summaryrefslogtreecommitdiffstats
path: root/fs/notify/fanotify/fanotify.c
blob: a2a15bc4df280268ce224fb64b0934513eb2f3e2 (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
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
// SPDX-License-Identifier: GPL-2.0
#include <linux/fanotify.h>
#include <linux/fdtable.h>
#include <linux/fsnotify_backend.h>
#include <linux/init.h>
#include <linux/jiffies.h>
#include <linux/kernel.h> /* UINT_MAX */
#include <linux/mount.h>
#include <linux/sched.h>
#include <linux/sched/user.h>
#include <linux/sched/signal.h>
#include <linux/types.h>
#include <linux/wait.h>
#include <linux/audit.h>
#include <linux/sched/mm.h>
#include <linux/statfs.h>
#include <linux/stringhash.h>

#include "fanotify.h"

static bool fanotify_path_equal(const struct path *p1, const struct path *p2)
{
	return p1->mnt == p2->mnt && p1->dentry == p2->dentry;
}

static unsigned int fanotify_hash_path(const struct path *path)
{
	return hash_ptr(path->dentry, FANOTIFY_EVENT_HASH_BITS) ^
		hash_ptr(path->mnt, FANOTIFY_EVENT_HASH_BITS);
}

static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
				       __kernel_fsid_t *fsid2)
{
	return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
}

static unsigned int fanotify_hash_fsid(__kernel_fsid_t *fsid)
{
	return hash_32(fsid->val[0], FANOTIFY_EVENT_HASH_BITS) ^
		hash_32(fsid->val[1], FANOTIFY_EVENT_HASH_BITS);
}

static bool fanotify_fh_equal(struct fanotify_fh *fh1,
			      struct fanotify_fh *fh2)
{
	if (fh1->type != fh2->type || fh1->len != fh2->len)
		return false;

	return !fh1->len ||
		!memcmp(fanotify_fh_buf(fh1), fanotify_fh_buf(fh2), fh1->len);
}

static unsigned int fanotify_hash_fh(struct fanotify_fh *fh)
{
	long salt = (long)fh->type | (long)fh->len << 8;

	/*
	 * full_name_hash() works long by long, so it handles fh buf optimally.
	 */
	return full_name_hash((void *)salt, fanotify_fh_buf(fh), fh->len);
}

static bool fanotify_fid_event_equal(struct fanotify_fid_event *ffe1,
				     struct fanotify_fid_event *ffe2)
{
	/* Do not merge fid events without object fh */
	if (!ffe1->object_fh.len)
		return false;

	return fanotify_fsid_equal(&ffe1->fsid, &ffe2->fsid) &&
		fanotify_fh_equal(&ffe1->object_fh, &ffe2->object_fh);
}

static bool fanotify_info_equal(struct fanotify_info *info1,
				struct fanotify_info *info2)
{
	if (info1->dir_fh_totlen != info2->dir_fh_totlen ||
	    info1->dir2_fh_totlen != info2->dir2_fh_totlen ||
	    info1->file_fh_totlen != info2->file_fh_totlen ||
	    info1->name_len != info2->name_len ||
	    info1->name2_len != info2->name2_len)
		return false;

	if (info1->dir_fh_totlen &&
	    !fanotify_fh_equal(fanotify_info_dir_fh(info1),
			       fanotify_info_dir_fh(info2)))
		return false;

	if (info1->dir2_fh_totlen &&
	    !fanotify_fh_equal(fanotify_info_dir2_fh(info1),
			       fanotify_info_dir2_fh(info2)))
		return false;

	if (info1->file_fh_totlen &&
	    !fanotify_fh_equal(fanotify_info_file_fh(info1),
			       fanotify_info_file_fh(info2)))
		return false;

	if (info1->name_len &&
	    memcmp(fanotify_info_name(info1), fanotify_info_name(info2),
		   info1->name_len))
		return false;

	return !info1->name2_len ||
		!memcmp(fanotify_info_name2(info1), fanotify_info_name2(info2),
			info1->name2_len);
}

static bool fanotify_name_event_equal(struct fanotify_name_event *fne1,
				      struct fanotify_name_event *fne2)
{
	struct fanotify_info *info1 = &fne1->info;
	struct fanotify_info *info2 = &fne2->info;

