-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdevinet.c
executable file
·2020 lines (1774 loc) · 47.7 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
/*
* NET3 IP device support routines.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Derived from the IP parts of dev.c 1.0.19
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
*
* Additional Authors:
* Alan Cox, <gw4pts@gw4pts.ampr.org>
* Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* 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 <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.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>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/kmod.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>
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,
},
};
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,
},
};
#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 },
};
static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
//http://www.linuxidc.com/Linux/2013-07/86999.htm如图 1中所示，
//Linux的网络子系统一共有3个通知链：表示ipv4地址发生变化时的inetaddr_chain；
//表示ipv6地址发生变化的inet6addr_chain；还有表示设备注册、状态变化的netdev_chain。
//static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
/*
原子通知链（ Atomic notifier chains ）：通知链元素的回调函数（当事件发生时要执行的函数）在中断或原子操作上下文中运行，不允许阻塞。对应的链表头结构：
可阻塞通知链（ Blocking notifier chains ）：通知链元素的回调函数在进程上下文中运行，允许阻塞。对应的链表头：
原始通知链（ Raw notifierchains ）：对通知链元素的回调函数没有任何限制，所有锁和保护机制都由调用者维护。对应的链表头：
SRCU 通知链（ SRCU notifier chains ）：可阻塞通知链的一种变体。对应的链表头：
register_inetaddr_notifier和unregister_inetaddr_notifier配对
*/
struct blocking_notifier_head inetaddr_chain = BLOCKING_NOTIFIER_INIT(inetaddr_chain)
static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
int destroy);
#ifdef CONFIG_SYSCTL
static void devinet_sysctl_register(struct in_device *idev);
static void devinet_sysctl_unregister(struct in_device *idev);
#else
static inline void devinet_sysctl_register(struct in_device *idev)
{
}
static inline 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 inline 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);
#ifdef NET_REFCNT_DEBUG
printk(KERN_DEBUG "in_dev_finish_destroy: %p=%s\n",
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);
/*
* inetdev_init()为通过参数指定的网络设备分配并绑定
* IP配置块。
*/
static struct in_device *inetdev_init(struct net_device *dev)
{
struct in_device *in_dev;
ASSERT_RTNL();
/*
* 分配一个IP配置块
*/
in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL);
if (!in_dev)
goto out;
/*
* 初始化IP配置块中的一些成员，包括
* IPv4配置的默认值，以及所属的网络设备。
*/
memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt,
sizeof(in_dev->cnf));
in_dev->cnf.sysctl = NULL;
in_dev->dev = dev;
/*
* 为IP配置块分配邻居协议参数配置块，
* 并根据ARP表初始化
*/
if ((in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl)) == NULL)
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) */
in_dev_hold(in_dev);
devinet_sysctl_register(in_dev);
/*
* 初始化IGMP模块
*/
ip_mc_init_dev(in_dev);
/*
* 如果网络设备已启用，则初始化该网络
* 设备上的组播消息，例如，将
* 该网络设备加入到224.0.0.1组播组等操作
*/
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);
/*
* 操作成功，返回分配并绑定成功的IP配置块，
* 否则返回NULL。
*/
out:
return in_dev;
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);
}
/*
* inetdev_destroy()通常在设备注销时被调用，
* 释放指定的IP配置块。
*/
static void inetdev_destroy(struct in_device *in_dev)
{
struct in_ifaddr *ifa;
struct net_device *dev;
ASSERT_RTNL();
dev = in_dev->dev;
/*
* 标识带释放的IP配置块正处在释放过程中。
*/
in_dev->dead = 1;
/*
* 销毁组播相关的配置，如停止相关定时器。
*/
ip_mc_destroy_dev(in_dev);
/*
* 删除并释放所有的IP地址块。
*/
while ((ifa = in_dev->ifa_list) != NULL) {
inet_del_ifa(in_dev, &in_dev->ifa_list, 0);
