summaryrefslogtreecommitdiffstats
path: root/fs/posix_acl.c
blob: d2271431f344248da3f30e8c344f680a28ed01fc (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2002,2003 by Andreas Gruenbacher <a.gruenbacher@computer.org>
 *
 * Fixes from William Schumacher incorporated on 15 March 2001.
 *    (Reported by Charles Bertsch, <CBertsch@microtest.com>).
 */

/*
 *  This file contains generic functions for manipulating
 *  POSIX 1003.1e draft standard 17 ACLs.
 */

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/atomic.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/cred.h>
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/xattr.h>
#include <linux/export.h>
#include <linux/user_namespace.h>
#include <linux/namei.h>
#include <linux/mnt_idmapping.h>
#include <linux/iversion.h>
#include <linux/security.h>
#include <linux/evm.h>
#include <linux/fsnotify.h>
#include <linux/filelock.h>

#include "internal.h"

static struct posix_acl **acl_by_type(struct inode *inode, int type)
{
	switch (type) {
	case ACL_TYPE_ACCESS:
		return &inode->i_acl;
	case ACL_TYPE_DEFAULT:
		return &inode->i_default_acl;
	default:
		BUG();
	}
}

struct posix_acl *get_cached_acl(struct inode *inode, int type)
{
	struct posix_acl **p = acl_by_type(inode, type);
	struct posix_acl *acl;

	for (;;) {
		rcu_read_lock();
		acl = rcu_dereference(*p);
		if (!acl || is_uncached_acl(acl) ||
		    refcount_inc_not_zero(&acl->a_refcount))
			break;
		rcu_read_unlock();
		cpu_relax();
	}
	rcu_read_unlock();
	return acl;
}
EXPORT_SYMBOL(get_cached_acl);

struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type)
{
	struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type));

	if (acl == ACL_DONT_CACHE) {
		struct posix_acl *ret;

		ret = inode->i_op->get_inode_acl(inode, type, LOOKUP_RCU);
		if (!IS_ERR(ret))
			acl = ret;
	}

	return acl;
}
EXPORT_SYMBOL(get_cached_acl_rcu);

void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl)
{
	struct posix_acl **p = acl_by_type(inode, type);
	struct posix_acl *old;

	old = xchg(p, posix_acl_dup(acl));
	if (!is_uncached_acl(old))
		posix_acl_release(old);
}
EXPORT_SYMBOL(set_cached_acl);

static void __forget_cached_acl(struct posix_acl **p)
{
	struct posix_acl *old;

	old = xchg(p, ACL_NOT_CACHED);
	if (!is_uncached_acl(old))
		posix_acl_release(old);
}

void forget_cached_acl(struct inode *inode, int type)
{
	__forget_cached_acl(acl_by_type(inode, type));
}
EXPORT_SYMBOL(forget_cached_acl);

void forget_all_cached_acls(struct inode *inode)
{
	__forget_cached_acl(&inode->i_acl);
	__forget_cached_acl(&inode->i_default_acl);
}
EXPORT_SYMBOL(forget_all_cached_acls);

static struct posix_acl *__get_acl(struct user_namespace *mnt_userns,
				   struct dentry *dentry, struct inode *inode,
				   int type)
{
	struct posix_acl *sentinel;
	struct posix_acl **p;
	struct posix_acl *acl;

	/*
	 * The sentinel is used to detect when another operation like
	 * set_cached_acl() or forget_cached_acl() races with get_inode_acl().
	 * It is guaranteed that is_uncached_acl(sentinel) is true.
	 */

	acl = get_cached_acl(inode, type);
	if (!is_uncached_acl(acl))
		return acl;

	if (!IS_POSIXACL(inode))
		return NULL;

	sentinel = uncached_acl_sentinel(current);
	p = acl_by_type(inode, type);

	/*
	 * If the ACL isn't being read yet, set our sentinel.  Otherwise, the
	 * current value of the ACL will not be ACL_NOT_CACHED and so our own
	 * sentinel will not be set; another task will update the cache.  We
	 * could wait for that other task to complete its job, but it's easier
	 * to just call ->get_inode_acl to fetch the ACL ourself.  (This is
	 * going to be an unlikely race.)
	 */
	cmpxchg(p, ACL_NOT_CACHED, sentinel);

