summaryrefslogtreecommitdiffstats
path: root/fs/kernfs/dir.c
blob: 4076e8a7c269aaa2179892b708c4e08123d5cd14 (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
/*
 * fs/kernfs/dir.c - kernfs directory implementation
 *
 * Copyright (c) 2001-3 Patrick Mochel
 * Copyright (c) 2007 SUSE Linux Products GmbH
 * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
 *
 * This file is released under the GPLv2.
 */

#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/idr.h>
#include <linux/slab.h>
#include <linux/security.h>
#include <linux/hash.h>

#include "kernfs-internal.h"

DEFINE_MUTEX(kernfs_mutex);

#define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)

static bool kernfs_lockdep(struct kernfs_node *kn)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	return kn->flags & KERNFS_LOCKDEP;
#else
	return false;
#endif
}

/**
 *	kernfs_name_hash
 *	@name: Null terminated string to hash
 *	@ns:   Namespace tag to hash
 *
 *	Returns 31 bit hash of ns + name (so it fits in an off_t )
 */
static unsigned int kernfs_name_hash(const char *name, const void *ns)
{
	unsigned long hash = init_name_hash();
	unsigned int len = strlen(name);
	while (len--)
		hash = partial_name_hash(*name++, hash);
	hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31));
	hash &= 0x7fffffffU;
	/* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */
	if (hash < 1)
		hash += 2;
	if (hash >= INT_MAX)
		hash = INT_MAX - 1;
	return hash;
}

static int kernfs_name_compare(unsigned int hash, const char *name,
			       const void *ns, const struct kernfs_node *kn)
{
	if (hash != kn->hash)
		return hash - kn->hash;
	if (ns != kn->ns)
		return ns - kn->ns;
	return strcmp(name, kn->name);
}

static int kernfs_sd_compare(const struct kernfs_node *left,
			     const struct kernfs_node *right)
{
	return kernfs_name_compare(left->hash, left->name, left->ns, right);
}

/**
 *	kernfs_link_sibling - link kernfs_node into sibling rbtree
 *	@kn: kernfs_node of interest
 *
 *	Link @kn into its sibling rbtree which starts from
 *	@kn->parent->dir.children.
 *
 *	Locking:
 *	mutex_lock(kernfs_mutex)
 *
 *	RETURNS:
 *	0 on susccess -EEXIST on failure.
 */
static int kernfs_link_sibling(struct kernfs_node *kn)
{
	struct rb_node **node = &kn->parent->dir.children.rb_node;
	struct rb_node *parent = NULL;

	if (kernfs_type(kn) == KERNFS_DIR)
		kn->parent->dir.subdirs++;

	while (*node) {
		struct kernfs_node *pos;
		int result;

		pos = rb_to_kn(*node);
		parent = *node;
		result = kernfs_sd_compare(kn, pos);
		if (result < 0)
			node = &pos->rb.rb_left;
		else if (result > 0)
			node = &pos->rb.rb_right;
		else
			return -EEXIST;
	}
	/* add new node and rebalance the tree */
	rb_link_node(&kn->rb, parent, node);
	rb_insert_color(&kn->rb, &kn->parent->dir.children);
	return 0;
}

/**
 *	kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree
 *	@kn: kernfs_node of interest
 *
 *	Unlink @kn from its sibling rbtree which starts from
 *	kn->parent->dir.children.
 *
 *	Locking:
 *	mutex_lock(kernfs_mutex)
 */
static bool kernfs_unlink_sibling(struct kernfs_node *kn)
{
	if (RB_EMPTY_NODE(&kn->rb))
		return false;

	if (kernfs_type(kn) == KERNFS_DIR)
		kn->parent->dir.subdirs--;

	rb_erase(&kn->rb, &kn->parent->dir.children);
	RB_CLEAR_NODE(&kn->rb);
	return true;
}

/**
 *	kernfs_get_active - get an active reference to kernfs_node
 *	@kn: kernfs_node to get an active reference to
 *
 *	Get an active reference of @kn.  This function is noop if @kn
 *	is NULL.
 *
 *	RETURNS:
 *	Pointer to @kn on success, NULL on failure.
 */
struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
{
	if (unlikely(!kn))
		return NULL;

	if (kernfs_lockdep(kn))
		rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_);

	/*
	 * Try to obtain an active ref.  If @kn is deactivated, we block
	 * till either it's reactivated or killed.
	 */
	do {
		if (atomic_inc_unless_negative(&kn->active))
			return kn;

		wait_event(kernfs_root(kn)->deactivate_waitq,
			   atomic_read(&kn->active) >= 0 ||
			   RB_EMPTY_NODE(&kn->rb));
	} while (!RB_EMPTY_NODE(&kn->rb));

	if (kernfs_lockdep(kn))
		rwsem_release(&kn->dep_map, 1, _RET_IP_);
	return NULL;
}

