aboutsummaryrefslogtreecommitdiff
path: root/fs/notify/inotify/inotify.c
blob: 27b75ebc7460947806315124517519119ac4c53b (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
/*
 * fs/inotify.c - inode-based file event notifications
 *
 * Authors:
 *	John McCutchan	<ttb@tentacle.dhs.org>
 *	Robert Love	<rml@novell.com>
 *
 * Kernel API added by: Amy Griffis <amy.griffis@hp.com>
 *
 * Copyright (C) 2005 John McCutchan
 * Copyright 2006 Hewlett-Packard Development Company, L.P.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the
 * Free Software Foundation; either version 2, or (at your option) any
 * later version.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/spinlock.h>
#include <linux/idr.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/writeback.h>
#include <linux/inotify.h>
#include <linux/fsnotify_backend.h>

static atomic_t inotify_cookie;

/*
 * Lock ordering:
 *
 * dentry->d_lock (used to keep d_move() away from dentry->d_parent)
 * iprune_mutex (synchronize shrink_icache_memory())
 * 	inode_lock (protects the super_block->s_inodes list)
 * 	inode->inotify_mutex (protects inode->inotify_watches and watches->i_list)
 * 		inotify_handle->mutex (protects inotify_handle and watches->h_list)
 *
 * The inode->inotify_mutex and inotify_handle->mutex and held during execution
 * of a caller's event handler.  Thus, the caller must not hold any locks
 * taken in their event handler while calling any of the published inotify
 * interfaces.
 */

/*
 * Lifetimes of the three main data structures--inotify_handle, inode, and
 * inotify_watch--are managed by reference count.
 *
 * inotify_handle: Lifetime is from inotify_init() to inotify_destroy().
 * Additional references can bump the count via get_inotify_handle() and drop
 * the count via put_inotify_handle().
 *
 * inotify_watch: for inotify's purposes, lifetime is from inotify_add_watch()
 * to remove_watch_no_event().  Additional references can bump the count via
 * get_inotify_watch() and drop the count via put_inotify_watch().  The caller
 * is reponsible for the final put after receiving IN_IGNORED, or when using
 * IN_ONESHOT after receiving the first event.  Inotify does the final put if
 * inotify_destroy() is called.
 *
 * inode: Pinned so long as the inode is associated with a watch, from
 * inotify_add_watch() to the final put_inotify_watch().
 */

/*
 * struct inotify_handle - represents an inotify instance
 *
 * This structure is protected by the mutex 'mutex'.
 */
struct inotify_handle {
	struct idr		idr;		/* idr mapping wd -> watch */
	struct mutex		mutex;		/* protects this bad boy */
	struct list_head	watches;	/* list of watches */
	atomic_t		count;		/* reference count */
	u32			last_wd;	/* the last wd allocated */
	const struct inotify_operations *in_ops; /* inotify caller operations */
};

static inline void get_inotify_handle(struct inotify_handle *ih)
{
	atomic_inc(&ih->count);
}

static inline void put_inotify_handle(struct inotify_handle *ih)
{
	if (atomic_dec_and_test(&ih->count)) {
		idr_destroy(&ih->idr);
		kfree(ih);
	}
}

/**
 * get_inotify_watch - grab a reference to an inotify_watch
 * @watch: watch to grab
 */
void get_inotify_watch(struct inotify_watch *watch)
{
	atomic_inc(&watch->count);
}
EXPORT_SYMBOL_GPL(get_inotify_watch);

int pin_inotify_watch(struct inotify_watch *watch)
{
	struct super_block *sb = watch->inode->i_sb;
	if (atomic_inc_not_zero(&sb->s_active)) {
		atomic_inc(&watch->count);
		return 1;
	}
	return 0;
}

