summaryrefslogtreecommitdiff
path: root/fs/proc/proc_sysctl.c
blob: 4e5488975415574ed921f8f0a92a6f1439e3a736 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
// SPDX-License-Identifier: GPL-2.0
/*
 * /proc/sys support
 */
#include <linux/init.h>
#include <linux/sysctl.h>
#include <linux/poll.h>
#include <linux/proc_fs.h>
#include <linux/printk.h>
#include <linux/security.h>
#include <linux/sched.h>
#include <linux/cred.h>
#include <linux/namei.h>
#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/module.h>
#include <linux/bpf-cgroup.h>
#include <linux/mount.h>
#include <linux/kmemleak.h>
#include "internal.h"

#define list_for_each_table_entry(entry, table) \
	for ((entry) = (table); (entry)->procname; (entry)++)

static const struct dentry_operations proc_sys_dentry_operations;
static const struct file_operations proc_sys_file_operations;
static const struct inode_operations proc_sys_inode_operations;
static const struct file_operations proc_sys_dir_file_operations;
static const struct inode_operations proc_sys_dir_operations;

/* Support for permanently empty directories */
struct ctl_table sysctl_mount_point[] = {
	{.type = SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY }
};

/**
 * register_sysctl_mount_point() - registers a sysctl mount point
 * @path: path for the mount point
 *
 * Used to create a permanently empty directory to serve as mount point.
 * There are some subtle but important permission checks this allows in the
 * case of unprivileged mounts.
 */
struct ctl_table_header *register_sysctl_mount_point(const char *path)
{
	return register_sysctl(path, sysctl_mount_point);
}
EXPORT_SYMBOL(register_sysctl_mount_point);

#define sysctl_is_perm_empty_ctl_table(tptr)		\
	(tptr[0].type == SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY)
#define sysctl_is_perm_empty_ctl_header(hptr)		\
	(sysctl_is_perm_empty_ctl_table(hptr->ctl_table))
#define sysctl_set_perm_empty_ctl_header(hptr)		\
	(hptr->ctl_table[0].type = SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY)
#define sysctl_clear_perm_empty_ctl_header(hptr)	\
	(hptr->ctl_table[0].type = SYSCTL_TABLE_TYPE_DEFAULT)

void proc_sys_poll_notify(struct ctl_table_poll *poll)
{
	if (!poll)
		return;

	atomic_inc(&poll->event);
	wake_up_interruptible(&poll->wait);
}

static struct ctl_table root_table[] = {
	{
		.procname = "",
		.mode = S_IFDIR|S_IRUGO|S_IXUGO,
	},
	{ }
};
static struct ctl_table_root sysctl_table_root = {
	.default_set.dir.header = {
		{{.count = 1,
		  .nreg = 1,
		  .ctl_table = root_table }},
		.ctl_table_arg = root_table,
		.root = &sysctl_table_root,
		.set = &sysctl_table_root.default_set,
	},
};

static DEFINE_SPINLOCK(sysctl_lock);

static void drop_sysctl_table(struct ctl_table_header *header);
static int sysctl_follow_link(struct ctl_table_header **phead,
	struct ctl_table **pentry);
static int insert_links(struct ctl_table_header *head);
static void put_links(struct ctl_table_header *header);

static void sysctl_print_dir(struct ctl_dir *dir)
{
	if (dir->header.parent)
		sysctl_print_dir(dir->header.parent);
	pr_cont("%s/", dir->header.ctl_table[0].procname);
}

static int namecmp(const char *name1, int len1, const char *name2, int len2)
{
	int cmp;

	cmp = memcmp(name1, name2, min(len1, len2));
	if (cmp == 0)
		cmp = len1 - len2;
	return cmp;
}

/* Called under sysctl_lock */
static struct ctl_table *find_entry(struct ctl_table_header **phead,
	struct ctl_dir *dir, const char *name, int namelen)
{
	struct ctl_table_header *head;
	struct ctl_table *entry;
	struct rb_node *node = dir->root.rb_node;

	while (node)
	{
		struct ctl_node *ctl_node;
		const char *procname;
		int cmp;

		ctl_node = rb_entry(node, struct ctl_node, node);
		head = ctl_node->header;
		entry = &head->ctl_table[ctl_node - head->node];
		procname = entry->procname;

		cmp = namecmp(name, namelen, procname, strlen(procname));
		if (cmp < 0)
			node = node->rb_left;
		else if (cmp > 0)
			node = node->rb_right;
		else {
			*phead = head;
			return entry;
		}
	}
	return NULL;
}

static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry)
{
	struct rb_node *node = &head->node[entry - head->ctl_table].node;
	struct rb_node **p = &head->parent->root.rb_node;
	struct rb_node *parent = NULL;
	const char *name = entry->procname;
	int namelen = strlen(name);

	while (*p) {
		struct ctl_table_header *parent_head;
		struct ctl_table *parent_entry;
		struct ctl_node *parent_node;
		const char *parent_name;
		int cmp;

		parent = *p;
		parent_node = rb_entry(parent, struct ctl_node, node);
		parent_head = parent_node->header;
		parent_entry = &parent_head->ctl_table[parent_node - parent_head->node];
		parent_name = parent_entry->procname;

		cmp = namecmp(name, namelen, parent_name, strlen(parent_name));
		if (cmp < 0)
			p = &(*p)->rb_left;
		else if (cmp > 0)
			p = &(*p)->rb_right;
		else {
			pr_err("sysctl duplicate entry: ");
			sysctl_print_dir(head->parent);
			pr_cont("%s\n", entry->procname);
			return -EEXIST;
		}
	}

	rb_link_node(node, parent, p);
	rb_insert_color(node, &head->parent->root);
	return 0;
}

static void erase_entry(struct ctl_table_header *head, struct ctl_table *entry)
{
	struct rb_node *node = &head->node[entry - head->ctl_table].node;

	rb_erase(node, &head->parent->root);
}

static void init_header(struct ctl_table_header *head,
	struct ctl_table_root *root, struct ctl_table_set *set,
	struct ctl_node *node, struct ctl_table *table)
{
	head->ctl_table = table;
	head->ctl_table_arg = table;
	head->used = 0;
	head->count = 1;
	head->nreg = 1;
	head->unregistering = NULL;
	head->root = root;
	head->set = set;
	head->parent = NULL;
	head->node = node;
	INIT_HLIST_HEAD(&head->inodes);
	if (node) {
		struct ctl_table *entry;

		list_for_each_table_entry(entry, table) {
			node->header = head;
			node++;
		}
	}
}

static void erase_header(struct ctl_table_header *head)
{
	struct ctl_table *entry;

	list_for_each_table_entry(entry, head->ctl_table)
		erase_entry(head, entry);
}

static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
{
	struct ctl_table *entry;
	struct ctl_table_header *dir_h = &dir->header;
	int err;


