summaryrefslogtreecommitdiffstats
path: root/fs/overlayfs/copy_up.c
blob: 696478f09cc1b459cbe26502ae4db81ec91300b3 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *
 * Copyright (C) 2011 Novell Inc.
 */

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fileattr.h>
#include <linux/splice.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include <linux/uaccess.h>
#include <linux/sched/signal.h>
#include <linux/cred.h>
#include <linux/namei.h>
#include <linux/fdtable.h>
#include <linux/ratelimit.h>
#include <linux/exportfs.h>
#include "overlayfs.h"

#define OVL_COPY_UP_CHUNK_SIZE (1 << 20)

static int ovl_ccup_set(const char *buf, const struct kernel_param *param)
{
	pr_warn("\"check_copy_up\" module option is obsolete\n");
	return 0;
}

static int ovl_ccup_get(char *buf, const struct kernel_param *param)
{
	return sprintf(buf, "N\n");
}

module_param_call(check_copy_up, ovl_ccup_set, ovl_ccup_get, NULL, 0644);
MODULE_PARM_DESC(check_copy_up, "Obsolete; does nothing");

static bool ovl_must_copy_xattr(const char *name)
{
	return !strcmp(name, XATTR_POSIX_ACL_ACCESS) ||
	       !strcmp(name, XATTR_POSIX_ACL_DEFAULT) ||
	       !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN);
}

static int ovl_copy_acl(struct ovl_fs *ofs, const struct path *path,
			struct dentry *dentry, const char *acl_name)
{
	int err;
	struct posix_acl *clone, *real_acl = NULL;

	real_acl = ovl_get_acl_path(path, acl_name, false);
	if (!real_acl)
		return 0;

	if (IS_ERR(real_acl)) {
		err = PTR_ERR(real_acl);
		if (err == -ENODATA || err == -EOPNOTSUPP)
			return 0;
		return err;
	}

	clone = posix_acl_clone(real_acl, GFP_KERNEL);
	posix_acl_release(real_acl); /* release original acl */
	if (!clone)
		return -ENOMEM;

	err = ovl_do_set_acl(ofs, dentry, acl_name, clone);

	/* release cloned acl */
	posix_acl_release(clone);
	return err;
}

int ovl_copy_xattr(struct super_block *sb, const struct path *oldpath, struct dentry *new)
{
	struct dentry *old = oldpath->dentry;
	ssize_t list_size, size, value_size = 0;
	char *buf, *name, *value = NULL;
	int error = 0;
	size_t slen;

	if (!old->d_inode->i_op->listxattr || !new->d_inode->i_op->listxattr)
		return 0;

	list_size = vfs_listxattr(old, NULL, 0);
	if (list_size <= 0) {
		if (list_size == -EOPNOTSUPP)
			return 0;
		return list_size;
	}

	buf = kvzalloc(list_size, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	list_size = vfs_listxattr(old, buf, list_size);
	if (list_size <= 0) {
		error = list_size;
		goto out;
	}

	for (name = buf; list_size; name += slen) {
		slen = strnlen(name, list_size) + 1;

		/* underlying fs providing us with an broken xattr list? */
		if (WARN_ON(slen > list_size)) {
			error = -EIO;
			break;
		}
		list_size -= slen;

		if (ovl_is_private_xattr(sb, name))
			continue;

		error = security_inode_copy_up_xattr(name);
		if (error < 0 && error != -EOPNOTSUPP)
			break;
		if (error == 1) {
			error = 0;
			continue; /* Discard */
		}

		if (is_posix_acl_xattr(name)) {
			error = ovl_copy_acl(OVL_FS(sb), oldpath, new, name);
			if (!error)
				continue;
			/* POSIX ACLs must be copied. */
			break;
		}

retry:
		size = ovl_do_getxattr(oldpath, name, value, value_size);
		if (size == -ERANGE)
			size = ovl_do_getxattr(oldpath, name, NULL, 0);

		if (size < 0) {
			error = size;
			break;
		}

		if (size > value_size) {
			void *new;

			new = kvmalloc(size, GFP_KERNEL);
			if (!new) {
				error = -ENOMEM;
				break;
			}
			kvfree(value);
			value = new;
			value_size = size;
			goto retry;
		}

		error = ovl_do_setxattr(OVL_FS(sb), new, name, value, size, 0);
		if (error) {
			if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name))
				break;

			/* Ignore failure to copy unknown xattrs */
			error = 0;
		}
	}
	kvfree(value);
out:
	kvfree(buf);
	return error;
}

static int ovl_copy_fileattr(struct inode *inode, const struct path *old,
			     const struct path *new)
{
	struct fileattr oldfa = { .flags_valid = true };
	struct fileattr newfa = { .flags_valid = true };
	int err;

	err = ovl_real_fileattr_get(old, &oldfa);
	if (err) {
		/* Ntfs-3g returns -EINVAL for "no fileattr support" */
		if (err == -ENOTTY || err == -EINVAL)
			return 0;
		pr_warn("failed to retrieve lower fileattr (%pd2, err=%i)\n",
			old->dentry, err);
		return err;
	}