/**
 * put_inotify_watch - decrements the ref count on a given watch.  cleans up
 * watch references if the count reaches zero.  inotify_watch is freed by
 * inotify callers via the destroy_watch() op.
 * @watch: watch to release
 */
void put_inotify_watch(struct inotify_watch *watch)
{
	if (atomic_dec_and_test(&watch->count)) {
		struct inotify_handle *ih = watch->ih;

		iput(watch->inode);
		ih->in_ops->destroy_watch(watch);
		put_inotify_handle(ih);
	}
}
EXPORT_SYMBOL_GPL(put_inotify_watch);

void unpin_inotify_watch(struct inotify_watch *watch)
{
	struct super_block *sb = watch->inode->i_sb;
	put_inotify_watch(watch);
	deactivate_super(sb);
}

/*
 * inotify_handle_get_wd - returns the next WD for use by the given handle
 *
 * Callers must hold ih->mutex.  This function can sleep.
 */
static int inotify_handle_get_wd(struct inotify_handle *ih,
				 struct inotify_watch *watch)
{
	int ret;

	do {
		if (unlikely(!idr_pre_get(&ih->idr, GFP_NOFS)))
			return -ENOSPC;
		ret = idr_get_new_above(&ih->idr, watch, ih->last_wd+1, &watch->wd);
	} while (ret == -EAGAIN);

	if (likely(!ret))
		ih->last_wd = watch->wd;

	return ret;
}

/*
 * inotify_inode_watched - returns nonzero if there are watches on this inode
 * and zero otherwise.  We call this lockless, we do not care if we race.
 */
static inline int inotify_inode_watched(struct inode *inode)
{
	return !list_empty(&inode->inotify_watches);
}

/*
 * Get child dentry flag into synch with parent inode.
 * Flag should always be clear for negative dentrys.
 */
static void set_dentry_child_flags(struct inode *inode, int watched)
{
	struct dentry *alias;

	spin_lock(&dcache_lock);
	list_for_each_entry(alias, &inode->i_dentry, d_alias) {
		struct dentry *child;

		list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) {
			if (!child->d_inode)
				continue;

			spin_lock(&child->d_lock);
			if (watched)
				child->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED;
			else
				child->d_flags &=~DCACHE_INOTIFY_PARENT_WATCHED;
			spin_unlock(&child->d_lock);
		}
	}
	spin_unlock(&dcache_lock);
}

/*
 * inotify_find_handle - find the watch associated with the given inode and
 * handle
 *
 * Callers must hold inode->inotify_mutex.
 */
static struct inotify_watch *inode_find_handle(struct inode *inode,
					       struct inotify_handle *ih)
{
	struct inotify_watch *watch;

	list_for_each_entry(watch, &inode->inotify_watches, i_list) {
		if (watch->ih == ih)
			return watch;
	}

	return NULL;
}

/*
 * remove_watch_no_event - remove watch without the IN_IGNORED event.
 *
 * Callers must hold both inode->inotify_mutex and ih->mutex.
 */
static void remove_watch_no_event(struct inotify_watch *watch,
				  struct inotify_handle *ih)
{
	list_del(&watch->i_list);
	list_del(&watch->h_list);

	if (!inotify_inode_watched(watch->inode))
		set_dentry_child_flags(watch->inode, 0);

	idr_remove(&ih->idr, watch->wd);
}

/**
 * inotify_remove_watch_locked - Remove a watch from both the handle and the
 * inode.  Sends the IN_IGNORED event signifying that the inode is no longer
 * watched.  May be invoked from a caller's event handler.
 * @ih: inotify handle associated with watch
 * @watch: watch to remove
 *
 * Callers must hold both inode->inotify_mutex and ih->mutex.
 */
void inotify_remove_watch_locked(struct inotify_handle *ih,
				 struct inotify_watch *watch)
{
	remove_watch_no_event(watch, ih);
	ih->in_ops->handle_event(watch, watch->wd, IN_IGNORED, 0, NULL, NULL);
}
EXPORT_SYMBOL_GPL(inotify_remove_watch_locked);

/* Kernel API for producing events */

/*
 * inotify_d_instantiate - instantiate dcache entry for inode
 */
void inotify_d_instantiate(struct dentry *entry, struct inode *inode)
{
	struct dentry *parent;

	if (!inode)
		return;

	spin_lock(&entry->d_lock);
	parent = entry->d_parent;
	if (parent->d_inode && inotify_inode_watched(parent->d_inode))
		entry->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED;
	spin_unlock(&entry->d_lock);
}

