard_header_len > MAX_MTU)
		return -EINVAL;
	dev->mtu = new_mtu;
	return 0;
}

static const struct net_device_ops tun_netdev_ops = {
	.ndo_uninit		= tun_net_uninit,
	.ndo_open		= tun_net_open,
	.ndo_stop		= tun_net_close,
	.ndo_start_xmit		= tun_net_xmit,
	.ndo_change_mtu		= tun_net_change_mtu,
};

static const struct net_device_ops tap_netdev_ops = {
	.ndo_uninit		= tun_net_uninit,
	.ndo_open		= tun_net_open,
	.ndo_stop		= tun_net_close,
	.ndo_start_xmit		= tun_net_xmit,
	.ndo_change_mtu		= tun_net_change_mtu,
	.ndo_set_multicast_list	= tun_net_mclist,
	.ndo_set_mac_address	= eth_mac_addr,
	.ndo_validate_addr	= eth_validate_addr,
};

/* Initialize net device. */
static void tun_net_init(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);

	switch (tun->flags & TUN_TYPE_MASK) {
	case TUN_TUN_DEV:
		dev->netdev_ops = &tun_netdev_ops;

		/* Point-to-Point TUN Device */
		dev->hard_header_len = 0;
		dev->addr_len = 0;
		dev->mtu = 1500;

		/* Zero header length */
		dev->type = ARPHRD_NONE;
		dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
		break;

	case TUN_TAP_DEV:
		dev->netdev_ops = &tap_netdev_ops;
		/* Ethernet TAP Device */
		ether_setup(dev);

		random_ether_addr(dev->dev_addr);

		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
		break;
	}
}

/* Character device part */

/* Poll */
static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
{
	struct tun_file *tfile = file->private_data;
	struct tun_struct *tun = __tun_get(tfile);
	unsigned int mask = POLLOUT | POLLWRNORM;

	if (!tun)
		return POLLERR;

	DBG(KERN_INFO "%s: tun_chr_poll\n", tun->dev->name);

	poll_wait(file, &tfile->read_wait, wait);

	if (!skb_queue_empty(&tun->readq))
		mask |= POLLIN | POLLRDNORM;

	if (tun->dev->reg_state != NETREG_REGISTERED)
		mask = POLLERR;

	tun_put(tun);
	return mask;
}

/* prepad is the amount to reserve at front.  len is length after that.
 * linear is a hint as to how much to copy (usually headers). */
static struct sk_buff *tun_alloc_skb(size_t prepad, size_t len, size_t linear,
				     gfp_t gfp)
{
	struct sk_buff *skb;
	unsigned int i;

	skb = alloc_skb(prepad + len, gfp|__GFP_NOWARN);
	if (skb) {
		skb_reserve(skb, prepad);
		skb_put(skb, len);
		return skb;
	}

	/* Under a page?  Don't bother with paged skb. */
	if (prepad + len < PAGE_SIZE)
		return NULL;

	/* Start with a normal skb, and add pages. */
	skb = alloc_skb(prepad + linear, gfp);
	if (!skb)
		return NULL;

	skb_reserve(skb, prepad);
	skb_put(skb, linear);

	len -= linear;

	for (i = 0; i < MAX_SKB_FRAGS; i++) {
		skb_frag_t *f = &skb_shinfo(skb)->frags[i];

		f->page = alloc_page(gfp|__GFP_ZERO);
		if (!f->page)
			break;

		f->page_offset = 0;
		f->size = PAGE_SIZE;

		skb->data_len += PAGE_SIZE;
		skb->len += PAGE_SIZE;
		skb->truesize += PAGE_SIZE;
		skb_shinfo(skb)->nr_frags++;

		if (len < PAGE_SIZE) {
			len = 0;
			break;
		}
		len -= PAGE_SIZE;
	}

	/* Too large, or alloc fail? */
	if (unlikely(len)) {
		kfree_skb(skb);
		skb = NULL;
	}