	/*
	 * We cannot set immutable and append-only flags on upper inode,
	 * because we would not be able to link upper inode to upper dir
	 * not set overlay private xattr on upper inode.
	 * Store these flags in overlay.protattr xattr instead.
	 */
	if (oldfa.flags & OVL_PROT_FS_FLAGS_MASK) {
		err = ovl_set_protattr(inode, new->dentry, &oldfa);
		if (err == -EPERM)
			pr_warn_once("copying fileattr: no xattr on upper\n");
		else if (err)
			return err;
	}

	/* Don't bother copying flags if none are set */
	if (!(oldfa.flags & OVL_COPY_FS_FLAGS_MASK))
		return 0;

	err = ovl_real_fileattr_get(new, &newfa);
	if (err) {
		/*
		 * Returning an error if upper doesn't support fileattr will
		 * result in a regression, so revert to the old behavior.
		 */
		if (err == -ENOTTY || err == -EINVAL) {
			pr_warn_once("copying fileattr: no support on upper\n");
			return 0;
		}
		pr_warn("failed to retrieve upper fileattr (%pd2, err=%i)\n",
			new->dentry, err);
		return err;
	}

	BUILD_BUG_ON(OVL_COPY_FS_FLAGS_MASK & ~FS_COMMON_FL);
	newfa.flags &= ~OVL_COPY_FS_FLAGS_MASK;
	newfa.flags |= (oldfa.flags & OVL_COPY_FS_FLAGS_MASK);

	BUILD_BUG_ON(OVL_COPY_FSX_FLAGS_MASK & ~FS_XFLAG_COMMON);
	newfa.fsx_xflags &= ~OVL_COPY_FSX_FLAGS_MASK;
	newfa.fsx_xflags |= (oldfa.fsx_xflags & OVL_COPY_FSX_FLAGS_MASK);

	return ovl_real_fileattr_set(new, &newfa);
}

static int ovl_verify_area(loff_t pos, loff_t pos2, loff_t len, loff_t totlen)
{
	loff_t tmp;

	if (WARN_ON_ONCE(pos != pos2))
		return -EIO;
	if (WARN_ON_ONCE(pos < 0 || len < 0 || totlen < 0))
		return -EIO;
	if (WARN_ON_ONCE(check_add_overflow(pos, len, &tmp)))
		return -EIO;
	return 0;
}

static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
			    struct file *new_file, loff_t len)
{
	struct path datapath;
	struct file *old_file;
	loff_t old_pos = 0;
	loff_t new_pos = 0;
	loff_t cloned;
	loff_t data_pos = -1;
	loff_t hole_len;
	bool skip_hole = false;
	int error = 0;

	ovl_path_lowerdata(dentry, &datapath);
	if (WARN_ON_ONCE(datapath.dentry == NULL) ||
	    WARN_ON_ONCE(len < 0))
		return -EIO;

	old_file = ovl_path_open(&datapath, O_LARGEFILE | O_RDONLY);
	if (IS_ERR(old_file))
		return PTR_ERR(old_file);

	error = rw_verify_area(READ, old_file, &old_pos, len);
	if (!error)
		error = rw_verify_area(WRITE, new_file, &new_pos, len);
	if (error)
		goto out_fput;

	/* Try to use clone_file_range to clone up within the same fs */
	ovl_start_write(dentry);
	cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0);
	ovl_end_write(dentry);
	if (cloned == len)
		goto out_fput;
	/* Couldn't clone, so now we try to copy the data */

	/* Check if lower fs supports seek operation */
	if (old_file->f_mode & FMODE_LSEEK)
		skip_hole = true;

	while (len) {
		size_t this_len = OVL_COPY_UP_CHUNK_SIZE;
		ssize_t bytes;

		if (len < this_len)
			this_len = len;

		if (signal_pending_state(TASK_KILLABLE, current)) {
			error = -EINTR;
			break;
		}

