-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathrtnetlink.c
executable file
·1857 lines (1575 loc) · 45.8 KB
/
rtnetlink.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
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Routing netlink socket interface: protocol independent part.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* 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.
*
* Fixes:
* Vitaly E. Lavrov RTA_OK arithmetics was wrong.
*/
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/kernel.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/security.h>
#include <linux/mutex.h>
#include <linux/if_addr.h>
#include <linux/pci.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/udp.h>
#include <net/sock.h>
#include <net/pkt_sched.h>
#include <net/fib_rules.h>
#include <net/rtnetlink.h>
#include <net/net_namespace.h>
struct rtnl_link {
rtnl_doit_func doit;
rtnl_dumpit_func dumpit;
};
//static DEFINE_MUTEX(rtnl_mutex);
struct mutex rtnl_mutex = __MUTEX_INITIALIZER(rtnl_mutex);
void rtnl_lock(void)
{
mutex_lock(&rtnl_mutex);
}
EXPORT_SYMBOL(rtnl_lock);
void __rtnl_unlock(void)
{
mutex_unlock(&rtnl_mutex);
}
void rtnl_unlock(void)
{
/* This fellow will unlock it for us. */
netdev_run_todo();
}
EXPORT_SYMBOL(rtnl_unlock);
int rtnl_trylock(void)
{
return mutex_trylock(&rtnl_mutex);
}
EXPORT_SYMBOL(rtnl_trylock);
int rtnl_is_locked(void)
{
return mutex_is_locked(&rtnl_mutex);
}
EXPORT_SYMBOL(rtnl_is_locked);
#ifdef CONFIG_PROVE_LOCKING
int lockdep_rtnl_is_held(void)
{
return lockdep_is_held(&rtnl_mutex);
}
EXPORT_SYMBOL(lockdep_rtnl_is_held);
#endif /* #ifdef CONFIG_PROVE_LOCKING */
/*下面以命令#tc qdisc add dev eth0 root handle 22 prio bands 4为例子说明如何进行通信的。
分析tc：main(int argc, char **argv)被调用，此函数在tc/tc.c中；
分析tc qdisc：do_qdisc(argc-2, argv+2);被调用，此函数在tc/tc_qdisc.c中；
分析tc qdisc add： tc_qdisc_modify(RTM_NEWQDISC, NLM_F_EXCL|NLM_F_CREATE, argc-1, argv+1); 被调用，此函数在tc/tc_qdisc.c中，在这个函数中，将分析完这一行tc的命令，各种参数（例如RTM_NEWQDISC） 被写到netlink包中，并且开始与核心通信。
Netlink包携带的数据如下
struct {
struct nlmsghdr n;
struct tcmsg t;
char buf[TCA_BUF_MAX];
} req;
req.n.nlmsg_type = cmd; = RTM_NEWQDISC
req.t.tcm_family = AF_UNSPEC;
内核是根据以上两个参数定位接收函数。
内核接收函数是static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
根据以上两个参数选择接收函数：
doit = rtnl_get_doit(family, type);
从前面初始化时注册的处理函数是：
rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL);
可以知道对应的接收函数是：
static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
通信总结如下：
1. 内核调用void rtnl_register(int protocol, int msgtype, rtnl_doit_func doit, rtnl_dumpit_func dumpit)将接收函数注册到rtnl_msg_handlers中。
2. 用户空间填充netlink数据包，使用的netlink协议是NETLINK_ROUTE。
3. 内核根据netlink数据包中的protocol和msgtype字段，搜索rtnl_msg_handlers，定位接收函数。
*/
//每个表头rtnl_msg_handlers[i]上面存储RTM_NR_MSGTYPES个rtnl_link，图解见TC流量控制实现分析
static struct rtnl_link *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1]; //rtnl_register注册的proto msgtype分布到该结构中，每个对应的函数见pktsched_init
static inline int rtm_msgindex(int msgtype)
{
int msgindex = msgtype - RTM_BASE;
/*
* msgindex < 0 implies someone tried to register a netlink
* control code. msgindex >= RTM_NR_MSGTYPES may indicate that
* the message type has not been added to linux/rtnetlink.h
*/
BUG_ON(msgindex < 0 || msgindex >= RTM_NR_MSGTYPES);
return msgindex;
}
//tc rtnl的dot函数在pktsched_init
static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex)
{
struct rtnl_link *tab;
if (protocol <= RTNL_FAMILY_MAX)
tab = rtnl_msg_handlers[protocol];
else
tab = NULL;