	/* Do not merge name events without dir fh */
	if (!info1->dir_fh_totlen)
		return false;

	if (!fanotify_fsid_equal(&fne1->fsid, &fne2->fsid))
		return false;

	return fanotify_info_equal(info1, info2);
}

static bool fanotify_error_event_equal(struct fanotify_error_event *fee1,
				       struct fanotify_error_event *fee2)
{
	/* Error events against the same file system are always merged. */
	if (!fanotify_fsid_equal(&fee1->fsid, &fee2->fsid))
		return false;

	return true;
}

static bool fanotify_should_merge(struct fanotify_event *old,
				  struct fanotify_event *new)
{
	pr_debug("%s: old=%p new=%p\n", __func__, old, new);

	if (old->hash != new->hash ||
	    old->type != new->type || old->pid != new->pid)
		return false;

	/*
	 * We want to merge many dirent events in the same dir (i.e.
	 * creates/unlinks/renames), but we do not want to merge dirent
	 * events referring to subdirs with dirent events referring to
	 * non subdirs, otherwise, user won't be able to tell from a
	 * mask FAN_CREATE|FAN_DELETE|FAN_ONDIR if it describes mkdir+
	 * unlink pair or rmdir+create pair of events.
	 */
	if ((old->mask & FS_ISDIR) != (new->mask & FS_ISDIR))
		return false;

	/*
	 * FAN_RENAME event is reported with special info record types,
	 * so we cannot merge it with other events.
	 */
	if ((old->mask & FAN_RENAME) != (new->mask & FAN_RENAME))
		return false;

	switch (old->type) {
	case FANOTIFY_EVENT_TYPE_PATH:
		return fanotify_path_equal(fanotify_event_path(old),
					   fanotify_event_path(new));
	case FANOTIFY_EVENT_TYPE_FID:
		return fanotify_fid_event_equal(FANOTIFY_FE(old),
						FANOTIFY_FE(new));
	case FANOTIFY_EVENT_TYPE_FID_NAME:
		return fanotify_name_event_equal(FANOTIFY_NE(old),
						 FANOTIFY_NE(new));
	case FANOTIFY_EVENT_TYPE_FS_ERROR:
		return fanotify_error_event_equal(FANOTIFY_EE(old),
						  FANOTIFY_EE(new));
	default:
		WARN_ON_ONCE(1);
	}

	return false;
}

/* Limit event merges to limit CPU overhead per event */
#define FANOTIFY_MAX_MERGE_EVENTS 128

/* and the list better be locked by something too! */
static int fanotify_merge(struct fsnotify_group *group,
			  struct fsnotify_event *event)
{
	struct fanotify_event *old, *new = FANOTIFY_E(event);
	unsigned int bucket = fanotify_event_hash_bucket(group, new);
	struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
	int i = 0;

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

	/*
	 * Don't merge a permission event with any other event so that we know
	 * the event structure we have created in fanotify_handle_event() is the
	 * one we should check for permission response.
	 */
	if (fanotify_is_perm_event(new->mask))
		return 0;

	hlist_for_each_entry(old, hlist, merge_list) {
		if (++i > FANOTIFY_MAX_MERGE_EVENTS)
			break;
		if (fanotify_should_merge(old, new)) {
			old->mask |= new->mask;

			if (fanotify_is_error_event(old->mask))
				FANOTIFY_EE(old)->err_count++;

			return 1;
		}
	}

	return 0;
}

/*
 * Wait for response to permission event. The function also takes care of
 * freeing the permission event (or offloads that in case the wait is canceled
 * by a signal). The function returns 0 in case access got allowed by userspace,
 * -EPERM in case userspace disallowed the access, and -ERESTARTSYS in case
 * the wait got interrupted by a signal.
 */
static int fanotify_get_response(struct fsnotify_group *group,
				 struct fanotify_perm_event *event,
				 struct fsnotify_iter_info *iter_info)
{
	int ret;

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

	ret = wait_event_killable(group->fanotify_data.access_waitq,
				  event->state == FAN_EVENT_ANSWERED);
	/* Signal pending? */
	if (ret < 0) {
		spin_lock(&group->notification_lock);
		/* Event reported to userspace and no answer yet? */
		if (event->state == FAN_EVENT_REPORTED) {
			/* Event will get freed once userspace answers to it */
			event->state = FAN_EVENT_CANCELED;
			spin_unlock(&group->notification_lock);
			return ret;
		}
		/* Event not yet reported? Just remove it. */
		if (event->state == FAN_EVENT_INIT) {
			fsnotify_remove_queued_event(group, &event->fae.fse);
			/* Permission events are not supposed to be hashed */
			WARN_ON_ONCE(!hlist_unhashed(&event->fae.merge_list));
		}
		/*
		 * Event may be also answered in case signal delivery raced
		 * with wakeup. In that case we have nothing to do besides
		 * freeing the event and reporting error.
		 */
		spin_unlock(&group->notification_lock);
		goto out;
	}