/**
 *	kernfs_put_active - put an active reference to kernfs_node
 *	@kn: kernfs_node to put an active reference to
 *
 *	Put an active reference to @kn.  This function is noop if @kn
 *	is NULL.
 */
void kernfs_put_active(struct kernfs_node *kn)
{
	struct kernfs_root *root = kernfs_root(kn);
	int v;

	if (unlikely(!kn))
		return;

	if (kernfs_lockdep(kn))
		rwsem_release(&kn->dep_map, 1, _RET_IP_);
	v = atomic_dec_return(&kn->active);
	if (likely(v != KN_DEACTIVATED_BIAS))
		return;

	wake_up_all(&root->deactivate_waitq);
}

/**
 * kernfs_drain - drain kernfs_node
 * @kn: kernfs_node to drain
 *
 * Drain existing usages of @kn.  Mutiple removers may invoke this function
 * concurrently on @kn and all will return after draining is complete.
 * Returns %true if drain is performed and kernfs_mutex was temporarily
 * released.  %false if @kn was already drained and no operation was
 * necessary.
 *
 * The caller is responsible for ensuring @kn stays pinned while this
 * function is in progress even if it gets removed by someone else.
 */
static bool kernfs_drain(struct kernfs_node *kn)
	__releases(&kernfs_mutex) __acquires(&kernfs_mutex)
{
	struct kernfs_root *root = kernfs_root(kn);

	lockdep_assert_held(&kernfs_mutex);
	WARN_ON_ONCE(atomic_read(&kn->active) >= 0);

	/*
	 * We want to go through the active ref lockdep annotation at least
	 * once for all node removals, but the lockdep annotation can't be
	 * nested inside kernfs_mutex and deactivation can't make forward
	 * progress if we keep dropping the mutex.  Use JUST_ACTIVATED to
	 * force the slow path once for each deactivation if lockdep is
	 * enabled.
	 */
	if ((!kernfs_lockdep(kn) || !(kn->flags & KERNFS_JUST_DEACTIVATED)) &&
	    atomic_read(&kn->active) == KN_DEACTIVATED_BIAS)
		return false;

	kn->flags &= ~KERNFS_JUST_DEACTIVATED;
	mutex_unlock(&kernfs_mutex);

	if (kernfs_lockdep(kn)) {
		rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
		if (atomic_read(&kn->active) != KN_DEACTIVATED_BIAS)
			lock_contended(&kn->dep_map, _RET_IP_);
	}

	wait_event(root->deactivate_waitq,
		   atomic_read(&kn->active) == KN_DEACTIVATED_BIAS);

	if (kernfs_lockdep(kn)) {
		lock_acquired(&kn->dep_map, _RET_IP_);
		rwsem_release(&kn->dep_map, 1, _RET_IP_);
	}

	mutex_lock(&kernfs_mutex);
	return true;
}

/**
 * kernfs_get - get a reference count on a kernfs_node
 * @kn: the target kernfs_node
 */
void kernfs_get(struct kernfs_node *kn)
{
	if (kn) {
		WARN_ON(!atomic_read(&kn->count));
		atomic_inc(&kn->count);
	}
}
EXPORT_SYMBOL_GPL(kernfs_get);

/**
 * kernfs_put - put a reference count on a kernfs_node
 * @kn: the target kernfs_node
 *
 * Put a reference count of @kn and destroy it if it reached zero.
 */
void kernfs_put(struct kernfs_node *kn)
{
	struct kernfs_node *parent;
	struct kernfs_root *root;

	if (!kn || !atomic_dec_and_test(&kn->count))
		return;
	root = kernfs_root(kn);
 repeat:
	/*
	 * Moving/renaming is always done while holding reference.
	 * kn->parent won't change beneath us.
	 */
	parent = kn->parent;

	WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS,
		  "kernfs_put: %s/%s: released with incorrect active_ref %d\n",
		  parent ? parent->name : "", kn->name, atomic_read(&kn->active));

	if (kernfs_type(kn) == KERNFS_LINK)
		kernfs_put(kn->symlink.target_kn);
	if (!(kn->flags & KERNFS_STATIC_NAME))
		kfree(kn->name);
	if (kn->iattr) {
		if (kn->iattr->ia_secdata)
			security_release_secctx(kn->iattr->ia_secdata,
						kn->iattr->ia_secdata_len);
		simple_xattrs_free(&kn->iattr->xattrs);
	}
	kfree(kn->iattr);
	ida_simple_remove(&root->ino_ida, kn->ino);
	kmem_cache_free(kernfs_node_cache, kn);

	kn = parent;
	if (kn) {
		if (atomic_dec_and_test(&kn->count))
			goto repeat;
	} else {
		/* just released the root kn, free @root too */
		ida_destroy(&root->ino_ida);
		kfree(root);
	}
}
EXPORT_SYMBOL_GPL(kernfs_put);

static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
{
	struct kernfs_node *kn;

	if (flags & LOOKUP_RCU)
		return -ECHILD;