	/* Is this a permanently empty directory? */
	if (sysctl_is_perm_empty_ctl_header(dir_h))
		return -EROFS;

	/* Am I creating a permanently empty directory? */
	if (sysctl_is_perm_empty_ctl_table(header->ctl_table)) {
		if (!RB_EMPTY_ROOT(&dir->root))
			return -EINVAL;
		sysctl_set_perm_empty_ctl_header(dir_h);
	}

	dir_h->nreg++;
	header->parent = dir;
	err = insert_links(header);
	if (err)
		goto fail_links;
	list_for_each_table_entry(entry, header->ctl_table) {
		err = insert_entry(header, entry);
		if (err)
			goto fail;
	}
	return 0;
fail:
	erase_header(header);
	put_links(header);
fail_links:
	if (header->ctl_table == sysctl_mount_point)
		sysctl_clear_perm_empty_ctl_header(dir_h);
	header->parent = NULL;
	drop_sysctl_table(dir_h);
	return err;
}

/* called under sysctl_lock */
static int use_table(struct ctl_table_header *p)
{
	if (unlikely(p->unregistering))
		return 0;
	p->used++;
	return 1;
}

/* called under sysctl_lock */
static void unuse_table(struct ctl_table_header *p)
{
	if (!--p->used)
		if (unlikely(p->unregistering))
			complete(p->unregistering);
}

static void proc_sys_invalidate_dcache(struct ctl_table_header *head)
{
	proc_invalidate_siblings_dcache(&head->inodes, &sysctl_lock);
}

/* called under sysctl_lock, will reacquire if has to wait */
static void start_unregistering(struct ctl_table_header *p)
{
	/*
	 * if p->used is 0, nobody will ever touch that entry again;
	 * we'll eliminate all paths to it before dropping sysctl_lock
	 */
	if (unlikely(p->used)) {
		struct completion wait;
		init_completion(&wait);
		p->unregistering = &wait;
		spin_unlock(&sysctl_lock);
		wait_for_completion(&wait);
	} else {
		/* anything non-NULL; we'll never dereference it */
		p->unregistering = ERR_PTR(-EINVAL);
		spin_unlock(&sysctl_lock);
	}
	/*
	 * Invalidate dentries for unregistered sysctls: namespaced sysctls
	 * can have duplicate names and contaminate dcache very badly.
	 */
	proc_sys_invalidate_dcache(p);
	/*
	 * do not remove from the list until nobody holds it; walking the
	 * list in do_sysctl() relies on that.
	 */
	spin_lock(&sysctl_lock);
	erase_header(p);
}

static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
{
	BUG_ON(!head);
	spin_lock(&sysctl_lock);
	if (!use_table(head))
		head = ERR_PTR(-ENOENT);
	spin_unlock(&sysctl_lock);
	return head;
}

static void sysctl_head_finish(struct ctl_table_header *head)
{
	if (!head)
		return;
	spin_lock(&sysctl_lock);
	unuse_table(head);
	spin_unlock(&sysctl_lock);
}

static struct ctl_table_set *
lookup_header_set(struct ctl_table_root *root)
{
	struct ctl_table_set *set = &root->default_set;
	if (root->lookup)
		set = root->lookup(root);
	return set;
}

static struct ctl_table *lookup_entry(struct ctl_table_header **phead,
				      struct ctl_dir *dir,
				      const char *name, int namelen)
{
	struct ctl_table_header *head;
	struct ctl_table *entry;

	spin_lock(&sysctl_lock);
	entry = find_entry(&head, dir, name, namelen);
	if (entry && use_table(head))
		*phead = head;
	else
		entry = NULL;
	spin_unlock(&sysctl_lock);
	return entry;
}

static struct ctl_node *first_usable_entry(struct rb_node *node)
{
	struct ctl_node *ctl_node;

	for (;node; node = rb_next(node)) {
		ctl_node = rb_entry(node, struct ctl_node, node);
		if (use_table(ctl_node->header))
			return ctl_node;
	}
	return NULL;
}

static void first_entry(struct ctl_dir *dir,
	struct ctl_table_header **phead, struct ctl_table **pentry)
{
	struct ctl_table_header *head = NULL;
	struct ctl_table *entry = NULL;
	struct ctl_node *ctl_node;

	spin_lock(&sysctl_lock);
	ctl_node = first_usable_entry(rb_first(&dir->root));
	spin_unlock(&sysctl_lock);
	if (ctl_node) {
		head = ctl_node->header;
		entry = &head->ctl_table[ctl_node - head->node];
	}
	*phead = head;
	*pentry = entry;
}

static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentry)
{
	struct ctl_table_header *head = *phead;
	struct ctl_table *entry = *pentry;
	struct ctl_node *ctl_node = &head->node[entry - head->ctl_table];

	spin_lock(&sysctl_lock);
	unuse_table(head);

	ctl_node = first_usable_entry(rb_next(&ctl_node->node));
	spin_unlock(&sysctl_lock);
	head = NULL;
	if (ctl_node) {
		head = ctl_node->header;
		entry = &head->ctl_table[ctl_node - head->node];
	}
	*phead = head;
	*pentry = entry;
}