/*
 * inotify_d_move - dcache entry has been moved
 */
void inotify_d_move(struct dentry *entry)
{
	struct dentry *parent;

	parent = entry->d_parent;
	if (inotify_inode_watched(parent->d_inode))
		entry->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED;
	else
		entry->d_flags &= ~DCACHE_INOTIFY_PARENT_WATCHED;
}

/**
 * inotify_inode_queue_event - queue an event to all watches on this inode
 * @inode: inode event is originating from
 * @mask: event mask describing this event
 * @cookie: cookie for synchronization, or zero
 * @name: filename, if any
 * @n_inode: inode associated with name
 */
void inotify_inode_queue_event(struct inode *inode, u32 mask, u32 cookie,
			       const char *name, struct inode *n_inode)
{
	struct inotify_watch *watch, *next;

	if (!inotify_inode_watched(inode))
		return;

	mutex_lock(&inode->inotify_mutex);
	list_for_each_entry_safe(watch, next, &inode->inotify_watches, i_list) {
		u32 watch_mask = watch->mask;
		if (watch_mask & mask) {
			struct inotify_handle *ih= watch->ih;
			mutex_lock(&ih->mutex);
			if (watch_mask & IN_ONESHOT)
				remove_watch_no_event(watch, ih);
			ih->in_ops->handle_event(watch, watch->wd, mask, cookie,
						 name, n_inode);
			mutex_unlock(&ih->mutex);
		}
	}
	mutex_unlock(&inode->inotify_mutex);
}
EXPORT_SYMBOL_GPL(inotify_inode_queue_event);

/**
 * inotify_dentry_parent_queue_event - queue an event to a dentry's parent
 * @dentry: the dentry in question, we queue against this dentry's parent
 * @mask: event mask describing this event
 * @cookie: cookie for synchronization, or zero
 * @name: filename, if any
 */
void inotify_dentry_parent_queue_event(struct dentry *dentry, u32 mask,
				       u32 cookie, const char *name)
{
	struct dentry *parent;
	struct inode *inode;

	if (!(dentry->d_flags & DCACHE_INOTIFY_PARENT_WATCHED))
		return;

	spin_lock(&dentry->d_lock);
	parent = dentry->d_parent;
	inode = parent->d_inode;

	if (inotify_inode_watched(inode)) {
		dget(parent);
		spin_unlock(&dentry->d_lock);
		inotify_inode_queue_event(inode, mask, cookie, name,
					  dentry->d_inode);
		dput(parent);
	} else
		spin_unlock(&dentry->d_lock);
}
EXPORT_SYMBOL_GPL(inotify_dentry_parent_queue_event);

/**
 * inotify_get_cookie - return a unique cookie for use in synchronizing events.
 */
u32 inotify_get_cookie(void)
{
	return atomic_inc_return(&inotify_cookie);
}
EXPORT_SYMBOL_GPL(inotify_get_cookie);

/**
 * inotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
 * @list: list of inodes being unmounted (sb->s_inodes)
 *
 * Called with inode_lock held, protecting the unmounting super block's list
 * of inodes, and with iprune_mutex held, keeping shrink_icache_memory() at bay.
 * We temporarily drop inode_lock, however, and CAN block.
 */
void inotify_unmount_inodes(struct list_head *list)
{
	struct inode *inode, *next_i, *need_iput = NULL;

	list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
		struct inotify_watch *watch, *next_w;
		struct inode *need_iput_tmp;
		struct list_head *watches;

		/*
		 * We cannot __iget() an inode in state I_CLEAR, I_FREEING,
		 * I_WILL_FREE, or I_NEW which is fine because by that point
		 * the inode cannot have any associated watches.
		 */
		if (inode->i_state & (I_CLEAR|I_FREEING|I_WILL_FREE|I_NEW))
			continue;

