summaryrefslogtreecommitdiff
path: root/fs/inotify_user.c
blob: 845dc79a4e9c3caa33b7d72aeee5e5bd7ea81a31 (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
/*
 * 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.
 *
 * 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/kernel.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/inotify.h>
#include <linux/syscalls.h>

#include <asm/ioctls.h>

static kmem_cache_t *watch_cachep __read_mostly;
static kmem_cache_t *event_cachep __read_mostly;

static struct vfsmount *inotify_mnt __read_mostly;

/* these are configurable via /proc/sys/fs/inotify/ */
int inotify_max_user_instances __read_mostly;
int inotify_max_user_watches __read_mostly;
int inotify_max_queued_events __read_mostly;

/*
 * Lock ordering:
 *
 * inotify_dev->up_mutex (ensures we don't re-add the same watch)
 * 	inode->inotify_mutex (protects inode's watch list)
 * 		inotify_handle->mutex (protects inotify_handle's watch list)
 * 			inotify_dev->ev_mutex (protects device's event queue)
 */

/*
 * Lifetimes of the main data structures:
 *
 * inotify_device: Lifetime is managed by reference count, from
 * sys_inotify_init() until release.  Additional references can bump the count
 * via get_inotify_dev() and drop the count via put_inotify_dev().
 *
 * inotify_user_watch: Lifetime is from create_watch() to the receipt of an
 * IN_IGNORED event from inotify, or when using IN_ONESHOT, to receipt of the
 * first event, or to inotify_destroy().
 */

/*
 * struct inotify_device - represents an inotify instance
 *
 * This structure is protected by the mutex 'mutex'.
 */
struct inotify_device {
	wait_queue_head_t 	wq;		/* wait queue for i/o */
	struct mutex		ev_mutex;	/* protects event queue */
	struct mutex		up_mutex;	/* synchronizes watch updates */
	struct list_head 	events;		/* list of queued events */
	atomic_t		count;		/* reference count */
	struct user_struct	*user;		/* user who opened this dev */
	struct inotify_handle	*ih;		/* inotify handle */
	unsigned int		queue_size;	/* size of the queue (bytes) */
	unsigned int		event_count;	/* number of pending events */
	unsigned int		max_events;	/* maximum number of events */
};

/*
 * struct inotify_kernel_event - An inotify event, originating from a watch and
 * queued for user-space.  A list of these is attached to each instance of the
 * device.  In read(), this list is walked and all events that can fit in the
 * buffer are returned.
 *
 * Protected by dev->ev_mutex of the device in which we are queued.
 */
struct inotify_kernel_event {
	struct inotify_event	event;	/* the user-space event */
	struct list_head        list;	/* entry in inotify_device's list */
	char			*name;	/* filename, if any */
};

/*
 * struct inotify_user_watch - our version of an inotify_watch, we add
 * a reference to the associated inotify_device.
 */
struct inotify_user_watch {
	struct inotify_device	*dev;	/* associated device */
	struct inotify_watch	wdata;	/* inotify watch data */
};

#ifdef CONFIG_SYSCTL

#include <linux/sysctl.h>

static int zero;

ctl_table inotify_table[] = {
	{
		.ctl_name	= INOTIFY_MAX_USER_INSTANCES,
		.procname	= "max_user_instances",
		.data		= &inotify_max_user_instances,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero,
	},
	{
		.ctl_name	= INOTIFY_MAX_USER_WATCHES,
		.procname	= "max_user_watches",
		.data		= &inotify_max_user_watches,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero,
	},
	{
		.ctl_name	= INOTIFY_MAX_QUEUED_EVENTS,
		.procname	= "max_queued_events",
		.data		= &inotify_max_queued_events,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero
	},
	{ .ctl_name = 0 }
};
#endif /* CONFIG_SYSCTL */

static inline void get_inotify_dev(struct inotify_device *dev)
{
	atomic_inc(&dev->count);
}

static inline void put_inotify_dev(struct inotify_device *dev)
{
	if (atomic_dec_and_test(&dev->count)) {
		atomic_dec(&dev->user->inotify_devs);
		free_uid(dev->user);
		kfree(dev);
	}
}

/*
 * free_inotify_user_watch - cleans up the watch and its references
 */
static void free_inotify_user_watch(struct inotify_watch *w)
{
	struct inotify_user_watch *watch;
	struct inotify_device *dev;

	watch = container_of(w, struct inotify_user_watch, wdata);
	dev = watch->dev;

	atomic_dec(&dev->user->inotify_watches);
	put_inotify_dev(dev);
	kmem_cache_free(watch_cachep, watch);
}

