summaryrefslogtreecommitdiffstats
path: root/fs/notify/inotify/inotify_user.c
blob: 69739b26c7e49a417dd35b939a8164d52826c124 (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
/*
 * fs/inotify_user.c - inotify support for userspace
 *
 * Authors:
 *	John McCutchan	<ttb@tentacle.dhs.org>
 *	Robert Love	<rml@novell.com>
 *
 * Copyright (C) 2005 John McCutchan
 * Copyright 2006 Hewlett-Packard Development Company, L.P.
 *
 * Copyright (C) 2009 Eric Paris <Red Hat Inc>
 * inotify was largely rewriten to make use of the fsnotify infrastructure
 *
 * 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/file.h>
#include <linux/fs.h> /* struct inode */
#include <linux/fsnotify_backend.h>
#include <linux/idr.h>
#include <linux/init.h> /* fs_initcall */
#include <linux/inotify.h>
#include <linux/kernel.h> /* roundup() */
#include <linux/namei.h> /* LOOKUP_FOLLOW */
#include <linux/sched/signal.h>
#include <linux/slab.h> /* struct kmem_cache */
#include <linux/syscalls.h>
#include <linux/types.h>
#include <linux/anon_inodes.h>
#include <linux/uaccess.h>
#include <linux/poll.h>
#include <linux/wait.h>

#include "inotify.h"
#include "../fdinfo.h"

#include <asm/ioctls.h>

/* configurable via /proc/sys/fs/inotify/ */
static int inotify_max_queued_events __read_mostly;

static struct kmem_cache *inotify_inode_mark_cachep __read_mostly;

#ifdef CONFIG_SYSCTL

#include <linux/sysctl.h>

static int zero;

struct ctl_table inotify_table[] = {
	{
		.procname	= "max_user_instances",
		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
	},
	{
		.procname	= "max_user_watches",
		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
	},
	{
		.procname	= "max_queued_events",
		.data		= &inotify_max_queued_events,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero
	},
	{ }
};
#endif /* CONFIG_SYSCTL */

static inline __u32 inotify_arg_to_mask(u32 arg)
{
	__u32 mask;

	/*
	 * everything should accept their own ignored, cares about children,
	 * and should receive events when the inode is unmounted
	 */
	mask = (FS_IN_IGNORED | FS_EVENT_ON_CHILD | FS_UNMOUNT);

	/* mask off the flags used to open the fd */
	mask |= (arg & (IN_ALL_EVENTS | IN_ONESHOT | IN_EXCL_UNLINK));

	return mask;
}

static inline u32 inotify_mask_to_arg(__u32 mask)
{
	return mask & (IN_ALL_EVENTS | IN_ISDIR | IN_UNMOUNT | IN_IGNORED |
		       IN_Q_OVERFLOW);
}

/* intofiy userspace file descriptor functions */
static unsigned int inotify_poll(struct file *file, poll_table *wait)
{
	struct fsnotify_group *group = file->private_data;
	int ret = 0;

	poll_wait(file, &group->notification_waitq, wait);
	spin_lock(&group->notification_lock);
	if (!fsnotify_notify_queue_is_empty(group))
		ret = POLLIN | POLLRDNORM;
	spin_unlock(&group->notification_lock);

	return ret;
}

static int round_event_name_len(struct fsnotify_event *fsn_event)
{
	struct inotify_event_info *event;

	event = INOTIFY_E(fsn_event);
	if (!event->name_len)
		return 0;
	return roundup(event->name_len + 1, sizeof(struct inotify_event));
}

/*
 * Get an inotify_kernel_event if one exists and is small
 * enough to fit in "count". Return an error pointer if
 * not large enough.
 *
 * Called with the group->notification_lock held.
 */
static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
					    size_t count)
{
	size_t event_size = sizeof(struct inotify_event);
	struct fsnotify_event *event;

	if (fsnotify_notify_queue_is_empty(group))
		return NULL;

	event = fsnotify_peek_first_event(group);

	pr_debug("%s: group=%p event=%p\n", __func__, group, event);

	event_size += round_event_name_len(event);
	if (event_size > count)
		return ERR_PTR(-EINVAL);

