forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathdevinet.c
2767 lines (2359 loc) · 68.1 KB
/
devinet.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
/*
* NET3 IP device support routines.
*
* Derived from the IP parts of dev.c 1.0.19
* Authors: Ross Biro
* Fred N. van Kempen, <[email protected]>
* Mark Evans, <[email protected]>
*
* Additional Authors:
* Alan Cox, <[email protected]>
* Alexey Kuznetsov, <[email protected]>
*
* Changes:
* Alexey Kuznetsov: pa_* fields are replaced with ifaddr
* lists.
* Cyrus Durgin: updated for kmod
* Matthias Andree: in devinet_ioctl, compare label and
* address (4.4BSD alias style support),
* fall back to comparing just the label
* if no match found.
*/
#include <linux/uaccess.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/if_addr.h>
#include <linux/if_ether.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/slab.h>
#include <linux/hash.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/kmod.h>
#include <linux/netconf.h>
#include <net/arp.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/ip_fib.h>
#include <net/rtnetlink.h>
#include <net/net_namespace.h>
#include <net/addrconf.h>
#define IPV6ONLY_FLAGS \
(IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \
IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \
IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY)
static struct ipv4_devconf ipv4_devconf = {
.data = {
[IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
[IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/,
[IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/,
},
};
static struct ipv4_devconf ipv4_devconf_dflt = {
.data = {
[IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
[IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1,
[IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/,
[IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/,
},
};
#define IPV4_DEVCONF_DFLT(net, attr) \
IPV4_DEVCONF((*net->ipv4.devconf_dflt), attr)
static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
[IFA_LOCAL] = { .type = NLA_U32 },
[IFA_ADDRESS] = { .type = NLA_U32 },
[IFA_BROADCAST] = { .type = NLA_U32 },
[IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
[IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) },
[IFA_FLAGS] = { .type = NLA_U32 },
[IFA_RT_PRIORITY] = { .type = NLA_U32 },
[IFA_TARGET_NETNSID] = { .type = NLA_S32 },
};
struct inet_fill_args {
u32 portid;
u32 seq;
int event;
unsigned int flags;
int netnsid;
int ifindex;
};
#define IN4_ADDR_HSIZE_SHIFT 8
#define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT)
static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE];
static u32 inet_addr_hash(const struct net *net, __be32 addr)
{
u32 val = (__force u32) addr ^ net_hash_mix(net);
return hash_32(val, IN4_ADDR_HSIZE_SHIFT);
}
static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa)
{
u32 hash = inet_addr_hash(net, ifa->ifa_local);
ASSERT_RTNL();
hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]);
}
static void inet_hash_remove(struct in_ifaddr *ifa)
{
ASSERT_RTNL();
hlist_del_init_rcu(&ifa->hash);
}
/**
* __ip_dev_find - find the first device with a given source address.
* @net: the net namespace
* @addr: the source address
* @devref: if true, take a reference on the found device
*
* If a caller uses devref=false, it should be protected by RCU, or RTNL
*/
struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
{
struct net_device *result = NULL;
struct in_ifaddr *ifa;
rcu_read_lock();
ifa = inet_lookup_ifaddr_rcu(net, addr);
if (!ifa) {
struct flowi4 fl4 = { .daddr = addr };
struct fib_result res = { 0 };
struct fib_table *local;
/* Fallback to FIB local table so that communication
* over loopback subnets work.
