summaryrefslogtreecommitdiff
path: root/fs/notify/fanotify/fanotify_user.c
blob: bd99430a128dc4d0fd28b75ae7ecf753d8322c44 (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
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
// SPDX-License-Identifier: GPL-2.0
#include <linux/fanotify.h>
#include <linux/fcntl.h>
#include <linux/fdtable.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 <linux/statfs.h>
#include <linux/exportfs.h>

#include <asm/ioctls.h>

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

#define FANOTIFY_DEFAULT_MAX_EVENTS	16384
#define FANOTIFY_OLD_DEFAULT_MAX_MARKS	8192
#define FANOTIFY_DEFAULT_MAX_GROUPS	128
#define FANOTIFY_DEFAULT_FEE_POOL_SIZE	32

/*
 * Legacy fanotify marks limits (8192) is per group and we introduced a tunable
 * limit of marks per user, similar to inotify.  Effectively, the legacy limit
 * of fanotify marks per user is <max marks per group> * <max groups per user>.
 * This default limit (1M) also happens to match the increased limit of inotify
 * max_user_watches since v5.10.
 */
#define FANOTIFY_DEFAULT_MAX_USER_MARKS	\
	(FANOTIFY_OLD_DEFAULT_MAX_MARKS * FANOTIFY_DEFAULT_MAX_GROUPS)

/*
 * Most of the memory cost of adding an inode mark is pinning the marked inode.
 * The size of the filesystem inode struct is not uniform across filesystems,
 * so double the size of a VFS inode is used as a conservative approximation.
 */
#define INODE_MARK_COST	(2 * sizeof(struct inode))

/* configurable via /proc/sys/fs/fanotify/ */
static int fanotify_max_queued_events __read_mostly;

#ifdef CONFIG_SYSCTL

#include <linux/sysctl.h>

static long ft_zero = 0;
static long ft_int_max = INT_MAX;

static struct ctl_table fanotify_table[] = {
	{
		.procname	= "max_user_groups",
		.data	= &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS],
		.maxlen		= sizeof(long),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
		.extra1		= &ft_zero,
		.extra2		= &ft_int_max,
	},
	{
		.procname	= "max_user_marks",
		.data	= &init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS],
		.maxlen		= sizeof(long),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
		.extra1		= &ft_zero,
		.extra2		= &ft_int_max,
	},
	{
		.procname	= "max_queued_events",
		.data		= &fanotify_max_queued_events,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= SYSCTL_ZERO
	},
	{ }
};

static void __init fanotify_sysctls_init(void)
{
	register_sysctl("fs/fanotify", fanotify_table);
}
#else
#define fanotify_sysctls_init() do { } while (0)
#endif /* CONFIG_SYSCTL */

/*
 * 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_fid_event_cachep __read_mostly;
struct kmem_cache *fanotify_path_event_cachep __read_mostly;
struct kmem_cache *fanotify_perm_event_cachep __read_mostly;

#define FANOTIFY_EVENT_ALIGN 4
#define FANOTIFY_FID_INFO_HDR_LEN \
	(sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
#define FANOTIFY_PIDFD_INFO_HDR_LEN \
	sizeof(struct fanotify_event_info_pidfd)
#define FANOTIFY_ERROR_INFO_LEN \
	(sizeof(struct fanotify_event_info_error))

static int fanotify_fid_info_len(int fh_len, int name_len)
{
	int info_len = fh_len;

	if (name_len)
		info_len += name_len + 1;

	return roundup(FANOTIFY_FID_INFO_HDR_LEN + info_len,
		       FANOTIFY_EVENT_ALIGN);
}

/* FAN_RENAME may have one or two dir+name info records */
static int fanotify_dir_name_info_len(struct fanotify_event *event)
{
	struct fanotify_info *info = fanotify_event_info(event);
	int dir_fh_len = fanotify_event_dir_fh_len(event);
	int dir2_fh_len = fanotify_event_dir2_fh_len(event);
	int info_len = 0;

	if (dir_fh_len)
		info_len += fanotify_fid_info_len(dir_fh_len,
						  info->name_len);
	if (dir2_fh_len)
		info_len += fanotify_fid_info_len(dir2_fh_len,
						  info->name2_len);

	return info_len;
}

static size_t fanotify_event_len(unsigned int info_mode,
				 struct fanotify_event *event)
{
	size_t event_len = FAN_EVENT_METADATA_LEN;
	int fh_len;
	int dot_len = 0;

	if (!info_mode)
		return event_len;

	if (fanotify_is_error_event(event->mask))
		event_len += FANOTIFY_ERROR_INFO_LEN;