	/* held the notification_lock the whole time, so this is the
	 * same event we peeked above */
	fsnotify_remove_first_event(group);

	return event;
}

/*
 * Copy an event to user space, returning how much we copied.
 *
 * We already checked that the event size is smaller than the
 * buffer we had in "get_one_event()" above.
 */
static ssize_t copy_event_to_user(struct fsnotify_group *group,
				  struct fsnotify_event *fsn_event,
				  char __user *buf)
{
	struct inotify_event inotify_event;
	struct inotify_event_info *event;
	size_t event_size = sizeof(struct inotify_event);
	size_t name_len;
	size_t pad_name_len;

	pr_debug("%s: group=%p event=%p\n", __func__, group, fsn_event);

	event = INOTIFY_E(fsn_event);
	name_len = event->name_len;
	/*
	 * round up name length so it is a multiple of event_size
	 * plus an extra byte for the terminating '\0'.
	 */
	pad_name_len = round_event_name_len(fsn_event);
	inotify_event.len = pad_name_len;
	inotify_event.mask = inotify_mask_to_arg(fsn_event->mask);
	inotify_event.wd = event->wd;
	inotify_event.cookie = event->sync_cookie;

	/* send the main event */
	if (copy_to_user(buf, &inotify_event, event_size))
		return -EFAULT;

	buf += event_size;

	/*
	 * fsnotify only stores the pathname, so here we have to send the pathname
	 * and then pad that pathname out to a multiple of sizeof(inotify_event)
	 * with zeros.
	 */
	if (pad_name_len) {
		/* copy the path name */
		if (copy_to_user(buf, event->name, name_len))
			return -EFAULT;
		buf += name_len;

		/* fill userspace with 0's */
		if (clear_user(buf, pad_name_len - name_len))
			return -EFAULT;
		event_size += pad_name_len;
	}

	return event_size;
}

static ssize_t inotify_read(struct file *file, char __user *buf,
			    size_t count, loff_t *pos)
{
	struct fsnotify_group *group;
	struct fsnotify_event *kevent;
	char __user *start;
	int ret;
	DEFINE_WAIT_FUNC(wait, woken_wake_function);

	start = buf;
	group = file->private_data;

	add_wait_queue(&group->notification_waitq, &wait);
	while (1) {
		spin_lock(&group->notification_lock);
		kevent = get_one_event(group, count);
		spin_unlock(&group->notification_lock);

		pr_debug("%s: group=%p kevent=%p\n", __func__, group, kevent);

		if (kevent) {
			ret = PTR_ERR(kevent);
			if (IS_ERR(kevent))
				break;
			ret = copy_event_to_user(group, kevent, buf);
			fsnotify_destroy_event(group, kevent);
			if (ret < 0)
				break;
			buf += ret;
			count -= ret;
			continue;
		}

		ret = -EAGAIN;
		if (file->f_flags & O_NONBLOCK)
			break;
		ret = -ERESTARTSYS;
		if (signal_pending(current))
			break;

		if (start != buf)
			break;

		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
	}
	remove_wait_queue(&group->notification_waitq, &wait);

	if (start != buf && ret != -EFAULT)
		ret = buf - start;
	return ret;
}

static int inotify_release(struct inode *ignored, struct file *file)
{
	struct fsnotify_group *group = file->private_data;

	pr_debug("%s: group=%p\n", __func__, group);

	/* free this group, matching get was inotify_init->fsnotify_obtain_group */
	fsnotify_destroy_group(group);

	return 0;
}

static long inotify_ioctl(struct file *file, unsigned int cmd,
			  unsigned long arg)
{
	struct fsnotify_group *group;
	struct fsnotify_event *fsn_event;
	void __user *p;
	int ret = -ENOTTY;
	size_t send_len = 0;

	group = file->private_data;
	p = (void __user *) arg;

	pr_debug("%s: group=%p cmd=%u\n", __func__, group, cmd);

	switch (cmd) {
	case FIONREAD:
		spin_lock(&group->notification_lock);
		list_for_each_entry(fsn_event, &group->notification_list,
				    list) {
			send_len += sizeof(struct inotify_event);
			send_len += round_event_name_len(fsn_event);
		}
		spin_unlock(&group->notification_lock);
		ret = put_user(send_len, (int __user *) p);
		break;
	}

	return ret;
}

static const struct file_operations inotify_fops = {
	.show_fdinfo	= inotify_show_fdinfo,
	.poll		= inotify_poll,
	.read		= inotify_read,
	.fasync		= fsnotify_fasync,
	.release	= inotify_release,
	.unlocked_ioctl	= inotify_ioctl,
	.compat_ioctl	= inotify_ioctl,
	.llseek		= noop_llseek,
};


