aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/user_namespace.c
blob: 86602316422d203fffb8c530cbf44f825199a5f7 (plain) (blame)
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
/*
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License as
 *  published by the Free Software Foundation, version 2 of the
 *  License.
 */

#include <linux/export.h>
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/user_namespace.h>
#include <linux/highuid.h>
#include <linux/cred.h>
#include <linux/securebits.h>
#include <linux/keyctl.h>
#include <linux/key-type.h>
#include <keys/user-type.h>
#include <linux/seq_file.h>
#include <linux/fs.h>
#include <linux/uaccess.h>
#include <linux/ctype.h>

static struct kmem_cache *user_ns_cachep __read_mostly;

static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
				struct uid_gid_map *map);

/*
 * Create a new user namespace, deriving the creator from the user in the
 * passed credentials, and replacing that user with the new root user for the
 * new namespace.
 *
 * This is called by copy_creds(), which will finish setting the target task's
 * credentials.
 */
int create_user_ns(struct cred *new)
{
	struct user_namespace *ns, *parent_ns = new->user_ns;
	kuid_t owner = new->euid;
	kgid_t group = new->egid;

	/* The creator needs a mapping in the parent user namespace
	 * or else we won't be able to reasonably tell userspace who
	 * created a user_namespace.
	 */
	if (!kuid_has_mapping(parent_ns, owner) ||
	    !kgid_has_mapping(parent_ns, group))
		return -EPERM;

	ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL);
	if (!ns)
		return -ENOMEM;

	kref_init(&ns->kref);
	ns->parent = parent_ns;
	ns->owner = owner;
	ns->group = group;

	/* Start with the same capabilities as init but useless for doing
	 * anything as the capabilities are bound to the new user namespace.
	 */
	new->securebits = SECUREBITS_DEFAULT;
	new->cap_inheritable = CAP_EMPTY_SET;
	new->cap_permitted = CAP_FULL_SET;
	new->cap_effective = CAP_FULL_SET;
	new->cap_bset = CAP_FULL_SET;
#ifdef CONFIG_KEYS
	key_put(new->request_key_auth);
	new->request_key_auth = NULL;
#endif
	/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */

	/* Leave the new->user_ns reference with the new user namespace. */
	/* Leave the reference to our user_ns with the new cred. */
	new->user_ns = ns;

	return 0;
}

void free_user_ns(struct kref *kref)
{
	struct user_namespace *parent, *ns =
		container_of(kref, struct user_namespace, kref);

	parent = ns->parent;
	kmem_cache_free(user_ns_cachep, ns);
	put_user_ns(parent);
}
EXPORT_SYMBOL(free_user_ns);

static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
{
	unsigned idx, extents;
	u32 first, last, id2;

	id2 = id + count - 1;

	/* Find the matching extent */
	extents = map->nr_extents;
	smp_read_barrier_depends();
	for (idx = 0; idx < extents; idx++) {
		first = map->extent[idx].first;
		last = first + map->extent[idx].count - 1;
		if (id >= first && id <= last &&
		    (id2 >= first && id2 <= last))
			break;
	}
	/* Map the id or note failure */
	if (idx < extents)
		id = (id - first) + map->extent[idx].lower_first;
	else
		id = (u32) -1;

	return id;
}

static u32 map_id_down(struct uid_gid_map *map, u32 id)
{
	unsigned idx, extents;
	u32 first, last;

	/* Find the matching extent */
	extents = map->nr_extents;
	smp_read_barrier_depends();
	for (idx = 0; idx < extents; idx++) {
		first = map->extent[idx].first;
		last = first + map->extent[idx].count - 1;
		if (id >= first && id <= last)
			break;
	}
	/* Map the id or note failure */
	if (idx < extents)
		id = (id - first) + map->extent[idx].lower_first;
	else
		id = (u32) -1;

	return id;
}

static u32 map_id_up(struct uid_gid_map *map, u32 id)
{
	unsigned idx, extents;
	u32 first, last;

	/* Find the matching extent */
	extents = map->nr_extents;
	smp_read_barrier_depends();
	for (idx = 0; idx < extents; idx++) {
		first = map->extent[idx].lower_first;
		last = first + map->extent[idx].count - 1;
		if (id >= first && id <= last)
			break;
	}
	/* Map the id or note failure */
	if (idx < extents)
		id = (id - first) + map->extent[idx].first;
	else
		id = (u32) -1;

	return id;
}

/**
 *	make_kuid - Map a user-namespace uid pair into a kuid.
 *	@ns:  User namespace that the uid is in
 *	@uid: User identifier
 *
 *	Maps a user-namespace uid pair into a kernel internal kuid,
 *	and returns that kuid.
 *
 *	When there is no mapping defined for the user-namespace uid
 *	pair INVALID_UID is returned.  Callers are expected to test
 *	for and handle handle INVALID_UID being returned.  INVALID_UID
 *	may be tested for using uid_valid().
 */
kuid_t make_kuid(struct user_namespace *ns, uid_t uid)
{
	/* Map the uid to a global kernel uid */
	return KUIDT_INIT(map_id_down(&ns->uid_map, uid));
}
EXPORT_SYMBOL(make_kuid);