	/* Always perform fresh lookup for negatives */
	if (!dentry->d_inode)
		goto out_bad_unlocked;

	kn = dentry->d_fsdata;
	mutex_lock(&kernfs_mutex);

	/* Force fresh lookup if removed */
	if (kn->parent && RB_EMPTY_NODE(&kn->rb))
		goto out_bad;

	/* The kernfs node has been moved? */
	if (dentry->d_parent->d_fsdata != kn->parent)
		goto out_bad;

	/* The kernfs node has been renamed */
	if (strcmp(dentry->d_name.name, kn->name) != 0)
		goto out_bad;

	/* The kernfs node has been moved to a different namespace */
	if (kn->parent && kernfs_ns_enabled(kn->parent) &&
	    kernfs_info(dentry->d_sb)->ns != kn->ns)
		goto out_bad;

	mutex_unlock(&kernfs_mutex);
out_valid:
	return 1;
out_bad:
	mutex_unlock(&kernfs_mutex);
out_bad_unlocked:
	/*
	 * @dentry doesn't match the underlying kernfs node, drop the
	 * dentry and force lookup.  If we have submounts we must allow the
	 * vfs caches to lie about the state of the filesystem to prevent
	 * leaks and other nasty things, so use check_submounts_and_drop()
	 * instead of d_drop().
	 */
	if (check_submounts_and_drop(dentry) != 0)
		goto out_valid;

	return 0;
}

static void kernfs_dop_release(struct dentry *dentry)
{
	kernfs_put(dentry->d_fsdata);
}

const struct dentry_operations kernfs_dops = {
	.d_revalidate	= kernfs_dop_revalidate,
	.d_release	= kernfs_dop_release,
};

struct kernfs_node *kernfs_new_node(struct kernfs_root *root, const char *name,
				    umode_t mode, unsigned flags)
{
	char *dup_name = NULL;
	struct kernfs_node *kn;
	int ret;

	if (!(flags & KERNFS_STATIC_NAME)) {
		name = dup_name = kstrdup(name, GFP_KERNEL);
		if (!name)
			return NULL;
	}

	kn = kmem_cache_zalloc(kernfs_node_cache, GFP_KERNEL);
	if (!kn)
		goto err_out1;

	ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL);
	if (ret < 0)
		goto err_out2;
	kn->ino = ret;

	atomic_set(&kn->count, 1);
	atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
	kn->deact_depth = 1;
	RB_CLEAR_NODE(&kn->rb);

	kn->name = name;
	kn->mode = mode;
	kn->flags = flags;

	return kn;

 err_out2:
	kmem_cache_free(kernfs_node_cache, kn);
 err_out1:
	kfree(dup_name);
	return NULL;
}

/**
 *	kernfs_add_one - add kernfs_node to parent without warning
 *	@kn: kernfs_node to be added
 *	@parent: the parent kernfs_node to add @kn to
 *
 *	Get @parent and set @kn->parent to it and increment nlink of the
 *	parent inode if @kn is a directory and link into the children list
 *	of the parent.
 *
 *	RETURNS:
 *	0 on success, -EEXIST if entry with the given name already
 *	exists.
 */
int kernfs_add_one(struct kernfs_node *kn, struct kernfs_node *parent)
{
	struct kernfs_iattrs *ps_iattr;
	bool has_ns;
	int ret;

	if (!kernfs_get_active(parent))
		return -ENOENT;

	mutex_lock(&kernfs_mutex);

	ret = -EINVAL;
	has_ns = kernfs_ns_enabled(parent);
	if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
		 has_ns ? "required" : "invalid", parent->name, kn->name))
		goto out_unlock;

	if (kernfs_type(parent) != KERNFS_DIR)
		goto out_unlock;

	kn->hash = kernfs_name_hash(kn->name, kn->ns);
	kn->parent = parent;
	kernfs_get(parent);

	ret = kernfs_link_sibling(kn);
	if (ret)
		goto out_unlock;

	/* Update timestamps on the parent */
	ps_iattr = parent->iattr;
	if (ps_iattr) {
		struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
		ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
	}

	/* Mark the entry added into directory tree */
	atomic_sub(KN_DEACTIVATED_BIAS, &kn->active);
	kn->deact_depth--;
	ret = 0;
out_unlock:
	mutex_unlock(&kernfs_mutex);
	kernfs_put_active(parent);
	return ret;
}

