aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/ipip.c
blob: 99af1f0cc65827c3faa40407c17b38527ac8a211 (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
/*
 *	Linux NET3:	IP/IP protocol decoder.
 *
 *	Authors:
 *		Sam Lantinga (slouken@cs.ucdavis.edu)  02/01/95
 *
 *	Fixes:
 *		Alan Cox	:	Merged and made usable non modular (its so tiny its silly as
 *					a module taking up 2 pages).
 *		Alan Cox	: 	Fixed bug with 1.3.18 and IPIP not working (now needs to set skb->h.iph)
 *					to keep ip_forward happy.
 *		Alan Cox	:	More fixes for 1.3.21, and firewall fix. Maybe this will work soon 8).
 *		Kai Schulte	:	Fixed #defines for IP_FIREWALL->FIREWALL
 *              David Woodhouse :       Perform some basic ICMP handling.
 *                                      IPIP Routing without decapsulation.
 *              Carlos Picoto   :       GRE over IP support
 *		Alexey Kuznetsov:	Reworked. Really, now it is truncated version of ipv4/ip_gre.c.
 *					I do not want to merge them together.
 *
 *	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.
 *
 */

/* tunnel.c: an IP tunnel driver

	The purpose of this driver is to provide an IP tunnel through
	which you can tunnel network traffic transparently across subnets.

	This was written by looking at Nick Holloway's dummy driver
	Thanks for the great code!

		-Sam Lantinga	(slouken@cs.ucdavis.edu)  02/01/95

	Minor tweaks:
		Cleaned up the code a little and added some pre-1.3.0 tweaks.
		dev->hard_header/hard_header_len changed to use no headers.
		Comments/bracketing tweaked.
		Made the tunnels use dev->name not tunnel: when error reporting.
		Added tx_dropped stat

		-Alan Cox	(alan@lxorguk.ukuu.org.uk) 21 March 95

	Reworked:
		Changed to tunnel to destination gateway in addition to the
			tunnel's pointopoint address
		Almost completely rewritten
		Note:  There is currently no firewall or ICMP handling done.

		-Sam Lantinga	(slouken@cs.ucdavis.edu) 02/13/96

*/

/* Things I wish I had known when writing the tunnel driver:

	When the tunnel_xmit() function is called, the skb contains the
	packet to be sent (plus a great deal of extra info), and dev
	contains the tunnel device that _we_ are.

	When we are passed a packet, we are expected to fill in the
	source address with our source IP address.

	What is the proper way to allocate, copy and free a buffer?
	After you allocate it, it is a "0 length" chunk of memory
	starting at zero.  If you want to add headers to the buffer
	later, you'll have to call "skb_reserve(skb, amount)" with
	the amount of memory you want reserved.  Then, you call
	"skb_put(skb, amount)" with the amount of space you want in
	the buffer.  skb_put() returns a pointer to the top (#0) of
	that buffer.  skb->len is set to the amount of space you have
	"allocated" with skb_put().  You can then write up to skb->len
	bytes to that buffer.  If you need more, you can call skb_put()
	again with the additional amount of space you need.  You can
	find out how much more space you can allocate by calling
	"skb_tailroom(skb)".
	Now, to add header space, call "skb_push(skb, header_len)".
	This creates space at the beginning of the buffer and returns
	a pointer to this new space.  If later you need to strip a
	header from a buffer, call "skb_pull(skb, header_len)".
	skb_headroom() will return how much space is left at the top
	of the buffer (before the main data).  Remember, this headroom
	space must be reserved before the skb_put() function is called.
	*/

/*
   This version of net/ipv4/ipip.c is cloned of net/ipv4/ip_gre.c

   For comments look at net/ipv4/ip_gre.c --ANK
 */


#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/netfilter_ipv4.h>
#include <linux/if_ether.h>

#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>

#define HASH_SIZE  16
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)

static int ipip_net_id __read_mostly;
struct ipip_net {
	struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
	struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
	struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
	struct ip_tunnel __rcu *tunnels_wc[1];
	struct ip_tunnel __rcu **tunnels[4];

	struct net_device *fb_tunnel_dev;
};

static int ipip_tunnel_init(struct net_device *dev);
static void ipip_tunnel_setup(struct net_device *dev);
static void ipip_dev_free(struct net_device *dev);

/*
 * 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 {
	u64	rx_packets;
	u64	rx_bytes;
	u64	tx_packets;
	u64	tx_bytes;
	struct u64_stats_sync	syncp;
};

static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev,
						  struct rtnl_link_stats64 *tot)
{
	int i;

	for_each_possible_cpu(i) {
		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
		unsigned int start;

		do {
			start = u64_stats_fetch_begin_bh(&tstats->syncp);
			rx_packets = tstats->rx_packets;
			tx_packets = tstats->tx_packets;
			rx_bytes = tstats->rx_bytes;
			tx_bytes = tstats->tx_bytes;
		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));

		tot->rx_packets += rx_packets;
		tot->tx_packets += tx_packets;
		tot->rx_bytes   += rx_bytes;
		tot->tx_bytes   += tx_bytes;
	}

