summaryrefslogtreecommitdiff
path: root/fs/notify/fanotify/fanotify_user.c
blob: 55cd87b0cc26089c41febdee77cafb829698df25 (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
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
// SPDX-License-Identifier: GPL-2.0
#include <linux/fanotify.h>
#include <linux/fcntl.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/anon_inodes.h>
#include <linux/fsnotify_backend.h>
#include <linux/init.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/poll.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/compat.h>
#include <linux/sched/signal.h>
#include <linux/memcontrol.h>

#include <asm/ioctls.h>

#include "../../mount.h"
#include "../fdinfo.h"
#include "fanotify.h"

#define FANOTIFY_DEFAULT_MAX_EVENTS	16384
#define FANOTIFY_DEFAULT_MAX_MARKS	8192
#define FANOTIFY_DEFAULT_MAX_LISTENERS	128

/*
 * All flags that may be specified in parameter event_f_flags of fanotify_init.
 *
 * Internal and external open flags are stored together in field f_flags of
 * struct file. Only external open flags shall be allowed in event_f_flags.
 * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be
 * excluded.
 */
#define	FANOTIFY_INIT_ALL_EVENT_F_BITS				( \
		O_ACCMODE	| O_APPEND	| O_NONBLOCK	| \
		__O_SYNC	| O_DSYNC	| O_CLOEXEC     | \
		O_LARGEFILE	| O_NOATIME	)

extern const struct fsnotify_ops fanotify_fsnotify_ops;

struct kmem_cache *fanotify_mark_cache __read_mostly;
struct kmem_cache *fanotify_event_cachep __read_mostly;
struct kmem_cache *fanotify_perm_event_cachep __read_mostly;

/*
 * 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_lock held.
 */
static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
					    size_t count)
{
	assert_spin_locked(&group->notification_lock);

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

static int create_fd(struct fsnotify_group *group,
		     struct fanotify_event *event,
		     struct file **file)
{
	int client_fd;
	struct file *new_file;

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

	client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
	if (client_fd < 0)
		return client_fd;

	/*
	 * we need a new file handle for the userspace program so it can read even if it was
	 * originally opened O_WRONLY.
	 */
	/* 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 (event->path.dentry && event->path.mnt)
		new_file = dentry_open(&event->path,
				       group->fanotify_data.f_flags | 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 {
		*file = new_file;
	}

	return client_fd;
}

static int fill_event_metadata(struct fsnotify_group *group,
			       struct fanotify_event_metadata *metadata,
			       struct fsnotify_event *fsn_event,
			       struct file **file)
{
	int ret = 0;
	struct fanotify_event *event;

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

	*file = NULL;
	event = container_of(fsn_event, struct fanotify_event, fse);
	metadata->event_len = FAN_EVENT_METADATA_LEN;
	metadata->metadata_len = FAN_EVENT_METADATA_LEN;
	metadata->vers = FANOTIFY_METADATA_VERSION;
	metadata->reserved = 0;
	metadata->mask = event->mask & FANOTIFY_OUTGOING_EVENTS;
	metadata->pid = pid_vnr(event->pid);
	if (unlikely(event->mask & FAN_Q_OVERFLOW))
		metadata->fd = FAN_NOFD;
	else {
		metadata->fd = create_fd(group, event, file);
		if (metadata->fd < 0)
			ret = metadata->fd;
	}

	return ret;
}

static struct fanotify_perm_event *dequeue_event(
				struct fsnotify_group *group, int fd)
{
	struct fanotify_perm_event *event, *return_e = NULL;

	spin_lock(&group->notification_lock);
	list_for_each_entry(event, &group->fanotify_data.access_list,
			    fae.fse.list) {
		if (event->fd != fd)
			continue;

		list_del_init(&event->fae.fse.list);
		return_e = event;
		break;
	}
	spin_unlock(&group->notification_lock);

	pr_debug("%s: found return_re=%p\n", __func__, return_e);

	return return_e;
}

static int process_access_response(struct fsnotify_group *group,
				   struct fanotify_response *response_struct)
{
	struct fanotify_perm_event *event;
	int fd = response_struct->fd;
	int response = response_struct->response;

	pr_debug("%s: group=%p fd=%d response=%d\n", __func__, group,
		 fd, response);
	/*
	 * make sure the response is valid, if invalid we do nothing and either
	 * userspace can send a valid response or we will clean it up after the
	 * timeout
	 */
	switch (response & ~FAN_AUDIT) {
	case FAN_ALLOW:
	case FAN_DENY:
		break;
	default:
		return -EINVAL;
	}

