summaryrefslogtreecommitdiff
path: root/fs/sysfs/dir.c
blob: 40596a0eee526db8fac44d8667bcb83e638c9e34 (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
/*
 * 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"

DECLARE_RWSEM(sysfs_rename_sem);
spinlock_t sysfs_lock = SPIN_LOCK_UNLOCKED;
spinlock_t kobj_sysfs_assoc_lock = SPIN_LOCK_UNLOCKED;

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

/**
 *	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.next.
	 */
	cmpl = (void *)sd->s_sibling.next;
	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.
 */
void sysfs_deactivate(struct sysfs_dirent *sd)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	int v;

	BUG_ON(!list_empty(&sd->s_sibling));
	sd->s_sibling.next = (void *)&wait;

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

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

	INIT_LIST_HEAD(&sd->s_sibling);
}

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:
	parent_sd = sd->s_parent;

	if (sd->s_type & SYSFS_KOBJ_LINK)
		sysfs_put(sd->s_elem.symlink.target_sd);
	if (sd->s_type & 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_lock.  This
		 * allows sysfs_drop_dentry() to dereference it.
		 */
		spin_lock(&sysfs_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_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 = NULL;

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

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

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

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

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

	return sd;

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

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_lock);
	sd->s_dentry = dentry;
	spin_unlock(&sysfs_lock);

	d_rehash(dentry);
}

void sysfs_attach_dirent(struct sysfs_dirent *sd,
			 struct sysfs_dirent *parent_sd, struct dentry *dentry)
{
	if (dentry)
		sysfs_attach_dentry(sd, dentry);

	if (parent_sd) {
		sd->s_parent = sysfs_get(parent_sd);
		list_add(&sd->s_sibling, &parent_sd->s_children);
	}
}

/*
 *
 * Return -EEXIST if there is already a sysfs element with the same name for
 * the same parent.
 *
 * called with parent inode's i_mutex held
 */
int sysfs_dirent_exist(struct sysfs_dirent *parent_sd,
			  const unsigned char *new)
{
	struct sysfs_dirent * sd;

	list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
		if (sd->s_type) {
			if (strcmp(sd->s_name, new))
				continue;
			else
				return -EEXIST;
		}
	}

	return 0;
}

static int create_dir(struct kobject *kobj, struct dentry *parent,
		      const char *name, struct dentry **p_dentry)
{
	int error;
	umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
	struct dentry *dentry;
	struct inode *inode;
	struct sysfs_dirent *sd;

	mutex_lock(&parent->d_inode->i_mutex);

	/* allocate */
	dentry = lookup_one_len(name, parent, strlen(name));
	if (IS_ERR(dentry)) {
		error = PTR_ERR(dentry);
		goto out_unlock;
	}

	error = -EEXIST;
	if (dentry->d_inode)
		goto out_dput;

	error = -ENOMEM;
	sd = sysfs_new_dirent(name, mode, SYSFS_DIR);
	if (!sd)
		goto out_drop;
	sd->s_elem.dir.kobj = kobj;

	inode = sysfs_get_inode(sd);
	if (!inode)
		goto out_sput;

	if (inode->i_state & I_NEW) {
		inode->i_op = &sysfs_dir_inode_operations;
		inode->i_fop = &sysfs_dir_operations;
		/* directory inodes start off with i_nlink == 2 (for ".") */
		inc_nlink(inode);
	}

	/* link in */
	error = -EEXIST;
	if (sysfs_dirent_exist(parent->d_fsdata, name))
		goto out_iput;

	sysfs_instantiate(dentry, inode);
	inc_nlink(parent->d_inode);
	sysfs_attach_dirent(sd, parent->d_fsdata, dentry);

	*p_dentry = dentry;
	error = 0;
	goto out_unlock;	/* pin directory dentry in core */

 out_iput:
	iput(inode);
 out_sput:
	sysfs_put(sd);
 out_drop:
	d_drop(dentry);
 out_dput:
	dput(dentry);
 out_unlock:
	mutex_unlock(&parent->d_inode->i_mutex);
	return error;
}


int sysfs_create_subdir(struct kobject * k, const char * n, struct dentry ** d)
{
	return create_dir(k,k->dentry,n,d);
}

/**
 *	sysfs_create_dir - create a directory for an object.
 *	@kobj:		object we're creating directory for. 
 *	@shadow_parent:	parent parent object.
 */

int sysfs_create_dir(struct kobject * kobj, struct dentry *shadow_parent)
{
	struct dentry * dentry = NULL;
	struct dentry * parent;
	int error = 0;

