summaryrefslogtreecommitdiffstats
path: root/fs/overlayfs/copy_up.c
blob: 5e0cde85bd6b040041cd09b9ca79628c7227574e (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
// 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/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);
}

int ovl_copy_xattr(struct dentry *old, struct dentry *new)
{
	ssize_t list_size, size, value_size = 0;
	char *buf, *name, *value = NULL;
	int error = 0;
	size_t slen;

	if (!(old->d_inode->i_opflags & IOP_XATTR) ||
	    !(new->d_inode->i_opflags & IOP_XATTR))
		return 0;

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

	buf = kzalloc(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(name))
			continue;
retry:
		size = vfs_getxattr(old, name, value, value_size);
		if (size == -ERANGE)
			size = vfs_getxattr(old, name, NULL, 0);

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

		if (size > value_size) {
			void *new;

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

		error = security_inode_copy_up_xattr(name);
		if (error < 0 && error != -EOPNOTSUPP)
			break;
		if (error == 1) {
			error = 0;
			continue; /* Discard */
		}
		error = vfs_setxattr(new, name, value, size, 0);
		if (error) {
			if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name))
				break;

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

static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
{
	struct file *old_file;
	struct file *new_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;

	if (len == 0)
		return 0;

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

	new_file = ovl_path_open(new, O_LARGEFILE | O_WRONLY);
	if (IS_ERR(new_file)) {
		error = PTR_ERR(new_file);
		goto out_fput;
	}

	/* Try to use clone_file_range to clone up within the same fs */
	cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0);
	if (cloned == len)
		goto out;
	/* 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 &&
	    old_file->f_op->llseek)
		skip_hole = true;

	while (len) {
		size_t this_len = OVL_COPY_UP_CHUNK_SIZE;
		long 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.
		 */

		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;
			}
		}

		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;
	}
out:
	if (!error)
		error = vfs_fsync(new_file, 0);
	fput(new_file);
out_fput:
	fput(old_file);
	return error;
}

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

	return notify_change(upperdentry, &attr, NULL);
}

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

	return notify_change(upperdentry, &attr, NULL);
}

int ovl_set_attr(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 = notify_change(upperdentry, &attr, NULL);
	}
	if (!err) {
		struct iattr attr = {
			.ia_valid = ATTR_UID | ATTR_GID,
			.ia_uid = stat->uid,
			.ia_gid = stat->gid,
		};
		err = notify_change(upperdentry, &attr, NULL);
	}
	if (!err)
		ovl_set_timestamps(upperdentry, stat);

	return err;
}

struct ovl_fh *ovl_encode_real_fh(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;
	fh->fb.uuid = *uuid;

	return fh;

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

int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
		   struct dentry *upper)
{
	const struct ovl_fh *fh = NULL;
	int err;

	/*
	 * 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(lower->d_sb)) {
		fh = ovl_encode_real_fh(lower, false);
		if (IS_ERR(fh))
			return PTR_ERR(fh);
	}

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

	return err;
}

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

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

	err = ovl_do_setxattr(index, OVL_XATTR_UPPER, fh->buf, fh->fb.len, 0);

	kfree(fh);
	return err;
}

/*
 * Create and install index entry.
 *
 * Caller must hold i_mutex on indexdir.
 */
static int ovl_create_index(struct dentry *dentry, struct dentry *origin,
			    struct dentry *upper)
{
	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(origin, &name);
	if (err)
		return err;

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

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

	index = lookup_one_len(name.name, indexdir, name.len);
	if (IS_ERR(index)) {
		err = PTR_ERR(index);
	} else {
		err = ovl_do_rename(dir, temp, dir, index, 0);
		dput(index);
	}
out:
	if (err)
		ovl_cleanup(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;
	bool origin;
	bool indexed;
	bool metacopy;
};

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 inode *udir = d_inode(upperdir);

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

	err = ovl_set_nlink_lower(c->dentry);
	if (err)
		return err;

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

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

	err = ovl_set_nlink_upper(c->dentry);

	return err;
}

static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
{
	int err;

