-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathaf_netlink.c
executable file
·2221 lines (1866 loc) · 55.4 KB
/
af_netlink.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
/*
* NETLINK Kernel-user communication protocol.
*
* Authors: Alan Cox <alan@lxorguk.ukuu.org.uk>
* 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.
*
* Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith
* added netlink_proto_exit
* Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <acme@conectiva.com.br>
* use nlk_sk, as sk->protinfo is on a diet 8)
* Fri Jul 22 19:51:12 MEST 2005 Harald Welte <laforge@gnumonks.org>
* - inc module use count of module that owns
* the kernel socket in case userspace opens
* socket of same protocol
* - remove all module support, since netlink is
* mandatory if CONFIG_NET=y these days
*/
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/socket.h>
#include <linux/un.h>
#include <linux/fcntl.h>
#include <linux/termios.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/security.h>
#include <linux/jhash.h>
#include <linux/jiffies.h>
#include <linux/random.h>
#include <linux/bitops.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <linux/audit.h>
#include <linux/mutex.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/scm.h>
#include <net/netlink.h>
#define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8)
#define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long))
struct netlink_sock {//第一个成员就是struct sock
/* struct sock has to be the first member of netlink_sock */
struct sock sk;
u32 pid;// 自己的pid, 通常是0
u32 dst_pid;// 对方的pid
u32 dst_group;// 对方的组
u32 flags;//如果是内核刚创建套接字netlink_kernel_create，则flags |= NETLINK_KERNEL_SOCKET
u32 subscriptions;
u32 ngroups;
unsigned long *groups;
unsigned long state;
wait_queue_head_t wait;//等待队列wake_up_interruptible_all wake_up_interruptible进行唤醒 add_wait_queue添加 wait_event和wait_event_interruptible挂起等待 可以在af_netlink.c中搜索我wait字符串查找
struct netlink_callback *cb;
struct mutex *cb_mutex;
struct mutex cb_def_mutex;
void (*netlink_rcv)(struct sk_buff *skb);//// 数据到达时 //的操作, netlink可有不同类型, 如ROUTE, FIREWALL, ARPD等, netlink_kernel_create的input函数,也就是netlink接收应用层数据的函数
struct module *module;
};
struct listeners_rcu_head {
struct rcu_head rcu_head;
void *ptr;
};
#define NETLINK_KERNEL_SOCKET 0x1
#define NETLINK_RECV_PKTINFO 0x2
#define NETLINK_BROADCAST_SEND_ERROR 0x4
#define NETLINK_RECV_NO_ENOBUFS 0x8
static inline struct netlink_sock *nlk_sk(struct sock *sk)
{
return container_of(sk, struct netlink_sock, sk);
}
static inline int netlink_is_kernel(struct sock *sk)
{
return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET;
}
struct nl_pid_hash {
struct hlist_head *table;
unsigned long rehash_time;// 重新计算HASH的时间间隔
unsigned int mask;
unsigned int shift;
unsigned int entries;// 链表节点数
unsigned int max_shift; // 最大幂值
u32 rnd;// 随机数
};
//最大可有MAX_LINKS(32)个表， 头部全局变量在 static struct netlink_table *nl_table;
struct netlink_table {
struct nl_pid_hash hash;// 根据pid进行HASH的netlink sock链表, 相当于客户端链表
struct hlist_head mc_list;// 多播的sock链表
unsigned long *listeners;//listerns是个位图对应groups中每个元素
unsigned int nl_nonroot;
unsigned int groups; // 每个netlink的协议类型可以定义多个组, 8的倍数,最小是32