		/*
		 * If i_count is zero, the inode cannot have any watches and
		 * doing an __iget/iput with MS_ACTIVE clear would actually
		 * evict all inodes with zero i_count from icache which is
		 * unnecessarily violent and may in fact be illegal to do.
		 */
		if (!atomic_read(&inode->i_count))
			continue;

		need_iput_tmp = need_iput;
		need_iput = NULL;
		/* In case inotify_remove_watch_locked() drops a reference. */
		if (inode != need_iput_tmp)
			__iget(inode);
		else
			need_iput_tmp = NULL;
		/* In case the dropping of a reference would nuke next_i. */
		if ((&next_i->i_sb_list != list) &&
				atomic_read(&next_i->i_count) &&
				!(next_i->i_state & (I_CLEAR | I_FREEING |
					I_WILL_FREE))) {
			__iget(next_i);
			need_iput = next_i;
		}

		/*
		 * We can safely drop inode_lock here because we hold
		 * references on both inode and next_i.  Also no new inodes
		 * will be added since the umount has begun.  Finally,
		 * iprune_mutex keeps shrink_icache_memory() away.
		 */
		spin_unlock(&inode_lock);

		if (need_iput_tmp)
			iput(need_iput_tmp);

		/* for each watch, send IN_UNMOUNT and then remove it */
		mutex_lock(&inode->inotify_mutex);
		watches = &inode->inotify_watches;
		list_for_each_entry_safe(watch, next_w, watches, i_list) {
			struct inotify_handle *ih= watch->ih;
			get_inotify_watch(watch);
			mutex_lock(&ih->mutex);
			ih->in_ops->handle_event(watch, watch->wd, IN_UNMOUNT, 0,
						 NULL, NULL);
			inotify_remove_watch_locked(ih, watch);
			mutex_unlock(&ih->mutex);
			put_inotify_watch(watch);
		}
		mutex_unlock(&inode->inotify_mutex);
		iput(inode);		

		spin_lock(&inode_lock);
	}
}
EXPORT_SYMBOL_GPL(inotify_unmount_inodes);

/**
 * inotify_inode_is_dead - an inode has been deleted, cleanup any watches
 * @inode: inode that is about to be removed
 */
void inotify_inode_is_dead(struct inode *inode)
{
	struct inotify_watch *watch, *next;

	mutex_lock(&inode->inotify_mutex);
	list_for_each_entry_safe(watch, next, &inode->inotify_watches, i_list) {
		struct inotify_handle *ih = watch->ih;
		mutex_lock(&ih->mutex);
		inotify_remove_watch_locked(ih, watch);
		mutex_unlock(&ih->mutex);
	}
	mutex_unlock(&inode->inotify_mutex);
}
EXPORT_SYMBOL_GPL(inotify_inode_is_dead);

/* Kernel Consumer API */

/**
 * inotify_init - allocate and initialize an inotify instance
 * @ops: caller's inotify operations
 */
struct inotify_handle *inotify_init(const struct inotify_operations *ops)
{
	struct inotify_handle *ih;

	ih = kmalloc(sizeof(struct inotify_handle), GFP_KERNEL);
	if (unlikely(!ih))
		return ERR_PTR(-ENOMEM);

	idr_init(&ih->idr);
	INIT_LIST_HEAD(&ih->watches);
	mutex_init(&ih->mutex);
	ih->last_wd = 0;
	ih->in_ops = ops;
	atomic_set(&ih->count, 0);
	get_inotify_handle(ih);

	return ih;
}
EXPORT_SYMBOL_GPL(inotify_init);

/**
 * inotify_init_watch - initialize an inotify watch
 * @watch: watch to initialize
 */
void inotify_init_watch(struct inotify_watch *watch)
{
	INIT_LIST_HEAD(&watch->h_list);
	INIT_LIST_HEAD(&watch->i_list);
	atomic_set(&watch->count, 0);
	get_inotify_watch(watch); /* initial get */
}
EXPORT_SYMBOL_GPL(inotify_init_watch);