	/*
	 * Copy up data first and then xattrs. Writing data after
	 * xattrs will remove security.capability xattr automatically.
	 */
	if (S_ISREG(c->stat.mode) && !c->metacopy) {
		struct path upperpath, datapath;

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

		ovl_path_lowerdata(c->dentry, &datapath);
		err = ovl_copy_up_data(&datapath, &upperpath, c->stat.size);
		if (err)
			return err;
	}

	err = ovl_copy_xattr(c->lowerpath.dentry, temp);
	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(c->dentry, c->lowerpath.dentry, temp);
		if (err)
			return err;
	}

	if (c->metacopy) {
		err = ovl_check_setxattr(c->dentry, temp, OVL_XATTR_METACOPY,
					 NULL, 0, -EOPNOTSUPP);
		if (err)
			return err;
	}

	inode_lock(temp->d_inode);
	if (S_ISREG(c->stat.mode))
		err = ovl_set_size(temp, &c->stat);
	if (!err)
		err = ovl_set_attr(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 inode *inode;
	struct inode *udir = d_inode(c->destdir), *wdir = d_inode(c->workdir);
	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
	};

	/* workdir and destdir could be the same when copying up to indexdir */
	err = -EIO;
	if (lock_rename(c->workdir, c->destdir) != NULL)
		goto unlock;

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

	temp = ovl_create_temp(c->workdir, &cattr);
	ovl_revert_cu_creds(&cc);

	err = PTR_ERR(temp);
	if (IS_ERR(temp))
		goto unlock;

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

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

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

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

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

	return err;

cleanup:
	ovl_cleanup(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 inode *udir = d_inode(c->destdir);
	struct dentry *temp, *upper;
	struct ovl_cu_creds cc;
	int err;

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

	temp = ovl_do_tmpfile(c->workdir, c->stat.mode);
	ovl_revert_cu_creds(&cc);

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

	err = ovl_copy_up_inode(c, temp);
	if (err)
		goto out_dput;

	inode_lock_nested(udir, I_MUTEX_PARENT);

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

	if (err)
		goto out_dput;

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

	return 0;

out_dput:
	dput(temp);
	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 = c->dentry->d_sb->s_fs_info;
	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)
		c->origin = true;

	if (to_index) {
		c->destdir = ovl_indexdir(c->dentry->d_sb);
		err = ovl_get_index_name(c->lowerpath.dentry, &c->destname);
		if (err)
			return err;
	} else if (WARN_ON(!c->parent)) {
		/* Disconnected dentry must be copied up to index dir */
		return -EIO;
	} else {
		/*
		 * Mark parent "impure" because it may now contain non-pure
		 * upper
		 */
		err = ovl_set_impure(c->parent, c->destdir);
		if (err)
			return err;
	}

	/* 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));

	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(c->destdir, &c->pstat);
		inode_unlock(udir);

		ovl_dentry_set_upper_alias(c->dentry);
	}

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

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

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

	if (!S_ISREG(mode))
		return false;

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

	return true;
}

/* 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 path upperpath, datapath;
	int err;
	char *capability = NULL;
	ssize_t uninitialized_var(cap_size);

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

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

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

	err = ovl_copy_up_data(&datapath, &upperpath, c->stat.size);
	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.
	 */
	if (capability) {
		err = ovl_do_setxattr(upperpath.dentry, XATTR_NAME_CAPS,
				      capability, cap_size, 0);
		if (err)
			goto out_free;
	}


	err = vfs_removexattr(upperpath.dentry, OVL_XATTR_METACOPY);
	if (err)
		goto out_free;

	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;

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

	if (parent) {
		ovl_path_upper(parent, &parentpath);
		ctx.destdir = parentpath.dentry;
		ctx.destname = dentry->d_name;

		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 = ovl_override_creds(dentry->d_sb);
	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;

	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)
{
	int err = 0;

	if (ovl_open_need_copy_up(dentry, flags)) {
		err = ovl_want_write(dentry);
		if (!err) {
			err = ovl_copy_up_flags(dentry, flags);
			ovl_drop_write(dentry);
		}
	}

	return err;
}

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);
}