forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
sit.c
1970 lines (1667 loc) · 45.7 KB
/
sit.c
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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* IPv6 over IPv4 tunnel device - Simple Internet Transition (SIT)
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <[email protected]>
* Alexey Kuznetsov <[email protected]>
*
* Changes:
* Roger Venning <[email protected]>: 6to4 support
* Nate Thompson <[email protected]>: 6to4 support
* Fred Templin <[email protected]>: isatap support
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmp.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/init.h>
#include <linux/netfilter_ipv4.h>
#include <linux/if_ether.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/icmp.h>
#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/dsfield.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
/*
This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c
For comments look at net/ipv4/ip_gre.c --ANK
*/
#define IP6_SIT_HASH_SIZE 16
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static int ipip6_tunnel_init(struct net_device *dev);
static void ipip6_tunnel_setup(struct net_device *dev);
static void ipip6_dev_free(struct net_device *dev);
static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst,
__be32 *v4dst);
static struct rtnl_link_ops sit_link_ops __read_mostly;
static unsigned int sit_net_id __read_mostly;
struct sit_net {
struct ip_tunnel __rcu *tunnels_r_l[IP6_SIT_HASH_SIZE];
struct ip_tunnel __rcu *tunnels_r[IP6_SIT_HASH_SIZE];
struct ip_tunnel __rcu *tunnels_l[IP6_SIT_HASH_SIZE];
struct ip_tunnel __rcu *tunnels_wc[1];
struct ip_tunnel __rcu **tunnels[4];
struct net_device *fb_tunnel_dev;
};
/*
* Must be invoked with rcu_read_lock
*/
static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net,
struct net_device *dev,
__be32 remote, __be32 local,
int sifindex)
{
unsigned int h0 = HASH(remote);
unsigned int h1 = HASH(local);
struct ip_tunnel *t;
struct sit_net *sitn = net_generic(net, sit_net_id);
int ifindex = dev ? dev->ifindex : 0;
for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
(!dev || !t->parms.link || ifindex == t->parms.link ||
sifindex == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) {
if (remote == t->parms.iph.daddr &&
(!dev || !t->parms.link || ifindex == t->parms.link ||
sifindex == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) {
if (local == t->parms.iph.saddr &&
(!dev || !t->parms.link || ifindex == t->parms.link ||
sifindex == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
t = rcu_dereference(sitn->tunnels_wc[0]);
if (t && (t->dev->flags & IFF_UP))
return t;
return NULL;
}
static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn,
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 &sitn->tunnels[prio][h];
}
static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn,
struct ip_tunnel *t)
{
return __ipip6_bucket(sitn, &t->parms);
}
static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t)
{
struct ip_tunnel __rcu **tp;
struct ip_tunnel *iter;
for (tp = ipip6_bucket(sitn, t);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
if (t == iter) {
rcu_assign_pointer(*tp, t->next);
break;
}
}
}
static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
{
struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t);
rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
{
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel *t = netdev_priv(dev);
if (dev == sitn->fb_tunnel_dev || !sitn->fb_tunnel_dev) {
ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
t->ip6rd.relay_prefix = 0;
t->ip6rd.prefixlen = 16;
t->ip6rd.relay_prefixlen = 0;
} else {
struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev);
memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd));
}
#endif
}
static int ipip6_tunnel_create(struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct sit_net *sitn = net_generic(net, sit_net_id);
int err;
memcpy(dev->dev_addr, &t->parms.iph.saddr, 4);
memcpy(dev->broadcast, &t->parms.iph.daddr, 4);
if ((__force u16)t->parms.i_flags & SIT_ISATAP)
dev->priv_flags |= IFF_ISATAP;
dev->rtnl_link_ops = &sit_link_ops;
err = register_netdevice(dev);
if (err < 0)
goto out;
ipip6_tunnel_clone_6rd(dev, sitn);
dev_hold(dev);
ipip6_tunnel_link(sitn, t);
return 0;
out:
return err;
}
static struct ip_tunnel *ipip6_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 sit_net *sitn = net_generic(net, sit_net_id);
for (tp = __ipip6_bucket(sitn, parms);
(t = rtnl_dereference(*tp)) != NULL;
tp = &t->next) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
parms->link == t->parms.link) {
if (create)
return NULL;
else
return t;
}
}
if (!create)
goto failed;
if (parms->name[0]) {
if (!dev_valid_name(parms->name))
goto failed;
strlcpy(name, parms->name, IFNAMSIZ);
} else {
strcpy(name, "sit%d");
}
dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
ipip6_tunnel_setup);
if (!dev)
return NULL;
dev_net_set(dev, net);
nt = netdev_priv(dev);
nt->parms = *parms;
if (ipip6_tunnel_create(dev) < 0)
goto failed_free;
return nt;
failed_free:
free_netdev(dev);
failed:
return NULL;
}
#define for_each_prl_rcu(start) \
for (prl = rcu_dereference(start); \
prl; \
prl = rcu_dereference(prl->next))
static struct ip_tunnel_prl_entry *
__ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr)
{
struct ip_tunnel_prl_entry *prl;
for_each_prl_rcu(t->prl)
if (prl->addr == addr)
break;
return prl;
}
static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
struct ip_tunnel_prl __user *a)
{
struct ip_tunnel_prl kprl, *kp;
struct ip_tunnel_prl_entry *prl;
unsigned int cmax, c = 0, ca, len;
int ret = 0;
if (copy_from_user(&kprl, a, sizeof(kprl)))
return -EFAULT;
cmax = kprl.datalen / sizeof(kprl);
if (cmax > 1 && kprl.addr != htonl(INADDR_ANY))
cmax = 1;
/* For simple GET or for root users,
* we try harder to allocate.