/*
 * find_inode - resolve a user-given path to a specific inode
 */
static int inotify_find_inode(const char __user *dirname, struct path *path, unsigned flags)
{
	int error;

	error = user_path_at(AT_FDCWD, dirname, flags, path);
	if (error)
		return error;
	/* you can only watch an inode if you have read permissions on it */
	error = inode_permission(path->dentry->d_inode, MAY_READ);
	if (error)
		path_put(path);
	return error;
}

static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock,
			      struct inotify_inode_mark *i_mark)
{
	int ret;

	idr_preload(GFP_KERNEL);
	spin_lock(idr_lock);

	ret = idr_alloc_cyclic(idr, i_mark, 1, 0, GFP_NOWAIT);
	if (ret >= 0) {
		/* we added the mark to the idr, take a reference */
		i_mark->wd = ret;
		fsnotify_get_mark(&i_mark->fsn_mark);
	}

	spin_unlock(idr_lock);
	idr_preload_end();
	return ret < 0 ? ret : 0;
}

static struct inotify_inode_mark *inotify_idr_find_locked(struct fsnotify_group *group,
								int wd)
{
	struct idr *idr = &group->inotify_data.idr;
	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
	struct inotify_inode_mark *i_mark;

	assert_spin_locked(idr_lock);

	i_mark = idr_find(idr, wd);
	if (i_mark) {
		struct fsnotify_mark *fsn_mark = &i_mark->fsn_mark;

		fsnotify_get_mark(fsn_mark);
		/* One ref for being in the idr, one ref we just took */
		BUG_ON(atomic_read(&fsn_mark->refcnt) < 2);
	}

	return i_mark;
}

static struct inotify_inode_mark *inotify_idr_find(struct fsnotify_group *group,
							 int wd)
{
	struct inotify_inode_mark *i_mark;
	spinlock_t *idr_lock = &group->inotify_data.idr_lock;

	spin_lock(idr_lock);
	i_mark = inotify_idr_find_locked(group, wd);
	spin_unlock(idr_lock);

	return i_mark;
}

/*
 * Remove the mark from the idr (if present) and drop the reference
 * on the mark because it was in the idr.
 */
static void inotify_remove_from_idr(struct fsnotify_group *group,
				    struct inotify_inode_mark *i_mark)
{
	struct idr *idr = &group->inotify_data.idr;
	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
	struct inotify_inode_mark *found_i_mark = NULL;
	int wd;

	spin_lock(idr_lock);
	wd = i_mark->wd;

	/*
	 * does this i_mark think it is in the idr?  we shouldn't get called
	 * if it wasn't....
	 */
	if (wd == -1) {
		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
			__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
		goto out;
	}

	/* Lets look in the idr to see if we find it */
	found_i_mark = inotify_idr_find_locked(group, wd);
	if (unlikely(!found_i_mark)) {
		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
			__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
		goto out;
	}

	/*
	 * We found an mark in the idr at the right wd, but it's
	 * not the mark we were told to remove.  eparis seriously
	 * fucked up somewhere.
	 */
	if (unlikely(found_i_mark != i_mark)) {
		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p "
			"found_i_mark=%p found_i_mark->wd=%d "
			"found_i_mark->group=%p\n", __func__, i_mark,
			i_mark->wd, i_mark->fsn_mark.group, found_i_mark,
			found_i_mark->wd, found_i_mark->fsn_mark.group);
		goto out;
	}

	/*
	 * One ref for being in the idr
	 * one ref grabbed by inotify_idr_find
	 */
	if (unlikely(atomic_read(&i_mark->fsn_mark.refcnt) < 2)) {
		printk(KERN_ERR "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
			 __func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
		/* we can't really recover with bad ref cnting.. */
		BUG();
	}

	idr_remove(idr, wd);
	/* Removed from the idr, drop that ref. */
	fsnotify_put_mark(&i_mark->fsn_mark);
out:
	i_mark->wd = -1;
	spin_unlock(idr_lock);
	/* match the ref taken by inotify_idr_find_locked() */
	if (found_i_mark)
		fsnotify_put_mark(&found_i_mark->fsn_mark);
}

/*
 * Send IN_IGNORED for this wd, remove this wd from the idr.
 */
void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
				    struct fsnotify_group *group)
{
	struct inotify_inode_mark *i_mark;

	/* Queue ignore event for the watch */
	inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
			     NULL, FSNOTIFY_EVENT_NONE, NULL, 0, NULL);