/*
 * sysctl_perm does NOT grant the superuser all rights automatically, because
 * some sysctl variables are readonly even to root.
 */

static int test_perm(int mode, int op)
{
	if (uid_eq(current_euid(), GLOBAL_ROOT_UID))
		mode >>= 6;
	else if (in_egroup_p(GLOBAL_ROOT_GID))
		mode >>= 3;
	if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
		return 0;
	return -EACCES;
}

static int sysctl_perm(struct ctl_table_header *head, struct ctl_table *table, int op)
{
	struct ctl_table_root *root = head->root;
	int mode;

	if (root->permissions)
		mode = root->permissions(head, table);
	else
		mode = table->mode;

	return test_perm(mode, op);
}

static struct inode *proc_sys_make_inode(struct super_block *sb,
		struct ctl_table_header *head, struct ctl_table *table)
{
	struct ctl_table_root *root = head->root;
	struct inode *inode;
	struct proc_inode *ei;

	inode = new_inode(sb);
	if (!inode)
		return ERR_PTR(-ENOMEM);

	inode->i_ino = get_next_ino();

	ei = PROC_I(inode);

	spin_lock(&sysctl_lock);
	if (unlikely(head->unregistering)) {
		spin_unlock(&sysctl_lock);
		iput(inode);
		return ERR_PTR(-ENOENT);
	}
	ei->sysctl = head;
	ei->sysctl_entry = table;
	hlist_add_head_rcu(&ei->sibling_inodes, &head->inodes);
	head->count++;
	spin_unlock(&sysctl_lock);

	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
	inode->i_mode = table->mode;
	if (!S_ISDIR(table->mode)) {
		inode->i_mode |= S_IFREG;
		inode->i_op = &proc_sys_inode_operations;
		inode->i_fop = &proc_sys_file_operations;
	} else {
		inode->i_mode |= S_IFDIR;
		inode->i_op = &proc_sys_dir_operations;
		inode->i_fop = &proc_sys_dir_file_operations;
		if (sysctl_is_perm_empty_ctl_header(head))
			make_empty_dir_inode(inode);
	}

	if (root->set_ownership)
		root->set_ownership(head, table, &inode->i_uid, &inode->i_gid);
	else {
		inode->i_uid = GLOBAL_ROOT_UID;
		inode->i_gid = GLOBAL_ROOT_GID;
	}

	return inode;
}

void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head)
{
	spin_lock(&sysctl_lock);
	hlist_del_init_rcu(&PROC_I(inode)->sibling_inodes);
	if (!--head->count)
		kfree_rcu(head, rcu);
	spin_unlock(&sysctl_lock);
}

static struct ctl_table_header *grab_header(struct inode *inode)
{
	struct ctl_table_header *head = PROC_I(inode)->sysctl;
	if (!head)
		head = &sysctl_table_root.default_set.dir.header;
	return sysctl_head_grab(head);
}

static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
					unsigned int flags)
{
	struct ctl_table_header *head = grab_header(dir);
	struct ctl_table_header *h = NULL;
	const struct qstr *name = &dentry->d_name;
	struct ctl_table *p;
	struct inode *inode;
	struct dentry *err = ERR_PTR(-ENOENT);
	struct ctl_dir *ctl_dir;
	int ret;

	if (IS_ERR(head))
		return ERR_CAST(head);

	ctl_dir = container_of(head, struct ctl_dir, header);

	p = lookup_entry(&h, ctl_dir, name->name, name->len);
	if (!p)
		goto out;

	if (S_ISLNK(p->mode)) {
		ret = sysctl_follow_link(&h, &p);
		err = ERR_PTR(ret);
		if (ret)
			goto out;
	}

	inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
	if (IS_ERR(inode)) {
		err = ERR_CAST(inode);
		goto out;
	}

	d_set_d_op(dentry, &proc_sys_dentry_operations);
	err = d_splice_alias(inode, dentry);

out:
	if (h)
		sysctl_head_finish(h);
	sysctl_head_finish(head);
	return err;
}

static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter,
		int write)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
	size_t count = iov_iter_count(iter);
	char *kbuf;
	ssize_t error;

	if (IS_ERR(head))
		return PTR_ERR(head);

	/*
	 * At this point we know that the sysctl was not unregistered
	 * and won't be until we finish.
	 */
	error = -EPERM;
	if (sysctl_perm(head, table, write ? MAY_WRITE : MAY_READ))
		goto out;

	/* if that can happen at all, it should be -EINVAL, not -EISDIR */
	error = -EINVAL;
	if (!table->proc_handler)
		goto out;

	/* don't even try if the size is too large */
	error = -ENOMEM;
	if (count >= KMALLOC_MAX_SIZE)
		goto out;
	kbuf = kvzalloc(count + 1, GFP_KERNEL);
	if (!kbuf)
		goto out;

	if (write) {
		error = -EFAULT;
		if (!copy_from_iter_full(kbuf, count, iter))
			goto out_free_buf;
		kbuf[count] = '\0';
	}

	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count,
					   &iocb->ki_pos);
	if (error)
		goto out_free_buf;

	/* careful: calling conventions are nasty here */
	error = table->proc_handler(table, write, kbuf, &count, &iocb->ki_pos);
	if (error)
		goto out_free_buf;

	if (!write) {
		error = -EFAULT;
		if (copy_to_iter(kbuf, count, iter) < count)
			goto out_free_buf;
	}

	error = count;
out_free_buf:
	kvfree(kbuf);
out:
	sysctl_head_finish(head);

	return error;
}

static ssize_t proc_sys_read(struct kiocb *iocb, struct iov_iter *iter)
{
	return proc_sys_call_handler(iocb, iter, 0);
}

static ssize_t proc_sys_write(struct kiocb *iocb, struct iov_iter *iter)
{
	return proc_sys_call_handler(iocb, iter, 1);
}

static int proc_sys_open(struct inode *inode, struct file *filp)
{
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;

	/* sysctl was unregistered */
	if (IS_ERR(head))
		return PTR_ERR(head);

	if (table->poll)
		filp->private_data = proc_sys_poll_event(table->poll);

	sysctl_head_finish(head);

	return 0;
}

static __poll_t proc_sys_poll(struct file *filp, poll_table *wait)
{
	struct inode *inode = file_inode(filp);
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
	__poll_t ret = DEFAULT_POLLMASK;
	unsigned long event;

