summaryrefslogtreecommitdiffstats
path: root/fs/overlayfs/namei.c
blob: 197b53d34861c376168e9aaf1b58b09b05ff764c (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
/*
 * 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/cred.h>
#include <linux/namei.h>
#include <linux/xattr.h>
#include <linux/ratelimit.h>
#include <linux/mount.h>
#include <linux/exportfs.h>
#include "overlayfs.h"
#include "ovl_entry.h"

struct ovl_lookup_data {
	struct qstr name;
	bool is_dir;
	bool opaque;
	bool stop;
	bool last;
	char *redirect;
};

static int ovl_check_redirect(struct dentry *dentry, struct ovl_lookup_data *d,
			      size_t prelen, const char *post)
{
	int res;
	char *s, *next, *buf = NULL;

	res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, NULL, 0);
	if (res < 0) {
		if (res == -ENODATA || res == -EOPNOTSUPP)
			return 0;
		goto fail;
	}
	buf = kzalloc(prelen + res + strlen(post) + 1, GFP_TEMPORARY);
	if (!buf)
		return -ENOMEM;

	if (res == 0)
		goto invalid;

	res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, buf, res);
	if (res < 0)
		goto fail;
	if (res == 0)
		goto invalid;
	if (buf[0] == '/') {
		for (s = buf; *s++ == '/'; s = next) {
			next = strchrnul(s, '/');
			if (s == next)
				goto invalid;
		}
	} else {
		if (strchr(buf, '/') != NULL)
			goto invalid;

		memmove(buf + prelen, buf, res);
		memcpy(buf, d->name.name, prelen);
	}

	strcat(buf, post);
	kfree(d->redirect);
	d->redirect = buf;
	d->name.name = d->redirect;
	d->name.len = strlen(d->redirect);

	return 0;

err_free:
	kfree(buf);
	return 0;
fail:
	pr_warn_ratelimited("overlayfs: failed to get redirect (%i)\n", res);
	goto err_free;
invalid:
	pr_warn_ratelimited("overlayfs: invalid redirect (%s)\n", buf);
	goto err_free;
}

static int ovl_acceptable(void *ctx, struct dentry *dentry)
{
	return 1;
}

static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry)
{
	int res;
	struct ovl_fh *fh = NULL;

	res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, NULL, 0);
	if (res < 0) {
		if (res == -ENODATA || res == -EOPNOTSUPP)
			return NULL;
		goto fail;
	}
	/* Zero size value means "copied up but origin unknown" */
	if (res == 0)
		return NULL;

	fh = kzalloc(res, GFP_TEMPORARY);
	if (!fh)
		return ERR_PTR(-ENOMEM);

	res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, fh, res);
	if (res < 0)
		goto fail;

	if (res < sizeof(struct ovl_fh) || res < fh->len)
		goto invalid;

	if (fh->magic != OVL_FH_MAGIC)
		goto invalid;

	/* Treat larger version and unknown flags as "origin unknown" */
	if (fh->version > OVL_FH_VERSION || fh->flags & ~OVL_FH_FLAG_ALL)
		goto out;

	/* Treat endianness mismatch as "origin unknown" */
	if (!(fh->flags & OVL_FH_FLAG_ANY_ENDIAN) &&
	    (fh->flags & OVL_FH_FLAG_BIG_ENDIAN) != OVL_FH_FLAG_CPU_ENDIAN)
		goto out;

	return fh;

out:
	kfree(fh);
	return NULL;

fail:
	pr_warn_ratelimited("overlayfs: failed to get origin (%i)\n", res);
	goto out;
invalid:
	pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", res, fh);
	goto out;
}

static struct dentry *ovl_get_origin(struct dentry *dentry,
				     struct vfsmount *mnt)
{
	struct dentry *origin = NULL;
	struct ovl_fh *fh = ovl_get_origin_fh(dentry);
	int bytes;

	if (IS_ERR_OR_NULL(fh))
		return (struct dentry *)fh;