struct mutex *cb_mutex;
struct module *module;
int registered;// 该标志表示该项被登记
};
static struct netlink_table *nl_table;
//这里面存的是struct nl_pid_hash *hash = &nl_table[i].hash;，i的范围0到MAX_LINKS，该结构为MAX_LINKS中的每种netlink协议类型添加一种
//见netlink_proto_init函数，在改函数中只开辟了MAX_LINKS个指针空间大小，所以NETLINK最多可以使用32个，其中前16个已经被系统使用
//static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
static wait_queue_head_t nl_table_wait;
static int netlink_dump(struct sock *sk);
static void netlink_destroy_callback(struct netlink_callback *cb);
//static DEFINE_RWLOCK(nl_table_lock); yang change
struct atomic_notifier_head nl_table_lock；
static atomic_t nl_table_users = ATOMIC_INIT(0); //没创建一个netlink netlink_create,该值加1
//static ATOMIC_NOTIFIER_HEAD(netlink_chain);
struct atomic_notifier_head netlink_chain;//
static u32 netlink_group_mask(u32 group)
{
return group ? 1 << (group - 1) : 0;
}
// nl_pid_hashfn根据pid查找相应HASH链表头
static struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid)
{
return &hash->table[jhash_1word(pid, hash->rnd) & hash->mask];
}
static void netlink_sock_destruct(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (nlk->cb) {
if (nlk->cb->done)
nlk->cb->done(nlk->cb);
netlink_destroy_callback(nlk->cb);
}
skb_queue_purge(&sk->sk_receive_queue);
if (!sock_flag(sk, SOCK_DEAD)) {
printk(KERN_ERR "Freeing alive netlink socket %p\n", sk);
return;
}
WARN_ON(atomic_read(&sk->sk_rmem_alloc));
WARN_ON(atomic_read(&sk->sk_wmem_alloc));
WARN_ON(nlk_sk(sk)->groups);
}
/* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
* SMP. Look, when several writers sleep and reader wakes them up, all but one
* immediately hit write lock and grab all the cpus. Exclusive sleep solves
* this, _but_ remember, it adds useless work on UP machines.
*/
//与netlink_table_ungrab配对 相当于加解锁
void netlink_table_grab(void)
__acquires(nl_table_lock)
{
might_sleep();
write_lock_irq(&nl_table_lock);
if (atomic_read(&nl_table_users)) {
DECLARE_WAITQUEUE(wait, current);
add_wait_queue_exclusive(&nl_table_wait, &wait);
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (atomic_read(&nl_table_users) == 0)
break;
write_unlock_irq(&nl_table_lock);
schedule();
write_lock_irq(&nl_table_lock);
}
__set_current_state(TASK_RUNNING);
remove_wait_queue(&nl_table_wait, &wait);
}
}
//和netlink_table_grab配对
void netlink_table_ungrab(void)
__releases(nl_table_lock)
{
write_unlock_irq(&nl_table_lock);
wake_up(&nl_table_wait);
}
static inline void
netlink_lock_table(void)
{
/* read_lock() synchronizes us to netlink_table_grab */
read_lock(&nl_table_lock);
atomic_inc(&nl_table_users);
read_unlock(&nl_table_lock);
}
static inline void
netlink_unlock_table(void)
{
if (atomic_dec_and_test(&nl_table_users))
wake_up(&nl_table_wait);
}
static inline struct sock *netlink_lookup(struct net *net, int protocol,
u32 pid)
{
struct nl_pid_hash *hash = &nl_table[protocol].hash;
struct hlist_head *head;
struct sock *sk;
struct hlist_node *node;
read_lock(&nl_table_lock);
head = nl_pid_hashfn(hash, pid);
sk_for_each(sk, node, head) {
if (net_eq(sock_net(sk), net) && (nlk_sk(sk)->pid == pid)) {
sock_hold(sk);
goto found;
}
}
sk = NULL;
found:
read_unlock(&nl_table_lock);
return sk;
}
static inline struct hlist_head *nl_pid_hash_zalloc(size_t size)
