aboutsummaryrefslogtreecommitdiffstats
path: root/fs/sysfs/dir.c
blob: 048e6054c2fdb7b60f35945eb87067463eee5896 (plain) (blame)
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
/*
 * dir.c - Operations for sysfs directories.
 */

#undef DEBUG

#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/module.h>
#include <linux/kobject.h>
#include <linux/namei.h>
#include <linux/idr.h>
#include <linux/completion.h>
#include <asm/semaphore.h>
#include "sysfs.h"

DEFINE_MUTEX(sysfs_mutex);
spinlock_t sysfs_assoc_lock = SPIN_LOCK_UNLOCKED;

static spinlock_t sysfs_ino_lock = SPIN_LOCK_UNLOCKED;
static DEFINE_IDA(sysfs_ino_ida);

/**
 *	sysfs_link_sibling - link sysfs_dirent into sibling list
 *	@sd: sysfs_dirent of interest
 *
 *	Link @sd into its sibling list which starts from
 *	sd->s_parent->s_children.
 *
 *	Locking:
 *	mutex_lock(sysfs_mutex)
 */
void sysfs_link_sibling(struct sysfs_dirent *sd)
{
	struct sysfs_dirent *parent_sd = sd->s_parent;

	BUG_ON(sd->s_sibling);
	sd->s_sibling = parent_sd->s_children;
	parent_sd->s_children = sd;
}

/**
 *	sysfs_unlink_sibling - unlink sysfs_dirent from sibling list
 *	@sd: sysfs_dirent of interest
 *
 *	Unlink @sd from its sibling list which starts from
 *	sd->s_parent->s_children.
 *
 *	Locking:
 *	mutex_lock(sysfs_mutex)
 */
void sysfs_unlink_sibling(struct sysfs_dirent *sd)
{
	struct sysfs_dirent **pos;

	for (pos = &sd->s_parent->s_children; *pos; pos = &(*pos)->s_sibling) {
		if (*pos == sd) {
			*pos = sd->s_sibling;
			sd->s_sibling = NULL;
			break;
		}
	}
}

/**
 *	sysfs_get_dentry - get dentry for the given sysfs_dirent
 *	@sd: sysfs_dirent of interest
 *
 *	Get dentry for @sd.  Dentry is looked up if currently not
 *	present.  This function climbs sysfs_dirent tree till it
 *	reaches a sysfs_dirent with valid dentry attached and descends
 *	down from there looking up dentry for each step.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep)
 *
 *	RETURNS:
 *	Pointer to found dentry on success, ERR_PTR() value on error.
 */
struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd)
{
	struct sysfs_dirent *cur;
	struct dentry *parent_dentry, *dentry;
	int i, depth;

	/* Find the first parent which has valid s_dentry and get the
	 * dentry.
	 */
	mutex_lock(&sysfs_mutex);
 restart0:
	spin_lock(&sysfs_assoc_lock);
 restart1:
	spin_lock(&dcache_lock);

	dentry = NULL;
	depth = 0;
	cur = sd;
	while (!cur->s_dentry || !cur->s_dentry->d_inode) {
		if (cur->s_flags & SYSFS_FLAG_REMOVED) {
			dentry = ERR_PTR(-ENOENT);
			depth = 0;
			break;
		}
		cur = cur->s_parent;
		depth++;
	}
	if (!IS_ERR(dentry))
		dentry = dget_locked(cur->s_dentry);

	spin_unlock(&dcache_lock);
	spin_unlock(&sysfs_assoc_lock);

	/* from the found dentry, look up depth times */
	while (depth--) {
		/* find and get depth'th ancestor */
		for (cur = sd, i = 0; cur && i < depth; i++)
			cur = cur->s_parent;

		/* This can happen if tree structure was modified due
		 * to move/rename.  Restart.
		 */
		if (i != depth) {
			dput(dentry);
			goto restart0;
		}

		sysfs_get(cur);

		mutex_unlock(&sysfs_mutex);

		/* look it up */
		parent_dentry = dentry;
		dentry = lookup_one_len_kern(cur->s_name, parent_dentry,
					     strlen(cur->s_name));
		dput(parent_dentry);

		if (IS_ERR(dentry)) {
			sysfs_put(cur);
			return dentry;
		}

		mutex_lock(&sysfs_mutex);
		spin_lock(&sysfs_assoc_lock);