	if (fd < 0)
		return -EINVAL;

	if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT))
		return -EINVAL;

	event = dequeue_event(group, fd);
	if (!event)
		return -ENOENT;

	event->response = response;
	wake_up(&group->fanotify_data.access_waitq);

	return 0;
}

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

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

	ret = fill_event_metadata(group, &fanotify_event_metadata, event, &f);
	if (ret < 0)
		return ret;

	fd = fanotify_event_metadata.fd;
	ret = -EFAULT;
	/*
	 * Sanity check copy size in case get_one_event() and
	 * fill_event_metadata() event_len sizes ever get out of sync.
	 */
	if (WARN_ON_ONCE(fanotify_event_metadata.event_len > count))
		goto out_close_fd;
	if (copy_to_user(buf, &fanotify_event_metadata,
			 fanotify_event_metadata.event_len))
		goto out_close_fd;

	if (fanotify_is_perm_event(FANOTIFY_E(event)->mask))
		FANOTIFY_PE(event)->fd = fd;

	if (fd != FAN_NOFD)
		fd_install(fd, f);
	return fanotify_event_metadata.event_len;

out_close_fd:
	if (fd != FAN_NOFD) {
		put_unused_fd(fd);
		fput(f);
	}
	return ret;
}

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

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

	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_FUNC(wait, woken_wake_function);

	start = buf;
	group = file->private_data;

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

	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);

		if (IS_ERR(kevent)) {
			ret = PTR_ERR(kevent);
			break;
		}

		if (!kevent) {
			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);
			continue;
		}

		ret = copy_event_to_user(group, kevent, buf, count);
		if (unlikely(ret == -EOPENSTALE)) {
			/*
			 * We cannot report events with stale fd so drop it.
			 * Setting ret to 0 will continue the event loop and
			 * do the right thing if there are no more events to
			 * read (i.e. return bytes read, -EAGAIN or wait).
			 */
			ret = 0;
		}

		/*
		 * Permission events get queued to wait for response.  Other
		 * events can be destroyed now.
		 */
		if (!fanotify_is_perm_event(FANOTIFY_E(kevent)->mask)) {
			fsnotify_destroy_event(group, kevent);
		} else {
			if (ret <= 0) {
				FANOTIFY_PE(kevent)->response = FAN_DENY;
				wake_up(&group->fanotify_data.access_waitq);
			} else {
				spin_lock(&group->notification_lock);
				list_add_tail(&kevent->list,
					&group->fanotify_data.access_list);
				spin_unlock(&group->notification_lock);
			}
		}
		if (ret < 0)
			break;
		buf += ret;
		count -= ret;
	}
	remove_wait_queue(&group->notification_waitq, &wait);

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

static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
	struct fanotify_response response = { .fd = -1, .response = -1 };
	struct fsnotify_group *group;
	int ret;

	if (!IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS))
		return -EINVAL;

	group = file->private_data;

	if (count > sizeof(response))
		count = sizeof(response);

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

	if (copy_from_user(&response, buf, count))
		return -EFAULT;

	ret = process_access_response(group, &response);
	if (ret < 0)
		count = ret;

	return count;
}

static int fanotify_release(struct inode *ignored, struct file *file)
{
	struct fsnotify_group *group = file->private_data;
	struct fanotify_perm_event *event, *next;
	struct fsnotify_event *fsn_event;

	/*
	 * Stop new events from arriving in the notification queue. since
	 * userspace cannot use fanotify fd anymore, no event can enter or
	 * leave access_list by now either.
	 */
	fsnotify_group_stop_queueing(group);

	/*
	 * Process all permission events on access_list and notification queue
	 * and simulate reply from userspace.
	 */
	spin_lock(&group->notification_lock);
	list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
				 fae.fse.list) {
		pr_debug("%s: found group=%p event=%p\n", __func__, group,
			 event);

		list_del_init(&event->fae.fse.list);
		event->response = FAN_ALLOW;
	}

	/*
	 * Destroy all non-permission events. For permission events just
	 * dequeue them and set the response. They will be freed once the
	 * response is consumed and fanotify_get_response() returns.
	 */
	while (!fsnotify_notify_queue_is_empty(group)) {
		fsn_event = fsnotify_remove_first_event(group);
		if (!(FANOTIFY_E(fsn_event)->mask & FANOTIFY_PERM_EVENTS)) {
			spin_unlock(&group->notification_lock);
			fsnotify_destroy_event(group, fsn_event);
			spin_lock(&group->notification_lock);
		} else {
			FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
		}
	}
	spin_unlock(&group->notification_lock);