{
if (size <= PAGE_SIZE)
return kzalloc(size, GFP_ATOMIC);
else
return (struct hlist_head *)
__get_free_pages(GFP_ATOMIC | __GFP_ZERO,
get_order(size));
}
static inline void nl_pid_hash_free(struct hlist_head *table, size_t size)
{
if (size <= PAGE_SIZE)
kfree(table);
else
free_pages((unsigned long)table, get_order(size));
}
static int nl_pid_hash_rehash(struct nl_pid_hash *hash, int grow)
{
unsigned int omask, mask, shift;
size_t osize, size;
struct hlist_head *otable, *table;
int i;
omask = mask = hash->mask;
osize = size = (mask + 1) * sizeof(*table);
shift = hash->shift;
if (grow) {
if (++shift > hash->max_shift)
return 0;
mask = mask * 2 + 1;
size *= 2;
}
table = nl_pid_hash_zalloc(size);
if (!table)
return 0;
otable = hash->table;
hash->table = table;
hash->mask = mask;
hash->shift = shift;
get_random_bytes(&hash->rnd, sizeof(hash->rnd));
for (i = 0; i <= omask; i++) {
struct sock *sk;
struct hlist_node *node, *tmp;
sk_for_each_safe(sk, node, tmp, &otable[i])
__sk_add_node(sk, nl_pid_hashfn(hash, nlk_sk(sk)->pid));
}
nl_pid_hash_free(otable, osize);
hash->rehash_time = jiffies + 10 * 60 * HZ;
return 1;
}
static inline int nl_pid_hash_dilute(struct nl_pid_hash *hash, int len)
{
int avg = hash->entries >> hash->shift;
if (unlikely(avg > 1) && nl_pid_hash_rehash(hash, 1))
return 1;
if (unlikely(len > avg) && time_after(jiffies, hash->rehash_time)) {
nl_pid_hash_rehash(hash, 0);
return 1;
}
return 0;
}
static const struct proto_ops netlink_ops;
static void
netlink_update_listeners(struct sock *sk)
{
struct netlink_table *tbl = &nl_table[sk->sk_protocol];
struct hlist_node *node;
unsigned long mask;
unsigned int i;
for (i = 0; i < NLGRPLONGS(tbl->groups); i++) {
mask = 0;
sk_for_each_bound(sk, node, &tbl->mc_list) {//// 遍历多播链表生成多播组的掩码
if (i < NLGRPLONGS(nlk_sk(sk)->ngroups))
mask |= nlk_sk(sk)->groups[i];
}
tbl->listeners[i] = mask;
}
/* this function is only called with the netlink table "grabbed", which
* makes sure updates are visible before bind or setsockopt return. */
}
//也就是说，pid是其中最为关键的键值，每个netlink 套接口的protocol+pid可以唯一的确定一个socket实例，这个也可以认为是一个地址
//pid如果为0，则代表内核
//为sock->pid赋值，并把sk添加到hash表中，该hash表通过pid做键值 应用层bind的时候该pid为应用层进程pid，内核netlink_kernel_create创建内核套接字的时候pid为0，0对应内核
////在netlink_insert中会根据PID=0以及 unit(最大32)从而把struct sock *sk添加到nl_table[unit].hash中
static int netlink_insert(struct sock *sk, struct net *net, u32 pid)
{
struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash;
struct hlist_head *head;
int err = -EADDRINUSE;
struct sock *osk;
struct hlist_node *node;
int len;
netlink_table_grab();
head = nl_pid_hashfn(hash, pid);
len = 0;
sk_for_each(osk, node, head) {
if (net_eq(sock_net(osk), net) && (nlk_sk(osk)->pid == pid))// 检查pid是否已经在链表中， 有则失败
break;
len++;
}
if (node)
goto err;
err = -EBUSY;
if (nlk_sk(sk)->pid)
goto err;
err = -ENOMEM;
if (BITS_PER_LONG > 32 && unlikely(hash->entries >= UINT_MAX))
goto err;
if (len && nl_pid_hash_dilute(hash, len))
head = nl_pid_hashfn(hash, pid);
hash->entries++;
nlk_sk(sk)->pid = pid;
sk_add_node(sk, head);
err = 0;
err:
netlink_table_ungrab();
return err;
}
static void netlink_remove(struct sock *sk)
{
netlink_table_grab();
if (sk_del_node_init(sk))