		/*
		 * Fill zero for hole will cost unnecessary disk space
		 * and meanwhile slow down the copy-up speed, so we do
		 * an optimization for hole during copy-up, it relies
		 * on SEEK_DATA implementation in lower fs so if lower
		 * fs does not support it, copy-up will behave as before.
		 *
		 * Detail logic of hole detection as below:
		 * When we detect next data position is larger than current
		 * position we will skip that hole, otherwise we copy
		 * data in the size of OVL_COPY_UP_CHUNK_SIZE. Actually,
		 * it may not recognize all kind of holes and sometimes
		 * only skips partial of hole area. However, it will be
		 * enough for most of the use cases.
		 *
		 * We do not hold upper sb_writers throughout the loop to avert
		 * lockdep warning with llseek of lower file in nested overlay:
		 * - upper sb_writers
		 * -- lower ovl_inode_lock (ovl_llseek)
		 */
		if (skip_hole && data_pos < old_pos) {
			data_pos = vfs_llseek(old_file, old_pos, SEEK_DATA);
			if (data_pos > old_pos) {
				hole_len = data_pos - old_pos;
				len -= hole_len;
				old_pos = new_pos = data_pos;
				continue;
			} else if (data_pos == -ENXIO) {
				break;
			} else if (data_pos < 0) {
				skip_hole = false;
			}
		}

		error = ovl_verify_area(old_pos, new_pos, this_len, len);
		if (error)
			break;

		bytes = do_splice_direct(old_file, &old_pos,
					 new_file, &new_pos,
					 this_len, SPLICE_F_MOVE);
		if (bytes <= 0) {
			error = bytes;
			break;
		}
		WARN_ON(old_pos != new_pos);

		len -= bytes;
	}
	if (!error && ovl_should_sync(ofs))
		error = vfs_fsync(new_file, 0);
out_fput:
	fput(old_file);
	return error;
}

static int ovl_set_size(struct ovl_fs *ofs,
			struct dentry *upperdentry, struct kstat *stat)
{
	struct iattr attr = {
		.ia_valid = ATTR_SIZE,
		.ia_size = stat->size,
	};

	return ovl_do_notify_change(ofs, upperdentry, &attr);
}

static int ovl_set_timestamps(struct ovl_fs *ofs, struct dentry *upperdentry,
			      struct kstat *stat)
{
	struct iattr attr = {
		.ia_valid =
		     ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_CTIME,
		.ia_atime = stat->atime,
		.ia_mtime = stat->mtime,
	};

	return ovl_do_notify_change(ofs, upperdentry, &attr);
}

int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upperdentry,
		 struct kstat *stat)
{
	int err = 0;

	if (!S_ISLNK(stat->mode)) {
		struct iattr attr = {
			.ia_valid = ATTR_MODE,
			.ia_mode = stat->mode,
		};
		err = ovl_do_notify_change(ofs, upperdentry, &attr);
	}
	if (!err) {
		struct iattr attr = {
			.ia_valid = ATTR_UID | ATTR_GID,
			.ia_vfsuid = VFSUIDT_INIT(stat->uid),
			.ia_vfsgid = VFSGIDT_INIT(stat->gid),
		};
		err = ovl_do_notify_change(ofs, upperdentry, &attr);
	}
	if (!err)
		ovl_set_timestamps(ofs, upperdentry, stat);

	return err;
}

struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real,
				  bool is_upper)
{
	struct ovl_fh *fh;
	int fh_type, dwords;
	int buflen = MAX_HANDLE_SZ;
	uuid_t *uuid = &real->d_sb->s_uuid;
	int err;

	/* Make sure the real fid stays 32bit aligned */
	BUILD_BUG_ON(OVL_FH_FID_OFFSET % 4);
	BUILD_BUG_ON(MAX_HANDLE_SZ + OVL_FH_FID_OFFSET > 255);

	fh = kzalloc(buflen + OVL_FH_FID_OFFSET, GFP_KERNEL);
	if (!fh)
		return ERR_PTR(-ENOMEM);

	/*
	 * We encode a non-connectable file handle for non-dir, because we
	 * only need to find the lower inode number and we don't want to pay
	 * the price or reconnecting the dentry.
	 */
	dwords = buflen >> 2;
	fh_type = exportfs_encode_fh(real, (void *)fh->fb.fid, &dwords, 0);
	buflen = (dwords << 2);

	err = -EIO;
	if (WARN_ON(fh_type < 0) ||
	    WARN_ON(buflen > MAX_HANDLE_SZ) ||
	    WARN_ON(fh_type == FILEID_INVALID))
		goto out_err;

	fh->fb.version = OVL_FH_VERSION;
	fh->fb.magic = OVL_FH_MAGIC;
	fh->fb.type = fh_type;
	fh->fb.flags = OVL_FH_FLAG_CPU_ENDIAN;
	/*
	 * When we will want to decode an overlay dentry from this handle
	 * and all layers are on the same fs, if we get a disconncted real
	 * dentry when we decode fid, the only way to tell if we should assign
	 * it to upperdentry or to lowerstack is by checking this flag.
	 */
	if (is_upper)
		fh->fb.flags |= OVL_FH_FLAG_PATH_UPPER;
	fh->fb.len = sizeof(fh->fb) + buflen;
	if (ovl_origin_uuid(ofs))
		fh->fb.uuid = *uuid;

	return fh;

out_err:
	kfree(fh);
	return ERR_PTR(err);
}

struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin)
{
	/*
	 * When lower layer doesn't support export operations store a 'null' fh,
	 * so we can use the overlay.origin xattr to distignuish between a copy
	 * up and a pure upper inode.
	 */
	if (!ovl_can_decode_fh(origin->d_sb))
		return NULL;

	return ovl_encode_real_fh(ofs, origin, false);
}

int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh,
		      struct dentry *upper)
{
	int err;

