summaryrefslogtreecommitdiff
path: root/fs/overlayfs/inode.c
blob: d613e2c41242a52a6c018f43f9987bdbf461e0bb (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
/*
 *
 * 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/slab.h>
#include <linux/cred.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include "overlayfs.h"

int ovl_setattr(struct dentry *dentry, struct iattr *attr)
{
	int err;
	struct dentry *upperdentry;
	const struct cred *old_cred;

	/*
	 * Check for permissions before trying to copy-up.  This is redundant
	 * since it will be rechecked later by ->setattr() on upper dentry.  But
	 * without this, copy-up can be triggered by just about anybody.
	 *
	 * We don't initialize inode->size, which just means that
	 * inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not
	 * check for a swapfile (which this won't be anyway).
	 */
	err = setattr_prepare(dentry, attr);
	if (err)
		return err;

	err = ovl_want_write(dentry);
	if (err)
		goto out;

	err = ovl_copy_up(dentry);
	if (!err) {
		upperdentry = ovl_dentry_upper(dentry);

		if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
			attr->ia_valid &= ~ATTR_MODE;

		inode_lock(upperdentry->d_inode);
		old_cred = ovl_override_creds(dentry->d_sb);
		err = notify_change(upperdentry, attr, NULL);
		revert_creds(old_cred);
		if (!err)
			ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
		inode_unlock(upperdentry->d_inode);
	}
	ovl_drop_write(dentry);
out:
	return err;
}

int ovl_getattr(const struct path *path, struct kstat *stat,
		u32 request_mask, unsigned int flags)
{
	struct dentry *dentry = path->dentry;
	enum ovl_path_type type;
	struct path realpath;
	const struct cred *old_cred;
	bool is_dir = S_ISDIR(dentry->d_inode->i_mode);
	int err;

	type = ovl_path_real(dentry, &realpath);
	old_cred = ovl_override_creds(dentry->d_sb);
	err = vfs_getattr(&realpath, stat, request_mask, flags);
	if (err)
		goto out;

	/*
	 * When all layers are on the same fs, all real inode number are
	 * unique, so we use the overlay st_dev, which is friendly to du -x.
	 *
	 * We also use st_ino of the copy up origin, if we know it.
	 * This guaranties constant st_dev/st_ino across copy up.
	 *
	 * If filesystem supports NFS export ops, this also guaranties
	 * persistent st_ino across mount cycle.
	 */
	if (ovl_same_sb(dentry->d_sb)) {
		if (OVL_TYPE_ORIGIN(type)) {
			struct kstat lowerstat;
			u32 lowermask = STATX_INO | (!is_dir ? STATX_NLINK : 0);

			ovl_path_lower(dentry, &realpath);
			err = vfs_getattr(&realpath, &lowerstat,
					  lowermask, flags);
			if (err)
				goto out;

			WARN_ON_ONCE(stat->dev != lowerstat.dev);
			/*
			 * Lower hardlinks are broken on copy up to different
			 * upper files, so we cannot use the lower origin st_ino
			 * for those different files, even for the same fs case.
			 */
			if (is_dir || lowerstat.nlink == 1)
				stat->ino = lowerstat.ino;
		}
		stat->dev = dentry->d_sb->s_dev;
	} else if (is_dir) {
		/*
		 * If not all layers are on the same fs the pair {real st_ino;
		 * overlay st_dev} is not unique, so use the non persistent
		 * overlay st_ino.
		 *
		 * Always use the overlay st_dev for directories, so 'find
		 * -xdev' will scan the entire overlay mount and won't cross the
		 * overlay mount boundaries.
		 */
		stat->dev = dentry->d_sb->s_dev;
		stat->ino = dentry->d_inode->i_ino;
	}

	/*
	 * It's probably not worth it to count subdirs to get the
	 * correct link count.  nlink=1 seems to pacify 'find' and
	 * other utilities.
	 */
	if (is_dir && OVL_TYPE_MERGE(type))
		stat->nlink = 1;

out:
	revert_creds(old_cred);

	return err;
}

int ovl_permission(struct inode *inode, int mask)
{
	bool is_upper;
	struct inode *realinode = ovl_inode_real(inode, &is_upper);
	const struct cred *old_cred;
	int err;

	/* Careful in RCU walk mode */
	if (!realinode) {
		WARN_ON(!(mask & MAY_NOT_BLOCK));
		return -ECHILD;
	}