	/* sysctl was unregistered */
	if (IS_ERR(head))
		return EPOLLERR | EPOLLHUP;

	if (!table->proc_handler)
		goto out;

	if (!table->poll)
		goto out;

	event = (unsigned long)filp->private_data;
	poll_wait(filp, &table->poll->wait, wait);

	if (event != atomic_read(&table->poll->event)) {
		filp->private_data = proc_sys_poll_event(table->poll);
		ret = EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI;
	}

out:
	sysctl_head_finish(head);

	return ret;
}

static bool proc_sys_fill_cache(struct file *file,
				struct dir_context *ctx,
				struct ctl_table_header *head,
				struct ctl_table *table)
{
	struct dentry *child, *dir = file->f_path.dentry;
	struct inode *inode;
	struct qstr qname;
	ino_t ino = 0;
	unsigned type = DT_UNKNOWN;

	qname.name = table->procname;
	qname.len  = strlen(table->procname);
	qname.hash = full_name_hash(dir, qname.name, qname.len);

	child = d_lookup(dir, &qname);
	if (!child) {
		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
		child = d_alloc_parallel(dir, &qname, &wq);
		if (IS_ERR(child))
			return false;
		if (d_in_lookup(child)) {
			struct dentry *res;
			inode = proc_sys_make_inode(dir->d_sb, head, table);
			if (IS_ERR(inode)) {
				d_lookup_done(child);
				dput(child);
				return false;
			}
			d_set_d_op(child, &proc_sys_dentry_operations);
			res = d_splice_alias(inode, child);
			d_lookup_done(child);
			if (unlikely(res)) {
				if (IS_ERR(res)) {
					dput(child);
					return false;
				}
				dput(child);
				child = res;
			}
		}
	}
	inode = d_inode(child);
	ino  = inode->i_ino;
	type = inode->i_mode >> 12;
	dput(child);
	return dir_emit(ctx, qname.name, qname.len, ino, type);
}

static bool proc_sys_link_fill_cache(struct file *file,
				    struct dir_context *ctx,
				    struct ctl_table_header *head,
				    struct ctl_table *table)
{
	bool ret = true;

	head = sysctl_head_grab(head);
	if (IS_ERR(head))
		return false;

	/* It is not an error if we can not follow the link ignore it */
	if (sysctl_follow_link(&head, &table))
		goto out;

	ret = proc_sys_fill_cache(file, ctx, head, table);
out:
	sysctl_head_finish(head);
	return ret;
}

static int scan(struct ctl_table_header *head, struct ctl_table *table,
		unsigned long *pos, struct file *file,
		struct dir_context *ctx)
{
	bool res;

	if ((*pos)++ < ctx->pos)
		return true;

	if (unlikely(S_ISLNK(table->mode)))
		res = proc_sys_link_fill_cache(file, ctx, head, table);
	else
		res = proc_sys_fill_cache(file, ctx, head, table);

	if (res)
		ctx->pos = *pos;

	return res;
}

static int proc_sys_readdir(struct file *file, struct dir_context *ctx)
{
	struct ctl_table_header *head = grab_header(file_inode(file));
	struct ctl_table_header *h = NULL;
	struct ctl_table *entry;
	struct ctl_dir *ctl_dir;
	unsigned long pos;

	if (IS_ERR(head))
		return PTR_ERR(head);

	ctl_dir = container_of(head, struct ctl_dir, header);

	if (!dir_emit_dots(file, ctx))
		goto out;

	pos = 2;

	for (first_entry(ctl_dir, &h, &entry); h; next_entry(&h, &entry)) {
		if (!scan(h, entry, &pos, file, ctx)) {
			sysctl_head_finish(h);
			break;
		}
	}
out:
	sysctl_head_finish(head);
	return 0;
}

static int proc_sys_permission(struct mnt_idmap *idmap,
			       struct inode *inode, int mask)
{
	/*
	 * sysctl entries that are not writeable,
	 * are _NOT_ writeable, capabilities or not.
	 */
	struct ctl_table_header *head;
	struct ctl_table *table;
	int error;

	/* Executable files are not allowed under /proc/sys/ */
	if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
		return -EACCES;

	head = grab_header(inode);
	if (IS_ERR(head))
		return PTR_ERR(head);

	table = PROC_I(inode)->sysctl_entry;
	if (!table) /* global root - r-xr-xr-x */
		error = mask & MAY_WRITE ? -EACCES : 0;
	else /* Use the permissions on the sysctl table entry */
		error = sysctl_perm(head, table, mask & ~MAY_NOT_BLOCK);

	sysctl_head_finish(head);
	return error;
}

static int proc_sys_setattr(struct mnt_idmap *idmap,
			    struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = d_inode(dentry);
	int error;

	if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
		return -EPERM;

	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
	if (error)
		return error;

	setattr_copy(&nop_mnt_idmap, inode, attr);
	return 0;
}

static int proc_sys_getattr(struct mnt_idmap *idmap,
			    const struct path *path, struct kstat *stat,
			    u32 request_mask, unsigned int query_flags)
{
	struct inode *inode = d_inode(path->dentry);
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;

	if (IS_ERR(head))
		return PTR_ERR(head);

	generic_fillattr(&nop_mnt_idmap, inode, stat);
	if (table)
		stat->mode = (stat->mode & S_IFMT) | table->mode;

	sysctl_head_finish(head);
	return 0;
}

static const struct file_operations proc_sys_file_operations = {
	.open		= proc_sys_open,
	.poll		= proc_sys_poll,
	.read_iter	= proc_sys_read,
	.write_iter	= proc_sys_write,
	.splice_read	= copy_splice_read,
	.splice_write	= iter_file_splice_write,
	.llseek		= default_llseek,
};

static const struct file_operations proc_sys_dir_file_operations = {
	.read		= generic_read_dir,
	.iterate_shared	= proc_sys_readdir,
	.llseek		= generic_file_llseek,
};

static const struct inode_operations proc_sys_inode_operations = {
	.permission	= proc_sys_permission,
	.setattr	= proc_sys_setattr,
	.getattr	= proc_sys_getattr,
};

static const struct inode_operations proc_sys_dir_operations = {
	.lookup		= proc_sys_lookup,
	.permission	= proc_sys_permission,
	.setattr	= proc_sys_setattr,
	.getattr	= proc_sys_getattr,
};

static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags)
{
	if (flags & LOOKUP_RCU)
		return -ECHILD;
	return !PROC_I(d_inode(dentry))->sysctl->unregistering;
}

static int proc_sys_delete(const struct dentry *dentry)
{
	return !!PROC_I(d_inode(dentry))->sysctl->unregistering;
}

static int sysctl_is_seen(struct ctl_table_header *p)
{
	struct ctl_table_set *set = p->set;
	int res;
	spin_lock(&sysctl_lock);
	if (p->unregistering)
		res = 0;
	else if (!set->is_seen)
		res = 1;
	else
		res = set->is_seen(set);
	spin_unlock(&sysctl_lock);
	return res;
}

static int proc_sys_compare(const struct dentry *dentry,
		unsigned int len, const char *str, const struct qstr *name)
{
	struct ctl_table_header *head;
	struct inode *inode;

