forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
ndisc.c
2059 lines (1786 loc) · 52.3 KB
/
ndisc.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
/*
* Neighbour Discovery for IPv6
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <[email protected]>
* Mike Shaver <[email protected]>
*/
/*
* Changes:
*
* Alexey I. Froloff : RFC6106 (DNSSL) support
* Pierre Ynard : export userland ND options
* through netlink (RDNSS support)
* Lars Fenneberg : fixed MTU setting on receipt
* of an RA.
* Janos Farkas : kmalloc failure checks
* Alexey Kuznetsov : state machine reworked
* and moved to net/core.
* Pekka Savola : RFC2461 validation
* YOSHIFUJI Hideaki @USAGI : Verify ND options properly
*/
#define pr_fmt(fmt) "ICMPv6: " fmt
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/sched.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/route.h>
#include <linux/init.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/if_addr.h>
#include <linux/if_ether.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/jhash.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/icmp.h>
#include <net/netlink.h>
#include <linux/rtnetlink.h>
#include <net/flow.h>
#include <net/ip6_checksum.h>
#include <net/inet_common.h>
#include <linux/proc_fs.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
static u32 ndisc_hash(const void *pkey,
const struct net_device *dev,
__u32 *hash_rnd);
static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey);
static bool ndisc_allow_add(const struct net_device *dev,
struct netlink_ext_ack *extack);
static int ndisc_constructor(struct neighbour *neigh);
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
static int pndisc_constructor(struct pneigh_entry *n);
static void pndisc_destructor(struct pneigh_entry *n);
static void pndisc_redo(struct sk_buff *skb);
static int ndisc_is_multicast(const void *pkey);
static const struct neigh_ops ndisc_generic_ops = {
.family = AF_INET6,
.solicit = ndisc_solicit,
.error_report = ndisc_error_report,
.output = neigh_resolve_output,
.connected_output = neigh_connected_output,
};
static const struct neigh_ops ndisc_hh_ops = {
.family = AF_INET6,
.solicit = ndisc_solicit,
.error_report = ndisc_error_report,
.output = neigh_resolve_output,
.connected_output = neigh_resolve_output,
};
static const struct neigh_ops ndisc_direct_ops = {
.family = AF_INET6,
.output = neigh_direct_output,
.connected_output = neigh_direct_output,
};
struct neigh_table nd_tbl = {
.family = AF_INET6,
.key_len = sizeof(struct in6_addr),
.protocol = cpu_to_be16(ETH_P_IPV6),
.hash = ndisc_hash,
.key_eq = ndisc_key_eq,
.constructor = ndisc_constructor,
.pconstructor = pndisc_constructor,
.pdestructor = pndisc_destructor,
.proxy_redo = pndisc_redo,
.is_multicast = ndisc_is_multicast,
.allow_add = ndisc_allow_add,
.id = "ndisc_cache",
.parms = {
.tbl = &nd_tbl,
.reachable_time = ND_REACHABLE_TIME,
.data = {
[NEIGH_VAR_MCAST_PROBES] = 3,
[NEIGH_VAR_UCAST_PROBES] = 3,
[NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER,
[NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME,
[NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ,
[NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ,
[NEIGH_VAR_GC_STALETIME] = 60 * HZ,
[NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX,
[NEIGH_VAR_PROXY_QLEN] = 64,
[NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ,
[NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10,
},
},
.gc_interval = 30 * HZ,
.gc_thresh1 = 128,
.gc_thresh2 = 512,
.gc_thresh3 = 1024,
};
EXPORT_SYMBOL_GPL(nd_tbl);
void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data,
int data_len, int pad)
{
int space = __ndisc_opt_addr_space(data_len, pad);
u8 *opt = skb_put(skb, space);
opt[0] = type;
opt[1] = space>>3;
memset(opt + 2, 0, pad);
opt += pad;
space -= pad;
memcpy(opt+2, data, data_len);
data_len += 2;
opt += data_len;
space -= data_len;
if (space > 0)
memset(opt, 0, space);
}
EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option);