	/* Response for all permission events it set, wakeup waiters */
	wake_up(&group->fanotify_data.access_waitq);

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

	return 0;
}

static long fanotify_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;

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

	return ret;
}

static const struct file_operations fanotify_fops = {
	.show_fdinfo	= fanotify_show_fdinfo,
	.poll		= fanotify_poll,
	.read		= fanotify_read,
	.write		= fanotify_write,
	.fasync		= NULL,
	.release	= fanotify_release,
	.unlocked_ioctl	= fanotify_ioctl,
	.compat_ioctl	= fanotify_ioctl,
	.llseek		= noop_llseek,
};

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 fd f = fdget(dfd);

		ret = -EBADF;
		if (!f.file)
			goto out;

		ret = -ENOTDIR;
		if ((flags & FAN_MARK_ONLYDIR) &&
		    !(S_ISDIR(file_inode(f.file)->i_mode))) {
			fdput(f);
			goto out;
		}

		*path = f.file->f_path;
		path_get(path);
		fdput(f);
	} 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 __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
					    __u32 mask,
					    unsigned int flags,
					    int *destroy)
{
	__u32 oldmask = 0;

	spin_lock(&fsn_mark->lock);
	if (!(flags & FAN_MARK_IGNORED_MASK)) {
		oldmask = fsn_mark->mask;
		fsn_mark->mask &= ~mask;
	} else {
		fsn_mark->ignored_mask &= ~mask;
	}
	*destroy = !(fsn_mark->mask | fsn_mark->ignored_mask);
	spin_unlock(&fsn_mark->lock);

	return mask & oldmask;
}

static int fanotify_remove_mark(struct fsnotify_group *group,
				fsnotify_connp_t *connp, __u32 mask,
				unsigned int flags)
{
	struct fsnotify_mark *fsn_mark = NULL;
	__u32 removed;
	int destroy_mark;

	mutex_lock(&group->mark_mutex);
	fsn_mark = fsnotify_find_mark(connp, group);
	if (!fsn_mark) {
		mutex_unlock(&group->mark_mutex);
		return -ENOENT;
	}

	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
						 &destroy_mark);
	if (removed & fsnotify_conn_mask(fsn_mark->connector))
		fsnotify_recalc_mask(fsn_mark->connector);
	if (destroy_mark)
		fsnotify_detach_mark(fsn_mark);
	mutex_unlock(&group->mark_mutex);
	if (destroy_mark)
		fsnotify_free_mark(fsn_mark);

	/* matches the fsnotify_find_mark() */
	fsnotify_put_mark(fsn_mark);
	return 0;
}

static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
					 struct vfsmount *mnt, __u32 mask,
					 unsigned int flags)
{
	return fanotify_remove_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
				    mask, flags);
}

static int fanotify_remove_sb_mark(struct fsnotify_group *group,
				      struct super_block *sb, __u32 mask,
				      unsigned int flags)
{
	return fanotify_remove_mark(group, &sb->s_fsnotify_marks, mask, flags);
}

static int fanotify_remove_inode_mark(struct fsnotify_group *group,
				      struct inode *inode, __u32 mask,
				      unsigned int flags)
{
	return fanotify_remove_mark(group, &inode->i_fsnotify_marks, mask,
				    flags);
}

static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
				       __u32 mask,
				       unsigned int flags)
{
	__u32 oldmask = -1;

	spin_lock(&fsn_mark->lock);
	if (!(flags & FAN_MARK_IGNORED_MASK)) {
		oldmask = fsn_mark->mask;
		fsn_mark->mask |= mask;
	} else {
		fsn_mark->ignored_mask |= mask;
		if (flags & FAN_MARK_IGNORED_SURV_MODIFY)
			fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
	}
	spin_unlock(&fsn_mark->lock);

	return mask & ~oldmask;
}

static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
						   fsnotify_connp_t *connp,
						   unsigned int type)
{
	struct fsnotify_mark *mark;
	int ret;

	if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
		return ERR_PTR(-ENOSPC);

	mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
	if (!mark)
		return ERR_PTR(-ENOMEM);