	/* userspace responded, convert to something usable */
	switch (event->response & ~FAN_AUDIT) {
	case FAN_ALLOW:
		ret = 0;
		break;
	case FAN_DENY:
	default:
		ret = -EPERM;
	}

	/* Check if the response should be audited */
	if (event->response & FAN_AUDIT)
		audit_fanotify(event->response & ~FAN_AUDIT);

	pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
		 group, event, ret);
out:
	fsnotify_destroy_event(group, &event->fae.fse);

	return ret;
}

/*
 * This function returns a mask for an event that only contains the flags
 * that have been specifically requested by the user. Flags that may have
 * been included within the event mask, but have not been explicitly
 * requested by the user, will not be present in the returned mask.
 */
static u32 fanotify_group_event_mask(struct fsnotify_group *group,
				     struct fsnotify_iter_info *iter_info,
				     u32 *match_mask, u32 event_mask,
				     const void *data, int data_type,
				     struct inode *dir)
{
	__u32 marks_mask = 0, marks_ignore_mask = 0;
	__u32 test_mask, user_mask = FANOTIFY_OUTGOING_EVENTS |
				     FANOTIFY_EVENT_FLAGS;
	const struct path *path = fsnotify_data_path(data, data_type);
	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
	struct fsnotify_mark *mark;
	bool ondir = event_mask & FAN_ONDIR;
	int type;

	pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
		 __func__, iter_info->report_mask, event_mask, data, data_type);

	if (!fid_mode) {
		/* Do we have path to open a file descriptor? */
		if (!path)
			return 0;
		/* Path type events are only relevant for files and dirs */
		if (!d_is_reg(path->dentry) && !d_can_lookup(path->dentry))
			return 0;
	} else if (!(fid_mode & FAN_REPORT_FID)) {
		/* Do we have a directory inode to report? */
		if (!dir && !ondir)
			return 0;
	}

	fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
		/*
		 * Apply ignore mask depending on event flags in ignore mask.
		 */
		marks_ignore_mask |=
			fsnotify_effective_ignore_mask(mark, ondir, type);

		/*
		 * Send the event depending on event flags in mark mask.
		 */
		if (!fsnotify_mask_applicable(mark->mask, ondir, type))
			continue;

		marks_mask |= mark->mask;

		/* Record the mark types of this group that matched the event */
		*match_mask |= 1U << type;
	}

	test_mask = event_mask & marks_mask & ~marks_ignore_mask;

	/*
	 * For dirent modification events (create/delete/move) that do not carry
	 * the child entry name information, we report FAN_ONDIR for mkdir/rmdir
	 * so user can differentiate them from creat/unlink.
	 *
	 * For backward compatibility and consistency, do not report FAN_ONDIR
	 * to user in legacy fanotify mode (reporting fd) and report FAN_ONDIR
	 * to user in fid mode for all event types.
	 *
	 * We never report FAN_EVENT_ON_CHILD to user, but we do pass it in to
	 * fanotify_alloc_event() when group is reporting fid as indication
	 * that event happened on child.
	 */
	if (fid_mode) {
		/* Do not report event flags without any event */
		if (!(test_mask & ~FANOTIFY_EVENT_FLAGS))
			return 0;
	} else {
		user_mask &= ~FANOTIFY_EVENT_FLAGS;
	}

	return test_mask & user_mask;
}

/*
 * Check size needed to encode fanotify_fh.
 *
 * Return size of encoded fh without fanotify_fh header.
 * Return 0 on failure to encode.
 */
static int fanotify_encode_fh_len(struct inode *inode)
{
	int dwords = 0;
	int fh_len;

	if (!inode)
		return 0;

	exportfs_encode_inode_fh(inode, NULL, &dwords, NULL);
	fh_len = dwords << 2;

	/*
	 * struct fanotify_error_event might be preallocated and is
	 * limited to MAX_HANDLE_SZ.  This should never happen, but
	 * safeguard by forcing an invalid file handle.
	 */
	if (WARN_ON_ONCE(fh_len > MAX_HANDLE_SZ))
		return 0;

	return fh_len;
}

/*
 * Encode fanotify_fh.
 *
 * Return total size of encoded fh including fanotify_fh header.
 * Return 0 on failure to encode.
 */
static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
			      unsigned int fh_len, unsigned int *hash,
			      gfp_t gfp)
{
	int dwords, type = 0;
	char *ext_buf = NULL;
	void *buf = fh->buf;
	int err;

	fh->type = FILEID_ROOT;
	fh->len = 0;
	fh->flags = 0;

