fanotify_user.c 12.4 KB
Newer Older
1
#include <linux/fcntl.h>
2
#include <linux/file.h>
3
#include <linux/fs.h>
4
#include <linux/anon_inodes.h>
5
#include <linux/fsnotify_backend.h>
6
#include <linux/init.h>
Eric Paris's avatar
Eric Paris committed
7
#include <linux/mount.h>
8
#include <linux/namei.h>
Eric Paris's avatar
Eric Paris committed
9
#include <linux/poll.h>
10
11
#include <linux/security.h>
#include <linux/syscalls.h>
12
#include <linux/types.h>
Eric Paris's avatar
Eric Paris committed
13
14
15
#include <linux/uaccess.h>

#include <asm/ioctls.h>
16
17
18

#include "fanotify.h"

19
20
static struct kmem_cache *fanotify_mark_cache __read_mostly;

Eric Paris's avatar
Eric Paris committed
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
/*
 * Get an fsnotify notification event if one exists and is small
 * enough to fit in "count". Return an error pointer if the count
 * is not large enough.
 *
 * Called with the group->notification_mutex held.
 */
static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
					    size_t count)
{
	BUG_ON(!mutex_is_locked(&group->notification_mutex));

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

	if (fsnotify_notify_queue_is_empty(group))
		return NULL;

	if (FAN_EVENT_METADATA_LEN > count)
		return ERR_PTR(-EINVAL);

	/* held the notification_mutex the whole time, so this is the
	 * same event we peeked above */
	return fsnotify_remove_notify_event(group);
}

static int create_and_fill_fd(struct fsnotify_group *group,
			      struct fanotify_event_metadata *metadata,
			      struct fsnotify_event *event)
{
	int client_fd;
	struct dentry *dentry;
	struct vfsmount *mnt;
	struct file *new_file;

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

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

	if (event->data_type != FSNOTIFY_EVENT_PATH) {
		WARN_ON(1);
		put_unused_fd(client_fd);
		return -EINVAL;
	}

	/*
	 * we need a new file handle for the userspace program so it can read even if it was
	 * originally opened O_WRONLY.
	 */
	dentry = dget(event->path.dentry);
	mnt = mntget(event->path.mnt);
	/* it's possible this event was an overflow event.  in that case dentry and mnt
	 * are NULL;  That's fine, just don't call dentry open */
	if (dentry && mnt)
		new_file = dentry_open(dentry, mnt,
				       O_RDONLY | O_LARGEFILE | FMODE_NONOTIFY,
				       current_cred());
	else
		new_file = ERR_PTR(-EOVERFLOW);
	if (IS_ERR(new_file)) {
		/*
		 * we still send an event even if we can't open the file.  this
		 * can happen when say tasks are gone and we try to open their
		 * /proc files or we try to open a WRONLY file like in sysfs
		 * we just send the errno to userspace since there isn't much
		 * else we can do.
		 */
		put_unused_fd(client_fd);
		client_fd = PTR_ERR(new_file);
	} else {
		fd_install(client_fd, new_file);
	}

	metadata->fd = client_fd;

	return 0;
}

static ssize_t fill_event_metadata(struct fsnotify_group *group,
				   struct fanotify_event_metadata *metadata,
				   struct fsnotify_event *event)
{
	pr_debug("%s: group=%p metadata=%p event=%p\n", __func__,
		 group, metadata, event);

	metadata->event_len = FAN_EVENT_METADATA_LEN;
	metadata->vers = FANOTIFY_METADATA_VERSION;
	metadata->mask = fanotify_outgoing_mask(event->mask);

	return create_and_fill_fd(group, metadata, event);

}

static ssize_t copy_event_to_user(struct fsnotify_group *group,
				  struct fsnotify_event *event,
				  char __user *buf)
{
	struct fanotify_event_metadata fanotify_event_metadata;
	int ret;

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

	ret = fill_event_metadata(group, &fanotify_event_metadata, event);
	if (ret)
		return ret;

	if (copy_to_user(buf, &fanotify_event_metadata, FAN_EVENT_METADATA_LEN))
		return -EFAULT;

	return FAN_EVENT_METADATA_LEN;
}

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

	poll_wait(file, &group->notification_waitq, wait);
	mutex_lock(&group->notification_mutex);
	if (!fsnotify_notify_queue_is_empty(group))
		ret = POLLIN | POLLRDNORM;
	mutex_unlock(&group->notification_mutex);

	return ret;
}

static ssize_t fanotify_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(wait);

	start = buf;
	group = file->private_data;

