summaryrefslogtreecommitdiffstats
path: root/fs/attr.c
blob: 3172f57f71f8dcae6b62a8c771ff759b1b8a3a4b (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/attr.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  changes by Thomas Schoebel-Theuer
 */

#include <linux/export.h>
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/sched/signal.h>
#include <linux/capability.h>
#include <linux/fsnotify.h>
#include <linux/fcntl.h>
#include <linux/security.h>
#include <linux/evm.h>
#include <linux/ima.h>

#include "internal.h"

/**
 * setattr_should_drop_sgid - determine whether the setgid bit needs to be
 *                            removed
 * @mnt_userns:	user namespace of the mount @inode was found from
 * @inode:	inode to check
 *
 * This function determines whether the setgid bit needs to be removed.
 * We retain backwards compatibility and require setgid bit to be removed
 * unconditionally if S_IXGRP is set. Otherwise we have the exact same
 * requirements as setattr_prepare() and setattr_copy().
 *
 * Return: ATTR_KILL_SGID if setgid bit needs to be removed, 0 otherwise.
 */
int setattr_should_drop_sgid(struct user_namespace *mnt_userns,
			     const struct inode *inode)
{
	umode_t mode = inode->i_mode;

	if (!(mode & S_ISGID))
		return 0;
	if (mode & S_IXGRP)
		return ATTR_KILL_SGID;
	if (!in_group_or_capable(mnt_userns, inode,
				 i_gid_into_vfsgid(mnt_userns, inode)))
		return ATTR_KILL_SGID;
	return 0;
}
EXPORT_SYMBOL(setattr_should_drop_sgid);

/**
 * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to
 *                               be dropped
 * @mnt_userns:	user namespace of the mount @inode was found from
 * @inode:	inode to check
 *
 * This function determines whether the set{g,u}id bits need to be removed.
 * If the setuid bit needs to be removed ATTR_KILL_SUID is returned. If the
 * setgid bit needs to be removed ATTR_KILL_SGID is returned. If both
 * set{g,u}id bits need to be removed the corresponding mask of both flags is
 * returned.
 *
 * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits
 * to remove, 0 otherwise.
 */
int setattr_should_drop_suidgid(struct user_namespace *mnt_userns,
				struct inode *inode)
{
	umode_t mode = inode->i_mode;
	int kill = 0;

	/* suid always must be killed */
	if (unlikely(mode & S_ISUID))
		kill = ATTR_KILL_SUID;

	kill |= setattr_should_drop_sgid(mnt_userns, inode);

	if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode)))
		return kill;

	return 0;
}
EXPORT_SYMBOL(setattr_should_drop_suidgid);

/**
 * chown_ok - verify permissions to chown inode
 * @mnt_userns:	user namespace of the mount @inode was found from
 * @inode:	inode to check permissions on
 * @ia_vfsuid:	uid to chown @inode to
 *
 * If the inode has been found through an idmapped mount the user namespace of
 * the vfsmount must be passed through @mnt_userns. This function will then
 * take care to map the inode according to @mnt_userns before checking
 * permissions. On non-idmapped mounts or if permission checking is to be
 * performed on the raw inode simply passs init_user_ns.
 */
static bool chown_ok(struct user_namespace *mnt_userns,
		     const struct inode *inode, vfsuid_t ia_vfsuid)
{
	vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
	if (vfsuid_eq_kuid(vfsuid, current_fsuid()) &&
	    vfsuid_eq(ia_vfsuid, vfsuid))
		return true;
	if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
		return true;
	if (!vfsuid_valid(vfsuid) &&
	    ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
		return true;
	return false;
}

/**
 * chgrp_ok - verify permissions to chgrp inode
 * @mnt_userns:	user namespace of the mount @inode was found from
 * @inode:	inode to check permissions on
 * @ia_vfsgid:	gid to chown @inode to
 *
 * If the inode has been found through an idmapped mount the user namespace of
 * the vfsmount must be passed through @mnt_userns. This function will then
 * take care to map the inode according to @mnt_userns before checking
 * permissions. On non-idmapped mounts or if permission checking is to be
 * performed on the raw inode simply passs init_user_ns.
 */
static bool chgrp_ok(struct user_namespace *mnt_userns,
		     const struct inode *inode, vfsgid_t ia_vfsgid)
{
	vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
	vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
	if (vfsuid_eq_kuid(vfsuid, current_fsuid())) {
		if (vfsgid_eq(ia_vfsgid, vfsgid))
			return true;
		if (vfsgid_in_group_p(ia_vfsgid))
			return true;
	}
	if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
		return true;
	if (!vfsgid_valid(vfsgid) &&
	    ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
		return true;
	return false;
}