		/* This, again, can happen if tree structure has
		 * changed and we looked up the wrong thing.  Restart.
		 */
		if (cur->s_dentry != dentry) {
			dput(dentry);
			sysfs_put(cur);
			goto restart1;
		}

		spin_unlock(&sysfs_assoc_lock);

		sysfs_put(cur);
	}

	mutex_unlock(&sysfs_mutex);
	return dentry;
}

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

	while (1) {
		int v, t;

		v = atomic_read(&sd->s_active);
		if (unlikely(v < 0))
			return NULL;

		t = atomic_cmpxchg(&sd->s_active, v, v + 1);
		if (likely(t == v))
			return sd;
		if (t < 0)
			return NULL;

		cpu_relax();
	}
}

/**
 *	sysfs_put_active - put an active reference to sysfs_dirent
 *	@sd: sysfs_dirent to put an active reference to
 *
 *	Put an active reference to @sd.  This function is noop if @sd
 *	is NULL.
 */
void sysfs_put_active(struct sysfs_dirent *sd)
{
	struct completion *cmpl;
	int v;

	if (unlikely(!sd))
		return;

	v = atomic_dec_return(&sd->s_active);
	if (likely(v != SD_DEACTIVATED_BIAS))
		return;

	/* atomic_dec_return() is a mb(), we'll always see the updated
	 * sd->s_sibling.
	 */
	cmpl = (void *)sd->s_sibling;
	complete(cmpl);
}

/**
 *	sysfs_get_active_two - get active references to sysfs_dirent and parent
 *	@sd: sysfs_dirent of interest
 *
 *	Get active reference to @sd and its parent.  Parent's active
 *	reference is grabbed first.  This function is noop if @sd is
 *	NULL.
 *
 *	RETURNS:
 *	Pointer to @sd on success, NULL on failure.
 */
struct sysfs_dirent *sysfs_get_active_two(struct sysfs_dirent *sd)
{
	if (sd) {
		if (sd->s_parent && unlikely(!sysfs_get_active(sd->s_parent)))
			return NULL;
		if (unlikely(!sysfs_get_active(sd))) {
			sysfs_put_active(sd->s_parent);
			return NULL;
		}
	}
	return sd;
}

/**
 *	sysfs_put_active_two - put active references to sysfs_dirent and parent
 *	@sd: sysfs_dirent of interest
 *
 *	Put active references to @sd and its parent.  This function is
 *	noop if @sd is NULL.
 */
void sysfs_put_active_two(struct sysfs_dirent *sd)
{
	if (sd) {
		sysfs_put_active(sd);
		sysfs_put_active(sd->s_parent);
	}
}

/**
 *	sysfs_deactivate - deactivate sysfs_dirent
 *	@sd: sysfs_dirent to deactivate
 *
 *	Deny new active references and drain existing ones.
 */
static void sysfs_deactivate(struct sysfs_dirent *sd)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	int v;

	BUG_ON(sd->s_sibling || !(sd->s_flags & SYSFS_FLAG_REMOVED));
	sd->s_sibling = (void *)&wait;

	/* atomic_add_return() is a mb(), put_active() will always see
	 * the updated sd->s_sibling.
	 */
	v = atomic_add_return(SD_DEACTIVATED_BIAS, &sd->s_active);

	if (v != SD_DEACTIVATED_BIAS)
		wait_for_completion(&wait);

	sd->s_sibling = NULL;
}

static int sysfs_alloc_ino(ino_t *pino)
{
	int ino, rc;

 retry:
	spin_lock(&sysfs_ino_lock);
	rc = ida_get_new_above(&sysfs_ino_ida, 2, &ino);
	spin_unlock(&sysfs_ino_lock);

	if (rc == -EAGAIN) {
		if (ida_pre_get(&sysfs_ino_ida, GFP_KERNEL))
			goto retry;
		rc = -ENOMEM;
	}

	*pino = ino;
	return rc;
}

static void sysfs_free_ino(ino_t ino)
{
	spin_lock(&sysfs_ino_lock);
	ida_remove(&sysfs_ino_ida, ino);
	spin_unlock(&sysfs_ino_lock);
}

void release_sysfs_dirent(struct sysfs_dirent * sd)
{
	struct sysfs_dirent *parent_sd;

 repeat:
	/* Moving/renaming is always done while holding reference.
	 * sd->s_parent won't change beneath us.
	 */
	parent_sd = sd->s_parent;

	if (sysfs_type(sd) == SYSFS_KOBJ_LINK)
		sysfs_put(sd->s_elem.symlink.target_sd);
	if (sysfs_type(sd) & SYSFS_COPY_NAME)
		kfree(sd->s_name);
	kfree(sd->s_iattr);
	sysfs_free_ino(sd->s_ino);
	kmem_cache_free(sysfs_dir_cachep, sd);

	sd = parent_sd;
	if (sd && atomic_dec_and_test(&sd->s_count))
		goto repeat;
}

static void sysfs_d_iput(struct dentry * dentry, struct inode * inode)
{
	struct sysfs_dirent * sd = dentry->d_fsdata;

	if (sd) {
		/* sd->s_dentry is protected with sysfs_assoc_lock.
		 * This allows sysfs_drop_dentry() to dereference it.
		 */
		spin_lock(&sysfs_assoc_lock);