static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type,
const void *data, u8 icmp6_type)
{
__ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len,
ndisc_addr_option_pad(skb->dev->type));
ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type);
}
static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb,
void *ha,
const u8 *ops_data)
{
ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT);
ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data);
}
static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
struct nd_opt_hdr *end)
{
int type;
if (!cur || !end || cur >= end)
return NULL;
type = cur->nd_opt_type;
do {
cur = ((void *)cur) + (cur->nd_opt_len << 3);
} while (cur < end && cur->nd_opt_type != type);
return cur <= end && cur->nd_opt_type == type ? cur : NULL;
}
static inline int ndisc_is_useropt(const struct net_device *dev,
struct nd_opt_hdr *opt)
{
return opt->nd_opt_type == ND_OPT_PREFIX_INFO ||
opt->nd_opt_type == ND_OPT_RDNSS ||
opt->nd_opt_type == ND_OPT_DNSSL ||
opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL ||
opt->nd_opt_type == ND_OPT_PREF64 ||
ndisc_ops_is_useropt(dev, opt->nd_opt_type);
}
static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev,
struct nd_opt_hdr *cur,
struct nd_opt_hdr *end)
{
if (!cur || !end || cur >= end)
return NULL;
do {
cur = ((void *)cur) + (cur->nd_opt_len << 3);
} while (cur < end && !ndisc_is_useropt(dev, cur));
return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL;
}
struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
u8 *opt, int opt_len,
struct ndisc_options *ndopts)
{
struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt;
if (!nd_opt || opt_len < 0 || !ndopts)
return NULL;
memset(ndopts, 0, sizeof(*ndopts));
while (opt_len) {
int l;
if (opt_len < sizeof(struct nd_opt_hdr))
return NULL;
l = nd_opt->nd_opt_len << 3;
if (opt_len < l || l == 0)
return NULL;
if (ndisc_ops_parse_options(dev, nd_opt, ndopts))
goto next_opt;
switch (nd_opt->nd_opt_type) {
case ND_OPT_SOURCE_LL_ADDR:
case ND_OPT_TARGET_LL_ADDR:
case ND_OPT_MTU:
case ND_OPT_NONCE:
case ND_OPT_REDIRECT_HDR:
if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) {
ND_PRINTK(2, warn,
"%s: duplicated ND6 option found: type=%d\n",
__func__, nd_opt->nd_opt_type);
} else {
ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
}
break;
case ND_OPT_PREFIX_INFO:
ndopts->nd_opts_pi_end = nd_opt;
if (!ndopts->nd_opt_array[nd_opt->nd_opt_type])
ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
break;
#ifdef CONFIG_IPV6_ROUTE_INFO
case ND_OPT_ROUTE_INFO:
ndopts->nd_opts_ri_end = nd_opt;
if (!ndopts->nd_opts_ri)
ndopts->nd_opts_ri = nd_opt;
break;
#endif
default:
if (ndisc_is_useropt(dev, nd_opt)) {
ndopts->nd_useropts_end = nd_opt;
if (!ndopts->nd_useropts)
ndopts->nd_useropts = nd_opt;
} else {
/*
* Unknown options must be silently ignored,
* to accommodate future extension to the
* protocol.
*/
ND_PRINTK(2, notice,
"%s: ignored unsupported option; type=%d, len=%d\n",
__func__,
nd_opt->nd_opt_type,
nd_opt->nd_opt_len);
}
}
next_opt:
opt_len -= l;
nd_opt = ((void *)nd_opt) + l;
}
return ndopts;
}
int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir)
{
switch (dev->type) {
case ARPHRD_ETHER:
case ARPHRD_IEEE802: /* Not sure. Check it later. --ANK */
case ARPHRD_FDDI:
ipv6_eth_mc_map(addr, buf);
return 0;
case ARPHRD_ARCNET:
ipv6_arcnet_mc_map(addr, buf);
return 0;
case ARPHRD_INFINIBAND:
ipv6_ib_mc_map(addr, dev->broadcast, buf);
return 0;
case ARPHRD_IPGRE:
return ipv6_ipgre_mc_map(addr, dev->broadcast, buf);
default:
if (dir) {
memcpy(buf, dev->broadcast, dev->addr_len);
return 0;
}
}
return -EINVAL;
}
EXPORT_SYMBOL(ndisc_mc_map);
static u32 ndisc_hash(const void *pkey,
const struct net_device *dev,
__u32 *hash_rnd)
{
return ndisc_hashfn(pkey, dev, hash_rnd);
}
static bool ndisc_key_eq(const struct neighbour *n, const void *pkey)
{
return neigh_key_eq128(n, pkey);
}
static int ndisc_constructor(struct neighbour *neigh)
{
struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key;
struct net_device *dev = neigh->dev;
struct inet6_dev *in6_dev;
struct neigh_parms *parms;
bool is_multicast = ipv6_addr_is_multicast(addr);
in6_dev = in6_dev_get(dev);
if (!in6_dev) {
return -EINVAL;
}
parms = in6_dev->nd_parms;
__neigh_parms_put(neigh->parms);
neigh->parms = neigh_parms_clone(parms);
neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST;
if (!dev->header_ops) {
neigh->nud_state = NUD_NOARP;
neigh->ops = &ndisc_direct_ops;
neigh->output = neigh_direct_output;
} else {
if (is_multicast) {
neigh->nud_state = NUD_NOARP;
ndisc_mc_map(addr, neigh->ha, dev, 1);
} else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) {
neigh->nud_state = NUD_NOARP;
memcpy(neigh->ha, dev->dev_addr, dev->addr_len);
if (dev->flags&IFF_LOOPBACK)
neigh->type = RTN_LOCAL;
} else if (dev->flags&IFF_POINTOPOINT) {
neigh->nud_state = NUD_NOARP;
memcpy(neigh->ha, dev->broadcast, dev->addr_len);
}
if (dev->header_ops->cache)
neigh->ops = &ndisc_hh_ops;
else
neigh->ops = &ndisc_generic_ops;
if (neigh->nud_state&NUD_VALID)
neigh->output = neigh->ops->connected_output;
else
neigh->output = neigh->ops->output;
}
in6_dev_put(in6_dev);
return 0;
}
static int pndisc_constructor(struct pneigh_entry *n)
{
struct in6_addr *addr = (struct in6_addr *)&n->key;
struct in6_addr maddr;
struct net_device *dev = n->dev;
if (!dev || !__in6_dev_get(dev))
return -EINVAL;
addrconf_addr_solict_mult(addr, &maddr);
ipv6_dev_mc_inc(dev, &maddr);
return 0;
}
static void pndisc_destructor(struct pneigh_entry *n)
{
struct in6_addr *addr = (struct in6_addr *)&n->key;
struct in6_addr maddr;
struct net_device *dev = n->dev;
if (!dev || !__in6_dev_get(dev))
return;
addrconf_addr_solict_mult(addr, &maddr);
ipv6_dev_mc_dec(dev, &maddr);
}
/* called with rtnl held */
static bool ndisc_allow_add(const struct net_device *dev,
struct netlink_ext_ack *extack)
{
struct inet6_dev *idev = __in6_dev_get(dev);
if (!idev || idev->cnf.disable_ipv6) {
NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device");
return false;
}
return true;
}
static struct sk_buff *ndisc_alloc_skb(struct net_device *dev,
int len)
{
int hlen = LL_RESERVED_SPACE(dev);
int tlen = dev->needed_tailroom;
struct sock *sk = dev_net(dev)->ipv6.ndisc_sk;
struct sk_buff *skb;
skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC);
if (!skb) {
ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n",
__func__);
return NULL;
}
skb->protocol = htons(ETH_P_IPV6);
skb->dev = dev;
skb_reserve(skb, hlen + sizeof(struct ipv6hdr));
skb_reset_transport_header(skb);
/* Manually assign socket ownership as we avoid calling
* sock_alloc_send_pskb() to bypass wmem buffer limits
*/
skb_set_owner_w(skb, sk);
return skb;
}
static void ip6_nd_hdr(struct sk_buff *skb,
const struct in6_addr *saddr,
const struct in6_addr *daddr,
int hop_limit, int len)
{
struct ipv6hdr *hdr;
struct inet6_dev *idev;
unsigned tclass;
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
tclass = idev ? idev->cnf.ndisc_tclass : 0;
rcu_read_unlock();
skb_push(skb, sizeof(*hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
ip6_flow_hdr(hdr, tclass, 0);
hdr->payload_len = htons(len);
hdr->nexthdr = IPPROTO_ICMPV6;
hdr->hop_limit = hop_limit;
hdr->saddr = *saddr;
hdr->daddr = *daddr;
}
void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
struct dst_entry *dst = skb_dst(skb);
struct net *net = dev_net(skb->dev);
struct sock *sk = net->ipv6.ndisc_sk;
struct inet6_dev *idev;
int err;
struct icmp6hdr *icmp6h = icmp6_hdr(skb);
u8 type;
type = icmp6h->icmp6_type;
if (!dst) {
struct flowi6 fl6;
int oif = skb->dev->ifindex;
icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif);
dst = icmp6_dst_alloc(skb->dev, &fl6);
if (IS_ERR(dst)) {
kfree_skb(skb);
return;
}
skb_dst_set(skb, dst);
}
icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, skb->len,
IPPROTO_ICMPV6,
csum_partial(icmp6h,
skb->len, 0));
ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len);
rcu_read_lock();