	/*
	 * Do not fail when upper doesn't support xattrs.
	 */
	err = ovl_check_setxattr(ofs, upper, OVL_XATTR_ORIGIN, fh->buf,
				 fh ? fh->fb.len : 0, 0);

	/* Ignore -EPERM from setting "user.*" on symlink/special */
	return err == -EPERM ? 0 : err;
}

/* Store file handle of @upper dir in @index dir entry */
static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper,
			    struct dentry *index)
{
	const struct ovl_fh *fh;
	int err;

	fh = ovl_encode_real_fh(ofs, upper, true);
	if (IS_ERR(fh))
		return PTR_ERR(fh);

	err = ovl_setxattr(ofs, index, OVL_XATTR_UPPER, fh->buf, fh->fb.len);

	kfree(fh);
	return err;
}

/*
 * Create and install index entry.
 *
 * Caller must hold i_mutex on indexdir.
 */
static int ovl_create_index(struct dentry *dentry, const struct ovl_fh *fh,
			    struct dentry *upper)
{
	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
	struct dentry *indexdir = ovl_indexdir(dentry->d_sb);
	struct inode *dir = d_inode(indexdir);
	struct dentry *index = NULL;
	struct dentry *temp = NULL;
	struct qstr name = { };
	int err;

	/*
	 * For now this is only used for creating index entry for directories,
	 * because non-dir are copied up directly to index and then hardlinked
	 * to upper dir.
	 *
	 * TODO: implement create index for non-dir, so we can call it when
	 * encoding file handle for non-dir in case index does not exist.
	 */
	if (WARN_ON(!d_is_dir(dentry)))
		return -EIO;

	/* Directory not expected to be indexed before copy up */
	if (WARN_ON(ovl_test_flag(OVL_INDEX, d_inode(dentry))))
		return -EIO;

	err = ovl_get_index_name_fh(fh, &name);
	if (err)
		return err;

	temp = ovl_create_temp(ofs, indexdir, OVL_CATTR(S_IFDIR | 0));
	err = PTR_ERR(temp);
	if (IS_ERR(temp))
		goto free_name;

	err = ovl_set_upper_fh(ofs, upper, temp);
	if (err)
		goto out;

	index = ovl_lookup_upper(ofs, name.name, indexdir, name.len);
	if (IS_ERR(index)) {
		err = PTR_ERR(index);
	} else {
		err = ovl_do_rename(ofs, dir, temp, dir, index, 0);
		dput(index);
	}
out:
	if (err)
		ovl_cleanup(ofs, dir, temp);
	dput(temp);
free_name:
	kfree(name.name);
	return err;
}

struct ovl_copy_up_ctx {
	struct dentry *parent;
	struct dentry *dentry;
	struct path lowerpath;
	struct kstat stat;
	struct kstat pstat;
	const char *link;
	struct dentry *destdir;
	struct qstr destname;
	struct dentry *workdir;
	const struct ovl_fh *origin_fh;
	bool origin;
	bool indexed;
	bool metacopy;
	bool metacopy_digest;
};

static int ovl_link_up(struct ovl_copy_up_ctx *c)
{
	int err;
	struct dentry *upper;
	struct dentry *upperdir = ovl_dentry_upper(c->parent);
	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
	struct inode *udir = d_inode(upperdir);

	ovl_start_write(c->dentry);

	/* Mark parent "impure" because it may now contain non-pure upper */
	err = ovl_set_impure(c->parent, upperdir);
	if (err)
		goto out;

	err = ovl_set_nlink_lower(c->dentry);
	if (err)
		goto out;

	inode_lock_nested(udir, I_MUTEX_PARENT);
	upper = ovl_lookup_upper(ofs, c->dentry->d_name.name, upperdir,
				 c->dentry->d_name.len);
	err = PTR_ERR(upper);
	if (!IS_ERR(upper)) {
		err = ovl_do_link(ofs, ovl_dentry_upper(c->dentry), udir, upper);
		dput(upper);

		if (!err) {
			/* Restore timestamps on parent (best effort) */
			ovl_set_timestamps(ofs, upperdir, &c->pstat);
			ovl_dentry_set_upper_alias(c->dentry);
			ovl_dentry_update_reval(c->dentry, upper);
		}
	}
	inode_unlock(udir);
	if (err)
		goto out;

	err = ovl_set_nlink_upper(c->dentry);