	/*
	 * Normally, the ACL returned by ->get{_inode}_acl will be cached.
	 * A filesystem can prevent that by calling
	 * forget_cached_acl(inode, type) in ->get{_inode}_acl.
	 *
	 * If the filesystem doesn't have a get{_inode}_ acl() function at all,
	 * we'll just create the negative cache entry.
	 */
	if (dentry && inode->i_op->get_acl) {
		acl = inode->i_op->get_acl(mnt_userns, dentry, type);
	} else if (inode->i_op->get_inode_acl) {
		acl = inode->i_op->get_inode_acl(inode, type, false);
	} else {
		set_cached_acl(inode, type, NULL);
		return NULL;
	}
	if (IS_ERR(acl)) {
		/*
		 * Remove our sentinel so that we don't block future attempts
		 * to cache the ACL.
		 */
		cmpxchg(p, sentinel, ACL_NOT_CACHED);
		return acl;
	}

	/*
	 * Cache the result, but only if our sentinel is still in place.
	 */
	posix_acl_dup(acl);
	if (unlikely(cmpxchg(p, sentinel, acl) != sentinel))
		posix_acl_release(acl);
	return acl;
}

struct posix_acl *get_inode_acl(struct inode *inode, int type)
{
	return __get_acl(&init_user_ns, NULL, inode, type);
}
EXPORT_SYMBOL(get_inode_acl);

/*
 * Init a fresh posix_acl
 */
void
posix_acl_init(struct posix_acl *acl, int count)
{
	refcount_set(&acl->a_refcount, 1);
	acl->a_count = count;
}
EXPORT_SYMBOL(posix_acl_init);

/*
 * Allocate a new ACL with the specified number of entries.
 */
struct posix_acl *
posix_acl_alloc(int count, gfp_t flags)
{
	const size_t size = sizeof(struct posix_acl) +
	                    count * sizeof(struct posix_acl_entry);
	struct posix_acl *acl = kmalloc(size, flags);
	if (acl)
		posix_acl_init(acl, count);
	return acl;
}
EXPORT_SYMBOL(posix_acl_alloc);

/*
 * Clone an ACL.
 */
struct posix_acl *
posix_acl_clone(const struct posix_acl *acl, gfp_t flags)
{
	struct posix_acl *clone = NULL;

	if (acl) {
		int size = sizeof(struct posix_acl) + acl->a_count *
		           sizeof(struct posix_acl_entry);
		clone = kmemdup(acl, size, flags);
		if (clone)
			refcount_set(&clone->a_refcount, 1);
	}
	return clone;
}
EXPORT_SYMBOL_GPL(posix_acl_clone);

/*
 * Check if an acl is valid. Returns 0 if it is, or -E... otherwise.
 */
int
posix_acl_valid(struct user_namespace *user_ns, const struct posix_acl *acl)
{
	const struct posix_acl_entry *pa, *pe;
	int state = ACL_USER_OBJ;
	int needs_mask = 0;

	FOREACH_ACL_ENTRY(pa, acl, pe) {
		if (pa->e_perm & ~(ACL_READ|ACL_WRITE|ACL_EXECUTE))
			return -EINVAL;
		switch (pa->e_tag) {
			case ACL_USER_OBJ:
				if (state == ACL_USER_OBJ) {
					state = ACL_USER;
					break;
				}
				return -EINVAL;

			case ACL_USER:
				if (state != ACL_USER)
					return -EINVAL;
				if (!kuid_has_mapping(user_ns, pa->e_uid))
					return -EINVAL;
				needs_mask = 1;
				break;

			case ACL_GROUP_OBJ:
				if (state == ACL_USER) {
					state = ACL_GROUP;
					break;
				}
				return -EINVAL;

			case ACL_GROUP:
				if (state != ACL_GROUP)
					return -EINVAL;
				if (!kgid_has_mapping(user_ns, pa->e_gid))
					return -EINVAL;
				needs_mask = 1;
				break;

			case ACL_MASK:
				if (state != ACL_GROUP)
					return -EINVAL;
				state = ACL_OTHER;
				break;

			case ACL_OTHER:
				if (state == ACL_OTHER ||
				    (state == ACL_GROUP && !needs_mask)) {
					state = 0;
					break;
				}
				return -EINVAL;

			default:
				return -EINVAL;
		}
	}
	if (state == 0)
		return 0;
	return -EINVAL;
}
EXPORT_SYMBOL(posix_acl_valid);

/*
 * Returns 0 if the acl can be exactly represented in the traditional
 * file mode permission bits, or else 1. Returns -E... on error.
 */
int
posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p)
{
	const struct posix_acl_entry *pa, *pe;
	umode_t mode = 0;
	int not_equiv = 0;

	/*
	 * A null ACL can always be presented as mode bits.
	 */
	if (!acl)
		return 0;