if (tab == NULL || tab[msgindex].doit == NULL)
tab = rtnl_msg_handlers[PF_UNSPEC];
return tab ? tab[msgindex].doit : NULL;
}
//tc rtnl的dumpit函数在pktsched_init
static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
{
struct rtnl_link *tab;
if (protocol <= RTNL_FAMILY_MAX)
tab = rtnl_msg_handlers[protocol];
else
tab = NULL;
if (tab == NULL || tab[msgindex].dumpit == NULL)
tab = rtnl_msg_handlers[PF_UNSPEC];
return tab ? tab[msgindex].dumpit : NULL;
}
/**
* __rtnl_register - Register a rtnetlink message type
* @protocol: Protocol family or PF_UNSPEC
* @msgtype: rtnetlink message type
* @doit: Function pointer called for each request message
* @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
*
* Registers the specified function pointers (at least one of them has
* to be non-NULL) to be called whenever a request message for the
* specified protocol family and message type is received.
*
* The special protocol family PF_UNSPEC may be used to define fallback
* function pointers for the case when no entry for the specific protocol
* family exists.
*
* Returns 0 on success or a negative error code.
*/
int __rtnl_register(int protocol, int msgtype,
rtnl_doit_func doit, rtnl_dumpit_func dumpit)
{
struct rtnl_link *tab;
int msgindex;
BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
msgindex = rtm_msgindex(msgtype);
tab = rtnl_msg_handlers[protocol];
if (tab == NULL) {
tab = kcalloc(RTM_NR_MSGTYPES, sizeof(*tab), GFP_KERNEL);
if (tab == NULL)
return -ENOBUFS;
rtnl_msg_handlers[protocol] = tab;
}
if (doit)
tab[msgindex].doit = doit;
if (dumpit)
tab[msgindex].dumpit = dumpit;
return 0;
}
EXPORT_SYMBOL_GPL(__rtnl_register);
/**
* rtnl_register - Register a rtnetlink message type
*
* Identical to __rtnl_register() but panics on failure. This is useful
* as failure of this function is very unlikely, it can only happen due
* to lack of memory when allocating the chain to store all message
* handlers for a protocol. Meant for use in init functions where lack
* of memory implies no sense in continueing.
*///其中的rtnl_register()函数用于注册TC要接收的消息类型以及对应的接收函数。
void rtnl_register(int protocol, int msgtype,
rtnl_doit_func doit, rtnl_dumpit_func dumpit)
{
if (__rtnl_register(protocol, msgtype, doit, dumpit) < 0)
panic("Unable to register rtnetlink message handler, "
"protocol = %d, message type = %d\n",
protocol, msgtype);
}
EXPORT_SYMBOL_GPL(rtnl_register);
/**
* rtnl_unregister - Unregister a rtnetlink message type
* @protocol: Protocol family or PF_UNSPEC
* @msgtype: rtnetlink message type
*
* Returns 0 on success or a negative error code.
*/
int rtnl_unregister(int protocol, int msgtype)
{
int msgindex;
BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
msgindex = rtm_msgindex(msgtype);
if (rtnl_msg_handlers[protocol] == NULL)
return -ENOENT;
rtnl_msg_handlers[protocol][msgindex].doit = NULL;
rtnl_msg_handlers[protocol][msgindex].dumpit = NULL;
return 0;
}
EXPORT_SYMBOL_GPL(rtnl_unregister);
/**
* rtnl_unregister_all - Unregister all rtnetlink message type of a protocol
* @protocol : Protocol family or PF_UNSPEC
*
* Identical to calling rtnl_unregster() for all registered message types
* of a certain protocol family.
*/
void rtnl_unregister_all(int protocol)
{
BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
kfree(rtnl_msg_handlers[protocol]);
rtnl_msg_handlers[protocol] = NULL;
}
EXPORT_SYMBOL_GPL(rtnl_unregister_all);
static LIST_HEAD(link_ops);
/**
* __rtnl_link_register - Register rtnl_link_ops with rtnetlink.
