summaryrefslogtreecommitdiff
path: root/fs/exportfs/expfs.c
blob: 07ea3d62b2982d308439cd9c4008b0c7113df5fa (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) Neil Brown 2002
 * Copyright (C) Christoph Hellwig 2007
 *
 * This file contains the code mapping from inodes to NFS file handles,
 * and for mapping back from file handles to dentries.
 *
 * For details on why we do all the strange and hairy things in here
 * take a look at Documentation/filesystems/nfs/exporting.rst.
 */
#include <linux/exportfs.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/sched.h>
#include <linux/cred.h>

#define dprintk(fmt, args...) pr_debug(fmt, ##args)


static int get_name(const struct path *path, char *name, struct dentry *child);


static int exportfs_get_name(struct vfsmount *mnt, struct dentry *dir,
		char *name, struct dentry *child)
{
	const struct export_operations *nop = dir->d_sb->s_export_op;
	struct path path = {.mnt = mnt, .dentry = dir};

	if (nop->get_name)
		return nop->get_name(dir, name, child);
	else
		return get_name(&path, name, child);
}

/*
 * Check if the dentry or any of it's aliases is acceptable.
 */
static struct dentry *
find_acceptable_alias(struct dentry *result,
		int (*acceptable)(void *context, struct dentry *dentry),
		void *context)
{
	struct dentry *dentry, *toput = NULL;
	struct inode *inode;

	if (acceptable(context, result))
		return result;

	inode = result->d_inode;
	spin_lock(&inode->i_lock);
	hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
		dget(dentry);
		spin_unlock(&inode->i_lock);
		if (toput)
			dput(toput);
		if (dentry != result && acceptable(context, dentry)) {
			dput(result);
			return dentry;
		}
		spin_lock(&inode->i_lock);
		toput = dentry;
	}
	spin_unlock(&inode->i_lock);

	if (toput)
		dput(toput);
	return NULL;
}

static bool dentry_connected(struct dentry *dentry)
{
	dget(dentry);
	while (dentry->d_flags & DCACHE_DISCONNECTED) {
		struct dentry *parent = dget_parent(dentry);

		dput(dentry);
		if (dentry == parent) {
			dput(parent);
			return false;
		}
		dentry = parent;
	}
	dput(dentry);
	return true;
}

static void clear_disconnected(struct dentry *dentry)
{
	dget(dentry);
	while (dentry->d_flags & DCACHE_DISCONNECTED) {
		struct dentry *parent = dget_parent(dentry);

		WARN_ON_ONCE(IS_ROOT(dentry));

		spin_lock(&dentry->d_lock);
		dentry->d_flags &= ~DCACHE_DISCONNECTED;
		spin_unlock(&dentry->d_lock);

		dput(dentry);
		dentry = parent;
	}
	dput(dentry);
}

/*
 * Reconnect a directory dentry with its parent.
 *
 * This can return a dentry, or NULL, or an error.
 *
 * In the first case the returned dentry is the parent of the given
 * dentry, and may itself need to be reconnected to its parent.
 *
 * In the NULL case, a concurrent VFS operation has either renamed or
 * removed this directory.  The concurrent operation has reconnected our
 * dentry, so we no longer need to.
 */
static struct dentry *reconnect_one(struct vfsmount *mnt,
		struct dentry *dentry, char *nbuf)
{
	struct dentry *parent;
	struct dentry *tmp;
	int err;

	parent = ERR_PTR(-EACCES);
	inode_lock(dentry->d_inode);
	if (mnt->mnt_sb->s_export_op->get_parent)
		parent = mnt->mnt_sb->s_export_op->get_parent(dentry);
	inode_unlock(dentry->d_inode);

	if (IS_ERR(parent)) {
		dprintk("get_parent of %lu failed, err %ld\n",
			dentry->d_inode->i_ino, PTR_ERR(parent));
		return parent;
	}