	FOREACH_ACL_ENTRY(pa, acl, pe) {
		switch (pa->e_tag) {
			case ACL_USER_OBJ:
				mode |= (pa->e_perm & S_IRWXO) << 6;
				break;
			case ACL_GROUP_OBJ:
				mode |= (pa->e_perm & S_IRWXO) << 3;
				break;
			case ACL_OTHER:
				mode |= pa->e_perm & S_IRWXO;
				break;
			case ACL_MASK:
				mode = (mode & ~S_IRWXG) |
				       ((pa->e_perm & S_IRWXO) << 3);
				not_equiv = 1;
				break;
			case ACL_USER:
			case ACL_GROUP:
				not_equiv = 1;
				break;
			default:
				return -EINVAL;
		}
	}
        if (mode_p)
                *mode_p = (*mode_p & ~S_IRWXUGO) | mode;
        return not_equiv;
}
EXPORT_SYMBOL(posix_acl_equiv_mode);

/*
 * Create an ACL representing the file mode permission bits of an inode.
 */
struct posix_acl *
posix_acl_from_mode(umode_t mode, gfp_t flags)
{
	struct posix_acl *acl = posix_acl_alloc(3, flags);
	if (!acl)
		return ERR_PTR(-ENOMEM);

	acl->a_entries[0].e_tag  = ACL_USER_OBJ;
	acl->a_entries[0].e_perm = (mode & S_IRWXU) >> 6;

	acl->a_entries[1].e_tag  = ACL_GROUP_OBJ;
	acl->a_entries[1].e_perm = (mode & S_IRWXG) >> 3;

	acl->a_entries[2].e_tag  = ACL_OTHER;
	acl->a_entries[2].e_perm = (mode & S_IRWXO);
	return acl;
}
EXPORT_SYMBOL(posix_acl_from_mode);

/*
 * Return 0 if current is granted want access to the inode
 * by the acl. Returns -E... otherwise.
 */
int
posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
		     const struct posix_acl *acl, int want)
{
	const struct posix_acl_entry *pa, *pe, *mask_obj;
	struct user_namespace *fs_userns = i_user_ns(inode);
	int found = 0;
	vfsuid_t vfsuid;
	vfsgid_t vfsgid;

	want &= MAY_READ | MAY_WRITE | MAY_EXEC;

	FOREACH_ACL_ENTRY(pa, acl, pe) {
                switch(pa->e_tag) {
                        case ACL_USER_OBJ:
				/* (May have been checked already) */
				vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
				if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
                                        goto check_perm;
                                break;
                        case ACL_USER:
				vfsuid = make_vfsuid(mnt_userns, fs_userns,
						     pa->e_uid);
				if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
                                        goto mask;
				break;
                        case ACL_GROUP_OBJ:
				vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
				if (vfsgid_in_group_p(vfsgid)) {
					found = 1;
					if ((pa->e_perm & want) == want)
						goto mask;
                                }
				break;
                        case ACL_GROUP:
				vfsgid = make_vfsgid(mnt_userns, fs_userns,
						     pa->e_gid);
				if (vfsgid_in_group_p(vfsgid)) {
					found = 1;
					if ((pa->e_perm & want) == want)
						goto mask;
                                }
                                break;
                        case ACL_MASK:
                                break;
                        case ACL_OTHER:
				if (found)
					return -EACCES;
				else
					goto check_perm;
			default:
				return -EIO;
                }
        }
	return -EIO;

mask:
	for (mask_obj = pa+1; mask_obj != pe; mask_obj++) {
		if (mask_obj->e_tag == ACL_MASK) {
			if ((pa->e_perm & mask_obj->e_perm & want) == want)
				return 0;
			return -EACCES;
		}
	}

check_perm:
	if ((pa->e_perm & want) == want)
		return 0;
	return -EACCES;
}

/*
 * Modify acl when creating a new inode. The caller must ensure the acl is
 * only referenced once.
 *
 * mode_p initially must contain the mode parameter to the open() / creat()
 * system calls. All permissions that are not granted by the acl are removed.
 * The permissions in the acl are changed to reflect the mode_p parameter.
 */
static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p)
{
	struct posix_acl_entry *pa, *pe;
	struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL;
	umode_t mode = *mode_p;
	int not_equiv = 0;

	/* assert(atomic_read(acl->a_refcount) == 1); */

	FOREACH_ACL_ENTRY(pa, acl, pe) {
                switch(pa->e_tag) {
                        case ACL_USER_OBJ:
				pa->e_perm &= (mode >> 6) | ~S_IRWXO;
				mode &= (pa->e_perm << 6) | ~S_IRWXU;
				break;

			case ACL_USER:
			case ACL_GROUP:
				not_equiv = 1;
				break;

                        case ACL_GROUP_OBJ:
				group_obj = pa;
                                break;

                        case ACL_OTHER:
				pa->e_perm &= mode | ~S_IRWXO;
				mode &= pa->e_perm | ~S_IRWXO;
                                break;