	return skb;
}

/* Get packet from user space buffer */
static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv, size_t count)
{
	struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) };
	struct sk_buff *skb;
	size_t len = count, align = 0;
	struct virtio_net_hdr gso = { 0 };

	if (!(tun->flags & TUN_NO_PI)) {
		if ((len -= sizeof(pi)) > count)
			return -EINVAL;

		if(memcpy_fromiovec((void *)&pi, iv, sizeof(pi)))
			return -EFAULT;
	}

	if (tun->flags & TUN_VNET_HDR) {
		if ((len -= sizeof(gso)) > count)
			return -EINVAL;

		if (memcpy_fromiovec((void *)&gso, iv, sizeof(gso)))
			return -EFAULT;

		if (gso.hdr_len > len)
			return -EINVAL;
	}

	if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
		align = NET_IP_ALIGN;
		if (unlikely(len < ETH_HLEN))
			return -EINVAL;
	}

	if (!(skb = tun_alloc_skb(align, len, gso.hdr_len, GFP_KERNEL))) {
		tun->dev->stats.rx_dropped++;
		return -ENOMEM;
	}

	if (skb_copy_datagram_from_iovec(skb, 0, iv, len)) {
		tun->dev->stats.rx_dropped++;
		kfree_skb(skb);
		return -EFAULT;
	}

	if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
		if (!skb_partial_csum_set(skb, gso.csum_start,
					  gso.csum_offset)) {
			tun->dev->stats.rx_frame_errors++;
			kfree_skb(skb);
			return -EINVAL;
		}
	} else if (tun->flags & TUN_NOCHECKSUM)
		skb->ip_summed = CHECKSUM_UNNECESSARY;

	switch (tun->flags & TUN_TYPE_MASK) {
	case TUN_TUN_DEV:
		if (tun->flags & TUN_NO_PI) {
			switch (skb->data[0] & 0xf0) {
			case 0x40:
				pi.proto = htons(ETH_P_IP);
				break;
			case 0x60:
				pi.proto = htons(ETH_P_IPV6);
				break;
			default:
				tun->dev->stats.rx_dropped++;
				kfree_skb(skb);
				return -EINVAL;
			}
		}

		skb_reset_mac_header(skb);
		skb->protocol = pi.proto;
		skb->dev = tun->dev;
		break;
	case TUN_TAP_DEV:
		skb->protocol = eth_type_trans(skb, tun->dev);
		break;
	};

	if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
		pr_debug("GSO!\n");
		switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
		case VIRTIO_NET_HDR_GSO_TCPV4:
			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
			break;
		case VIRTIO_NET_HDR_GSO_TCPV6:
			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
			break;
		default:
			tun->dev->stats.rx_frame_errors++;
			kfree_skb(skb);
			return -EINVAL;
		}

		if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN)
			skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;

		skb_shinfo(skb)->gso_size = gso.gso_size;
		if (skb_shinfo(skb)->gso_size == 0) {
			tun->dev->stats.rx_frame_errors++;
			kfree_skb(skb);
			return -EINVAL;
		}

		/* Header must be checked, and gso_segs computed. */
		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
		skb_shinfo(skb)->gso_segs = 0;
	}

	netif_rx_ni(skb);

	tun->dev->stats.rx_packets++;
	tun->dev->stats.rx_bytes += len;

	return count;
}

static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv,
			      unsigned long count, loff_t pos)
{
	struct tun_struct *tun = tun_get(iocb->ki_filp);
	ssize_t result;

	if (!tun)
		return -EBADFD;

