summaryrefslogtreecommitdiffstats
path: root/fs/overlayfs/util.c
blob: d6bb1c9f5e7a5fa507a6295a5050fb845425d7e6 (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
/*
 * Copyright (C) 2011 Novell Inc.
 * Copyright (C) 2016 Red Hat, Inc.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published by
 * the Free Software Foundation.
 */

#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/xattr.h>
#include <linux/exportfs.h>
#include <linux/uuid.h>
#include <linux/namei.h>
#include <linux/ratelimit.h>
#include "overlayfs.h"

int ovl_want_write(struct dentry *dentry)
{
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
	return mnt_want_write(ofs->upper_mnt);
}

void ovl_drop_write(struct dentry *dentry)
{
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
	mnt_drop_write(ofs->upper_mnt);
}

struct dentry *ovl_workdir(struct dentry *dentry)
{
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
	return ofs->workdir;
}

const struct cred *ovl_override_creds(struct super_block *sb)
{
	struct ovl_fs *ofs = sb->s_fs_info;

	return override_creds(ofs->creator_cred);
}

struct super_block *ovl_same_sb(struct super_block *sb)
{
	struct ovl_fs *ofs = sb->s_fs_info;

	return ofs->same_sb;
}

bool ovl_can_decode_fh(struct super_block *sb)
{
	return (sb->s_export_op && sb->s_export_op->fh_to_dentry &&
		!uuid_is_null(&sb->s_uuid));
}

struct dentry *ovl_indexdir(struct super_block *sb)
{
	struct ovl_fs *ofs = sb->s_fs_info;

	return ofs->indexdir;
}

struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
{
	size_t size = offsetof(struct ovl_entry, lowerstack[numlower]);
	struct ovl_entry *oe = kzalloc(size, GFP_KERNEL);

	if (oe)
		oe->numlower = numlower;

	return oe;
}

bool ovl_dentry_remote(struct dentry *dentry)
{
	return dentry->d_flags &
		(DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE |
		 DCACHE_OP_REAL);
}

bool ovl_dentry_weird(struct dentry *dentry)
{
	return dentry->d_flags & (DCACHE_NEED_AUTOMOUNT |
				  DCACHE_MANAGE_TRANSIT |
				  DCACHE_OP_HASH |
				  DCACHE_OP_COMPARE);
}

enum ovl_path_type ovl_path_type(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;
	enum ovl_path_type type = 0;

	if (ovl_dentry_upper(dentry)) {
		type = __OVL_PATH_UPPER;

		/*
		 * Non-dir dentry can hold lower dentry of its copy up origin.
		 */
		if (oe->numlower) {
			type |= __OVL_PATH_ORIGIN;
			if (d_is_dir(dentry))
				type |= __OVL_PATH_MERGE;
		}
	} else {
		if (oe->numlower > 1)
			type |= __OVL_PATH_MERGE;
	}
	return type;
}

void ovl_path_upper(struct dentry *dentry, struct path *path)
{
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;

	path->mnt = ofs->upper_mnt;
	path->dentry = ovl_dentry_upper(dentry);
}

void ovl_path_lower(struct dentry *dentry, struct path *path)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	if (oe->numlower) {
		path->mnt = oe->lowerstack[0].layer->mnt;
		path->dentry = oe->lowerstack[0].dentry;
	} else {
		*path = (struct path) { };
	}
}

enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
{
	enum ovl_path_type type = ovl_path_type(dentry);

	if (!OVL_TYPE_UPPER(type))
		ovl_path_lower(dentry, path);
	else
		ovl_path_upper(dentry, path);

	return type;
}

struct dentry *ovl_dentry_upper(struct dentry *dentry)
{
	return ovl_upperdentry_dereference(OVL_I(d_inode(dentry)));
}

struct dentry *ovl_dentry_lower(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	return oe->numlower ? oe->lowerstack[0].dentry : NULL;
}

struct dentry *ovl_dentry_real(struct dentry *dentry)
{
	return ovl_dentry_upper(dentry) ?: ovl_dentry_lower(dentry);
}