                        case ACL_MASK:
				mask_obj = pa;
				not_equiv = 1;
                                break;

			default:
				return -EIO;
                }
        }

	if (mask_obj) {
		mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
		mode &= (mask_obj->e_perm << 3) | ~S_IRWXG;
	} else {
		if (!group_obj)
			return -EIO;
		group_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
		mode &= (group_obj->e_perm << 3) | ~S_IRWXG;
	}

	*mode_p = (*mode_p & ~S_IRWXUGO) | mode;
        return not_equiv;
}

/*
 * Modify the ACL for the chmod syscall.
 */
static int __posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode)
{
	struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL;
	struct posix_acl_entry *pa, *pe;

	/* assert(atomic_read(acl->a_refcount) == 1); */

	FOREACH_ACL_ENTRY(pa, acl, pe) {
		switch(pa->e_tag) {
			case ACL_USER_OBJ:
				pa->e_perm = (mode & S_IRWXU) >> 6;
				break;

			case ACL_USER:
			case ACL_GROUP:
				break;

			case ACL_GROUP_OBJ:
				group_obj = pa;
				break;

			case ACL_MASK:
				mask_obj = pa;
				break;

			case ACL_OTHER:
				pa->e_perm = (mode & S_IRWXO);
				break;

			default:
				return -EIO;
		}
	}

	if (mask_obj) {
		mask_obj->e_perm = (mode & S_IRWXG) >> 3;
	} else {
		if (!group_obj)
			return -EIO;
		group_obj->e_perm = (mode & S_IRWXG) >> 3;
	}

	return 0;
}

int
__posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p)
{
	struct posix_acl *clone = posix_acl_clone(*acl, gfp);
	int err = -ENOMEM;
	if (clone) {
		err = posix_acl_create_masq(clone, mode_p);
		if (err < 0) {
			posix_acl_release(clone);
			clone = NULL;
		}
	}
	posix_acl_release(*acl);
	*acl = clone;
	return err;
}
EXPORT_SYMBOL(__posix_acl_create);

int
__posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode)
{
	struct posix_acl *clone = posix_acl_clone(*acl, gfp);
	int err = -ENOMEM;
	if (clone) {
		err = __posix_acl_chmod_masq(clone, mode);
		if (err) {
			posix_acl_release(clone);
			clone = NULL;
		}
	}
	posix_acl_release(*acl);
	*acl = clone;
	return err;
}
EXPORT_SYMBOL(__posix_acl_chmod);

/**
 * posix_acl_chmod - chmod a posix acl
 *
 * @mnt_userns:	user namespace of the mount @inode was found from
 * @dentry:	dentry to check permissions on
 * @mode:	the new mode of @inode
 *
 * If the dentry has been found through an idmapped mount the user namespace of
 * the vfsmount must be passed through @mnt_userns. This function will then
 * take care to map the inode according to @mnt_userns before checking
 * permissions. On non-idmapped mounts or if permission checking is to be
 * performed on the raw inode simply passs init_user_ns.
 */
int
 posix_acl_chmod(struct user_namespace *mnt_userns, struct dentry *dentry,
		    umode_t mode)
{
	struct inode *inode = d_inode(dentry);
	struct posix_acl *acl;
	int ret = 0;

	if (!IS_POSIXACL(inode))
		return 0;
	if (!inode->i_op->set_acl)
		return -EOPNOTSUPP;

	acl = get_inode_acl(inode, ACL_TYPE_ACCESS);
	if (IS_ERR_OR_NULL(acl)) {
		if (acl == ERR_PTR(-EOPNOTSUPP))
			return 0;
		return PTR_ERR(acl);
	}

	ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode);
	if (ret)
		return ret;
	ret = inode->i_op->set_acl(mnt_userns, dentry, acl, ACL_TYPE_ACCESS);
	posix_acl_release(acl);
	return ret;
}
EXPORT_SYMBOL(posix_acl_chmod);

int
posix_acl_create(struct inode *dir, umode_t *mode,
		struct posix_acl **default_acl, struct posix_acl **acl)
{
	struct posix_acl *p;
	struct posix_acl *clone;
	int ret;

	*acl = NULL;
	*default_acl = NULL;

	if (S_ISLNK(*mode) || !IS_POSIXACL(dir))
		return 0;

	p = get_inode_acl(dir, ACL_TYPE_DEFAULT);
	if (!p || p == ERR_PTR(-EOPNOTSUPP)) {
		*mode &= ~current_umask();
		return 0;
	}
	if (IS_ERR(p))
		return PTR_ERR(p);

	ret = -ENOMEM;
	clone = posix_acl_clone(p, GFP_NOFS);
	if (!clone)
		goto err_release;

	ret = posix_acl_create_masq(clone, mode);
	if (ret < 0)
		goto err_release_clone;

	if (ret == 0)
		posix_acl_release(clone);
	else
		*acl = clone;

	if (!S_ISDIR(*mode))
		posix_acl_release(p);
	else
		*default_acl = p;

	return 0;

err_release_clone:
	posix_acl_release(clone);
err_release:
	posix_acl_release(p);
	return ret;
}
EXPORT_SYMBOL_GPL(posix_acl_create);