	if (fanotify_event_has_any_dir_fh(event)) {
		event_len += fanotify_dir_name_info_len(event);
	} else if ((info_mode & FAN_REPORT_NAME) &&
		   (event->mask & FAN_ONDIR)) {
		/*
		 * With group flag FAN_REPORT_NAME, if name was not recorded in
		 * event on a directory, we will report the name ".".
		 */
		dot_len = 1;
	}

	if (info_mode & FAN_REPORT_PIDFD)
		event_len += FANOTIFY_PIDFD_INFO_HDR_LEN;

	if (fanotify_event_has_object_fh(event)) {
		fh_len = fanotify_event_object_fh_len(event);
		event_len += fanotify_fid_info_len(fh_len, dot_len);
	}

	return event_len;
}

/*
 * Remove an hashed event from merge hash table.
 */
static void fanotify_unhash_event(struct fsnotify_group *group,
				  struct fanotify_event *event)
{
	assert_spin_locked(&group->notification_lock);

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

	if (WARN_ON_ONCE(hlist_unhashed(&event->merge_list)))
		return;

	hlist_del_init(&event->merge_list);
}

/*
 * Get an fanotify notification event if one exists and is small
 * enough to fit in "count". Return an error pointer if the count
 * is not large enough. When permission event is dequeued, its state is
 * updated accordingly.
 */
static struct fanotify_event *get_one_event(struct fsnotify_group *group,
					    size_t count)
{
	size_t event_size;
	struct fanotify_event *event = NULL;
	struct fsnotify_event *fsn_event;
	unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);

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

	spin_lock(&group->notification_lock);
	fsn_event = fsnotify_peek_first_event(group);
	if (!fsn_event)
		goto out;

	event = FANOTIFY_E(fsn_event);
	event_size = fanotify_event_len(info_mode, event);

	if (event_size > count) {
		event = ERR_PTR(-EINVAL);
		goto out;
	}

	/*
	 * Held the notification_lock the whole time, so this is the
	 * same event we peeked above.
	 */
	fsnotify_remove_first_event(group);
	if (fanotify_is_perm_event(event->mask))
		FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED;
	if (fanotify_is_hashed_event(event->mask))
		fanotify_unhash_event(group, event);
out:
	spin_unlock(&group->notification_lock);
	return event;
}

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

	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.
	 */
	new_file = dentry_open(path,
			       group->fanotify_data.f_flags | FMODE_NONOTIFY,
			       current_cred());
	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;
}

/*
 * Finish processing of permission event by setting it to ANSWERED state and
 * drop group->notification_lock.
 */
static void finish_permission_event(struct fsnotify_group *group,
				    struct fanotify_perm_event *event,
				    unsigned int response)
				    __releases(&group->notification_lock)
{
	bool destroy = false;

	assert_spin_locked(&group->notification_lock);
	event->response = response;
	if (event->state == FAN_EVENT_CANCELED)
		destroy = true;
	else
		event->state = FAN_EVENT_ANSWERED;
	spin_unlock(&group->notification_lock);
	if (destroy)
		fsnotify_destroy_event(group, &event->fae.fse);
}

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;

	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);
		finish_permission_event(group, event, response);
		wake_up(&group->fanotify_data.access_waitq);
		return 0;
	}
	spin_unlock(&group->notification_lock);

	return -ENOENT;
}

static size_t copy_error_info_to_user(struct fanotify_event *event,
				      char __user *buf, int count)
{
	struct fanotify_event_info_error info = { };
	struct fanotify_error_event *fee = FANOTIFY_EE(event);

	info.hdr.info_type = FAN_EVENT_INFO_TYPE_ERROR;
	info.hdr.len = FANOTIFY_ERROR_INFO_LEN;

	if (WARN_ON(count < info.hdr.len))
		return -EFAULT;

	info.error = fee->error;
	info.error_count = fee->err_count;

	if (copy_to_user(buf, &info, sizeof(info)))
		return -EFAULT;

	return info.hdr.len;
}

static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
				 int info_type, const char *name,
				 size_t name_len,
				 char __user *buf, size_t count)
{
	struct fanotify_event_info_fid info = { };
	struct file_handle handle = { };
	unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh_buf;
	size_t fh_len = fh ? fh->len : 0;
	size_t info_len = fanotify_fid_info_len(fh_len, name_len);
	size_t len = info_len;

	pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n",
		 __func__, fh_len, name_len, info_len, count);

	if (WARN_ON_ONCE(len < sizeof(info) || len > count))
		return -EFAULT;