/**
 * kernfs_find_ns - find kernfs_node with the given name
 * @parent: kernfs_node to search under
 * @name: name to look for
 * @ns: the namespace tag to use
 *
 * Look for kernfs_node with name @name under @parent.  Returns pointer to
 * the found kernfs_node on success, %NULL on failure.
 */
static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent,
					  const unsigned char *name,
					  const void *ns)
{
	struct rb_node *node = parent->dir.children.rb_node;
	bool has_ns = kernfs_ns_enabled(parent);
	unsigned int hash;

	lockdep_assert_held(&kernfs_mutex);

	if (has_ns != (bool)ns) {
		WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
		     has_ns ? "required" : "invalid", parent->name, name);
		return NULL;
	}

	hash = kernfs_name_hash(name, ns);
	while (node) {
		struct kernfs_node *kn;
		int result;

		kn = rb_to_kn(node);
		result = kernfs_name_compare(hash, name, ns, kn);
		if (result < 0)
			node = node->rb_left;
		else if (result > 0)
			node = node->rb_right;
		else
			return kn;
	}
	return NULL;
}

/**
 * kernfs_find_and_get_ns - find and get kernfs_node with the given name
 * @parent: kernfs_node to search under
 * @name: name to look for
 * @ns: the namespace tag to use
 *
 * Look for kernfs_node with name @name under @parent and get a reference
 * if found.  This function may sleep and returns pointer to the found
 * kernfs_node on success, %NULL on failure.
 */
struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
					   const char *name, const void *ns)
{
	struct kernfs_node *kn;

	mutex_lock(&kernfs_mutex);
	kn = kernfs_find_ns(parent, name, ns);
	kernfs_get(kn);
	mutex_unlock(&kernfs_mutex);

	return kn;
}
EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns);

/**
 * kernfs_create_root - create a new kernfs hierarchy
 * @kdops: optional directory syscall operations for the hierarchy
 * @priv: opaque data associated with the new directory
 *
 * Returns the root of the new hierarchy on success, ERR_PTR() value on
 * failure.
 */
struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
{
	struct kernfs_root *root;
	struct kernfs_node *kn;

	root = kzalloc(sizeof(*root), GFP_KERNEL);
	if (!root)
		return ERR_PTR(-ENOMEM);

	ida_init(&root->ino_ida);

	kn = kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO, KERNFS_DIR);
	if (!kn) {
		ida_destroy(&root->ino_ida);
		kfree(root);
		return ERR_PTR(-ENOMEM);
	}

	atomic_sub(KN_DEACTIVATED_BIAS, &kn->active);
	kn->deact_depth--;
	kn->priv = priv;
	kn->dir.root = root;

	root->dir_ops = kdops;
	root->kn = kn;
	init_waitqueue_head(&root->deactivate_waitq);

	return root;
}

/**
 * kernfs_destroy_root - destroy a kernfs hierarchy
 * @root: root of the hierarchy to destroy
 *
 * Destroy the hierarchy anchored at @root by removing all existing
 * directories and destroying @root.
 */
void kernfs_destroy_root(struct kernfs_root *root)
{
	kernfs_remove(root->kn);	/* will also free @root */
}

/**
 * kernfs_create_dir_ns - create a directory
 * @parent: parent in which to create a new directory
 * @name: name of the new directory
 * @mode: mode of the new directory
 * @priv: opaque data associated with the new directory
 * @ns: optional namespace tag of the directory
 *
 * Returns the created node on success, ERR_PTR() value on failure.
 */
struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
					 const char *name, umode_t mode,
					 void *priv, const void *ns)
{
	struct kernfs_node *kn;
	int rc;

	/* allocate */
	kn = kernfs_new_node(kernfs_root(parent), name, mode | S_IFDIR,
			     KERNFS_DIR);
	if (!kn)
		return ERR_PTR(-ENOMEM);

	kn->dir.root = parent->dir.root;
	kn->ns = ns;
	kn->priv = priv;

	/* link in */
	rc = kernfs_add_one(kn, parent);
	if (!rc)
		return kn;

	kernfs_put(kn);
	return ERR_PTR(rc);
}

static struct dentry *kernfs_iop_lookup(struct inode *dir,
					struct dentry *dentry,
					unsigned int flags)
{
	struct dentry *ret;
	struct kernfs_node *parent = dentry->d_parent->d_fsdata;
	struct kernfs_node *kn;
	struct inode *inode;
	const void *ns = NULL;

	mutex_lock(&kernfs_mutex);

	if (kernfs_ns_enabled(parent))
		ns = kernfs_info(dir->i_sb)->ns;

	kn = kernfs_find_ns(parent, dentry->d_name.name, ns);

	/* no such entry */
	if (!kn) {
		ret = NULL;
		goto out_unlock;
	}
	kernfs_get(kn);
	dentry->d_fsdata = kn;

