forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
ip6mr.c
2636 lines (2235 loc) · 62.7 KB
/
ip6mr.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
/*
* Linux IPv6 multicast routing support for BSD pim6sd
* Based on net/ipv4/ipmr.c.
*
* (c) 2004 Mickael Hoerdt, <[email protected]>
* LSIIT Laboratory, Strasbourg, France
* (c) 2004 Jean-Philippe Andriot, <[email protected]>
* 6WIND, Paris, France
* Copyright (C)2007,2008 USAGI/WIDE Project
* YOSHIFUJI Hideaki <[email protected]>
*/
#include <linux/uaccess.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/kernel.h>
#include <linux/fcntl.h>
#include <linux/stat.h>
#include <linux/socket.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/compat.h>
#include <linux/rhashtable.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/raw.h>
#include <linux/notifier.h>
#include <linux/if_arp.h>
#include <net/checksum.h>
#include <net/netlink.h>
#include <net/fib_rules.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <linux/mroute6.h>
#include <linux/pim.h>
#include <net/addrconf.h>
#include <linux/netfilter_ipv6.h>
#include <linux/export.h>
#include <net/ip6_checksum.h>
#include <linux/netconf.h>
#include <net/ip_tunnels.h>
#include <linux/nospec.h>
struct ip6mr_rule {
struct fib_rule common;
};
struct ip6mr_result {
struct mr_table *mrt;
};
/* Big lock, protecting vif table, mrt cache and mroute socket state.
Note that the changes are semaphored via rtnl_lock.
*/
static DEFINE_SPINLOCK(mrt_lock);
static struct net_device *vif_dev_read(const struct vif_device *vif)
{
return rcu_dereference(vif->dev);
}
/* Multicast router control variables */
/* Special spinlock for queue of unresolved entries */
static DEFINE_SPINLOCK(mfc_unres_lock);
/* We return to original Alan's scheme. Hash table of resolved
entries is changed only in process context and protected
with weak lock mrt_lock. Queue of unresolved entries is protected
with strong spinlock mfc_unres_lock.
In this case data path is free of exclusive locks at all.
*/
static struct kmem_cache *mrt_cachep __read_mostly;
static struct mr_table *ip6mr_new_table(struct net *net, u32 id);
static void ip6mr_free_table(struct mr_table *mrt);
static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
struct net_device *dev, struct sk_buff *skb,
struct mfc6_cache *cache);
static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt,
mifi_t mifi, int assert);
static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc,
int cmd);
static void mrt6msg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt);
static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack);
static int ip6mr_rtm_dumproute(struct sk_buff *skb,
struct netlink_callback *cb);
static void mroute_clean_tables(struct mr_table *mrt, int flags);
static void ipmr_expire_process(struct timer_list *t);
#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
#define ip6mr_for_each_table(mrt, net) \
list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list, \
lockdep_rtnl_is_held() || \
list_empty(&net->ipv6.mr6_tables))
static struct mr_table *ip6mr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
struct mr_table *ret;
if (!mrt)
ret = list_entry_rcu(net->ipv6.mr6_tables.next,
struct mr_table, list);
else
ret = list_entry_rcu(mrt->list.next,
struct mr_table, list);
if (&ret->list == &net->ipv6.mr6_tables)
return NULL;
return ret;
}
static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
{