	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
	/* remove this mark from the idr */
	inotify_remove_from_idr(group, i_mark);

	dec_inotify_watches(group->inotify_data.ucounts);
}

/* ding dong the mark is dead */
static void inotify_free_mark(struct fsnotify_mark *fsn_mark)
{
	struct inotify_inode_mark *i_mark;

	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);

	kmem_cache_free(inotify_inode_mark_cachep, i_mark);
}

static int inotify_update_existing_watch(struct fsnotify_group *group,
					 struct inode *inode,
					 u32 arg)
{
	struct fsnotify_mark *fsn_mark;
	struct inotify_inode_mark *i_mark;
	__u32 old_mask, new_mask;
	__u32 mask;
	int add = (arg & IN_MASK_ADD);
	int ret;

	mask = inotify_arg_to_mask(arg);

	fsn_mark = fsnotify_find_inode_mark(group, inode);
	if (!fsn_mark)
		return -ENOENT;

	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);

	spin_lock(&fsn_mark->lock);
	old_mask = fsn_mark->mask;
	if (add)
		fsn_mark->mask |= mask;
	else
		fsn_mark->mask = mask;
	new_mask = fsn_mark->mask;
	spin_unlock(&fsn_mark->lock);

	if (old_mask != new_mask) {
		/* more bits in old than in new? */
		int dropped = (old_mask & ~new_mask);
		/* more bits in this fsn_mark than the inode's mask? */
		int do_inode = (new_mask & ~inode->i_fsnotify_mask);

		/* update the inode with this new fsn_mark */
		if (dropped || do_inode)
			fsnotify_recalc_inode_mask(inode);

	}

	/* return the wd */
	ret = i_mark->wd;

	/* match the get from fsnotify_find_mark() */
	fsnotify_put_mark(fsn_mark);

	return ret;
}

static int inotify_new_watch(struct fsnotify_group *group,
			     struct inode *inode,
			     u32 arg)
{
	struct inotify_inode_mark *tmp_i_mark;
	__u32 mask;
	int ret;
	struct idr *idr = &group->inotify_data.idr;
	spinlock_t *idr_lock = &group->inotify_data.idr_lock;

	mask = inotify_arg_to_mask(arg);

	tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
	if (unlikely(!tmp_i_mark))
		return -ENOMEM;

	fsnotify_init_mark(&tmp_i_mark->fsn_mark, inotify_free_mark);
	tmp_i_mark->fsn_mark.mask = mask;
	tmp_i_mark->wd = -1;

	ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
	if (ret)
		goto out_err;

	/* increment the number of watches the user has */
	if (!inc_inotify_watches(group->inotify_data.ucounts)) {
		inotify_remove_from_idr(group, tmp_i_mark);
		ret = -ENOSPC;
		goto out_err;
	}

	/* we are on the idr, now get on the inode */
	ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, group, inode,
				       NULL, 0);
	if (ret) {
		/* we failed to get on the inode, get off the idr */
		inotify_remove_from_idr(group, tmp_i_mark);
		goto out_err;
	}


	/* return the watch descriptor for this new mark */
	ret = tmp_i_mark->wd;

out_err:
	/* match the ref from fsnotify_init_mark() */
	fsnotify_put_mark(&tmp_i_mark->fsn_mark);

	return ret;
}

static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
{
	int ret = 0;

	mutex_lock(&group->mark_mutex);
	/* try to update and existing watch with the new arg */
	ret = inotify_update_existing_watch(group, inode, arg);
	/* no mark present, try to add a new one */
	if (ret == -ENOENT)
		ret = inotify_new_watch(group, inode, arg);
	mutex_unlock(&group->mark_mutex);

	return ret;
}

static struct fsnotify_group *inotify_new_group(unsigned int max_events)
{
	struct fsnotify_group *group;
	struct inotify_event_info *oevent;

	group = fsnotify_alloc_group(&inotify_fsnotify_ops);
	if (IS_ERR(group))
		return group;

	oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL);
	if (unlikely(!oevent)) {
		fsnotify_destroy_group(group);
		return ERR_PTR(-ENOMEM);
	}
	group->overflow_event = &oevent->fse;
	fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
	oevent->wd = -1;
	oevent->sync_cookie = 0;
	oevent->name_len = 0;

	group->max_events = max_events;

	spin_lock_init(&group->inotify_data.idr_lock);
	idr_init(&group->inotify_data.idr);
	group->inotify_data.ucounts = inc_ucount(current_user_ns(),
						 current_euid(),
						 UCOUNT_INOTIFY_INSTANCES);

	if (!group->inotify_data.ucounts) {
		fsnotify_destroy_group(group);
		return ERR_PTR(-EMFILE);
	}

	return group;
}


/* inotify syscalls */
SYSCALL_DEFINE1(inotify_init1, int, flags)
{
	struct fsnotify_group *group;
	int ret;