	/* Although proc doesn't have negative dentries, rcu-walk means
	 * that inode here can be NULL */
	/* AV: can it, indeed? */
	inode = d_inode_rcu(dentry);
	if (!inode)
		return 1;
	if (name->len != len)
		return 1;
	if (memcmp(name->name, str, len))
		return 1;
	head = rcu_dereference(PROC_I(inode)->sysctl);
	return !head || !sysctl_is_seen(head);
}

static const struct dentry_operations proc_sys_dentry_operations = {
	.d_revalidate	= proc_sys_revalidate,
	.d_delete	= proc_sys_delete,
	.d_compare	= proc_sys_compare,
};

static struct ctl_dir *find_subdir(struct ctl_dir *dir,
				   const char *name, int namelen)
{
	struct ctl_table_header *head;
	struct ctl_table *entry;

	entry = find_entry(&head, dir, name, namelen);
	if (!entry)
		return ERR_PTR(-ENOENT);
	if (!S_ISDIR(entry->mode))
		return ERR_PTR(-ENOTDIR);
	return container_of(head, struct ctl_dir, header);
}

static struct ctl_dir *new_dir(struct ctl_table_set *set,
			       const char *name, int namelen)
{
	struct ctl_table *table;
	struct ctl_dir *new;
	struct ctl_node *node;
	char *new_name;

	new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) +
		      sizeof(struct ctl_table)*2 +  namelen + 1,
		      GFP_KERNEL);
	if (!new)
		return NULL;

	node = (struct ctl_node *)(new + 1);
	table = (struct ctl_table *)(node + 1);
	new_name = (char *)(table + 2);
	memcpy(new_name, name, namelen);
	table[0].procname = new_name;
	table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
	init_header(&new->header, set->dir.header.root, set, node, table);

	return new;
}

/**
 * get_subdir - find or create a subdir with the specified name.
 * @dir:  Directory to create the subdirectory in
 * @name: The name of the subdirectory to find or create
 * @namelen: The length of name
 *
 * Takes a directory with an elevated reference count so we know that
 * if we drop the lock the directory will not go away.  Upon success
 * the reference is moved from @dir to the returned subdirectory.
 * Upon error an error code is returned and the reference on @dir is
 * simply dropped.
 */
static struct ctl_dir *get_subdir(struct ctl_dir *dir,
				  const char *name, int namelen)
{
	struct ctl_table_set *set = dir->header.set;
	struct ctl_dir *subdir, *new = NULL;
	int err;

	spin_lock(&sysctl_lock);
	subdir = find_subdir(dir, name, namelen);
	if (!IS_ERR(subdir))
		goto found;
	if (PTR_ERR(subdir) != -ENOENT)
		goto failed;

	spin_unlock(&sysctl_lock);
	new = new_dir(set, name, namelen);
	spin_lock(&sysctl_lock);
	subdir = ERR_PTR(-ENOMEM);
	if (!new)
		goto failed;

	/* Was the subdir added while we dropped the lock? */
	subdir = find_subdir(dir, name, namelen);
	if (!IS_ERR(subdir))
		goto found;
	if (PTR_ERR(subdir) != -ENOENT)
		goto failed;

	/* Nope.  Use the our freshly made directory entry. */
	err = insert_header(dir, &new->header);
	subdir = ERR_PTR(err);
	if (err)
		goto failed;
	subdir = new;
found:
	subdir->header.nreg++;
failed:
	if (IS_ERR(subdir)) {
		pr_err("sysctl could not get directory: ");
		sysctl_print_dir(dir);
		pr_cont("%*.*s %ld\n", namelen, namelen, name,
			PTR_ERR(subdir));
	}
	drop_sysctl_table(&dir->header);
	if (new)
		drop_sysctl_table(&new->header);
	spin_unlock(&sysctl_lock);
	return subdir;
}

static struct ctl_dir *xlate_dir(struct ctl_table_set *set, struct ctl_dir *dir)
{
	struct ctl_dir *parent;
	const char *procname;
	if (!dir->header.parent)
		return &set->dir;
	parent = xlate_dir(set, dir->header.parent);
	if (IS_ERR(parent))
		return parent;
	procname = dir->header.ctl_table[0].procname;
	return find_subdir(parent, procname, strlen(procname));
}

static int sysctl_follow_link(struct ctl_table_header **phead,
	struct ctl_table **pentry)
{
	struct ctl_table_header *head;
	struct ctl_table_root *root;
	struct ctl_table_set *set;
	struct ctl_table *entry;
	struct ctl_dir *dir;
	int ret;

	spin_lock(&sysctl_lock);
	root = (*pentry)->data;
	set = lookup_header_set(root);
	dir = xlate_dir(set, (*phead)->parent);
	if (IS_ERR(dir))
		ret = PTR_ERR(dir);
	else {
		const char *procname = (*pentry)->procname;
		head = NULL;
		entry = find_entry(&head, dir, procname, strlen(procname));
		ret = -ENOENT;
		if (entry && use_table(head)) {
			unuse_table(*phead);
			*phead = head;
			*pentry = entry;
			ret = 0;
		}
	}

	spin_unlock(&sysctl_lock);
	return ret;
}

static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;

	pr_err("sysctl table check failed: %s/%s %pV\n",
	       path, table->procname, &vaf);

	va_end(args);
	return -EINVAL;
}

static int sysctl_check_table_array(const char *path, struct ctl_table *table)
{
	int err = 0;

	if ((table->proc_handler == proc_douintvec) ||
	    (table->proc_handler == proc_douintvec_minmax)) {
		if (table->maxlen != sizeof(unsigned int))
			err |= sysctl_err(path, table, "array not allowed");
	}