/**
 * posix_acl_update_mode  -  update mode in set_acl
 * @mnt_userns:	user namespace of the mount @inode was found from
 * @inode:	target inode
 * @mode_p:	mode (pointer) for update
 * @acl:	acl pointer
 *
 * Update the file mode when setting an ACL: compute the new file permission
 * bits based on the ACL.  In addition, if the ACL is equivalent to the new
 * file mode, set *@acl to NULL to indicate that no ACL should be set.
 *
 * As with chmod, clear the setgid bit if the caller is not in the owning group
 * or capable of CAP_FSETID (see inode_change_ok).
 *
 * If the inode has been found through an idmapped mount the user namespace of
 * the vfsmount must be passed through @mnt_userns. This function will then
 * take care to map the inode according to @mnt_userns before checking
 * permissions. On non-idmapped mounts or if permission checking is to be
 * performed on the raw inode simply passs init_user_ns.
 *
 * Called from set_acl inode operations.
 */
int posix_acl_update_mode(struct user_namespace *mnt_userns,
			  struct inode *inode, umode_t *mode_p,
			  struct posix_acl **acl)
{
	umode_t mode = inode->i_mode;
	int error;

	error = posix_acl_equiv_mode(*acl, &mode);
	if (error < 0)
		return error;
	if (error == 0)
		*acl = NULL;
	if (!vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode)) &&
	    !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
		mode &= ~S_ISGID;
	*mode_p = mode;
	return 0;
}
EXPORT_SYMBOL(posix_acl_update_mode);

/*
 * Fix up the uids and gids in posix acl extended attributes in place.
 */
static int posix_acl_fix_xattr_common(const void *value, size_t size)
{
	const struct posix_acl_xattr_header *header = value;
	int count;

	if (!header)
		return -EINVAL;
	if (size < sizeof(struct posix_acl_xattr_header))
		return -EINVAL;
	if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION))
		return -EOPNOTSUPP;

	count = posix_acl_xattr_count(size);
	if (count < 0)
		return -EINVAL;
	if (count == 0)
		return 0;

	return count;
}

/**
 * posix_acl_from_xattr - convert POSIX ACLs from backing store to VFS format
 * @userns: the filesystem's idmapping
 * @value: the uapi representation of POSIX ACLs
 * @size: the size of @void
 *
 * Filesystems that store POSIX ACLs in the unaltered uapi format should use
 * posix_acl_from_xattr() when reading them from the backing store and
 * converting them into the struct posix_acl VFS format. The helper is
 * specifically intended to be called from the acl inode operation.
 *
 * The posix_acl_from_xattr() function will map the raw {g,u}id values stored
 * in ACL_{GROUP,USER} entries into idmapping in @userns.
 *
 * Note that posix_acl_from_xattr() does not take idmapped mounts into account.
 * If it did it calling it from the get acl inode operation would return POSIX
 * ACLs mapped according to an idmapped mount which would mean that the value
 * couldn't be cached for the filesystem. Idmapped mounts are taken into
 * account on the fly during permission checking or right at the VFS -
 * userspace boundary before reporting them to the user.
 *
 * Return: Allocated struct posix_acl on success, NULL for a valid header but
 *         without actual POSIX ACL entries, or ERR_PTR() encoded error code.
 */
struct posix_acl *posix_acl_from_xattr(struct user_namespace *userns,
				       const void *value, size_t size)
{
	const struct posix_acl_xattr_header *header = value;
	const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end;
	int count;
	struct posix_acl *acl;
	struct posix_acl_entry *acl_e;

	count = posix_acl_fix_xattr_common(value, size);
	if (count < 0)
		return ERR_PTR(count);
	if (count == 0)
		return NULL;
	
	acl = posix_acl_alloc(count, GFP_NOFS);
	if (!acl)
		return ERR_PTR(-ENOMEM);
	acl_e = acl->a_entries;
	
	for (end = entry + count; entry != end; acl_e++, entry++) {
		acl_e->e_tag  = le16_to_cpu(entry->e_tag);
		acl_e->e_perm = le16_to_cpu(entry->e_perm);

		switch(acl_e->e_tag) {
			case ACL_USER_OBJ:
			case ACL_GROUP_OBJ:
			case ACL_MASK:
			case ACL_OTHER:
				break;

			case ACL_USER:
				acl_e->e_uid = make_kuid(userns,
						le32_to_cpu(entry->e_id));
				if (!uid_valid(acl_e->e_uid))
					goto fail;
				break;
			case ACL_GROUP:
				acl_e->e_gid = make_kgid(userns,
						le32_to_cpu(entry->e_id));
				if (!gid_valid(acl_e->e_gid))
					goto fail;
				break;

			default:
				goto fail;
		}
	}
	return acl;

fail:
	posix_acl_release(acl);
	return ERR_PTR(-EINVAL);
}
EXPORT_SYMBOL (posix_acl_from_xattr);