	dprintk("%s: find name of %lu in %lu\n", __func__,
		dentry->d_inode->i_ino, parent->d_inode->i_ino);
	err = exportfs_get_name(mnt, parent, nbuf, dentry);
	if (err == -ENOENT)
		goto out_reconnected;
	if (err)
		goto out_err;
	dprintk("%s: found name: %s\n", __func__, nbuf);
	tmp = lookup_one_unlocked(mnt_idmap(mnt), nbuf, parent, strlen(nbuf));
	if (IS_ERR(tmp)) {
		dprintk("lookup failed: %ld\n", PTR_ERR(tmp));
		err = PTR_ERR(tmp);
		goto out_err;
	}
	if (tmp != dentry) {
		/*
		 * Somebody has renamed it since exportfs_get_name();
		 * great, since it could've only been renamed if it
		 * got looked up and thus connected, and it would
		 * remain connected afterwards.  We are done.
		 */
		dput(tmp);
		goto out_reconnected;
	}
	dput(tmp);
	if (IS_ROOT(dentry)) {
		err = -ESTALE;
		goto out_err;
	}
	return parent;

out_err:
	dput(parent);
	return ERR_PTR(err);
out_reconnected:
	dput(parent);
	/*
	 * Someone must have renamed our entry into another parent, in
	 * which case it has been reconnected by the rename.
	 *
	 * Or someone removed it entirely, in which case filehandle
	 * lookup will succeed but the directory is now IS_DEAD and
	 * subsequent operations on it will fail.
	 *
	 * Alternatively, maybe there was no race at all, and the
	 * filesystem is just corrupt and gave us a parent that doesn't
	 * actually contain any entry pointing to this inode.  So,
	 * double check that this worked and return -ESTALE if not:
	 */
	if (!dentry_connected(dentry))
		return ERR_PTR(-ESTALE);
	return NULL;
}

/*
 * Make sure target_dir is fully connected to the dentry tree.
 *
 * On successful return, DCACHE_DISCONNECTED will be cleared on
 * target_dir, and target_dir->d_parent->...->d_parent will reach the
 * root of the filesystem.
 *
 * Whenever DCACHE_DISCONNECTED is unset, target_dir is fully connected.
 * But the converse is not true: target_dir may have DCACHE_DISCONNECTED
 * set but already be connected.  In that case we'll verify the
 * connection to root and then clear the flag.
 *
 * Note that target_dir could be removed by a concurrent operation.  In
 * that case reconnect_path may still succeed with target_dir fully
 * connected, but further operations using the filehandle will fail when
 * necessary (due to S_DEAD being set on the directory).
 */
static int
reconnect_path(struct vfsmount *mnt, struct dentry *target_dir, char *nbuf)
{
	struct dentry *dentry, *parent;

	dentry = dget(target_dir);

	while (dentry->d_flags & DCACHE_DISCONNECTED) {
		BUG_ON(dentry == mnt->mnt_sb->s_root);

		if (IS_ROOT(dentry))
			parent = reconnect_one(mnt, dentry, nbuf);
		else
			parent = dget_parent(dentry);

		if (!parent)
			break;
		dput(dentry);
		if (IS_ERR(parent))
			return PTR_ERR(parent);
		dentry = parent;
	}
	dput(dentry);
	clear_disconnected(target_dir);
	return 0;
}

struct getdents_callback {
	struct dir_context ctx;
	char *name;		/* name that was found. It already points to a
				   buffer NAME_MAX+1 is size */
	u64 ino;		/* the inum we are looking for */
	int found;		/* inode matched? */
	int sequence;		/* sequence counter */
};

/*
 * A rather strange filldir function to capture
 * the name matching the specified inode number.
 */
static bool filldir_one(struct dir_context *ctx, const char *name, int len,
			loff_t pos, u64 ino, unsigned int d_type)
{
	struct getdents_callback *buf =
		container_of(ctx, struct getdents_callback, ctx);

	buf->sequence++;
	if (buf->ino == ino && len <= NAME_MAX && !is_dot_dotdot(name, len)) {
		memcpy(buf->name, name, len);
		buf->name[len] = '\0';
		buf->found = 1;
		return false;	// no more
	}
	return true;
}

/**
 * get_name - default export_operations->get_name function
 * @path:   the directory in which to find a name
 * @name:   a pointer to a %NAME_MAX+1 char buffer to store the name
 * @child:  the dentry for the child directory.
 *
 * calls readdir on the parent until it finds an entry with
 * the same inode number as the child, and returns that.
 */
static int get_name(const struct path *path, char *name, struct dentry *child)
{
	const struct cred *cred = current_cred();
	struct inode *dir = path->dentry->d_inode;
	int error;
	struct file *file;
	struct kstat stat;
	struct path child_path = {
		.mnt = path->mnt,
		.dentry = child,
	};
	struct getdents_callback buffer = {
		.ctx.actor = filldir_one,
		.name = name,
	};

