summaryrefslogtreecommitdiff
path: root/fs/overlayfs/super.c
blob: 227710aad78116e968f28db71a55742ed9e5545d (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
/*
 *
 * Copyright (C) 2011 Novell 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/namei.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/slab.h>
#include <linux/parser.h>
#include <linux/module.h>
#include <linux/sched.h>
#include "overlayfs.h"

MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Overlay filesystem");
MODULE_LICENSE("GPL");

/* private information held for overlayfs's superblock */
struct ovl_fs {
	struct vfsmount *upper_mnt;
	struct vfsmount *lower_mnt;
	struct dentry *workdir;
};

struct ovl_dir_cache;

/* private information held for every overlayfs dentry */
struct ovl_entry {
	struct dentry *__upperdentry;
	struct dentry *lowerdentry;
	struct ovl_dir_cache *cache;
	union {
		struct {
			u64 version;
			bool opaque;
		};
		struct rcu_head rcu;
	};
};

const char *ovl_opaque_xattr = "trusted.overlay.opaque";


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

	if (oe->__upperdentry) {
		if (oe->lowerdentry) {
			if (S_ISDIR(dentry->d_inode->i_mode))
				return OVL_PATH_MERGE;
			else
				return OVL_PATH_UPPER;
		} else {
			if (oe->opaque)
				return OVL_PATH_UPPER;
			else
				return OVL_PATH_PURE_UPPER;
		}
	} else {
		return OVL_PATH_LOWER;
	}
}

static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe)
{
	struct dentry *upperdentry = ACCESS_ONCE(oe->__upperdentry);
	/*
	 * Make sure to order reads to upperdentry wrt ovl_dentry_update()
	 */
	smp_read_barrier_depends();
	return upperdentry;
}

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

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

enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
{

	enum ovl_path_type type = ovl_path_type(dentry);

	if (type == OVL_PATH_LOWER)
		ovl_path_lower(dentry, path);
	else
		ovl_path_upper(dentry, path);

	return type;
}

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

	return ovl_upperdentry_dereference(oe);
}

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

	return oe->lowerdentry;
}

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

	realdentry = ovl_upperdentry_dereference(oe);
	if (!realdentry)
		realdentry = oe->lowerdentry;

	return realdentry;
}

struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper)
{
	struct dentry *realdentry;

	realdentry = ovl_upperdentry_dereference(oe);
	if (realdentry) {
		*is_upper = true;
	} else {
		realdentry = oe->lowerdentry;
		*is_upper = false;
	}
	return realdentry;
}

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

	return oe->cache;
}

void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	oe->cache = cache;
}

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

	path->mnt = ofs->lower_mnt;
	path->dentry = oe->lowerdentry;
}

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;
}

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

void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque)
{
	struct ovl_entry *oe = dentry->d_fsdata;
	oe->opaque = opaque;
}

void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	WARN_ON(!mutex_is_locked(&upperdentry->d_parent->d_inode->i_mutex));
	WARN_ON(oe->__upperdentry);
	BUG_ON(!upperdentry->d_inode);
	/*
	 * Make sure upperdentry is consistent before making it visible to
	 * ovl_upperdentry_dereference().
	 */
	smp_wmb();
	oe->__upperdentry = upperdentry;
}

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

	WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
	oe->version++;
}

u64 ovl_dentry_version_get(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
	return oe->version;
}

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

	return inode && IS_WHITEOUT(inode);
}

static bool ovl_is_opaquedir(struct dentry *dentry)
{
	int res;
	char val;
	struct inode *inode = dentry->d_inode;

	if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr)
		return false;

	res = inode->i_op->getxattr(dentry, ovl_opaque_xattr, &val, 1);
	if (res == 1 && val == 'y')
		return true;

	return false;
}

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

	if (oe) {
		dput(oe->__upperdentry);
		dput(oe->lowerdentry);
		kfree_rcu(oe, rcu);
	}
}

static const struct dentry_operations ovl_dentry_operations = {
	.d_release = ovl_dentry_release,
};

static struct ovl_entry *ovl_alloc_entry(void)
{
	return kzalloc(sizeof(struct ovl_entry), GFP_KERNEL);
}