	/*
	 * Make sure that the stored uuid matches the uuid of the lower
	 * layer where file handle will be decoded.
	 */
	if (!uuid_equal(&fh->uuid, &mnt->mnt_sb->s_uuid))
		goto out;

	bytes = (fh->len - offsetof(struct ovl_fh, fid));
	origin = exportfs_decode_fh(mnt, (struct fid *)fh->fid,
				    bytes >> 2, (int)fh->type,
				    ovl_acceptable, NULL);
	if (IS_ERR(origin)) {
		/* Treat stale file handle as "origin unknown" */
		if (origin == ERR_PTR(-ESTALE))
			origin = NULL;
		goto out;
	}

	if (ovl_dentry_weird(origin) ||
	    ((d_inode(origin)->i_mode ^ d_inode(dentry)->i_mode) & S_IFMT))
		goto invalid;

out:
	kfree(fh);
	return origin;

invalid:
	pr_warn_ratelimited("overlayfs: invalid origin (%pd2)\n", origin);
	dput(origin);
	origin = NULL;
	goto out;
}

static bool ovl_is_opaquedir(struct dentry *dentry)
{
	return ovl_check_dir_xattr(dentry, OVL_XATTR_OPAQUE);
}

static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
			     const char *name, unsigned int namelen,
			     size_t prelen, const char *post,
			     struct dentry **ret)
{
	struct dentry *this;
	int err;

	this = lookup_one_len_unlocked(name, base, namelen);
	if (IS_ERR(this)) {
		err = PTR_ERR(this);
		this = NULL;
		if (err == -ENOENT || err == -ENAMETOOLONG)
			goto out;
		goto out_err;
	}
	if (!this->d_inode)
		goto put_and_out;

	if (ovl_dentry_weird(this)) {
		/* Don't support traversing automounts and other weirdness */
		err = -EREMOTE;
		goto out_err;
	}
	if (ovl_is_whiteout(this)) {
		d->stop = d->opaque = true;
		goto put_and_out;
	}
	if (!d_can_lookup(this)) {
		d->stop = true;
		if (d->is_dir)
			goto put_and_out;
		goto out;
	}
	d->is_dir = true;
	if (!d->last && ovl_is_opaquedir(this)) {
		d->stop = d->opaque = true;
		goto out;
	}
	err = ovl_check_redirect(this, d, prelen, post);
	if (err)
		goto out_err;
out:
	*ret = this;
	return 0;

put_and_out:
	dput(this);
	this = NULL;
	goto out;

out_err:
	dput(this);
	return err;
}

static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d,
			    struct dentry **ret)
{
	/* Counting down from the end, since the prefix can change */
	size_t rem = d->name.len - 1;
	struct dentry *dentry = NULL;
	int err;

	if (d->name.name[0] != '/')
		return ovl_lookup_single(base, d, d->name.name, d->name.len,
					 0, "", ret);

	while (!IS_ERR_OR_NULL(base) && d_can_lookup(base)) {
		const char *s = d->name.name + d->name.len - rem;
		const char *next = strchrnul(s, '/');
		size_t thislen = next - s;
		bool end = !next[0];

		/* Verify we did not go off the rails */
		if (WARN_ON(s[-1] != '/'))
			return -EIO;

		err = ovl_lookup_single(base, d, s, thislen,
					d->name.len - rem, next, &base);
		dput(dentry);
		if (err)
			return err;
		dentry = base;
		if (end)
			break;

		rem -= thislen + 1;

		if (WARN_ON(rem >= d->name.len))
			return -EIO;
	}
	*ret = dentry;
	return 0;
}


static int ovl_check_origin(struct dentry *dentry, struct dentry *upperdentry,
			    struct path **stackp, unsigned int *ctrp)
{
	struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata;
	struct vfsmount *mnt;
	struct dentry *origin = NULL;
	int i;


	for (i = 0; i < roe->numlower; i++) {
		mnt = roe->lowerstack[i].mnt;
		origin = ovl_get_origin(upperdentry, mnt);
		if (IS_ERR(origin))
			return PTR_ERR(origin);

		if (origin)
			break;
	}

	if (!origin)
		return 0;