/**
 * setattr_prepare - check if attribute changes to a dentry are allowed
 * @mnt_userns:	user namespace of the mount the inode was found from
 * @dentry:	dentry to check
 * @attr:	attributes to change
 *
 * Check if we are allowed to change the attributes contained in @attr
 * in the given dentry.  This includes the normal unix access permission
 * checks, as well as checks for rlimits and others. The function also clears
 * SGID bit from mode if user is not allowed to set it. Also file capabilities
 * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set.
 *
 * If the inode has been found through an idmapped mount the user namespace of
 * the vfsmount must be passed through @mnt_userns. This function will then
 * take care to map the inode according to @mnt_userns before checking
 * permissions. On non-idmapped mounts or if permission checking is to be
 * performed on the raw inode simply passs init_user_ns.
 *
 * Should be called as the first thing in ->setattr implementations,
 * possibly after taking additional locks.
 */
int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry,
		    struct iattr *attr)
{
	struct inode *inode = d_inode(dentry);
	unsigned int ia_valid = attr->ia_valid;

	/*
	 * First check size constraints.  These can't be overriden using
	 * ATTR_FORCE.
	 */
	if (ia_valid & ATTR_SIZE) {
		int error = inode_newsize_ok(inode, attr->ia_size);
		if (error)
			return error;
	}

	/* If force is set do it anyway. */
	if (ia_valid & ATTR_FORCE)
		goto kill_priv;

	/* Make sure a caller can chown. */
	if ((ia_valid & ATTR_UID) &&
	    !chown_ok(mnt_userns, inode, attr->ia_vfsuid))
		return -EPERM;

	/* Make sure caller can chgrp. */
	if ((ia_valid & ATTR_GID) &&
	    !chgrp_ok(mnt_userns, inode, attr->ia_vfsgid))
		return -EPERM;

	/* Make sure a caller can chmod. */
	if (ia_valid & ATTR_MODE) {
		vfsgid_t vfsgid;

		if (!inode_owner_or_capable(mnt_userns, inode))
			return -EPERM;

		if (ia_valid & ATTR_GID)
			vfsgid = attr->ia_vfsgid;
		else
			vfsgid = i_gid_into_vfsgid(mnt_userns, inode);

		/* Also check the setgid bit! */
		if (!in_group_or_capable(mnt_userns, inode, vfsgid))
			attr->ia_mode &= ~S_ISGID;
	}

	/* Check for setting the inode time. */
	if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) {
		if (!inode_owner_or_capable(mnt_userns, inode))
			return -EPERM;
	}

kill_priv:
	/* User has permission for the change */
	if (ia_valid & ATTR_KILL_PRIV) {
		int error;

		error = security_inode_killpriv(mnt_userns, dentry);
		if (error)
			return error;
	}

	return 0;
}
EXPORT_SYMBOL(setattr_prepare);

/**
 * inode_newsize_ok - may this inode be truncated to a given size
 * @inode:	the inode to be truncated
 * @offset:	the new size to assign to the inode
 *
 * inode_newsize_ok must be called with i_mutex held.
 *
 * inode_newsize_ok will check filesystem limits and ulimits to check that the
 * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ
 * when necessary. Caller must not proceed with inode size change if failure is
 * returned. @inode must be a file (not directory), with appropriate
 * permissions to allow truncate (inode_newsize_ok does NOT check these
 * conditions).
 *
 * Return: 0 on success, -ve errno on failure
 */
int inode_newsize_ok(const struct inode *inode, loff_t offset)
{
	if (offset < 0)
		return -EINVAL;
	if (inode->i_size < offset) {
		unsigned long limit;

		limit = rlimit(RLIMIT_FSIZE);
		if (limit != RLIM_INFINITY && offset > limit)
			goto out_sig;
		if (offset > inode->i_sb->s_maxbytes)
			goto out_big;
	} else {
		/*
		 * truncation of in-use swapfiles is disallowed - it would
		 * cause subsequent swapout to scribble on the now-freed
		 * blocks.
		 */
		if (IS_SWAPFILE(inode))
			return -ETXTBSY;
	}

	return 0;
out_sig:
	send_sig(SIGXFSZ, current, 0);
out_big:
	return -EFBIG;
}
EXPORT_SYMBOL(inode_newsize_ok);