	/* attach dentry and inode */
	inode = kernfs_get_inode(dir->i_sb, kn);
	if (!inode) {
		ret = ERR_PTR(-ENOMEM);
		goto out_unlock;
	}

	/* instantiate and hash dentry */
	ret = d_materialise_unique(dentry, inode);
 out_unlock:
	mutex_unlock(&kernfs_mutex);
	return ret;
}

static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry,
			    umode_t mode)
{
	struct kernfs_node *parent = dir->i_private;
	struct kernfs_dir_ops *kdops = kernfs_root(parent)->dir_ops;

	if (!kdops || !kdops->mkdir)
		return -EPERM;

	return kdops->mkdir(parent, dentry->d_name.name, mode);
}

static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry)
{
	struct kernfs_node *kn  = dentry->d_fsdata;
	struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;

	if (!kdops || !kdops->rmdir)
		return -EPERM;

	return kdops->rmdir(kn);
}

static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
			     struct inode *new_dir, struct dentry *new_dentry)
{
	struct kernfs_node *kn  = old_dentry->d_fsdata;
	struct kernfs_node *new_parent = new_dir->i_private;
	struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;

	if (!kdops || !kdops->rename)
		return -EPERM;

	return kdops->rename(kn, new_parent, new_dentry->d_name.name);
}

const struct inode_operations kernfs_dir_iops = {
	.lookup		= kernfs_iop_lookup,
	.permission	= kernfs_iop_permission,
	.setattr	= kernfs_iop_setattr,
	.getattr	= kernfs_iop_getattr,
	.setxattr	= kernfs_iop_setxattr,
	.removexattr	= kernfs_iop_removexattr,
	.getxattr	= kernfs_iop_getxattr,
	.listxattr	= kernfs_iop_listxattr,

	.mkdir		= kernfs_iop_mkdir,
	.rmdir		= kernfs_iop_rmdir,
	.rename		= kernfs_iop_rename,
};

static struct kernfs_node *kernfs_leftmost_descendant(struct kernfs_node *pos)
{
	struct kernfs_node *last;

	while (true) {
		struct rb_node *rbn;

		last = pos;

		if (kernfs_type(pos) != KERNFS_DIR)
			break;

		rbn = rb_first(&pos->dir.children);
		if (!rbn)
			break;

		pos = rb_to_kn(rbn);
	}

	return last;
}

/**
 * kernfs_next_descendant_post - find the next descendant for post-order walk
 * @pos: the current position (%NULL to initiate traversal)
 * @root: kernfs_node whose descendants to walk
 *
 * Find the next descendant to visit for post-order traversal of @root's
 * descendants.  @root is included in the iteration and the last node to be
 * visited.
 */
static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
						       struct kernfs_node *root)
{
	struct rb_node *rbn;

	lockdep_assert_held(&kernfs_mutex);

	/* if first iteration, visit leftmost descendant which may be root */
	if (!pos)
		return kernfs_leftmost_descendant(root);

	/* if we visited @root, we're done */
	if (pos == root)
		return NULL;

	/* if there's an unvisited sibling, visit its leftmost descendant */
	rbn = rb_next(&pos->rb);
	if (rbn)
		return kernfs_leftmost_descendant(rb_to_kn(rbn));

	/* no sibling left, visit parent */
	return pos->parent;
}

static void __kernfs_deactivate(struct kernfs_node *kn)
{
	struct kernfs_node *pos;

	lockdep_assert_held(&kernfs_mutex);

	/* prevent any new usage under @kn by deactivating all nodes */
	pos = NULL;
	while ((pos = kernfs_next_descendant_post(pos, kn))) {
		if (!pos->deact_depth++) {
			WARN_ON_ONCE(atomic_read(&pos->active) < 0);
			atomic_add(KN_DEACTIVATED_BIAS, &pos->active);
			pos->flags |= KERNFS_JUST_DEACTIVATED;
		}
	}

	/*
	 * Drain the subtree.  If kernfs_drain() blocked to drain, which is
	 * indicated by %true return, it temporarily released kernfs_mutex
	 * and the rbtree might have been modified inbetween breaking our
	 * future walk.  Restart the walk after each %true return.
	 */
	pos = NULL;
	while ((pos = kernfs_next_descendant_post(pos, kn))) {
		bool drained;

		kernfs_get(pos);
		drained = kernfs_drain(pos);
		kernfs_put(pos);
		if (drained)
			pos = NULL;
	}
}

static void __kernfs_reactivate(struct kernfs_node *kn)
{
	struct kernfs_node *pos;

	lockdep_assert_held(&kernfs_mutex);

	pos = NULL;
	while ((pos = kernfs_next_descendant_post(pos, kn))) {
		if (!--pos->deact_depth) {
			WARN_ON_ONCE(atomic_read(&pos->active) >= 0);
			atomic_sub(KN_DEACTIVATED_BIAS, &pos->active);
		}
		WARN_ON_ONCE(pos->deact_depth < 0);
	}