	BUG_ON(*stackp || *ctrp);
	*stackp = kmalloc(sizeof(struct path), GFP_TEMPORARY);
	if (!*stackp) {
		dput(origin);
		return -ENOMEM;
	}
	**stackp = (struct path) { .dentry = origin, .mnt = mnt };
	*ctrp = 1;

	return 0;
}

/*
 * Verify that @fh matches the origin file handle stored in OVL_XATTR_ORIGIN.
 * Return 0 on match, -ESTALE on mismatch, < 0 on error.
 */
static int ovl_verify_origin_fh(struct dentry *dentry, const struct ovl_fh *fh)
{
	struct ovl_fh *ofh = ovl_get_origin_fh(dentry);
	int err = 0;

	if (!ofh)
		return -ENODATA;

	if (IS_ERR(ofh))
		return PTR_ERR(ofh);

	if (fh->len != ofh->len || memcmp(fh, ofh, fh->len))
		err = -ESTALE;

	kfree(ofh);
	return err;
}

/*
 * Verify that an inode matches the origin file handle stored in upper inode.
 *
 * If @set is true and there is no stored file handle, encode and store origin
 * file handle in OVL_XATTR_ORIGIN.
 *
 * Return 0 on match, -ESTALE on mismatch, < 0 on error.
 */
int ovl_verify_origin(struct dentry *dentry, struct vfsmount *mnt,
		      struct dentry *origin, bool set)
{
	struct inode *inode;
	struct ovl_fh *fh;
	int err;

	fh = ovl_encode_fh(origin);
	err = PTR_ERR(fh);
	if (IS_ERR(fh))
		goto fail;

	err = ovl_verify_origin_fh(dentry, fh);
	if (set && err == -ENODATA)
		err = ovl_do_setxattr(dentry, OVL_XATTR_ORIGIN, fh, fh->len, 0);
	if (err)
		goto fail;

out:
	kfree(fh);
	return err;

fail:
	inode = d_inode(origin);
	pr_warn_ratelimited("overlayfs: failed to verify origin (%pd2, ino=%lu, err=%i)\n",
			    origin, inode ? inode->i_ino : 0, err);
	goto out;
}

/*
 * Returns next layer in stack starting from top.
 * Returns -1 if this is the last layer.
 */
int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
{
	struct ovl_entry *oe = dentry->d_fsdata;

	BUG_ON(idx < 0);
	if (idx == 0) {
		ovl_path_upper(dentry, path);
		if (path->dentry)
			return oe->numlower ? 1 : -1;
		idx++;
	}
	BUG_ON(idx > oe->numlower);
	*path = oe->lowerstack[idx - 1];

	return (idx < oe->numlower) ? idx + 1 : -1;
}

struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
			  unsigned int flags)
{
	struct ovl_entry *oe;
	const struct cred *old_cred;
	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
	struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata;
	struct path *stack = NULL;
	struct dentry *upperdir, *upperdentry = NULL;
	unsigned int ctr = 0;
	struct inode *inode = NULL;
	bool upperopaque = false;
	char *upperredirect = NULL;
	struct dentry *this;
	unsigned int i;
	int err;
	struct ovl_lookup_data d = {
		.name = dentry->d_name,
		.is_dir = false,
		.opaque = false,
		.stop = false,
		.last = !poe->numlower,
		.redirect = NULL,
	};

	if (dentry->d_name.len > ofs->namelen)
		return ERR_PTR(-ENAMETOOLONG);

	old_cred = ovl_override_creds(dentry->d_sb);
	upperdir = ovl_dentry_upper(dentry->d_parent);
	if (upperdir) {
		err = ovl_lookup_layer(upperdir, &d, &upperdentry);
		if (err)
			goto out;