/*
 * kernel_event - create a new kernel event with the given parameters
 *
 * This function can sleep.
 */
static struct inotify_kernel_event * kernel_event(s32 wd, u32 mask, u32 cookie,
						  const char *name)
{
	struct inotify_kernel_event *kevent;

	kevent = kmem_cache_alloc(event_cachep, GFP_KERNEL);
	if (unlikely(!kevent))
		return NULL;

	/* we hand this out to user-space, so zero it just in case */
	memset(&kevent->event, 0, sizeof(struct inotify_event));

	kevent->event.wd = wd;
	kevent->event.mask = mask;
	kevent->event.cookie = cookie;

	INIT_LIST_HEAD(&kevent->list);

	if (name) {
		size_t len, rem, event_size = sizeof(struct inotify_event);

		/*
		 * We need to pad the filename so as to properly align an
		 * array of inotify_event structures.  Because the structure is
		 * small and the common case is a small filename, we just round
		 * up to the next multiple of the structure's sizeof.  This is
		 * simple and safe for all architectures.
		 */
		len = strlen(name) + 1;
		rem = event_size - len;
		if (len > event_size) {
			rem = event_size - (len % event_size);
			if (len % event_size == 0)
				rem = 0;
		}

		kevent->name = kmalloc(len + rem, GFP_KERNEL);
		if (unlikely(!kevent->name)) {
			kmem_cache_free(event_cachep, kevent);
			return NULL;
		}
		memcpy(kevent->name, name, len);
		if (rem)
			memset(kevent->name + len, 0, rem);
		kevent->event.len = len + rem;
	} else {
		kevent->event.len = 0;
		kevent->name = NULL;
	}

	return kevent;
}

/*
 * inotify_dev_get_event - return the next event in the given dev's queue
 *
 * Caller must hold dev->ev_mutex.
 */
static inline struct inotify_kernel_event *
inotify_dev_get_event(struct inotify_device *dev)
{
	return list_entry(dev->events.next, struct inotify_kernel_event, list);
}

/*
 * inotify_dev_queue_event - event handler registered with core inotify, adds
 * a new event to the given device
 *
 * Can sleep (calls kernel_event()).
 */
static void inotify_dev_queue_event(struct inotify_watch *w, u32 wd, u32 mask,
				    u32 cookie, const char *name)
{
	struct inotify_user_watch *watch;
	struct inotify_device *dev;
	struct inotify_kernel_event *kevent, *last;

	watch = container_of(w, struct inotify_user_watch, wdata);
	dev = watch->dev;

	mutex_lock(&dev->ev_mutex);

	/* we can safely put the watch as we don't reference it while
	 * generating the event
	 */
	if (mask & IN_IGNORED || mask & IN_ONESHOT)
		put_inotify_watch(w); /* final put */

	/* coalescing: drop this event if it is a dupe of the previous */
	last = inotify_dev_get_event(dev);
	if (last && last->event.mask == mask && last->event.wd == wd &&
			last->event.cookie == cookie) {
		const char *lastname = last->name;

		if (!name && !lastname)
			goto out;
		if (name && lastname && !strcmp(lastname, name))
			goto out;
	}

	/* the queue overflowed and we already sent the Q_OVERFLOW event */
	if (unlikely(dev->event_count > dev->max_events))
		goto out;

	/* if the queue overflows, we need to notify user space */
	if (unlikely(dev->event_count == dev->max_events))
		kevent = kernel_event(-1, IN_Q_OVERFLOW, cookie, NULL);
	else
		kevent = kernel_event(wd, mask, cookie, name);

	if (unlikely(!kevent))
		goto out;

	/* queue the event and wake up anyone waiting */
	dev->event_count++;
	dev->queue_size += sizeof(struct inotify_event) + kevent->event.len;
	list_add_tail(&kevent->list, &dev->events);
	wake_up_interruptible(&dev->wq);

out:
	mutex_unlock(&dev->ev_mutex);
}

/*
 * remove_kevent - cleans up and ultimately frees the given kevent
 *
 * Caller must hold dev->ev_mutex.
 */
static void remove_kevent(struct inotify_device *dev,
			  struct inotify_kernel_event *kevent)
{
	list_del(&kevent->list);

	dev->event_count--;
	dev->queue_size -= sizeof(struct inotify_event) + kevent->event.len;

	kfree(kevent->name);
	kmem_cache_free(event_cachep, kevent);
}

/*
 * inotify_dev_event_dequeue - destroy an event on the given device
 *
 * Caller must hold dev->ev_mutex.
 */
static void inotify_dev_event_dequeue(struct inotify_device *dev)
{
	if (!list_empty(&dev->events)) {
		struct inotify_kernel_event *kevent;
		kevent = inotify_dev_get_event(dev);
		remove_kevent(dev, kevent);
	}
}