/**
 *	from_kuid - Create a uid from a kuid user-namespace pair.
 *	@targ: The user namespace we want a uid in.
 *	@kuid: The kernel internal uid to start with.
 *
 *	Map @kuid into the user-namespace specified by @targ and
 *	return the resulting uid.
 *
 *	There is always a mapping into the initial user_namespace.
 *
 *	If @kuid has no mapping in @targ (uid_t)-1 is returned.
 */
uid_t from_kuid(struct user_namespace *targ, kuid_t kuid)
{
	/* Map the uid from a global kernel uid */
	return map_id_up(&targ->uid_map, __kuid_val(kuid));
}
EXPORT_SYMBOL(from_kuid);

/**
 *	from_kuid_munged - Create a uid from a kuid user-namespace pair.
 *	@targ: The user namespace we want a uid in.
 *	@kuid: The kernel internal uid to start with.
 *
 *	Map @kuid into the user-namespace specified by @targ and
 *	return the resulting uid.
 *
 *	There is always a mapping into the initial user_namespace.
 *
 *	Unlike from_kuid from_kuid_munged never fails and always
 *	returns a valid uid.  This makes from_kuid_munged appropriate
 *	for use in syscalls like stat and getuid where failing the
 *	system call and failing to provide a valid uid are not an
 *	options.
 *
 *	If @kuid has no mapping in @targ overflowuid is returned.
 */
uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid)
{
	uid_t uid;
	uid = from_kuid(targ, kuid);

	if (uid == (uid_t) -1)
		uid = overflowuid;
	return uid;
}
EXPORT_SYMBOL(from_kuid_munged);

/**
 *	make_kgid - Map a user-namespace gid pair into a kgid.
 *	@ns:  User namespace that the gid is in
 *	@uid: group identifier
 *
 *	Maps a user-namespace gid pair into a kernel internal kgid,
 *	and returns that kgid.
 *
 *	When there is no mapping defined for the user-namespace gid
 *	pair INVALID_GID is returned.  Callers are expected to test
 *	for and handle INVALID_GID being returned.  INVALID_GID may be
 *	tested for using gid_valid().
 */
kgid_t make_kgid(struct user_namespace *ns, gid_t gid)
{
	/* Map the gid to a global kernel gid */
	return KGIDT_INIT(map_id_down(&ns->gid_map, gid));
}
EXPORT_SYMBOL(make_kgid);

/**
 *	from_kgid - Create a gid from a kgid user-namespace pair.
 *	@targ: The user namespace we want a gid in.
 *	@kgid: The kernel internal gid to start with.
 *
 *	Map @kgid into the user-namespace specified by @targ and
 *	return the resulting gid.
 *
 *	There is always a mapping into the initial user_namespace.
 *
 *	If @kgid has no mapping in @targ (gid_t)-1 is returned.
 */
gid_t from_kgid(struct user_namespace *targ, kgid_t kgid)
{
	/* Map the gid from a global kernel gid */
	return map_id_up(&targ->gid_map, __kgid_val(kgid));
}
EXPORT_SYMBOL(from_kgid);

/**
 *	from_kgid_munged - Create a gid from a kgid user-namespace pair.
 *	@targ: The user namespace we want a gid in.
 *	@kgid: The kernel internal gid to start with.
 *
 *	Map @kgid into the user-namespace specified by @targ and
 *	return the resulting gid.
 *
 *	There is always a mapping into the initial user_namespace.
 *
 *	Unlike from_kgid from_kgid_munged never fails and always
 *	returns a valid gid.  This makes from_kgid_munged appropriate
 *	for use in syscalls like stat and getgid where failing the
 *	system call and failing to provide a valid gid are not options.
 *
 *	If @kgid has no mapping in @targ overflowgid is returned.
 */
gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid)
{
	gid_t gid;
	gid = from_kgid(targ, kgid);

	if (gid == (gid_t) -1)
		gid = overflowgid;
	return gid;
}
EXPORT_SYMBOL(from_kgid_munged);

static int uid_m_show(struct seq_file *seq, void *v)
{
	struct user_namespace *ns = seq->private;
	struct uid_gid_extent *extent = v;
	struct user_namespace *lower_ns;
	uid_t lower;

	lower_ns = current_user_ns();
	if ((lower_ns == ns) && lower_ns->parent)
		lower_ns = lower_ns->parent;

	lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first));

	seq_printf(seq, "%10u %10u %10u\n",
		extent->first,
		lower,
		extent->count);

	return 0;
}

static int gid_m_show(struct seq_file *seq, void *v)
{
	struct user_namespace *ns = seq->private;
	struct uid_gid_extent *extent = v;
	struct user_namespace *lower_ns;
	gid_t lower;