	DBG(KERN_INFO "%s: tun_chr_write %ld\n", tun->dev->name, count);

	result = tun_get_user(tun, (struct iovec *) iv, iov_length(iv, count));

	tun_put(tun);
	return result;
}

/* Put packet to the user space buffer */
static __inline__ ssize_t tun_put_user(struct tun_struct *tun,
				       struct sk_buff *skb,
				       struct iovec *iv, int len)
{
	struct tun_pi pi = { 0, skb->protocol };
	ssize_t total = 0;

	if (!(tun->flags & TUN_NO_PI)) {
		if ((len -= sizeof(pi)) < 0)
			return -EINVAL;

		if (len < skb->len) {
			/* Packet will be striped */
			pi.flags |= TUN_PKT_STRIP;
		}

		if (memcpy_toiovec(iv, (void *) &pi, sizeof(pi)))
			return -EFAULT;
		total += sizeof(pi);
	}

	if (tun->flags & TUN_VNET_HDR) {
		struct virtio_net_hdr gso = { 0 }; /* no info leak */
		if ((len -= sizeof(gso)) < 0)
			return -EINVAL;

		if (skb_is_gso(skb)) {
			struct skb_shared_info *sinfo = skb_shinfo(skb);

			/* This is a hint as to how much should be linear. */
			gso.hdr_len = skb_headlen(skb);
			gso.gso_size = sinfo->gso_size;
			if (sinfo->gso_type & SKB_GSO_TCPV4)
				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
			else if (sinfo->gso_type & SKB_GSO_TCPV6)
				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
			else
				BUG();
			if (sinfo->gso_type & SKB_GSO_TCP_ECN)
				gso.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
		} else
			gso.gso_type = VIRTIO_NET_HDR_GSO_NONE;

		if (skb->ip_summed == CHECKSUM_PARTIAL) {
			gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
			gso.csum_start = skb->csum_start - skb_headroom(skb);
			gso.csum_offset = skb->csum_offset;
		} /* else everything is zero */

		if (unlikely(memcpy_toiovec(iv, (void *)&gso, sizeof(gso))))
			return -EFAULT;
		total += sizeof(gso);
	}

	len = min_t(int, skb->len, len);

	skb_copy_datagram_iovec(skb, 0, iv, len);
	total += len;

	tun->dev->stats.tx_packets++;
	tun->dev->stats.tx_bytes += len;

	return total;
}

static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
			    unsigned long count, loff_t pos)
{
	struct file *file = iocb->ki_filp;
	struct tun_file *tfile = file->private_data;
	struct tun_struct *tun = __tun_get(tfile);
	DECLARE_WAITQUEUE(wait, current);
	struct sk_buff *skb;
	ssize_t len, ret = 0;

	if (!tun)
		return -EBADFD;

	DBG(KERN_INFO "%s: tun_chr_read\n", tun->dev->name);

	len = iov_length(iv, count);
	if (len < 0) {
		ret = -EINVAL;
		goto out;
	}

	add_wait_queue(&tfile->read_wait, &wait);
	while (len) {
		current->state = TASK_INTERRUPTIBLE;

		/* Read frames from the queue */
		if (!(skb=skb_dequeue(&tun->readq))) {
			if (file->f_flags & O_NONBLOCK) {
				ret = -EAGAIN;
				break;
			}
			if (signal_pending(current)) {
				ret = -ERESTARTSYS;
				break;
			}
			if (tun->dev->reg_state != NETREG_REGISTERED) {
				ret = -EIO;
				break;
			}

			/* Nothing to read, let's sleep */
			schedule();
			continue;
		}
		netif_wake_queue(tun->dev);

		ret = tun_put_user(tun, skb, (struct iovec *) iv, len);
		kfree_skb(skb);
		break;
	}

	current->state = TASK_RUNNING;
	remove_wait_queue(&tfile->read_wait, &wait);

out:
	tun_put(tun);
	return ret;
}

static void tun_setup(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);

	skb_queue_head_init(&tun->readq);

	tun->owner = -1;
	tun->group = -1;

	dev->ethtool_ops = &tun_ethtool_ops;
	dev->destructor = free_netdev;
}

/* Trivial set of netlink ops to allow deleting tun or tap
 * device with netlink.
 */
static int tun_validate(struct nlattr *tb[], struct nlattr *data[])
{
	return -EINVAL;
}