	/*
	 * Invalid FHs are used by FAN_FS_ERROR for errors not
	 * linked to any inode. The f_handle won't be reported
	 * back to userspace.
	 */
	if (!inode)
		goto out;

	/*
	 * !gpf means preallocated variable size fh, but fh_len could
	 * be zero in that case if encoding fh len failed.
	 */
	err = -ENOENT;
	if (fh_len < 4 || WARN_ON_ONCE(fh_len % 4) || fh_len > MAX_HANDLE_SZ)
		goto out_err;

	/* No external buffer in a variable size allocated fh */
	if (gfp && fh_len > FANOTIFY_INLINE_FH_LEN) {
		/* Treat failure to allocate fh as failure to encode fh */
		err = -ENOMEM;
		ext_buf = kmalloc(fh_len, gfp);
		if (!ext_buf)
			goto out_err;

		*fanotify_fh_ext_buf_ptr(fh) = ext_buf;
		buf = ext_buf;
		fh->flags |= FANOTIFY_FH_FLAG_EXT_BUF;
	}

	dwords = fh_len >> 2;
	type = exportfs_encode_inode_fh(inode, buf, &dwords, NULL);
	err = -EINVAL;
	if (!type || type == FILEID_INVALID || fh_len != dwords << 2)
		goto out_err;

	fh->type = type;
	fh->len = fh_len;

out:
	/*
	 * Mix fh into event merge key.  Hash might be NULL in case of
	 * unhashed FID events (i.e. FAN_FS_ERROR).
	 */
	if (hash)
		*hash ^= fanotify_hash_fh(fh);

	return FANOTIFY_FH_HDR_LEN + fh_len;

out_err:
	pr_warn_ratelimited("fanotify: failed to encode fid (type=%d, len=%d, err=%i)\n",
			    type, fh_len, err);
	kfree(ext_buf);
	*fanotify_fh_ext_buf_ptr(fh) = NULL;
	/* Report the event without a file identifier on encode error */
	fh->type = FILEID_INVALID;
	fh->len = 0;
	return 0;
}

/*
 * FAN_REPORT_FID is ambiguous in that it reports the fid of the child for
 * some events and the fid of the parent for create/delete/move events.
 *
 * With the FAN_REPORT_TARGET_FID flag, the fid of the child is reported
 * also in create/delete/move events in addition to the fid of the parent
 * and the name of the child.
 */
static inline bool fanotify_report_child_fid(unsigned int fid_mode, u32 mask)
{
	if (mask & ALL_FSNOTIFY_DIRENT_EVENTS)
		return (fid_mode & FAN_REPORT_TARGET_FID);

	return (fid_mode & FAN_REPORT_FID) && !(mask & FAN_ONDIR);
}

/*
 * The inode to use as identifier when reporting fid depends on the event
 * and the group flags.
 *
 * With the group flag FAN_REPORT_TARGET_FID, always report the child fid.
 *
 * Without the group flag FAN_REPORT_TARGET_FID, report the modified directory
 * fid on dirent events and the child fid otherwise.
 *
 * For example:
 * FS_ATTRIB reports the child fid even if reported on a watched parent.
 * FS_CREATE reports the modified dir fid without FAN_REPORT_TARGET_FID.
 *       and reports the created child fid with FAN_REPORT_TARGET_FID.
 */
static struct inode *fanotify_fid_inode(u32 event_mask, const void *data,
					int data_type, struct inode *dir,
					unsigned int fid_mode)
{
	if ((event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) &&
	    !(fid_mode & FAN_REPORT_TARGET_FID))
		return dir;

	return fsnotify_data_inode(data, data_type);
}

/*
 * The inode to use as identifier when reporting dir fid depends on the event.
 * Report the modified directory inode on dirent modification events.
 * Report the "victim" inode if "victim" is a directory.
 * Report the parent inode if "victim" is not a directory and event is
 * reported to parent.
 * Otherwise, do not report dir fid.
 */
static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data,
					 int data_type, struct inode *dir)
{
	struct inode *inode = fsnotify_data_inode(data, data_type);

	if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS)
		return dir;

	if (inode && S_ISDIR(inode->i_mode))
		return inode;

	return dir;
}

static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
							unsigned int *hash,
							gfp_t gfp)
{
	struct fanotify_path_event *pevent;