/*
 * Watch removals suck violently.  To kick the watch out we need (in this
 * order) inode->inotify_mutex and ih->mutex.  That's fine if we have
 * a hold on inode; however, for all other cases we need to make damn sure
 * we don't race with umount.  We can *NOT* just grab a reference to a
 * watch - inotify_unmount_inodes() will happily sail past it and we'll end
 * with reference to inode potentially outliving its superblock.  Ideally
 * we just want to grab an active reference to superblock if we can; that
 * will make sure we won't go into inotify_umount_inodes() until we are
 * done.  Cleanup is just deactivate_super().  However, that leaves a messy
 * case - what if we *are* racing with umount() and active references to
 * superblock can't be acquired anymore?  We can bump ->s_count, grab
 * ->s_umount, which will wait until the superblock is shut down and the
 * watch in question is pining for fjords.
 *
 * And yes, this is far beyond mere "not very pretty"; so's the entire
 * concept of inotify to start with.
 */

/**
 * pin_to_kill - pin the watch down for removal
 * @ih: inotify handle
 * @watch: watch to kill
 *
 * Called with ih->mutex held, drops it.  Possible return values:
 * 0 - nothing to do, it has died
 * 1 - remove it, drop the reference and deactivate_super()
 */
static int pin_to_kill(struct inotify_handle *ih, struct inotify_watch *watch)
{
	struct super_block *sb = watch->inode->i_sb;

	if (atomic_inc_not_zero(&sb->s_active)) {
		get_inotify_watch(watch);
		mutex_unlock(&ih->mutex);
		return 1;	/* the best outcome */
	}
	spin_lock(&sb_lock);
	sb->s_count++;
	spin_unlock(&sb_lock);
	mutex_unlock(&ih->mutex); /* can't grab ->s_umount under it */
	down_read(&sb->s_umount);
	/* fs is already shut down; the watch is dead */
	drop_super(sb);
	return 0;
}

static void unpin_and_kill(struct inotify_watch *watch)
{
	struct super_block *sb = watch->inode->i_sb;
	put_inotify_watch(watch);
	deactivate_super(sb);
}

/**
 * inotify_destroy - clean up and destroy an inotify instance
 * @ih: inotify handle
 */
void inotify_destroy(struct inotify_handle *ih)
{
	/*
	 * Destroy all of the watches for this handle. Unfortunately, not very
	 * pretty.  We cannot do a simple iteration over the list, because we
	 * do not know the inode until we iterate to the watch.  But we need to
	 * hold inode->inotify_mutex before ih->mutex.  The following works.
	 *
	 * AV: it had to become even uglier to start working ;-/
	 */
	while (1) {
		struct inotify_watch *watch;
		struct list_head *watches;
		struct super_block *sb;
		struct inode *inode;

		mutex_lock(&ih->mutex);
		watches = &ih->watches;
		if (list_empty(watches)) {
			mutex_unlock(&ih->mutex);
			break;
		}
		watch = list_first_entry(watches, struct inotify_watch, h_list);
		sb = watch->inode->i_sb;
		if (!pin_to_kill(ih, watch))
			continue;

		inode = watch->inode;
		mutex_lock(&inode->inotify_mutex);
		mutex_lock(&ih->mutex);

		/* make sure we didn't race with another list removal */
		if (likely(idr_find(&ih->idr, watch->wd))) {
			remove_watch_no_event(watch, ih);
			put_inotify_watch(watch);
		}

		mutex_unlock(&ih->mutex);
		mutex_unlock(&inode->inotify_mutex);
		unpin_and_kill(watch);
	}

	/* free this handle: the put matching the get in inotify_init() */
	put_inotify_handle(ih);
}
EXPORT_SYMBOL_GPL(inotify_destroy);

/**
 * inotify_find_watch - find an existing watch for an (ih,inode) pair
 * @ih: inotify handle
 * @inode: inode to watch
 * @watchp: pointer to existing inotify_watch
 *
 * Caller must pin given inode (via nameidata).
 */
s32 inotify_find_watch(struct inotify_handle *ih, struct inode *inode,
		       struct inotify_watch **watchp)
{
	struct inotify_watch *old;
	int ret = -ENOENT;

	mutex_lock(&inode->inotify_mutex);
	mutex_lock(&ih->mutex);

	old = inode_find_handle(inode, ih);
	if (unlikely(old)) {
		get_inotify_watch(old); /* caller must put watch */
		*watchp = old;
		ret = old->wd;
	}

	mutex_unlock(&ih->mutex);
	mutex_unlock(&inode->inotify_mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(inotify_find_watch);