nl_table[sk->sk_protocol].hash.entries--; //entries在netlink_insert函数中自增
if (nlk_sk(sk)->subscriptions)
__sk_del_bind_node(sk);
netlink_table_ungrab();
}
static struct proto netlink_proto = {//tcp 对应tcp_prot udp对应udp_prot
.name = "NETLINK",
.owner = THIS_MODULE,
.obj_size = sizeof(struct netlink_sock),
};
//创建一个sturct sock
//在__netlink_create函数中定义了netlink套接口的操作结构为netlink_ops:
//然后创建static struct proto netlink_proto结构空间，并初始化该结构中的成员
//创建struct sock结构，并把struct socket与struct sock关联起来，通过sock_init_data
static int __netlink_create(struct net *net, struct socket *sock,
struct mutex *cb_mutex, int protocol)
{
struct sock *sk;
struct netlink_sock *nlk;
sock->ops = &netlink_ops;
sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto);//开辟struct netlink_sock空间大小，该结构中包括struct sock，是struct sock的扩展
if (!sk)
return -ENOMEM;
sock_init_data(sock, sk);//初始化BSD socket和sock的关系
nlk = nlk_sk(sk);//获取struct netlink_sock首地址
if (cb_mutex)
nlk->cb_mutex = cb_mutex;
else {
nlk->cb_mutex = &nlk->cb_def_mutex;
mutex_init(nlk->cb_mutex);
}
init_waitqueue_head(&nlk->wait);/// 初始化等待队列
sk->sk_destruct = netlink_sock_destruct;
sk->sk_protocol = protocol;
return 0;
}
// 在用户空间每次打开netlink socket时都会调用此函数: //应用层创建netlink套接字的时候，会调用__sock_create，从而执行netlink_create函数
//执行该函数的用户程序，内核需要通过sock_register函数来注册后才会调用该函数
//PF_NETLINK协议族套接字会调用这个函数，因为sock_register(&netlink_family_ops);注册了netlink套接字
//netlink_create建立对应客户端的套接口，这个是应用程序的套接字，应用程序创建socket套接字的时候，内核会有一个对应的内核套接字，就是客户端套接口
//netlink_kernel_create为服务器端套接口，在各种协议类型模块初始化时调用的,, 而不是socket系统调用时调用的, 每个netlink协议初始化是只调用一次(MAX_LINKS里面的每一个值最多netlink_kernel_create一次)
//该函数在应用层创建套接字的时候，引起系统调用sys_socket，然后执行int __sock_create(struct net *net, int family, int type, int protocol,函数的时候会调用该函数创建应用层对应的套接字
static int netlink_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
struct module *module = NULL;
struct mutex *cb_mutex;
struct netlink_sock *nlk;
int err = 0;
sock->state = SS_UNCONNECTED;
if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)//应用程序创建socket套接字的时候，socket(PF_NETLINK, SOCK_RAW, NETLINK_FIREWALL)，type字段只能用SOCK_RAW或者SOCK_DGRAM
return -ESOCKTNOSUPPORT;
if (protocol < 0 || protocol >= MAX_LINKS)
return -EPROTONOSUPPORT;
netlink_lock_table();
#ifdef CONFIG_MODULES
if (!nl_table[protocol].registered) {// 如果相应的netlink协议是模块又没有加载的话先加载该模块
netlink_unlock_table();
request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol);
netlink_lock_table();
}
#endif
if (nl_table[protocol].registered &&
try_module_get(nl_table[protocol].module))
module = nl_table[protocol].module;
else
err = -EPROTONOSUPPORT;
cb_mutex = nl_table[protocol].cb_mutex;
netlink_unlock_table();
if (err < 0)
goto out;
err = __netlink_create(net, sock, cb_mutex, protocol);
if (err < 0)
goto out_module;
local_bh_disable();
sock_prot_inuse_add(net, &netlink_proto, 1);
local_bh_enable();
nlk = nlk_sk(sock->sk);
nlk->module = module;
out:
return err;
out_module:
module_put(module);
goto out;
}
//netlink_kernel_create创建内核服务器端套接口的时候返回的就是struct socket
static int netlink_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct netlink_sock *nlk;
if (!sk)
return 0;
netlink_remove(sk);
sock_orphan(sk);
nlk = nlk_sk(sk);
/*
* OK. Socket is unlinked, any packets that arrive now
* will be purged.