	pevent = kmem_cache_alloc(fanotify_path_event_cachep, gfp);
	if (!pevent)
		return NULL;

	pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH;
	pevent->path = *path;
	*hash ^= fanotify_hash_path(path);
	path_get(path);

	return &pevent->fae;
}

static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path,
							gfp_t gfp)
{
	struct fanotify_perm_event *pevent;

	pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
	if (!pevent)
		return NULL;

	pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH_PERM;
	pevent->response = 0;
	pevent->state = FAN_EVENT_INIT;
	pevent->path = *path;
	path_get(path);

	return &pevent->fae;
}

static struct fanotify_event *fanotify_alloc_fid_event(struct inode *id,
						       __kernel_fsid_t *fsid,
						       unsigned int *hash,
						       gfp_t gfp)
{
	struct fanotify_fid_event *ffe;

	ffe = kmem_cache_alloc(fanotify_fid_event_cachep, gfp);
	if (!ffe)
		return NULL;

	ffe->fae.type = FANOTIFY_EVENT_TYPE_FID;
	ffe->fsid = *fsid;
	*hash ^= fanotify_hash_fsid(fsid);
	fanotify_encode_fh(&ffe->object_fh, id, fanotify_encode_fh_len(id),
			   hash, gfp);

	return &ffe->fae;
}

static struct fanotify_event *fanotify_alloc_name_event(struct inode *dir,
							__kernel_fsid_t *fsid,
							const struct qstr *name,
							struct inode *child,
							struct dentry *moved,
							unsigned int *hash,
							gfp_t gfp)
{
	struct fanotify_name_event *fne;
	struct fanotify_info *info;
	struct fanotify_fh *dfh, *ffh;
	struct inode *dir2 = moved ? d_inode(moved->d_parent) : NULL;
	const struct qstr *name2 = moved ? &moved->d_name : NULL;
	unsigned int dir_fh_len = fanotify_encode_fh_len(dir);
	unsigned int dir2_fh_len = fanotify_encode_fh_len(dir2);
	unsigned int child_fh_len = fanotify_encode_fh_len(child);
	unsigned long name_len = name ? name->len : 0;
	unsigned long name2_len = name2 ? name2->len : 0;
	unsigned int len, size;

	/* Reserve terminating null byte even for empty name */
	size = sizeof(*fne) + name_len + name2_len + 2;
	if (dir_fh_len)
		size += FANOTIFY_FH_HDR_LEN + dir_fh_len;
	if (dir2_fh_len)
		size += FANOTIFY_FH_HDR_LEN + dir2_fh_len;
	if (child_fh_len)
		size += FANOTIFY_FH_HDR_LEN + child_fh_len;
	fne = kmalloc(size, gfp);
	if (!fne)
		return NULL;

	fne->fae.type = FANOTIFY_EVENT_TYPE_FID_NAME;
	fne->fsid = *fsid;
	*hash ^= fanotify_hash_fsid(fsid);
	info = &fne->info;
	fanotify_info_init(info);
	if (dir_fh_len) {
		dfh = fanotify_info_dir_fh(info);
		len = fanotify_encode_fh(dfh, dir, dir_fh_len, hash, 0);
		fanotify_info_set_dir_fh(info, len);
	}
	if (dir2_fh_len) {
		dfh = fanotify_info_dir2_fh(info);
		len = fanotify_encode_fh(dfh, dir2, dir2_fh_len, hash, 0);
		fanotify_info_set_dir2_fh(info, len);
	}
	if (child_fh_len) {
		ffh = fanotify_info_file_fh(info);
		len = fanotify_encode_fh(ffh, child, child_fh_len, hash, 0);
		fanotify_info_set_file_fh(info, len);
	}
	if (name_len) {
		fanotify_info_copy_name(info, name);
		*hash ^= full_name_hash((void *)name_len, name->name, name_len);
	}
	if (name2_len) {
		fanotify_info_copy_name2(info, name2);
		*hash ^= full_name_hash((void *)name2_len, name2->name,
					name2_len);
	}

	pr_debug("%s: size=%u dir_fh_len=%u child_fh_len=%u name_len=%u name='%.*s'\n",
		 __func__, size, dir_fh_len, child_fh_len,
		 info->name_len, info->name_len, fanotify_info_name(info));

	if (dir2_fh_len) {
		pr_debug("%s: dir2_fh_len=%u name2_len=%u name2='%.*s'\n",
			 __func__, dir2_fh_len, info->name2_len,
			 info->name2_len, fanotify_info_name2(info));
	}

