summaryrefslogtreecommitdiff
path: root/security/landlock/fs.c
blob: 0171f7eb6ee15d384835a6cd68a2afcff1f3b653 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Landlock LSM - Filesystem management and hooks
 *
 * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
 * Copyright © 2018-2020 ANSSI
 * Copyright © 2021-2022 Microsoft Corporation
 */

#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/bits.h>
#include <linux/compiler_types.h>
#include <linux/dcache.h>
#include <linux/err.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/limits.h>
#include <linux/list.h>
#include <linux/lsm_hooks.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/path.h>
#include <linux/rcupdate.h>
#include <linux/spinlock.h>
#include <linux/stat.h>
#include <linux/types.h>
#include <linux/wait_bit.h>
#include <linux/workqueue.h>
#include <uapi/linux/landlock.h>

#include "common.h"
#include "cred.h"
#include "fs.h"
#include "limits.h"
#include "object.h"
#include "ruleset.h"
#include "setup.h"

/* Underlying object management */

static void release_inode(struct landlock_object *const object)
	__releases(object->lock)
{
	struct inode *const inode = object->underobj;
	struct super_block *sb;

	if (!inode) {
		spin_unlock(&object->lock);
		return;
	}

	/*
	 * Protects against concurrent use by hook_sb_delete() of the reference
	 * to the underlying inode.
	 */
	object->underobj = NULL;
	/*
	 * Makes sure that if the filesystem is concurrently unmounted,
	 * hook_sb_delete() will wait for us to finish iput().
	 */
	sb = inode->i_sb;
	atomic_long_inc(&landlock_superblock(sb)->inode_refs);
	spin_unlock(&object->lock);
	/*
	 * Because object->underobj was not NULL, hook_sb_delete() and
	 * get_inode_object() guarantee that it is safe to reset
	 * landlock_inode(inode)->object while it is not NULL.  It is therefore
	 * not necessary to lock inode->i_lock.
	 */
	rcu_assign_pointer(landlock_inode(inode)->object, NULL);
	/*
	 * Now, new rules can safely be tied to @inode with get_inode_object().
	 */

	iput(inode);
	if (atomic_long_dec_and_test(&landlock_superblock(sb)->inode_refs))
		wake_up_var(&landlock_superblock(sb)->inode_refs);
}

static const struct landlock_object_underops landlock_fs_underops = {
	.release = release_inode
};

/* Ruleset management */

static struct landlock_object *get_inode_object(struct inode *const inode)
{
	struct landlock_object *object, *new_object;
	struct landlock_inode_security *inode_sec = landlock_inode(inode);

	rcu_read_lock();
retry:
	object = rcu_dereference(inode_sec->object);
	if (object) {
		if (likely(refcount_inc_not_zero(&object->usage))) {
			rcu_read_unlock();
			return object;
		}
		/*
		 * We are racing with release_inode(), the object is going
		 * away.  Wait for release_inode(), then retry.
		 */
		spin_lock(&object->lock);
		spin_unlock(&object->lock);
		goto retry;
	}
	rcu_read_unlock();

	/*
	 * If there is no object tied to @inode, then create a new one (without
	 * holding any locks).
	 */
	new_object = landlock_create_object(&landlock_fs_underops, inode);
	if (IS_ERR(new_object))
		return new_object;

	/*
	 * Protects against concurrent calls to get_inode_object() or
	 * hook_sb_delete().
	 */
	spin_lock(&inode->i_lock);
	if (unlikely(rcu_access_pointer(inode_sec->object))) {
		/* Someone else just created the object, bail out and retry. */
		spin_unlock(&inode->i_lock);
		kfree(new_object);

		rcu_read_lock();
		goto retry;
	}

	/*
	 * @inode will be released by hook_sb_delete() on its superblock
	 * shutdown, or by release_inode() when no more ruleset references the
	 * related object.
	 */
	ihold(inode);
	rcu_assign_pointer(inode_sec->object, new_object);
	spin_unlock(&inode->i_lock);
	return new_object;
}

/* All access rights that can be tied to files. */
/* clang-format off */
#define ACCESS_FILE ( \
	LANDLOCK_ACCESS_FS_EXECUTE | \
	LANDLOCK_ACCESS_FS_WRITE_FILE | \
	LANDLOCK_ACCESS_FS_READ_FILE | \
	LANDLOCK_ACCESS_FS_TRUNCATE)
/* clang-format on */

/*
 * @path: Should have been checked by get_path_from_fd().
 */
int landlock_append_fs_rule(struct landlock_ruleset *const ruleset,
			    const struct path *const path,
			    access_mask_t access_rights)
{
	int err;
	struct landlock_id id = {
		.type = LANDLOCK_KEY_INODE,
	};

	/* Files only get access rights that make sense. */
	if (!d_is_dir(path->dentry) &&
	    (access_rights | ACCESS_FILE) != ACCESS_FILE)
		return -EINVAL;
	if (WARN_ON_ONCE(ruleset->num_layers != 1))
		return -EINVAL;

	/* Transforms relative access rights to absolute ones. */
	access_rights |= LANDLOCK_MASK_ACCESS_FS &
			 ~landlock_get_fs_access_mask(ruleset, 0);
	id.key.object = get_inode_object(d_backing_inode(path->dentry));
	if (IS_ERR(id.key.object))
		return PTR_ERR(id.key.object);
	mutex_lock(&ruleset->lock);
	err = landlock_insert_rule(ruleset, id, access_rights);
	mutex_unlock(&ruleset->lock);
	/*
	 * No need to check for an error because landlock_insert_rule()
	 * increments the refcount for the new object if needed.
	 */
	landlock_put_object(id.key.object);
	return err;
}