	fsnotify_init_mark(mark, group);
	ret = fsnotify_add_mark_locked(mark, connp, type, 0);
	if (ret) {
		fsnotify_put_mark(mark);
		return ERR_PTR(ret);
	}

	return mark;
}


static int fanotify_add_mark(struct fsnotify_group *group,
			     fsnotify_connp_t *connp, unsigned int type,
			     __u32 mask, unsigned int flags)
{
	struct fsnotify_mark *fsn_mark;
	__u32 added;

	mutex_lock(&group->mark_mutex);
	fsn_mark = fsnotify_find_mark(connp, group);
	if (!fsn_mark) {
		fsn_mark = fanotify_add_new_mark(group, connp, type);
		if (IS_ERR(fsn_mark)) {
			mutex_unlock(&group->mark_mutex);
			return PTR_ERR(fsn_mark);
		}
	}
	added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
	if (added & ~fsnotify_conn_mask(fsn_mark->connector))
		fsnotify_recalc_mask(fsn_mark->connector);
	mutex_unlock(&group->mark_mutex);

	fsnotify_put_mark(fsn_mark);
	return 0;
}

static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
				      struct vfsmount *mnt, __u32 mask,
				      unsigned int flags)
{
	return fanotify_add_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
				 FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags);
}

static int fanotify_add_sb_mark(struct fsnotify_group *group,
				      struct super_block *sb, __u32 mask,
				      unsigned int flags)
{
	return fanotify_add_mark(group, &sb->s_fsnotify_marks,
				 FSNOTIFY_OBJ_TYPE_SB, mask, flags);
}

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

	/*
	 * If some other task has this inode open for write we should not add
	 * an ignored mark, unless that ignored mark is supposed to survive
	 * modification changes anyway.
	 */
	if ((flags & FAN_MARK_IGNORED_MASK) &&
	    !(flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
	    inode_is_open_for_write(inode))
		return 0;

	return fanotify_add_mark(group, &inode->i_fsnotify_marks,
				 FSNOTIFY_OBJ_TYPE_INODE, mask, flags);
}

/* fanotify syscalls */
SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
{
	struct fsnotify_group *group;
	int f_flags, fd;
	struct user_struct *user;
	struct fanotify_event *oevent;

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

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

#ifdef CONFIG_AUDITSYSCALL
	if (flags & ~(FANOTIFY_INIT_FLAGS | FAN_ENABLE_AUDIT))
#else
	if (flags & ~FANOTIFY_INIT_FLAGS)
#endif
		return -EINVAL;

	if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
		return -EINVAL;

	switch (event_f_flags & O_ACCMODE) {
	case O_RDONLY:
	case O_RDWR:
	case O_WRONLY:
		break;
	default:
		return -EINVAL;
	}

	user = get_current_user();
	if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
		free_uid(user);
		return -EMFILE;
	}

	f_flags = O_RDWR | 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)) {
		free_uid(user);
		return PTR_ERR(group);
	}

	group->fanotify_data.user = user;
	group->fanotify_data.flags = flags;
	atomic_inc(&user->fanotify_listeners);
	group->memcg = get_mem_cgroup_from_mm(current->mm);

	oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL);
	if (unlikely(!oevent)) {
		fd = -ENOMEM;
		goto out_destroy_group;
	}
	group->overflow_event = &oevent->fse;

	if (force_o_largefile())
		event_f_flags |= O_LARGEFILE;
	group->fanotify_data.f_flags = event_f_flags;
	init_waitqueue_head(&group->fanotify_data.access_waitq);
	INIT_LIST_HEAD(&group->fanotify_data.access_list);
	switch (flags & FANOTIFY_CLASS_BITS) {
	case FAN_CLASS_NOTIF:
		group->priority = FS_PRIO_0;
		break;
	case FAN_CLASS_CONTENT:
		group->priority = FS_PRIO_1;
		break;
	case FAN_CLASS_PRE_CONTENT:
		group->priority = FS_PRIO_2;
		break;
	default:
		fd = -EINVAL;
		goto out_destroy_group;
	}

	if (flags & FAN_UNLIMITED_QUEUE) {
		fd = -EPERM;
		if (!capable(CAP_SYS_ADMIN))
			goto out_destroy_group;
		group->max_events = UINT_MAX;
	} else {
		group->max_events = FANOTIFY_DEFAULT_MAX_EVENTS;
	}

	if (flags & FAN_UNLIMITED_MARKS) {
		fd = -EPERM;
		if (!capable(CAP_SYS_ADMIN))
			goto out_destroy_group;
		group->fanotify_data.max_marks = UINT_MAX;
	} else {
		group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS;
	}

	if (flags & FAN_ENABLE_AUDIT) {
		fd = -EPERM;
		if (!capable(CAP_AUDIT_WRITE))
			goto out_destroy_group;
	}