*/
sock->sk = NULL;
wake_up_interruptible_all(&nlk->wait);
skb_queue_purge(&sk->sk_write_queue);
if (nlk->pid) {
struct netlink_notify n = {
.net = sock_net(sk),
.protocol = sk->sk_protocol,
.pid = nlk->pid,
};
atomic_notifier_call_chain(&netlink_chain,
NETLINK_URELEASE, &n);
}
module_put(nlk->module);
netlink_table_grab();
if (netlink_is_kernel(sk)) {
BUG_ON(nl_table[sk->sk_protocol].registered == 0);
if (--nl_table[sk->sk_protocol].registered == 0) {
kfree(nl_table[sk->sk_protocol].listeners);
nl_table[sk->sk_protocol].module = NULL;
nl_table[sk->sk_protocol].registered = 0;
}
} else if (nlk->subscriptions)
netlink_update_listeners(sk);
netlink_table_ungrab();
kfree(nlk->groups);
nlk->groups = NULL;
local_bh_disable();
sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
local_bh_enable();
sock_put(sk);
return 0;
}
//未指定pid时的自动绑定,有可能应用层bind的时候没有指定pid，这时候pid为0，我们内核创建sock的时候给其自动分配一个pid
static int netlink_autobind(struct socket *sock)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash;
struct hlist_head *head;
struct sock *osk;
struct hlist_node *node;
s32 pid = task_tgid_vnr(current);// pid取为当前进程的组ID
int err;
static s32 rover = -4097;
retry:
cond_resched();
netlink_table_grab();
head = nl_pid_hashfn(hash, pid);
sk_for_each(osk, node, head) {//遍历为其分配一个没有使用的pid
if (!net_eq(sock_net(osk), net))
continue;
if (nlk_sk(osk)->pid == pid) {
/* Bind collision, search negative pid values. */
pid = rover--;
if (rover > -4097)
rover = -4097;
netlink_table_ungrab();
goto retry;
}
}
netlink_table_ungrab();
// 此时的pid是一个负数转换为无符号32位数， 将是一个非常大的数
err = netlink_insert(sk, net, pid);
if (err == -EADDRINUSE)
goto retry;
/* If 2 threads race to autobind, that is fine. */
if (err == -EBUSY)
err = 0;
return err;
}
static inline int netlink_capable(struct socket *sock, unsigned int flag)
{
return (nl_table[sock->sk->sk_protocol].nl_nonroot & flag) ||
capable(CAP_NET_ADMIN);
}
static void
netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (nlk->subscriptions && !subscriptions)
__sk_del_bind_node(sk);
else if (!nlk->subscriptions && subscriptions)
sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list);
nlk->subscriptions = subscriptions;
}
static int netlink_realloc_groups(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
unsigned int groups;
unsigned long *new_groups;
int err = 0;
netlink_table_grab();
groups = nl_table[sk->sk_protocol].groups;
if (!nl_table[sk->sk_protocol].registered) {
err = -ENOENT;
goto out_unlock;
}
if (nlk->ngroups >= groups)
goto out_unlock;
new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC);
if (new_groups == NULL) {
err = -ENOMEM;
goto out_unlock;
}
memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0,
NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups));
nlk->groups = new_groups;
nlk->ngroups = groups;
out_unlock:
netlink_table_ungrab();
return err;
}
//参考SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)的err = sock->ops->bind(sock,
//就是通过应用层addr中的pid，然后与struct sock *sk建立关系，然后添加到nl_table[].hash对应hash中
static int netlink_bind(struct socket *sock, struct sockaddr *addr,
int addr_len)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct netlink_sock *nlk = nlk_sk(sk);//之前sk_alloc开辟的是netlink_socket空间
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
int err;
if (nladdr->nl_family != AF_NETLINK)
return -EINVAL;
/* Only superuser is allowed to listen multicasts */
if (nladdr->nl_groups) {
if (!netlink_capable(sock, NL_NONROOT_RECV))
return -EPERM;
err = netlink_realloc_groups(sk);
if (err)
return err;
}
if (nlk->pid) {
if (nladdr->nl_pid != nlk->pid)
return -EINVAL;
} else {//把pid加入nl_table[]对应hash表中
err = nladdr->nl_pid ?