static struct rtnl_link_ops tun_link_ops __read_mostly = {
	.kind		= DRV_NAME,
	.priv_size	= sizeof(struct tun_struct),
	.setup		= tun_setup,
	.validate	= tun_validate,
};


static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
{
	struct tun_struct *tun;
	struct net_device *dev;
	int err;

	dev = __dev_get_by_name(net, ifr->ifr_name);
	if (dev) {
		if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops)
			tun = netdev_priv(dev);
		else if ((ifr->ifr_flags & IFF_TAP) && dev->netdev_ops == &tap_netdev_ops)
			tun = netdev_priv(dev);
		else
			return -EINVAL;

		err = tun_attach(tun, file);
		if (err < 0)
			return err;
	}
	else {
		char *name;
		unsigned long flags = 0;

		err = -EINVAL;

		if (!capable(CAP_NET_ADMIN))
			return -EPERM;

		/* Set dev type */
		if (ifr->ifr_flags & IFF_TUN) {
			/* TUN device */
			flags |= TUN_TUN_DEV;
			name = "tun%d";
		} else if (ifr->ifr_flags & IFF_TAP) {
			/* TAP device */
			flags |= TUN_TAP_DEV;
			name = "tap%d";
		} else
			goto failed;

		if (*ifr->ifr_name)
			name = ifr->ifr_name;

		dev = alloc_netdev(sizeof(struct tun_struct), name,
				   tun_setup);
		if (!dev)
			return -ENOMEM;

		dev_net_set(dev, net);
		dev->rtnl_link_ops = &tun_link_ops;

		tun = netdev_priv(dev);
		tun->dev = dev;
		tun->flags = flags;
		tun->txflt.count = 0;

		tun_net_init(dev);

		if (strchr(dev->name, '%')) {
			err = dev_alloc_name(dev, dev->name);
			if (err < 0)
				goto err_free_dev;
		}

		err = register_netdevice(tun->dev);
		if (err < 0)
			goto err_free_dev;

		err = tun_attach(tun, file);
		if (err < 0)
			goto err_free_dev;
	}

	DBG(KERN_INFO "%s: tun_set_iff\n", tun->dev->name);

	if (ifr->ifr_flags & IFF_NO_PI)
		tun->flags |= TUN_NO_PI;
	else
		tun->flags &= ~TUN_NO_PI;

	if (ifr->ifr_flags & IFF_ONE_QUEUE)
		tun->flags |= TUN_ONE_QUEUE;
	else
		tun->flags &= ~TUN_ONE_QUEUE;

	if (ifr->ifr_flags & IFF_VNET_HDR)
		tun->flags |= TUN_VNET_HDR;
	else
		tun->flags &= ~TUN_VNET_HDR;

	/* Make sure persistent devices do not get stuck in
	 * xoff state.
	 */
	if (netif_running(tun->dev))
		netif_wake_queue(tun->dev);

	strcpy(ifr->ifr_name, tun->dev->name);
	return 0;

 err_free_dev:
	free_netdev(dev);
 failed:
	return err;
}

static int tun_get_iff(struct net *net, struct file *file, struct ifreq *ifr)
{
	struct tun_struct *tun = tun_get(file);

	if (!tun)
		return -EBADFD;

	DBG(KERN_INFO "%s: tun_get_iff\n", tun->dev->name);

	strcpy(ifr->ifr_name, tun->dev->name);

	ifr->ifr_flags = 0;

	if (ifr->ifr_flags & TUN_TUN_DEV)
		ifr->ifr_flags |= IFF_TUN;
	else
		ifr->ifr_flags |= IFF_TAP;

	if (tun->flags & TUN_NO_PI)
		ifr->ifr_flags |= IFF_NO_PI;

	if (tun->flags & TUN_ONE_QUEUE)
		ifr->ifr_flags |= IFF_ONE_QUEUE;

	if (tun->flags & TUN_VNET_HDR)
		ifr->ifr_flags |= IFF_VNET_HDR;