		/* The dentry might have been deleted or another
		 * lookup could have happened updating sd->s_dentry to
		 * point the new dentry.  Ignore if it isn't pointing
		 * to this dentry.
		 */
		if (sd->s_dentry == dentry)
			sd->s_dentry = NULL;
		spin_unlock(&sysfs_assoc_lock);
		sysfs_put(sd);
	}
	iput(inode);
}

static struct dentry_operations sysfs_dentry_ops = {
	.d_iput		= sysfs_d_iput,
};

struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
{
	char *dup_name = NULL;
	struct sysfs_dirent *sd;

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

	sd = kmem_cache_zalloc(sysfs_dir_cachep, GFP_KERNEL);
	if (!sd)
		goto err_out1;

	if (sysfs_alloc_ino(&sd->s_ino))
		goto err_out2;

	atomic_set(&sd->s_count, 1);
	atomic_set(&sd->s_active, 0);
	atomic_set(&sd->s_event, 1);

	sd->s_name = name;
	sd->s_mode = mode;
	sd->s_flags = type;

	return sd;

 err_out2:
	kmem_cache_free(sysfs_dir_cachep, sd);
 err_out1:
	kfree(dup_name);
	return NULL;
}

/**
 *	sysfs_attach_dentry - associate sysfs_dirent with dentry
 *	@sd: target sysfs_dirent
 *	@dentry: dentry to associate
 *
 *	Associate @sd with @dentry.  This is protected by
 *	sysfs_assoc_lock to avoid race with sysfs_d_iput().
 *
 *	LOCKING:
 *	mutex_lock(sysfs_mutex)
 */
static void sysfs_attach_dentry(struct sysfs_dirent *sd, struct dentry *dentry)
{
	dentry->d_op = &sysfs_dentry_ops;
	dentry->d_fsdata = sysfs_get(sd);

	/* protect sd->s_dentry against sysfs_d_iput */
	spin_lock(&sysfs_assoc_lock);
	sd->s_dentry = dentry;
	spin_unlock(&sysfs_assoc_lock);

	d_rehash(dentry);
}

static int sysfs_ilookup_test(struct inode *inode, void *arg)
{
	struct sysfs_dirent *sd = arg;
	return inode->i_ino == sd->s_ino;
}

/**
 *	sysfs_addrm_start - prepare for sysfs_dirent add/remove
 *	@acxt: pointer to sysfs_addrm_cxt to be used
 *	@parent_sd: parent sysfs_dirent
 *
 *	This function is called when the caller is about to add or
 *	remove sysfs_dirent under @parent_sd.  This function acquires
 *	sysfs_mutex, grabs inode for @parent_sd if available and lock
 *	i_mutex of it.  @acxt is used to keep and pass context to
 *	other addrm functions.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).  sysfs_mutex is locked on
 *	return.  i_mutex of parent inode is locked on return if
 *	available.
 */
void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
		       struct sysfs_dirent *parent_sd)
{
	struct inode *inode;

	memset(acxt, 0, sizeof(*acxt));
	acxt->parent_sd = parent_sd;

	/* Lookup parent inode.  inode initialization and I_NEW
	 * clearing are protected by sysfs_mutex.  By grabbing it and
	 * looking up with _nowait variant, inode state can be
	 * determined reliably.
	 */
	mutex_lock(&sysfs_mutex);

	inode = ilookup5_nowait(sysfs_sb, parent_sd->s_ino, sysfs_ilookup_test,
				parent_sd);

	if (inode && !(inode->i_state & I_NEW)) {
		/* parent inode available */
		acxt->parent_inode = inode;

		/* sysfs_mutex is below i_mutex in lock hierarchy.
		 * First, trylock i_mutex.  If fails, unlock
		 * sysfs_mutex and lock them in order.
		 */
		if (!mutex_trylock(&inode->i_mutex)) {
			mutex_unlock(&sysfs_mutex);
			mutex_lock(&inode->i_mutex);
			mutex_lock(&sysfs_mutex);
		}
	} else
		iput(inode);
}

/**
 *	sysfs_add_one - add sysfs_dirent to parent
 *	@acxt: addrm context to use
 *	@sd: sysfs_dirent to be added
 *
 *	Get @acxt->parent_sd and set sd->s_parent to it and increment
 *	nlink of parent inode if @sd is a directory.  @sd is NOT
 *	linked into the children list of the parent.  The caller
 *	should invoke sysfs_link_sibling() after this function
 *	completes if @sd needs to be on the children list.
 *
 *	This function should be called between calls to
 *	sysfs_addrm_start() and sysfs_addrm_finish() and should be
 *	passed the same @acxt as passed to sysfs_addrm_start().
 *
 *	LOCKING:
 *	Determined by sysfs_addrm_start().
 */
void sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
	sd->s_parent = sysfs_get(acxt->parent_sd);