inet_free_ifa(ifa);
}
/*
* 将网络设备指向IP配置块的指针设置为NULL。
*/
dev->ip_ptr = NULL;
/*
* 注销邻居子系统相关的配置参数
*/
devinet_sysctl_unregister(in_dev);
/*
* 释放IP配置块中的邻居协议参数配置块。
*/
neigh_parms_release(&arp_tbl, in_dev->arp_parms);
arp_ifdown(dev);
/*
* 通过RCU机制释放IP配置块。
*/
call_rcu(&in_dev->rcu_head, in_dev_rcu_put);
}
/*
* 根据指定网络设备的IP配置块，检查两个给定的
* IP地址是否同属于一个子网
*/
int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b)
{
rcu_read_lock();
for_primary_ifa(in_dev) {
if (inet_ifa_match(a, ifa)) {
if (!b || inet_ifa_match(b, ifa)) {
rcu_read_unlock();
return 1;
}
}
} endfor_ifa(in_dev);
rcu_read_unlock();
return 0;
}
static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
int destroy, struct nlmsghdr *nlh, u32 pid)
{
struct in_ifaddr *promote = NULL;
struct in_ifaddr *ifa, *ifa1 = *ifap;
struct in_ifaddr *last_prim = in_dev->ifa_list;
struct in_ifaddr *prev_prom = NULL;
int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev);
ASSERT_RTNL();
/* 1. Deleting primary ifaddr forces deletion all secondaries
* unless alias promotion is set
**/
/*
* 如果删除的是主IP地址，则需对从属
* IP地址作相应的处理。如果没有启用
* promote_secondaries，则删除所有该主IP地址的
* 从属IP地址，否则选择一个从属IP地址，
* 升级为主IP地址。
*/
if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) {
struct in_ifaddr **ifap1 = &ifa1->ifa_next;
while ((ifa = *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) {
*ifap1 = ifa->ifa_next;
rtmsg_ifa(RTM_DELADDR, ifa, nlh, pid);
blocking_notifier_call_chain(&inetaddr_chain,
NETDEV_DOWN, ifa);
inet_free_ifa(ifa);
} else {
promote = ifa;
break;
}
}
}
/* 2. Unlink it */
/*
* 先将待删除的IP地址块从链表中删除，
* 后续操作中再根据destroy作处理
*/
*ifap = ifa1->ifa_next;
/* 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.
*/
/*
* 通过netlink发送RTM_DELADDR消息给感兴趣的
* 用户进程
*/
rtmsg_ifa(RTM_DELADDR, ifa1, nlh, pid);
/*
* 通过inetaddr_chain通知链发送删除IP地址事件
* 和IP地址信息给感兴趣的其他内核模块
*/
blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1);
/*
* 如果启用了promote_secondaries，将选择到的
* 从属IP地址升级为主IP地址，发送从属
* IP地址升级为主IP地址消息。并通过
* fib_add_ifaddr()将从属IP地址相关的路由
* 表项添加到ip_fib_local_table路由表中。
*/
if (promote) {
if (prev_prom) {
prev_prom->ifa_next = promote->ifa_next;
promote->ifa_next = last_prim->ifa_next;
last_prim->ifa_next = promote;
}
promote->ifa_flags &= ~IFA_F_SECONDARY;
rtmsg_ifa(RTM_NEWADDR, promote, nlh, pid);
blocking_notifier_call_chain(&inetaddr_chain,
NETDEV_UP, promote);
for (ifa = promote->ifa_next; ifa; ifa = ifa->ifa_next) {
if (ifa1->ifa_mask != ifa->ifa_mask ||
!inet_ifa_match(ifa1->ifa_address, ifa))
continue;
fib_add_ifaddr(ifa);
}
}
/*
* 如果根据destroy需要释放，则通过RCU机制
* 释放IP配置块。在删除掉最后一个地址后，
* 释放所有的IP配置块。
*/
if (destroy)
inet_free_ifa(ifa1);
}
static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
int destroy)
{
__inet_del_ifa(in_dev, ifap, destroy, NULL, 0);
}
static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
u32 pid)
{
struct in_device *in_dev = ifa->ifa_dev;
struct in_ifaddr *ifa1, **ifap, **last_primary;
ASSERT_RTNL();
if (!ifa->ifa_local) {
inet_free_ifa(ifa);
return 0;
}
/*
* 先清除地址的从属标志，因为配置的地址
* 是主IP地址还是从属IP地址，并非根据标志
* 而是根据当前已配置的IP地址
*/
ifa->ifa_flags &= ~IFA_F_SECONDARY;
last_primary = &in_dev->ifa_list;
/*
* 在所有主IP地址中查找，如果存在相同
* 寻址范围的地址，则本次添加的IP地址
* 为从属IP地址。而如果已配置了相同的
* 地址，则返回错误码-EEXIST。
*/
for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL;
ifap = &ifa1->ifa_next) {
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;
}
}
/*
* 如果配置的是第一个地址，则先添加
* 熵到伪随机数引擎中，然后将其地址
* 添加到IP配置块中。
*/
if (!(ifa->ifa_flags & IFA_F_SECONDARY)) {
net_srandom(ifa->ifa_local);
ifap = last_primary;
}
ifa->ifa_next = *ifap;
*ifap = ifa;
/* Send message first, then call notifier.