	if (table->proc_handler == proc_dou8vec_minmax) {
		if (table->maxlen != sizeof(u8))
			err |= sysctl_err(path, table, "array not allowed");
	}

	if (table->proc_handler == proc_dobool) {
		if (table->maxlen != sizeof(bool))
			err |= sysctl_err(path, table, "array not allowed");
	}

	return err;
}

static int sysctl_check_table(const char *path, struct ctl_table *table)
{
	struct ctl_table *entry;
	int err = 0;
	list_for_each_table_entry(entry, table) {
		if ((entry->proc_handler == proc_dostring) ||
		    (entry->proc_handler == proc_dobool) ||
		    (entry->proc_handler == proc_dointvec) ||
		    (entry->proc_handler == proc_douintvec) ||
		    (entry->proc_handler == proc_douintvec_minmax) ||
		    (entry->proc_handler == proc_dointvec_minmax) ||
		    (entry->proc_handler == proc_dou8vec_minmax) ||
		    (entry->proc_handler == proc_dointvec_jiffies) ||
		    (entry->proc_handler == proc_dointvec_userhz_jiffies) ||
		    (entry->proc_handler == proc_dointvec_ms_jiffies) ||
		    (entry->proc_handler == proc_doulongvec_minmax) ||
		    (entry->proc_handler == proc_doulongvec_ms_jiffies_minmax)) {
			if (!entry->data)
				err |= sysctl_err(path, entry, "No data");
			if (!entry->maxlen)
				err |= sysctl_err(path, entry, "No maxlen");
			else
				err |= sysctl_check_table_array(path, entry);
		}
		if (!entry->proc_handler)
			err |= sysctl_err(path, entry, "No proc_handler");

		if ((entry->mode & (S_IRUGO|S_IWUGO)) != entry->mode)
			err |= sysctl_err(path, entry, "bogus .mode 0%o",
				entry->mode);
	}
	return err;
}

static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table *table,
	struct ctl_table_root *link_root)
{
	struct ctl_table *link_table, *entry, *link;
	struct ctl_table_header *links;
	struct ctl_node *node;
	char *link_name;
	int nr_entries, name_bytes;

	name_bytes = 0;
	nr_entries = 0;
	list_for_each_table_entry(entry, table) {
		nr_entries++;
		name_bytes += strlen(entry->procname) + 1;
	}

	links = kzalloc(sizeof(struct ctl_table_header) +
			sizeof(struct ctl_node)*nr_entries +
			sizeof(struct ctl_table)*(nr_entries + 1) +
			name_bytes,
			GFP_KERNEL);

	if (!links)
		return NULL;

	node = (struct ctl_node *)(links + 1);
	link_table = (struct ctl_table *)(node + nr_entries);
	link_name = (char *)&link_table[nr_entries + 1];
	link = link_table;

	list_for_each_table_entry(entry, table) {
		int len = strlen(entry->procname) + 1;
		memcpy(link_name, entry->procname, len);
		link->procname = link_name;
		link->mode = S_IFLNK|S_IRWXUGO;
		link->data = link_root;
		link_name += len;
		link++;
	}
	init_header(links, dir->header.root, dir->header.set, node, link_table);
	links->nreg = nr_entries;

	return links;
}

static bool get_links(struct ctl_dir *dir,
	struct ctl_table *table, struct ctl_table_root *link_root)
{
	struct ctl_table_header *head;
	struct ctl_table *entry, *link;

	/* Are there links available for every entry in table? */
	list_for_each_table_entry(entry, table) {
		const char *procname = entry->procname;
		link = find_entry(&head, dir, procname, strlen(procname));
		if (!link)
			return false;
		if (S_ISDIR(link->mode) && S_ISDIR(entry->mode))
			continue;
		if (S_ISLNK(link->mode) && (link->data == link_root))
			continue;
		return false;
	}

	/* The checks passed.  Increase the registration count on the links */
	list_for_each_table_entry(entry, table) {
		const char *procname = entry->procname;
		link = find_entry(&head, dir, procname, strlen(procname));
		head->nreg++;
	}
	return true;
}

static int insert_links(struct ctl_table_header *head)
{
	struct ctl_table_set *root_set = &sysctl_table_root.default_set;
	struct ctl_dir *core_parent;
	struct ctl_table_header *links;
	int err;

	if (head->set == root_set)
		return 0;

	core_parent = xlate_dir(root_set, head->parent);
	if (IS_ERR(core_parent))
		return 0;

	if (get_links(core_parent, head->ctl_table, head->root))
		return 0;

	core_parent->header.nreg++;
	spin_unlock(&sysctl_lock);

	links = new_links(core_parent, head->ctl_table, head->root);

	spin_lock(&sysctl_lock);
	err = -ENOMEM;
	if (!links)
		goto out;

	err = 0;
	if (get_links(core_parent, head->ctl_table, head->root)) {
		kfree(links);
		goto out;
	}

	err = insert_header(core_parent, links);
	if (err)
		kfree(links);
out:
	drop_sysctl_table(&core_parent->header);
	return err;
}

/* Find the directory for the ctl_table. If one is not found create it. */
static struct ctl_dir *sysctl_mkdir_p(struct ctl_dir *dir, const char *path)
{
	const char *name, *nextname;

	for (name = path; name; name = nextname) {
		int namelen;
		nextname = strchr(name, '/');
		if (nextname) {
			namelen = nextname - name;
			nextname++;
		} else {
			namelen = strlen(name);
		}
		if (namelen == 0)
			continue;

		/*
		 * namelen ensures if name is "foo/bar/yay" only foo is
		 * registered first. We traverse as if using mkdir -p and
		 * return a ctl_dir for the last directory entry.
		 */
		dir = get_subdir(dir, name, namelen);
		if (IS_ERR(dir))
			break;
	}
	return dir;
}