/*
 * Convert from in-memory to extended attribute representation.
 */
int
posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
		   void *buffer, size_t size)
{
	struct posix_acl_xattr_header *ext_acl = buffer;
	struct posix_acl_xattr_entry *ext_entry;
	int real_size, n;

	real_size = posix_acl_xattr_size(acl->a_count);
	if (!buffer)
		return real_size;
	if (real_size > size)
		return -ERANGE;

	ext_entry = (void *)(ext_acl + 1);
	ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION);

	for (n=0; n < acl->a_count; n++, ext_entry++) {
		const struct posix_acl_entry *acl_e = &acl->a_entries[n];
		ext_entry->e_tag  = cpu_to_le16(acl_e->e_tag);
		ext_entry->e_perm = cpu_to_le16(acl_e->e_perm);
		switch(acl_e->e_tag) {
		case ACL_USER:
			ext_entry->e_id =
				cpu_to_le32(from_kuid(user_ns, acl_e->e_uid));
			break;
		case ACL_GROUP:
			ext_entry->e_id =
				cpu_to_le32(from_kgid(user_ns, acl_e->e_gid));
			break;
		default:
			ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID);
			break;
		}
	}
	return real_size;
}
EXPORT_SYMBOL (posix_acl_to_xattr);

/**
 * vfs_posix_acl_to_xattr - convert from kernel to userspace representation
 * @idmap: idmap of the mount
 * @inode: inode the posix acls are set on
 * @acl: the posix acls as represented by the vfs
 * @buffer: the buffer into which to convert @acl
 * @size: size of @buffer
 *
 * This converts @acl from the VFS representation in the filesystem idmapping
 * to the uapi form reportable to userspace. And mount and caller idmappings
 * are handled appropriately.
 *
 * Return: On success, the size of the stored uapi posix acls, on error a
 * negative errno.
 */
static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap,
				      struct inode *inode,
				      const struct posix_acl *acl, void *buffer,
				      size_t size)

{
	struct posix_acl_xattr_header *ext_acl = buffer;
	struct posix_acl_xattr_entry *ext_entry;
	struct user_namespace *fs_userns, *caller_userns;
	struct user_namespace *mnt_userns;
	ssize_t real_size, n;
	vfsuid_t vfsuid;
	vfsgid_t vfsgid;

	real_size = posix_acl_xattr_size(acl->a_count);
	if (!buffer)
		return real_size;
	if (real_size > size)
		return -ERANGE;

	ext_entry = (void *)(ext_acl + 1);
	ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION);

	fs_userns = i_user_ns(inode);
	caller_userns = current_user_ns();
	mnt_userns = mnt_idmap_owner(idmap);
	for (n=0; n < acl->a_count; n++, ext_entry++) {
		const struct posix_acl_entry *acl_e = &acl->a_entries[n];
		ext_entry->e_tag  = cpu_to_le16(acl_e->e_tag);
		ext_entry->e_perm = cpu_to_le16(acl_e->e_perm);
		switch(acl_e->e_tag) {
		case ACL_USER:
			vfsuid = make_vfsuid(mnt_userns, fs_userns, acl_e->e_uid);
			ext_entry->e_id = cpu_to_le32(from_kuid(
				caller_userns, vfsuid_into_kuid(vfsuid)));
			break;
		case ACL_GROUP:
			vfsgid = make_vfsgid(mnt_userns, fs_userns, acl_e->e_gid);
			ext_entry->e_id = cpu_to_le32(from_kgid(
				caller_userns, vfsgid_into_kgid(vfsgid)));
			break;
		default:
			ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID);
			break;
		}
	}
	return real_size;
}

int
set_posix_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
	      int type, struct posix_acl *acl)
{
	struct inode *inode = d_inode(dentry);

	if (!IS_POSIXACL(inode))
		return -EOPNOTSUPP;
	if (!inode->i_op->set_acl)
		return -EOPNOTSUPP;

	if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
		return acl ? -EACCES : 0;
	if (!inode_owner_or_capable(mnt_userns, inode))
		return -EPERM;