	return &fne->fae;
}

static struct fanotify_event *fanotify_alloc_error_event(
						struct fsnotify_group *group,
						__kernel_fsid_t *fsid,
						const void *data, int data_type,
						unsigned int *hash)
{
	struct fs_error_report *report =
			fsnotify_data_error_report(data, data_type);
	struct inode *inode;
	struct fanotify_error_event *fee;
	int fh_len;

	if (WARN_ON_ONCE(!report))
		return NULL;

	fee = mempool_alloc(&group->fanotify_data.error_events_pool, GFP_NOFS);
	if (!fee)
		return NULL;

	fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR;
	fee->error = report->error;
	fee->err_count = 1;
	fee->fsid = *fsid;

	inode = report->inode;
	fh_len = fanotify_encode_fh_len(inode);

	/* Bad fh_len. Fallback to using an invalid fh. Should never happen. */
	if (!fh_len && inode)
		inode = NULL;

	fanotify_encode_fh(&fee->object_fh, inode, fh_len, NULL, 0);

	*hash ^= fanotify_hash_fsid(fsid);

	return &fee->fae;
}

static struct fanotify_event *fanotify_alloc_event(
				struct fsnotify_group *group,
				u32 mask, const void *data, int data_type,
				struct inode *dir, const struct qstr *file_name,
				__kernel_fsid_t *fsid, u32 match_mask)
{
	struct fanotify_event *event = NULL;
	gfp_t gfp = GFP_KERNEL_ACCOUNT;
	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
	struct inode *id = fanotify_fid_inode(mask, data, data_type, dir,
					      fid_mode);
	struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir);
	const struct path *path = fsnotify_data_path(data, data_type);
	struct mem_cgroup *old_memcg;
	struct dentry *moved = NULL;
	struct inode *child = NULL;
	bool name_event = false;
	unsigned int hash = 0;
	bool ondir = mask & FAN_ONDIR;
	struct pid *pid;

	if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) {
		/*
		 * For certain events and group flags, report the child fid
		 * in addition to reporting the parent fid and maybe child name.
		 */
		if (fanotify_report_child_fid(fid_mode, mask) && id != dirid)
			child = id;

		id = dirid;

		/*
		 * We record file name only in a group with FAN_REPORT_NAME
		 * and when we have a directory inode to report.
		 *
		 * For directory entry modification event, we record the fid of
		 * the directory and the name of the modified entry.
		 *
		 * For event on non-directory that is reported to parent, we
		 * record the fid of the parent and the name of the child.
		 *
		 * Even if not reporting name, we need a variable length
		 * fanotify_name_event if reporting both parent and child fids.
		 */
		if (!(fid_mode & FAN_REPORT_NAME)) {
			name_event = !!child;
			file_name = NULL;
		} else if ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) || !ondir) {
			name_event = true;
		}

		/*
		 * In the special case of FAN_RENAME event, use the match_mask
		 * to determine if we need to report only the old parent+name,
		 * only the new parent+name or both.
		 * 'dirid' and 'file_name' are the old parent+name and
		 * 'moved' has the new parent+name.
		 */
		if (mask & FAN_RENAME) {
			bool report_old, report_new;

			if (WARN_ON_ONCE(!match_mask))
				return NULL;

			/* Report both old and new parent+name if sb watching */
			report_old = report_new =
				match_mask & (1U << FSNOTIFY_ITER_TYPE_SB);
			report_old |=
				match_mask & (1U << FSNOTIFY_ITER_TYPE_INODE);
			report_new |=
				match_mask & (1U << FSNOTIFY_ITER_TYPE_INODE2);

			if (!report_old) {
				/* Do not report old parent+name */
				dirid = NULL;
				file_name = NULL;
			}
			if (report_new) {
				/* Report new parent+name */
				moved = fsnotify_data_dentry(data, data_type);
			}
		}
	}

	/*
	 * For queues with unlimited length lost events are not expected and
	 * can possibly have security implications. Avoid losing events when
	 * memory is short. For the limited size queues, avoid OOM killer in the
	 * target monitoring memcg as it may have security repercussion.
	 */
	if (group->max_events == UINT_MAX)
		gfp |= __GFP_NOFAIL;
	else
		gfp |= __GFP_RETRY_MAYFAIL;