struct dentry *ovl_i_dentry_upper(struct inode *inode)
{
	return ovl_upperdentry_dereference(OVL_I(inode));
}

struct inode *ovl_inode_upper(struct inode *inode)
{
	struct dentry *upperdentry = ovl_i_dentry_upper(inode);

	return upperdentry ? d_inode(upperdentry) : NULL;
}

struct inode *ovl_inode_lower(struct inode *inode)
{
	return OVL_I(inode)->lower;
}

struct inode *ovl_inode_real(struct inode *inode)
{
	return ovl_inode_upper(inode) ?: ovl_inode_lower(inode);
}


struct ovl_dir_cache *ovl_dir_cache(struct inode *inode)
{
	return OVL_I(inode)->cache;
}

void ovl_set_dir_cache(struct inode *inode, struct ovl_dir_cache *cache)
{
	OVL_I(inode)->cache = cache;
}

bool ovl_dentry_is_opaque(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;
	return oe->opaque;
}

bool ovl_dentry_is_whiteout(struct dentry *dentry)
{
	return !dentry->d_inode && ovl_dentry_is_opaque(dentry);
}

void ovl_dentry_set_opaque(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	oe->opaque = true;
}

/*
 * For hard links it's possible for ovl_dentry_upper() to return positive, while
 * there's no actual upper alias for the inode.  Copy up code needs to know
 * about the existence of the upper alias, so it can't use ovl_dentry_upper().
 */
bool ovl_dentry_has_upper_alias(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	return oe->has_upper;
}

void ovl_dentry_set_upper_alias(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	oe->has_upper = true;
}

bool ovl_redirect_dir(struct super_block *sb)
{
	struct ovl_fs *ofs = sb->s_fs_info;

	return ofs->config.redirect_dir && !ofs->noxattr;
}

const char *ovl_dentry_get_redirect(struct dentry *dentry)
{
	return OVL_I(d_inode(dentry))->redirect;
}

void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect)
{
	struct ovl_inode *oi = OVL_I(d_inode(dentry));

	kfree(oi->redirect);
	oi->redirect = redirect;
}

void ovl_inode_init(struct inode *inode, struct dentry *upperdentry,
		    struct dentry *lowerdentry)
{
	if (upperdentry)
		OVL_I(inode)->__upperdentry = upperdentry;
	if (lowerdentry)
		OVL_I(inode)->lower = d_inode(lowerdentry);

	ovl_copyattr(d_inode(upperdentry ?: lowerdentry), inode);
}

void ovl_inode_update(struct inode *inode, struct dentry *upperdentry)
{
	struct inode *upperinode = d_inode(upperdentry);

	WARN_ON(OVL_I(inode)->__upperdentry);

	/*
	 * Make sure upperdentry is consistent before making it visible
	 */
	smp_wmb();
	OVL_I(inode)->__upperdentry = upperdentry;
	if (!S_ISDIR(upperinode->i_mode) && inode_unhashed(inode)) {
		inode->i_private = upperinode;
		__insert_inode_hash(inode, (unsigned long) upperinode);
	}
}

void ovl_dentry_version_inc(struct dentry *dentry, bool impurity)
{
	struct inode *inode = d_inode(dentry);

	WARN_ON(!inode_is_locked(inode));
	/*
	 * Version is used by readdir code to keep cache consistent.  For merge
	 * dirs all changes need to be noted.  For non-merge dirs, cache only
	 * contains impure (ones which have been copied up and have origins)
	 * entries, so only need to note changes to impure entries.
	 */
	if (OVL_TYPE_MERGE(ovl_path_type(dentry)) || impurity)
		OVL_I(inode)->version++;
}

u64 ovl_dentry_version_get(struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);