Notifier will trigger FIB update, so that
listeners of netlink will know about new ifaddr */
/*
* 通过netlink发送RTM_NEWADDR消息给感兴趣的
* 用户进程。
*/
rtmsg_ifa(RTM_NEWADDR, ifa, nlh, pid);
/*
* 通过inetaddr_chain通知链发送添加IP地址事件
* 和IP地址消息给感兴趣的其他内核模块。
*/
blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
return 0;
}
/*
* inet_insert_ifa()用来添加一个IP地址。
* 通常在设置广播地址、点对点对端
* 地址和地址掩码时，先调用inet_del_ifa()清除
* 原有的信息，然后再调用inet_insert_ifa()进行
* 设置
*/
static int inet_insert_ifa(struct in_ifaddr *ifa)
{
return __inet_insert_ifa(ifa, NULL, 0);
}
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);
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);
}
/*
* inetdev_by_index()根据网络设备索引号获取
* 对应网络设备的IP配置块
*/
struct in_device *inetdev_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
struct in_device *in_dev = NULL;
read_lock(&dev_base_lock);
/*
* 根据索引获取对应的网络设备
*/
dev = __dev_get_by_index(net, ifindex);
/*
* 如果获得的网络设备有效，则返回其
* IP配置块，否则返回NULL。
*/
if (dev)
in_dev = in_dev_get(dev);
read_unlock(&dev_base_lock);
return in_dev;
}
EXPORT_SYMBOL(inetdev_by_index);
/* Called only from RTNL semaphored context. No locks. */
/*
* inet_ifa_byprefix()在正在配置的输入设备的主IP
* 地址中查找与前缀和掩码匹配的IP地址
*/
struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
__be32 mask)
{
ASSERT_RTNL();
for_primary_ifa(in_dev) {
if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa))
return ifa;
} endfor_ifa(in_dev);
return NULL;
}
/*
* 当通过netlink，操作类型为RTM_DELADDR删除IP地址时，
* 才调用此函数
*/
static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tb[IFA_MAX+1];
struct in_device *in_dev;
struct ifaddrmsg *ifm;
struct in_ifaddr *ifa, **ifap;
int err = -EINVAL;
ASSERT_RTNL();
/*
* 解析netlink报文，获取配置参数。
*/
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
if (err < 0)
goto errout;
ifm = nlmsg_data(nlh);
in_dev = inetdev_by_index(net, ifm->ifa_index);
if (in_dev == NULL) {
err = -ENODEV;
goto errout;
}
__in_dev_put(in_dev);
/*
* 根据本地地址、标签以及掩码查找待删除的
* IP地址块，如果查找命中，则将其删除并释放。
*/
for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
ifap = &ifa->ifa_next) {
if (tb[IFA_LOCAL] &&
ifa->ifa_local != nla_get_be32(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_be32(tb[IFA_ADDRESS]), ifa)))
continue;
__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).pid);
return 0;
}
err = -EADDRNOTAVAIL;
errout:
return err;
}
static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh)
{
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(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
if (err < 0)
goto errout;
ifm = nlmsg_data(nlh);
err = -EINVAL;
if (ifm->ifa_prefixlen > 32 || tb[IFA_LOCAL] == NULL)
goto errout;
dev = __dev_get_by_index(net, ifm->ifa_index);
err = -ENODEV;
if (dev == NULL)
goto errout;
in_dev = __in_dev_get_rtnl(dev);
err = -ENOBUFS;
if (in_dev == NULL)
goto errout;