	/*
	 * Copy event info fid header followed by variable sized file handle
	 * and optionally followed by variable sized filename.
	 */
	switch (info_type) {
	case FAN_EVENT_INFO_TYPE_FID:
	case FAN_EVENT_INFO_TYPE_DFID:
		if (WARN_ON_ONCE(name_len))
			return -EFAULT;
		break;
	case FAN_EVENT_INFO_TYPE_DFID_NAME:
	case FAN_EVENT_INFO_TYPE_OLD_DFID_NAME:
	case FAN_EVENT_INFO_TYPE_NEW_DFID_NAME:
		if (WARN_ON_ONCE(!name || !name_len))
			return -EFAULT;
		break;
	default:
		return -EFAULT;
	}

	info.hdr.info_type = info_type;
	info.hdr.len = len;
	info.fsid = *fsid;
	if (copy_to_user(buf, &info, sizeof(info)))
		return -EFAULT;

	buf += sizeof(info);
	len -= sizeof(info);
	if (WARN_ON_ONCE(len < sizeof(handle)))
		return -EFAULT;

	handle.handle_type = fh->type;
	handle.handle_bytes = fh_len;

	/* Mangle handle_type for bad file_handle */
	if (!fh_len)
		handle.handle_type = FILEID_INVALID;

	if (copy_to_user(buf, &handle, sizeof(handle)))
		return -EFAULT;

	buf += sizeof(handle);
	len -= sizeof(handle);
	if (WARN_ON_ONCE(len < fh_len))
		return -EFAULT;

	/*
	 * For an inline fh and inline file name, copy through stack to exclude
	 * the copy from usercopy hardening protections.
	 */
	fh_buf = fanotify_fh_buf(fh);
	if (fh_len <= FANOTIFY_INLINE_FH_LEN) {
		memcpy(bounce, fh_buf, fh_len);
		fh_buf = bounce;
	}
	if (copy_to_user(buf, fh_buf, fh_len))
		return -EFAULT;

	buf += fh_len;
	len -= fh_len;

	if (name_len) {
		/* Copy the filename with terminating null */
		name_len++;
		if (WARN_ON_ONCE(len < name_len))
			return -EFAULT;

		if (copy_to_user(buf, name, name_len))
			return -EFAULT;

		buf += name_len;
		len -= name_len;
	}

	/* Pad with 0's */
	WARN_ON_ONCE(len < 0 || len >= FANOTIFY_EVENT_ALIGN);
	if (len > 0 && clear_user(buf, len))
		return -EFAULT;

	return info_len;
}

static int copy_pidfd_info_to_user(int pidfd,
				   char __user *buf,
				   size_t count)
{
	struct fanotify_event_info_pidfd info = { };
	size_t info_len = FANOTIFY_PIDFD_INFO_HDR_LEN;

	if (WARN_ON_ONCE(info_len > count))
		return -EFAULT;

	info.hdr.info_type = FAN_EVENT_INFO_TYPE_PIDFD;
	info.hdr.len = info_len;
	info.pidfd = pidfd;

	if (copy_to_user(buf, &info, info_len))
		return -EFAULT;

	return info_len;
}

static int copy_info_records_to_user(struct fanotify_event *event,
				     struct fanotify_info *info,
				     unsigned int info_mode, int pidfd,
				     char __user *buf, size_t count)
{
	int ret, total_bytes = 0, info_type = 0;
	unsigned int fid_mode = info_mode & FANOTIFY_FID_BITS;
	unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD;

	/*
	 * Event info records order is as follows:
	 * 1. dir fid + name
	 * 2. (optional) new dir fid + new name
	 * 3. (optional) child fid
	 */
	if (fanotify_event_has_dir_fh(event)) {
		info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
					     FAN_EVENT_INFO_TYPE_DFID;

		/* FAN_RENAME uses special info types */
		if (event->mask & FAN_RENAME)
			info_type = FAN_EVENT_INFO_TYPE_OLD_DFID_NAME;

		ret = copy_fid_info_to_user(fanotify_event_fsid(event),
					    fanotify_info_dir_fh(info),
					    info_type,
					    fanotify_info_name(info),
					    info->name_len, buf, count);
		if (ret < 0)
			return ret;

		buf += ret;
		count -= ret;
		total_bytes += ret;
	}

	/* New dir fid+name may be reported in addition to old dir fid+name */
	if (fanotify_event_has_dir2_fh(event)) {
		info_type = FAN_EVENT_INFO_TYPE_NEW_DFID_NAME;
		ret = copy_fid_info_to_user(fanotify_event_fsid(event),
					    fanotify_info_dir2_fh(info),
					    info_type,
					    fanotify_info_name2(info),
					    info->name2_len, buf, count);
		if (ret < 0)
			return ret;