	if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
		inc_nlink(acxt->parent_inode);

	acxt->cnt++;
}

/**
 *	sysfs_remove_one - remove sysfs_dirent from parent
 *	@acxt: addrm context to use
 *	@sd: sysfs_dirent to be added
 *
 *	Mark @sd removed and drop nlink of parent inode if @sd is a
 *	directory.  @sd is NOT unlinked from the children list of the
 *	parent.  The caller is repsonsible for removing @sd from the
 *	children list before calling this function.
 *
 *	This function should be called between calls to
 *	sysfs_addrm_start() and sysfs_addrm_finish() and should be
 *	passed the same @acxt as passed to sysfs_addrm_start().
 *
 *	LOCKING:
 *	Determined by sysfs_addrm_start().
 */
void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
	BUG_ON(sd->s_sibling || (sd->s_flags & SYSFS_FLAG_REMOVED));

	sd->s_flags |= SYSFS_FLAG_REMOVED;
	sd->s_sibling = acxt->removed;
	acxt->removed = sd;

	if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
		drop_nlink(acxt->parent_inode);

	acxt->cnt++;
}

/**
 *	sysfs_drop_dentry - drop dentry for the specified sysfs_dirent
 *	@sd: target sysfs_dirent
 *
 *	Drop dentry for @sd.  @sd must have been unlinked from its
 *	parent on entry to this function such that it can't be looked
 *	up anymore.
 *
 *	@sd->s_dentry which is protected with sysfs_assoc_lock points
 *	to the currently associated dentry but we're not holding a
 *	reference to it and racing with dput().  Grab dcache_lock and
 *	verify dentry before dropping it.  If @sd->s_dentry is NULL or
 *	dput() beats us, no need to bother.
 */
static void sysfs_drop_dentry(struct sysfs_dirent *sd)
{
	struct dentry *dentry = NULL;
	struct inode *inode;

	/* We're not holding a reference to ->s_dentry dentry but the
	 * field will stay valid as long as sysfs_assoc_lock is held.
	 */
	spin_lock(&sysfs_assoc_lock);
	spin_lock(&dcache_lock);

	/* drop dentry if it's there and dput() didn't kill it yet */
	if (sd->s_dentry && sd->s_dentry->d_inode) {
		dentry = dget_locked(sd->s_dentry);
		spin_lock(&dentry->d_lock);
		__d_drop(dentry);
		spin_unlock(&dentry->d_lock);
	}

	spin_unlock(&dcache_lock);
	spin_unlock(&sysfs_assoc_lock);

	/* dentries for shadowed inodes are pinned, unpin */
	if (dentry && sysfs_is_shadowed_inode(dentry->d_inode))
		dput(dentry);
	dput(dentry);

	/* adjust nlink and update timestamp */
	inode = ilookup(sysfs_sb, sd->s_ino);
	if (inode) {
		mutex_lock(&inode->i_mutex);

		inode->i_ctime = CURRENT_TIME;
		drop_nlink(inode);
		if (sysfs_type(sd) == SYSFS_DIR)
			drop_nlink(inode);

		mutex_unlock(&inode->i_mutex);
		iput(inode);
	}
}

/**
 *	sysfs_addrm_finish - finish up sysfs_dirent add/remove
 *	@acxt: addrm context to finish up
 *
 *	Finish up sysfs_dirent add/remove.  Resources acquired by
 *	sysfs_addrm_start() are released and removed sysfs_dirents are
 *	cleaned up.  Timestamps on the parent inode are updated.
 *
 *	LOCKING:
 *	All mutexes acquired by sysfs_addrm_start() are released.
 *
 *	RETURNS:
 *	Number of added/removed sysfs_dirents since sysfs_addrm_start().
 */
int sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
{
	/* release resources acquired by sysfs_addrm_start() */
	mutex_unlock(&sysfs_mutex);
	if (acxt->parent_inode) {
		struct inode *inode = acxt->parent_inode;

		/* if added/removed, update timestamps on the parent */
		if (acxt->cnt)
			inode->i_ctime = inode->i_mtime = CURRENT_TIME;

		mutex_unlock(&inode->i_mutex);
		iput(inode);
	}

	/* kill removed sysfs_dirents */
	while (acxt->removed) {
		struct sysfs_dirent *sd = acxt->removed;

		acxt->removed = sd->s_sibling;
		sd->s_sibling = NULL;

		sysfs_drop_dentry(sd);
		sysfs_deactivate(sd);
		sysfs_put(sd);
	}

	return acxt->cnt;
}

/**
 *	sysfs_find_dirent - find sysfs_dirent with the given name
 *	@parent_sd: sysfs_dirent to search under
 *	@name: name to look for
 *
 *	Look for sysfs_dirent with name @name under @parent_sd.
 *
 *	LOCKING:
 *	mutex_lock(sysfs_mutex)
 *
 *	RETURNS:
 *	Pointer to sysfs_dirent if found, NULL if not.
 */
struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
				       const unsigned char *name)
{
	struct sysfs_dirent *sd;

	for (sd = parent_sd->s_children; sd; sd = sd->s_sibling)
		if (sysfs_type(sd) && !strcmp(sd->s_name, name))
			return sd;
	return NULL;
}