out:
	ovl_end_write(c->dentry);
	return err;
}

static int ovl_copy_up_data(struct ovl_copy_up_ctx *c, const struct path *temp)
{
	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
	struct file *new_file;
	int err;

	if (!S_ISREG(c->stat.mode) || c->metacopy || !c->stat.size)
		return 0;

	new_file = ovl_path_open(temp, O_LARGEFILE | O_WRONLY);
	if (IS_ERR(new_file))
		return PTR_ERR(new_file);

	err = ovl_copy_up_file(ofs, c->dentry, new_file, c->stat.size);
	fput(new_file);

	return err;
}

static int ovl_copy_up_metadata(struct ovl_copy_up_ctx *c, struct dentry *temp)
{
	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
	struct inode *inode = d_inode(c->dentry);
	struct path upperpath = { .mnt = ovl_upper_mnt(ofs), .dentry = temp };
	int err;

	err = ovl_copy_xattr(c->dentry->d_sb, &c->lowerpath, temp);
	if (err)
		return err;

	if (inode->i_flags & OVL_COPY_I_FLAGS_MASK &&
	    (S_ISREG(c->stat.mode) || S_ISDIR(c->stat.mode))) {
		/*
		 * Copy the fileattr inode flags that are the source of already
		 * copied i_flags
		 */
		err = ovl_copy_fileattr(inode, &c->lowerpath, &upperpath);
		if (err)
			return err;
	}

	/*
	 * Store identifier of lower inode in upper inode xattr to
	 * allow lookup of the copy up origin inode.
	 *
	 * Don't set origin when we are breaking the association with a lower
	 * hard link.
	 */
	if (c->origin) {
		err = ovl_set_origin_fh(ofs, c->origin_fh, temp);
		if (err)
			return err;
	}

	if (c->metacopy) {
		struct path lowerdatapath;
		struct ovl_metacopy metacopy_data = OVL_METACOPY_INIT;

		ovl_path_lowerdata(c->dentry, &lowerdatapath);
		if (WARN_ON_ONCE(lowerdatapath.dentry == NULL))
			return -EIO;
		err = ovl_get_verity_digest(ofs, &lowerdatapath, &metacopy_data);
		if (err)
			return err;

		if (metacopy_data.digest_algo)
			c->metacopy_digest = true;

		err = ovl_set_metacopy_xattr(ofs, temp, &metacopy_data);
		if (err)
			return err;
	}

	inode_lock(temp->d_inode);
	if (S_ISREG(c->stat.mode))
		err = ovl_set_size(ofs, temp, &c->stat);
	if (!err)
		err = ovl_set_attr(ofs, temp, &c->stat);
	inode_unlock(temp->d_inode);

	return err;
}

struct ovl_cu_creds {
	const struct cred *old;
	struct cred *new;
};

static int ovl_prep_cu_creds(struct dentry *dentry, struct ovl_cu_creds *cc)
{
	int err;

	cc->old = cc->new = NULL;
	err = security_inode_copy_up(dentry, &cc->new);
	if (err < 0)
		return err;

	if (cc->new)
		cc->old = override_creds(cc->new);

	return 0;
}

static void ovl_revert_cu_creds(struct ovl_cu_creds *cc)
{
	if (cc->new) {
		revert_creds(cc->old);
		put_cred(cc->new);
	}
}

/*
 * Copyup using workdir to prepare temp file.  Used when copying up directories,
 * special files or when upper fs doesn't support O_TMPFILE.
 */
static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c)
{
	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
	struct inode *inode;
	struct inode *udir = d_inode(c->destdir), *wdir = d_inode(c->workdir);
	struct path path = { .mnt = ovl_upper_mnt(ofs) };
	struct dentry *temp, *upper;
	struct ovl_cu_creds cc;
	int err;
	struct ovl_cattr cattr = {
		/* Can't properly set mode on creation because of the umask */
		.mode = c->stat.mode & S_IFMT,
		.rdev = c->stat.rdev,
		.link = c->link
	};

	err = ovl_prep_cu_creds(c->dentry, &cc);
	if (err)
		return err;

	ovl_start_write(c->dentry);
	inode_lock(wdir);
	temp = ovl_create_temp(ofs, c->workdir, &cattr);
	inode_unlock(wdir);
	ovl_end_write(c->dentry);
	ovl_revert_cu_creds(&cc);

	if (IS_ERR(temp))
		return PTR_ERR(temp);