		buf += ret;
		count -= ret;
		total_bytes += ret;
	}

	if (fanotify_event_has_object_fh(event)) {
		const char *dot = NULL;
		int dot_len = 0;

		if (fid_mode == FAN_REPORT_FID || info_type) {
			/*
			 * With only group flag FAN_REPORT_FID only type FID is
			 * reported. Second info record type is always FID.
			 */
			info_type = FAN_EVENT_INFO_TYPE_FID;
		} else if ((fid_mode & FAN_REPORT_NAME) &&
			   (event->mask & FAN_ONDIR)) {
			/*
			 * With group flag FAN_REPORT_NAME, if name was not
			 * recorded in an event on a directory, report the name
			 * "." with info type DFID_NAME.
			 */
			info_type = FAN_EVENT_INFO_TYPE_DFID_NAME;
			dot = ".";
			dot_len = 1;
		} else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
			   (event->mask & FAN_ONDIR)) {
			/*
			 * With group flag FAN_REPORT_DIR_FID, a single info
			 * record has type DFID for directory entry modification
			 * event and for event on a directory.
			 */
			info_type = FAN_EVENT_INFO_TYPE_DFID;
		} else {
			/*
			 * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID,
			 * a single info record has type FID for event on a
			 * non-directory, when there is no directory to report.
			 * For example, on FAN_DELETE_SELF event.
			 */
			info_type = FAN_EVENT_INFO_TYPE_FID;
		}

		ret = copy_fid_info_to_user(fanotify_event_fsid(event),
					    fanotify_event_object_fh(event),
					    info_type, dot, dot_len,
					    buf, count);
		if (ret < 0)
			return ret;

		buf += ret;
		count -= ret;
		total_bytes += ret;
	}

	if (pidfd_mode) {
		ret = copy_pidfd_info_to_user(pidfd, buf, count);
		if (ret < 0)
			return ret;

		buf += ret;
		count -= ret;
		total_bytes += ret;
	}

	if (fanotify_is_error_event(event->mask)) {
		ret = copy_error_info_to_user(event, buf, count);
		if (ret < 0)
			return ret;
		buf += ret;
		count -= ret;
		total_bytes += ret;
	}

	return total_bytes;
}

static ssize_t copy_event_to_user(struct fsnotify_group *group,
				  struct fanotify_event *event,
				  char __user *buf, size_t count)
{
	struct fanotify_event_metadata metadata;
	struct path *path = fanotify_event_path(event);
	struct fanotify_info *info = fanotify_event_info(event);
	unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);
	unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD;
	struct file *f = NULL;
	int ret, pidfd = FAN_NOPIDFD, fd = FAN_NOFD;

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

	metadata.event_len = fanotify_event_len(info_mode, event);
	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);
	/*
	 * For an unprivileged listener, event->pid can be used to identify the
	 * events generated by the listener process itself, without disclosing
	 * the pids of other processes.
	 */
	if (FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
	    task_tgid(current) != event->pid)
		metadata.pid = 0;

	/*
	 * For now, fid mode is required for an unprivileged listener and
	 * fid mode does not report fd in events.  Keep this check anyway
	 * for safety in case fid mode requirement is relaxed in the future
	 * to allow unprivileged listener to get events with no fd and no fid.
	 */
	if (!FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
	    path && path->mnt && path->dentry) {
		fd = create_fd(group, path, &f);
		if (fd < 0)
			return fd;
	}
	metadata.fd = fd;

	if (pidfd_mode) {
		/*
		 * Complain if the FAN_REPORT_PIDFD and FAN_REPORT_TID mutual
		 * exclusion is ever lifted. At the time of incoporating pidfd
		 * support within fanotify, the pidfd API only supported the
		 * creation of pidfds for thread-group leaders.
		 */
		WARN_ON_ONCE(FAN_GROUP_FLAG(group, FAN_REPORT_TID));

		/*
		 * The PIDTYPE_TGID check for an event->pid is performed
		 * preemptively in an attempt to catch out cases where the event
		 * listener reads events after the event generating process has
		 * already terminated. Report FAN_NOPIDFD to the event listener
		 * in those cases, with all other pidfd creation errors being
		 * reported as FAN_EPIDFD.
		 */
		if (metadata.pid == 0 ||
		    !pid_has_task(event->pid, PIDTYPE_TGID)) {
			pidfd = FAN_NOPIDFD;
		} else {
			pidfd = pidfd_create(event->pid, 0);
			if (pidfd < 0)
				pidfd = FAN_EPIDFD;
		}
	}

	ret = -EFAULT;
	/*
	 * Sanity check copy size in case get_one_event() and
	 * event_len sizes ever get out of sync.
	 */
	if (WARN_ON_ONCE(metadata.event_len > count))
		goto out_close_fd;

	if (copy_to_user(buf, &metadata, FAN_EVENT_METADATA_LEN))
		goto out_close_fd;

	buf += FAN_EVENT_METADATA_LEN;
	count -= FAN_EVENT_METADATA_LEN;

	if (fanotify_is_perm_event(event->mask))
		FANOTIFY_PERM(event)->fd = fd;

	if (info_mode) {
		ret = copy_info_records_to_user(event, info, info_mode, pidfd,
						buf, count);
		if (ret < 0)
			goto out_close_fd;
	}

	if (f)
		fd_install(fd, f);

	return metadata.event_len;