	tun_put(tun);
	return 0;
}

/* This is like a cut-down ethtool ops, except done via tun fd so no
 * privs required. */
static int set_offload(struct net_device *dev, unsigned long arg)
{
	unsigned int old_features, features;

	old_features = dev->features;
	/* Unset features, set them as we chew on the arg. */
	features = (old_features & ~(NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST
				    |NETIF_F_TSO_ECN|NETIF_F_TSO|NETIF_F_TSO6));

	if (arg & TUN_F_CSUM) {
		features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
		arg &= ~TUN_F_CSUM;

		if (arg & (TUN_F_TSO4|TUN_F_TSO6)) {
			if (arg & TUN_F_TSO_ECN) {
				features |= NETIF_F_TSO_ECN;
				arg &= ~TUN_F_TSO_ECN;
			}
			if (arg & TUN_F_TSO4)
				features |= NETIF_F_TSO;
			if (arg & TUN_F_TSO6)
				features |= NETIF_F_TSO6;
			arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
		}
	}

	/* This gives the user a way to test for new features in future by
	 * trying to set them. */
	if (arg)
		return -EINVAL;

	dev->features = features;
	if (old_features != dev->features)
		netdev_features_change(dev);

	return 0;
}

static int tun_chr_ioctl(struct inode *inode, struct file *file,
			 unsigned int cmd, unsigned long arg)
{
	struct tun_file *tfile = file->private_data;
	struct tun_struct *tun;
	void __user* argp = (void __user*)arg;
	struct ifreq ifr;
	int ret;

	if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89)
		if (copy_from_user(&ifr, argp, sizeof ifr))
			return -EFAULT;

	if (cmd == TUNGETFEATURES) {
		/* Currently this just means: "what IFF flags are valid?".
		 * This is needed because we never checked for invalid flags on
		 * TUNSETIFF. */
		return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE |
				IFF_VNET_HDR,
				(unsigned int __user*)argp);
	}

	tun = __tun_get(tfile);
	if (cmd == TUNSETIFF && !tun) {
		int err;

		ifr.ifr_name[IFNAMSIZ-1] = '\0';

		rtnl_lock();
		err = tun_set_iff(tfile->net, file, &ifr);
		rtnl_unlock();

		if (err)
			return err;

		if (copy_to_user(argp, &ifr, sizeof(ifr)))
			return -EFAULT;
		return 0;
	}


	if (!tun)
		return -EBADFD;

	DBG(KERN_INFO "%s: tun_chr_ioctl cmd %d\n", tun->dev->name, cmd);

	ret = 0;
	switch (cmd) {
	case TUNGETIFF:
		ret = tun_get_iff(current->nsproxy->net_ns, file, &ifr);
		if (ret)
			break;

		if (copy_to_user(argp, &ifr, sizeof(ifr)))
			ret = -EFAULT;
		break;

	case TUNSETNOCSUM:
		/* Disable/Enable checksum */
		if (arg)
			tun->flags |= TUN_NOCHECKSUM;
		else
			tun->flags &= ~TUN_NOCHECKSUM;

		DBG(KERN_INFO "%s: checksum %s\n",
		    tun->dev->name, arg ? "disabled" : "enabled");
		break;

	case TUNSETPERSIST:
		/* Disable/Enable persist mode */
		if (arg)
			tun->flags |= TUN_PERSIST;
		else
			tun->flags &= ~TUN_PERSIST;

		DBG(KERN_INFO "%s: persist %s\n",
		    tun->dev->name, arg ? "enabled" : "disabled");
		break;

	case TUNSETOWNER:
		/* Set owner of the device */
		tun->owner = (uid_t) arg;

		DBG(KERN_INFO "%s: owner set to %d\n", tun->dev->name, tun->owner);
		break;

	case TUNSETGROUP:
		/* Set group of the device */
		tun->group= (gid_t) arg;