/* Access-control management */

/*
 * The lifetime of the returned rule is tied to @domain.
 *
 * Returns NULL if no rule is found or if @dentry is negative.
 */
static const struct landlock_rule *
find_rule(const struct landlock_ruleset *const domain,
	  const struct dentry *const dentry)
{
	const struct landlock_rule *rule;
	const struct inode *inode;
	struct landlock_id id = {
		.type = LANDLOCK_KEY_INODE,
	};

	/* Ignores nonexistent leafs. */
	if (d_is_negative(dentry))
		return NULL;

	inode = d_backing_inode(dentry);
	rcu_read_lock();
	id.key.object = rcu_dereference(landlock_inode(inode)->object);
	rule = landlock_find_rule(domain, id);
	rcu_read_unlock();
	return rule;
}

/*
 * Allows access to pseudo filesystems that will never be mountable (e.g.
 * sockfs, pipefs), but can still be reachable through
 * /proc/<pid>/fd/<file-descriptor>
 */
static bool is_nouser_or_private(const struct dentry *dentry)
{
	return (dentry->d_sb->s_flags & SB_NOUSER) ||
	       (d_is_positive(dentry) &&
		unlikely(IS_PRIVATE(d_backing_inode(dentry))));
}

static access_mask_t
get_raw_handled_fs_accesses(const struct landlock_ruleset *const domain)
{
	access_mask_t access_dom = 0;
	size_t layer_level;

	for (layer_level = 0; layer_level < domain->num_layers; layer_level++)
		access_dom |=
			landlock_get_raw_fs_access_mask(domain, layer_level);
	return access_dom;
}

static access_mask_t
get_handled_fs_accesses(const struct landlock_ruleset *const domain)
{
	/* Handles all initially denied by default access rights. */
	return get_raw_handled_fs_accesses(domain) |
	       LANDLOCK_ACCESS_FS_INITIALLY_DENIED;
}

static const struct landlock_ruleset *get_current_fs_domain(void)
{
	const struct landlock_ruleset *const dom =
		landlock_get_current_domain();

	if (!dom || !get_raw_handled_fs_accesses(dom))
		return NULL;

	return dom;
}

/*
 * Check that a destination file hierarchy has more restrictions than a source
 * file hierarchy.  This is only used for link and rename actions.
 *
 * @layer_masks_child2: Optional child masks.
 */
static bool no_more_access(
	const layer_mask_t (*const layer_masks_parent1)[LANDLOCK_NUM_ACCESS_FS],
	const layer_mask_t (*const layer_masks_child1)[LANDLOCK_NUM_ACCESS_FS],
	const bool child1_is_directory,
	const layer_mask_t (*const layer_masks_parent2)[LANDLOCK_NUM_ACCESS_FS],
	const layer_mask_t (*const layer_masks_child2)[LANDLOCK_NUM_ACCESS_FS],
	const bool child2_is_directory)
{
	unsigned long access_bit;

	for (access_bit = 0; access_bit < ARRAY_SIZE(*layer_masks_parent2);
	     access_bit++) {
		/* Ignores accesses that only make sense for directories. */
		const bool is_file_access =
			!!(BIT_ULL(access_bit) & ACCESS_FILE);

		if (child1_is_directory || is_file_access) {
			/*
			 * Checks if the destination restrictions are a
			 * superset of the source ones (i.e. inherited access
			 * rights without child exceptions):
			 * restrictions(parent2) >= restrictions(child1)
			 */
			if ((((*layer_masks_parent1)[access_bit] &
			      (*layer_masks_child1)[access_bit]) |
			     (*layer_masks_parent2)[access_bit]) !=
			    (*layer_masks_parent2)[access_bit])
				return false;
		}

		if (!layer_masks_child2)
			continue;
		if (child2_is_directory || is_file_access) {
			/*
			 * Checks inverted restrictions for RENAME_EXCHANGE:
			 * restrictions(parent1) >= restrictions(child2)
			 */
			if ((((*layer_masks_parent2)[access_bit] &
			      (*layer_masks_child2)[access_bit]) |
			     (*layer_masks_parent1)[access_bit]) !=
			    (*layer_masks_parent1)[access_bit])
				return false;
		}
	}
	return true;
}

/*
 * Removes @layer_masks accesses that are not requested.
 *
 * Returns true if the request is allowed, false otherwise.
 */
static bool
scope_to_request(const access_mask_t access_request,
		 layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS])
{
	const unsigned long access_req = access_request;
	unsigned long access_bit;

	if (WARN_ON_ONCE(!layer_masks))
		return true;

	for_each_clear_bit(access_bit, &access_req, ARRAY_SIZE(*layer_masks))
		(*layer_masks)[access_bit] = 0;
	return !memchr_inv(layer_masks, 0, sizeof(*layer_masks));
}