* @ops: struct rtnl_link_ops * to register
*
* The caller must hold the rtnl_mutex. This function should be used
* by drivers that create devices during module initialization. It
* must be called before registering the devices.
*
* Returns 0 on success or a negative error code.
*/
int __rtnl_link_register(struct rtnl_link_ops *ops)
{
if (!ops->dellink)
ops->dellink = unregister_netdevice_queue;
list_add_tail(&ops->list, &link_ops);
return 0;
}
EXPORT_SYMBOL_GPL(__rtnl_link_register);
/**
* rtnl_link_register - Register rtnl_link_ops with rtnetlink.
* @ops: struct rtnl_link_ops * to register
*
* Returns 0 on success or a negative error code.
*/
int rtnl_link_register(struct rtnl_link_ops *ops)
{
int err;
rtnl_lock();
err = __rtnl_link_register(ops);
rtnl_unlock();
return err;
}
EXPORT_SYMBOL_GPL(rtnl_link_register);
static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops)
{
struct net_device *dev;
LIST_HEAD(list_kill);
for_each_netdev(net, dev) {
if (dev->rtnl_link_ops == ops)
ops->dellink(dev, &list_kill);
}
unregister_netdevice_many(&list_kill);
}
void rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops)
{
rtnl_lock();
__rtnl_kill_links(net, ops);
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(rtnl_kill_links);
/**
* __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
* @ops: struct rtnl_link_ops * to unregister
*
* The caller must hold the rtnl_mutex.
*/
void __rtnl_link_unregister(struct rtnl_link_ops *ops)
{
struct net *net;
for_each_net(net) {
__rtnl_kill_links(net, ops);
}
list_del(&ops->list);
}
EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
/**
* rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
* @ops: struct rtnl_link_ops * to unregister
*/
void rtnl_link_unregister(struct rtnl_link_ops *ops)
{
rtnl_lock();
__rtnl_link_unregister(ops);
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(rtnl_link_unregister);
static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind)
{
const struct rtnl_link_ops *ops;
list_for_each_entry(ops, &link_ops, list) {
if (!strcmp(ops->kind, kind))
return ops;
}
return NULL;
}
static size_t rtnl_link_get_size(const struct net_device *dev)
{
const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
size_t size;
if (!ops)
return 0;
size = nlmsg_total_size(sizeof(struct nlattr)) + /* IFLA_LINKINFO */
nlmsg_total_size(strlen(ops->kind) + 1); /* IFLA_INFO_KIND */
if (ops->get_size)
/* IFLA_INFO_DATA + nested data */
size += nlmsg_total_size(sizeof(struct nlattr)) +
ops->get_size(dev);
if (ops->get_xstats_size)
size += ops->get_xstats_size(dev); /* IFLA_INFO_XSTATS */
return size;
}
static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev)
{
const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
struct nlattr *linkinfo, *data;
int err = -EMSGSIZE;
linkinfo = nla_nest_start(skb, IFLA_LINKINFO);
if (linkinfo == NULL)
goto out;
if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0)
goto err_cancel_link;
if (ops->fill_xstats) {
err = ops->fill_xstats(skb, dev);
if (err < 0)
goto err_cancel_link;
}
if (ops->fill_info) {
data = nla_nest_start(skb, IFLA_INFO_DATA);
if (data == NULL)
goto err_cancel_link;
err = ops->fill_info(skb, dev);
if (err < 0)
goto err_cancel_data;
nla_nest_end(skb, data);
}
nla_nest_end(skb, linkinfo);
return 0;
err_cancel_data:
nla_nest_cancel(skb, data);
err_cancel_link:
nla_nest_cancel(skb, linkinfo);
out:
return err;
}
static const int rtm_min[RTM_NR_FAMILIES] =
{
[RTM_FAM(RTM_NEWLINK)] = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
[RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)),
[RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)),
[RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)),
[RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)),
[RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)),
[RTM_FAM(RTM_NEWTFILTER)] = NLMSG_LENGTH(sizeof(struct tcmsg)),
[RTM_FAM(RTM_NEWACTION)] = NLMSG_LENGTH(sizeof(struct tcamsg)),
[RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
[RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
};
static const int rta_max[RTM_NR_FAMILIES] =
{
[RTM_FAM(RTM_NEWLINK)] = IFLA_MAX,
[RTM_FAM(RTM_NEWADDR)] = IFA_MAX,
[RTM_FAM(RTM_NEWROUTE)] = RTA_MAX,
[RTM_FAM(RTM_NEWRULE)] = FRA_MAX,
[RTM_FAM(RTM_NEWQDISC)] = TCA_MAX,
[RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX,
[RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX,
[RTM_FAM(RTM_NEWACTION)] = TCAA_MAX,
};
void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data)
{
struct rtattr *rta;
int size = RTA_LENGTH(attrlen);
rta = (struct rtattr *)skb_put(skb, RTA_ALIGN(size));
rta->rta_type = attrtype;
rta->rta_len = size;
memcpy(RTA_DATA(rta), data, attrlen);
memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size);
}
EXPORT_SYMBOL(__rta_fill);
int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo)
{
struct sock *rtnl = net->rtnl;
int err = 0;
NETLINK_CB(skb).dst_group = group;
if (echo)
atomic_inc(&skb->users);
netlink_broadcast(rtnl, skb, pid, group, GFP_KERNEL);
if (echo)
err = netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT);
return err;
}
int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid)
{
struct sock *rtnl = net->rtnl;
return nlmsg_unicast(rtnl, skb, pid);
}
EXPORT_SYMBOL(rtnl_unicast);
void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
struct nlmsghdr *nlh, gfp_t flags)
{
struct sock *rtnl = net->rtnl;
int report = 0;
if (nlh)
report = nlmsg_report(nlh);
nlmsg_notify(rtnl, skb, pid, group, report, flags);
}
EXPORT_SYMBOL(rtnl_notify);
void rtnl_set_sk_err(struct net *net, u32 group, int error)
{
struct sock *rtnl = net->rtnl;
netlink_set_err(rtnl, 0, group, error);
}
EXPORT_SYMBOL(rtnl_set_sk_err);
int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
{
struct nlattr *mx;
int i, valid = 0;
mx = nla_nest_start(skb, RTA_METRICS);
if (mx == NULL)
return -ENOBUFS;
for (i = 0; i < RTAX_MAX; i++) {
if (metrics[i]) {
valid++;
NLA_PUT_U32(skb, i+1, metrics[i]);
}
}
if (!valid) {
nla_nest_cancel(skb, mx);
return 0;
}
return nla_nest_end(skb, mx);
nla_put_failure:
nla_nest_cancel(skb, mx);
return -EMSGSIZE;
}
EXPORT_SYMBOL(rtnetlink_put_metrics);
int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
u32 ts, u32 tsage, long expires, u32 error)
{
struct rta_cacheinfo ci = {
.rta_lastuse = jiffies_to_clock_t(jiffies - dst->lastuse),
.rta_used = dst->__use,
.rta_clntref = atomic_read(&(dst->__refcnt)),
.rta_error = error,
.rta_id = id,
.rta_ts = ts,
.rta_tsage = tsage,
};
if (expires)
ci.rta_expires = jiffies_to_clock_t(expires);
return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci);
}
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
static void set_operstate(struct net_device *dev, unsigned char transition)
{
unsigned char operstate = dev->operstate;
switch (transition) {
case IF_OPER_UP:
if ((operstate == IF_OPER_DORMANT ||
operstate == IF_OPER_UNKNOWN) &&
!netif_dormant(dev))
operstate = IF_OPER_UP;
break;
case IF_OPER_DORMANT:
if (operstate == IF_OPER_UP ||
operstate == IF_OPER_UNKNOWN)