/**
 *	sysfs_get_dirent - find and get sysfs_dirent with the given name
 *	@parent_sd: sysfs_dirent to search under
 *	@name: name to look for
 *
 *	Look for sysfs_dirent with name @name under @parent_sd and get
 *	it if found.
 *
 *	LOCKING:
 *	Kernel thread context (may sleep).  Grabs sysfs_mutex.
 *
 *	RETURNS:
 *	Pointer to sysfs_dirent if found, NULL if not.
 */
struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
				      const unsigned char *name)
{
	struct sysfs_dirent *sd;

	mutex_lock(&sysfs_mutex);
	sd = sysfs_find_dirent(parent_sd, name);
	sysfs_get(sd);
	mutex_unlock(&sysfs_mutex);

	return sd;
}

static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
		      const char *name, struct sysfs_dirent **p_sd)
{
	umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
	struct sysfs_addrm_cxt acxt;
	struct sysfs_dirent *sd;

	/* allocate */
	sd = sysfs_new_dirent(name, mode, SYSFS_DIR);
	if (!sd)
		return -ENOMEM;
	sd->s_elem.dir.kobj = kobj;

	/* link in */
	sysfs_addrm_start(&acxt, parent_sd);

	if (!sysfs_find_dirent(parent_sd, name)) {
		sysfs_add_one(&acxt, sd);
		sysfs_link_sibling(sd);
	}

	if (!sysfs_addrm_finish(&acxt)) {
		sysfs_put(sd);
		return -EEXIST;
	}

	*p_sd = sd;
	return 0;
}

int sysfs_create_subdir(struct kobject *kobj, const char *name,
			struct sysfs_dirent **p_sd)
{
	return create_dir(kobj, kobj->sd, name, p_sd);
}

/**
 *	sysfs_create_dir - create a directory for an object.
 *	@kobj:		object we're creating directory for. 
 *	@shadow_parent:	parent object.
 */
int sysfs_create_dir(struct kobject *kobj,
		     struct sysfs_dirent *shadow_parent_sd)
{
	struct sysfs_dirent *parent_sd, *sd;
	int error = 0;

	BUG_ON(!kobj);

	if (shadow_parent_sd)
		parent_sd = shadow_parent_sd;
	else if (kobj->parent)
		parent_sd = kobj->parent->sd;
	else if (sysfs_mount && sysfs_mount->mnt_sb)
		parent_sd = sysfs_mount->mnt_sb->s_root->d_fsdata;
	else
		return -EFAULT;

	error = create_dir(kobj, parent_sd, kobject_name(kobj), &sd);
	if (!error)
		kobj->sd = sd;
	return error;
}

static int sysfs_count_nlink(struct sysfs_dirent *sd)
{
	struct sysfs_dirent *child;
	int nr = 0;

	for (child = sd->s_children; child; child = child->s_sibling)
		if (sysfs_type(child) == SYSFS_DIR)
			nr++;
	return nr + 2;
}

static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
				struct nameidata *nd)
{
	struct sysfs_dirent * parent_sd = dentry->d_parent->d_fsdata;
	struct sysfs_dirent * sd;
	struct bin_attribute *bin_attr;
	struct inode *inode;
	int found = 0;

	for (sd = parent_sd->s_children; sd; sd = sd->s_sibling) {
		if (sysfs_type(sd) &&
		    !strcmp(sd->s_name, dentry->d_name.name)) {
			found = 1;
			break;
		}
	}

	/* no such entry */
	if (!found)
		return NULL;

	/* attach dentry and inode */
	inode = sysfs_get_inode(sd);
	if (!inode)
		return ERR_PTR(-ENOMEM);

	mutex_lock(&sysfs_mutex);

	if (inode->i_state & I_NEW) {
		/* initialize inode according to type */
		switch (sysfs_type(sd)) {
		case SYSFS_DIR:
			inode->i_op = &sysfs_dir_inode_operations;
			inode->i_fop = &sysfs_dir_operations;
			inode->i_nlink = sysfs_count_nlink(sd);
			break;
		case SYSFS_KOBJ_ATTR:
			inode->i_size = PAGE_SIZE;
			inode->i_fop = &sysfs_file_operations;
			break;
		case SYSFS_KOBJ_BIN_ATTR:
			bin_attr = sd->s_elem.bin_attr.bin_attr;
			inode->i_size = bin_attr->size;
			inode->i_fop = &bin_fops;
			break;
		case SYSFS_KOBJ_LINK:
			inode->i_op = &sysfs_symlink_inode_operations;
			break;
		default:
			BUG();
		}
	}