/*
 * Returns true if there is at least one access right different than
 * LANDLOCK_ACCESS_FS_REFER.
 */
static bool
is_eacces(const layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS],
	  const access_mask_t access_request)
{
	unsigned long access_bit;
	/* LANDLOCK_ACCESS_FS_REFER alone must return -EXDEV. */
	const unsigned long access_check = access_request &
					   ~LANDLOCK_ACCESS_FS_REFER;

	if (!layer_masks)
		return false;

	for_each_set_bit(access_bit, &access_check, ARRAY_SIZE(*layer_masks)) {
		if ((*layer_masks)[access_bit])
			return true;
	}
	return false;
}

/**
 * is_access_to_paths_allowed - Check accesses for requests with a common path
 *
 * @domain: Domain to check against.
 * @path: File hierarchy to walk through.
 * @access_request_parent1: Accesses to check, once @layer_masks_parent1 is
 *     equal to @layer_masks_parent2 (if any).  This is tied to the unique
 *     requested path for most actions, or the source in case of a refer action
 *     (i.e. rename or link), or the source and destination in case of
 *     RENAME_EXCHANGE.
 * @layer_masks_parent1: Pointer to a matrix of layer masks per access
 *     masks, identifying the layers that forbid a specific access.  Bits from
 *     this matrix can be unset according to the @path walk.  An empty matrix
 *     means that @domain allows all possible Landlock accesses (i.e. not only
 *     those identified by @access_request_parent1).  This matrix can
 *     initially refer to domain layer masks and, when the accesses for the
 *     destination and source are the same, to requested layer masks.
 * @dentry_child1: Dentry to the initial child of the parent1 path.  This
 *     pointer must be NULL for non-refer actions (i.e. not link nor rename).
 * @access_request_parent2: Similar to @access_request_parent1 but for a
 *     request involving a source and a destination.  This refers to the
 *     destination, except in case of RENAME_EXCHANGE where it also refers to
 *     the source.  Must be set to 0 when using a simple path request.
 * @layer_masks_parent2: Similar to @layer_masks_parent1 but for a refer
 *     action.  This must be NULL otherwise.
 * @dentry_child2: Dentry to the initial child of the parent2 path.  This
 *     pointer is only set for RENAME_EXCHANGE actions and must be NULL
 *     otherwise.
 *
 * This helper first checks that the destination has a superset of restrictions
 * compared to the source (if any) for a common path.  Because of
 * RENAME_EXCHANGE actions, source and destinations may be swapped.  It then
 * checks that the collected accesses and the remaining ones are enough to
 * allow the request.
 *
 * Returns:
 * - true if the access request is granted;
 * - false otherwise.
 */
static bool is_access_to_paths_allowed(
	const struct landlock_ruleset *const domain,
	const struct path *const path,
	const access_mask_t access_request_parent1,
	layer_mask_t (*const layer_masks_parent1)[LANDLOCK_NUM_ACCESS_FS],
	const struct dentry *const dentry_child1,
	const access_mask_t access_request_parent2,
	layer_mask_t (*const layer_masks_parent2)[LANDLOCK_NUM_ACCESS_FS],
	const struct dentry *const dentry_child2)
{
	bool allowed_parent1 = false, allowed_parent2 = false, is_dom_check,
	     child1_is_directory = true, child2_is_directory = true;
	struct path walker_path;
	access_mask_t access_masked_parent1, access_masked_parent2;
	layer_mask_t _layer_masks_child1[LANDLOCK_NUM_ACCESS_FS],
		_layer_masks_child2[LANDLOCK_NUM_ACCESS_FS];
	layer_mask_t(*layer_masks_child1)[LANDLOCK_NUM_ACCESS_FS] = NULL,
	(*layer_masks_child2)[LANDLOCK_NUM_ACCESS_FS] = NULL;

	if (!access_request_parent1 && !access_request_parent2)
		return true;
	if (WARN_ON_ONCE(!domain || !path))
		return true;
	if (is_nouser_or_private(path->dentry))
		return true;
	if (WARN_ON_ONCE(domain->num_layers < 1 || !layer_masks_parent1))
		return false;

	if (unlikely(layer_masks_parent2)) {
		if (WARN_ON_ONCE(!dentry_child1))
			return false;
		/*
		 * For a double request, first check for potential privilege
		 * escalation by looking at domain handled accesses (which are
		 * a superset of the meaningful requested accesses).
		 */
		access_masked_parent1 = access_masked_parent2 =
			get_handled_fs_accesses(domain);
		is_dom_check = true;
	} else {
		if (WARN_ON_ONCE(dentry_child1 || dentry_child2))
			return false;
		/* For a simple request, only check for requested accesses. */
		access_masked_parent1 = access_request_parent1;
		access_masked_parent2 = access_request_parent2;
		is_dom_check = false;
	}

	if (unlikely(dentry_child1)) {
		landlock_unmask_layers(
			find_rule(domain, dentry_child1),
			landlock_init_layer_masks(
				domain, LANDLOCK_MASK_ACCESS_FS,
				&_layer_masks_child1, LANDLOCK_KEY_INODE),
			&_layer_masks_child1, ARRAY_SIZE(_layer_masks_child1));
		layer_masks_child1 = &_layer_masks_child1;
		child1_is_directory = d_is_dir(dentry_child1);
	}
	if (unlikely(dentry_child2)) {
		landlock_unmask_layers(
			find_rule(domain, dentry_child2),
			landlock_init_layer_masks(
				domain, LANDLOCK_MASK_ACCESS_FS,
				&_layer_masks_child2, LANDLOCK_KEY_INODE),
			&_layer_masks_child2, ARRAY_SIZE(_layer_masks_child2));
		layer_masks_child2 = &_layer_masks_child2;
		child2_is_directory = d_is_dir(dentry_child2);
	}

	walker_path = *path;
	path_get(&walker_path);
	/*
	 * We need to walk through all the hierarchy to not miss any relevant
	 * restriction.
	 */
	while (true) {
		struct dentry *parent_dentry;
		const struct landlock_rule *rule;