	/* some nodes reactivated, kick get_active waiters */
	wake_up_all(&kernfs_root(kn)->deactivate_waitq);
}

static void __kernfs_deactivate_self(struct kernfs_node *kn)
{
	/*
	 * Take out ourself out of the active ref dependency chain and
	 * deactivate.  If we're called without an active ref, lockdep will
	 * complain.
	 */
	kernfs_put_active(kn);
	__kernfs_deactivate(kn);
}

static void __kernfs_reactivate_self(struct kernfs_node *kn)
{
	__kernfs_reactivate(kn);
	/*
	 * Restore active ref dropped by deactivate_self() so that it's
	 * balanced on return.  put_active() will soon be called on @kn, so
	 * this can't break anything regardless of @kn's state.
	 */
	atomic_inc(&kn->active);
	if (kernfs_lockdep(kn))
		rwsem_acquire(&kn->dep_map, 0, 1, _RET_IP_);
}

/**
 * kernfs_deactivate - deactivate subtree of a node
 * @kn: kernfs_node to deactivate subtree of
 *
 * Deactivate the subtree of @kn.  On return, there's no active operation
 * going on under @kn and creation or renaming of a node under @kn is
 * blocked until @kn is reactivated or removed.  This function can be
 * called multiple times and nests properly.  Each invocation should be
 * paired with kernfs_reactivate().
 *
 * For a kernfs user which uses simple locking, the subsystem lock would
 * nest inside active reference.  This becomes problematic if the user
 * tries to remove nodes while holding the subystem lock as it would create
 * a reverse locking dependency from the subsystem lock to active ref.
 * This function can be used to break such reverse dependency.  The user
 * can call this function outside the subsystem lock and then proceed to
 * invoke kernfs_remove() while holding the subsystem lock without
 * introducing such reverse dependency.
 */
void kernfs_deactivate(struct kernfs_node *kn)
{
	mutex_lock(&kernfs_mutex);
	__kernfs_deactivate(kn);
	mutex_unlock(&kernfs_mutex);
}

/**
 * kernfs_reactivate - reactivate subtree of a node
 * @kn: kernfs_node to reactivate subtree of
 *
 * Undo kernfs_deactivate().
 */
void kernfs_reactivate(struct kernfs_node *kn)
{
	mutex_lock(&kernfs_mutex);
	__kernfs_reactivate(kn);
	mutex_unlock(&kernfs_mutex);
}

/**
 * kernfs_deactivate_self - deactivate subtree of a node from its own method
 * @kn: the self kernfs_node to deactivate subtree of
 *
 * The caller must be running off of a kernfs operation which is invoked
 * with an active reference - e.g. one of kernfs_ops.  Once this function
 * is called, @kn may be removed by someone else while the enclosing method
 * is in progress.  Other than that, this function is equivalent to
 * kernfs_deactivate() and should be paired with kernfs_reactivate_self().
 */
void kernfs_deactivate_self(struct kernfs_node *kn)
{
	mutex_lock(&kernfs_mutex);
	__kernfs_deactivate_self(kn);
	mutex_unlock(&kernfs_mutex);
}

/**
 * kernfs_reactivate_self - reactivate subtree of a node from its own method
 * @kn: the self kernfs_node to reactivate subtree of
 *
 * Undo kernfs_deactivate_self().
 */
void kernfs_reactivate_self(struct kernfs_node *kn)
{
	mutex_lock(&kernfs_mutex);
	__kernfs_reactivate_self(kn);
	mutex_unlock(&kernfs_mutex);
}

static void __kernfs_remove(struct kernfs_node *kn)
{
	struct kernfs_root *root = kernfs_root(kn);
	struct kernfs_node *pos;

	lockdep_assert_held(&kernfs_mutex);

	pr_debug("kernfs %s: removing\n", kn->name);

	__kernfs_deactivate(kn);

	/* unlink the subtree node-by-node */
	do {
		pos = kernfs_leftmost_descendant(kn);

		/*
		 * We're gonna release kernfs_mutex to unmap bin files,
		 * Make sure @pos doesn't go away inbetween.
		 */
		kernfs_get(pos);

		/*
		 * This must be come before unlinking; otherwise, when
		 * there are multiple removers, some may finish before
		 * unmapping is complete.
		 */
		if (pos->flags & KERNFS_HAS_MMAP) {
			mutex_unlock(&kernfs_mutex);
			kernfs_unmap_file(pos);
			mutex_lock(&kernfs_mutex);
		}

		/*
		 * kernfs_unlink_sibling() succeeds once per node.  Use it
		 * to decide who's responsible for cleanups.
		 */
		if (!pos->parent || kernfs_unlink_sibling(pos)) {
			struct kernfs_iattrs *ps_iattr =
				pos->parent ? pos->parent->iattr : NULL;