*/
local = fib_get_table(net, RT_TABLE_LOCAL);
if (local &&
!fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
res.type == RTN_LOCAL)
result = FIB_RES_DEV(res);
} else {
result = ifa->ifa_dev->dev;
}
if (result && devref)
dev_hold(result);
rcu_read_unlock();
return result;
}
EXPORT_SYMBOL(__ip_dev_find);
/* called under RCU lock */
struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr)
{
u32 hash = inet_addr_hash(net, addr);
struct in_ifaddr *ifa;
hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash)
if (ifa->ifa_local == addr &&
net_eq(dev_net(ifa->ifa_dev->dev), net))
return ifa;
return NULL;
}
static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain);
static void inet_del_ifa(struct in_device *in_dev,
struct in_ifaddr __rcu **ifap,
int destroy);
#ifdef CONFIG_SYSCTL
static int devinet_sysctl_register(struct in_device *idev);
static void devinet_sysctl_unregister(struct in_device *idev);
#else
static int devinet_sysctl_register(struct in_device *idev)
{
return 0;
}
static void devinet_sysctl_unregister(struct in_device *idev)
{
}
#endif
/* Locks all the inet devices. */
static struct in_ifaddr *inet_alloc_ifa(void)
{
return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL);
}
static void inet_rcu_free_ifa(struct rcu_head *head)
{
struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head);
if (ifa->ifa_dev)
in_dev_put(ifa->ifa_dev);
kfree(ifa);
}
static void inet_free_ifa(struct in_ifaddr *ifa)
{
call_rcu(&ifa->rcu_head, inet_rcu_free_ifa);
}
void in_dev_finish_destroy(struct in_device *idev)
{
struct net_device *dev = idev->dev;
WARN_ON(idev->ifa_list);
WARN_ON(idev->mc_list);
kfree(rcu_dereference_protected(idev->mc_hash, 1));
#ifdef NET_REFCNT_DEBUG
pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL");
#endif
dev_put(dev);
if (!idev->dead)
pr_err("Freeing alive in_device %p\n", idev);
else
kfree(idev);
}
EXPORT_SYMBOL(in_dev_finish_destroy);
static struct in_device *inetdev_init(struct net_device *dev)
{
struct in_device *in_dev;
int err = -ENOMEM;
ASSERT_RTNL();
in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL);
if (!in_dev)
goto out;
memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt,
sizeof(in_dev->cnf));
in_dev->cnf.sysctl = NULL;
in_dev->dev = dev;
in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl);
if (!in_dev->arp_parms)
goto out_kfree;
if (IPV4_DEVCONF(in_dev->cnf, FORWARDING))
dev_disable_lro(dev);
/* Reference in_dev->dev */
dev_hold(dev);
/* Account for reference dev->ip_ptr (below) */
refcount_set(&in_dev->refcnt, 1);
err = devinet_sysctl_register(in_dev);
if (err) {
in_dev->dead = 1;
in_dev_put(in_dev);
in_dev = NULL;
goto out;
}
ip_mc_init_dev(in_dev);
if (dev->flags & IFF_UP)
ip_mc_up(in_dev);
/* we can receive as soon as ip_ptr is set -- do this last */
rcu_assign_pointer(dev->ip_ptr, in_dev);
out:
return in_dev ?: ERR_PTR(err);
out_kfree:
kfree(in_dev);
in_dev = NULL;
goto out;
}
static void in_dev_rcu_put(struct rcu_head *head)
{
struct in_device *idev = container_of(head, struct in_device, rcu_head);
in_dev_put(idev);
}
static void inetdev_destroy(struct in_device *in_dev)
{
struct net_device *dev;
struct in_ifaddr *ifa;
ASSERT_RTNL();
dev = in_dev->dev;
in_dev->dead = 1;
ip_mc_destroy_dev(in_dev);
while ((ifa = rtnl_dereference(in_dev->ifa_list)) != NULL) {
inet_del_ifa(in_dev, &in_dev->ifa_list, 0);
inet_free_ifa(ifa);
}
RCU_INIT_POINTER(dev->ip_ptr, NULL);
devinet_sysctl_unregister(in_dev);
neigh_parms_release(&arp_tbl, in_dev->arp_parms);
arp_ifdown(dev);
call_rcu(&in_dev->rcu_head, in_dev_rcu_put);
}
int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b)
{
const struct in_ifaddr *ifa;
rcu_read_lock();
in_dev_for_each_ifa_rcu(ifa, in_dev) {
if (inet_ifa_match(a, ifa)) {
if (!b || inet_ifa_match(b, ifa)) {
rcu_read_unlock();
return 1;
}
}
}
rcu_read_unlock();
return 0;
}
static void __inet_del_ifa(struct in_device *in_dev,
struct in_ifaddr __rcu **ifap,
int destroy, struct nlmsghdr *nlh, u32 portid)
{
struct in_ifaddr *promote = NULL;
struct in_ifaddr *ifa, *ifa1;
struct in_ifaddr *last_prim;
struct in_ifaddr *prev_prom = NULL;
int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev);
ASSERT_RTNL();
ifa1 = rtnl_dereference(*ifap);
last_prim = rtnl_dereference(in_dev->ifa_list);
if (in_dev->dead)
goto no_promotions;
/* 1. Deleting primary ifaddr forces deletion all secondaries
* unless alias promotion is set
**/
if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) {
struct in_ifaddr __rcu **ifap1 = &ifa1->ifa_next;
while ((ifa = rtnl_dereference(*ifap1)) != NULL) {
if (!(ifa->ifa_flags & IFA_F_SECONDARY) &&
ifa1->ifa_scope <= ifa->ifa_scope)
last_prim = ifa;
if (!(ifa->ifa_flags & IFA_F_SECONDARY) ||
ifa1->ifa_mask != ifa->ifa_mask ||
!inet_ifa_match(ifa1->ifa_address, ifa)) {
ifap1 = &ifa->ifa_next;
prev_prom = ifa;
continue;
}
if (!do_promote) {
inet_hash_remove(ifa);
*ifap1 = ifa->ifa_next;
rtmsg_ifa(RTM_DELADDR, ifa, nlh, portid);
blocking_notifier_call_chain(&inetaddr_chain,
NETDEV_DOWN, ifa);
inet_free_ifa(ifa);
} else {
promote = ifa;
break;
}
}
}
/* On promotion all secondaries from subnet are changing
* the primary IP, we must remove all their routes silently
* and later to add them back with new prefsrc. Do this
* while all addresses are on the device list.