		/*
		 * If at least all accesses allowed on the destination are
		 * already allowed on the source, respectively if there is at
		 * least as much as restrictions on the destination than on the
		 * source, then we can safely refer files from the source to
		 * the destination without risking a privilege escalation.
		 * This also applies in the case of RENAME_EXCHANGE, which
		 * implies checks on both direction.  This is crucial for
		 * standalone multilayered security policies.  Furthermore,
		 * this helps avoid policy writers to shoot themselves in the
		 * foot.
		 */
		if (unlikely(is_dom_check &&
			     no_more_access(
				     layer_masks_parent1, layer_masks_child1,
				     child1_is_directory, layer_masks_parent2,
				     layer_masks_child2,
				     child2_is_directory))) {
			allowed_parent1 = scope_to_request(
				access_request_parent1, layer_masks_parent1);
			allowed_parent2 = scope_to_request(
				access_request_parent2, layer_masks_parent2);

			/* Stops when all accesses are granted. */
			if (allowed_parent1 && allowed_parent2)
				break;

			/*
			 * Now, downgrades the remaining checks from domain
			 * handled accesses to requested accesses.
			 */
			is_dom_check = false;
			access_masked_parent1 = access_request_parent1;
			access_masked_parent2 = access_request_parent2;
		}

		rule = find_rule(domain, walker_path.dentry);
		allowed_parent1 = landlock_unmask_layers(
			rule, access_masked_parent1, layer_masks_parent1,
			ARRAY_SIZE(*layer_masks_parent1));
		allowed_parent2 = landlock_unmask_layers(
			rule, access_masked_parent2, layer_masks_parent2,
			ARRAY_SIZE(*layer_masks_parent2));

		/* Stops when a rule from each layer grants access. */
		if (allowed_parent1 && allowed_parent2)
			break;
jump_up:
		if (walker_path.dentry == walker_path.mnt->mnt_root) {
			if (follow_up(&walker_path)) {
				/* Ignores hidden mount points. */
				goto jump_up;
			} else {
				/*
				 * Stops at the real root.  Denies access
				 * because not all layers have granted access.
				 */
				break;
			}
		}
		if (unlikely(IS_ROOT(walker_path.dentry))) {
			/*
			 * Stops at disconnected root directories.  Only allows
			 * access to internal filesystems (e.g. nsfs, which is
			 * reachable through /proc/<pid>/ns/<namespace>).
			 */
			allowed_parent1 = allowed_parent2 =
				!!(walker_path.mnt->mnt_flags & MNT_INTERNAL);
			break;
		}
		parent_dentry = dget_parent(walker_path.dentry);
		dput(walker_path.dentry);
		walker_path.dentry = parent_dentry;
	}
	path_put(&walker_path);

	return allowed_parent1 && allowed_parent2;
}

static int check_access_path(const struct landlock_ruleset *const domain,
			     const struct path *const path,
			     access_mask_t access_request)
{
	layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {};

	access_request = landlock_init_layer_masks(
		domain, access_request, &layer_masks, LANDLOCK_KEY_INODE);
	if (is_access_to_paths_allowed(domain, path, access_request,
				       &layer_masks, NULL, 0, NULL, NULL))
		return 0;
	return -EACCES;
}

static int current_check_access_path(const struct path *const path,
				     const access_mask_t access_request)
{
	const struct landlock_ruleset *const dom = get_current_fs_domain();

	if (!dom)
		return 0;
	return check_access_path(dom, path, access_request);
}

static access_mask_t get_mode_access(const umode_t mode)
{
	switch (mode & S_IFMT) {
	case S_IFLNK:
		return LANDLOCK_ACCESS_FS_MAKE_SYM;
	case 0:
		/* A zero mode translates to S_IFREG. */
	case S_IFREG:
		return LANDLOCK_ACCESS_FS_MAKE_REG;
	case S_IFDIR:
		return LANDLOCK_ACCESS_FS_MAKE_DIR;
	case S_IFCHR:
		return LANDLOCK_ACCESS_FS_MAKE_CHAR;
	case S_IFBLK:
		return LANDLOCK_ACCESS_FS_MAKE_BLOCK;
	case S_IFIFO:
		return LANDLOCK_ACCESS_FS_MAKE_FIFO;
	case S_IFSOCK:
		return LANDLOCK_ACCESS_FS_MAKE_SOCK;
	default:
		WARN_ON_ONCE(1);
		return 0;
	}
}

static access_mask_t maybe_remove(const struct dentry *const dentry)
{
	if (d_is_negative(dentry))
		return 0;
	return d_is_dir(dentry) ? LANDLOCK_ACCESS_FS_REMOVE_DIR :
				  LANDLOCK_ACCESS_FS_REMOVE_FILE;
}