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

	if (pidfd >= 0)
		close_fd(pidfd);

	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 fanotify_event *event;
	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) {
		/*
		 * User can supply arbitrarily large buffer. Avoid softlockups
		 * in case there are lots of available events.
		 */
		cond_resched();
		event = get_one_event(group, count);
		if (IS_ERR(event)) {
			ret = PTR_ERR(event);
			break;
		}

		if (!event) {
			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, event, 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(event->mask)) {
			fsnotify_destroy_event(group, &event->fse);
		} else {
			if (ret <= 0) {
				spin_lock(&group->notification_lock);
				finish_permission_event(group,
					FANOTIFY_PERM(event), FAN_DENY);
				wake_up(&group->fanotify_data.access_waitq);
			} else {
				spin_lock(&group->notification_lock);
				list_add_tail(&event->fse.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))
		return -EINVAL;

	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 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);
	while (!list_empty(&group->fanotify_data.access_list)) {
		struct fanotify_perm_event *event;

		event = list_first_entry(&group->fanotify_data.access_list,
				struct fanotify_perm_event, fae.fse.list);
		list_del_init(&event->fae.fse.list);
		finish_permission_event(group, event, FAN_ALLOW);
		spin_lock(&group->notification_lock);
	}

	/*
	 * 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 ((fsn_event = fsnotify_remove_first_event(group))) {
		struct fanotify_event *event = FANOTIFY_E(fsn_event);

		if (!(event->mask & FANOTIFY_PERM_EVENTS)) {
			spin_unlock(&group->notification_lock);
			fsnotify_destroy_event(group, fsn_event);
		} else {
			finish_permission_event(group, FANOTIFY_PERM(event),
						FAN_ALLOW);
		}
		spin_lock(&group->notification_lock);
	}
	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	= compat_ptr_ioctl,
	.llseek		= noop_llseek,
};

static int fanotify_find_path(int dfd, const char __user *filename,
			      struct path *path, unsigned int flags, __u64 mask,
			      unsigned int obj_type)
{
	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 = path_permission(path, MAY_READ);
	if (ret) {
		path_put(path);
		goto out;
	}

	ret = security_path_notify(path, mask, obj_type);
	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,
					    __u32 umask, int *destroy)
{
	__u32 oldmask, newmask;

	/* umask bits cannot be removed by user */
	mask &= ~umask;
	spin_lock(&fsn_mark->lock);
	oldmask = fsnotify_calc_mask(fsn_mark);
	if (!(flags & FAN_MARK_IGNORED_MASK)) {
		fsn_mark->mask &= ~mask;
	} else {
		fsn_mark->ignored_mask &= ~mask;
	}
	newmask = fsnotify_calc_mask(fsn_mark);
	/*
	 * We need to keep the mark around even if remaining mask cannot
	 * result in any events (e.g. mask == FAN_ONDIR) to support incremenal
	 * changes to the mask.
	 * Destroy mark when only umask bits remain.
	 */
	*destroy = !((fsn_mark->mask | fsn_mark->ignored_mask) & ~umask);
	spin_unlock(&fsn_mark->lock);

	return oldmask & ~newmask;
}

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

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

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

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

	spin_lock(&fsn_mark->lock);
	oldmask = fsnotify_calc_mask(fsn_mark);
	if (!(flags & FAN_MARK_IGNORED_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;
	}
	newmask = fsnotify_calc_mask(fsn_mark);
	spin_unlock(&fsn_mark->lock);

	return newmask & ~oldmask;
}

static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
						   fsnotify_connp_t *connp,
						   unsigned int obj_type,
						   __kernel_fsid_t *fsid)
{
	struct ucounts *ucounts = group->fanotify_data.ucounts;
	struct fsnotify_mark *mark;
	int ret;