/**
 * inotify_find_update_watch - find and update the mask of an existing watch
 * @ih: inotify handle
 * @inode: inode's watch to update
 * @mask: mask of events to watch
 *
 * Caller must pin given inode (via nameidata).
 */
s32 inotify_find_update_watch(struct inotify_handle *ih, struct inode *inode,
			      u32 mask)
{
	struct inotify_watch *old;
	int mask_add = 0;
	int ret;

	if (mask & IN_MASK_ADD)
		mask_add = 1;

	/* don't allow invalid bits: we don't want flags set */
	mask &= IN_ALL_EVENTS | IN_ONESHOT;
	if (unlikely(!mask))
		return -EINVAL;

	mutex_lock(&inode->inotify_mutex);
	mutex_lock(&ih->mutex);

	/*
	 * Handle the case of re-adding a watch on an (inode,ih) pair that we
	 * are already watching.  We just update the mask and return its wd.
	 */
	old = inode_find_handle(inode, ih);
	if (unlikely(!old)) {
		ret = -ENOENT;
		goto out;
	}

	if (mask_add)
		old->mask |= mask;
	else
		old->mask = mask;
	ret = old->wd;
out:
	mutex_unlock(&ih->mutex);
	mutex_unlock(&inode->inotify_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(inotify_find_update_watch);

/**
 * inotify_add_watch - add a watch to an inotify instance
 * @ih: inotify handle
 * @watch: caller allocated watch structure
 * @inode: inode to watch
 * @mask: mask of events to watch
 *
 * Caller must pin given inode (via nameidata).
 * Caller must ensure it only calls inotify_add_watch() once per watch.
 * Calls inotify_handle_get_wd() so may sleep.
 */
s32 inotify_add_watch(struct inotify_handle *ih, struct inotify_watch *watch,
		      struct inode *inode, u32 mask)
{
	int ret = 0;
	int newly_watched;

	/* don't allow invalid bits: we don't want flags set */
	mask &= IN_ALL_EVENTS | IN_ONESHOT;
	if (unlikely(!mask))
		return -EINVAL;
	watch->mask = mask;

	mutex_lock(&inode->inotify_mutex);
	mutex_lock(&ih->mutex);

	/* Initialize a new watch */
	ret = inotify_handle_get_wd(ih, watch);
	if (unlikely(ret))
		goto out;
	ret = watch->wd;

	/* save a reference to handle and bump the count to make it official */
	get_inotify_handle(ih);
	watch->ih = ih;

	/*
	 * Save a reference to the inode and bump the ref count to make it
	 * official.  We hold a reference to nameidata, which makes this safe.
	 */
	watch->inode = igrab(inode);

	/* Add the watch to the handle's and the inode's list */
	newly_watched = !inotify_inode_watched(inode);
	list_add(&watch->h_list, &ih->watches);
	list_add(&watch->i_list, &inode->inotify_watches);
	/*
	 * Set child flags _after_ adding the watch, so there is no race
	 * windows where newly instantiated children could miss their parent's
	 * watched flag.
	 */
	if (newly_watched)
		set_dentry_child_flags(inode, 1);

out:
	mutex_unlock(&ih->mutex);
	mutex_unlock(&inode->inotify_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(inotify_add_watch);

/**
 * inotify_clone_watch - put the watch next to existing one
 * @old: already installed watch
 * @new: new watch
 *
 * Caller must hold the inotify_mutex of inode we are dealing with;
 * it is expected to remove the old watch before unlocking the inode.
 */
s32 inotify_clone_watch(struct inotify_watch *old, struct inotify_watch *new)
{
	struct inotify_handle *ih = old->ih;
	int ret = 0;

	new->mask = old->mask;
	new->ih = ih;

	mutex_lock(&ih->mutex);