	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
	tot->tx_dropped = dev->stats.tx_dropped;
	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
	tot->tx_errors = dev->stats.tx_errors;
	tot->collisions = dev->stats.collisions;

	return tot;
}

static struct ip_tunnel *ipip_tunnel_lookup(struct net *net,
		__be32 remote, __be32 local)
{
	unsigned int h0 = HASH(remote);
	unsigned int h1 = HASH(local);
	struct ip_tunnel *t;
	struct ipip_net *ipn = net_generic(net, ipip_net_id);

	for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1])
		if (local == t->parms.iph.saddr &&
		    remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
			return t;

	for_each_ip_tunnel_rcu(ipn->tunnels_r[h0])
		if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
			return t;

	for_each_ip_tunnel_rcu(ipn->tunnels_l[h1])
		if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
			return t;

	t = rcu_dereference(ipn->tunnels_wc[0]);
	if (t && (t->dev->flags&IFF_UP))
		return t;
	return NULL;
}

static struct ip_tunnel __rcu **__ipip_bucket(struct ipip_net *ipn,
		struct ip_tunnel_parm *parms)
{
	__be32 remote = parms->iph.daddr;
	__be32 local = parms->iph.saddr;
	unsigned int h = 0;
	int prio = 0;

	if (remote) {
		prio |= 2;
		h ^= HASH(remote);
	}
	if (local) {
		prio |= 1;
		h ^= HASH(local);
	}
	return &ipn->tunnels[prio][h];
}

static inline struct ip_tunnel __rcu **ipip_bucket(struct ipip_net *ipn,
		struct ip_tunnel *t)
{
	return __ipip_bucket(ipn, &t->parms);
}

static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t)
{
	struct ip_tunnel __rcu **tp;
	struct ip_tunnel *iter;

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

static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t)
{
	struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t);

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

static struct ip_tunnel *ipip_tunnel_locate(struct net *net,
		struct ip_tunnel_parm *parms, int create)
{
	__be32 remote = parms->iph.daddr;
	__be32 local = parms->iph.saddr;
	struct ip_tunnel *t, *nt;
	struct ip_tunnel __rcu **tp;
	struct net_device *dev;
	char name[IFNAMSIZ];
	struct ipip_net *ipn = net_generic(net, ipip_net_id);

	for (tp = __ipip_bucket(ipn, parms);
		 (t = rtnl_dereference(*tp)) != NULL;
		 tp = &t->next) {
		if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr)
			return t;
	}
	if (!create)
		return NULL;

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

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

	dev_net_set(dev, net);

	nt = netdev_priv(dev);
	nt->parms = *parms;

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

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

	strcpy(nt->parms.name, dev->name);

	dev_hold(dev);
	ipip_tunnel_link(ipn, nt);
	return nt;

failed_free:
	ipip_dev_free(dev);
	return NULL;
}

/* called with RTNL */
static void ipip_tunnel_uninit(struct net_device *dev)
{
	struct net *net = dev_net(dev);
	struct ipip_net *ipn = net_generic(net, ipip_net_id);

	if (dev == ipn->fb_tunnel_dev)
		RCU_INIT_POINTER(ipn->tunnels_wc[0], NULL);
	else
		ipip_tunnel_unlink(ipn, netdev_priv(dev));
	dev_put(dev);
}

static int ipip_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.
 */
	const struct iphdr *iph = (const struct iphdr *)skb->data;
	const int type = icmp_hdr(skb)->type;
	const int code = icmp_hdr(skb)->code;
	struct ip_tunnel *t;
	int err;

	switch (type) {
	default:
	case ICMP_PARAMETERPROB:
		return 0;

	case ICMP_DEST_UNREACH:
		switch (code) {
		case ICMP_SR_FAILED:
		case ICMP_PORT_UNREACH:
			/* Impossible event. */
			return 0;
		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 0;
		break;
	case ICMP_REDIRECT:
		break;
	}

	err = -ENOENT;

	rcu_read_lock();
	t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
	if (t == NULL)
		goto out;