*/
kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ?
kcalloc(cmax, sizeof(*kp), GFP_KERNEL | __GFP_NOWARN) :
NULL;
rcu_read_lock();
ca = t->prl_count < cmax ? t->prl_count : cmax;
if (!kp) {
/* We don't try hard to allocate much memory for
* non-root users.
* For root users, retry allocating enough memory for
* the answer.
*/
kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC);
if (!kp) {
ret = -ENOMEM;
goto out;
}
}
c = 0;
for_each_prl_rcu(t->prl) {
if (c >= cmax)
break;
if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr)
continue;
kp[c].addr = prl->addr;
kp[c].flags = prl->flags;
c++;
if (kprl.addr != htonl(INADDR_ANY))
break;
}
out:
rcu_read_unlock();
len = sizeof(*kp) * c;
ret = 0;
if ((len && copy_to_user(a + 1, kp, len)) || put_user(len, &a->datalen))
ret = -EFAULT;
kfree(kp);
return ret;
}
static int
ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
{
struct ip_tunnel_prl_entry *p;
int err = 0;
if (a->addr == htonl(INADDR_ANY))
return -EINVAL;
ASSERT_RTNL();
for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) {
if (p->addr == a->addr) {
if (chg) {
p->flags = a->flags;
goto out;
}
err = -EEXIST;
goto out;
}
}
if (chg) {
err = -ENXIO;
goto out;
}
p = kzalloc(sizeof(struct ip_tunnel_prl_entry), GFP_KERNEL);
if (!p) {
err = -ENOBUFS;
goto out;
}
p->next = t->prl;
p->addr = a->addr;
p->flags = a->flags;
t->prl_count++;
rcu_assign_pointer(t->prl, p);
out:
return err;
}
static void prl_list_destroy_rcu(struct rcu_head *head)
{
struct ip_tunnel_prl_entry *p, *n;
p = container_of(head, struct ip_tunnel_prl_entry, rcu_head);
do {
n = rcu_dereference_protected(p->next, 1);
kfree(p);
p = n;
} while (p);
}
static int
ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a)
{
struct ip_tunnel_prl_entry *x;
struct ip_tunnel_prl_entry __rcu **p;
int err = 0;
ASSERT_RTNL();
if (a && a->addr != htonl(INADDR_ANY)) {
for (p = &t->prl;
(x = rtnl_dereference(*p)) != NULL;
p = &x->next) {
if (x->addr == a->addr) {
*p = x->next;
kfree_rcu(x, rcu_head);
t->prl_count--;
goto out;
}
}
err = -ENXIO;
} else {
x = rtnl_dereference(t->prl);
if (x) {
t->prl_count = 0;
call_rcu(&x->rcu_head, prl_list_destroy_rcu);
t->prl = NULL;
}
}
out:
return err;
}
static int
isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t)
{
struct ip_tunnel_prl_entry *p;
int ok = 1;
rcu_read_lock();
p = __ipip6_tunnel_locate_prl(t, iph->saddr);
if (p) {
if (p->flags & PRL_DEFAULT)
skb->ndisc_nodetype = NDISC_NODETYPE_DEFAULT;
else
skb->ndisc_nodetype = NDISC_NODETYPE_NODEFAULT;
} else {
const struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr;
if (ipv6_addr_is_isatap(addr6) &&
(addr6->s6_addr32[3] == iph->saddr) &&
ipv6_chk_prefix(addr6, t->dev))
skb->ndisc_nodetype = NDISC_NODETYPE_HOST;
else
ok = 0;
}
rcu_read_unlock();
return ok;
}
static void ipip6_tunnel_uninit(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct sit_net *sitn = net_generic(tunnel->net, sit_net_id);
if (dev == sitn->fb_tunnel_dev) {
RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL);
} else {
ipip6_tunnel_unlink(sitn, tunnel);
ipip6_tunnel_del_prl(tunnel, NULL);
}
dst_cache_reset(&tunnel->dst_cache);
dev_put(dev);
}
static int ipip6_err(struct sk_buff *skb, u32 info)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
unsigned int data_len = 0;
struct ip_tunnel *t;
int sifindex;
int err;
switch (type) {
default:
case ICMP_PARAMETERPROB:
return 0;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
/* 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;
data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
break;
case ICMP_REDIRECT:
break;
}
err = -ENOENT;
sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0;
t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
iph->daddr, iph->saddr, sifindex);
if (!t)
goto out;
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
t->parms.link, iph->protocol);
err = 0;
goto out;
}
if (type == ICMP_REDIRECT) {
ipv4_redirect(skb, dev_net(skb->dev), t->parms.link,
iph->protocol);
err = 0;
goto out;
}
err = 0;
if (__in6_dev_get(skb->dev) &&
!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
goto out;
if (t->parms.iph.daddr == 0)
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:
return err;
}
static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr,
const struct in6_addr *v6addr)
{
__be32 v4embed = 0;
if (check_6rd(tunnel, v6addr, &v4embed) && v4addr != v4embed)
return true;
return false;
}
/* Checks if an address matches an address on the tunnel interface.