/**
 * setattr_copy - copy simple metadata updates into the generic inode
 * @mnt_userns:	user namespace of the mount the inode was found from
 * @inode:	the inode to be updated
 * @attr:	the new attributes
 *
 * setattr_copy must be called with i_mutex held.
 *
 * setattr_copy updates the inode's metadata with that specified
 * in attr on idmapped mounts. Necessary permission checks to determine
 * whether or not the S_ISGID property needs to be removed are performed with
 * the correct idmapped mount permission helpers.
 * Noticeably missing is inode size update, which is more complex
 * as it requires pagecache updates.
 *
 * If the inode has been found through an idmapped mount the user namespace of
 * the vfsmount must be passed through @mnt_userns. This function will then
 * take care to map the inode according to @mnt_userns before checking
 * permissions. On non-idmapped mounts or if permission checking is to be
 * performed on the raw inode simply passs init_user_ns.
 *
 * The inode is not marked as dirty after this operation. The rationale is
 * that for "simple" filesystems, the struct inode is the inode storage.
 * The caller is free to mark the inode dirty afterwards if needed.
 */
void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode,
		  const struct iattr *attr)
{
	unsigned int ia_valid = attr->ia_valid;

	i_uid_update(mnt_userns, attr, inode);
	i_gid_update(mnt_userns, attr, inode);
	if (ia_valid & ATTR_ATIME)
		inode->i_atime = attr->ia_atime;
	if (ia_valid & ATTR_MTIME)
		inode->i_mtime = attr->ia_mtime;
	if (ia_valid & ATTR_CTIME)
		inode->i_ctime = attr->ia_ctime;
	if (ia_valid & ATTR_MODE) {
		umode_t mode = attr->ia_mode;
		if (!in_group_or_capable(mnt_userns, inode,
					 i_gid_into_vfsgid(mnt_userns, inode)))
			mode &= ~S_ISGID;
		inode->i_mode = mode;
	}
}
EXPORT_SYMBOL(setattr_copy);

int may_setattr(struct user_namespace *mnt_userns, struct inode *inode,
		unsigned int ia_valid)
{
	int error;

	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
		if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
			return -EPERM;
	}

	/*
	 * If utimes(2) and friends are called with times == NULL (or both
	 * times are UTIME_NOW), then we need to check for write permission
	 */
	if (ia_valid & ATTR_TOUCH) {
		if (IS_IMMUTABLE(inode))
			return -EPERM;

		if (!inode_owner_or_capable(mnt_userns, inode)) {
			error = inode_permission(mnt_userns, inode, MAY_WRITE);
			if (error)
				return error;
		}
	}
	return 0;
}
EXPORT_SYMBOL(may_setattr);

/**
 * notify_change - modify attributes of a filesytem object
 * @mnt_userns:	user namespace of the mount the inode was found from
 * @dentry:	object affected
 * @attr:	new attributes
 * @delegated_inode: returns inode, if the inode is delegated
 *
 * The caller must hold the i_mutex on the affected object.
 *
 * If notify_change discovers a delegation in need of breaking,
 * it will return -EWOULDBLOCK and return a reference to the inode in
 * delegated_inode.  The caller should then break the delegation and
 * retry.  Because breaking a delegation may take a long time, the
 * caller should drop the i_mutex before doing so.
 *
 * Alternatively, a caller may pass NULL for delegated_inode.  This may
 * be appropriate for callers that expect the underlying filesystem not
 * to be NFS exported.  Also, passing NULL is fine for callers holding
 * the file open for write, as there can be no conflicting delegation in
 * that case.
 *
 * If the inode has been found through an idmapped mount the user namespace of
 * the vfsmount must be passed through @mnt_userns. This function will then
 * take care to map the inode according to @mnt_userns before checking
 * permissions. On non-idmapped mounts or if permission checking is to be
 * performed on the raw inode simply passs init_user_ns.
 */
int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
		  struct iattr *attr, struct inode **delegated_inode)
{
	struct inode *inode = dentry->d_inode;
	umode_t mode = inode->i_mode;
	int error;
	struct timespec64 now;
	unsigned int ia_valid = attr->ia_valid;