		DBG(KERN_INFO "%s: group set to %d\n", tun->dev->name, tun->group);
		break;

	case TUNSETLINK:
		/* Only allow setting the type when the interface is down */
		rtnl_lock();
		if (tun->dev->flags & IFF_UP) {
			DBG(KERN_INFO "%s: Linktype set failed because interface is up\n",
				tun->dev->name);
			ret = -EBUSY;
		} else {
			tun->dev->type = (int) arg;
			DBG(KERN_INFO "%s: linktype set to %d\n", tun->dev->name, tun->dev->type);
			ret = 0;
		}
		rtnl_unlock();
		break;

#ifdef TUN_DEBUG
	case TUNSETDEBUG:
		tun->debug = arg;
		break;
#endif
	case TUNSETOFFLOAD:
		rtnl_lock();
		ret = set_offload(tun->dev, arg);
		rtnl_unlock();
		break;

	case TUNSETTXFILTER:
		/* Can be set only for TAPs */
		ret = -EINVAL;
		if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
			break;
		rtnl_lock();
		ret = update_filter(&tun->txflt, (void __user *)arg);
		rtnl_unlock();
		break;

	case SIOCGIFHWADDR:
		/* Get hw addres */
		memcpy(ifr.ifr_hwaddr.sa_data, tun->dev->dev_addr, ETH_ALEN);
		ifr.ifr_hwaddr.sa_family = tun->dev->type;
		if (copy_to_user(argp, &ifr, sizeof ifr))
			ret = -EFAULT;
		break;

	case SIOCSIFHWADDR:
		/* Set hw address */
		DBG(KERN_DEBUG "%s: set hw address: %pM\n",
			tun->dev->name, ifr.ifr_hwaddr.sa_data);

		rtnl_lock();
		ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr);
		rtnl_unlock();
		break;
	default:
		ret = -EINVAL;
		break;
	};

	tun_put(tun);
	return ret;
}

static int tun_chr_fasync(int fd, struct file *file, int on)
{
	struct tun_struct *tun = tun_get(file);
	int ret;

	if (!tun)
		return -EBADFD;

	DBG(KERN_INFO "%s: tun_chr_fasync %d\n", tun->dev->name, on);

	lock_kernel();
	if ((ret = fasync_helper(fd, file, on, &tun->fasync)) < 0)
		goto out;

	if (on) {
		ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0);
		if (ret)
			goto out;
		tun->flags |= TUN_FASYNC;
	} else
		tun->flags &= ~TUN_FASYNC;
	ret = 0;
out:
	unlock_kernel();
	tun_put(tun);
	return ret;
}

static int tun_chr_open(struct inode *inode, struct file * file)
{
	struct tun_file *tfile;
	cycle_kernel_lock();
	DBG1(KERN_INFO "tunX: tun_chr_open\n");

	tfile = kmalloc(sizeof(*tfile), GFP_KERNEL);
	if (!tfile)
		return -ENOMEM;
	atomic_set(&tfile->count, 0);
	tfile->tun = NULL;
	tfile->net = get_net(current->nsproxy->net_ns);
	init_waitqueue_head(&tfile->read_wait);
	file->private_data = tfile;
	return 0;
}

static int tun_chr_close(struct inode *inode, struct file *file)
{
	struct tun_file *tfile = file->private_data;
	struct tun_struct *tun = __tun_get(tfile);


	if (tun) {
		DBG(KERN_INFO "%s: tun_chr_close\n", tun->dev->name);

		rtnl_lock();
		__tun_detach(tun);