	error = -ENOTDIR;
	if (!dir || !S_ISDIR(dir->i_mode))
		goto out;
	error = -EINVAL;
	if (!dir->i_fop)
		goto out;
	/*
	 * inode->i_ino is unsigned long, kstat->ino is u64, so the
	 * former would be insufficient on 32-bit hosts when the
	 * filesystem supports 64-bit inode numbers.  So we need to
	 * actually call ->getattr, not just read i_ino:
	 */
	error = vfs_getattr_nosec(&child_path, &stat,
				  STATX_INO, AT_STATX_SYNC_AS_STAT);
	if (error)
		return error;
	buffer.ino = stat.ino;
	/*
	 * Open the directory ...
	 */
	file = dentry_open(path, O_RDONLY, cred);
	error = PTR_ERR(file);
	if (IS_ERR(file))
		goto out;

	error = -EINVAL;
	if (!file->f_op->iterate_shared)
		goto out_close;

	buffer.sequence = 0;
	while (1) {
		int old_seq = buffer.sequence;

		error = iterate_dir(file, &buffer.ctx);
		if (buffer.found) {
			error = 0;
			break;
		}

		if (error < 0)
			break;

		error = -ENOENT;
		if (old_seq == buffer.sequence)
			break;
	}

out_close:
	fput(file);
out:
	return error;
}

#define FILEID_INO64_GEN_LEN 3

/**
 * exportfs_encode_ino64_fid - encode non-decodeable 64bit ino file id
 * @inode:   the object to encode
 * @fid:     where to store the file handle fragment
 * @max_len: maximum length to store there (in 4 byte units)
 *
 * This generic function is used to encode a non-decodeable file id for
 * fanotify for filesystems that do not support NFS export.
 */
static int exportfs_encode_ino64_fid(struct inode *inode, struct fid *fid,
				     int *max_len)
{
	if (*max_len < FILEID_INO64_GEN_LEN) {
		*max_len = FILEID_INO64_GEN_LEN;
		return FILEID_INVALID;
	}

	fid->i64.ino = inode->i_ino;
	fid->i64.gen = inode->i_generation;
	*max_len = FILEID_INO64_GEN_LEN;

	return FILEID_INO64_GEN;
}

/**
 * exportfs_encode_inode_fh - encode a file handle from inode
 * @inode:   the object to encode
 * @fid:     where to store the file handle fragment
 * @max_len: maximum length to store there
 * @parent:  parent directory inode, if wanted
 * @flags:   properties of the requested file handle
 *
 * Returns an enum fid_type or a negative errno.
 */
int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
			     int *max_len, struct inode *parent, int flags)
{
	const struct export_operations *nop = inode->i_sb->s_export_op;

	if (!exportfs_can_encode_fh(nop, flags))
		return -EOPNOTSUPP;

	if (!nop && (flags & EXPORT_FH_FID))
		return exportfs_encode_ino64_fid(inode, fid, max_len);

	return nop->encode_fh(inode, fid->raw, max_len, parent);
}
EXPORT_SYMBOL_GPL(exportfs_encode_inode_fh);

/**
 * exportfs_encode_fh - encode a file handle from dentry
 * @dentry:  the object to encode
 * @fid:     where to store the file handle fragment
 * @max_len: maximum length to store there
 * @flags:   properties of the requested file handle
 *
 * Returns an enum fid_type or a negative errno.
 */
int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len,
		       int flags)
{
	int error;
	struct dentry *p = NULL;
	struct inode *inode = dentry->d_inode, *parent = NULL;

	if ((flags & EXPORT_FH_CONNECTABLE) && !S_ISDIR(inode->i_mode)) {
		p = dget_parent(dentry);
		/*
		 * note that while p might've ceased to be our parent already,
		 * it's still pinned by and still positive.
		 */
		parent = p->d_inode;
	}

	error = exportfs_encode_inode_fh(inode, fid, max_len, parent, flags);
	dput(p);

	return error;
}
EXPORT_SYMBOL_GPL(exportfs_encode_fh);

struct dentry *
exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len,
		       int fileid_type,
		       int (*acceptable)(void *, struct dentry *),
		       void *context)
{
	const struct export_operations *nop = mnt->mnt_sb->s_export_op;
	struct dentry *result, *alias;
	char nbuf[NAME_MAX+1];
	int err;