/**
 * collect_domain_accesses - Walk through a file path and collect accesses
 *
 * @domain: Domain to check against.
 * @mnt_root: Last directory to check.
 * @dir: Directory to start the walk from.
 * @layer_masks_dom: Where to store the collected accesses.
 *
 * This helper is useful to begin a path walk from the @dir directory to a
 * @mnt_root directory used as a mount point.  This mount point is the common
 * ancestor between the source and the destination of a renamed and linked
 * file.  While walking from @dir to @mnt_root, we record all the domain's
 * allowed accesses in @layer_masks_dom.
 *
 * This is similar to is_access_to_paths_allowed() but much simpler because it
 * only handles walking on the same mount point and only checks one set of
 * accesses.
 *
 * Returns:
 * - true if all the domain access rights are allowed for @dir;
 * - false if the walk reached @mnt_root.
 */
static bool collect_domain_accesses(
	const struct landlock_ruleset *const domain,
	const struct dentry *const mnt_root, struct dentry *dir,
	layer_mask_t (*const layer_masks_dom)[LANDLOCK_NUM_ACCESS_FS])
{
	unsigned long access_dom;
	bool ret = false;

	if (WARN_ON_ONCE(!domain || !mnt_root || !dir || !layer_masks_dom))
		return true;
	if (is_nouser_or_private(dir))
		return true;

	access_dom = landlock_init_layer_masks(domain, LANDLOCK_MASK_ACCESS_FS,
					       layer_masks_dom,
					       LANDLOCK_KEY_INODE);

	dget(dir);
	while (true) {
		struct dentry *parent_dentry;

		/* Gets all layers allowing all domain accesses. */
		if (landlock_unmask_layers(find_rule(domain, dir), access_dom,
					   layer_masks_dom,
					   ARRAY_SIZE(*layer_masks_dom))) {
			/*
			 * Stops when all handled accesses are allowed by at
			 * least one rule in each layer.
			 */
			ret = true;
			break;
		}

		/* We should not reach a root other than @mnt_root. */
		if (dir == mnt_root || WARN_ON_ONCE(IS_ROOT(dir)))
			break;

		parent_dentry = dget_parent(dir);
		dput(dir);
		dir = parent_dentry;
	}
	dput(dir);
	return ret;
}

/**
 * current_check_refer_path - Check if a rename or link action is allowed
 *
 * @old_dentry: File or directory requested to be moved or linked.
 * @new_dir: Destination parent directory.
 * @new_dentry: Destination file or directory.
 * @removable: Sets to true if it is a rename operation.
 * @exchange: Sets to true if it is a rename operation with RENAME_EXCHANGE.
 *
 * Because of its unprivileged constraints, Landlock relies on file hierarchies
 * (and not only inodes) to tie access rights to files.  Being able to link or
 * rename a file hierarchy brings some challenges.  Indeed, moving or linking a
 * file (i.e. creating a new reference to an inode) can have an impact on the
 * actions allowed for a set of files if it would change its parent directory
 * (i.e. reparenting).
 *
 * To avoid trivial access right bypasses, Landlock first checks if the file or
 * directory requested to be moved would gain new access rights inherited from
 * its new hierarchy.  Before returning any error, Landlock then checks that
 * the parent source hierarchy and the destination hierarchy would allow the
 * link or rename action.  If it is not the case, an error with EACCES is
 * returned to inform user space that there is no way to remove or create the
 * requested source file type.  If it should be allowed but the new inherited
 * access rights would be greater than the source access rights, then the
 * kernel returns an error with EXDEV.  Prioritizing EACCES over EXDEV enables
 * user space to abort the whole operation if there is no way to do it, or to
 * manually copy the source to the destination if this remains allowed, e.g.
 * because file creation is allowed on the destination directory but not direct
 * linking.
 *
 * To achieve this goal, the kernel needs to compare two file hierarchies: the
 * one identifying the source file or directory (including itself), and the
 * destination one.  This can be seen as a multilayer partial ordering problem.
 * The kernel walks through these paths and collects in a matrix the access
 * rights that are denied per layer.  These matrices are then compared to see
 * if the destination one has more (or the same) restrictions as the source
 * one.  If this is the case, the requested action will not return EXDEV, which
 * doesn't mean the action is allowed.  The parent hierarchy of the source
 * (i.e. parent directory), and the destination hierarchy must also be checked
 * to verify that they explicitly allow such action (i.e.  referencing,
 * creation and potentially removal rights).  The kernel implementation is then
 * required to rely on potentially four matrices of access rights: one for the
 * source file or directory (i.e. the child), a potentially other one for the
 * other source/destination (in case of RENAME_EXCHANGE), one for the source
 * parent hierarchy and a last one for the destination hierarchy.  These
 * ephemeral matrices take some space on the stack, which limits the number of
 * layers to a deemed reasonable number: 16.
 *
 * Returns:
 * - 0 if access is allowed;
 * - -EXDEV if @old_dentry would inherit new access rights from @new_dir;
 * - -EACCES if file removal or creation is denied.
 */
static int current_check_refer_path(struct dentry *const old_dentry,
				    const struct path *const new_dir,
				    struct dentry *const new_dentry,
				    const bool removable, const bool exchange)
{
	const struct landlock_ruleset *const dom = get_current_fs_domain();
	bool allow_parent1, allow_parent2;
	access_mask_t access_request_parent1, access_request_parent2;
	struct path mnt_dir;
	layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS] = {},
		     layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS] = {};

	if (!dom)
		return 0;
	if (WARN_ON_ONCE(dom->num_layers < 1))
		return -EACCES;
	if (unlikely(d_is_negative(old_dentry)))
		return -ENOENT;
	if (exchange) {
		if (unlikely(d_is_negative(new_dentry)))
			return -ENOENT;
		access_request_parent1 =
			get_mode_access(d_backing_inode(new_dentry)->i_mode);
	} else {
		access_request_parent1 = 0;
	}
	access_request_parent2 =
		get_mode_access(d_backing_inode(old_dentry)->i_mode);
	if (removable) {
		access_request_parent1 |= maybe_remove(old_dentry);
		access_request_parent2 |= maybe_remove(new_dentry);
	}