/**
 * __register_sysctl_table - register a leaf sysctl table
 * @set: Sysctl tree to register on
 * @path: The path to the directory the sysctl table is in.
 * @table: the top-level table structure without any child. This table
 * 	 should not be free'd after registration. So it should not be
 * 	 used on stack. It can either be a global or dynamically allocated
 * 	 by the caller and free'd later after sysctl unregistration.
 *
 * Register a sysctl table hierarchy. @table should be a filled in ctl_table
 * array. A completely 0 filled entry terminates the table.
 *
 * The members of the &struct ctl_table structure are used as follows:
 *
 * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
 *            enter a sysctl file
 *
 * data - a pointer to data for use by proc_handler
 *
 * maxlen - the maximum size in bytes of the data
 *
 * mode - the file permissions for the /proc/sys file
 *
 * child - must be %NULL.
 *
 * proc_handler - the text handler routine (described below)
 *
 * extra1, extra2 - extra pointers usable by the proc handler routines
 * XXX: we should eventually modify these to use long min / max [0]
 * [0] https://lkml.kernel.org/87zgpte9o4.fsf@email.froward.int.ebiederm.org
 *
 * Leaf nodes in the sysctl tree will be represented by a single file
 * under /proc; non-leaf nodes (where child is not NULL) are not allowed,
 * sysctl_check_table() verifies this.
 *
 * There must be a proc_handler routine for any terminal nodes.
 * Several default handlers are available to cover common cases -
 *
 * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(),
 * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(),
 * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax()
 *
 * It is the handler's job to read the input buffer from user memory
 * and process it. The handler should return 0 on success.
 *
 * This routine returns %NULL on a failure to register, and a pointer
 * to the table header on success.
 */
struct ctl_table_header *__register_sysctl_table(
	struct ctl_table_set *set,
	const char *path, struct ctl_table *table)
{
	struct ctl_table_root *root = set->dir.header.root;
	struct ctl_table_header *header;
	struct ctl_dir *dir;
	struct ctl_table *entry;
	struct ctl_node *node;
	int nr_entries = 0;

	list_for_each_table_entry(entry, table)
		nr_entries++;

	header = kzalloc(sizeof(struct ctl_table_header) +
			 sizeof(struct ctl_node)*nr_entries, GFP_KERNEL_ACCOUNT);
	if (!header)
		return NULL;

	node = (struct ctl_node *)(header + 1);
	init_header(header, root, set, node, table);
	if (sysctl_check_table(path, table))
		goto fail;

	spin_lock(&sysctl_lock);
	dir = &set->dir;
	/* Reference moved down the directory tree get_subdir */
	dir->header.nreg++;
	spin_unlock(&sysctl_lock);

	dir = sysctl_mkdir_p(dir, path);
	if (IS_ERR(dir))
		goto fail;
	spin_lock(&sysctl_lock);
	if (insert_header(dir, header))
		goto fail_put_dir_locked;

	drop_sysctl_table(&dir->header);
	spin_unlock(&sysctl_lock);

	return header;

fail_put_dir_locked:
	drop_sysctl_table(&dir->header);
	spin_unlock(&sysctl_lock);
fail:
	kfree(header);
	return NULL;
}

/**
 * register_sysctl - register a sysctl table
 * @path: The path to the directory the sysctl table is in. If the path
 * 	doesn't exist we will create it for you.
 * @table: the table structure. The calller must ensure the life of the @table
 * 	will be kept during the lifetime use of the syctl. It must not be freed
 * 	until unregister_sysctl_table() is called with the given returned table
 * 	with this registration. If your code is non modular then you don't need
 * 	to call unregister_sysctl_table() and can instead use something like
 * 	register_sysctl_init() which does not care for the result of the syctl
 * 	registration.
 *
 * Register a sysctl table. @table should be a filled in ctl_table
 * array. A completely 0 filled entry terminates the table.
 *
 * See __register_sysctl_table for more details.
 */
struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table)
{
	return __register_sysctl_table(&sysctl_table_root.default_set,
					path, table);
}
EXPORT_SYMBOL(register_sysctl);

/**
 * __register_sysctl_init() - register sysctl table to path
 * @path: path name for sysctl base. If that path doesn't exist we will create
 * 	it for you.
 * @table: This is the sysctl table that needs to be registered to the path.
 * 	The caller must ensure the life of the @table will be kept during the
 * 	lifetime use of the sysctl.
 * @table_name: The name of sysctl table, only used for log printing when
 *              registration fails
 *
 * The sysctl interface is used by userspace to query or modify at runtime
 * a predefined value set on a variable. These variables however have default
 * values pre-set. Code which depends on these variables will always work even
 * if register_sysctl() fails. If register_sysctl() fails you'd just loose the
 * ability to query or modify the sysctls dynamically at run time. Chances of
 * register_sysctl() failing on init are extremely low, and so for both reasons
 * this function does not return any error as it is used by initialization code.
 *
 * Context: if your base directory does not exist it will be created for you.
 */
void __init __register_sysctl_init(const char *path, struct ctl_table *table,
				 const char *table_name)
{
	struct ctl_table_header *hdr = register_sysctl(path, table);

	if (unlikely(!hdr)) {
		pr_err("failed when register_sysctl %s to %s\n", table_name, path);
		return;
	}
	kmemleak_not_leak(hdr);
}

static void put_links(struct ctl_table_header *header)
{
	struct ctl_table_set *root_set = &sysctl_table_root.default_set;
	struct ctl_table_root *root = header->root;
	struct ctl_dir *parent = header->parent;
	struct ctl_dir *core_parent;
	struct ctl_table *entry;

	if (header->set == root_set)
		return;

	core_parent = xlate_dir(root_set, parent);
	if (IS_ERR(core_parent))
		return;

	list_for_each_table_entry(entry, header->ctl_table) {
		struct ctl_table_header *link_head;
		struct ctl_table *link;
		const char *name = entry->procname;

		link = find_entry(&link_head, core_parent, name, strlen(name));
		if (link &&
		    ((S_ISDIR(link->mode) && S_ISDIR(entry->mode)) ||
		     (S_ISLNK(link->mode) && (link->data == root)))) {
			drop_sysctl_table(link_head);
		}
		else {
			pr_err("sysctl link missing during unregister: ");
			sysctl_print_dir(parent);
			pr_cont("%s\n", name);
		}
	}
}

static void drop_sysctl_table(struct ctl_table_header *header)
{
	struct ctl_dir *parent = header->parent;

	if (--header->nreg)
		return;

	if (parent) {
		put_links(header);
		start_unregistering(header);
	}

	if (!--header->count)
		kfree_rcu(header, rcu);