static inline struct dentry *ovl_lookup_real(struct dentry *dir,
					     struct qstr *name)
{
	struct dentry *dentry;

	mutex_lock(&dir->d_inode->i_mutex);
	dentry = lookup_one_len(name->name, dir, name->len);
	mutex_unlock(&dir->d_inode->i_mutex);

	if (IS_ERR(dentry)) {
		if (PTR_ERR(dentry) == -ENOENT)
			dentry = NULL;
	} else if (!dentry->d_inode) {
		dput(dentry);
		dentry = NULL;
	}
	return dentry;
}

struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
			  unsigned int flags)
{
	struct ovl_entry *oe;
	struct dentry *upperdir;
	struct dentry *lowerdir;
	struct dentry *upperdentry = NULL;
	struct dentry *lowerdentry = NULL;
	struct inode *inode = NULL;
	int err;

	err = -ENOMEM;
	oe = ovl_alloc_entry();
	if (!oe)
		goto out;

	upperdir = ovl_dentry_upper(dentry->d_parent);
	lowerdir = ovl_dentry_lower(dentry->d_parent);

	if (upperdir) {
		upperdentry = ovl_lookup_real(upperdir, &dentry->d_name);
		err = PTR_ERR(upperdentry);
		if (IS_ERR(upperdentry))
			goto out_put_dir;

		if (lowerdir && upperdentry) {
			if (ovl_is_whiteout(upperdentry)) {
				dput(upperdentry);
				upperdentry = NULL;
				oe->opaque = true;
			} else if (ovl_is_opaquedir(upperdentry)) {
				oe->opaque = true;
			}
		}
	}
	if (lowerdir && !oe->opaque) {
		lowerdentry = ovl_lookup_real(lowerdir, &dentry->d_name);
		err = PTR_ERR(lowerdentry);
		if (IS_ERR(lowerdentry))
			goto out_dput_upper;
	}

	if (lowerdentry && upperdentry &&
	    (!S_ISDIR(upperdentry->d_inode->i_mode) ||
	     !S_ISDIR(lowerdentry->d_inode->i_mode))) {
		dput(lowerdentry);
		lowerdentry = NULL;
		oe->opaque = true;
	}

	if (lowerdentry || upperdentry) {
		struct dentry *realdentry;

		realdentry = upperdentry ? upperdentry : lowerdentry;
		err = -ENOMEM;
		inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode,
				      oe);
		if (!inode)
			goto out_dput;
		ovl_copyattr(realdentry->d_inode, inode);
	}

	oe->__upperdentry = upperdentry;
	oe->lowerdentry = lowerdentry;

	dentry->d_fsdata = oe;
	d_add(dentry, inode);

	return NULL;

out_dput:
	dput(lowerdentry);
out_dput_upper:
	dput(upperdentry);
out_put_dir:
	kfree(oe);
out:
	return ERR_PTR(err);
}

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

static void ovl_put_super(struct super_block *sb)
{
	struct ovl_fs *ufs = sb->s_fs_info;

	dput(ufs->workdir);
	mntput(ufs->upper_mnt);
	mntput(ufs->lower_mnt);

	kfree(ufs);
}

static const struct super_operations ovl_super_operations = {
	.put_super	= ovl_put_super,
};

struct ovl_config {
	char *lowerdir;
	char *upperdir;
	char *workdir;
};

enum {
	OPT_LOWERDIR,
	OPT_UPPERDIR,
	OPT_WORKDIR,
	OPT_ERR,
};

static const match_table_t ovl_tokens = {
	{OPT_LOWERDIR,			"lowerdir=%s"},
	{OPT_UPPERDIR,			"upperdir=%s"},
	{OPT_WORKDIR,			"workdir=%s"},
	{OPT_ERR,			NULL}
};

static int ovl_parse_opt(char *opt, struct ovl_config *config)
{
	char *p;

	config->upperdir = NULL;
	config->lowerdir = NULL;
	config->workdir = NULL;

	while ((p = strsep(&opt, ",")) != NULL) {
		int token;
		substring_t args[MAX_OPT_ARGS];

		if (!*p)
			continue;