operstate = IF_OPER_DORMANT;
break;
}
if (dev->operstate != operstate) {
write_lock_bh(&dev_base_lock);
dev->operstate = operstate;
write_unlock_bh(&dev_base_lock);
netdev_state_change(dev);
}
}
static unsigned int rtnl_dev_combine_flags(const struct net_device *dev,
const struct ifinfomsg *ifm)
{
unsigned int flags = ifm->ifi_flags;
/* bugwards compatibility: ifi_change == 0 is treated as ~0 */
if (ifm->ifi_change)
flags = (flags & ifm->ifi_change) |
(dev->flags & ~ifm->ifi_change);
return flags;
}
static void copy_rtnl_link_stats(struct rtnl_link_stats *a,
const struct net_device_stats *b)
{
a->rx_packets = b->rx_packets;
a->tx_packets = b->tx_packets;
a->rx_bytes = b->rx_bytes;
a->tx_bytes = b->tx_bytes;
a->rx_errors = b->rx_errors;
a->tx_errors = b->tx_errors;
a->rx_dropped = b->rx_dropped;
a->tx_dropped = b->tx_dropped;
a->multicast = b->multicast;
a->collisions = b->collisions;
a->rx_length_errors = b->rx_length_errors;
a->rx_over_errors = b->rx_over_errors;
a->rx_crc_errors = b->rx_crc_errors;
a->rx_frame_errors = b->rx_frame_errors;
a->rx_fifo_errors = b->rx_fifo_errors;
a->rx_missed_errors = b->rx_missed_errors;
a->tx_aborted_errors = b->tx_aborted_errors;
a->tx_carrier_errors = b->tx_carrier_errors;
a->tx_fifo_errors = b->tx_fifo_errors;
a->tx_heartbeat_errors = b->tx_heartbeat_errors;
a->tx_window_errors = b->tx_window_errors;
a->rx_compressed = b->rx_compressed;
a->tx_compressed = b->tx_compressed;
}
static void copy_rtnl_link_stats64(void *v, const struct net_device_stats *b)
{
struct rtnl_link_stats64 a;
a.rx_packets = b->rx_packets;
a.tx_packets = b->tx_packets;
a.rx_bytes = b->rx_bytes;
a.tx_bytes = b->tx_bytes;
a.rx_errors = b->rx_errors;
a.tx_errors = b->tx_errors;
a.rx_dropped = b->rx_dropped;
a.tx_dropped = b->tx_dropped;
a.multicast = b->multicast;
a.collisions = b->collisions;
a.rx_length_errors = b->rx_length_errors;
a.rx_over_errors = b->rx_over_errors;
a.rx_crc_errors = b->rx_crc_errors;
a.rx_frame_errors = b->rx_frame_errors;
a.rx_fifo_errors = b->rx_fifo_errors;
a.rx_missed_errors = b->rx_missed_errors;
a.tx_aborted_errors = b->tx_aborted_errors;
a.tx_carrier_errors = b->tx_carrier_errors;
a.tx_fifo_errors = b->tx_fifo_errors;
a.tx_heartbeat_errors = b->tx_heartbeat_errors;
a.tx_window_errors = b->tx_window_errors;
a.rx_compressed = b->rx_compressed;
a.tx_compressed = b->tx_compressed;
memcpy(v, &a, sizeof(a));
}
/* All VF info */
static inline int rtnl_vfinfo_size(const struct net_device *dev)
{
if (dev->dev.parent && dev_is_pci(dev->dev.parent)) {
int num_vfs = dev_num_vf(dev->dev.parent);
size_t size = nla_total_size(sizeof(struct nlattr));
size += nla_total_size(num_vfs * sizeof(struct nlattr));
size += num_vfs *
(nla_total_size(sizeof(struct ifla_vf_mac)) +
nla_total_size(sizeof(struct ifla_vf_vlan)) +
nla_total_size(sizeof(struct ifla_vf_tx_rate)));
return size;
} else
return 0;
}
static size_t rtnl_port_size(const struct net_device *dev)
{
size_t port_size = nla_total_size(4) /* PORT_VF */
+ nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */
+ nla_total_size(sizeof(struct ifla_port_vsi))
/* PORT_VSI_TYPE */
+ nla_total_size(PORT_UUID_MAX) /* PORT_INSTANCE_UUID */
+ nla_total_size(PORT_UUID_MAX) /* PORT_HOST_UUID */
+ nla_total_size(1) /* PROT_VDP_REQUEST */
+ nla_total_size(2); /* PORT_VDP_RESPONSE */
size_t vf_ports_size = nla_total_size(sizeof(struct nlattr));
size_t vf_port_size = nla_total_size(sizeof(struct nlattr))
+ port_size;
size_t port_self_size = nla_total_size(sizeof(struct nlattr))