	/*
	 * Copy up data first and then xattrs. Writing data after
	 * xattrs will remove security.capability xattr automatically.
	 */
	path.dentry = temp;
	err = ovl_copy_up_data(c, &path);
	/*
	 * We cannot hold lock_rename() throughout this helper, because of
	 * lock ordering with sb_writers, which shouldn't be held when calling
	 * ovl_copy_up_data(), so lock workdir and destdir and make sure that
	 * temp wasn't moved before copy up completion or cleanup.
	 */
	ovl_start_write(c->dentry);
	if (lock_rename(c->workdir, c->destdir) != NULL ||
	    temp->d_parent != c->workdir) {
		/* temp or workdir moved underneath us? abort without cleanup */
		dput(temp);
		err = -EIO;
		goto unlock;
	} else if (err) {
		goto cleanup;
	}

	err = ovl_copy_up_metadata(c, temp);
	if (err)
		goto cleanup;

	if (S_ISDIR(c->stat.mode) && c->indexed) {
		err = ovl_create_index(c->dentry, c->origin_fh, temp);
		if (err)
			goto cleanup;
	}

	upper = ovl_lookup_upper(ofs, c->destname.name, c->destdir,
				 c->destname.len);
	err = PTR_ERR(upper);
	if (IS_ERR(upper))
		goto cleanup;

	err = ovl_do_rename(ofs, wdir, temp, udir, upper, 0);
	dput(upper);
	if (err)
		goto cleanup;

	inode = d_inode(c->dentry);
	if (c->metacopy_digest)
		ovl_set_flag(OVL_HAS_DIGEST, inode);
	else
		ovl_clear_flag(OVL_HAS_DIGEST, inode);
	ovl_clear_flag(OVL_VERIFIED_DIGEST, inode);

	if (!c->metacopy)
		ovl_set_upperdata(inode);
	ovl_inode_update(inode, temp);
	if (S_ISDIR(inode->i_mode))
		ovl_set_flag(OVL_WHITEOUTS, inode);
unlock:
	unlock_rename(c->workdir, c->destdir);
	ovl_end_write(c->dentry);

	return err;

cleanup:
	ovl_cleanup(ofs, wdir, temp);
	dput(temp);
	goto unlock;
}

/* Copyup using O_TMPFILE which does not require cross dir locking */
static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c)
{
	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
	struct inode *udir = d_inode(c->destdir);
	struct dentry *temp, *upper;
	struct file *tmpfile;
	struct ovl_cu_creds cc;
	int err;

	err = ovl_prep_cu_creds(c->dentry, &cc);
	if (err)
		return err;

	ovl_start_write(c->dentry);
	tmpfile = ovl_do_tmpfile(ofs, c->workdir, c->stat.mode);
	ovl_end_write(c->dentry);
	ovl_revert_cu_creds(&cc);
	if (IS_ERR(tmpfile))
		return PTR_ERR(tmpfile);

	temp = tmpfile->f_path.dentry;
	if (!c->metacopy && c->stat.size) {
		err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size);
		if (err)
			goto out_fput;
	}

	ovl_start_write(c->dentry);

	err = ovl_copy_up_metadata(c, temp);
	if (err)
		goto out;

	inode_lock_nested(udir, I_MUTEX_PARENT);

	upper = ovl_lookup_upper(ofs, c->destname.name, c->destdir,
				 c->destname.len);
	err = PTR_ERR(upper);
	if (!IS_ERR(upper)) {
		err = ovl_do_link(ofs, temp, udir, upper);
		dput(upper);
	}
	inode_unlock(udir);

	if (err)
		goto out;

	if (c->metacopy_digest)
		ovl_set_flag(OVL_HAS_DIGEST, d_inode(c->dentry));
	else
		ovl_clear_flag(OVL_HAS_DIGEST, d_inode(c->dentry));
	ovl_clear_flag(OVL_VERIFIED_DIGEST, d_inode(c->dentry));

	if (!c->metacopy)
		ovl_set_upperdata(d_inode(c->dentry));
	ovl_inode_update(d_inode(c->dentry), dget(temp));

out:
	ovl_end_write(c->dentry);
out_fput:
	fput(tmpfile);
	return err;
}

/*
 * Copy up a single dentry
 *
 * All renames start with copy up of source if necessary.  The actual
 * rename will only proceed once the copy up was successful.  Copy up uses
 * upper parent i_mutex for exclusion.  Since rename can change d_parent it
 * is possible that the copy up will lock the old parent.  At that point
 * the file will have already been copied up anyway.
 */
static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
{
	int err;
	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
	struct dentry *origin = c->lowerpath.dentry;
	struct ovl_fh *fh = NULL;
	bool to_index = false;

	/*
	 * Indexed non-dir is copied up directly to the index entry and then
	 * hardlinked to upper dir. Indexed dir is copied up to indexdir,
	 * then index entry is created and then copied up dir installed.
	 * Copying dir up to indexdir instead of workdir simplifies locking.
	 */
	if (ovl_need_index(c->dentry)) {
		c->indexed = true;
		if (S_ISDIR(c->stat.mode))
			c->workdir = ovl_indexdir(c->dentry->d_sb);
		else
			to_index = true;
	}

	if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || to_index) {
		fh = ovl_get_origin_fh(ofs, origin);
		if (IS_ERR(fh))
			return PTR_ERR(fh);