	if (acl) {
		int ret = posix_acl_valid(inode->i_sb->s_user_ns, acl);
		if (ret)
			return ret;
	}
	return inode->i_op->set_acl(mnt_userns, dentry, acl, type);
}
EXPORT_SYMBOL(set_posix_acl);

static bool
posix_acl_xattr_list(struct dentry *dentry)
{
	return IS_POSIXACL(d_backing_inode(dentry));
}

const struct xattr_handler posix_acl_access_xattr_handler = {
	.name = XATTR_NAME_POSIX_ACL_ACCESS,
	.flags = ACL_TYPE_ACCESS,
	.list = posix_acl_xattr_list,
};
EXPORT_SYMBOL_GPL(posix_acl_access_xattr_handler);

const struct xattr_handler posix_acl_default_xattr_handler = {
	.name = XATTR_NAME_POSIX_ACL_DEFAULT,
	.flags = ACL_TYPE_DEFAULT,
	.list = posix_acl_xattr_list,
};
EXPORT_SYMBOL_GPL(posix_acl_default_xattr_handler);

int simple_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
		   struct posix_acl *acl, int type)
{
	int error;
	struct inode *inode = d_inode(dentry);

	if (type == ACL_TYPE_ACCESS) {
		error = posix_acl_update_mode(mnt_userns, inode,
				&inode->i_mode, &acl);
		if (error)
			return error;
	}

	inode->i_ctime = current_time(inode);
	if (IS_I_VERSION(inode))
		inode_inc_iversion(inode);
	set_cached_acl(inode, type, acl);
	return 0;
}

int simple_acl_create(struct inode *dir, struct inode *inode)
{
	struct posix_acl *default_acl, *acl;
	int error;

	error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
	if (error)
		return error;

	set_cached_acl(inode, ACL_TYPE_DEFAULT, default_acl);
	set_cached_acl(inode, ACL_TYPE_ACCESS, acl);

	if (default_acl)
		posix_acl_release(default_acl);
	if (acl)
		posix_acl_release(acl);
	return 0;
}

static int vfs_set_acl_idmapped_mnt(struct user_namespace *mnt_userns,
				    struct user_namespace *fs_userns,
				    struct posix_acl *acl)
{
	for (int n = 0; n < acl->a_count; n++) {
		struct posix_acl_entry *acl_e = &acl->a_entries[n];

		switch (acl_e->e_tag) {
		case ACL_USER:
			acl_e->e_uid = from_vfsuid(mnt_userns, fs_userns,
						   VFSUIDT_INIT(acl_e->e_uid));
			break;
		case ACL_GROUP:
			acl_e->e_gid = from_vfsgid(mnt_userns, fs_userns,
						   VFSGIDT_INIT(acl_e->e_gid));
			break;
		}
	}

	return 0;
}

/**
 * vfs_set_acl - set posix acls
 * @mnt_userns: user namespace of the mount
 * @dentry: the dentry based on which to set the posix acls
 * @acl_name: the name of the posix acl
 * @kacl: the posix acls in the appropriate VFS format
 *
 * This function sets @kacl. The caller must all posix_acl_release() on @kacl
 * afterwards.
 *
 * Return: On success 0, on error negative errno.
 */
int vfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
		const char *acl_name, struct posix_acl *kacl)
{
	int acl_type;
	int error;
	struct inode *inode = d_inode(dentry);
	struct inode *delegated_inode = NULL;

	acl_type = posix_acl_type(acl_name);
	if (acl_type < 0)
		return -EINVAL;

	if (kacl) {
		/*
		 * If we're on an idmapped mount translate from mount specific
		 * vfs{g,u}id_t into global filesystem k{g,u}id_t.
		 * Afterwards we can cache the POSIX ACLs filesystem wide and -
		 * if this is a filesystem with a backing store - ultimately
		 * translate them to backing store values.
		 */
		error = vfs_set_acl_idmapped_mnt(mnt_userns, i_user_ns(inode), kacl);
		if (error)
			return error;
	}

retry_deleg:
	inode_lock(inode);

	/*
	 * We only care about restrictions the inode struct itself places upon
	 * us otherwise POSIX ACLs aren't subject to any VFS restrictions.
	 */
	error = may_write_xattr(mnt_userns, inode);
	if (error)
		goto out_inode_unlock;

	error = security_inode_set_acl(mnt_userns, dentry, acl_name, kacl);
	if (error)
		goto out_inode_unlock;

	error = try_break_deleg(inode, &delegated_inode);
	if (error)
		goto out_inode_unlock;

	if (inode->i_opflags & IOP_XATTR)
		error = set_posix_acl(mnt_userns, dentry, acl_type, kacl);
	else if (unlikely(is_bad_inode(inode)))
		error = -EIO;
	else
		error = -EOPNOTSUPP;
	if (!error) {
		fsnotify_xattr(dentry);
		evm_inode_post_set_acl(dentry, acl_name, kacl);
	}

out_inode_unlock:
	inode_unlock(inode);

	if (delegated_inode) {
		error = break_deleg_wait(&delegated_inode);
		if (!error)
			goto retry_deleg;
	}

	return error;
}
EXPORT_SYMBOL_GPL(vfs_set_acl);