	/* Whoever is interested in the event, pays for the allocation. */
	old_memcg = set_active_memcg(group->memcg);

	if (fanotify_is_perm_event(mask)) {
		event = fanotify_alloc_perm_event(path, gfp);
	} else if (fanotify_is_error_event(mask)) {
		event = fanotify_alloc_error_event(group, fsid, data,
						   data_type, &hash);
	} else if (name_event && (file_name || moved || child)) {
		event = fanotify_alloc_name_event(dirid, fsid, file_name, child,
						  moved, &hash, gfp);
	} else if (fid_mode) {
		event = fanotify_alloc_fid_event(id, fsid, &hash, gfp);
	} else {
		event = fanotify_alloc_path_event(path, &hash, gfp);
	}

	if (!event)
		goto out;

	if (FAN_GROUP_FLAG(group, FAN_REPORT_TID))
		pid = get_pid(task_pid(current));
	else
		pid = get_pid(task_tgid(current));

	/* Mix event info, FAN_ONDIR flag and pid into event merge key */
	hash ^= hash_long((unsigned long)pid | ondir, FANOTIFY_EVENT_HASH_BITS);
	fanotify_init_event(event, hash, mask);
	event->pid = pid;

out:
	set_active_memcg(old_memcg);
	return event;
}

/*
 * Get cached fsid of the filesystem containing the object from any connector.
 * All connectors are supposed to have the same fsid, but we do not verify that
 * here.
 */
static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
{
	struct fsnotify_mark *mark;
	int type;
	__kernel_fsid_t fsid = {};

	fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
		struct fsnotify_mark_connector *conn;

		conn = READ_ONCE(mark->connector);
		/* Mark is just getting destroyed or created? */
		if (!conn)
			continue;
		if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID))
			continue;
		/* Pairs with smp_wmb() in fsnotify_add_mark_list() */
		smp_rmb();
		fsid = conn->fsid;
		if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
			continue;
		return fsid;
	}

	return fsid;
}

/*
 * Add an event to hash table for faster merge.
 */
static void fanotify_insert_event(struct fsnotify_group *group,
				  struct fsnotify_event *fsn_event)
{
	struct fanotify_event *event = FANOTIFY_E(fsn_event);
	unsigned int bucket = fanotify_event_hash_bucket(group, event);
	struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];

	assert_spin_locked(&group->notification_lock);

	if (!fanotify_is_hashed_event(event->mask))
		return;

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

	hlist_add_head(&event->merge_list, hlist);
}

static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
				 const void *data, int data_type,
				 struct inode *dir,
				 const struct qstr *file_name, u32 cookie,
				 struct fsnotify_iter_info *iter_info)
{
	int ret = 0;
	struct fanotify_event *event;
	struct fsnotify_event *fsn_event;
	__kernel_fsid_t fsid = {};
	u32 match_mask = 0;

	BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS);
	BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY);
	BUILD_BUG_ON(FAN_ATTRIB != FS_ATTRIB);
	BUILD_BUG_ON(FAN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
	BUILD_BUG_ON(FAN_CLOSE_WRITE != FS_CLOSE_WRITE);
	BUILD_BUG_ON(FAN_OPEN != FS_OPEN);
	BUILD_BUG_ON(FAN_MOVED_TO != FS_MOVED_TO);
	BUILD_BUG_ON(FAN_MOVED_FROM != FS_MOVED_FROM);
	BUILD_BUG_ON(FAN_CREATE != FS_CREATE);
	BUILD_BUG_ON(FAN_DELETE != FS_DELETE);
	BUILD_BUG_ON(FAN_DELETE_SELF != FS_DELETE_SELF);
	BUILD_BUG_ON(FAN_MOVE_SELF != FS_MOVE_SELF);
	BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD);
	BUILD_BUG_ON(FAN_Q_OVERFLOW != FS_Q_OVERFLOW);
	BUILD_BUG_ON(FAN_OPEN_PERM != FS_OPEN_PERM);
	BUILD_BUG_ON(FAN_ACCESS_PERM != FS_ACCESS_PERM);
	BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR);
	BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC);
	BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
	BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR);
	BUILD_BUG_ON(FAN_RENAME != FS_RENAME);

	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21);

	mask = fanotify_group_event_mask(group, iter_info, &match_mask,
					 mask, data, data_type, dir);
	if (!mask)
		return 0;