		/* origin_fh may be NULL */
		c->origin_fh = fh;
		c->origin = true;
	}

	if (to_index) {
		c->destdir = ovl_indexdir(c->dentry->d_sb);
		err = ovl_get_index_name(ofs, origin, &c->destname);
		if (err)
			goto out_free_fh;
	} else if (WARN_ON(!c->parent)) {
		/* Disconnected dentry must be copied up to index dir */
		err = -EIO;
		goto out_free_fh;
	} else {
		/*
		 * c->dentry->d_name is stabilzed by ovl_copy_up_start(),
		 * because if we got here, it means that c->dentry has no upper
		 * alias and changing ->d_name means going through ovl_rename()
		 * that will call ovl_copy_up() on source and target dentry.
		 */
		c->destname = c->dentry->d_name;
		/*
		 * Mark parent "impure" because it may now contain non-pure
		 * upper
		 */
		ovl_start_write(c->dentry);
		err = ovl_set_impure(c->parent, c->destdir);
		ovl_end_write(c->dentry);
		if (err)
			goto out_free_fh;
	}

	/* Should we copyup with O_TMPFILE or with workdir? */
	if (S_ISREG(c->stat.mode) && ofs->tmpfile)
		err = ovl_copy_up_tmpfile(c);
	else
		err = ovl_copy_up_workdir(c);
	if (err)
		goto out;

	if (c->indexed)
		ovl_set_flag(OVL_INDEX, d_inode(c->dentry));

	ovl_start_write(c->dentry);
	if (to_index) {
		/* Initialize nlink for copy up of disconnected dentry */
		err = ovl_set_nlink_upper(c->dentry);
	} else {
		struct inode *udir = d_inode(c->destdir);

		/* Restore timestamps on parent (best effort) */
		inode_lock(udir);
		ovl_set_timestamps(ofs, c->destdir, &c->pstat);
		inode_unlock(udir);

		ovl_dentry_set_upper_alias(c->dentry);
		ovl_dentry_update_reval(c->dentry, ovl_dentry_upper(c->dentry));
	}
	ovl_end_write(c->dentry);

out:
	if (to_index)
		kfree(c->destname.name);
out_free_fh:
	kfree(fh);
	return err;
}

static bool ovl_need_meta_copy_up(struct dentry *dentry, umode_t mode,
				  int flags)
{
	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);

	if (!ofs->config.metacopy)
		return false;

	if (!S_ISREG(mode))
		return false;

	if (flags && ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC)))
		return false;

	/* Fall back to full copy if no fsverity on source data and we require verity */
	if (ofs->config.verity_mode == OVL_VERITY_REQUIRE) {
		struct path lowerdata;

		ovl_path_lowerdata(dentry, &lowerdata);

		if (WARN_ON_ONCE(lowerdata.dentry == NULL) ||
		    ovl_ensure_verity_loaded(&lowerdata) ||
		    !fsverity_active(d_inode(lowerdata.dentry))) {
			return false;
		}
	}

	return true;
}

static ssize_t ovl_getxattr_value(const struct path *path, char *name, char **value)
{
	ssize_t res;
	char *buf;

	res = ovl_do_getxattr(path, name, NULL, 0);
	if (res == -ENODATA || res == -EOPNOTSUPP)
		res = 0;

	if (res > 0) {
		buf = kzalloc(res, GFP_KERNEL);
		if (!buf)
			return -ENOMEM;

		res = ovl_do_getxattr(path, name, buf, res);
		if (res < 0)
			kfree(buf);
		else
			*value = buf;
	}
	return res;
}

/* Copy up data of an inode which was copied up metadata only in the past. */
static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c)
{
	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
	struct path upperpath;
	int err;
	char *capability = NULL;
	ssize_t cap_size;

	ovl_path_upper(c->dentry, &upperpath);
	if (WARN_ON(upperpath.dentry == NULL))
		return -EIO;

	if (c->stat.size) {
		err = cap_size = ovl_getxattr_value(&upperpath, XATTR_NAME_CAPS,
						    &capability);
		if (cap_size < 0)
			goto out;
	}

	err = ovl_copy_up_data(c, &upperpath);
	if (err)
		goto out_free;