+ port_size;
if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
return 0;
if (dev_num_vf(dev->dev.parent))
return port_self_size + vf_ports_size +
vf_port_size * dev_num_vf(dev->dev.parent);
else
return port_self_size;
}
static inline size_t if_nlmsg_size(const struct net_device *dev)
{
return NLMSG_ALIGN(sizeof(struct ifinfomsg))
+ nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
+ nla_total_size(IFALIASZ) /* IFLA_IFALIAS */
+ nla_total_size(IFNAMSIZ) /* IFLA_QDISC */
+ nla_total_size(sizeof(struct rtnl_link_ifmap))
+ nla_total_size(sizeof(struct rtnl_link_stats))
+ nla_total_size(sizeof(struct rtnl_link_stats64))
+ nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
+ nla_total_size(MAX_ADDR_LEN) /* IFLA_BROADCAST */
+ nla_total_size(4) /* IFLA_TXQLEN */
+ nla_total_size(4) /* IFLA_WEIGHT */
+ nla_total_size(4) /* IFLA_MTU */
+ nla_total_size(4) /* IFLA_LINK */
+ nla_total_size(4) /* IFLA_MASTER */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ nla_total_size(4) /* IFLA_NUM_VF */
+ rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */
+ rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ rtnl_link_get_size(dev); /* IFLA_LINKINFO */
}
static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
{
struct nlattr *vf_ports;
struct nlattr *vf_port;
int vf;
int err;
vf_ports = nla_nest_start(skb, IFLA_VF_PORTS);
if (!vf_ports)
return -EMSGSIZE;
for (vf = 0; vf < dev_num_vf(dev->dev.parent); vf++) {
vf_port = nla_nest_start(skb, IFLA_VF_PORT);
if (!vf_port)
goto nla_put_failure;
NLA_PUT_U32(skb, IFLA_PORT_VF, vf);
err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb);
if (err == -EMSGSIZE)
goto nla_put_failure;
if (err) {
nla_nest_cancel(skb, vf_port);
continue;
}
nla_nest_end(skb, vf_port);
}
nla_nest_end(skb, vf_ports);
return 0;
nla_put_failure:
nla_nest_cancel(skb, vf_ports);
return -EMSGSIZE;
}
static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
{
struct nlattr *port_self;
int err;
port_self = nla_nest_start(skb, IFLA_PORT_SELF);
if (!port_self)
return -EMSGSIZE;
err = dev->netdev_ops->ndo_get_vf_port(dev, PORT_SELF_VF, skb);
if (err) {
nla_nest_cancel(skb, port_self);
return (err == -EMSGSIZE) ? err : 0;
}
nla_nest_end(skb, port_self);
return 0;
}
static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev)
{
int err;
if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
return 0;
err = rtnl_port_self_fill(skb, dev);
if (err)
return err;
if (dev_num_vf(dev->dev.parent)) {
err = rtnl_vf_ports_fill(skb, dev);
if (err)
return err;
}
return 0;
}
static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags)
{
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
const struct net_device_stats *stats;
struct nlattr *attr;
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
if (nlh == NULL)
return -EMSGSIZE;
ifm = nlmsg_data(nlh);
ifm->ifi_family = AF_UNSPEC;
ifm->__ifi_pad = 0;
ifm->ifi_type = dev->type;
ifm->ifi_index = dev->ifindex;
ifm->ifi_flags = dev_get_flags(dev);
ifm->ifi_change = change;
NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name);
NLA_PUT_U32(skb, IFLA_TXQLEN, dev->tx_queue_len);
NLA_PUT_U8(skb, IFLA_OPERSTATE,
netif_running(dev) ? dev->operstate : IF_OPER_DOWN);
NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode);
NLA_PUT_U32(skb, IFLA_MTU, dev->mtu);
if (dev->ifindex != dev->iflink)
NLA_PUT_U32(skb, IFLA_LINK, dev->iflink);
if (dev->master)
NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex);
if (dev->qdisc)
NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc->ops->id);