	/*
	 * Check overlay inode with the creds of task and underlying inode
	 * with creds of mounter
	 */
	err = generic_permission(inode, mask);
	if (err)
		return err;

	old_cred = ovl_override_creds(inode->i_sb);
	if (!is_upper && !special_file(realinode->i_mode) && mask & MAY_WRITE) {
		mask &= ~(MAY_WRITE | MAY_APPEND);
		/* Make sure mounter can read file for copy up later */
		mask |= MAY_READ;
	}
	err = inode_permission(realinode, mask);
	revert_creds(old_cred);

	return err;
}

static const char *ovl_get_link(struct dentry *dentry,
				struct inode *inode,
				struct delayed_call *done)
{
	const struct cred *old_cred;
	const char *p;

	if (!dentry)
		return ERR_PTR(-ECHILD);

	old_cred = ovl_override_creds(dentry->d_sb);
	p = vfs_get_link(ovl_dentry_real(dentry), done);
	revert_creds(old_cred);
	return p;
}

bool ovl_is_private_xattr(const char *name)
{
	return strncmp(name, OVL_XATTR_PREFIX,
		       sizeof(OVL_XATTR_PREFIX) - 1) == 0;
}

int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
		  size_t size, int flags)
{
	int err;
	struct path realpath;
	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
	const struct cred *old_cred;

	err = ovl_want_write(dentry);
	if (err)
		goto out;

	if (!value && !OVL_TYPE_UPPER(type)) {
		err = vfs_getxattr(realpath.dentry, name, NULL, 0);
		if (err < 0)
			goto out_drop_write;
	}

	err = ovl_copy_up(dentry);
	if (err)
		goto out_drop_write;

	if (!OVL_TYPE_UPPER(type))
		ovl_path_upper(dentry, &realpath);

	old_cred = ovl_override_creds(dentry->d_sb);
	if (value)
		err = vfs_setxattr(realpath.dentry, name, value, size, flags);
	else {
		WARN_ON(flags != XATTR_REPLACE);
		err = vfs_removexattr(realpath.dentry, name);
	}
	revert_creds(old_cred);

out_drop_write:
	ovl_drop_write(dentry);
out:
	return err;
}

int ovl_xattr_get(struct dentry *dentry, const char *name,
		  void *value, size_t size)
{
	struct dentry *realdentry = ovl_dentry_real(dentry);
	ssize_t res;
	const struct cred *old_cred;

	old_cred = ovl_override_creds(dentry->d_sb);
	res = vfs_getxattr(realdentry, name, value, size);
	revert_creds(old_cred);
	return res;
}

static bool ovl_can_list(const char *s)
{
	/* List all non-trusted xatts */
	if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0)
		return true;

	/* Never list trusted.overlay, list other trusted for superuser only */
	return !ovl_is_private_xattr(s) && capable(CAP_SYS_ADMIN);
}

ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
{
	struct dentry *realdentry = ovl_dentry_real(dentry);
	ssize_t res;
	size_t len;
	char *s;
	const struct cred *old_cred;

	old_cred = ovl_override_creds(dentry->d_sb);
	res = vfs_listxattr(realdentry, list, size);
	revert_creds(old_cred);
	if (res <= 0 || size == 0)
		return res;

	/* filter out private xattrs */
	for (s = list, len = res; len;) {
		size_t slen = strnlen(s, len) + 1;

		/* underlying fs providing us with an broken xattr list? */
		if (WARN_ON(slen > len))
			return -EIO;

		len -= slen;
		if (!ovl_can_list(s)) {
			res -= slen;
			memmove(s, s + slen, len);
		} else {
			s += slen;
		}
	}

	return res;
}

struct posix_acl *ovl_get_acl(struct inode *inode, int type)
{
	struct inode *realinode = ovl_inode_real(inode, NULL);
	const struct cred *old_cred;
	struct posix_acl *acl;

	if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
		return NULL;

	old_cred = ovl_override_creds(inode->i_sb);
	acl = get_acl(realinode, type);
	revert_creds(old_cred);

	return acl;
}

static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type,
				  struct dentry *realdentry)
{
	if (OVL_TYPE_UPPER(type))
		return false;