	/*
	 * Writing to upper file will clear security.capability xattr. We
	 * don't want that to happen for normal copy-up operation.
	 */
	ovl_start_write(c->dentry);
	if (capability) {
		err = ovl_do_setxattr(ofs, upperpath.dentry, XATTR_NAME_CAPS,
				      capability, cap_size, 0);
	}
	if (!err) {
		err = ovl_removexattr(ofs, upperpath.dentry,
				      OVL_XATTR_METACOPY);
	}
	ovl_end_write(c->dentry);
	if (err)
		goto out_free;

	ovl_clear_flag(OVL_HAS_DIGEST, d_inode(c->dentry));
	ovl_clear_flag(OVL_VERIFIED_DIGEST, d_inode(c->dentry));
	ovl_set_upperdata(d_inode(c->dentry));
out_free:
	kfree(capability);
out:
	return err;
}

static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
			   int flags)
{
	int err;
	DEFINE_DELAYED_CALL(done);
	struct path parentpath;
	struct ovl_copy_up_ctx ctx = {
		.parent = parent,
		.dentry = dentry,
		.workdir = ovl_workdir(dentry),
	};

	if (WARN_ON(!ctx.workdir))
		return -EROFS;

	ovl_path_lower(dentry, &ctx.lowerpath);
	err = vfs_getattr(&ctx.lowerpath, &ctx.stat,
			  STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
	if (err)
		return err;

	if (!kuid_has_mapping(current_user_ns(), ctx.stat.uid) ||
	    !kgid_has_mapping(current_user_ns(), ctx.stat.gid))
		return -EOVERFLOW;

	ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags);

	if (parent) {
		ovl_path_upper(parent, &parentpath);
		ctx.destdir = parentpath.dentry;

		err = vfs_getattr(&parentpath, &ctx.pstat,
				  STATX_ATIME | STATX_MTIME,
				  AT_STATX_SYNC_AS_STAT);
		if (err)
			return err;
	}

	/* maybe truncate regular file. this has no effect on dirs */
	if (flags & O_TRUNC)
		ctx.stat.size = 0;

	if (S_ISLNK(ctx.stat.mode)) {
		ctx.link = vfs_get_link(ctx.lowerpath.dentry, &done);
		if (IS_ERR(ctx.link))
			return PTR_ERR(ctx.link);
	}

	err = ovl_copy_up_start(dentry, flags);
	/* err < 0: interrupted, err > 0: raced with another copy-up */
	if (unlikely(err)) {
		if (err > 0)
			err = 0;
	} else {
		if (!ovl_dentry_upper(dentry))
			err = ovl_do_copy_up(&ctx);
		if (!err && parent && !ovl_dentry_has_upper_alias(dentry))
			err = ovl_link_up(&ctx);
		if (!err && ovl_dentry_needs_data_copy_up_locked(dentry, flags))
			err = ovl_copy_up_meta_inode_data(&ctx);
		ovl_copy_up_end(dentry);
	}
	do_delayed_call(&done);

	return err;
}

static int ovl_copy_up_flags(struct dentry *dentry, int flags)
{
	int err = 0;
	const struct cred *old_cred;
	bool disconnected = (dentry->d_flags & DCACHE_DISCONNECTED);

	/*
	 * With NFS export, copy up can get called for a disconnected non-dir.
	 * In this case, we will copy up lower inode to index dir without
	 * linking it to upper dir.
	 */
	if (WARN_ON(disconnected && d_is_dir(dentry)))
		return -EIO;

	/*
	 * We may not need lowerdata if we are only doing metacopy up, but it is
	 * not very important to optimize this case, so do lazy lowerdata lookup
	 * before any copy up, so we can do it before taking ovl_inode_lock().
	 */
	err = ovl_verify_lowerdata(dentry);
	if (err)
		return err;

	old_cred = ovl_override_creds(dentry->d_sb);
	while (!err) {
		struct dentry *next;
		struct dentry *parent = NULL;

		if (ovl_already_copied_up(dentry, flags))
			break;

		next = dget(dentry);
		/* find the topmost dentry not yet copied up */
		for (; !disconnected;) {
			parent = dget_parent(next);

			if (ovl_dentry_upper(parent))
				break;

			dput(next);
			next = parent;
		}

		err = ovl_copy_up_one(parent, next, flags);

		dput(parent);
		dput(next);
	}
	revert_creds(old_cred);

	return err;
}

static bool ovl_open_need_copy_up(struct dentry *dentry, int flags)
{
	/* Copy up of disconnected dentry does not set upper alias */
	if (ovl_already_copied_up(dentry, flags))
		return false;

	if (special_file(d_inode(dentry)->i_mode))
		return false;

	if (!ovl_open_flags_need_copy_up(flags))
		return false;

	return true;
}

int ovl_maybe_copy_up(struct dentry *dentry, int flags)
{
	if (!ovl_open_need_copy_up(dentry, flags))
		return 0;

	return ovl_copy_up_flags(dentry, flags);
}

int ovl_copy_up_with_data(struct dentry *dentry)
{
	return ovl_copy_up_flags(dentry, O_WRONLY);
}

int ovl_copy_up(struct dentry *dentry)
{
	return ovl_copy_up_flags(dentry, 0);
}