	/*
	 * Enforce per user marks limits per user in all containing user ns.
	 * A group with FAN_UNLIMITED_MARKS does not contribute to mark count
	 * in the limited groups account.
	 */
	if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS) &&
	    !inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_FANOTIFY_MARKS))
		return ERR_PTR(-ENOSPC);

	mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
	if (!mark) {
		ret = -ENOMEM;
		goto out_dec_ucounts;
	}

	fsnotify_init_mark(mark, group);
	ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0, fsid);
	if (ret) {
		fsnotify_put_mark(mark);
		goto out_dec_ucounts;
	}

	return mark;

out_dec_ucounts:
	if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
		dec_ucount(ucounts, UCOUNT_FANOTIFY_MARKS);
	return ERR_PTR(ret);
}

static int fanotify_group_init_error_pool(struct fsnotify_group *group)
{
	if (mempool_initialized(&group->fanotify_data.error_events_pool))
		return 0;

	return mempool_init_kmalloc_pool(&group->fanotify_data.error_events_pool,
					 FANOTIFY_DEFAULT_FEE_POOL_SIZE,
					 sizeof(struct fanotify_error_event));
}

static int fanotify_add_mark(struct fsnotify_group *group,
			     fsnotify_connp_t *connp, unsigned int obj_type,
			     __u32 mask, unsigned int flags,
			     __kernel_fsid_t *fsid)
{
	struct fsnotify_mark *fsn_mark;
	__u32 added;
	int ret = 0;

	mutex_lock(&group->mark_mutex);
	fsn_mark = fsnotify_find_mark(connp, group);
	if (!fsn_mark) {
		fsn_mark = fanotify_add_new_mark(group, connp, obj_type, fsid);
		if (IS_ERR(fsn_mark)) {
			mutex_unlock(&group->mark_mutex);
			return PTR_ERR(fsn_mark);
		}
	}

	/*
	 * Error events are pre-allocated per group, only if strictly
	 * needed (i.e. FAN_FS_ERROR was requested).
	 */
	if (!(flags & FAN_MARK_IGNORED_MASK) && (mask & FAN_FS_ERROR)) {
		ret = fanotify_group_init_error_pool(group);
		if (ret)
			goto out;
	}

	added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
	if (added & ~fsnotify_conn_mask(fsn_mark->connector))
		fsnotify_recalc_mask(fsn_mark->connector);

out:
	mutex_unlock(&group->mark_mutex);

	fsnotify_put_mark(fsn_mark);
	return ret;
}

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

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

static int fanotify_add_inode_mark(struct fsnotify_group *group,
				   struct inode *inode, __u32 mask,
				   unsigned int flags, __kernel_fsid_t *fsid)
{
	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, fsid);
}

static struct fsnotify_event *fanotify_alloc_overflow_event(void)
{
	struct fanotify_event *oevent;

	oevent = kmalloc(sizeof(*oevent), GFP_KERNEL_ACCOUNT);
	if (!oevent)
		return NULL;

	fanotify_init_event(oevent, 0, FS_Q_OVERFLOW);
	oevent->type = FANOTIFY_EVENT_TYPE_OVERFLOW;

	return &oevent->fse;
}

static struct hlist_head *fanotify_alloc_merge_hash(void)
{
	struct hlist_head *hash;

	hash = kmalloc(sizeof(struct hlist_head) << FANOTIFY_HTABLE_BITS,
		       GFP_KERNEL_ACCOUNT);
	if (!hash)
		return NULL;

	__hash_init(hash, FANOTIFY_HTABLE_SIZE);

	return hash;
}

/* fanotify syscalls */
SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
{
	struct fsnotify_group *group;
	int f_flags, fd;
	unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
	unsigned int class = flags & FANOTIFY_CLASS_BITS;
	unsigned int internal_flags = 0;

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

	if (!capable(CAP_SYS_ADMIN)) {
		/*
		 * An unprivileged user can setup an fanotify group with
		 * limited functionality - an unprivileged group is limited to
		 * notification events with file handles and it cannot use
		 * unlimited queue/marks.
		 */
		if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode)
			return -EPERM;

		/*
		 * Setting the internal flag FANOTIFY_UNPRIV on the group
		 * prevents setting mount/filesystem marks on this group and
		 * prevents reporting pid and open fd in events.
		 */
		internal_flags |= FANOTIFY_UNPRIV;
	}

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

	/*
	 * A pidfd can only be returned for a thread-group leader; thus
	 * FAN_REPORT_PIDFD and FAN_REPORT_TID need to remain mutually
	 * exclusive.
	 */
	if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID))
		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;
	}

	if (fid_mode && class != FAN_CLASS_NOTIF)
		return -EINVAL;

	/*
	 * Child name is reported with parent fid so requires dir fid.
	 * We can report both child fid and dir fid with or without name.
	 */
	if ((fid_mode & FAN_REPORT_NAME) && !(fid_mode & FAN_REPORT_DIR_FID))
		return -EINVAL;