		token = match_token(p, ovl_tokens, args);
		switch (token) {
		case OPT_UPPERDIR:
			kfree(config->upperdir);
			config->upperdir = match_strdup(&args[0]);
			if (!config->upperdir)
				return -ENOMEM;
			break;

		case OPT_LOWERDIR:
			kfree(config->lowerdir);
			config->lowerdir = match_strdup(&args[0]);
			if (!config->lowerdir)
				return -ENOMEM;
			break;

		case OPT_WORKDIR:
			kfree(config->workdir);
			config->workdir = match_strdup(&args[0]);
			if (!config->workdir)
				return -ENOMEM;
			break;

		default:
			return -EINVAL;
		}
	}
	return 0;
}

#define OVL_WORKDIR_NAME "work"

static struct dentry *ovl_workdir_create(struct vfsmount *mnt,
					 struct dentry *dentry)
{
	struct inode *dir = dentry->d_inode;
	struct dentry *work;
	int err;
	bool retried = false;

	err = mnt_want_write(mnt);
	if (err)
		return ERR_PTR(err);

	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
retry:
	work = lookup_one_len(OVL_WORKDIR_NAME, dentry,
			      strlen(OVL_WORKDIR_NAME));

	if (!IS_ERR(work)) {
		struct kstat stat = {
			.mode = S_IFDIR | 0,
		};

		if (work->d_inode) {
			err = -EEXIST;
			if (retried)
				goto out_dput;

			retried = true;
			ovl_cleanup(dir, work);
			dput(work);
			goto retry;
		}

		err = ovl_create_real(dir, work, &stat, NULL, NULL, true);
		if (err)
			goto out_dput;
	}
out_unlock:
	mutex_unlock(&dir->i_mutex);
	mnt_drop_write(mnt);

	return work;

out_dput:
	dput(work);
	work = ERR_PTR(err);
	goto out_unlock;
}

static int ovl_mount_dir(const char *name, struct path *path)
{
	int err;

	err = kern_path(name, LOOKUP_FOLLOW, path);
	if (err) {
		pr_err("overlayfs: failed to resolve '%s': %i\n", name, err);
		err = -EINVAL;
	}
	return err;
}

static bool ovl_is_allowed_fs_type(struct dentry *root)
{
	const struct dentry_operations *dop = root->d_op;

	/*
	 * We don't support:
	 *  - automount filesystems
	 *  - filesystems with revalidate (FIXME for lower layer)
	 *  - filesystems with case insensitive names
	 */
	if (dop &&
	    (dop->d_manage || dop->d_automount ||
	     dop->d_revalidate || dop->d_weak_revalidate ||
	     dop->d_compare || dop->d_hash)) {
		return false;
	}
	return true;
}

/* Workdir should not be subdir of upperdir and vice versa */
static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir)
{
	bool ok = false;

	if (workdir != upperdir) {
		ok = (lock_rename(workdir, upperdir) == NULL);
		unlock_rename(workdir, upperdir);
	}
	return ok;
}

static int ovl_fill_super(struct super_block *sb, void *data, int silent)
{
	struct path lowerpath;
	struct path upperpath;
	struct path workpath;
	struct inode *root_inode;
	struct dentry *root_dentry;
	struct ovl_entry *oe;
	struct ovl_fs *ufs;
	struct ovl_config config;
	int err;

	err = ovl_parse_opt((char *) data, &config);
	if (err)
		goto out;

	/* FIXME: workdir is not needed for a R/O mount */
	err = -EINVAL;
	if (!config.upperdir || !config.lowerdir || !config.workdir) {
		pr_err("overlayfs: missing upperdir or lowerdir or workdir\n");
		goto out_free_config;
	}

	err = -ENOMEM;
	ufs = kmalloc(sizeof(struct ovl_fs), GFP_KERNEL);
	if (!ufs)
		goto out_free_config;

	oe = ovl_alloc_entry();
	if (oe == NULL)
		goto out_free_ufs;

	err = ovl_mount_dir(config.upperdir, &upperpath);
	if (err)
		goto out_free_oe;

	err = ovl_mount_dir(config.lowerdir, &lowerpath);
	if (err)
		goto out_put_upperpath;

	err = ovl_mount_dir(config.workdir, &workpath);
	if (err)
		goto out_put_lowerpath;