* Used to detect the NAT of proto 41 packets and let them pass spoofing test.
* Long story:
* This function is called after we considered the packet as spoofed
* in is_spoofed_6rd.
* We may have a router that is doing NAT for proto 41 packets
* for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb
* will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd
* function will return true, dropping the packet.
* But, we can still check if is spoofed against the IP
* addresses associated with the interface.
*/
static bool only_dnatted(const struct ip_tunnel *tunnel,
const struct in6_addr *v6dst)
{
int prefix_len;
#ifdef CONFIG_IPV6_SIT_6RD
prefix_len = tunnel->ip6rd.prefixlen + 32
- tunnel->ip6rd.relay_prefixlen;
#else
prefix_len = 48;
#endif
return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev);
}
/* Returns true if a packet is spoofed */
static bool packet_is_spoofed(struct sk_buff *skb,
const struct iphdr *iph,
struct ip_tunnel *tunnel)
{
const struct ipv6hdr *ipv6h;
if (tunnel->dev->priv_flags & IFF_ISATAP) {
if (!isatap_chksrc(skb, iph, tunnel))
return true;
return false;
}
if (tunnel->dev->flags & IFF_POINTOPOINT)
return false;
ipv6h = ipv6_hdr(skb);
if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) {
net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n",
&iph->saddr, &ipv6h->saddr,
&iph->daddr, &ipv6h->daddr);
return true;
}
if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr)))
return false;
if (only_dnatted(tunnel, &ipv6h->daddr))
return false;
net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n",
&iph->saddr, &ipv6h->saddr,
&iph->daddr, &ipv6h->daddr);
return true;
}
static int ipip6_rcv(struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
struct ip_tunnel *tunnel;
int sifindex;
int err;
sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0;
tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
iph->saddr, iph->daddr, sifindex);
if (tunnel) {
struct pcpu_sw_netstats *tstats;
if (tunnel->parms.iph.protocol != IPPROTO_IPV6 &&
tunnel->parms.iph.protocol != 0)
goto out;
skb->mac_header = skb->network_header;
skb_reset_network_header(skb);
IPCB(skb)->flags = 0;
skb->dev = tunnel->dev;
if (packet_is_spoofed(skb, iph, tunnel)) {
tunnel->dev->stats.rx_errors++;
goto out;
}
if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6),
!net_eq(tunnel->net, dev_net(tunnel->dev))))
goto out;
/* skb can be uncloned in iptunnel_pull_header, so
* old iph is no longer valid
*/
iph = (const struct iphdr *)skb_mac_header(skb);
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
if (log_ecn_error)
net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
&iph->saddr, iph->tos);
if (err > 1) {
++tunnel->dev->stats.rx_frame_errors;
++tunnel->dev->stats.rx_errors;
goto out;
}
}
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);
netif_rx(skb);
return 0;
}
/* no tunnel matched, let upstream know, ipsec may handle it */
return 1;
out:
kfree_skb(skb);
return 0;
}
static const struct tnl_ptk_info ipip_tpi = {
/* no tunnel info required for ipip. */
.proto = htons(ETH_P_IP),
};
#if IS_ENABLED(CONFIG_MPLS)
static const struct tnl_ptk_info mplsip_tpi = {
/* no tunnel info required for mplsip. */
.proto = htons(ETH_P_MPLS_UC),
};
#endif
static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
{
const struct iphdr *iph;
struct ip_tunnel *tunnel;
int sifindex;
sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0;
iph = ip_hdr(skb);
tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
iph->saddr, iph->daddr, sifindex);
if (tunnel) {
const struct tnl_ptk_info *tpi;
if (tunnel->parms.iph.protocol != ipproto &&
tunnel->parms.iph.protocol != 0)
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
#if IS_ENABLED(CONFIG_MPLS)
if (ipproto == IPPROTO_MPLS)
tpi = &mplsip_tpi;
else
#endif
tpi = &ipip_tpi;
if (iptunnel_pull_header(skb, 0, tpi->proto, false))
goto drop;
return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error);
}
return 1;
drop:
kfree_skb(skb);
return 0;
}
static int ipip_rcv(struct sk_buff *skb)
{
return sit_tunnel_rcv(skb, IPPROTO_IPIP);
}
#if IS_ENABLED(CONFIG_MPLS)
static int mplsip_rcv(struct sk_buff *skb)
{
return sit_tunnel_rcv(skb, IPPROTO_MPLS);
}
#endif
/*
* If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function
* stores the embedded IPv4 address in v4dst and returns true.