struct mr_table *mrt;
ip6mr_for_each_table(mrt, net) {
if (mrt->id == id)
return mrt;
}
return NULL;
}
static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
struct mr_table **mrt)
{
int err;
struct ip6mr_result res;
struct fib_lookup_arg arg = {
.result = &res,
.flags = FIB_LOOKUP_NOREF,
};
/* update flow if oif or iif point to device enslaved to l3mdev */
l3mdev_update_flow(net, flowi6_to_flowi(flp6));
err = fib_rules_lookup(net->ipv6.mr6_rules_ops,
flowi6_to_flowi(flp6), 0, &arg);
if (err < 0)
return err;
*mrt = res.mrt;
return 0;
}
static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp,
int flags, struct fib_lookup_arg *arg)
{
struct ip6mr_result *res = arg->result;
struct mr_table *mrt;
switch (rule->action) {
case FR_ACT_TO_TBL:
break;
case FR_ACT_UNREACHABLE:
return -ENETUNREACH;
case FR_ACT_PROHIBIT:
return -EACCES;
case FR_ACT_BLACKHOLE:
default:
return -EINVAL;
}
arg->table = fib_rule_get_table(rule, arg);
mrt = ip6mr_get_table(rule->fr_net, arg->table);
if (!mrt)
return -EAGAIN;
res->mrt = mrt;
return 0;
}
static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags)
{
return 1;
}
static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct fib_rule_hdr *frh, struct nlattr **tb,
struct netlink_ext_ack *extack)
{
return 0;
}
static int ip6mr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
struct nlattr **tb)
{
return 1;
}
static int ip6mr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
struct fib_rule_hdr *frh)
{
frh->dst_len = 0;
frh->src_len = 0;
frh->tos = 0;
return 0;
}
static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = {
.family = RTNL_FAMILY_IP6MR,
.rule_size = sizeof(struct ip6mr_rule),
.addr_size = sizeof(struct in6_addr),
.action = ip6mr_rule_action,
.match = ip6mr_rule_match,
.configure = ip6mr_rule_configure,
.compare = ip6mr_rule_compare,
.fill = ip6mr_rule_fill,
.nlgroup = RTNLGRP_IPV6_RULE,
.owner = THIS_MODULE,
};
static int __net_init ip6mr_rules_init(struct net *net)
{
struct fib_rules_ops *ops;
struct mr_table *mrt;
int err;
ops = fib_rules_register(&ip6mr_rules_ops_template, net);
if (IS_ERR(ops))
return PTR_ERR(ops);
INIT_LIST_HEAD(&net->ipv6.mr6_tables);
mrt = ip6mr_new_table(net, RT6_TABLE_DFLT);
if (IS_ERR(mrt)) {
err = PTR_ERR(mrt);
goto err1;
}
err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT, 0);
if (err < 0)
goto err2;
net->ipv6.mr6_rules_ops = ops;
return 0;
err2:
rtnl_lock();
ip6mr_free_table(mrt);
rtnl_unlock();
err1:
fib_rules_unregister(ops);
return err;
}
static void __net_exit ip6mr_rules_exit(struct net *net)
{
struct mr_table *mrt, *next;
ASSERT_RTNL();
list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) {
list_del(&mrt->list);
ip6mr_free_table(mrt);
}
fib_rules_unregister(net->ipv6.mr6_rules_ops);
}
static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb,
struct netlink_ext_ack *extack)
{
return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR, extack);
}
static unsigned int ip6mr_rules_seq_read(struct net *net)
{
return fib_rules_seq_read(net, RTNL_FAMILY_IP6MR);
}
bool ip6mr_rule_default(const struct fib_rule *rule)
{
return fib_rule_matchall(rule) && rule->action == FR_ACT_TO_TBL &&
rule->table == RT6_TABLE_DFLT && !rule->l3mdev;
}
EXPORT_SYMBOL(ip6mr_rule_default);
#else
#define ip6mr_for_each_table(mrt, net) \
for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
static struct mr_table *ip6mr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
if (!mrt)
return net->ipv6.mrt6;