*/
for (ifa = promote; ifa; ifa = rtnl_dereference(ifa->ifa_next)) {
if (ifa1->ifa_mask == ifa->ifa_mask &&
inet_ifa_match(ifa1->ifa_address, ifa))
fib_del_ifaddr(ifa, ifa1);
}
no_promotions:
/* 2. Unlink it */
*ifap = ifa1->ifa_next;
inet_hash_remove(ifa1);
/* 3. Announce address deletion */
/* Send message first, then call notifier.
At first sight, FIB update triggered by notifier
will refer to already deleted ifaddr, that could confuse
netlink listeners. It is not true: look, gated sees
that route deleted and if it still thinks that ifaddr
is valid, it will try to restore deleted routes... Grr.
So that, this order is correct.
*/
rtmsg_ifa(RTM_DELADDR, ifa1, nlh, portid);
blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1);
if (promote) {
struct in_ifaddr *next_sec;
next_sec = rtnl_dereference(promote->ifa_next);
if (prev_prom) {
struct in_ifaddr *last_sec;
rcu_assign_pointer(prev_prom->ifa_next, next_sec);
last_sec = rtnl_dereference(last_prim->ifa_next);
rcu_assign_pointer(promote->ifa_next, last_sec);
rcu_assign_pointer(last_prim->ifa_next, promote);
}
promote->ifa_flags &= ~IFA_F_SECONDARY;
rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid);
blocking_notifier_call_chain(&inetaddr_chain,
NETDEV_UP, promote);
for (ifa = next_sec; ifa;
ifa = rtnl_dereference(ifa->ifa_next)) {
if (ifa1->ifa_mask != ifa->ifa_mask ||
!inet_ifa_match(ifa1->ifa_address, ifa))
continue;
fib_add_ifaddr(ifa);
}
}
if (destroy)
inet_free_ifa(ifa1);
}
static void inet_del_ifa(struct in_device *in_dev,
struct in_ifaddr __rcu **ifap,
int destroy)
{
__inet_del_ifa(in_dev, ifap, destroy, NULL, 0);
}
static void check_lifetime(struct work_struct *work);
static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime);
static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
u32 portid, struct netlink_ext_ack *extack)
{
struct in_ifaddr __rcu **last_primary, **ifap;
struct in_device *in_dev = ifa->ifa_dev;
struct in_validator_info ivi;
struct in_ifaddr *ifa1;
int ret;
ASSERT_RTNL();
if (!ifa->ifa_local) {
inet_free_ifa(ifa);
return 0;
}
ifa->ifa_flags &= ~IFA_F_SECONDARY;
last_primary = &in_dev->ifa_list;
/* Don't set IPv6 only flags to IPv4 addresses */
ifa->ifa_flags &= ~IPV6ONLY_FLAGS;
ifap = &in_dev->ifa_list;
ifa1 = rtnl_dereference(*ifap);
while (ifa1) {
if (!(ifa1->ifa_flags & IFA_F_SECONDARY) &&
ifa->ifa_scope <= ifa1->ifa_scope)
last_primary = &ifa1->ifa_next;
if (ifa1->ifa_mask == ifa->ifa_mask &&
inet_ifa_match(ifa1->ifa_address, ifa)) {
if (ifa1->ifa_local == ifa->ifa_local) {
inet_free_ifa(ifa);
return -EEXIST;
}
if (ifa1->ifa_scope != ifa->ifa_scope) {
inet_free_ifa(ifa);
return -EINVAL;
}
ifa->ifa_flags |= IFA_F_SECONDARY;
}
ifap = &ifa1->ifa_next;
ifa1 = rtnl_dereference(*ifap);
}
/* Allow any devices that wish to register ifaddr validtors to weigh
* in now, before changes are committed. The rntl lock is serializing
* access here, so the state should not change between a validator call
* and a final notify on commit. This isn't invoked on promotion under
* the assumption that validators are checking the address itself, and
* not the flags.