	sysfs_instantiate(dentry, inode);
	sysfs_attach_dentry(sd, dentry);

	mutex_unlock(&sysfs_mutex);

	return NULL;
}

const struct inode_operations sysfs_dir_inode_operations = {
	.lookup		= sysfs_lookup,
	.setattr	= sysfs_setattr,
};

static void remove_dir(struct sysfs_dirent *sd)
{
	struct sysfs_addrm_cxt acxt;

	sysfs_addrm_start(&acxt, sd->s_parent);
	sysfs_unlink_sibling(sd);
	sysfs_remove_one(&acxt, sd);
	sysfs_addrm_finish(&acxt);
}

void sysfs_remove_subdir(struct sysfs_dirent *sd)
{
	remove_dir(sd);
}


static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd)
{
	struct sysfs_addrm_cxt acxt;
	struct sysfs_dirent **pos;

	if (!dir_sd)
		return;

	pr_debug("sysfs %s: removing dir\n", dir_sd->s_name);
	sysfs_addrm_start(&acxt, dir_sd);
	pos = &dir_sd->s_children;
	while (*pos) {
		struct sysfs_dirent *sd = *pos;

		if (sysfs_type(sd) && sysfs_type(sd) != SYSFS_DIR) {
			*pos = sd->s_sibling;
			sd->s_sibling = NULL;
			sysfs_remove_one(&acxt, sd);
		} else
			pos = &(*pos)->s_sibling;
	}
	sysfs_addrm_finish(&acxt);

	remove_dir(dir_sd);
}

/**
 *	sysfs_remove_dir - remove an object's directory.
 *	@kobj:	object.
 *
 *	The only thing special about this is that we remove any files in
 *	the directory before we remove the directory, and we've inlined
 *	what used to be sysfs_rmdir() below, instead of calling separately.
 */

void sysfs_remove_dir(struct kobject * kobj)
{
	struct sysfs_dirent *sd = kobj->sd;

	spin_lock(&sysfs_assoc_lock);
	kobj->sd = NULL;
	spin_unlock(&sysfs_assoc_lock);

	__sysfs_remove_dir(sd);
}

int sysfs_rename_dir(struct kobject *kobj, struct sysfs_dirent *new_parent_sd,
		     const char *new_name)
{
	struct sysfs_dirent *sd = kobj->sd;
	struct dentry *new_parent = NULL;
	struct dentry *old_dentry = NULL, *new_dentry = NULL;
	const char *dup_name = NULL;
	int error;

	/* get dentries */
	old_dentry = sysfs_get_dentry(sd);
	if (IS_ERR(old_dentry)) {
		error = PTR_ERR(old_dentry);
		goto out_dput;
	}

	new_parent = sysfs_get_dentry(new_parent_sd);
	if (IS_ERR(new_parent)) {
		error = PTR_ERR(new_parent);
		goto out_dput;
	}

	/* lock new_parent and get dentry for new name */
	mutex_lock(&new_parent->d_inode->i_mutex);

	new_dentry = lookup_one_len(new_name, new_parent, strlen(new_name));
	if (IS_ERR(new_dentry)) {
		error = PTR_ERR(new_dentry);
		goto out_unlock;
	}

	/* By allowing two different directories with the same
	 * d_parent we allow this routine to move between different
	 * shadows of the same directory
	 */
	error = -EINVAL;
	if (old_dentry->d_parent->d_inode != new_parent->d_inode ||
	    new_dentry->d_parent->d_inode != new_parent->d_inode ||
	    old_dentry == new_dentry)
		goto out_unlock;

	error = -EEXIST;
	if (new_dentry->d_inode)
		goto out_unlock;

	/* rename kobject and sysfs_dirent */
	error = -ENOMEM;
	new_name = dup_name = kstrdup(new_name, GFP_KERNEL);
	if (!new_name)
		goto out_drop;

	error = kobject_set_name(kobj, "%s", new_name);
	if (error)
		goto out_drop;

	dup_name = sd->s_name;
	sd->s_name = new_name;

	/* move under the new parent */
	d_add(new_dentry, NULL);
	d_move(sd->s_dentry, new_dentry);

	mutex_lock(&sysfs_mutex);

	sysfs_unlink_sibling(sd);
	sysfs_get(new_parent_sd);
	sysfs_put(sd->s_parent);
	sd->s_parent = new_parent_sd;
	sysfs_link_sibling(sd);

	mutex_unlock(&sysfs_mutex);

	error = 0;
	goto out_unlock;

 out_drop:
	d_drop(new_dentry);
 out_unlock:
	mutex_unlock(&new_parent->d_inode->i_mutex);
 out_dput:
	kfree(dup_name);
	dput(new_parent);
	dput(old_dentry);
	dput(new_dentry);
	return error;
}

int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj)
{
	struct sysfs_dirent *sd = kobj->sd;
	struct sysfs_dirent *new_parent_sd;
	struct dentry *old_parent, *new_parent = NULL;
	struct dentry *old_dentry = NULL, *new_dentry = NULL;
	int error;