return NULL;
}
static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
{
return net->ipv6.mrt6;
}
static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
struct mr_table **mrt)
{
*mrt = net->ipv6.mrt6;
return 0;
}
static int __net_init ip6mr_rules_init(struct net *net)
{
struct mr_table *mrt;
mrt = ip6mr_new_table(net, RT6_TABLE_DFLT);
if (IS_ERR(mrt))
return PTR_ERR(mrt);
net->ipv6.mrt6 = mrt;
return 0;
}
static void __net_exit ip6mr_rules_exit(struct net *net)
{
ASSERT_RTNL();
ip6mr_free_table(net->ipv6.mrt6);
net->ipv6.mrt6 = NULL;
}
static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb,
struct netlink_ext_ack *extack)
{
return 0;
}
static unsigned int ip6mr_rules_seq_read(struct net *net)
{
return 0;
}
#endif
static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg,
const void *ptr)
{
const struct mfc6_cache_cmp_arg *cmparg = arg->key;
struct mfc6_cache *c = (struct mfc6_cache *)ptr;
return !ipv6_addr_equal(&c->mf6c_mcastgrp, &cmparg->mf6c_mcastgrp) ||
!ipv6_addr_equal(&c->mf6c_origin, &cmparg->mf6c_origin);
}
static const struct rhashtable_params ip6mr_rht_params = {
.head_offset = offsetof(struct mr_mfc, mnode),
.key_offset = offsetof(struct mfc6_cache, cmparg),
.key_len = sizeof(struct mfc6_cache_cmp_arg),
.nelem_hint = 3,
.obj_cmpfn = ip6mr_hash_cmp,
.automatic_shrinking = true,
};
static void ip6mr_new_table_set(struct mr_table *mrt,
struct net *net)
{
#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables);
#endif
}
static struct mfc6_cache_cmp_arg ip6mr_mr_table_ops_cmparg_any = {
.mf6c_origin = IN6ADDR_ANY_INIT,
.mf6c_mcastgrp = IN6ADDR_ANY_INIT,
};
static struct mr_table_ops ip6mr_mr_table_ops = {
.rht_params = &ip6mr_rht_params,
.cmparg_any = &ip6mr_mr_table_ops_cmparg_any,
};
static struct mr_table *ip6mr_new_table(struct net *net, u32 id)
{
struct mr_table *mrt;
mrt = ip6mr_get_table(net, id);
if (mrt)
return mrt;
return mr_table_alloc(net, id, &ip6mr_mr_table_ops,
ipmr_expire_process, ip6mr_new_table_set);
}
static void ip6mr_free_table(struct mr_table *mrt)
{
del_timer_sync(&mrt->ipmr_expire_timer);
mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC |
MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC);
rhltable_destroy(&mrt->mfc_hash);
kfree(mrt);
}
#ifdef CONFIG_PROC_FS
/* The /proc interfaces to multicast routing
* /proc/ip6_mr_cache /proc/ip6_mr_vif
*/
static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
struct mr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
struct mr_table *mrt;
mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
if (!mrt)
return ERR_PTR(-ENOENT);
iter->mrt = mrt;
rcu_read_lock();
return mr_vif_seq_start(seq, pos);
}
static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v)
__releases(RCU)
{
rcu_read_unlock();
}
static int ip6mr_vif_seq_show(struct seq_file *seq, void *v)
{
struct mr_vif_iter *iter = seq->private;
struct mr_table *mrt = iter->mrt;
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
"Interface BytesIn PktsIn BytesOut PktsOut Flags\n");
} else {
const struct vif_device *vif = v;
const struct net_device *vif_dev;
const char *name;
vif_dev = vif_dev_read(vif);
name = vif_dev ? vif_dev->name : "none";
seq_printf(seq,
"%2td %-10s %8ld %7ld %8ld %7ld %05X\n",
vif - mrt->vif_table,
name, vif->bytes_in, vif->pkt_in,
vif->bytes_out, vif->pkt_out,
vif->flags);
}
return 0;
}
static const struct seq_operations ip6mr_vif_seq_ops = {
.start = ip6mr_vif_seq_start,