	err = -EINVAL;
	if (!S_ISDIR(upperpath.dentry->d_inode->i_mode) ||
	    !S_ISDIR(lowerpath.dentry->d_inode->i_mode) ||
	    !S_ISDIR(workpath.dentry->d_inode->i_mode)) {
		pr_err("overlayfs: upperdir or lowerdir or workdir not a directory\n");
		goto out_put_workpath;
	}

	if (upperpath.mnt != workpath.mnt) {
		pr_err("overlayfs: workdir and upperdir must reside under the same mount\n");
		goto out_put_workpath;
	}
	if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) {
		pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
		goto out_put_workpath;
	}

	if (!ovl_is_allowed_fs_type(upperpath.dentry)) {
		pr_err("overlayfs: filesystem of upperdir is not supported\n");
		goto out_put_workpath;
	}

	if (!ovl_is_allowed_fs_type(lowerpath.dentry)) {
		pr_err("overlayfs: filesystem of lowerdir is not supported\n");
		goto out_put_workpath;
	}

	ufs->upper_mnt = clone_private_mount(&upperpath);
	err = PTR_ERR(ufs->upper_mnt);
	if (IS_ERR(ufs->upper_mnt)) {
		pr_err("overlayfs: failed to clone upperpath\n");
		goto out_put_workpath;
	}

	ufs->lower_mnt = clone_private_mount(&lowerpath);
	err = PTR_ERR(ufs->lower_mnt);
	if (IS_ERR(ufs->lower_mnt)) {
		pr_err("overlayfs: failed to clone lowerpath\n");
		goto out_put_upper_mnt;
	}

	ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry);
	err = PTR_ERR(ufs->workdir);
	if (IS_ERR(ufs->workdir)) {
		pr_err("overlayfs: failed to create directory %s/%s\n",
		       config.workdir, OVL_WORKDIR_NAME);
		goto out_put_lower_mnt;
	}

	/*
	 * Make lower_mnt R/O.  That way fchmod/fchown on lower file
	 * will fail instead of modifying lower fs.
	 */
	ufs->lower_mnt->mnt_flags |= MNT_READONLY;

	/* If the upper fs is r/o, we mark overlayfs r/o too */
	if (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY)
		sb->s_flags |= MS_RDONLY;

	sb->s_d_op = &ovl_dentry_operations;

	err = -ENOMEM;
	root_inode = ovl_new_inode(sb, S_IFDIR, oe);
	if (!root_inode)
		goto out_put_workdir;

	root_dentry = d_make_root(root_inode);
	if (!root_dentry)
		goto out_put_workdir;

	mntput(upperpath.mnt);
	mntput(lowerpath.mnt);
	path_put(&workpath);

	oe->__upperdentry = upperpath.dentry;
	oe->lowerdentry = lowerpath.dentry;

	root_dentry->d_fsdata = oe;

	sb->s_op = &ovl_super_operations;
	sb->s_root = root_dentry;
	sb->s_fs_info = ufs;

	return 0;

out_put_workdir:
	dput(ufs->workdir);
out_put_lower_mnt:
	mntput(ufs->lower_mnt);
out_put_upper_mnt:
	mntput(ufs->upper_mnt);
out_put_workpath:
	path_put(&workpath);
out_put_lowerpath:
	path_put(&lowerpath);
out_put_upperpath:
	path_put(&upperpath);
out_free_oe:
	kfree(oe);
out_free_ufs:
	kfree(ufs);
out_free_config:
	kfree(config.lowerdir);
	kfree(config.upperdir);
	kfree(config.workdir);
out:
	return err;
}

static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags,
				const char *dev_name, void *raw_data)
{
	return mount_nodev(fs_type, flags, raw_data, ovl_fill_super);
}

static struct file_system_type ovl_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "overlayfs",
	.mount		= ovl_mount,
	.kill_sb	= kill_anon_super,
};
MODULE_ALIAS_FS("overlayfs");

static int __init ovl_init(void)
{
	return register_filesystem(&ovl_fs_type);
}

static void __exit ovl_exit(void)
{
	unregister_filesystem(&ovl_fs_type);
}

module_init(ovl_init);
module_exit(ovl_exit);