	WARN_ON(!inode_is_locked(inode));
	return OVL_I(inode)->version;
}

bool ovl_is_whiteout(struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;

	return inode && IS_WHITEOUT(inode);
}

struct file *ovl_path_open(struct path *path, int flags)
{
	return dentry_open(path, flags | O_NOATIME, current_cred());
}

int ovl_copy_up_start(struct dentry *dentry)
{
	struct ovl_inode *oi = OVL_I(d_inode(dentry));
	int err;

	err = mutex_lock_interruptible(&oi->lock);
	if (!err && ovl_dentry_has_upper_alias(dentry)) {
		err = 1; /* Already copied up */
		mutex_unlock(&oi->lock);
	}

	return err;
}

void ovl_copy_up_end(struct dentry *dentry)
{
	mutex_unlock(&OVL_I(d_inode(dentry))->lock);
}

bool ovl_check_origin_xattr(struct dentry *dentry)
{
	int res;

	res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, NULL, 0);

	/* Zero size value means "copied up but origin unknown" */
	if (res >= 0)
		return true;

	return false;
}

bool ovl_check_dir_xattr(struct dentry *dentry, const char *name)
{
	int res;
	char val;

	if (!d_is_dir(dentry))
		return false;

	res = vfs_getxattr(dentry, name, &val, 1);
	if (res == 1 && val == 'y')
		return true;

	return false;
}

int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
		       const char *name, const void *value, size_t size,
		       int xerr)
{
	int err;
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;

	if (ofs->noxattr)
		return xerr;

	err = ovl_do_setxattr(upperdentry, name, value, size, 0);

	if (err == -EOPNOTSUPP) {
		pr_warn("overlayfs: cannot set %s xattr on upper\n", name);
		ofs->noxattr = true;
		return xerr;
	}

	return err;
}

int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry)
{
	int err;

	if (ovl_test_flag(OVL_IMPURE, d_inode(dentry)))
		return 0;

	/*
	 * Do not fail when upper doesn't support xattrs.
	 * Upper inodes won't have origin nor redirect xattr anyway.
	 */
	err = ovl_check_setxattr(dentry, upperdentry, OVL_XATTR_IMPURE,
				 "y", 1, 0);
	if (!err)
		ovl_set_flag(OVL_IMPURE, d_inode(dentry));

	return err;
}

void ovl_set_flag(unsigned long flag, struct inode *inode)
{
	set_bit(flag, &OVL_I(inode)->flags);
}

void ovl_clear_flag(unsigned long flag, struct inode *inode)
{
	clear_bit(flag, &OVL_I(inode)->flags);
}

bool ovl_test_flag(unsigned long flag, struct inode *inode)
{
	return test_bit(flag, &OVL_I(inode)->flags);
}

/**
 * Caller must hold a reference to inode to prevent it from being freed while
 * it is marked inuse.
 */
bool ovl_inuse_trylock(struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);
	bool locked = false;

	spin_lock(&inode->i_lock);
	if (!(inode->i_state & I_OVL_INUSE)) {
		inode->i_state |= I_OVL_INUSE;
		locked = true;
	}
	spin_unlock(&inode->i_lock);

	return locked;
}

void ovl_inuse_unlock(struct dentry *dentry)
{
	if (dentry) {
		struct inode *inode = d_inode(dentry);

		spin_lock(&inode->i_lock);
		WARN_ON(!(inode->i_state & I_OVL_INUSE));
		inode->i_state &= ~I_OVL_INUSE;
		spin_unlock(&inode->i_lock);
	}
}

/* Caller must hold OVL_I(inode)->lock */
static void ovl_cleanup_index(struct dentry *dentry)
{
	struct inode *dir = ovl_indexdir(dentry->d_sb)->d_inode;
	struct dentry *lowerdentry = ovl_dentry_lower(dentry);
	struct dentry *upperdentry = ovl_dentry_upper(dentry);
	struct dentry *index = NULL;
	struct inode *inode;
	struct qstr name;
	int err;

	err = ovl_get_index_name(lowerdentry, &name);
	if (err)
		goto fail;