	/*
	 * FAN_REPORT_TARGET_FID requires FAN_REPORT_NAME and FAN_REPORT_FID
	 * and is used as an indication to report both dir and child fid on all
	 * dirent events.
	 */
	if ((fid_mode & FAN_REPORT_TARGET_FID) &&
	    (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID)))
		return -EINVAL;

	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_user_group(&fanotify_fsnotify_ops);
	if (IS_ERR(group)) {
		return PTR_ERR(group);
	}

	/* Enforce groups limits per user in all containing user ns */
	group->fanotify_data.ucounts = inc_ucount(current_user_ns(),
						  current_euid(),
						  UCOUNT_FANOTIFY_GROUPS);
	if (!group->fanotify_data.ucounts) {
		fd = -EMFILE;
		goto out_destroy_group;
	}

	group->fanotify_data.flags = flags | internal_flags;
	group->memcg = get_mem_cgroup_from_mm(current->mm);

	group->fanotify_data.merge_hash = fanotify_alloc_merge_hash();
	if (!group->fanotify_data.merge_hash) {
		fd = -ENOMEM;
		goto out_destroy_group;
	}

	group->overflow_event = fanotify_alloc_overflow_event();
	if (unlikely(!group->overflow_event)) {
		fd = -ENOMEM;
		goto out_destroy_group;
	}

	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 (class) {
	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_max_queued_events;
	}

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

	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 fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid)
{
	__kernel_fsid_t root_fsid;
	int err;

	/*
	 * Make sure dentry is not of a filesystem with zero fsid (e.g. fuse).
	 */
	err = vfs_get_fsid(dentry, fsid);
	if (err)
		return err;

	if (!fsid->val[0] && !fsid->val[1])
		return -ENODEV;

	/*
	 * Make sure dentry is not of a filesystem subvolume (e.g. btrfs)
	 * which uses a different fsid than sb root.
	 */
	err = vfs_get_fsid(dentry->d_sb->s_root, &root_fsid);
	if (err)
		return err;

	if (root_fsid.val[0] != fsid->val[0] ||
	    root_fsid.val[1] != fsid->val[1])
		return -EXDEV;

	return 0;
}

/* Check if filesystem can encode a unique fid */
static int fanotify_test_fid(struct dentry *dentry)
{
	/*
	 * We need to make sure that the file system supports at least
	 * encoding a file handle so user can use name_to_handle_at() to
	 * compare fid returned with event to the file handle of watched
	 * objects. However, name_to_handle_at() requires that the
	 * filesystem also supports decoding file handles.
	 */
	if (!dentry->d_sb->s_export_op ||
	    !dentry->d_sb->s_export_op->fh_to_dentry)
		return -EOPNOTSUPP;

	return 0;
}

static int fanotify_events_supported(struct path *path, __u64 mask)
{
	/*
	 * Some filesystems such as 'proc' acquire unusual locks when opening
	 * files. For them fanotify permission events have high chances of
	 * deadlocking the system - open done when reporting fanotify event
	 * blocks on this "unusual" lock while another process holding the lock
	 * waits for fanotify permission event to be answered. Just disallow
	 * permission events for such filesystems.
	 */
	if (mask & FANOTIFY_PERM_EVENTS &&
	    path->mnt->mnt_sb->s_type->fs_flags & FS_DISALLOW_NOTIFY_PERM)
		return -EINVAL;
	return 0;
}

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;
	__kernel_fsid_t __fsid, *fsid = NULL;
	u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
	unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
	bool ignored = flags & FAN_MARK_IGNORED_MASK;
	unsigned int obj_type, fid_mode;
	u32 umask = 0;
	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 (upper_32_bits(mask))
		return -EINVAL;

	if (flags & ~FANOTIFY_MARK_FLAGS)
		return -EINVAL;

	switch (mark_type) {
	case FAN_MARK_INODE:
		obj_type = FSNOTIFY_OBJ_TYPE_INODE;
		break;
	case FAN_MARK_MOUNT:
		obj_type = FSNOTIFY_OBJ_TYPE_VFSMOUNT;
		break;
	case FAN_MARK_FILESYSTEM:
		obj_type = FSNOTIFY_OBJ_TYPE_SB;
		break;
	default:
		return -EINVAL;
	}

	switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
	case FAN_MARK_ADD:
	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;

	/* Event flags (ONDIR, ON_CHILD) are meaningless in ignored mask */
	if (ignored)
		mask &= ~FANOTIFY_EVENT_FLAGS;

	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;