	BUG_ON(!kobj);

	if (shadow_parent)
		parent = shadow_parent;
	else if (kobj->parent)
		parent = kobj->parent->dentry;
	else if (sysfs_mount && sysfs_mount->mnt_sb)
		parent = sysfs_mount->mnt_sb->s_root;
	else
		return -EFAULT;

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

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 inode *inode;
	int found = 0;

	list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
		if ((sd->s_type & SYSFS_NOT_PINNED) &&
		    !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);

	if (inode->i_state & I_NEW) {
		/* initialize inode according to type */
		if (sd->s_type & SYSFS_KOBJ_ATTR) {
			inode->i_size = PAGE_SIZE;
			inode->i_fop = &sysfs_file_operations;
		} else if (sd->s_type & SYSFS_KOBJ_BIN_ATTR) {
			struct bin_attribute *bin_attr =
				sd->s_elem.bin_attr.bin_attr;
			inode->i_size = bin_attr->size;
			inode->i_fop = &bin_fops;
		} else if (sd->s_type & SYSFS_KOBJ_LINK)
			inode->i_op = &sysfs_symlink_inode_operations;
	}

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

	return NULL;
}

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

static void remove_dir(struct dentry * d)
{
	struct dentry *parent = d->d_parent;
	struct sysfs_dirent *sd = d->d_fsdata;

	mutex_lock(&parent->d_inode->i_mutex);

 	list_del_init(&sd->s_sibling);

	pr_debug(" o %s removing done (%d)\n",d->d_name.name,
		 atomic_read(&d->d_count));

	mutex_unlock(&parent->d_inode->i_mutex);

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

void sysfs_remove_subdir(struct dentry * d)
{
	remove_dir(d);
}


static void __sysfs_remove_dir(struct dentry *dentry)
{
	LIST_HEAD(removed);
	struct sysfs_dirent * parent_sd;
	struct sysfs_dirent * sd, * tmp;

	if (!dentry)
		return;

	pr_debug("sysfs %s: removing dir\n",dentry->d_name.name);
	mutex_lock(&dentry->d_inode->i_mutex);
	parent_sd = dentry->d_fsdata;
	list_for_each_entry_safe(sd, tmp, &parent_sd->s_children, s_sibling) {
		if (!sd->s_type || !(sd->s_type & SYSFS_NOT_PINNED))
			continue;
		list_move(&sd->s_sibling, &removed);
	}
	mutex_unlock(&dentry->d_inode->i_mutex);

	list_for_each_entry_safe(sd, tmp, &removed, s_sibling) {
		list_del_init(&sd->s_sibling);
		sysfs_drop_dentry(sd);
		sysfs_deactivate(sd);
		sysfs_put(sd);
	}

	remove_dir(dentry);
}

/**
 *	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 dentry *d = kobj->dentry;

	spin_lock(&kobj_sysfs_assoc_lock);
	kobj->dentry = NULL;
	spin_unlock(&kobj_sysfs_assoc_lock);

	__sysfs_remove_dir(d);
}

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

	if (!new_parent)
		return -EFAULT;

	down_write(&sysfs_rename_sem);
	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 (kobj->dentry->d_parent->d_inode != new_parent->d_inode ||
	    new_dentry->d_parent->d_inode != new_parent->d_inode ||
	    new_dentry == kobj->dentry)
		goto out_dput;

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

	/* 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_free;

	kfree(sd->s_name);
	sd->s_name = new_name;

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

	list_del_init(&sd->s_sibling);
	sysfs_get(parent_sd);
	sysfs_put(sd->s_parent);
	sd->s_parent = parent_sd;
	list_add(&sd->s_sibling, &parent_sd->s_children);

	error = 0;
	goto out_unlock;