			/* update timestamps on the parent */
			if (ps_iattr) {
				ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME;
				ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME;
			}

			kernfs_put(pos);
		}

		kernfs_put(pos);
	} while (pos != kn);

	/* some nodes killed, kick get_active waiters */
	wake_up_all(&root->deactivate_waitq);
}

/**
 * kernfs_remove - remove a kernfs_node recursively
 * @kn: the kernfs_node to remove
 *
 * Remove @kn along with all its subdirectories and files.
 */
void kernfs_remove(struct kernfs_node *kn)
{
	mutex_lock(&kernfs_mutex);
	__kernfs_remove(kn);
	mutex_unlock(&kernfs_mutex);
}

/**
 * kernfs_remove_self - remove a kernfs_node from its own method
 * @kn: the self kernfs_node to remove
 *
 * The caller must be running off of a kernfs operation which is invoked
 * with an active reference - e.g. one of kernfs_ops.  This can be used to
 * implement a file operation which deletes itself.
 *
 * For example, the "delete" file for a sysfs device directory can be
 * implemented by invoking kernfs_remove_self() on the "delete" file
 * itself.  This function breaks the circular dependency of trying to
 * deactivate self while holding an active ref itself.  It isn't necessary
 * to modify the usual removal path to use kernfs_remove_self().  The
 * "delete" implementation can simply invoke kernfs_remove_self() on self
 * before proceeding with the usual removal path.  kernfs will ignore later
 * kernfs_remove() on self.
 *
 * kernfs_remove_self() can be called multiple times concurrently on the
 * same kernfs_node.  Only the first one actually performs removal and
 * returns %true.  All others will wait until the kernfs operation which
 * won self-removal finishes and return %false.  Note that the losers wait
 * for the completion of not only the winning kernfs_remove_self() but also
 * the whole kernfs_ops which won the arbitration.  This can be used to
 * guarantee, for example, all concurrent writes to a "delete" file to
 * finish only after the whole operation is complete.
 */
bool kernfs_remove_self(struct kernfs_node *kn)
{
	bool ret;

	mutex_lock(&kernfs_mutex);
	__kernfs_deactivate_self(kn);

	/*
	 * SUICIDAL is used to arbitrate among competing invocations.  Only
	 * the first one will actually perform removal.  When the removal
	 * is complete, SUICIDED is set and the active ref is restored
	 * while holding kernfs_mutex.  The ones which lost arbitration
	 * waits for SUICDED && drained which can happen only after the
	 * enclosing kernfs operation which executed the winning instance
	 * of kernfs_remove_self() finished.
	 */
	if (!(kn->flags & KERNFS_SUICIDAL)) {
		kn->flags |= KERNFS_SUICIDAL;
		__kernfs_remove(kn);
		kn->flags |= KERNFS_SUICIDED;
		ret = true;
	} else {
		wait_queue_head_t *waitq = &kernfs_root(kn)->deactivate_waitq;
		DEFINE_WAIT(wait);

		while (true) {
			prepare_to_wait(waitq, &wait, TASK_UNINTERRUPTIBLE);

			if ((kn->flags & KERNFS_SUICIDED) &&
			    atomic_read(&kn->active) == KN_DEACTIVATED_BIAS)
				break;

			mutex_unlock(&kernfs_mutex);
			schedule();
			mutex_lock(&kernfs_mutex);
		}
		finish_wait(waitq, &wait);
		WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb));
		ret = false;
	}

	__kernfs_reactivate_self(kn);
	mutex_unlock(&kernfs_mutex);
	return ret;
}

/**
 * kernfs_remove_by_name_ns - find a kernfs_node by name and remove it
 * @parent: parent of the target
 * @name: name of the kernfs_node to remove
 * @ns: namespace tag of the kernfs_node to remove
 *
 * Look for the kernfs_node with @name and @ns under @parent and remove it.
 * Returns 0 on success, -ENOENT if such entry doesn't exist.
 */
int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
			     const void *ns)
{
	struct kernfs_node *kn;

	if (!parent) {
		WARN(1, KERN_WARNING "kernfs: can not remove '%s', no directory\n",
			name);
		return -ENOENT;
	}

	mutex_lock(&kernfs_mutex);

	kn = kernfs_find_ns(parent, name, ns);
	if (kn)
		__kernfs_remove(kn);

	mutex_unlock(&kernfs_mutex);

	if (kn)
		return 0;
	else
		return -ENOENT;
}

/**
 * kernfs_rename_ns - move and rename a kernfs_node
 * @kn: target node
 * @new_parent: new parent to put @sd under
 * @new_name: new name
 * @new_ns: new namespace tag
 */
int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
		     const char *new_name, const void *new_ns)
{
	int error;

	error = -ENOENT;
	if (!kernfs_get_active(new_parent))
		goto out;
	if (!kernfs_get_active(kn))
		goto out_put_new_parent;

	mutex_lock(&kernfs_mutex);

	error = 0;
	if ((kn->parent == new_parent) && (kn->ns == new_ns) &&
	    (strcmp(kn->name, new_name) == 0))
		goto out_unlock;	/* nothing to rename */

	error = -EEXIST;
	if (kernfs_find_ns(new_parent, new_name, new_ns))
		goto out_unlock;