	/*
	 * An unprivileged user is not allowed to setup mount nor filesystem
	 * marks.  This also includes setting up such marks by a group that
	 * was initialized by an unprivileged user.
	 */
	ret = -EPERM;
	if ((!capable(CAP_SYS_ADMIN) ||
	     FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV)) &&
	    mark_type != FAN_MARK_INODE)
		goto fput_and_out;

	/*
	 * 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 (mask & FAN_FS_ERROR &&
	    mark_type != FAN_MARK_FILESYSTEM)
		goto fput_and_out;

	/*
	 * Events that do not carry enough information to report
	 * event->fd require a group that supports reporting fid.  Those
	 * events are not supported on a mount mark, because they do not
	 * carry enough information (i.e. path) to be filtered by mount
	 * point.
	 */
	fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
	if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) &&
	    (!fid_mode || mark_type == FAN_MARK_MOUNT))
		goto fput_and_out;

	/*
	 * FAN_RENAME uses special info type records to report the old and
	 * new parent+name.  Reporting only old and new parent id is less
	 * useful and was not implemented.
	 */
	if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME))
		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,
			(mask & ALL_FSNOTIFY_EVENTS), obj_type);
	if (ret)
		goto fput_and_out;

	if (flags & FAN_MARK_ADD) {
		ret = fanotify_events_supported(&path, mask);
		if (ret)
			goto path_put_and_out;
	}

	if (fid_mode) {
		ret = fanotify_test_fsid(path.dentry, &__fsid);
		if (ret)
			goto path_put_and_out;

		ret = fanotify_test_fid(path.dentry);
		if (ret)
			goto path_put_and_out;

		fsid = &__fsid;
	}

	/* 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;

	/* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */
	if (mnt || !S_ISDIR(inode->i_mode)) {
		mask &= ~FAN_EVENT_ON_CHILD;
		umask = FAN_EVENT_ON_CHILD;
		/*
		 * If group needs to report parent fid, register for getting
		 * events with parent/name info for non-directory.
		 */
		if ((fid_mode & FAN_REPORT_DIR_FID) &&
		    (flags & FAN_MARK_ADD) && !ignored)
			mask |= FAN_EVENT_ON_CHILD;
	}

	/* 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, fsid);
		else if (mark_type == FAN_MARK_FILESYSTEM)
			ret = fanotify_add_sb_mark(group, mnt->mnt_sb, mask,
						   flags, fsid);
		else
			ret = fanotify_add_inode_mark(group, inode, mask,
						      flags, fsid);
		break;
	case FAN_MARK_REMOVE:
		if (mark_type == FAN_MARK_MOUNT)
			ret = fanotify_remove_vfsmount_mark(group, mnt, mask,
							    flags, umask);
		else if (mark_type == FAN_MARK_FILESYSTEM)
			ret = fanotify_remove_sb_mark(group, mnt->mnt_sb, mask,
						      flags, umask);
		else
			ret = fanotify_remove_inode_mark(group, inode, mask,
							 flags, umask);
		break;
	default:
		ret = -EINVAL;
	}

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

#ifndef CONFIG_ARCH_SPLIT_ARG64
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);
}
#endif

#if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT)
SYSCALL32_DEFINE6(fanotify_mark,
				int, fanotify_fd, unsigned int, flags,
				SC_ARG64(mask), int, dfd,
				const char  __user *, pathname)
{
	return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask),
				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)
{
	struct sysinfo si;
	int max_marks;

	si_meminfo(&si);
	/*
	 * Allow up to 1% of addressable memory to be accounted for per user
	 * marks limited to the range [8192, 1048576]. mount and sb marks are
	 * a lot cheaper than inode marks, but there is no reason for a user
	 * to have many of those, so calculate by the cost of inode marks.
	 */
	max_marks = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) /
		    INODE_MARK_COST;
	max_marks = clamp(max_marks, FANOTIFY_OLD_DEFAULT_MAX_MARKS,
				     FANOTIFY_DEFAULT_MAX_USER_MARKS);

	BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12);
	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);

	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
					 SLAB_PANIC|SLAB_ACCOUNT);
	fanotify_fid_event_cachep = KMEM_CACHE(fanotify_fid_event,
					       SLAB_PANIC);
	fanotify_path_event_cachep = KMEM_CACHE(fanotify_path_event,
						SLAB_PANIC);
	if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) {
		fanotify_perm_event_cachep =
			KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);
	}

	fanotify_max_queued_events = FANOTIFY_DEFAULT_MAX_EVENTS;
	init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] =
					FANOTIFY_DEFAULT_MAX_GROUPS;
	init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS] = max_marks;
	fanotify_sysctls_init();

	return 0;
}
device_initcall(fanotify_user_setup);