*/
static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst,
__be32 *v4dst)
{
#ifdef CONFIG_IPV6_SIT_6RD
if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix,
tunnel->ip6rd.prefixlen)) {
unsigned int pbw0, pbi0;
int pbi1;
u32 d;
pbw0 = tunnel->ip6rd.prefixlen >> 5;
pbi0 = tunnel->ip6rd.prefixlen & 0x1f;
d = tunnel->ip6rd.relay_prefixlen < 32 ?
(ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >>
tunnel->ip6rd.relay_prefixlen : 0;
pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen;
if (pbi1 > 0)
d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >>
(32 - pbi1);
*v4dst = tunnel->ip6rd.relay_prefix | htonl(d);
return true;
}
#else
if (v6dst->s6_addr16[0] == htons(0x2002)) {
/* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */
memcpy(v4dst, &v6dst->s6_addr16[1], 4);
return true;
}
#endif
return false;
}
static inline __be32 try_6rd(struct ip_tunnel *tunnel,
const struct in6_addr *v6dst)
{
__be32 dst = 0;
check_6rd(tunnel, v6dst, &dst);
return dst;
}
/*
* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
const struct ipv6hdr *iph6 = ipv6_hdr(skb);
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 */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
struct flowi4 fl4;
int mtu;
const struct in6_addr *addr6;
int addr_type;
u8 ttl;
u8 protocol = IPPROTO_IPV6;
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
if (tos == 1)
tos = ipv6_get_dsfield(iph6);
/* ISATAP (RFC4214) - must come before 6to4 */
if (dev->priv_flags & IFF_ISATAP) {
struct neighbour *neigh = NULL;
bool do_tx_error = false;
if (skb_dst(skb))
neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
if (!neigh) {
net_dbg_ratelimited("nexthop == NULL\n");
goto tx_error;
}
addr6 = (const struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if ((addr_type & IPV6_ADDR_UNICAST) &&
ipv6_addr_is_isatap(addr6))
dst = addr6->s6_addr32[3];
else
do_tx_error = true;
neigh_release(neigh);
if (do_tx_error)
goto tx_error;
}
if (!dst)
dst = try_6rd(tunnel, &iph6->daddr);
if (!dst) {
struct neighbour *neigh = NULL;
bool do_tx_error = false;
if (skb_dst(skb))
neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
if (!neigh) {
net_dbg_ratelimited("nexthop == NULL\n");
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)
dst = addr6->s6_addr32[3];
else
do_tx_error = true;
neigh_release(neigh);
if (do_tx_error)
goto tx_error;
}
flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark,
RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6,
0, dst, tiph->saddr, 0, 0,
sock_net_uid(tunnel->net, NULL));
rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr);
if (!rt) {
rt = ip_route_output_flow(tunnel->net, &fl4, NULL);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr);
}
if (rt->rt_type != RTN_UNICAST) {
ip_rt_put(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;
}
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) {
ip_rt_put(rt);
goto tx_error;
}
if (df) {
mtu = dst_mtu(&rt->dst) - t_hlen;
if (mtu < 68) {
dev->stats.collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (mtu < IPV6_MIN_MTU) {
mtu = IPV6_MIN_MTU;
df = 0;
}
if (tunnel->parms.iph.daddr)
skb_dst_update_pmtu(skb, mtu);
if (skb->len > mtu && !skb_is_gso(skb)) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, 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) + t_hlen;
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++;
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;
iph6 = ipv6_hdr(skb);
}
ttl = tiph->ttl;
if (ttl == 0)
ttl = iph6->hop_limit;
tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) {
ip_rt_put(rt);
goto tx_error;
}
skb_set_inner_ipproto(skb, IPPROTO_IPV6);
iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl,
df, !net_eq(tunnel->net, dev_net(dev)));
return NETDEV_TX_OK;