if (dev->ifalias)
NLA_PUT_STRING(skb, IFLA_IFALIAS, dev->ifalias);
if (1) {
struct rtnl_link_ifmap map = {
.mem_start = dev->mem_start,
.mem_end = dev->mem_end,
.base_addr = dev->base_addr,
.irq = dev->irq,
.dma = dev->dma,
.port = dev->if_port,
};
NLA_PUT(skb, IFLA_MAP, sizeof(map), &map);
}
if (dev->addr_len) {
NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr);
NLA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast);
}
attr = nla_reserve(skb, IFLA_STATS,
sizeof(struct rtnl_link_stats));
if (attr == NULL)
goto nla_put_failure;
stats = dev_get_stats(dev);
copy_rtnl_link_stats(nla_data(attr), stats);
attr = nla_reserve(skb, IFLA_STATS64,
sizeof(struct rtnl_link_stats64));
if (attr == NULL)
goto nla_put_failure;
copy_rtnl_link_stats64(nla_data(attr), stats);
if (dev->dev.parent)
NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent));
if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) {
int i;
struct nlattr *vfinfo, *vf;
int num_vfs = dev_num_vf(dev->dev.parent);
vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST);
if (!vfinfo)
goto nla_put_failure;
for (i = 0; i < num_vfs; i++) {
struct ifla_vf_info ivi;
struct ifla_vf_mac vf_mac;
struct ifla_vf_vlan vf_vlan;
struct ifla_vf_tx_rate vf_tx_rate;
if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi))
break;
vf_mac.vf = vf_vlan.vf = vf_tx_rate.vf = ivi.vf;
memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
vf_vlan.vlan = ivi.vlan;
vf_vlan.qos = ivi.qos;
vf_tx_rate.rate = ivi.tx_rate;
vf = nla_nest_start(skb, IFLA_VF_INFO);
if (!vf) {
nla_nest_cancel(skb, vfinfo);
goto nla_put_failure;
}
NLA_PUT(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac);
NLA_PUT(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan);
NLA_PUT(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), &vf_tx_rate);
nla_nest_end(skb, vf);
}
nla_nest_end(skb, vfinfo);
}
if (rtnl_port_fill(skb, dev))
goto nla_put_failure;
if (dev->rtnl_link_ops) {
if (rtnl_link_fill(skb, dev) < 0)
goto nla_put_failure;
}
return nlmsg_end(skb, nlh);
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
int h, s_h;
int idx = 0, s_idx;
struct net_device *dev;
struct hlist_head *head;
struct hlist_node *node;
s_h = cb->args[0];
s_idx = cb->args[1];
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
hlist_for_each_entry(dev, node, head, index_hlist) {
if (idx < s_idx)
goto cont;
if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, 0,
NLM_F_MULTI) <= 0)
goto out;
cont:
idx++;
}
}
out:
cb->args[1] = idx;
cb->args[0] = h;
return skb->len;
}
const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 },
[IFLA_ADDRESS] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[IFLA_BROADCAST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) },
[IFLA_MTU] = { .type = NLA_U32 },
[IFLA_LINK] = { .type = NLA_U32 },
[IFLA_TXQLEN] = { .type = NLA_U32 },
[IFLA_WEIGHT] = { .type = NLA_U32 },
[IFLA_OPERSTATE] = { .type = NLA_U8 },
[IFLA_LINKMODE] = { .type = NLA_U8 },
[IFLA_LINKINFO] = { .type = NLA_NESTED },
[IFLA_NET_NS_PID] = { .type = NLA_U32 },
[IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 },
[IFLA_VFINFO_LIST] = {. type = NLA_NESTED },
[IFLA_VF_PORTS] = { .type = NLA_NESTED },
[IFLA_PORT_SELF] = { .type = NLA_NESTED },
};
EXPORT_SYMBOL(ifla_policy);
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
[IFLA_INFO_KIND] = { .type = NLA_STRING },
[IFLA_INFO_DATA] = { .type = NLA_NESTED },
};
static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
[IFLA_VF_INFO] = { .type = NLA_NESTED },