.next = mr_vif_seq_next,
.stop = ip6mr_vif_seq_stop,
.show = ip6mr_vif_seq_show,
};
static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
{
struct net *net = seq_file_net(seq);
struct mr_table *mrt;
mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
if (!mrt)
return ERR_PTR(-ENOENT);
return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock);
}
static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
{
int n;
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
"Group "
"Origin "
"Iif Pkts Bytes Wrong Oifs\n");
} else {
const struct mfc6_cache *mfc = v;
const struct mr_mfc_iter *it = seq->private;
struct mr_table *mrt = it->mrt;
seq_printf(seq, "%pI6 %pI6 %-3hd",
&mfc->mf6c_mcastgrp, &mfc->mf6c_origin,
mfc->_c.mfc_parent);
if (it->cache != &mrt->mfc_unres_queue) {
seq_printf(seq, " %8lu %8lu %8lu",
mfc->_c.mfc_un.res.pkt,
mfc->_c.mfc_un.res.bytes,
mfc->_c.mfc_un.res.wrong_if);
for (n = mfc->_c.mfc_un.res.minvif;
n < mfc->_c.mfc_un.res.maxvif; n++) {
if (VIF_EXISTS(mrt, n) &&
mfc->_c.mfc_un.res.ttls[n] < 255)
seq_printf(seq,
" %2d:%-3d", n,
mfc->_c.mfc_un.res.ttls[n]);
}
} else {
/* unresolved mfc_caches don't contain
* pkt, bytes and wrong_if values
*/
seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul);
}
seq_putc(seq, '\n');
}
return 0;
}
static const struct seq_operations ipmr_mfc_seq_ops = {
.start = ipmr_mfc_seq_start,
.next = mr_mfc_seq_next,
.stop = mr_mfc_seq_stop,
.show = ipmr_mfc_seq_show,
};
#endif
#ifdef CONFIG_IPV6_PIMSM_V2
static int pim6_rcv(struct sk_buff *skb)
{
struct pimreghdr *pim;
struct ipv6hdr *encap;
struct net_device *reg_dev = NULL;
struct net *net = dev_net(skb->dev);
struct mr_table *mrt;
struct flowi6 fl6 = {
.flowi6_iif = skb->dev->ifindex,
.flowi6_mark = skb->mark,
};
int reg_vif_num;
if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap)))
goto drop;
pim = (struct pimreghdr *)skb_transport_header(skb);
if (pim->type != ((PIM_VERSION << 4) | PIM_TYPE_REGISTER) ||
(pim->flags & PIM_NULL_REGISTER) ||
(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
sizeof(*pim), IPPROTO_PIM,
csum_partial((void *)pim, sizeof(*pim), 0)) &&
csum_fold(skb_checksum(skb, 0, skb->len, 0))))
goto drop;
/* check if the inner packet is destined to mcast group */
encap = (struct ipv6hdr *)(skb_transport_header(skb) +
sizeof(*pim));
if (!ipv6_addr_is_multicast(&encap->daddr) ||
encap->payload_len == 0 ||
ntohs(encap->payload_len) + sizeof(*pim) > skb->len)
goto drop;
if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
goto drop;
/* Pairs with WRITE_ONCE() in mif6_add()/mif6_delete() */
reg_vif_num = READ_ONCE(mrt->mroute_reg_vif_num);
if (reg_vif_num >= 0)
reg_dev = vif_dev_read(&mrt->vif_table[reg_vif_num]);
if (!reg_dev)
goto drop;
skb->mac_header = skb->network_header;
skb_pull(skb, (u8 *)encap - skb->data);
skb_reset_network_header(skb);
skb->protocol = htons(ETH_P_IPV6);
skb->ip_summed = CHECKSUM_NONE;
skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev));
netif_rx(skb);
return 0;
drop:
kfree_skb(skb);
return 0;
}
static const struct inet6_protocol pim6_protocol = {
.handler = pim6_rcv,
};
/* Service routines creating virtual interfaces: PIMREG */
static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct net *net = dev_net(dev);
struct mr_table *mrt;
struct flowi6 fl6 = {
.flowi6_oif = dev->ifindex,
.flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX,
.flowi6_mark = skb->mark,
};
if (!pskb_inet_may_pull(skb))