*/
ivi.ivi_addr = ifa->ifa_address;
ivi.ivi_dev = ifa->ifa_dev;
ivi.extack = extack;
ret = blocking_notifier_call_chain(&inetaddr_validator_chain,
NETDEV_UP, &ivi);
ret = notifier_to_errno(ret);
if (ret) {
inet_free_ifa(ifa);
return ret;
}
if (!(ifa->ifa_flags & IFA_F_SECONDARY)) {
prandom_seed((__force u32) ifa->ifa_local);
ifap = last_primary;
}
rcu_assign_pointer(ifa->ifa_next, *ifap);
rcu_assign_pointer(*ifap, ifa);
inet_hash_insert(dev_net(in_dev->dev), ifa);
cancel_delayed_work(&check_lifetime_work);
queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0);
/* Send message first, then call notifier.
Notifier will trigger FIB update, so that
listeners of netlink will know about new ifaddr */
rtmsg_ifa(RTM_NEWADDR, ifa, nlh, portid);
blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
return 0;
}
static int inet_insert_ifa(struct in_ifaddr *ifa)
{
return __inet_insert_ifa(ifa, NULL, 0, NULL);
}
static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
{
struct in_device *in_dev = __in_dev_get_rtnl(dev);
ASSERT_RTNL();
if (!in_dev) {
inet_free_ifa(ifa);
return -ENOBUFS;
}
ipv4_devconf_setall(in_dev);
neigh_parms_data_state_setall(in_dev->arp_parms);
if (ifa->ifa_dev != in_dev) {
WARN_ON(ifa->ifa_dev);
in_dev_hold(in_dev);
ifa->ifa_dev = in_dev;
}
if (ipv4_is_loopback(ifa->ifa_local))
ifa->ifa_scope = RT_SCOPE_HOST;
return inet_insert_ifa(ifa);
}
/* Caller must hold RCU or RTNL :
* We dont take a reference on found in_device
*/
struct in_device *inetdev_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
struct in_device *in_dev = NULL;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifindex);
if (dev)
in_dev = rcu_dereference_rtnl(dev->ip_ptr);
rcu_read_unlock();
return in_dev;
}
EXPORT_SYMBOL(inetdev_by_index);
/* Called only from RTNL semaphored context. No locks. */
struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
__be32 mask)
{
struct in_ifaddr *ifa;
ASSERT_RTNL();
in_dev_for_each_ifa_rtnl(ifa, in_dev) {
if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa))
return ifa;
}
return NULL;
}
static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
{
struct ip_mreqn mreq = {
.imr_multiaddr.s_addr = ifa->ifa_address,
.imr_ifindex = ifa->ifa_dev->dev->ifindex,
};
int ret;
ASSERT_RTNL();
lock_sock(sk);
if (join)
ret = ip_mc_join_group(sk, &mreq);
else
ret = ip_mc_leave_group(sk, &mreq);
release_sock(sk);
return ret;
}
static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct in_ifaddr __rcu **ifap;
struct nlattr *tb[IFA_MAX+1];
struct in_device *in_dev;
struct ifaddrmsg *ifm;
struct in_ifaddr *ifa;
int err = -EINVAL;
ASSERT_RTNL();
err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
ifa_ipv4_policy, extack);
if (err < 0)
goto errout;
ifm = nlmsg_data(nlh);
in_dev = inetdev_by_index(net, ifm->ifa_index);
if (!in_dev) {
err = -ENODEV;
goto errout;
}
for (ifap = &in_dev->ifa_list; (ifa = rtnl_dereference(*ifap)) != NULL;
ifap = &ifa->ifa_next) {
if (tb[IFA_LOCAL] &&
ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL]))
continue;
if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label))
continue;
if (tb[IFA_ADDRESS] &&
(ifm->ifa_prefixlen != ifa->ifa_prefixlen ||
!inet_ifa_match(nla_get_in_addr(tb[IFA_ADDRESS]), ifa)))
continue;
if (ipv4_is_multicast(ifa->ifa_address))
ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa);
__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid);
return 0;
}
err = -EADDRNOTAVAIL;
errout:
return err;
}
#define INFINITY_LIFE_TIME 0xFFFFFFFF
static void check_lifetime(struct work_struct *work)
{
unsigned long now, next, next_sec, next_sched;
struct in_ifaddr *ifa;