	/* rename kernfs_node */
	if (strcmp(kn->name, new_name) != 0) {
		error = -ENOMEM;
		new_name = kstrdup(new_name, GFP_KERNEL);
		if (!new_name)
			goto out_unlock;

		if (kn->flags & KERNFS_STATIC_NAME)
			kn->flags &= ~KERNFS_STATIC_NAME;
		else
			kfree(kn->name);

		kn->name = new_name;
	}

	/*
	 * Move to the appropriate place in the appropriate directories rbtree.
	 */
	kernfs_unlink_sibling(kn);
	kernfs_get(new_parent);
	kernfs_put(kn->parent);
	kn->ns = new_ns;
	kn->hash = kernfs_name_hash(kn->name, kn->ns);
	kn->parent = new_parent;
	kernfs_link_sibling(kn);

	error = 0;
out_unlock:
	mutex_unlock(&kernfs_mutex);
	kernfs_put_active(kn);
out_put_new_parent:
	kernfs_put_active(new_parent);
out:
	return error;
}

/* Relationship between s_mode and the DT_xxx types */
static inline unsigned char dt_type(struct kernfs_node *kn)
{
	return (kn->mode >> 12) & 15;
}

static int kernfs_dir_fop_release(struct inode *inode, struct file *filp)
{
	kernfs_put(filp->private_data);
	return 0;
}

static struct kernfs_node *kernfs_dir_pos(const void *ns,
	struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos)
{
	if (pos) {
		int valid = pos->parent == parent && hash == pos->hash;
		kernfs_put(pos);
		if (!valid)
			pos = NULL;
	}
	if (!pos && (hash > 1) && (hash < INT_MAX)) {
		struct rb_node *node = parent->dir.children.rb_node;
		while (node) {
			pos = rb_to_kn(node);

			if (hash < pos->hash)
				node = node->rb_left;
			else if (hash > pos->hash)
				node = node->rb_right;
			else
				break;
		}
	}
	/* Skip over entries in the wrong namespace */
	while (pos && pos->ns != ns) {
		struct rb_node *node = rb_next(&pos->rb);
		if (!node)
			pos = NULL;
		else
			pos = rb_to_kn(node);
	}
	return pos;
}

static struct kernfs_node *kernfs_dir_next_pos(const void *ns,
	struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos)
{
	pos = kernfs_dir_pos(ns, parent, ino, pos);
	if (pos)
		do {
			struct rb_node *node = rb_next(&pos->rb);
			if (!node)
				pos = NULL;
			else
				pos = rb_to_kn(node);
		} while (pos && pos->ns != ns);
	return pos;
}

static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
{
	struct dentry *dentry = file->f_path.dentry;
	struct kernfs_node *parent = dentry->d_fsdata;
	struct kernfs_node *pos = file->private_data;
	const void *ns = NULL;

	if (!dir_emit_dots(file, ctx))
		return 0;
	mutex_lock(&kernfs_mutex);

	if (kernfs_ns_enabled(parent))
		ns = kernfs_info(dentry->d_sb)->ns;

	for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos);
	     pos;
	     pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) {
		const char *name = pos->name;
		unsigned int type = dt_type(pos);
		int len = strlen(name);
		ino_t ino = pos->ino;

		ctx->pos = pos->hash;
		file->private_data = pos;
		kernfs_get(pos);

		mutex_unlock(&kernfs_mutex);
		if (!dir_emit(ctx, name, len, ino, type))
			return 0;
		mutex_lock(&kernfs_mutex);
	}
	mutex_unlock(&kernfs_mutex);
	file->private_data = NULL;
	ctx->pos = INT_MAX;
	return 0;
}

static loff_t kernfs_dir_fop_llseek(struct file *file, loff_t offset,
				    int whence)
{
	struct inode *inode = file_inode(file);
	loff_t ret;

	mutex_lock(&inode->i_mutex);
	ret = generic_file_llseek(file, offset, whence);
	mutex_unlock(&inode->i_mutex);

	return ret;
}

const struct file_operations kernfs_dir_fops = {
	.read		= generic_read_dir,
	.iterate	= kernfs_fop_readdir,
	.release	= kernfs_dir_fop_release,
	.llseek		= kernfs_dir_fop_llseek,
};