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

	error = __user_walk(dirname, flags, nd);
	if (error)
		return error;
	/* you can only watch an inode if you have read permissions on it */
	error = vfs_permission(nd, MAY_READ);
	if (error)
		path_release(nd);
	return error;
}

/*
 * create_watch - creates a watch on the given device.
 *
 * Callers must hold dev->up_mutex.
 */
static int create_watch(struct inotify_device *dev, struct inode *inode,
			u32 mask)
{
	struct inotify_user_watch *watch;
	int ret;

	if (atomic_read(&dev->user->inotify_watches) >=
			inotify_max_user_watches)
		return -ENOSPC;

	watch = kmem_cache_alloc(watch_cachep, GFP_KERNEL);
	if (unlikely(!watch))
		return -ENOMEM;

	/* save a reference to device and bump the count to make it official */
	get_inotify_dev(dev);
	watch->dev = dev;

	atomic_inc(&dev->user->inotify_watches);

	ret = inotify_add_watch(dev->ih, &watch->wdata, inode, mask);
	if (ret < 0)
		free_inotify_user_watch(&watch->wdata);

	return ret;
}

/* Device Interface */

static unsigned int inotify_poll(struct file *file, poll_table *wait)
{
	struct inotify_device *dev = file->private_data;
	int ret = 0;

	poll_wait(file, &dev->wq, wait);
	mutex_lock(&dev->ev_mutex);
	if (!list_empty(&dev->events))
		ret = POLLIN | POLLRDNORM;
	mutex_unlock(&dev->ev_mutex);

	return ret;
}

static ssize_t inotify_read(struct file *file, char __user *buf,
			    size_t count, loff_t *pos)
{
	size_t event_size = sizeof (struct inotify_event);
	struct inotify_device *dev;
	char __user *start;
	int ret;
	DEFINE_WAIT(wait);

	start = buf;
	dev = file->private_data;

	while (1) {
		int events;

		prepare_to_wait(&dev->wq, &wait, TASK_INTERRUPTIBLE);

		mutex_lock(&dev->ev_mutex);
		events = !list_empty(&dev->events);
		mutex_unlock(&dev->ev_mutex);
		if (events) {
			ret = 0;
			break;
		}

		if (file->f_flags & O_NONBLOCK) {
			ret = -EAGAIN;
			break;
		}

		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}

		schedule();
	}

	finish_wait(&dev->wq, &wait);
	if (ret)
		return ret;

	mutex_lock(&dev->ev_mutex);
	while (1) {
		struct inotify_kernel_event *kevent;

		ret = buf - start;
		if (list_empty(&dev->events))
			break;

		kevent = inotify_dev_get_event(dev);
		if (event_size + kevent->event.len > count)
			break;

		if (copy_to_user(buf, &kevent->event, event_size)) {
			ret = -EFAULT;
			break;
		}
		buf += event_size;
		count -= event_size;

		if (kevent->name) {
			if (copy_to_user(buf, kevent->name, kevent->event.len)){
				ret = -EFAULT;
				break;
			}
			buf += kevent->event.len;
			count -= kevent->event.len;
		}

		remove_kevent(dev, kevent);
	}
	mutex_unlock(&dev->ev_mutex);

	return ret;
}

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

	inotify_destroy(dev->ih);

	/* destroy all of the events on this device */
	mutex_lock(&dev->ev_mutex);
	while (!list_empty(&dev->events))
		inotify_dev_event_dequeue(dev);
	mutex_unlock(&dev->ev_mutex);

	/* free this device: the put matching the get in inotify_init() */
	put_inotify_dev(dev);

	return 0;
}

static long inotify_ioctl(struct file *file, unsigned int cmd,
			  unsigned long arg)
{
	struct inotify_device *dev;
	void __user *p;
	int ret = -ENOTTY;

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

	switch (cmd) {
	case FIONREAD:
		ret = put_user(dev->queue_size, (int __user *) p);
		break;
	}

	return ret;
}

static const struct file_operations inotify_fops = {
	.poll           = inotify_poll,
	.read           = inotify_read,
	.release        = inotify_release,
	.unlocked_ioctl = inotify_ioctl,
	.compat_ioctl	= inotify_ioctl,
};

static const struct inotify_operations inotify_user_ops = {
	.handle_event	= inotify_dev_queue_event,
	.destroy_watch	= free_inotify_user_watch,
};

asmlinkage long sys_inotify_init(void)
{
	struct inotify_device *dev;
	struct inotify_handle *ih;
	struct user_struct *user;
	struct file *filp;
	int fd, ret;

	fd = get_unused_fd();
	if (fd < 0)
		return fd;