idev = __in6_dev_get(dst->dev);
IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS);
err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
net, sk, skb, NULL, dst->dev,
dst_output);
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, type);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
}
rcu_read_unlock();
}
EXPORT_SYMBOL(ndisc_send_skb);
void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
const struct in6_addr *solicited_addr,
bool router, bool solicited, bool override, bool inc_opt)
{
struct sk_buff *skb;
struct in6_addr tmpaddr;
struct inet6_ifaddr *ifp;
const struct in6_addr *src_addr;
struct nd_msg *msg;
int optlen = 0;
/* for anycast or proxy, solicited_addr != src_addr */
ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1);
if (ifp) {
src_addr = solicited_addr;
if (ifp->flags & IFA_F_OPTIMISTIC)
override = false;
inc_opt |= ifp->idev->cnf.force_tllao;
in6_ifa_put(ifp);
} else {
if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr,
inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs,
&tmpaddr))
return;
src_addr = &tmpaddr;
}
if (!dev->addr_len)
inc_opt = false;
if (inc_opt)
optlen += ndisc_opt_addr_space(dev,
NDISC_NEIGHBOUR_ADVERTISEMENT);
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
return;
msg = skb_put(skb, sizeof(*msg));
*msg = (struct nd_msg) {
.icmph = {
.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT,
.icmp6_router = router,
.icmp6_solicited = solicited,
.icmp6_override = override,
},
.target = *solicited_addr,
};
if (inc_opt)
ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR,
dev->dev_addr,
NDISC_NEIGHBOUR_ADVERTISEMENT);
ndisc_send_skb(skb, daddr, src_addr);
}
static void ndisc_send_unsol_na(struct net_device *dev)
{
struct inet6_dev *idev;
struct inet6_ifaddr *ifa;
idev = in6_dev_get(dev);
if (!idev)
return;
read_lock_bh(&idev->lock);
list_for_each_entry(ifa, &idev->addr_list, if_list) {
/* skip tentative addresses until dad completes */
if (ifa->flags & IFA_F_TENTATIVE &&
!(ifa->flags & IFA_F_OPTIMISTIC))
continue;
ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr,
/*router=*/ !!idev->cnf.forwarding,
/*solicited=*/ false, /*override=*/ true,
/*inc_opt=*/ true);
}
read_unlock_bh(&idev->lock);
in6_dev_put(idev);
}
struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit,
const struct in6_addr *saddr, u64 nonce)
{
int inc_opt = dev->addr_len;
struct sk_buff *skb;
struct nd_msg *msg;
int optlen = 0;
if (!saddr)
return NULL;
if (ipv6_addr_any(saddr))
inc_opt = false;
if (inc_opt)
optlen += ndisc_opt_addr_space(dev,
NDISC_NEIGHBOUR_SOLICITATION);
if (nonce != 0)
optlen += 8;
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
return NULL;
msg = skb_put(skb, sizeof(*msg));
*msg = (struct nd_msg) {
.icmph = {
.icmp6_type = NDISC_NEIGHBOUR_SOLICITATION,
},
.target = *solicit,
};
if (inc_opt)
ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
dev->dev_addr,
NDISC_NEIGHBOUR_SOLICITATION);
if (nonce != 0) {
u8 *opt = skb_put(skb, 8);
opt[0] = ND_OPT_NONCE;
opt[1] = 8 >> 3;
memcpy(opt + 2, &nonce, 6);
}
return skb;
}
EXPORT_SYMBOL(ndisc_ns_create);
void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
const struct in6_addr *daddr, const struct in6_addr *saddr,
u64 nonce)
{
struct in6_addr addr_buf;
struct sk_buff *skb;
if (!saddr) {
if (ipv6_get_lladdr(dev, &addr_buf,
(IFA_F_TENTATIVE | IFA_F_OPTIMISTIC)))
return;
saddr = &addr_buf;
}
skb = ndisc_ns_create(dev, solicit, saddr, nonce);
if (skb)
ndisc_send_skb(skb, daddr, saddr);
}
void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
const struct in6_addr *daddr)
{
struct sk_buff *skb;
struct rs_msg *msg;
int send_sllao = dev->addr_len;
int optlen = 0;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* According to section 2.2 of RFC 4429, we must not
* send router solicitations with a sllao from
* optimistic addresses, but we may send the solicitation
* if we don't include the sllao. So here we check
* if our address is optimistic, and if so, we
* suppress the inclusion of the sllao.