		if (upperdentry && unlikely(ovl_dentry_remote(upperdentry))) {
			dput(upperdentry);
			err = -EREMOTE;
			goto out;
		}
		if (upperdentry && !d.is_dir) {
			BUG_ON(!d.stop || d.redirect);
			/*
			 * Lookup copy up origin by decoding origin file handle.
			 * We may get a disconnected dentry, which is fine,
			 * because we only need to hold the origin inode in
			 * cache and use its inode number.  We may even get a
			 * connected dentry, that is not under any of the lower
			 * layers root.  That is also fine for using it's inode
			 * number - it's the same as if we held a reference
			 * to a dentry in lower layer that was moved under us.
			 */
			err = ovl_check_origin(dentry, upperdentry,
					       &stack, &ctr);
			if (err)
				goto out;
		}

		if (d.redirect) {
			upperredirect = kstrdup(d.redirect, GFP_KERNEL);
			if (!upperredirect)
				goto out_put_upper;
			if (d.redirect[0] == '/')
				poe = roe;
		}
		upperopaque = d.opaque;
	}

	if (!d.stop && poe->numlower) {
		err = -ENOMEM;
		stack = kcalloc(ofs->numlower, sizeof(struct path),
				GFP_TEMPORARY);
		if (!stack)
			goto out_put_upper;
	}

	for (i = 0; !d.stop && i < poe->numlower; i++) {
		struct path lowerpath = poe->lowerstack[i];

		d.last = i == poe->numlower - 1;
		err = ovl_lookup_layer(lowerpath.dentry, &d, &this);
		if (err)
			goto out_put;

		if (!this)
			continue;

		stack[ctr].dentry = this;
		stack[ctr].mnt = lowerpath.mnt;
		ctr++;

		if (d.stop)
			break;

		if (d.redirect && d.redirect[0] == '/' && poe != roe) {
			poe = roe;

			/* Find the current layer on the root dentry */
			for (i = 0; i < poe->numlower; i++)
				if (poe->lowerstack[i].mnt == lowerpath.mnt)
					break;
			if (WARN_ON(i == poe->numlower))
				break;
		}
	}

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

	oe->opaque = upperopaque;
	memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
	dentry->d_fsdata = oe;

	if (upperdentry || ctr) {
		err = -ENOMEM;
		inode = ovl_get_inode(dentry, upperdentry);
		if (!inode)
			goto out_free_oe;

		OVL_I(inode)->redirect = upperredirect;
	}

	revert_creds(old_cred);
	kfree(stack);
	kfree(d.redirect);
	d_add(dentry, inode);

	return NULL;

out_free_oe:
	dentry->d_fsdata = NULL;
	kfree(oe);
out_put:
	for (i = 0; i < ctr; i++)
		dput(stack[i].dentry);
	kfree(stack);
out_put_upper:
	dput(upperdentry);
	kfree(upperredirect);
out:
	kfree(d.redirect);
	revert_creds(old_cred);
	return ERR_PTR(err);
}

bool ovl_lower_positive(struct dentry *dentry)
{
	struct ovl_entry *oe = dentry->d_fsdata;
	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
	const struct qstr *name = &dentry->d_name;
	unsigned int i;
	bool positive = false;
	bool done = false;

	/*
	 * If dentry is negative, then lower is positive iff this is a
	 * whiteout.
	 */
	if (!dentry->d_inode)
		return oe->opaque;

	/* Negative upper -> positive lower */
	if (!ovl_dentry_upper(dentry))
		return true;

	/* Positive upper -> have to look up lower to see whether it exists */
	for (i = 0; !done && !positive && i < poe->numlower; i++) {
		struct dentry *this;
		struct dentry *lowerdir = poe->lowerstack[i].dentry;

		this = lookup_one_len_unlocked(name->name, lowerdir,
					       name->len);
		if (IS_ERR(this)) {
			switch (PTR_ERR(this)) {
			case -ENOENT:
			case -ENAMETOOLONG:
				break;

			default:
				/*
				 * Assume something is there, we just couldn't
				 * access it.
				 */
				positive = true;
				break;
			}
		} else {
			if (this->d_inode) {
				positive = !ovl_is_whiteout(this);
				done = true;
			}
			dput(this);
		}
	}

	return positive;
}
OpenPOWER on IntegriCloud