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

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

	return true;
}

int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags)
{
	int err = 0;
	struct path realpath;
	enum ovl_path_type type;

	type = ovl_path_real(dentry, &realpath);
	if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) {
		err = ovl_want_write(dentry);
		if (!err) {
			err = ovl_copy_up_flags(dentry, file_flags);
			ovl_drop_write(dentry);
		}
	}

	return err;
}

int ovl_update_time(struct inode *inode, struct timespec *ts, int flags)
{
	struct dentry *alias;
	struct path upperpath;

	if (!(flags & S_ATIME))
		return 0;

	alias = d_find_any_alias(inode);
	if (!alias)
		return 0;

	ovl_path_upper(alias, &upperpath);
	if (upperpath.dentry) {
		touch_atime(&upperpath);
		inode->i_atime = d_inode(upperpath.dentry)->i_atime;
	}

	dput(alias);

	return 0;
}

static const struct inode_operations ovl_file_inode_operations = {
	.setattr	= ovl_setattr,
	.permission	= ovl_permission,
	.getattr	= ovl_getattr,
	.listxattr	= ovl_listxattr,
	.get_acl	= ovl_get_acl,
	.update_time	= ovl_update_time,
};

static const struct inode_operations ovl_symlink_inode_operations = {
	.setattr	= ovl_setattr,
	.get_link	= ovl_get_link,
	.getattr	= ovl_getattr,
	.listxattr	= ovl_listxattr,
	.update_time	= ovl_update_time,
};

/*
 * It is possible to stack overlayfs instance on top of another
 * overlayfs instance as lower layer. We need to annonate the
 * stackable i_mutex locks according to stack level of the super
 * block instance. An overlayfs instance can never be in stack
 * depth 0 (there is always a real fs below it).  An overlayfs
 * inode lock will use the lockdep annotaion ovl_i_mutex_key[depth].
 *
 * For example, here is a snip from /proc/lockdep_chains after
 * dir_iterate of nested overlayfs:
 *
 * [...] &ovl_i_mutex_dir_key[depth]   (stack_depth=2)
 * [...] &ovl_i_mutex_dir_key[depth]#2 (stack_depth=1)
 * [...] &type->i_mutex_dir_key        (stack_depth=0)
 */
#define OVL_MAX_NESTING FILESYSTEM_MAX_STACK_DEPTH

static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode)
{
#ifdef CONFIG_LOCKDEP
	static struct lock_class_key ovl_i_mutex_key[OVL_MAX_NESTING];
	static struct lock_class_key ovl_i_mutex_dir_key[OVL_MAX_NESTING];

	int depth = inode->i_sb->s_stack_depth - 1;

	if (WARN_ON_ONCE(depth < 0 || depth >= OVL_MAX_NESTING))
		depth = 0;

	if (S_ISDIR(inode->i_mode))
		lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_dir_key[depth]);
	else
		lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_key[depth]);
#endif
}

static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
{
	inode->i_ino = get_next_ino();
	inode->i_mode = mode;
	inode->i_flags |= S_NOCMTIME;
#ifdef CONFIG_FS_POSIX_ACL
	inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
#endif

	ovl_lockdep_annotate_inode_mutex_key(inode);

	switch (mode & S_IFMT) {
	case S_IFREG:
		inode->i_op = &ovl_file_inode_operations;
		break;

	case S_IFDIR:
		inode->i_op = &ovl_dir_inode_operations;
		inode->i_fop = &ovl_dir_operations;
		break;

	case S_IFLNK:
		inode->i_op = &ovl_symlink_inode_operations;
		break;

	default:
		inode->i_op = &ovl_file_inode_operations;
		init_special_inode(inode, mode, rdev);
		break;
	}
}

struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev)
{
	struct inode *inode;

	inode = new_inode(sb);
	if (inode)
		ovl_fill_inode(inode, mode, rdev);

	return inode;
}

static int ovl_inode_test(struct inode *inode, void *data)
{
	return ovl_inode_real(inode, NULL) == data;
}

static int ovl_inode_set(struct inode *inode, void *data)
{
	inode->i_private = (void *) (((unsigned long) data) | OVL_ISUPPER_MASK);
	return 0;
}

struct inode *ovl_get_inode(struct super_block *sb, struct inode *realinode)

{
	struct inode *inode;

	inode = iget5_locked(sb, (unsigned long) realinode,
			     ovl_inode_test, ovl_inode_set, realinode);
	if (inode && inode->i_state & I_NEW) {
		ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev);
		set_nlink(inode, realinode->i_nlink);
		unlock_new_inode(inode);
	}

	return inode;
}