ifa = inet_alloc_ifa();
if (ifa == NULL)
/*
* 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);
in_dev_hold(in_dev);
if (tb[IFA_ADDRESS] == NULL)
tb[IFA_ADDRESS] = tb[IFA_LOCAL];
ifa->ifa_prefixlen = ifm->ifa_prefixlen;
ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen);
ifa->ifa_flags = ifm->ifa_flags;
ifa->ifa_scope = ifm->ifa_scope;
ifa->ifa_dev = in_dev;
ifa->ifa_local = nla_get_be32(tb[IFA_LOCAL]);
ifa->ifa_address = nla_get_be32(tb[IFA_ADDRESS]);
if (tb[IFA_BROADCAST])
ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]);
if (tb[IFA_LABEL])
nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
return ifa;
errout:
return ERR_PTR(err);
}
/*
* 当通过netlink，操作类型为RTM_NEWADDR添加IP地址
* 时，会调用此函数
*/
static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
struct in_ifaddr *ifa;
ASSERT_RTNL();
/*
* 从配置IP地址的消息中获取地址信息
*/
ifa = rtm_to_ifaddr(net, nlh);
if (IS_ERR(ifa))
return PTR_ERR(ifa);
/*
* 将IP地址配置到指定的网络设备上
*/
return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).pid);
}
/*
* Determine a default network mask, based on the IP address.
*/
/*
* inet_abc_len()根据指定的IP地址获取默认掩码
* 长度。默认掩码长度表:
* ------------------------------------------
* 地址 默认掩码长度
* ------------------------------------------
* 0地址 0
* A类地址 8
* B类地址 16
* C类地址 24
*/
static __inline__ int inet_abc_len(__be32 addr)
{
int rc = -1; /* Something else, probably a multicast. */
if (ipv4_is_zeronet(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;
}
return rc;
}
/*
* 应用程序对套接字有关接口层地址的ioctl操作，
* 最终由devinet_ioctl()来处理
*/
int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
struct ifreq ifr;
struct sockaddr_in sin_orig;
struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
struct in_device *in_dev;
struct in_ifaddr **ifap = NULL;
struct in_ifaddr *ifa = NULL;
struct net_device *dev;
char *colon;
int ret = -EFAULT;
int tryaddrmatch = 0;
/*
* Fetch the caller's info block into kernel space
*/
/*
* 从用户空间复制配置参数
*/
if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
goto out;
ifr.ifr_name[IFNAMSIZ - 1] = 0;
/* save original address for comparison */
/*
* 将原始的配置参数保存起来，用于
* 后续的比较操作。
*/
memcpy(&sin_orig, sin, sizeof(*sin));
/*
* 配置的设备名中如果存在":"，则表示
* 配置了别名。由于需要根据名称操作，
* 因此先将该设备名截断，后续再恢复
*/
colon = strchr(ifr.ifr_name, ':');
if (colon)
*colon = 0;
/*
* 根据网络设备名，记载相应的设备驱动
* 模块
*/
dev_load(net, ifr.ifr_name);
/*
* 进行相关校验。对于获取操作，则检测
* 地址族是否为AF_INET；对于设置操作，
* 则必须要有相应的特权；而对于SIOCSIFADDR、
* SIOCSIFBRDADDR、SIOCSIFDSTADDR和SIOCSIFNETMASK操作，
* 地址族也必须是AF_INET。
*/
switch (cmd) {
case SIOCGIFADDR: /* Get interface address */
case SIOCGIFBRDADDR: /* Get the broadcast address */
case SIOCGIFDSTADDR: /* Get the destination address */
case SIOCGIFNETMASK: /* Get the netmask for the interface */
/* Note that these ioctls will not sleep,
so that we do not impose a lock.