	/* The mount points are the same for old and new paths, cf. EXDEV. */
	if (old_dentry->d_parent == new_dir->dentry) {
		/*
		 * The LANDLOCK_ACCESS_FS_REFER access right is not required
		 * for same-directory referer (i.e. no reparenting).
		 */
		access_request_parent1 = landlock_init_layer_masks(
			dom, access_request_parent1 | access_request_parent2,
			&layer_masks_parent1, LANDLOCK_KEY_INODE);
		if (is_access_to_paths_allowed(
			    dom, new_dir, access_request_parent1,
			    &layer_masks_parent1, NULL, 0, NULL, NULL))
			return 0;
		return -EACCES;
	}

	access_request_parent1 |= LANDLOCK_ACCESS_FS_REFER;
	access_request_parent2 |= LANDLOCK_ACCESS_FS_REFER;

	/* Saves the common mount point. */
	mnt_dir.mnt = new_dir->mnt;
	mnt_dir.dentry = new_dir->mnt->mnt_root;

	/* new_dir->dentry is equal to new_dentry->d_parent */
	allow_parent1 = collect_domain_accesses(dom, mnt_dir.dentry,
						old_dentry->d_parent,
						&layer_masks_parent1);
	allow_parent2 = collect_domain_accesses(
		dom, mnt_dir.dentry, new_dir->dentry, &layer_masks_parent2);

	if (allow_parent1 && allow_parent2)
		return 0;

	/*
	 * To be able to compare source and destination domain access rights,
	 * take into account the @old_dentry access rights aggregated with its
	 * parent access rights.  This will be useful to compare with the
	 * destination parent access rights.
	 */
	if (is_access_to_paths_allowed(
		    dom, &mnt_dir, access_request_parent1, &layer_masks_parent1,
		    old_dentry, access_request_parent2, &layer_masks_parent2,
		    exchange ? new_dentry : NULL))
		return 0;

	/*
	 * This prioritizes EACCES over EXDEV for all actions, including
	 * renames with RENAME_EXCHANGE.
	 */
	if (likely(is_eacces(&layer_masks_parent1, access_request_parent1) ||
		   is_eacces(&layer_masks_parent2, access_request_parent2)))
		return -EACCES;

	/*
	 * Gracefully forbids reparenting if the destination directory
	 * hierarchy is not a superset of restrictions of the source directory
	 * hierarchy, or if LANDLOCK_ACCESS_FS_REFER is not allowed by the
	 * source or the destination.
	 */
	return -EXDEV;
}

/* Inode hooks */

static void hook_inode_free_security(struct inode *const inode)
{
	/*
	 * All inodes must already have been untied from their object by
	 * release_inode() or hook_sb_delete().
	 */
	WARN_ON_ONCE(landlock_inode(inode)->object);
}

/* Super-block hooks */

/*
 * Release the inodes used in a security policy.
 *
 * Cf. fsnotify_unmount_inodes() and invalidate_inodes()
 */
static void hook_sb_delete(struct super_block *const sb)
{
	struct inode *inode, *prev_inode = NULL;

	if (!landlock_initialized)
		return;

	spin_lock(&sb->s_inode_list_lock);
	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
		struct landlock_object *object;

		/* Only handles referenced inodes. */
		if (!atomic_read(&inode->i_count))
			continue;

		/*
		 * Protects against concurrent modification of inode (e.g.
		 * from get_inode_object()).
		 */
		spin_lock(&inode->i_lock);
		/*
		 * Checks I_FREEING and I_WILL_FREE  to protect against a race
		 * condition when release_inode() just called iput(), which
		 * could lead to a NULL dereference of inode->security or a
		 * second call to iput() for the same Landlock object.  Also
		 * checks I_NEW because such inode cannot be tied to an object.
		 */
		if (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW)) {
			spin_unlock(&inode->i_lock);
			continue;
		}

		rcu_read_lock();
		object = rcu_dereference(landlock_inode(inode)->object);
		if (!object) {
			rcu_read_unlock();
			spin_unlock(&inode->i_lock);
			continue;
		}
		/* Keeps a reference to this inode until the next loop walk. */
		__iget(inode);
		spin_unlock(&inode->i_lock);

		/*
		 * If there is no concurrent release_inode() ongoing, then we
		 * are in charge of calling iput() on this inode, otherwise we
		 * will just wait for it to finish.
		 */
		spin_lock(&object->lock);
		if (object->underobj == inode) {
			object->underobj = NULL;
			spin_unlock(&object->lock);
			rcu_read_unlock();