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

	return fd;

out_destroy_group:
	fsnotify_destroy_group(group);
	return fd;
}

static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
			    int dfd, const char  __user *pathname)
{
	struct inode *inode = NULL;
	struct vfsmount *mnt = NULL;
	struct fsnotify_group *group;
	struct fd f;
	struct path path;
	u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
	unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
	int ret;

	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 (flags & ~FANOTIFY_MARK_FLAGS)
		return -EINVAL;

	switch (mark_type) {
	case FAN_MARK_INODE:
	case FAN_MARK_MOUNT:
	case FAN_MARK_FILESYSTEM:
		break;
	default:
		return -EINVAL;
	}

	switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
	case FAN_MARK_ADD:		/* fallthrough */
	case FAN_MARK_REMOVE:
		if (!mask)
			return -EINVAL;
		break;
	case FAN_MARK_FLUSH:
		if (flags & ~(FANOTIFY_MARK_TYPE_BITS | FAN_MARK_FLUSH))
			return -EINVAL;
		break;
	default:
		return -EINVAL;
	}

	if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS))
		valid_mask |= FANOTIFY_PERM_EVENTS;

	if (mask & ~valid_mask)
		return -EINVAL;

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

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

	/*
	 * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF.  These are not
	 * allowed to set permissions events.
	 */
	ret = -EINVAL;
	if (mask & FANOTIFY_PERM_EVENTS &&
	    group->priority == FS_PRIO_0)
		goto fput_and_out;

	if (flags & FAN_MARK_FLUSH) {
		ret = 0;
		if (mark_type == FAN_MARK_MOUNT)
			fsnotify_clear_vfsmount_marks_by_group(group);
		else if (mark_type == FAN_MARK_FILESYSTEM)
			fsnotify_clear_sb_marks_by_group(group);
		else
			fsnotify_clear_inode_marks_by_group(group);
		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 */
	if (mark_type == FAN_MARK_INODE)
		inode = path.dentry->d_inode;
	else
		mnt = path.mnt;

	/* create/update an inode mark */
	switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) {
	case FAN_MARK_ADD:
		if (mark_type == FAN_MARK_MOUNT)
			ret = fanotify_add_vfsmount_mark(group, mnt, mask, flags);
		else if (mark_type == FAN_MARK_FILESYSTEM)
			ret = fanotify_add_sb_mark(group, mnt->mnt_sb, mask, flags);
		else
			ret = fanotify_add_inode_mark(group, inode, mask, flags);
		break;
	case FAN_MARK_REMOVE:
		if (mark_type == FAN_MARK_MOUNT)
			ret = fanotify_remove_vfsmount_mark(group, mnt, mask, flags);
		else if (mark_type == FAN_MARK_FILESYSTEM)
			ret = fanotify_remove_sb_mark(group, mnt->mnt_sb, mask, flags);
		else
			ret = fanotify_remove_inode_mark(group, inode, mask, flags);
		break;
	default:
		ret = -EINVAL;
	}

	path_put(&path);
fput_and_out:
	fdput(f);
	return ret;
}

SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
			      __u64, mask, int, dfd,
			      const char  __user *, pathname)
{
	return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname);
}

#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE6(fanotify_mark,
				int, fanotify_fd, unsigned int, flags,
				__u32, mask0, __u32, mask1, int, dfd,
				const char  __user *, pathname)
{
	return do_fanotify_mark(fanotify_fd, flags,
#ifdef __BIG_ENDIAN
				((__u64)mask0 << 32) | mask1,
#else
				((__u64)mask1 << 32) | mask0,
#endif
				 dfd, pathname);
}
#endif

/*
 * fanotify_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 fanotify_user_setup(void)
{
	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 7);
	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);

	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
					 SLAB_PANIC|SLAB_ACCOUNT);
	fanotify_event_cachep = KMEM_CACHE(fanotify_event, SLAB_PANIC);
	if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) {
		fanotify_perm_event_cachep =
			KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);
	}

	return 0;
}
device_initcall(fanotify_user_setup);