/**
 * vfs_get_acl - get posix acls
 * @mnt_userns: user namespace of the mount
 * @dentry: the dentry based on which to retrieve the posix acls
 * @acl_name: the name of the posix acl
 *
 * This function retrieves @kacl from the filesystem. The caller must all
 * posix_acl_release() on @kacl.
 *
 * Return: On success POSIX ACLs in VFS format, on error negative errno.
 */
struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns,
			      struct dentry *dentry, const char *acl_name)
{
	struct inode *inode = d_inode(dentry);
	struct posix_acl *acl;
	int acl_type, error;

	acl_type = posix_acl_type(acl_name);
	if (acl_type < 0)
		return ERR_PTR(-EINVAL);

	/*
	 * The VFS has no restrictions on reading POSIX ACLs so calling
	 * something like xattr_permission() isn't needed. Only LSMs get a say.
	 */
	error = security_inode_get_acl(mnt_userns, dentry, acl_name);
	if (error)
		return ERR_PTR(error);

	if (!IS_POSIXACL(inode))
		return ERR_PTR(-EOPNOTSUPP);
	if (S_ISLNK(inode->i_mode))
		return ERR_PTR(-EOPNOTSUPP);

	acl = __get_acl(mnt_userns, dentry, inode, acl_type);
	if (IS_ERR(acl))
		return acl;
	if (!acl)
		return ERR_PTR(-ENODATA);

	return acl;
}
EXPORT_SYMBOL_GPL(vfs_get_acl);

/**
 * vfs_remove_acl - remove posix acls
 * @mnt_userns: user namespace of the mount
 * @dentry: the dentry based on which to retrieve the posix acls
 * @acl_name: the name of the posix acl
 *
 * This function removes posix acls.
 *
 * Return: On success 0, on error negative errno.
 */
int vfs_remove_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
		   const char *acl_name)
{
	int acl_type;
	int error;
	struct inode *inode = d_inode(dentry);
	struct inode *delegated_inode = NULL;

	acl_type = posix_acl_type(acl_name);
	if (acl_type < 0)
		return -EINVAL;

retry_deleg:
	inode_lock(inode);

	/*
	 * We only care about restrictions the inode struct itself places upon
	 * us otherwise POSIX ACLs aren't subject to any VFS restrictions.
	 */
	error = may_write_xattr(mnt_userns, inode);
	if (error)
		goto out_inode_unlock;

	error = security_inode_remove_acl(mnt_userns, dentry, acl_name);
	if (error)
		goto out_inode_unlock;

	error = try_break_deleg(inode, &delegated_inode);
	if (error)
		goto out_inode_unlock;

	if (inode->i_opflags & IOP_XATTR)
		error = set_posix_acl(mnt_userns, dentry, acl_type, NULL);
	else if (unlikely(is_bad_inode(inode)))
		error = -EIO;
	else
		error = -EOPNOTSUPP;
	if (!error) {
		fsnotify_xattr(dentry);
		evm_inode_post_remove_acl(mnt_userns, dentry, acl_name);
	}

out_inode_unlock:
	inode_unlock(inode);

	if (delegated_inode) {
		error = break_deleg_wait(&delegated_inode);
		if (!error)
			goto retry_deleg;
	}

	return error;
}
EXPORT_SYMBOL_GPL(vfs_remove_acl);

int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
	       const char *acl_name, const void *kvalue, size_t size)
{
	int error;
	struct posix_acl *acl = NULL;

	if (size) {
		/*
		 * Note that posix_acl_from_xattr() uses GFP_NOFS when it
		 * probably doesn't need to here.
		 */
		acl = posix_acl_from_xattr(current_user_ns(), kvalue, size);
		if (IS_ERR(acl))
			return PTR_ERR(acl);
	}

	error = vfs_set_acl(mnt_idmap_owner(idmap), dentry, acl_name, acl);
	posix_acl_release(acl);
	return error;
}

ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry,
		   const char *acl_name, void *kvalue, size_t size)
{
	ssize_t error;
	struct posix_acl *acl;

	acl = vfs_get_acl(mnt_idmap_owner(idmap), dentry, acl_name);
	if (IS_ERR(acl))
		return PTR_ERR(acl);

	error = vfs_posix_acl_to_xattr(idmap, d_inode(dentry),
				       acl, kvalue, size);
	posix_acl_release(acl);
	return error;
}