	BUG_ON(!sd->s_parent);
	new_parent_sd = new_parent_kobj->sd ? new_parent_kobj->sd : &sysfs_root;

	/* get dentries */
	old_dentry = sysfs_get_dentry(sd);
	if (IS_ERR(old_dentry)) {
		error = PTR_ERR(old_dentry);
		goto out_dput;
	}
	old_parent = sd->s_parent->s_dentry;

	new_parent = sysfs_get_dentry(new_parent_sd);
	if (IS_ERR(new_parent)) {
		error = PTR_ERR(new_parent);
		goto out_dput;
	}

	if (old_parent->d_inode == new_parent->d_inode) {
		error = 0;
		goto out_dput;	/* nothing to move */
	}
again:
	mutex_lock(&old_parent->d_inode->i_mutex);
	if (!mutex_trylock(&new_parent->d_inode->i_mutex)) {
		mutex_unlock(&old_parent->d_inode->i_mutex);
		goto again;
	}

	new_dentry = lookup_one_len(kobj->name, new_parent, strlen(kobj->name));
	if (IS_ERR(new_dentry)) {
		error = PTR_ERR(new_dentry);
		goto out_unlock;
	} else
		error = 0;
	d_add(new_dentry, NULL);
	d_move(sd->s_dentry, new_dentry);
	dput(new_dentry);

	/* Remove from old parent's list and insert into new parent's list. */
	mutex_lock(&sysfs_mutex);

	sysfs_unlink_sibling(sd);
	sysfs_get(new_parent_sd);
	sysfs_put(sd->s_parent);
	sd->s_parent = new_parent_sd;
	sysfs_link_sibling(sd);

	mutex_unlock(&sysfs_mutex);

 out_unlock:
	mutex_unlock(&new_parent->d_inode->i_mutex);
	mutex_unlock(&old_parent->d_inode->i_mutex);
 out_dput:
	dput(new_parent);
	dput(old_dentry);
	dput(new_dentry);
	return error;
}

static int sysfs_dir_open(struct inode *inode, struct file *file)
{
	struct dentry * dentry = file->f_path.dentry;
	struct sysfs_dirent * parent_sd = dentry->d_fsdata;
	struct sysfs_dirent * sd;

	sd = sysfs_new_dirent("_DIR_", 0, 0);
	if (sd) {
		mutex_lock(&sysfs_mutex);
		sd->s_parent = sysfs_get(parent_sd);
		sysfs_link_sibling(sd);
		mutex_unlock(&sysfs_mutex);
	}

	file->private_data = sd;
	return sd ? 0 : -ENOMEM;
}

static int sysfs_dir_close(struct inode *inode, struct file *file)
{
	struct sysfs_dirent * cursor = file->private_data;

	mutex_lock(&sysfs_mutex);
	sysfs_unlink_sibling(cursor);
	mutex_unlock(&sysfs_mutex);

	release_sysfs_dirent(cursor);

	return 0;
}

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

static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
	struct dentry *dentry = filp->f_path.dentry;
	struct sysfs_dirent * parent_sd = dentry->d_fsdata;
	struct sysfs_dirent *cursor = filp->private_data;
	struct sysfs_dirent **pos;
	ino_t ino;
	int i = filp->f_pos;

	switch (i) {
		case 0:
			ino = parent_sd->s_ino;
			if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
				break;
			filp->f_pos++;
			i++;
			/* fallthrough */
		case 1:
			if (parent_sd->s_parent)
				ino = parent_sd->s_parent->s_ino;
			else
				ino = parent_sd->s_ino;
			if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
				break;
			filp->f_pos++;
			i++;
			/* fallthrough */
		default:
			mutex_lock(&sysfs_mutex);

			pos = &parent_sd->s_children;
			while (*pos != cursor)
				pos = &(*pos)->s_sibling;