*/
if (send_sllao) {
struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr,
dev, 1);
if (ifp) {
if (ifp->flags & IFA_F_OPTIMISTIC) {
send_sllao = 0;
}
in6_ifa_put(ifp);
} else {
send_sllao = 0;
}
}
#endif
if (send_sllao)
optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION);
skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
if (!skb)
return;
msg = skb_put(skb, sizeof(*msg));
*msg = (struct rs_msg) {
.icmph = {
.icmp6_type = NDISC_ROUTER_SOLICITATION,
},
};
if (send_sllao)
ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
dev->dev_addr,
NDISC_ROUTER_SOLICITATION);
ndisc_send_skb(skb, daddr, saddr);
}
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb)
{
/*
* "The sender MUST return an ICMP
* destination unreachable"
*/
dst_link_failure(skb);
kfree_skb(skb);
}
/* Called with locked neigh: either read or both */
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
{
struct in6_addr *saddr = NULL;
struct in6_addr mcaddr;
struct net_device *dev = neigh->dev;
struct in6_addr *target = (struct in6_addr *)&neigh->primary_key;
int probes = atomic_read(&neigh->probes);
if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr,
dev, false, 1,
IFA_F_TENTATIVE|IFA_F_OPTIMISTIC))
saddr = &ipv6_hdr(skb)->saddr;
probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES);
if (probes < 0) {
if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) {
ND_PRINTK(1, dbg,
"%s: trying to ucast probe in NUD_INVALID: %pI6\n",
__func__, target);
}
ndisc_send_ns(dev, target, target, saddr, 0);
} else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) {
neigh_app_ns(neigh);
} else {
addrconf_addr_solict_mult(target, &mcaddr);
ndisc_send_ns(dev, target, &mcaddr, saddr, 0);
}
}
static int pndisc_is_router(const void *pkey,
struct net_device *dev)
{
struct pneigh_entry *n;
int ret = -1;
read_lock_bh(&nd_tbl.lock);
n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev);
if (n)
ret = !!(n->flags & NTF_ROUTER);
read_unlock_bh(&nd_tbl.lock);
return ret;
}
void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
struct ndisc_options *ndopts)
{
neigh_update(neigh, lladdr, new, flags, 0);
/* report ndisc ops about neighbour update */
ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts);
}
static enum skb_drop_reason ndisc_recv_ns(struct sk_buff *skb)
{
struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
u8 *lladdr = NULL;
u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
offsetof(struct nd_msg, opt));
struct ndisc_options ndopts;
struct net_device *dev = skb->dev;
struct inet6_ifaddr *ifp;
struct inet6_dev *idev = NULL;
struct neighbour *neigh;
int dad = ipv6_addr_any(saddr);
int is_router = -1;
SKB_DR(reason);
u64 nonce = 0;
bool inc;
if (skb->len < sizeof(struct nd_msg))
return SKB_DROP_REASON_PKT_TOO_SMALL;
if (ipv6_addr_is_multicast(&msg->target)) {
ND_PRINTK(2, warn, "NS: multicast target address\n");
return reason;
}
/*
* RFC2461 7.1.1:
* DAD has to be destined for solicited node multicast address.