struct hlist_node *n;
int i;
now = jiffies;
next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
for (i = 0; i < IN4_ADDR_HSIZE; i++) {
bool change_needed = false;
rcu_read_lock();
hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) {
unsigned long age;
if (ifa->ifa_flags & IFA_F_PERMANENT)
continue;
/* We try to batch several events at once. */
age = (now - ifa->ifa_tstamp +
ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
age >= ifa->ifa_valid_lft) {
change_needed = true;
} else if (ifa->ifa_preferred_lft ==
INFINITY_LIFE_TIME) {
continue;
} else if (age >= ifa->ifa_preferred_lft) {
if (time_before(ifa->ifa_tstamp +
ifa->ifa_valid_lft * HZ, next))
next = ifa->ifa_tstamp +
ifa->ifa_valid_lft * HZ;
if (!(ifa->ifa_flags & IFA_F_DEPRECATED))
change_needed = true;
} else if (time_before(ifa->ifa_tstamp +
ifa->ifa_preferred_lft * HZ,
next)) {
next = ifa->ifa_tstamp +
ifa->ifa_preferred_lft * HZ;
}
}
rcu_read_unlock();
if (!change_needed)
continue;
rtnl_lock();
hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) {
unsigned long age;
if (ifa->ifa_flags & IFA_F_PERMANENT)
continue;
/* We try to batch several events at once. */
age = (now - ifa->ifa_tstamp +
ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
age >= ifa->ifa_valid_lft) {
struct in_ifaddr __rcu **ifap;
struct in_ifaddr *tmp;
ifap = &ifa->ifa_dev->ifa_list;
tmp = rtnl_dereference(*ifap);
while (tmp) {
if (tmp == ifa) {
inet_del_ifa(ifa->ifa_dev,
ifap, 1);
break;
}
ifap = &tmp->ifa_next;
tmp = rtnl_dereference(*ifap);
}
} else if (ifa->ifa_preferred_lft !=
INFINITY_LIFE_TIME &&
age >= ifa->ifa_preferred_lft &&
!(ifa->ifa_flags & IFA_F_DEPRECATED)) {
ifa->ifa_flags |= IFA_F_DEPRECATED;
rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
}
}
rtnl_unlock();
}
next_sec = round_jiffies_up(next);
next_sched = next;
/* If rounded timeout is accurate enough, accept it. */
if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ))
next_sched = next_sec;
now = jiffies;
/* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */
if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX))
next_sched = now + ADDRCONF_TIMER_FUZZ_MAX;
queue_delayed_work(system_power_efficient_wq, &check_lifetime_work,
next_sched - now);
}
static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft,
__u32 prefered_lft)
{
unsigned long timeout;
ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED);
timeout = addrconf_timeout_fixup(valid_lft, HZ);
if (addrconf_finite_timeout(timeout))
ifa->ifa_valid_lft = timeout;
else
ifa->ifa_flags |= IFA_F_PERMANENT;
timeout = addrconf_timeout_fixup(prefered_lft, HZ);
if (addrconf_finite_timeout(timeout)) {
if (timeout == 0)
ifa->ifa_flags |= IFA_F_DEPRECATED;
ifa->ifa_preferred_lft = timeout;
}
ifa->ifa_tstamp = jiffies;
if (!ifa->ifa_cstamp)
ifa->ifa_cstamp = ifa->ifa_tstamp;
}
static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
__u32 *pvalid_lft, __u32 *pprefered_lft,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[IFA_MAX+1];
struct in_ifaddr *ifa;
struct ifaddrmsg *ifm;
struct net_device *dev;
struct in_device *in_dev;
int err;
err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
ifa_ipv4_policy, extack);
if (err < 0)
goto errout;
ifm = nlmsg_data(nlh);
err = -EINVAL;
if (ifm->ifa_prefixlen > 32 || !tb[IFA_LOCAL])
goto errout;
dev = __dev_get_by_index(net, ifm->ifa_index);
err = -ENODEV;
if (!dev)
goto errout;
in_dev = __in_dev_get_rtnl(dev);
err = -ENOBUFS;
if (!in_dev)
goto errout;
ifa = inet_alloc_ifa();
if (!ifa)
/*
* A potential indev allocation can be left alive, it stays
* assigned to its device and is destroy with it.