	/*
	 * Try to get any dentry for the given file handle from the filesystem.
	 */
	if (!exportfs_can_decode_fh(nop))
		return ERR_PTR(-ESTALE);
	result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
	if (IS_ERR_OR_NULL(result))
		return result;

	/*
	 * If no acceptance criteria was specified by caller, a disconnected
	 * dentry is also accepatable. Callers may use this mode to query if
	 * file handle is stale or to get a reference to an inode without
	 * risking the high overhead caused by directory reconnect.
	 */
	if (!acceptable)
		return result;

	if (d_is_dir(result)) {
		/*
		 * This request is for a directory.
		 *
		 * On the positive side there is only one dentry for each
		 * directory inode.  On the negative side this implies that we
		 * to ensure our dentry is connected all the way up to the
		 * filesystem root.
		 */
		if (result->d_flags & DCACHE_DISCONNECTED) {
			err = reconnect_path(mnt, result, nbuf);
			if (err)
				goto err_result;
		}

		if (!acceptable(context, result)) {
			err = -EACCES;
			goto err_result;
		}

		return result;
	} else {
		/*
		 * It's not a directory.  Life is a little more complicated.
		 */
		struct dentry *target_dir, *nresult;

		/*
		 * See if either the dentry we just got from the filesystem
		 * or any alias for it is acceptable.  This is always true
		 * if this filesystem is exported without the subtreecheck
		 * option.  If the filesystem is exported with the subtree
		 * check option there's a fair chance we need to look at
		 * the parent directory in the file handle and make sure
		 * it's connected to the filesystem root.
		 */
		alias = find_acceptable_alias(result, acceptable, context);
		if (alias)
			return alias;

		/*
		 * Try to extract a dentry for the parent directory from the
		 * file handle.  If this fails we'll have to give up.
		 */
		err = -ESTALE;
		if (!nop->fh_to_parent)
			goto err_result;

		target_dir = nop->fh_to_parent(mnt->mnt_sb, fid,
				fh_len, fileid_type);
		if (!target_dir)
			goto err_result;
		err = PTR_ERR(target_dir);
		if (IS_ERR(target_dir))
			goto err_result;

		/*
		 * And as usual we need to make sure the parent directory is
		 * connected to the filesystem root.  The VFS really doesn't
		 * like disconnected directories..
		 */
		err = reconnect_path(mnt, target_dir, nbuf);
		if (err) {
			dput(target_dir);
			goto err_result;
		}

		/*
		 * Now that we've got both a well-connected parent and a
		 * dentry for the inode we're after, make sure that our
		 * inode is actually connected to the parent.
		 */
		err = exportfs_get_name(mnt, target_dir, nbuf, result);
		if (err) {
			dput(target_dir);
			goto err_result;
		}

		inode_lock(target_dir->d_inode);
		nresult = lookup_one(mnt_idmap(mnt), nbuf,
				     target_dir, strlen(nbuf));
		if (!IS_ERR(nresult)) {
			if (unlikely(nresult->d_inode != result->d_inode)) {
				dput(nresult);
				nresult = ERR_PTR(-ESTALE);
			}
		}
		inode_unlock(target_dir->d_inode);
		/*
		 * At this point we are done with the parent, but it's pinned
		 * by the child dentry anyway.
		 */
		dput(target_dir);

		if (IS_ERR(nresult)) {
			err = PTR_ERR(nresult);
			goto err_result;
		}
		dput(result);
		result = nresult;

		/*
		 * And finally make sure the dentry is actually acceptable
		 * to NFSD.
		 */
		alias = find_acceptable_alias(result, acceptable, context);
		if (!alias) {
			err = -EACCES;
			goto err_result;
		}

		return alias;
	}

 err_result:
	dput(result);
	return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(exportfs_decode_fh_raw);

struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
				  int fh_len, int fileid_type,
				  int (*acceptable)(void *, struct dentry *),
				  void *context)
{
	struct dentry *ret;

	ret = exportfs_decode_fh_raw(mnt, fid, fh_len, fileid_type,
				     acceptable, context);
	if (IS_ERR_OR_NULL(ret)) {
		if (ret == ERR_PTR(-ENOMEM))
			return ret;
		return ERR_PTR(-ESTALE);
	}
	return ret;
}
EXPORT_SYMBOL_GPL(exportfs_decode_fh);

MODULE_LICENSE("GPL");