netlink_insert(sk, net, nladdr->nl_pid) :
netlink_autobind(sock);
if (err)
return err;
}
if (!nladdr->nl_groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
return 0;
netlink_table_grab();
netlink_update_subscriptions(sk, nlk->subscriptions +
hweight32(nladdr->nl_groups) -
hweight32(nlk->groups[0]));
nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups;
netlink_update_listeners(sk);
netlink_table_ungrab();
return 0;
}
static int netlink_connect(struct socket *sock, struct sockaddr *addr,
int alen, int flags)
{
int err = 0;
struct sock *sk = sock->sk;
struct netlink_sock *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
if (alen < sizeof(addr->sa_family))
return -EINVAL;
if (addr->sa_family == AF_UNSPEC) {
sk->sk_state = NETLINK_UNCONNECTED;
nlk->dst_pid = 0;
nlk->dst_group = 0;
return 0;
}
if (addr->sa_family != AF_NETLINK)
return -EINVAL;
/* Only superuser is allowed to send multicasts */
if (nladdr->nl_groups && !netlink_capable(sock, NL_NONROOT_SEND))
return -EPERM;
if (!nlk->pid)
err = netlink_autobind(sock);
if (err == 0) {
sk->sk_state = NETLINK_CONNECTED;
nlk->dst_pid = nladdr->nl_pid;
nlk->dst_group = ffs(nladdr->nl_groups);
}
return err;
}
static int netlink_getname(struct socket *sock, struct sockaddr *addr,
int *addr_len, int peer)
{
struct sock *sk = sock->sk;
struct netlink_sock *nlk = nlk_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_nl *, nladdr, addr);
nladdr->nl_family = AF_NETLINK;
nladdr->nl_pad = 0;
*addr_len = sizeof(*nladdr);
if (peer) {
nladdr->nl_pid = nlk->dst_pid;
nladdr->nl_groups = netlink_group_mask(nlk->dst_group);
} else {
nladdr->nl_pid = nlk->pid;
nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0;
}
return 0;
}
static void netlink_overrun(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) {
if (!test_and_set_bit(0, &nlk_sk(sk)->state)) {
sk->sk_err = ENOBUFS;
sk->sk_error_report(sk);
}
}
atomic_inc(&sk->sk_drops);
}
//通过PID和protocol(netlink最多为32，系统用了16个)查找sock
//根据pid和应用层sk对应的sk_protocol来找到对应的内核sock，最终执行内核sk->sk_data_ready(sk, len);，这样内核就收到数据了
static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid)
{
struct sock *sock;
struct netlink_sock *nlk;
//sk_protocol对应socket(PF_NETLINK, SOCK_RAW, NETLINK_KERNEL_MSG);中的NETLINK_KERNEL_MSG
sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, pid);
if (!sock)
return ERR_PTR(-ECONNREFUSED);
/* Don't bother queuing skb if kernel socket has no input function */
nlk = nlk_sk(sock);
if (sock->sk_state == NETLINK_CONNECTED &&
nlk->dst_pid != nlk_sk(ssk)->pid) {
sock_put(sock);
return ERR_PTR(-ECONNREFUSED);
}
return sock;
}
struct sock *netlink_getsockbyfilp(struct file *filp)
{
struct inode *inode = filp->f_path.dentry->d_inode;
struct sock *sock;
if (!S_ISSOCK(inode->i_mode))
return ERR_PTR(-ENOTSOCK);
sock = SOCKET_I(inode)->sk;
if (sock->sk_family != AF_NETLINK)
return ERR_PTR(-EINVAL);
sock_hold(sock);
return sock;
}
/*
* Attach a skb to a netlink socket.
* The caller must hold a reference to the destination socket. On error, the
* reference is dropped. The skb is not send to the destination, just all
* all error checks are performed and memory in the queue is reserved.
* Return values:
* < 0: error. skb freed, reference to sock dropped.
* 0: continue
* 1: repeat lookup - reference dropped while waiting for socket memory.