	/* Initialize a new watch */
	ret = inotify_handle_get_wd(ih, new);
	if (unlikely(ret))
		goto out;
	ret = new->wd;

	get_inotify_handle(ih);

	new->inode = igrab(old->inode);

	list_add(&new->h_list, &ih->watches);
	list_add(&new->i_list, &old->inode->inotify_watches);
out:
	mutex_unlock(&ih->mutex);
	return ret;
}

void inotify_evict_watch(struct inotify_watch *watch)
{
	get_inotify_watch(watch);
	mutex_lock(&watch->ih->mutex);
	inotify_remove_watch_locked(watch->ih, watch);
	mutex_unlock(&watch->ih->mutex);
}

/**
 * inotify_rm_wd - remove a watch from an inotify instance
 * @ih: inotify handle
 * @wd: watch descriptor to remove
 *
 * Can sleep.
 */
int inotify_rm_wd(struct inotify_handle *ih, u32 wd)
{
	struct inotify_watch *watch;
	struct super_block *sb;
	struct inode *inode;

	mutex_lock(&ih->mutex);
	watch = idr_find(&ih->idr, wd);
	if (unlikely(!watch)) {
		mutex_unlock(&ih->mutex);
		return -EINVAL;
	}
	sb = watch->inode->i_sb;
	if (!pin_to_kill(ih, watch))
		return 0;

	inode = watch->inode;

	mutex_lock(&inode->inotify_mutex);
	mutex_lock(&ih->mutex);

	/* make sure that we did not race */
	if (likely(idr_find(&ih->idr, wd) == watch))
		inotify_remove_watch_locked(ih, watch);

	mutex_unlock(&ih->mutex);
	mutex_unlock(&inode->inotify_mutex);
	unpin_and_kill(watch);

	return 0;
}
EXPORT_SYMBOL_GPL(inotify_rm_wd);

/**
 * inotify_rm_watch - remove a watch from an inotify instance
 * @ih: inotify handle
 * @watch: watch to remove
 *
 * Can sleep.
 */
int inotify_rm_watch(struct inotify_handle *ih,
		     struct inotify_watch *watch)
{
	return inotify_rm_wd(ih, watch->wd);
}
EXPORT_SYMBOL_GPL(inotify_rm_watch);

/*
 * inotify_setup - core initialization function
 */
static int __init inotify_setup(void)
{
	BUILD_BUG_ON(IN_ACCESS != FS_ACCESS);
	BUILD_BUG_ON(IN_MODIFY != FS_MODIFY);
	BUILD_BUG_ON(IN_ATTRIB != FS_ATTRIB);
	BUILD_BUG_ON(IN_CLOSE_WRITE != FS_CLOSE_WRITE);
	BUILD_BUG_ON(IN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
	BUILD_BUG_ON(IN_OPEN != FS_OPEN);
	BUILD_BUG_ON(IN_MOVED_FROM != FS_MOVED_FROM);
	BUILD_BUG_ON(IN_MOVED_TO != FS_MOVED_TO);
	BUILD_BUG_ON(IN_CREATE != FS_CREATE);
	BUILD_BUG_ON(IN_DELETE != FS_DELETE);
	BUILD_BUG_ON(IN_DELETE_SELF != FS_DELETE_SELF);
	BUILD_BUG_ON(IN_MOVE_SELF != FS_MOVE_SELF);
	BUILD_BUG_ON(IN_Q_OVERFLOW != FS_Q_OVERFLOW);

	BUILD_BUG_ON(IN_UNMOUNT != FS_UNMOUNT);
	BUILD_BUG_ON(IN_ISDIR != FS_IN_ISDIR);
	BUILD_BUG_ON(IN_IGNORED != FS_IN_IGNORED);
	BUILD_BUG_ON(IN_ONESHOT != FS_IN_ONESHOT);

	atomic_set(&inotify_cookie, 0);

	return 0;
}

module_init(inotify_setup);