goto tx_err;
if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
goto tx_err;
dev->stats.tx_bytes += skb->len;
dev->stats.tx_packets++;
rcu_read_lock();
ip6mr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num),
MRT6MSG_WHOLEPKT);
rcu_read_unlock();
kfree_skb(skb);
return NETDEV_TX_OK;
tx_err:
dev->stats.tx_errors++;
kfree_skb(skb);
return NETDEV_TX_OK;
}
static int reg_vif_get_iflink(const struct net_device *dev)
{
return 0;
}
static const struct net_device_ops reg_vif_netdev_ops = {
.ndo_start_xmit = reg_vif_xmit,
.ndo_get_iflink = reg_vif_get_iflink,
};
static void reg_vif_setup(struct net_device *dev)
{
dev->type = ARPHRD_PIMREG;
dev->mtu = 1500 - sizeof(struct ipv6hdr) - 8;
dev->flags = IFF_NOARP;
dev->netdev_ops = ®_vif_netdev_ops;
dev->needs_free_netdev = true;
dev->features |= NETIF_F_NETNS_LOCAL;
}
static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt)
{
struct net_device *dev;
char name[IFNAMSIZ];
if (mrt->id == RT6_TABLE_DFLT)
sprintf(name, "pim6reg");
else
sprintf(name, "pim6reg%u", mrt->id);
dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup);
if (!dev)
return NULL;
dev_net_set(dev, net);
if (register_netdevice(dev)) {
free_netdev(dev);
return NULL;
}
if (dev_open(dev, NULL))
goto failure;
dev_hold(dev);
return dev;
failure:
unregister_netdevice(dev);
return NULL;
}
#endif
static int call_ip6mr_vif_entry_notifiers(struct net *net,
enum fib_event_type event_type,
struct vif_device *vif,
struct net_device *vif_dev,
mifi_t vif_index, u32 tb_id)
{
return mr_call_vif_notifiers(net, RTNL_FAMILY_IP6MR, event_type,
vif, vif_dev, vif_index, tb_id,
&net->ipv6.ipmr_seq);
}
static int call_ip6mr_mfc_entry_notifiers(struct net *net,
enum fib_event_type event_type,
struct mfc6_cache *mfc, u32 tb_id)
{
return mr_call_mfc_notifiers(net, RTNL_FAMILY_IP6MR, event_type,
&mfc->_c, tb_id, &net->ipv6.ipmr_seq);
}
/* Delete a VIF entry */
static int mif6_delete(struct mr_table *mrt, int vifi, int notify,
struct list_head *head)
{
struct vif_device *v;
struct net_device *dev;
struct inet6_dev *in6_dev;
if (vifi < 0 || vifi >= mrt->maxvif)
return -EADDRNOTAVAIL;
v = &mrt->vif_table[vifi];
dev = rtnl_dereference(v->dev);
if (!dev)
return -EADDRNOTAVAIL;
call_ip6mr_vif_entry_notifiers(read_pnet(&mrt->net),
FIB_EVENT_VIF_DEL, v, dev,
vifi, mrt->id);
spin_lock(&mrt_lock);
RCU_INIT_POINTER(v->dev, NULL);
#ifdef CONFIG_IPV6_PIMSM_V2
if (vifi == mrt->mroute_reg_vif_num) {
/* Pairs with READ_ONCE() in ip6mr_cache_report() and reg_vif_xmit() */
WRITE_ONCE(mrt->mroute_reg_vif_num, -1);
}
#endif
if (vifi + 1 == mrt->maxvif) {
int tmp;
for (tmp = vifi - 1; tmp >= 0; tmp--) {
if (VIF_EXISTS(mrt, tmp))
break;
}
WRITE_ONCE(mrt->maxvif, tmp + 1);
}
spin_unlock(&mrt_lock);
dev_set_allmulti(dev, -1);
in6_dev = __in6_dev_get(dev);
if (in6_dev) {
atomic_dec(&in6_dev->cnf.mc_forwarding);
inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
dev->ifindex, &in6_dev->cnf);
}
if ((v->flags & MIFF_REGISTER) && !notify)
unregister_netdevice_queue(dev, head);
netdev_put(dev, &v->dev_tracker);
return 0;
}
static inline void ip6mr_cache_free_rcu(struct rcu_head *head)
{
struct mr_mfc *c = container_of(head, struct mr_mfc, rcu);
kmem_cache_free(mrt_cachep, (struct mfc6_cache *)c);
}
static inline void ip6mr_cache_free(struct mfc6_cache *c)
{
call_rcu(&c->_c.rcu, ip6mr_cache_free_rcu);
}
/* Destroy an unresolved cache entry, killing queued skbs
and reporting error to netlink readers.