	filp = get_empty_filp();
	if (!filp) {
		ret = -ENFILE;
		goto out_put_fd;
	}

	user = get_uid(current->user);
	if (unlikely(atomic_read(&user->inotify_devs) >=
			inotify_max_user_instances)) {
		ret = -EMFILE;
		goto out_free_uid;
	}

	dev = kmalloc(sizeof(struct inotify_device), GFP_KERNEL);
	if (unlikely(!dev)) {
		ret = -ENOMEM;
		goto out_free_uid;
	}

	ih = inotify_init(&inotify_user_ops);
	if (unlikely(IS_ERR(ih))) {
		ret = PTR_ERR(ih);
		goto out_free_dev;
	}
	dev->ih = ih;

	filp->f_op = &inotify_fops;
	filp->f_vfsmnt = mntget(inotify_mnt);
	filp->f_dentry = dget(inotify_mnt->mnt_root);
	filp->f_mapping = filp->f_dentry->d_inode->i_mapping;
	filp->f_mode = FMODE_READ;
	filp->f_flags = O_RDONLY;
	filp->private_data = dev;

	INIT_LIST_HEAD(&dev->events);
	init_waitqueue_head(&dev->wq);
	mutex_init(&dev->ev_mutex);
	mutex_init(&dev->up_mutex);
	dev->event_count = 0;
	dev->queue_size = 0;
	dev->max_events = inotify_max_queued_events;
	dev->user = user;
	atomic_set(&dev->count, 0);

	get_inotify_dev(dev);
	atomic_inc(&user->inotify_devs);
	fd_install(fd, filp);

	return fd;
out_free_dev:
	kfree(dev);
out_free_uid:
	free_uid(user);
	put_filp(filp);
out_put_fd:
	put_unused_fd(fd);
	return ret;
}

asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
{
	struct inode *inode;
	struct inotify_device *dev;
	struct nameidata nd;
	struct file *filp;
	int ret, fput_needed;
	unsigned flags = 0;

	filp = fget_light(fd, &fput_needed);
	if (unlikely(!filp))
		return -EBADF;

	/* verify that this is indeed an inotify instance */
	if (unlikely(filp->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 = find_inode(path, &nd, flags);
	if (unlikely(ret))
		goto fput_and_out;

	/* inode held in place by reference to nd; dev by fget on fd */
	inode = nd.dentry->d_inode;
	dev = filp->private_data;

	mutex_lock(&dev->up_mutex);
	ret = inotify_find_update_watch(dev->ih, inode, mask);
	if (ret == -ENOENT)
		ret = create_watch(dev, inode, mask);
	mutex_unlock(&dev->up_mutex);

	path_release(&nd);
fput_and_out:
	fput_light(filp, fput_needed);
	return ret;
}

asmlinkage long sys_inotify_rm_watch(int fd, u32 wd)
{
	struct file *filp;
	struct inotify_device *dev;
	int ret, fput_needed;

	filp = fget_light(fd, &fput_needed);
	if (unlikely(!filp))
		return -EBADF;

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

	dev = filp->private_data;

	/* we free our watch data when we get IN_IGNORED */
	ret = inotify_rm_wd(dev->ih, wd);

out:
	fput_light(filp, fput_needed);
	return ret;
}

static struct super_block *
inotify_get_sb(struct file_system_type *fs_type, int flags,
	       const char *dev_name, void *data)
{
    return get_sb_pseudo(fs_type, "inotify", NULL, 0xBAD1DEA);
}

static struct file_system_type inotify_fs_type = {
    .name           = "inotifyfs",
    .get_sb         = inotify_get_sb,
    .kill_sb        = kill_anon_super,
};

/*
 * inotify_user_setup - Our initialization function.  Note that we cannnot 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)
{
	int ret;

	ret = register_filesystem(&inotify_fs_type);
	if (unlikely(ret))
		panic("inotify: register_filesystem returned %d!\n", ret);

	inotify_mnt = kern_mount(&inotify_fs_type);
	if (IS_ERR(inotify_mnt))
		panic("inotify: kern_mount ret %ld!\n", PTR_ERR(inotify_mnt));

	inotify_max_queued_events = 16384;
	inotify_max_user_instances = 128;
	inotify_max_user_watches = 8192;

	watch_cachep = kmem_cache_create("inotify_watch_cache",
					 sizeof(struct inotify_user_watch),
					 0, SLAB_PANIC, NULL, NULL);
	event_cachep = kmem_cache_create("inotify_event_cache",
					 sizeof(struct inotify_kernel_event),
					 0, SLAB_PANIC, NULL, NULL);

	return 0;
}

module_init(inotify_user_setup);