	WARN_ON_ONCE(!inode_is_locked(inode));

	error = may_setattr(mnt_userns, inode, ia_valid);
	if (error)
		return error;

	if ((ia_valid & ATTR_MODE)) {
		/*
		 * Don't allow changing the mode of symlinks:
		 *
		 * (1) The vfs doesn't take the mode of symlinks into account
		 *     during permission checking.
		 * (2) This has never worked correctly. Most major filesystems
		 *     did return EOPNOTSUPP due to interactions with POSIX ACLs
		 *     but did still updated the mode of the symlink.
		 *     This inconsistency led system call wrapper providers such
		 *     as libc to block changing the mode of symlinks with
		 *     EOPNOTSUPP already.
		 * (3) To even do this in the first place one would have to use
		 *     specific file descriptors and quite some effort.
		 */
		if (S_ISLNK(inode->i_mode))
			return -EOPNOTSUPP;

		/* Flag setting protected by i_mutex */
		if (is_sxid(attr->ia_mode))
			inode->i_flags &= ~S_NOSEC;
	}

	now = current_time(inode);

	attr->ia_ctime = now;
	if (!(ia_valid & ATTR_ATIME_SET))
		attr->ia_atime = now;
	else
		attr->ia_atime = timestamp_truncate(attr->ia_atime, inode);
	if (!(ia_valid & ATTR_MTIME_SET))
		attr->ia_mtime = now;
	else
		attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode);

	if (ia_valid & ATTR_KILL_PRIV) {
		error = security_inode_need_killpriv(dentry);
		if (error < 0)
			return error;
		if (error == 0)
			ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV;
	}

	/*
	 * We now pass ATTR_KILL_S*ID to the lower level setattr function so
	 * that the function has the ability to reinterpret a mode change
	 * that's due to these bits. This adds an implicit restriction that
	 * no function will ever call notify_change with both ATTR_MODE and
	 * ATTR_KILL_S*ID set.
	 */
	if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) &&
	    (ia_valid & ATTR_MODE))
		BUG();

	if (ia_valid & ATTR_KILL_SUID) {
		if (mode & S_ISUID) {
			ia_valid = attr->ia_valid |= ATTR_MODE;
			attr->ia_mode = (inode->i_mode & ~S_ISUID);
		}
	}
	if (ia_valid & ATTR_KILL_SGID) {
		if (mode & S_ISGID) {
			if (!(ia_valid & ATTR_MODE)) {
				ia_valid = attr->ia_valid |= ATTR_MODE;
				attr->ia_mode = inode->i_mode;
			}
			attr->ia_mode &= ~S_ISGID;
		}
	}
	if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID)))
		return 0;

	/*
	 * Verify that uid/gid changes are valid in the target
	 * namespace of the superblock.
	 */
	if (ia_valid & ATTR_UID &&
	    !vfsuid_has_fsmapping(mnt_userns, inode->i_sb->s_user_ns,
				  attr->ia_vfsuid))
		return -EOVERFLOW;
	if (ia_valid & ATTR_GID &&
	    !vfsgid_has_fsmapping(mnt_userns, inode->i_sb->s_user_ns,
				  attr->ia_vfsgid))
		return -EOVERFLOW;

	/* Don't allow modifications of files with invalid uids or
	 * gids unless those uids & gids are being made valid.
	 */
	if (!(ia_valid & ATTR_UID) &&
	    !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)))
		return -EOVERFLOW;
	if (!(ia_valid & ATTR_GID) &&
	    !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode)))
		return -EOVERFLOW;

	error = security_inode_setattr(mnt_userns, dentry, attr);
	if (error)
		return error;
	error = try_break_deleg(inode, delegated_inode);
	if (error)
		return error;

	if (inode->i_op->setattr)
		error = inode->i_op->setattr(mnt_userns, dentry, attr);
	else
		error = simple_setattr(mnt_userns, dentry, attr);

	if (!error) {
		fsnotify_change(dentry, ia_valid);
		ima_inode_post_setattr(mnt_userns, dentry);
		evm_inode_post_setattr(dentry, ia_valid);
	}

	return error;
}
EXPORT_SYMBOL(notify_change);