	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
				 t->dev->ifindex, 0, IPPROTO_IPIP, 0);
		err = 0;
		goto out;
	}

	if (type == ICMP_REDIRECT) {
		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
			      IPPROTO_IPIP, 0);
		err = 0;
		goto out;
	}

	if (t->parms.iph.daddr == 0)
		goto out;

	err = 0;
	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();
	return err;
}

static inline void ipip_ecn_decapsulate(const struct iphdr *outer_iph,
					struct sk_buff *skb)
{
	struct iphdr *inner_iph = ip_hdr(skb);

	if (INET_ECN_is_ce(outer_iph->tos))
		IP_ECN_set_ce(inner_iph);
}

static int ipip_rcv(struct sk_buff *skb)
{
	struct ip_tunnel *tunnel;
	const struct iphdr *iph = ip_hdr(skb);

	rcu_read_lock();
	tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
	if (tunnel != NULL) {
		struct pcpu_tstats *tstats;

		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
			rcu_read_unlock();
			kfree_skb(skb);
			return 0;
		}

		secpath_reset(skb);

		skb->mac_header = skb->network_header;
		skb_reset_network_header(skb);
		skb->protocol = htons(ETH_P_IP);
		skb->pkt_type = PACKET_HOST;

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

		__skb_tunnel_rx(skb, tunnel->dev);

		ipip_ecn_decapsulate(iph, skb);

		netif_rx(skb);

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

	return -1;
}

/*
 *	This function assumes it is being called from dev_queue_xmit()
 *	and that skb is filled properly by that function.
 */

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

	if (skb->protocol != htons(ETH_P_IP))
		goto tx_error;

	if (tos & 1)
		tos = old_iph->tos;

	if (!dst) {
		/* NBMA tunnel */
		if ((rt = skb_rtable(skb)) == NULL) {
			dev->stats.tx_fifo_errors++;
			goto tx_error;
		}
		dst = rt_nexthop(rt, old_iph->daddr);
	}

	rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
				   dst, tiph->saddr,
				   0, 0,
				   IPPROTO_IPIP, RT_TOS(tos),
				   tunnel->parms.link);
	if (IS_ERR(rt)) {
		dev->stats.tx_carrier_errors++;
		goto tx_error_icmp;
	}
	tdev = rt->dst.dev;

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

	df |= old_iph->frag_off & htons(IP_DF);

	if (df) {
		mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);

		if (mtu < 68) {
			dev->stats.collisions++;
			ip_rt_put(rt);
			goto tx_error;
		}

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

		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 (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;
	}

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

	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 (!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->transport_header = skb->network_header;
	skb_push(skb, sizeof(struct iphdr));
	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_IPIP;
	iph->tos		=	INET_ECN_encapsulate(tos, old_iph->tos);
	iph->daddr		=	fl4.daddr;
	iph->saddr		=	fl4.saddr;

	if ((iph->ttl = tiph->ttl) == 0)
		iph->ttl	=	old_iph->ttl;

	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 void ipip_tunnel_bind_dev(struct net_device *dev)
{
	struct net_device *tdev = NULL;
	struct ip_tunnel *tunnel;
	const struct iphdr *iph;

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

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

		rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
					   iph->daddr, iph->saddr,
					   0, 0,
					   IPPROTO_IPIP,
					   RT_TOS(iph->tos),
					   tunnel->parms.link);
		if (!IS_ERR(rt)) {
			tdev = rt->dst.dev;
			ip_rt_put(rt);
		}
		dev->flags |= IFF_POINTOPOINT;
	}

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

	if (tdev) {
		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
		dev->mtu = tdev->mtu - sizeof(struct iphdr);
	}
	dev->iflink = tunnel->parms.link;
}

static int
ipip_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 ipip_net *ipn = net_generic(net, ipip_net_id);

	switch (cmd) {
	case SIOCGETTUNNEL:
		t = NULL;
		if (dev == ipn->fb_tunnel_dev) {
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
				err = -EFAULT;
				break;
			}
			t = ipip_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_IPIP ||
		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
			goto done;
		if (p.iph.ttl)
			p.iph.frag_off |= htons(IP_DF);

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

		if (dev != ipn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
			if (t != NULL) {
				if (t->dev != dev) {
					err = -EEXIST;
					break;
				}
			} else {
				if (((dev->flags&IFF_POINTOPOINT) && !p.iph.daddr) ||
				    (!(dev->flags&IFF_POINTOPOINT) && p.iph.daddr)) {
					err = -EINVAL;
					break;
				}
				t = netdev_priv(dev);
				ipip_tunnel_unlink(ipn, t);
				synchronize_net();
				t->parms.iph.saddr = p.iph.saddr;
				t->parms.iph.daddr = p.iph.daddr;
				memcpy(dev->dev_addr, &p.iph.saddr, 4);
				memcpy(dev->broadcast, &p.iph.daddr, 4);
				ipip_tunnel_link(ipn, 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;
					ipip_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 == ipn->fb_tunnel_dev) {
			err = -EFAULT;
			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
				goto done;
			err = -ENOENT;
			if ((t = ipip_tunnel_locate(net, &p, 0)) == NULL)
				goto done;
			err = -EPERM;
			if (t->dev == ipn->fb_tunnel_dev)
				goto done;
			dev = t->dev;
		}
		unregister_netdevice(dev);
		err = 0;
		break;