			/*
			 * Because object->underobj was not NULL,
			 * release_inode() and get_inode_object() guarantee
			 * that it is safe to reset
			 * landlock_inode(inode)->object while it is not NULL.
			 * It is therefore not necessary to lock inode->i_lock.
			 */
			rcu_assign_pointer(landlock_inode(inode)->object, NULL);
			/*
			 * At this point, we own the ihold() reference that was
			 * originally set up by get_inode_object() and the
			 * __iget() reference that we just set in this loop
			 * walk.  Therefore the following call to iput() will
			 * not sleep nor drop the inode because there is now at
			 * least two references to it.
			 */
			iput(inode);
		} else {
			spin_unlock(&object->lock);
			rcu_read_unlock();
		}

		if (prev_inode) {
			/*
			 * At this point, we still own the __iget() reference
			 * that we just set in this loop walk.  Therefore we
			 * can drop the list lock and know that the inode won't
			 * disappear from under us until the next loop walk.
			 */
			spin_unlock(&sb->s_inode_list_lock);
			/*
			 * We can now actually put the inode reference from the
			 * previous loop walk, which is not needed anymore.
			 */
			iput(prev_inode);
			cond_resched();
			spin_lock(&sb->s_inode_list_lock);
		}
		prev_inode = inode;
	}
	spin_unlock(&sb->s_inode_list_lock);

	/* Puts the inode reference from the last loop walk, if any. */
	if (prev_inode)
		iput(prev_inode);
	/* Waits for pending iput() in release_inode(). */
	wait_var_event(&landlock_superblock(sb)->inode_refs,
		       !atomic_long_read(&landlock_superblock(sb)->inode_refs));
}

/*
 * Because a Landlock security policy is defined according to the filesystem
 * topology (i.e. the mount namespace), changing it may grant access to files
 * not previously allowed.
 *
 * To make it simple, deny any filesystem topology modification by landlocked
 * processes.  Non-landlocked processes may still change the namespace of a
 * landlocked process, but this kind of threat must be handled by a system-wide
 * access-control security policy.
 *
 * This could be lifted in the future if Landlock can safely handle mount
 * namespace updates requested by a landlocked process.  Indeed, we could
 * update the current domain (which is currently read-only) by taking into
 * account the accesses of the source and the destination of a new mount point.
 * However, it would also require to make all the child domains dynamically
 * inherit these new constraints.  Anyway, for backward compatibility reasons,
 * a dedicated user space option would be required (e.g. as a ruleset flag).
 */
static int hook_sb_mount(const char *const dev_name,
			 const struct path *const path, const char *const type,
			 const unsigned long flags, void *const data)
{
	if (!get_current_fs_domain())
		return 0;
	return -EPERM;
}

static int hook_move_mount(const struct path *const from_path,
			   const struct path *const to_path)
{
	if (!get_current_fs_domain())
		return 0;
	return -EPERM;
}

/*
 * Removing a mount point may reveal a previously hidden file hierarchy, which
 * may then grant access to files, which may have previously been forbidden.
 */
static int hook_sb_umount(struct vfsmount *const mnt, const int flags)
{
	if (!get_current_fs_domain())
		return 0;
	return -EPERM;
}

static int hook_sb_remount(struct super_block *const sb, void *const mnt_opts)
{
	if (!get_current_fs_domain())
		return 0;
	return -EPERM;
}

/*
 * pivot_root(2), like mount(2), changes the current mount namespace.  It must
 * then be forbidden for a landlocked process.
 *
 * However, chroot(2) may be allowed because it only changes the relative root
 * directory of the current process.  Moreover, it can be used to restrict the
 * view of the filesystem.
 */
static int hook_sb_pivotroot(const struct path *const old_path,
			     const struct path *const new_path)
{
	if (!get_current_fs_domain())
		return 0;
	return -EPERM;
}

/* Path hooks */

static int hook_path_link(struct dentry *const old_dentry,
			  const struct path *const new_dir,
			  struct dentry *const new_dentry)
{
	return current_check_refer_path(old_dentry, new_dir, new_dentry, false,
					false);
}

static int hook_path_rename(const struct path *const old_dir,
			    struct dentry *const old_dentry,
			    const struct path *const new_dir,
			    struct dentry *const new_dentry,
			    const unsigned int flags)
{
	/* old_dir refers to old_dentry->d_parent and new_dir->mnt */
	return current_check_refer_path(old_dentry, new_dir, new_dentry, true,
					!!(flags & RENAME_EXCHANGE));
}

static int hook_path_mkdir(const struct path *const dir,
			   struct dentry *const dentry, const umode_t mode)
{
	return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_DIR);
}

static int hook_path_mknod(const struct path *const dir,
			   struct dentry *const dentry, const umode_t mode,
			   const unsigned int dev)
{
	const struct landlock_ruleset *const dom = get_current_fs_domain();

	if (!dom)
		return 0;
	return check_access_path(dom, dir, get_mode_access(mode));
}

static int hook_path_symlink(const struct path *const dir,
			     struct dentry *const dentry,
			     const char *const old_name)
{
	return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_SYM);
}

static int hook_path_unlink(const struct path *const dir,
			    struct dentry *const dentry)
{
	return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_FILE);
}

static int hook_path_rmdir(const struct path *const dir,
			   struct dentry *const dentry)
{
	return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_DIR);
}

static int hook_path_truncate(const struct path *const path)
{
	return current_check_access_path(path, LANDLOCK_ACCESS_FS_TRUNCATE);
}