			/* unlink cursor */
			*pos = cursor->s_sibling;

			if (filp->f_pos == 2)
				pos = &parent_sd->s_children;

			for ( ; *pos; pos = &(*pos)->s_sibling) {
				struct sysfs_dirent *next = *pos;
				const char * name;
				int len;

				if (!sysfs_type(next))
					continue;

				name = next->s_name;
				len = strlen(name);
				ino = next->s_ino;

				if (filldir(dirent, name, len, filp->f_pos, ino,
						 dt_type(next)) < 0)
					break;

				filp->f_pos++;
			}

			/* put cursor back in */
			cursor->s_sibling = *pos;
			*pos = cursor;

			mutex_unlock(&sysfs_mutex);
	}
	return 0;
}

static loff_t sysfs_dir_lseek(struct file * file, loff_t offset, int origin)
{
	struct dentry * dentry = file->f_path.dentry;

	switch (origin) {
		case 1:
			offset += file->f_pos;
		case 0:
			if (offset >= 0)
				break;
		default:
			return -EINVAL;
	}
	if (offset != file->f_pos) {
		mutex_lock(&sysfs_mutex);

		file->f_pos = offset;
		if (file->f_pos >= 2) {
			struct sysfs_dirent *sd = dentry->d_fsdata;
			struct sysfs_dirent *cursor = file->private_data;
			struct sysfs_dirent **pos;
			loff_t n = file->f_pos - 2;

			sysfs_unlink_sibling(cursor);

			pos = &sd->s_children;
			while (n && *pos) {
				struct sysfs_dirent *next = *pos;
				if (sysfs_type(next))
					n--;
				pos = &(*pos)->s_sibling;
			}

			cursor->s_sibling = *pos;
			*pos = cursor;
		}

		mutex_unlock(&sysfs_mutex);
	}

	return offset;
}


/**
 *	sysfs_make_shadowed_dir - Setup so a directory can be shadowed
 *	@kobj:	object we're creating shadow of.
 */

int sysfs_make_shadowed_dir(struct kobject *kobj,
	void * (*follow_link)(struct dentry *, struct nameidata *))
{
	struct dentry *dentry;
	struct inode *inode;
	struct inode_operations *i_op;

	/* get dentry for @kobj->sd, dentry of a shadowed dir is pinned */
	dentry = sysfs_get_dentry(kobj->sd);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);

	inode = dentry->d_inode;
	if (inode->i_op != &sysfs_dir_inode_operations) {
		dput(dentry);
		return -EINVAL;
	}

	i_op = kmalloc(sizeof(*i_op), GFP_KERNEL);
	if (!i_op)
		return -ENOMEM;

	memcpy(i_op, &sysfs_dir_inode_operations, sizeof(*i_op));
	i_op->follow_link = follow_link;

	/* Locking of inode->i_op?
	 * Since setting i_op is a single word write and they
	 * are atomic we should be ok here.
	 */
	inode->i_op = i_op;
	return 0;
}

/**
 *	sysfs_create_shadow_dir - create a shadow directory for an object.
 *	@kobj:	object we're creating directory for.
 *
 *	sysfs_make_shadowed_dir must already have been called on this
 *	directory.
 */

struct sysfs_dirent *sysfs_create_shadow_dir(struct kobject *kobj)
{
	struct sysfs_dirent *parent_sd = kobj->sd->s_parent;
	struct dentry *dir, *parent, *shadow;
	struct inode *inode;
	struct sysfs_dirent *sd;
	struct sysfs_addrm_cxt acxt;

	dir = sysfs_get_dentry(kobj->sd);
	if (IS_ERR(dir)) {
		sd = (void *)dir;
		goto out;
	}
	parent = dir->d_parent;

	inode = dir->d_inode;
	sd = ERR_PTR(-EINVAL);
	if (!sysfs_is_shadowed_inode(inode))
		goto out_dput;

	shadow = d_alloc(parent, &dir->d_name);
	if (!shadow)
		goto nomem;

	sd = sysfs_new_dirent("_SHADOW_", inode->i_mode, SYSFS_DIR);
	if (!sd)
		goto nomem;
	sd->s_elem.dir.kobj = kobj;

	sysfs_addrm_start(&acxt, parent_sd);

	/* add but don't link into children list */
	sysfs_add_one(&acxt, sd);

	/* attach and instantiate dentry */
	sysfs_attach_dentry(sd, shadow);
	d_instantiate(shadow, igrab(inode));
	inc_nlink(inode);	/* tj: synchronization? */

	sysfs_addrm_finish(&acxt);

	dget(shadow);		/* Extra count - pin the dentry in core */

	goto out_dput;

 nomem:
	dput(shadow);
	sd = ERR_PTR(-ENOMEM);
 out_dput:
	dput(dir);
 out:
	return sd;
}

/**
 *	sysfs_remove_shadow_dir - remove an object's directory.
 *	@shadow_sd: sysfs_dirent of shadow directory
 *
 *	The only thing special about this is that we remove any files in
 *	the directory before we remove the directory, and we've inlined
 *	what used to be sysfs_rmdir() below, instead of calling separately.
 */

void sysfs_remove_shadow_dir(struct sysfs_dirent *shadow_sd)
{
	__sysfs_remove_dir(shadow_sd);
}

const struct file_operations sysfs_dir_operations = {
	.open		= sysfs_dir_open,
	.release	= sysfs_dir_close,
	.llseek		= sysfs_dir_lseek,
	.read		= generic_read_dir,
	.readdir	= sysfs_readdir,
};