	inode = d_inode(upperdentry);
	if (inode->i_nlink != 1) {
		pr_warn_ratelimited("overlayfs: cleanup linked index (%pd2, ino=%lu, nlink=%u)\n",
				    upperdentry, inode->i_ino, inode->i_nlink);
		/*
		 * We either have a bug with persistent union nlink or a lower
		 * hardlink was added while overlay is mounted. Adding a lower
		 * hardlink and then unlinking all overlay hardlinks would drop
		 * overlay nlink to zero before all upper inodes are unlinked.
		 * As a safety measure, when that situation is detected, set
		 * the overlay nlink to the index inode nlink minus one for the
		 * index entry itself.
		 */
		set_nlink(d_inode(dentry), inode->i_nlink - 1);
		ovl_set_nlink_upper(dentry);
		goto out;
	}

	inode_lock_nested(dir, I_MUTEX_PARENT);
	/* TODO: whiteout instead of cleanup to block future open by handle */
	index = lookup_one_len(name.name, ovl_indexdir(dentry->d_sb), name.len);
	err = PTR_ERR(index);
	if (!IS_ERR(index))
		err = ovl_cleanup(dir, index);
	else
		index = NULL;

	inode_unlock(dir);
	if (err)
		goto fail;

out:
	dput(index);
	return;

fail:
	pr_err("overlayfs: cleanup index of '%pd2' failed (%i)\n", dentry, err);
	goto out;
}

/*
 * Operations that change overlay inode and upper inode nlink need to be
 * synchronized with copy up for persistent nlink accounting.
 */
int ovl_nlink_start(struct dentry *dentry, bool *locked)
{
	struct ovl_inode *oi = OVL_I(d_inode(dentry));
	const struct cred *old_cred;
	int err;

	if (!d_inode(dentry) || d_is_dir(dentry))
		return 0;

	/*
	 * With inodes index is enabled, we store the union overlay nlink
	 * in an xattr on the index inode. When whiting out lower hardlinks
	 * we need to decrement the overlay persistent nlink, but before the
	 * first copy up, we have no upper index inode to store the xattr.
	 *
	 * As a workaround, before whiteout/rename over of a lower hardlink,
	 * copy up to create the upper index. Creating the upper index will
	 * initialize the overlay nlink, so it could be dropped if unlink
	 * or rename succeeds.
	 *
	 * TODO: implement metadata only index copy up when called with
	 *       ovl_copy_up_flags(dentry, O_PATH).
	 */
	if (ovl_indexdir(dentry->d_sb) && !ovl_dentry_has_upper_alias(dentry) &&
	    d_inode(ovl_dentry_lower(dentry))->i_nlink > 1) {
		err = ovl_copy_up(dentry);
		if (err)
			return err;
	}

	err = mutex_lock_interruptible(&oi->lock);
	if (err)
		return err;

	if (!ovl_test_flag(OVL_INDEX, d_inode(dentry)))
		goto out;

	old_cred = ovl_override_creds(dentry->d_sb);
	/*
	 * The overlay inode nlink should be incremented/decremented IFF the
	 * upper operation succeeds, along with nlink change of upper inode.
	 * Therefore, before link/unlink/rename, we store the union nlink
	 * value relative to the upper inode nlink in an upper inode xattr.
	 */
	err = ovl_set_nlink_upper(dentry);
	revert_creds(old_cred);

out:
	if (err)
		mutex_unlock(&oi->lock);
	else
		*locked = true;

	return err;
}

void ovl_nlink_end(struct dentry *dentry, bool locked)
{
	if (locked) {
		if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) &&
		    d_inode(dentry)->i_nlink == 0) {
			const struct cred *old_cred;

			old_cred = ovl_override_creds(dentry->d_sb);
			ovl_cleanup_index(dentry);
			revert_creds(old_cred);
		}

		mutex_unlock(&OVL_I(d_inode(dentry))->lock);
	}
}

int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir)
{
	/* Workdir should not be the same as upperdir */
	if (workdir == upperdir)
		goto err;

	/* Workdir should not be subdir of upperdir and vice versa */
	if (lock_rename(workdir, upperdir) != NULL)
		goto err_unlock;

	return 0;

err_unlock:
	unlock_rename(workdir, upperdir);
err:
	pr_err("overlayfs: failed to lock workdir+upperdir\n");
	return -EIO;
}