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

	while (1) {
		prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE);

		mutex_lock(&group->notification_mutex);
		kevent = get_one_event(group, count);
		mutex_unlock(&group->notification_mutex);

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

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

		if (start != buf)
			break;

		schedule();
	}

	finish_wait(&group->notification_waitq, &wait);
	if (start != buf && ret != -EFAULT)
		ret = buf - start;
	return ret;
}

203
204
205
206
207
208
209
210
211
212
213
214
static int fanotify_release(struct inode *ignored, struct file *file)
{
	struct fsnotify_group *group = file->private_data;

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

	/* matches the fanotify_init->fsnotify_alloc_group */
	fsnotify_put_group(group);

	return 0;
}

Eric Paris's avatar
Eric Paris committed
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
static long fanotify_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	struct fsnotify_group *group;
	struct fsnotify_event_holder *holder;
	void __user *p;
	int ret = -ENOTTY;
	size_t send_len = 0;

	group = file->private_data;

	p = (void __user *) arg;

	switch (cmd) {
	case FIONREAD:
		mutex_lock(&group->notification_mutex);
		list_for_each_entry(holder, &group->notification_list, event_list)
			send_len += FAN_EVENT_METADATA_LEN;
		mutex_unlock(&group->notification_mutex);
		ret = put_user(send_len, (int __user *) p);
		break;
	}

	return ret;
}

240
static const struct file_operations fanotify_fops = {
Eric Paris's avatar
Eric Paris committed
241
242
	.poll		= fanotify_poll,
	.read		= fanotify_read,
243
244
	.fasync		= NULL,
	.release	= fanotify_release,
Eric Paris's avatar
Eric Paris committed
245
246
	.unlocked_ioctl	= fanotify_ioctl,
	.compat_ioctl	= fanotify_ioctl,
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
static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
{
	kmem_cache_free(fanotify_mark_cache, fsn_mark);
}

static int fanotify_find_path(int dfd, const char __user *filename,
			      struct path *path, unsigned int flags)
{
	int ret;

	pr_debug("%s: dfd=%d filename=%p flags=%x\n", __func__,
		 dfd, filename, flags);

	if (filename == NULL) {
		struct file *file;
		int fput_needed;

		ret = -EBADF;
		file = fget_light(dfd, &fput_needed);
		if (!file)
			goto out;

		ret = -ENOTDIR;
		if ((flags & FAN_MARK_ONLYDIR) &&
		    !(S_ISDIR(file->f_path.dentry->d_inode->i_mode))) {
			fput_light(file, fput_needed);
			goto out;
		}

		*path = file->f_path;
		path_get(path);
		fput_light(file, fput_needed);
	} else {
		unsigned int lookup_flags = 0;

		if (!(flags & FAN_MARK_DONT_FOLLOW))
			lookup_flags |= LOOKUP_FOLLOW;
		if (flags & FAN_MARK_ONLYDIR)
			lookup_flags |= LOOKUP_DIRECTORY;

		ret = user_path_at(dfd, filename, lookup_flags, path);
		if (ret)
			goto out;
	}

	/* you can only watch an inode if you have read permissions on it */
	ret = inode_permission(path->dentry->d_inode, MAY_READ);
	if (ret)
		path_put(path);
out:
	return ret;
}

static int fanotify_remove_mark(struct fsnotify_group *group,
				struct inode *inode,
				__u32 mask)
{
	struct fsnotify_mark *fsn_mark;
	__u32 new_mask;

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

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

	spin_lock(&fsn_mark->lock);
	fsn_mark->mask &= ~mask;
	new_mask = fsn_mark->mask;
	spin_unlock(&fsn_mark->lock);

	if (!new_mask)
		fsnotify_destroy_mark(fsn_mark);
	else
		fsnotify_recalc_inode_mask(inode);

	fsnotify_recalc_group_mask(group);

	/* matches the fsnotify_find_mark() */
	fsnotify_put_mark(fsn_mark);

	return 0;
}

static int fanotify_add_mark(struct fsnotify_group *group,
			     struct inode *inode,
			     __u32 mask)
{
	struct fsnotify_mark *fsn_mark;
	__u32 old_mask, new_mask;
	int ret;