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

int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent)
{
	struct dentry *old_parent_dentry, *new_parent_dentry, *new_dentry;
	struct sysfs_dirent *new_parent_sd, *sd;
	int error;

	old_parent_dentry = kobj->parent ?
		kobj->parent->dentry : sysfs_mount->mnt_sb->s_root;
	new_parent_dentry = new_parent ?
		new_parent->dentry : sysfs_mount->mnt_sb->s_root;

	if (old_parent_dentry->d_inode == new_parent_dentry->d_inode)
		return 0;	/* nothing to move */
again:
	mutex_lock(&old_parent_dentry->d_inode->i_mutex);
	if (!mutex_trylock(&new_parent_dentry->d_inode->i_mutex)) {
		mutex_unlock(&old_parent_dentry->d_inode->i_mutex);
		goto again;
	}

	new_parent_sd = new_parent_dentry->d_fsdata;
	sd = kobj->dentry->d_fsdata;

	new_dentry = lookup_one_len(kobj->name, new_parent_dentry,
				    strlen(kobj->name));
	if (IS_ERR(new_dentry)) {
		error = PTR_ERR(new_dentry);
		goto out;
	} else
		error = 0;
	d_add(new_dentry, NULL);
	d_move(kobj->dentry, new_dentry);
	dput(new_dentry);

	/* Remove from old parent's list and insert into new parent's list. */
	list_del_init(&sd->s_sibling);
	sysfs_get(new_parent_sd);
	sysfs_put(sd->s_parent);
	sd->s_parent = new_parent_sd;
	list_add(&sd->s_sibling, &new_parent_sd->s_children);

out:
	mutex_unlock(&new_parent_dentry->d_inode->i_mutex);
	mutex_unlock(&old_parent_dentry->d_inode->i_mutex);

	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;

	mutex_lock(&dentry->d_inode->i_mutex);
	sd = sysfs_new_dirent("_DIR_", 0, 0);
	if (sd)
		sysfs_attach_dirent(sd, parent_sd, NULL);
	mutex_unlock(&dentry->d_inode->i_mutex);

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

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

	mutex_lock(&dentry->d_inode->i_mutex);
	list_del_init(&cursor->s_sibling);
	mutex_unlock(&dentry->d_inode->i_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 list_head *p, *q = &cursor->s_sibling;
	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:
			if (filp->f_pos == 2)
				list_move(q, &parent_sd->s_children);

			for (p=q->next; p!= &parent_sd->s_children; p=p->next) {
				struct sysfs_dirent *next;
				const char * name;
				int len;

				next = list_entry(p, struct sysfs_dirent,
						   s_sibling);
				if (!next->s_type)
					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)
					return 0;

				list_move(q, p);
				p = q;
				filp->f_pos++;
			}
	}
	return 0;
}

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

	mutex_lock(&dentry->d_inode->i_mutex);
	switch (origin) {
		case 1:
			offset += file->f_pos;
		case 0:
			if (offset >= 0)
				break;
		default:
			mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
			return -EINVAL;
	}
	if (offset != file->f_pos) {
		file->f_pos = offset;
		if (file->f_pos >= 2) {
			struct sysfs_dirent *sd = dentry->d_fsdata;
			struct sysfs_dirent *cursor = file->private_data;
			struct list_head *p;
			loff_t n = file->f_pos - 2;

			list_del(&cursor->s_sibling);
			p = sd->s_children.next;
			while (n && p != &sd->s_children) {
				struct sysfs_dirent *next;
				next = list_entry(p, struct sysfs_dirent,
						   s_sibling);
				if (next->s_type)
					n--;
				p = p->next;
			}
			list_add_tail(&cursor->s_sibling, p);
		}
	}
	mutex_unlock(&dentry->d_inode->i_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 inode *inode;
	struct inode_operations *i_op;

	inode = kobj->dentry->d_inode;
	if (inode->i_op != &sysfs_dir_inode_operations)
		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 dentry *sysfs_create_shadow_dir(struct kobject *kobj)
{
	struct dentry *dir = kobj->dentry;
	struct inode *inode = dir->d_inode;
	struct dentry *parent = dir->d_parent;
	struct sysfs_dirent *parent_sd = parent->d_fsdata;
	struct dentry *shadow;
	struct sysfs_dirent *sd;

	shadow = ERR_PTR(-EINVAL);
	if (!sysfs_is_shadowed_inode(inode))
		goto out;

	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;
	/* point to parent_sd but don't attach to it */
	sd->s_parent = sysfs_get(parent_sd);
	sysfs_attach_dirent(sd, NULL, shadow);

	d_instantiate(shadow, igrab(inode));
	inc_nlink(inode);
	inc_nlink(parent->d_inode);

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

out:
	return shadow;
nomem:
	dput(shadow);
	shadow = ERR_PTR(-ENOMEM);
	goto out;
}

/**
 *	sysfs_remove_shadow_dir - remove an object's directory.
 *	@shadow: dentry 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 dentry *shadow)
{
	__sysfs_remove_dir(shadow);
}

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,
};