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

	if (fanotify_is_perm_event(mask)) {
		/*
		 * fsnotify_prepare_user_wait() fails if we race with mark
		 * deletion.  Just let the operation pass in that case.
		 */
		if (!fsnotify_prepare_user_wait(iter_info))
			return 0;
	}

	if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS)) {
		fsid = fanotify_get_fsid(iter_info);
		/* Racing with mark destruction or creation? */
		if (!fsid.val[0] && !fsid.val[1])
			return 0;
	}

	event = fanotify_alloc_event(group, mask, data, data_type, dir,
				     file_name, &fsid, match_mask);
	ret = -ENOMEM;
	if (unlikely(!event)) {
		/*
		 * We don't queue overflow events for permission events as
		 * there the access is denied and so no event is in fact lost.
		 */
		if (!fanotify_is_perm_event(mask))
			fsnotify_queue_overflow(group);
		goto finish;
	}

	fsn_event = &event->fse;
	ret = fsnotify_insert_event(group, fsn_event, fanotify_merge,
				    fanotify_insert_event);
	if (ret) {
		/* Permission events shouldn't be merged */
		BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS);
		/* Our event wasn't used in the end. Free it. */
		fsnotify_destroy_event(group, fsn_event);

		ret = 0;
	} else if (fanotify_is_perm_event(mask)) {
		ret = fanotify_get_response(group, FANOTIFY_PERM(event),
					    iter_info);
	}
finish:
	if (fanotify_is_perm_event(mask))
		fsnotify_finish_user_wait(iter_info);

	return ret;
}

static void fanotify_free_group_priv(struct fsnotify_group *group)
{
	kfree(group->fanotify_data.merge_hash);
	if (group->fanotify_data.ucounts)
		dec_ucount(group->fanotify_data.ucounts,
			   UCOUNT_FANOTIFY_GROUPS);

	if (mempool_initialized(&group->fanotify_data.error_events_pool))
		mempool_exit(&group->fanotify_data.error_events_pool);
}

static void fanotify_free_path_event(struct fanotify_event *event)
{
	path_put(fanotify_event_path(event));
	kmem_cache_free(fanotify_path_event_cachep, FANOTIFY_PE(event));
}

static void fanotify_free_perm_event(struct fanotify_event *event)
{
	path_put(fanotify_event_path(event));
	kmem_cache_free(fanotify_perm_event_cachep, FANOTIFY_PERM(event));
}

static void fanotify_free_fid_event(struct fanotify_event *event)
{
	struct fanotify_fid_event *ffe = FANOTIFY_FE(event);

	if (fanotify_fh_has_ext_buf(&ffe->object_fh))
		kfree(fanotify_fh_ext_buf(&ffe->object_fh));
	kmem_cache_free(fanotify_fid_event_cachep, ffe);
}

static void fanotify_free_name_event(struct fanotify_event *event)
{
	kfree(FANOTIFY_NE(event));
}

static void fanotify_free_error_event(struct fsnotify_group *group,
				      struct fanotify_event *event)
{
	struct fanotify_error_event *fee = FANOTIFY_EE(event);

	mempool_free(fee, &group->fanotify_data.error_events_pool);
}

static void fanotify_free_event(struct fsnotify_group *group,
				struct fsnotify_event *fsn_event)
{
	struct fanotify_event *event;

	event = FANOTIFY_E(fsn_event);
	put_pid(event->pid);
	switch (event->type) {
	case FANOTIFY_EVENT_TYPE_PATH:
		fanotify_free_path_event(event);
		break;
	case FANOTIFY_EVENT_TYPE_PATH_PERM:
		fanotify_free_perm_event(event);
		break;
	case FANOTIFY_EVENT_TYPE_FID:
		fanotify_free_fid_event(event);
		break;
	case FANOTIFY_EVENT_TYPE_FID_NAME:
		fanotify_free_name_event(event);
		break;
	case FANOTIFY_EVENT_TYPE_OVERFLOW:
		kfree(event);
		break;
	case FANOTIFY_EVENT_TYPE_FS_ERROR:
		fanotify_free_error_event(group, event);
		break;
	default:
		WARN_ON_ONCE(1);
	}
}

static void fanotify_freeing_mark(struct fsnotify_mark *mark,
				  struct fsnotify_group *group)
{
	if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
		dec_ucount(group->fanotify_data.ucounts, UCOUNT_FANOTIFY_MARKS);
}

static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
{
	kmem_cache_free(fanotify_mark_cache, fsn_mark);
}

const struct fsnotify_ops fanotify_fsnotify_ops = {
	.handle_event = fanotify_handle_event,
	.free_group_priv = fanotify_free_group_priv,
	.free_event = fanotify_free_event,
	.freeing_mark = fanotify_freeing_mark,
	.free_mark = fanotify_free_mark,
};