One day we will be forced to put shlock here (I mean SMP)
*/
tryaddrmatch = (sin_orig.sin_family == AF_INET);
memset(sin, 0, sizeof(*sin));
sin->sin_family = AF_INET;
break;
case SIOCSIFFLAGS:
ret = -EACCES;
if (!capable(CAP_NET_ADMIN))
goto out;
break;
case SIOCSIFADDR: /* Set interface address (and family) */
case SIOCSIFBRDADDR: /* Set the broadcast address */
case SIOCSIFDSTADDR: /* Set the destination address */
case SIOCSIFNETMASK: /* Set the netmask for the interface */
ret = -EACCES;
if (!capable(CAP_NET_ADMIN))
goto out;
ret = -EINVAL;
if (sin->sin_family != AF_INET)
goto out;
break;
default:
ret = -EINVAL;
goto out;
}
rtnl_lock();
ret = -ENODEV;
/*
* 根据网络设备名获取网络设备
*/
if ((dev = __dev_get_by_name(net, ifr.ifr_name)) == NULL)
goto done;
/*
* 恢复配置参数中的标签别名
*/
if (colon)
*colon = ':';
/*
* 取IP配置块，及用户地址标签对应的设备地址
* 结构
*/
if ((in_dev = __in_dev_get_rtnl(dev)) != NULL) {
if (tryaddrmatch) {
/* Matthias Andree */
/* compare label and address (4.4BSD style) */
/* note: we only do this for a limited set of ioctls
and only if the original address family was AF_INET.
This is checked above. */
for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
ifap = &ifa->ifa_next) {
if (!strcmp(ifr.ifr_name, ifa->ifa_label) &&
sin_orig.sin_addr.s_addr ==
ifa->ifa_address) {
break; /* found */
}
}
}
/* we didn't get a match, maybe the application is
4.3BSD-style and passed in junk so we fall back to
comparing just the label */
if (!ifa) {
for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
ifap = &ifa->ifa_next)
if (!strcmp(ifr.ifr_name, ifa->ifa_label))
break;
}
}
/*
* 设置地址和标志。SIOCSIFFLAGS是设置网络设备
* 的标志，SIOCSIFADDR是添加IP地址，这两个操作
* 不针对现有的IP地址块。而其他操作
* ，如SIOCGIFBRDADDR，都是针对现有的IP地址块，如果
* 不存在与配置参数中的标签或地址匹配的IP
* 地址块，则不能继续操作。
*/
ret = -EADDRNOTAVAIL;
if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS)
goto done;
/*
* 针对具体的命令进行操作。
*/
switch (cmd) {
/*
* 获取指定网络设备的本地IP地址
*/
case SIOCGIFADDR: /* Get interface address */
sin->sin_addr.s_addr = ifa->ifa_local;
goto rarok;
/*
* 获取指定网络设备的组播地址
*/
case SIOCGIFBRDADDR: /* Get the broadcast address */
sin->sin_addr.s_addr = ifa->ifa_broadcast;
goto rarok;
/*
* 在点对点连接的情况下，获取指定
* 网络设备点对点对端的IP地址
*/
case SIOCGIFDSTADDR: /* Get the destination address */
sin->sin_addr.s_addr = ifa->ifa_address;
goto rarok;
/*
* 获取指定网络设备的地址掩码
*/
case SIOCGIFNETMASK: /* Get the netmask for the interface */
sin->sin_addr.s_addr = ifa->ifa_mask;
goto rarok;
/*
* 获取网络设备的标志
*/
case SIOCSIFFLAGS:
/*
* 对于关闭网络设备，如果指定了网络
* 设备别名，并且存在与之对应的
* IP地址块，则需要删除释放该IP地址块
*/
if (colon) {
ret = -EADDRNOTAVAIL;
if (!ifa)
break;
ret = 0;
if (!(ifr.ifr_flags & IFF_UP))
inet_del_ifa(in_dev, ifap, 1);
break;
}
/*
* 将地址设置到网络设备中。
*/
ret = dev_change_flags(dev, ifr.ifr_flags);
break;
/*
* 设置指定网络设备的本地地址
*/
case SIOCSIFADDR: /* Set interface address (and family) */
ret = -EINVAL;
/*
* 根据本地地址默认的掩码长度，校验
* 本地地址的有效性
*/
if (inet_abc_len(sin->sin_addr.s_addr) < 0)
break;
/*
* 如果尚未分配IP地址块，则进行分配，
* 并将网络设备别名或网络设备名
* 设置到地址标签中
*/
if (!ifa) {
ret = -ENOBUFS;
if ((ifa = inet_alloc_ifa()) == NULL)
break;
if (colon)
memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
} else {
ret = 0;
if (ifa->ifa_local == sin->sin_addr.s_addr)
break;
/*
* 首先将对应的IP地址块从地址列表
* 中删除
*/