	if (parent)
		drop_sysctl_table(&parent->header);
}

/**
 * unregister_sysctl_table - unregister a sysctl table hierarchy
 * @header: the header returned from register_sysctl or __register_sysctl_table
 *
 * Unregisters the sysctl table and all children. proc entries may not
 * actually be removed until they are no longer used by anyone.
 */
void unregister_sysctl_table(struct ctl_table_header * header)
{
	might_sleep();

	if (header == NULL)
		return;

	spin_lock(&sysctl_lock);
	drop_sysctl_table(header);
	spin_unlock(&sysctl_lock);
}
EXPORT_SYMBOL(unregister_sysctl_table);

void setup_sysctl_set(struct ctl_table_set *set,
	struct ctl_table_root *root,
	int (*is_seen)(struct ctl_table_set *))
{
	memset(set, 0, sizeof(*set));
	set->is_seen = is_seen;
	init_header(&set->dir.header, root, set, NULL, root_table);
}

void retire_sysctl_set(struct ctl_table_set *set)
{
	WARN_ON(!RB_EMPTY_ROOT(&set->dir.root));
}

int __init proc_sys_init(void)
{
	struct proc_dir_entry *proc_sys_root;

	proc_sys_root = proc_mkdir("sys", NULL);
	proc_sys_root->proc_iops = &proc_sys_dir_operations;
	proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations;
	proc_sys_root->nlink = 0;

	return sysctl_init_bases();
}

struct sysctl_alias {
	const char *kernel_param;
	const char *sysctl_param;
};

/*
 * Historically some settings had both sysctl and a command line parameter.
 * With the generic sysctl. parameter support, we can handle them at a single
 * place and only keep the historical name for compatibility. This is not meant
 * to add brand new aliases. When adding existing aliases, consider whether
 * the possibly different moment of changing the value (e.g. from early_param
 * to the moment do_sysctl_args() is called) is an issue for the specific
 * parameter.
 */
static const struct sysctl_alias sysctl_aliases[] = {
	{"hardlockup_all_cpu_backtrace",	"kernel.hardlockup_all_cpu_backtrace" },
	{"hung_task_panic",			"kernel.hung_task_panic" },
	{"numa_zonelist_order",			"vm.numa_zonelist_order" },
	{"softlockup_all_cpu_backtrace",	"kernel.softlockup_all_cpu_backtrace" },
	{"softlockup_panic",			"kernel.softlockup_panic" },
	{ }
};

static const char *sysctl_find_alias(char *param)
{
	const struct sysctl_alias *alias;

	for (alias = &sysctl_aliases[0]; alias->kernel_param != NULL; alias++) {
		if (strcmp(alias->kernel_param, param) == 0)
			return alias->sysctl_param;
	}

	return NULL;
}

/* Set sysctl value passed on kernel command line. */
static int process_sysctl_arg(char *param, char *val,
			       const char *unused, void *arg)
{
	char *path;
	struct vfsmount **proc_mnt = arg;
	struct file_system_type *proc_fs_type;
	struct file *file;
	int len;
	int err;
	loff_t pos = 0;
	ssize_t wret;

	if (strncmp(param, "sysctl", sizeof("sysctl") - 1) == 0) {
		param += sizeof("sysctl") - 1;

		if (param[0] != '/' && param[0] != '.')
			return 0;

		param++;
	} else {
		param = (char *) sysctl_find_alias(param);
		if (!param)
			return 0;
	}

	if (!val)
		return -EINVAL;
	len = strlen(val);
	if (len == 0)
		return -EINVAL;

	/*
	 * To set sysctl options, we use a temporary mount of proc, look up the
	 * respective sys/ file and write to it. To avoid mounting it when no
	 * options were given, we mount it only when the first sysctl option is
	 * found. Why not a persistent mount? There are problems with a
	 * persistent mount of proc in that it forces userspace not to use any
	 * proc mount options.
	 */
	if (!*proc_mnt) {
		proc_fs_type = get_fs_type("proc");
		if (!proc_fs_type) {
			pr_err("Failed to find procfs to set sysctl from command line\n");
			return 0;
		}
		*proc_mnt = kern_mount(proc_fs_type);
		put_filesystem(proc_fs_type);
		if (IS_ERR(*proc_mnt)) {
			pr_err("Failed to mount procfs to set sysctl from command line\n");
			return 0;
		}
	}

	path = kasprintf(GFP_KERNEL, "sys/%s", param);
	if (!path)
		panic("%s: Failed to allocate path for %s\n", __func__, param);
	strreplace(path, '.', '/');

	file = file_open_root_mnt(*proc_mnt, path, O_WRONLY, 0);
	if (IS_ERR(file)) {
		err = PTR_ERR(file);
		if (err == -ENOENT)
			pr_err("Failed to set sysctl parameter '%s=%s': parameter not found\n",
				param, val);
		else if (err == -EACCES)
			pr_err("Failed to set sysctl parameter '%s=%s': permission denied (read-only?)\n",
				param, val);
		else
			pr_err("Error %pe opening proc file to set sysctl parameter '%s=%s'\n",
				file, param, val);
		goto out;
	}
	wret = kernel_write(file, val, len, &pos);
	if (wret < 0) {
		err = wret;
		if (err == -EINVAL)
			pr_err("Failed to set sysctl parameter '%s=%s': invalid value\n",
				param, val);
		else
			pr_err("Error %pe writing to proc file to set sysctl parameter '%s=%s'\n",
				ERR_PTR(err), param, val);
	} else if (wret != len) {
		pr_err("Wrote only %zd bytes of %d writing to proc file %s to set sysctl parameter '%s=%s\n",
			wret, len, path, param, val);
	}

	err = filp_close(file, NULL);
	if (err)
		pr_err("Error %pe closing proc file to set sysctl parameter '%s=%s\n",
			ERR_PTR(err), param, val);
out:
	kfree(path);
	return 0;
}

void do_sysctl_args(void)
{
	char *command_line;
	struct vfsmount *proc_mnt = NULL;

	command_line = kstrdup(saved_command_line, GFP_KERNEL);
	if (!command_line)
		panic("%s: Failed to allocate copy of command line\n", __func__);

	parse_args("Setting sysctl args", command_line,
		   NULL, 0, -1, -1, &proc_mnt, process_sysctl_arg);

	if (proc_mnt)
		kern_unmount(proc_mnt);

	kfree(command_line);
}