*/
static void ip6mr_destroy_unres(struct mr_table *mrt, struct mfc6_cache *c)
{
struct net *net = read_pnet(&mrt->net);
struct sk_buff *skb;
atomic_dec(&mrt->cache_resolve_queue_len);
while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved)) != NULL) {
if (ipv6_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = skb_pull(skb,
sizeof(struct ipv6hdr));
nlh->nlmsg_type = NLMSG_ERROR;
nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr));
skb_trim(skb, nlh->nlmsg_len);
((struct nlmsgerr *)nlmsg_data(nlh))->error = -ETIMEDOUT;
rtnl_unicast(skb, net, NETLINK_CB(skb).portid);
} else
kfree_skb(skb);
}
ip6mr_cache_free(c);
}
/* Timer process for all the unresolved queue. */
static void ipmr_do_expire_process(struct mr_table *mrt)
{
unsigned long now = jiffies;
unsigned long expires = 10 * HZ;
struct mr_mfc *c, *next;
list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
if (time_after(c->mfc_un.unres.expires, now)) {
/* not yet... */
unsigned long interval = c->mfc_un.unres.expires - now;
if (interval < expires)
expires = interval;
continue;
}
list_del(&c->list);
mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
}
if (!list_empty(&mrt->mfc_unres_queue))
mod_timer(&mrt->ipmr_expire_timer, jiffies + expires);
}
static void ipmr_expire_process(struct timer_list *t)
{
struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer);
if (!spin_trylock(&mfc_unres_lock)) {
mod_timer(&mrt->ipmr_expire_timer, jiffies + 1);
return;
}
if (!list_empty(&mrt->mfc_unres_queue))
ipmr_do_expire_process(mrt);
spin_unlock(&mfc_unres_lock);
}
/* Fill oifs list. It is called under locked mrt_lock. */
static void ip6mr_update_thresholds(struct mr_table *mrt,
struct mr_mfc *cache,
unsigned char *ttls)
{
int vifi;
cache->mfc_un.res.minvif = MAXMIFS;
cache->mfc_un.res.maxvif = 0;
memset(cache->mfc_un.res.ttls, 255, MAXMIFS);
for (vifi = 0; vifi < mrt->maxvif; vifi++) {
if (VIF_EXISTS(mrt, vifi) &&
ttls[vifi] && ttls[vifi] < 255) {
cache->mfc_un.res.ttls[vifi] = ttls[vifi];
if (cache->mfc_un.res.minvif > vifi)
cache->mfc_un.res.minvif = vifi;
if (cache->mfc_un.res.maxvif <= vifi)
cache->mfc_un.res.maxvif = vifi + 1;
}
}
cache->mfc_un.res.lastuse = jiffies;
}
static int mif6_add(struct net *net, struct mr_table *mrt,
struct mif6ctl *vifc, int mrtsock)
{
int vifi = vifc->mif6c_mifi;
struct vif_device *v = &mrt->vif_table[vifi];
struct net_device *dev;
struct inet6_dev *in6_dev;
int err;
/* Is vif busy ? */
if (VIF_EXISTS(mrt, vifi))
return -EADDRINUSE;
switch (vifc->mif6c_flags) {
#ifdef CONFIG_IPV6_PIMSM_V2
case MIFF_REGISTER:
/*
* Special Purpose VIF in PIM
* All the packets will be sent to the daemon
*/
if (mrt->mroute_reg_vif_num >= 0)
return -EADDRINUSE;