*///将sock和sk_buff绑定在一起，在netlink中套接字和skb的绑定与解绑定是很频繁的。
int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
long *timeo, struct sock *ssk)
{
struct netlink_sock *nlk;
nlk = nlk_sk(sk);
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
test_bit(0, &nlk->state)) {
DECLARE_WAITQUEUE(wait, current);
if (!*timeo) {
if (!ssk || netlink_is_kernel(ssk))
netlink_overrun(sk);
sock_put(sk);
kfree_skb(skb);
return -EAGAIN;
}
__set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&nlk->wait, &wait);
//如果此时这个sock不能接受这个sk，那么就要等待了，正好等在nlk->wait上，待到和该sock相关的进程在netlink_rcv_wake中唤醒之，说明可以过继skb了。
if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
test_bit(0, &nlk->state)) && //在函数netlink_rcv_wake中清零，表示没有数据在等待队列，需要等待 也就是应用层调用了接收消息的函数才可以指向该函数后续拷贝动作等
!sock_flag(sk, SOCK_DEAD))
*timeo = schedule_timeout(*timeo);
__set_current_state(TASK_RUNNING);
remove_wait_queue(&nlk->wait, &wait);
sock_put(sk);
if (signal_pending(current)) {
kfree_skb(skb);
return sock_intr_errno(*timeo);
}
return 1;
}
skb_set_owner_r(skb, sk);
return 0;
}
//内核向用户空间发送数据调用该函数，参考netlink_unicast_kernel
int netlink_sendskb(struct sock *sk, struct sk_buff *skb)
{
int len = skb->len;
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk, len);
sock_put(sk);
return len;
}
void netlink_detachskb(struct sock *sk, struct sk_buff *skb)
{
kfree_skb(skb);
sock_put(sk);
}
static inline struct sk_buff *netlink_trim(struct sk_buff *skb,
gfp_t allocation)
{
int delta;
skb_orphan(skb);
delta = skb->end - skb->tail;
if (delta * 2 < skb->truesize)
return skb;
if (skb_shared(skb)) {
struct sk_buff *nskb = skb_clone(skb, allocation);
if (!nskb)
return skb;
kfree_skb(skb);
skb = nskb;
}
if (!pskb_expand_head(skb, 0, -delta, allocation))
skb->truesize -= delta;
return skb;
}
//在函数中检查该状态netlink_attachskb
static inline void netlink_rcv_wake(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (skb_queue_empty(&sk->sk_receive_queue))//是否接收已经完成
clear_bit(0, &nlk->state);//当队列没有数据的时候，清空
if (!test_bit(0, &nlk->state))
wake_up_interruptible(&nlk->wait);//如果清位说明接收完成，那么就唤醒等待发送的进程，这个接收进程可以继续接收了。 其实只有在溢出的情况下才会置位state
}
//用户空间sendmsg的时候会调用该函数。用户空间向内核发送数据。内核向用户空间用netlink_sendskb
static inline int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb)
{
int ret;
struct netlink_sock *nlk = nlk_sk(sk);
ret = -ECONNREFUSED;
if (nlk->netlink_rcv != NULL) {
ret = skb->len;
skb_set_owner_r(skb, sk);
nlk->netlink_rcv(skb);//在函数netlink_kernel_create中注册。
}
kfree_skb(skb);
sock_put(sk);
return ret;
}
int netlink_unicast(struct sock *ssk, struct sk_buff *skb,
u32 pid, int nonblock)
{
struct sock *sk;
int err;
long timeo;
skb = netlink_trim(skb, gfp_any());
timeo = sock_sndtimeo(ssk, nonblock);
retry://netlink_unicast的参数dst_pid为确定目标sock提供了方向
sk = netlink_getsockbypid(ssk, pid);//用户空间sendmsg的时候，填写的PID为0，也就是获取内核端创建的sock
if (IS_ERR(sk)) {
kfree_skb(skb);
return PTR_ERR(sk);
}
if (netlink_is_kernel(sk))
return netlink_unicast_kernel(sk, skb); //这里应该是内核向应用层发送数据的时候
if (sk_filter(sk, skb)) {
err = skb->len;
kfree_skb(skb);
sock_put(sk);
return err;
}
err = netlink_attachskb(sk, skb, &timeo, ssk);
if (err == 1)
goto retry;
if (err)
return err;
return netlink_sendskb(sk, skb);//在套接字sk上传输这个skb，其实就是将这个skb排入了该sk的接收队列的后头。
}
EXPORT_SYMBOL(netlink_unicast);
int netlink_has_listeners(struct sock *sk, unsigned int group)
{
int res = 0;
unsigned long *listeners;
BUG_ON(!netlink_is_kernel(sk));
rcu_read_lock();
listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners);
if (group - 1 < nl_table[sk->sk_protocol].groups)
res = test_bit(group - 1, listeners);
rcu_read_unlock();
return res;
}
EXPORT_SYMBOL_GPL(netlink_has_listeners);
static inline int netlink_broadcast_deliver(struct sock *sk,
struct sk_buff *skb)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
!test_bit(0, &nlk->state)) {
skb_set_owner_r(skb, sk);
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk, skb->len);