*/
if (dad && !ipv6_addr_is_solict_mult(daddr)) {
ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n");
return reason;
}
if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts))
return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
if (ndopts.nd_opts_src_lladdr) {
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev);
if (!lladdr) {
ND_PRINTK(2, warn,
"NS: invalid link-layer address length\n");
return reason;
}
/* RFC2461 7.1.1:
* If the IP source address is the unspecified address,
* there MUST NOT be source link-layer address option
* in the message.
*/
if (dad) {
ND_PRINTK(2, warn,
"NS: bad DAD packet (link-layer address option)\n");
return reason;
}
}
if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1)
memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6);
inc = ipv6_addr_is_multicast(daddr);
ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1);
if (ifp) {
have_ifp:
if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) {
if (dad) {
if (nonce != 0 && ifp->dad_nonce == nonce) {
u8 *np = (u8 *)&nonce;
/* Matching nonce if looped back */
ND_PRINTK(2, notice,
"%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n",
ifp->idev->dev->name,
&ifp->addr, np);
goto out;
}
/*
* We are colliding with another node
* who is doing DAD
* so fail our DAD process
*/
addrconf_dad_failure(skb, ifp);
return reason;
} else {
/*
* This is not a dad solicitation.
* If we are an optimistic node,
* we should respond.
* Otherwise, we should ignore it.
*/
if (!(ifp->flags & IFA_F_OPTIMISTIC))
goto out;
}
}
idev = ifp->idev;
} else {
struct net *net = dev_net(dev);
/* perhaps an address on the master device */
if (netif_is_l3_slave(dev)) {
struct net_device *mdev;
mdev = netdev_master_upper_dev_get_rcu(dev);
if (mdev) {
ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1);
if (ifp)
goto have_ifp;
}
}
idev = in6_dev_get(dev);
if (!idev) {
/* XXX: count this drop? */
return reason;
}
if (ipv6_chk_acast_addr(net, dev, &msg->target) ||
(idev->cnf.forwarding &&
(net->ipv6.devconf_all->proxy_ndp || idev->cnf.proxy_ndp) &&
(is_router = pndisc_is_router(&msg->target, dev)) >= 0)) {
if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) &&
skb->pkt_type != PACKET_HOST &&
inc &&
NEIGH_VAR(idev->nd_parms, PROXY_DELAY) != 0) {
/*
* for anycast or proxy,
* sender should delay its response
* by a random time between 0 and
* MAX_ANYCAST_DELAY_TIME seconds.
* (RFC2461) -- yoshfuji
*/
struct sk_buff *n = skb_clone(skb, GFP_ATOMIC);
if (n)
pneigh_enqueue(&nd_tbl, idev->nd_parms, n);
goto out;
}
} else {
SKB_DR_SET(reason, IPV6_NDISC_NS_OTHERHOST);
goto out;
}
}
if (is_router < 0)
is_router = idev->cnf.forwarding;
if (dad) {
ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target,
!!is_router, false, (ifp != NULL), true);
goto out;
}
if (inc)
NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_mcast);
else
NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_ucast);
/*
* update / create cache entry
* for the source address
*/
neigh = __neigh_lookup(&nd_tbl, saddr, dev,
!inc || lladdr || !dev->addr_len);
if (neigh)
ndisc_update(dev, neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE,
NDISC_NEIGHBOUR_SOLICITATION, &ndopts);
if (neigh || !dev->header_ops) {
ndisc_send_na(dev, saddr, &msg->target, !!is_router,
true, (ifp != NULL && inc), inc);
if (neigh)
neigh_release(neigh);
reason = SKB_CONSUMED;
}
out:
if (ifp)
in6_ifa_put(ifp);
else
in6_dev_put(idev);
return reason;
}
static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr)
{
struct inet6_dev *idev = __in6_dev_get(dev);
switch (idev->cnf.accept_untracked_na) {
case 0: /* Don't accept untracked na (absent in neighbor cache) */
return 0;
case 1: /* Create new entries from na if currently untracked */
return 1;
case 2: /* Create new entries from untracked na only if saddr is in the
* same subnet as an address configured on the interface that
* received the na
*/
return !!ipv6_chk_prefix(saddr, dev);
default:
return 0;
}
}
static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb)
{
struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
u8 *lladdr = NULL;
u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
offsetof(struct nd_msg, opt));
struct ndisc_options ndopts;
struct net_device *dev = skb->dev;