	/* Check the IN_* constants for consistency.  */
	BUILD_BUG_ON(IN_CLOEXEC != O_CLOEXEC);
	BUILD_BUG_ON(IN_NONBLOCK != O_NONBLOCK);

	if (flags & ~(IN_CLOEXEC | IN_NONBLOCK))
		return -EINVAL;

	/* fsnotify_obtain_group took a reference to group, we put this when we kill the file in the end */
	group = inotify_new_group(inotify_max_queued_events);
	if (IS_ERR(group))
		return PTR_ERR(group);

	ret = anon_inode_getfd("inotify", &inotify_fops, group,
				  O_RDONLY | flags);
	if (ret < 0)
		fsnotify_destroy_group(group);

	return ret;
}

SYSCALL_DEFINE0(inotify_init)
{
	return sys_inotify_init1(0);
}

SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
		u32, mask)
{
	struct fsnotify_group *group;
	struct inode *inode;
	struct path path;
	struct fd f;
	int ret;
	unsigned flags = 0;

	/*
	 * We share a lot of code with fs/dnotify.  We also share
	 * the bit layout between inotify's IN_* and the fsnotify
	 * FS_*.  This check ensures that only the inotify IN_*
	 * bits get passed in and set in watches/events.
	 */
	if (unlikely(mask & ~ALL_INOTIFY_BITS))
		return -EINVAL;
	/*
	 * Require at least one valid bit set in the mask.
	 * Without _something_ set, we would have no events to
	 * watch for.
	 */
	if (unlikely(!(mask & ALL_INOTIFY_BITS)))
		return -EINVAL;

	f = fdget(fd);
	if (unlikely(!f.file))
		return -EBADF;

	/* verify that this is indeed an inotify instance */
	if (unlikely(f.file->f_op != &inotify_fops)) {
		ret = -EINVAL;
		goto fput_and_out;
	}

	if (!(mask & IN_DONT_FOLLOW))
		flags |= LOOKUP_FOLLOW;
	if (mask & IN_ONLYDIR)
		flags |= LOOKUP_DIRECTORY;

	ret = inotify_find_inode(pathname, &path, flags);
	if (ret)
		goto fput_and_out;

	/* inode held in place by reference to path; group by fget on fd */
	inode = path.dentry->d_inode;
	group = f.file->private_data;

	/* create/update an inode mark */
	ret = inotify_update_watch(group, inode, mask);
	path_put(&path);
fput_and_out:
	fdput(f);
	return ret;
}

SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
{
	struct fsnotify_group *group;
	struct inotify_inode_mark *i_mark;
	struct fd f;
	int ret = 0;

	f = fdget(fd);
	if (unlikely(!f.file))
		return -EBADF;

	/* verify that this is indeed an inotify instance */
	ret = -EINVAL;
	if (unlikely(f.file->f_op != &inotify_fops))
		goto out;

	group = f.file->private_data;

	ret = -EINVAL;
	i_mark = inotify_idr_find(group, wd);
	if (unlikely(!i_mark))
		goto out;

	ret = 0;

	fsnotify_destroy_mark(&i_mark->fsn_mark, group);

	/* match ref taken by inotify_idr_find */
	fsnotify_put_mark(&i_mark->fsn_mark);

out:
	fdput(f);
	return ret;
}

/*
 * inotify_user_setup - Our initialization function.  Note that we cannot return
 * error because we have compiled-in VFS hooks.  So an (unlikely) failure here
 * must result in panic().
 */
static int __init inotify_user_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_UNMOUNT != FS_UNMOUNT);
	BUILD_BUG_ON(IN_Q_OVERFLOW != FS_Q_OVERFLOW);
	BUILD_BUG_ON(IN_IGNORED != FS_IN_IGNORED);
	BUILD_BUG_ON(IN_EXCL_UNLINK != FS_EXCL_UNLINK);
	BUILD_BUG_ON(IN_ISDIR != FS_ISDIR);
	BUILD_BUG_ON(IN_ONESHOT != FS_IN_ONESHOT);

	BUG_ON(hweight32(ALL_INOTIFY_BITS) != 21);

	inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC);

	inotify_max_queued_events = 16384;
	init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;
	init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = 8192;

	return 0;
}
fs_initcall(inotify_user_setup);