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

	fsn_mark = fsnotify_find_mark(group, inode);
	if (!fsn_mark) {
		struct fsnotify_mark *new_fsn_mark;

		ret = -ENOMEM;
		new_fsn_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
		if (!new_fsn_mark)
			goto out;

		fsnotify_init_mark(new_fsn_mark, fanotify_free_mark);
		ret = fsnotify_add_mark(new_fsn_mark, group, inode, 0);
		if (ret) {
			fanotify_free_mark(new_fsn_mark);
			goto out;
		}

		fsn_mark = new_fsn_mark;
	}

	ret = 0;

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

	/* we made changes to a mask, update the group mask and the inode mask
	 * so things happen quickly. */
	if (old_mask != new_mask) {
		/* more bits in old than in new? */
		int dropped = (old_mask & ~new_mask);
		/* more bits in this mark than the inode's mask? */
		int do_inode = (new_mask & ~inode->i_fsnotify_mask);
		/* more bits in this mark than the group? */
		int do_group = (new_mask & ~group->mask);

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

		/* update the group mask with the new mask */
		if (dropped || do_group)
			fsnotify_recalc_group_mask(group);
	}

	/* match the init or the find.... */
	fsnotify_put_mark(fsn_mark);
out:
	return ret;
}

static int fanotify_update_mark(struct fsnotify_group *group,
				struct inode *inode, int flags,
				__u32 mask)
{
	pr_debug("%s: group=%p inode=%p flags=%x mask=%x\n", __func__,
		 group, inode, flags, mask);

	if (flags & FAN_MARK_ADD)
		fanotify_add_mark(group, inode, mask);
	else if (flags & FAN_MARK_REMOVE)
		fanotify_remove_mark(group, inode, mask);
	else
		BUG();

	return 0;
}

static bool fanotify_mark_validate_input(int flags,
					 __u32 mask)
{
	pr_debug("%s: flags=%x mask=%x\n", __func__, flags, mask);

	/* are flags valid of this operation? */
	if (!fanotify_mark_flags_valid(flags))
		return false;
	/* is the mask valid? */
	if (!fanotify_mask_valid(mask))
		return false;
	return true;
}

428
/* fanotify syscalls */
429
430
431
SYSCALL_DEFINE3(fanotify_init, unsigned int, flags, unsigned int, event_f_flags,
		unsigned int, priority)
{
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
	struct fsnotify_group *group;
	int f_flags, fd;

	pr_debug("%s: flags=%d event_f_flags=%d priority=%d\n",
		__func__, flags, event_f_flags, priority);

	if (event_f_flags)
		return -EINVAL;
	if (priority)
		return -EINVAL;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;

	if (flags & ~FAN_ALL_INIT_FLAGS)
		return -EINVAL;

	f_flags = (O_RDONLY | FMODE_NONOTIFY);
	if (flags & FAN_CLOEXEC)
		f_flags |= O_CLOEXEC;
	if (flags & FAN_NONBLOCK)
		f_flags |= O_NONBLOCK;

	/* fsnotify_alloc_group takes a ref.  Dropped in fanotify_release */
	group = fsnotify_alloc_group(&fanotify_fsnotify_ops);
	if (IS_ERR(group))
		return PTR_ERR(group);

	fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
	if (fd < 0)
		goto out_put_group;

	return fd;

out_put_group:
	fsnotify_put_group(group);
	return fd;
469
}
470
471
472
473

SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
		__u64, mask, int, dfd, const char  __user *, pathname)
{
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
	struct inode *inode;
	struct fsnotify_group *group;
	struct file *filp;
	struct path path;
	int ret, fput_needed;

	pr_debug("%s: fanotify_fd=%d flags=%x dfd=%d pathname=%p mask=%llx\n",
		 __func__, fanotify_fd, flags, dfd, pathname, mask);

	/* we only use the lower 32 bits as of right now. */
	if (mask & ((__u64)0xffffffff << 32))
		return -EINVAL;

	if (!fanotify_mark_validate_input(flags, mask))
		return -EINVAL;

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

	/* verify that this is indeed an fanotify instance */
	ret = -EINVAL;
	if (unlikely(filp->f_op != &fanotify_fops))
		goto fput_and_out;

	ret = fanotify_find_path(dfd, 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 = filp->private_data;

	/* create/update an inode mark */
	ret = fanotify_update_mark(group, inode, flags, mask);

	path_put(&path);
fput_and_out:
	fput_light(filp, fput_needed);
	return ret;
}

/*
 * fanotify_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 fanotify_user_setup(void)
{
	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC);

	return 0;
526
}
527
device_initcall(fanotify_user_setup);