*/
goto errout;
ipv4_devconf_setall(in_dev);
neigh_parms_data_state_setall(in_dev->arp_parms);
in_dev_hold(in_dev);
if (!tb[IFA_ADDRESS])
tb[IFA_ADDRESS] = tb[IFA_LOCAL];
INIT_HLIST_NODE(&ifa->hash);
ifa->ifa_prefixlen = ifm->ifa_prefixlen;
ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen);
ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) :
ifm->ifa_flags;
ifa->ifa_scope = ifm->ifa_scope;
ifa->ifa_dev = in_dev;
ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]);
ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]);
if (tb[IFA_BROADCAST])
ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]);
if (tb[IFA_LABEL])
nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
if (tb[IFA_RT_PRIORITY])
ifa->ifa_rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]);
if (tb[IFA_CACHEINFO]) {
struct ifa_cacheinfo *ci;
ci = nla_data(tb[IFA_CACHEINFO]);
if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) {
err = -EINVAL;
goto errout_free;
}
*pvalid_lft = ci->ifa_valid;
*pprefered_lft = ci->ifa_prefered;
}
return ifa;
errout_free:
inet_free_ifa(ifa);
errout:
return ERR_PTR(err);
}
static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa)
{
struct in_device *in_dev = ifa->ifa_dev;
struct in_ifaddr *ifa1;
if (!ifa->ifa_local)
return NULL;
in_dev_for_each_ifa_rtnl(ifa1, in_dev) {
if (ifa1->ifa_mask == ifa->ifa_mask &&
inet_ifa_match(ifa1->ifa_address, ifa) &&
ifa1->ifa_local == ifa->ifa_local)
return ifa1;
}
return NULL;
}
static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct in_ifaddr *ifa;
struct in_ifaddr *ifa_existing;
__u32 valid_lft = INFINITY_LIFE_TIME;
__u32 prefered_lft = INFINITY_LIFE_TIME;
ASSERT_RTNL();
ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft, extack);
if (IS_ERR(ifa))
return PTR_ERR(ifa);
ifa_existing = find_matching_ifa(ifa);
if (!ifa_existing) {
/* It would be best to check for !NLM_F_CREATE here but
* userspace already relies on not having to provide this.
*/
set_ifa_lifetime(ifa, valid_lft, prefered_lft);
if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) {
int ret = ip_mc_config(net->ipv4.mc_autojoin_sk,
true, ifa);
if (ret < 0) {
inet_free_ifa(ifa);
return ret;
}
}
return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid,
extack);
} else {
u32 new_metric = ifa->ifa_rt_priority;
inet_free_ifa(ifa);
if (nlh->nlmsg_flags & NLM_F_EXCL ||
!(nlh->nlmsg_flags & NLM_F_REPLACE))
return -EEXIST;
ifa = ifa_existing;
if (ifa->ifa_rt_priority != new_metric) {
fib_modify_prefix_metric(ifa, new_metric);
ifa->ifa_rt_priority = new_metric;
}
set_ifa_lifetime(ifa, valid_lft, prefered_lft);
cancel_delayed_work(&check_lifetime_work);
queue_delayed_work(system_power_efficient_wq,
&check_lifetime_work, 0);
rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
}
return 0;
}
/*
* Determine a default network mask, based on the IP address.
*/
static int inet_abc_len(__be32 addr)
{
int rc = -1; /* Something else, probably a multicast. */
if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr))
rc = 0;
else {
__u32 haddr = ntohl(addr);
if (IN_CLASSA(haddr))
rc = 8;
else if (IN_CLASSB(haddr))
rc = 16;
else if (IN_CLASSC(haddr))
rc = 24;
else if (IN_CLASSE(haddr))
rc = 32;
}
return rc;
}