dev = ip6mr_reg_vif(net, mrt);
if (!dev)
return -ENOBUFS;
err = dev_set_allmulti(dev, 1);
if (err) {
unregister_netdevice(dev);
dev_put(dev);
return err;
}
break;
#endif
case 0:
dev = dev_get_by_index(net, vifc->mif6c_pifi);
if (!dev)
return -EADDRNOTAVAIL;
err = dev_set_allmulti(dev, 1);
if (err) {
dev_put(dev);
return err;
}
break;
default:
return -EINVAL;
}
in6_dev = __in6_dev_get(dev);
if (in6_dev) {
atomic_inc(&in6_dev->cnf.mc_forwarding);
inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
dev->ifindex, &in6_dev->cnf);
}
/* Fill in the VIF structures */
vif_device_init(v, dev, vifc->vifc_rate_limit, vifc->vifc_threshold,
vifc->mif6c_flags | (!mrtsock ? VIFF_STATIC : 0),
MIFF_REGISTER);
/* And finish update writing critical data */
spin_lock(&mrt_lock);
rcu_assign_pointer(v->dev, dev);
netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC);
#ifdef CONFIG_IPV6_PIMSM_V2
if (v->flags & MIFF_REGISTER)
WRITE_ONCE(mrt->mroute_reg_vif_num, vifi);
#endif
if (vifi + 1 > mrt->maxvif)
WRITE_ONCE(mrt->maxvif, vifi + 1);
spin_unlock(&mrt_lock);
call_ip6mr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD,
v, dev, vifi, mrt->id);
return 0;
}
static struct mfc6_cache *ip6mr_cache_find(struct mr_table *mrt,
const struct in6_addr *origin,
const struct in6_addr *mcastgrp)
{
struct mfc6_cache_cmp_arg arg = {
.mf6c_origin = *origin,
.mf6c_mcastgrp = *mcastgrp,
};
return mr_mfc_find(mrt, &arg);
}
/* Look for a (*,G) entry */
static struct mfc6_cache *ip6mr_cache_find_any(struct mr_table *mrt,
struct in6_addr *mcastgrp,
mifi_t mifi)
{
struct mfc6_cache_cmp_arg arg = {
.mf6c_origin = in6addr_any,
.mf6c_mcastgrp = *mcastgrp,
};
if (ipv6_addr_any(mcastgrp))
return mr_mfc_find_any_parent(mrt, mifi);
return mr_mfc_find_any(mrt, mifi, &arg);
}
/* Look for a (S,G,iif) entry if parent != -1 */
static struct mfc6_cache *
ip6mr_cache_find_parent(struct mr_table *mrt,
const struct in6_addr *origin,
const struct in6_addr *mcastgrp,
int parent)
{
struct mfc6_cache_cmp_arg arg = {
.mf6c_origin = *origin,
.mf6c_mcastgrp = *mcastgrp,
};
return mr_mfc_find_parent(mrt, &arg, parent);
}
/* Allocate a multicast cache entry */
static struct mfc6_cache *ip6mr_cache_alloc(void)
{
struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
if (!c)
return NULL;
c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->_c.mfc_un.res.minvif = MAXMIFS;
c->_c.free = ip6mr_cache_free_rcu;
refcount_set(&c->_c.mfc_un.res.refcount, 1);
return c;
}
static struct mfc6_cache *ip6mr_cache_alloc_unres(void)
{
struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
if (!c)
return NULL;
skb_queue_head_init(&c->_c.mfc_un.unres.unresolved);
c->_c.mfc_un.unres.expires = jiffies + 10 * HZ;
return c;