		/* If desireable, unregister the netdevice. */
		if (!(tun->flags & TUN_PERSIST))
			unregister_netdevice(tun->dev);

		rtnl_unlock();
	}

	put_net(tfile->net);
	kfree(tfile);

	return 0;
}

static const struct file_operations tun_fops = {
	.owner	= THIS_MODULE,
	.llseek = no_llseek,
	.read  = do_sync_read,
	.aio_read  = tun_chr_aio_read,
	.write = do_sync_write,
	.aio_write = tun_chr_aio_write,
	.poll	= tun_chr_poll,
	.ioctl	= tun_chr_ioctl,
	.open	= tun_chr_open,
	.release = tun_chr_close,
	.fasync = tun_chr_fasync
};

static struct miscdevice tun_miscdev = {
	.minor = TUN_MINOR,
	.name = "tun",
	.fops = &tun_fops,
};

/* ethtool interface */

static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
	cmd->supported		= 0;
	cmd->advertising	= 0;
	cmd->speed		= SPEED_10;
	cmd->duplex		= DUPLEX_FULL;
	cmd->port		= PORT_TP;
	cmd->phy_address	= 0;
	cmd->transceiver	= XCVR_INTERNAL;
	cmd->autoneg		= AUTONEG_DISABLE;
	cmd->maxtxpkt		= 0;
	cmd->maxrxpkt		= 0;
	return 0;
}

static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
	struct tun_struct *tun = netdev_priv(dev);

	strcpy(info->driver, DRV_NAME);
	strcpy(info->version, DRV_VERSION);
	strcpy(info->fw_version, "N/A");

	switch (tun->flags & TUN_TYPE_MASK) {
	case TUN_TUN_DEV:
		strcpy(info->bus_info, "tun");
		break;
	case TUN_TAP_DEV:
		strcpy(info->bus_info, "tap");
		break;
	}
}

static u32 tun_get_msglevel(struct net_device *dev)
{
#ifdef TUN_DEBUG
	struct tun_struct *tun = netdev_priv(dev);
	return tun->debug;
#else
	return -EOPNOTSUPP;
#endif
}

static void tun_set_msglevel(struct net_device *dev, u32 value)
{
#ifdef TUN_DEBUG
	struct tun_struct *tun = netdev_priv(dev);
	tun->debug = value;
#endif
}

static u32 tun_get_link(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);
	return !!tun->tfile;
}

static u32 tun_get_rx_csum(struct net_device *dev)
{
	struct tun_struct *tun = netdev_priv(dev);
	return (tun->flags & TUN_NOCHECKSUM) == 0;
}

static int tun_set_rx_csum(struct net_device *dev, u32 data)
{
	struct tun_struct *tun = netdev_priv(dev);
	if (data)
		tun->flags &= ~TUN_NOCHECKSUM;
	else
		tun->flags |= TUN_NOCHECKSUM;
	return 0;
}

static const struct ethtool_ops tun_ethtool_ops = {
	.get_settings	= tun_get_settings,
	.get_drvinfo	= tun_get_drvinfo,
	.get_msglevel	= tun_get_msglevel,
	.set_msglevel	= tun_set_msglevel,
	.get_link	= tun_get_link,
	.get_rx_csum	= tun_get_rx_csum,
	.set_rx_csum	= tun_set_rx_csum
};


static int __init tun_init(void)
{
	int ret = 0;

	printk(KERN_INFO "tun: %s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
	printk(KERN_INFO "tun: %s\n", DRV_COPYRIGHT);

	ret = rtnl_link_register(&tun_link_ops);
	if (ret) {
		printk(KERN_ERR "tun: Can't register link_ops\n");
		goto err_linkops;
	}

	ret = misc_register(&tun_miscdev);
	if (ret) {
		printk(KERN_ERR "tun: Can't register misc device %d\n", TUN_MINOR);
		goto err_misc;
	}
	return  0;
err_misc:
	rtnl_link_unregister(&tun_link_ops);
err_linkops:
	return ret;
}

static void tun_cleanup(void)
{
	misc_deregister(&tun_miscdev);
	rtnl_link_unregister(&tun_link_ops);
}

module_init(tun_init);
module_exit(tun_cleanup);
MODULE_DESCRIPTION(DRV_DESCRIPTION);
MODULE_AUTHOR(DRV_COPYRIGHT);
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(TUN_MINOR);