	default:
		err = -EINVAL;
	}

done:
	return err;
}

static int ipip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu < 68 || new_mtu > 0xFFF8 - sizeof(struct iphdr))
		return -EINVAL;
	dev->mtu = new_mtu;
	return 0;
}

static const struct net_device_ops ipip_netdev_ops = {
	.ndo_uninit	= ipip_tunnel_uninit,
	.ndo_start_xmit	= ipip_tunnel_xmit,
	.ndo_do_ioctl	= ipip_tunnel_ioctl,
	.ndo_change_mtu	= ipip_tunnel_change_mtu,
	.ndo_get_stats64 = ipip_get_stats64,
};

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

static void ipip_tunnel_setup(struct net_device *dev)
{
	dev->netdev_ops		= &ipip_netdev_ops;
	dev->destructor		= ipip_dev_free;

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

static int ipip_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);

	tunnel->dev = dev;

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

	ipip_tunnel_bind_dev(dev);

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

	return 0;
}

static int __net_init ipip_fb_tunnel_init(struct net_device *dev)
{
	struct ip_tunnel *tunnel = netdev_priv(dev);
	struct iphdr *iph = &tunnel->parms.iph;
	struct ipip_net *ipn = net_generic(dev_net(dev), ipip_net_id);

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

	iph->version		= 4;
	iph->protocol		= IPPROTO_IPIP;
	iph->ihl		= 5;

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

	dev_hold(dev);
	rcu_assign_pointer(ipn->tunnels_wc[0], tunnel);
	return 0;
}

static struct xfrm_tunnel ipip_handler __read_mostly = {
	.handler	=	ipip_rcv,
	.err_handler	=	ipip_err,
	.priority	=	1,
};

static const char banner[] __initconst =
	KERN_INFO "IPv4 over IPv4 tunneling driver\n";

static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
{
	int prio;

	for (prio = 1; prio < 4; prio++) {
		int h;
		for (h = 0; h < HASH_SIZE; h++) {
			struct ip_tunnel *t;

			t = rtnl_dereference(ipn->tunnels[prio][h]);
			while (t != NULL) {
				unregister_netdevice_queue(t->dev, head);
				t = rtnl_dereference(t->next);
			}
		}
	}
}

static int __net_init ipip_init_net(struct net *net)
{
	struct ipip_net *ipn = net_generic(net, ipip_net_id);
	struct ip_tunnel *t;
	int err;

	ipn->tunnels[0] = ipn->tunnels_wc;
	ipn->tunnels[1] = ipn->tunnels_l;
	ipn->tunnels[2] = ipn->tunnels_r;
	ipn->tunnels[3] = ipn->tunnels_r_l;

	ipn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel),
					   "tunl0",
					   ipip_tunnel_setup);
	if (!ipn->fb_tunnel_dev) {
		err = -ENOMEM;
		goto err_alloc_dev;
	}
	dev_net_set(ipn->fb_tunnel_dev, net);

	err = ipip_fb_tunnel_init(ipn->fb_tunnel_dev);
	if (err)
		goto err_reg_dev;

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

	t = netdev_priv(ipn->fb_tunnel_dev);

	strcpy(t->parms.name, ipn->fb_tunnel_dev->name);
	return 0;

err_reg_dev:
	ipip_dev_free(ipn->fb_tunnel_dev);
err_alloc_dev:
	/* nothing */
	return err;
}

static void __net_exit ipip_exit_net(struct net *net)
{
	struct ipip_net *ipn = net_generic(net, ipip_net_id);
	LIST_HEAD(list);

	rtnl_lock();
	ipip_destroy_tunnels(ipn, &list);
	unregister_netdevice_queue(ipn->fb_tunnel_dev, &list);
	unregister_netdevice_many(&list);
	rtnl_unlock();
}

static struct pernet_operations ipip_net_ops = {
	.init = ipip_init_net,
	.exit = ipip_exit_net,
	.id   = &ipip_net_id,
	.size = sizeof(struct ipip_net),
};

static int __init ipip_init(void)
{
	int err;

	printk(banner);

	err = register_pernet_device(&ipip_net_ops);
	if (err < 0)
		return err;
	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
	if (err < 0) {
		unregister_pernet_device(&ipip_net_ops);
		pr_info("%s: can't register tunnel\n", __func__);
	}
	return err;
}

static void __exit ipip_fini(void)
{
	if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET))
		pr_info("%s: can't deregister tunnel\n", __func__);

	unregister_pernet_device(&ipip_net_ops);
}

module_init(ipip_init);
module_exit(ipip_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NETDEV("tunl0");