/* File hooks */

/**
 * get_required_file_open_access - Get access needed to open a file
 *
 * @file: File being opened.
 *
 * Returns the access rights that are required for opening the given file,
 * depending on the file type and open mode.
 */
static access_mask_t
get_required_file_open_access(const struct file *const file)
{
	access_mask_t access = 0;

	if (file->f_mode & FMODE_READ) {
		/* A directory can only be opened in read mode. */
		if (S_ISDIR(file_inode(file)->i_mode))
			return LANDLOCK_ACCESS_FS_READ_DIR;
		access = LANDLOCK_ACCESS_FS_READ_FILE;
	}
	if (file->f_mode & FMODE_WRITE)
		access |= LANDLOCK_ACCESS_FS_WRITE_FILE;
	/* __FMODE_EXEC is indeed part of f_flags, not f_mode. */
	if (file->f_flags & __FMODE_EXEC)
		access |= LANDLOCK_ACCESS_FS_EXECUTE;
	return access;
}

static int hook_file_alloc_security(struct file *const file)
{
	/*
	 * Grants all access rights, even if most of them are not checked later
	 * on. It is more consistent.
	 *
	 * Notably, file descriptors for regular files can also be acquired
	 * without going through the file_open hook, for example when using
	 * memfd_create(2).
	 */
	landlock_file(file)->allowed_access = LANDLOCK_MASK_ACCESS_FS;
	return 0;
}

static int hook_file_open(struct file *const file)
{
	layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {};
	access_mask_t open_access_request, full_access_request, allowed_access;
	const access_mask_t optional_access = LANDLOCK_ACCESS_FS_TRUNCATE;
	const struct landlock_ruleset *const dom = get_current_fs_domain();

	if (!dom)
		return 0;

	/*
	 * Because a file may be opened with O_PATH, get_required_file_open_access()
	 * may return 0.  This case will be handled with a future Landlock
	 * evolution.
	 */
	open_access_request = get_required_file_open_access(file);

	/*
	 * We look up more access than what we immediately need for open(), so
	 * that we can later authorize operations on opened files.
	 */
	full_access_request = open_access_request | optional_access;

	if (is_access_to_paths_allowed(
		    dom, &file->f_path,
		    landlock_init_layer_masks(dom, full_access_request,
					      &layer_masks, LANDLOCK_KEY_INODE),
		    &layer_masks, NULL, 0, NULL, NULL)) {
		allowed_access = full_access_request;
	} else {
		unsigned long access_bit;
		const unsigned long access_req = full_access_request;

		/*
		 * Calculate the actual allowed access rights from layer_masks.
		 * Add each access right to allowed_access which has not been
		 * vetoed by any layer.
		 */
		allowed_access = 0;
		for_each_set_bit(access_bit, &access_req,
				 ARRAY_SIZE(layer_masks)) {
			if (!layer_masks[access_bit])
				allowed_access |= BIT_ULL(access_bit);
		}
	}

	/*
	 * For operations on already opened files (i.e. ftruncate()), it is the
	 * access rights at the time of open() which decide whether the
	 * operation is permitted. Therefore, we record the relevant subset of
	 * file access rights in the opened struct file.
	 */
	landlock_file(file)->allowed_access = allowed_access;

	if ((open_access_request & allowed_access) == open_access_request)
		return 0;

	return -EACCES;
}

static int hook_file_truncate(struct file *const file)
{
	/*
	 * Allows truncation if the truncate right was available at the time of
	 * opening the file, to get a consistent access check as for read, write
	 * and execute operations.
	 *
	 * Note: For checks done based on the file's Landlock allowed access, we
	 * enforce them independently of whether the current thread is in a
	 * Landlock domain, so that open files passed between independent
	 * processes retain their behaviour.
	 */
	if (landlock_file(file)->allowed_access & LANDLOCK_ACCESS_FS_TRUNCATE)
		return 0;
	return -EACCES;
}

static struct security_hook_list landlock_hooks[] __ro_after_init = {
	LSM_HOOK_INIT(inode_free_security, hook_inode_free_security),

	LSM_HOOK_INIT(sb_delete, hook_sb_delete),
	LSM_HOOK_INIT(sb_mount, hook_sb_mount),
	LSM_HOOK_INIT(move_mount, hook_move_mount),
	LSM_HOOK_INIT(sb_umount, hook_sb_umount),
	LSM_HOOK_INIT(sb_remount, hook_sb_remount),
	LSM_HOOK_INIT(sb_pivotroot, hook_sb_pivotroot),

	LSM_HOOK_INIT(path_link, hook_path_link),
	LSM_HOOK_INIT(path_rename, hook_path_rename),
	LSM_HOOK_INIT(path_mkdir, hook_path_mkdir),
	LSM_HOOK_INIT(path_mknod, hook_path_mknod),
	LSM_HOOK_INIT(path_symlink, hook_path_symlink),
	LSM_HOOK_INIT(path_unlink, hook_path_unlink),
	LSM_HOOK_INIT(path_rmdir, hook_path_rmdir),
	LSM_HOOK_INIT(path_truncate, hook_path_truncate),

	LSM_HOOK_INIT(file_alloc_security, hook_file_alloc_security),
	LSM_HOOK_INIT(file_open, hook_file_open),
	LSM_HOOK_INIT(file_truncate, hook_file_truncate),
};

__init void landlock_add_fs_hooks(void)
{
	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
			   &landlock_lsmid);
}