	lower_ns = current_user_ns();
	if ((lower_ns == ns) && lower_ns->parent)
		lower_ns = lower_ns->parent;

	lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first));

	seq_printf(seq, "%10u %10u %10u\n",
		extent->first,
		lower,
		extent->count);

	return 0;
}

static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map)
{
	struct uid_gid_extent *extent = NULL;
	loff_t pos = *ppos;

	if (pos < map->nr_extents)
		extent = &map->extent[pos];

	return extent;
}

static void *uid_m_start(struct seq_file *seq, loff_t *ppos)
{
	struct user_namespace *ns = seq->private;

	return m_start(seq, ppos, &ns->uid_map);
}

static void *gid_m_start(struct seq_file *seq, loff_t *ppos)
{
	struct user_namespace *ns = seq->private;

	return m_start(seq, ppos, &ns->gid_map);
}

static void *m_next(struct seq_file *seq, void *v, loff_t *pos)
{
	(*pos)++;
	return seq->op->start(seq, pos);
}

static void m_stop(struct seq_file *seq, void *v)
{
	return;
}

struct seq_operations proc_uid_seq_operations = {
	.start = uid_m_start,
	.stop = m_stop,
	.next = m_next,
	.show = uid_m_show,
};

struct seq_operations proc_gid_seq_operations = {
	.start = gid_m_start,
	.stop = m_stop,
	.next = m_next,
	.show = gid_m_show,
};

static DEFINE_MUTEX(id_map_mutex);

static ssize_t map_write(struct file *file, const char __user *buf,
			 size_t count, loff_t *ppos,
			 int cap_setid,
			 struct uid_gid_map *map,
			 struct uid_gid_map *parent_map)
{
	struct seq_file *seq = file->private_data;
	struct user_namespace *ns = seq->private;
	struct uid_gid_map new_map;
	unsigned idx;
	struct uid_gid_extent *extent, *last = NULL;
	unsigned long page = 0;
	char *kbuf, *pos, *next_line;
	ssize_t ret = -EINVAL;

	/*
	 * The id_map_mutex serializes all writes to any given map.
	 *
	 * Any map is only ever written once.
	 *
	 * An id map fits within 1 cache line on most architectures.
	 *
	 * On read nothing needs to be done unless you are on an
	 * architecture with a crazy cache coherency model like alpha.
	 *
	 * There is a one time data dependency between reading the
	 * count of the extents and the values of the extents.  The
	 * desired behavior is to see the values of the extents that
	 * were written before the count of the extents.
	 *
	 * To achieve this smp_wmb() is used on guarantee the write
	 * order and smp_read_barrier_depends() is guaranteed that we
	 * don't have crazy architectures returning stale data.
	 *
	 */
	mutex_lock(&id_map_mutex);

	ret = -EPERM;
	/* Only allow one successful write to the map */
	if (map->nr_extents != 0)
		goto out;

	/* Require the appropriate privilege CAP_SETUID or CAP_SETGID
	 * over the user namespace in order to set the id mapping.
	 */
	if (!ns_capable(ns, cap_setid))
		goto out;

	/* Get a buffer */
	ret = -ENOMEM;
	page = __get_free_page(GFP_TEMPORARY);
	kbuf = (char *) page;
	if (!page)
		goto out;

	/* Only allow <= page size writes at the beginning of the file */
	ret = -EINVAL;
	if ((*ppos != 0) || (count >= PAGE_SIZE))
		goto out;

	/* Slurp in the user data */
	ret = -EFAULT;
	if (copy_from_user(kbuf, buf, count))
		goto out;
	kbuf[count] = '\0';

	/* Parse the user data */
	ret = -EINVAL;
	pos = kbuf;
	new_map.nr_extents = 0;
	for (;pos; pos = next_line) {
		extent = &new_map.extent[new_map.nr_extents];

		/* Find the end of line and ensure I don't look past it */
		next_line = strchr(pos, '\n');
		if (next_line) {
			*next_line = '\0';
			next_line++;
			if (*next_line == '\0')
				next_line = NULL;
		}

		pos = skip_spaces(pos);
		extent->first = simple_strtoul(pos, &pos, 10);
		if (!isspace(*pos))
			goto out;

		pos = skip_spaces(pos);
		extent->lower_first = simple_strtoul(pos, &pos, 10);
		if (!isspace(*pos))
			goto out;

		pos = skip_spaces(pos);
		extent->count = simple_strtoul(pos, &pos, 10);
		if (*pos && !isspace(*pos))
			goto out;

		/* Verify there is not trailing junk on the line */
		pos = skip_spaces(pos);
		if (*pos != '\0')
			goto out;

		/* Verify we have been given valid starting values */
		if ((extent->first == (u32) -1) ||
		    (extent->lower_first == (u32) -1 ))
			goto out;

		/* Verify count is not zero and does not cause the extent to wrap */
		if ((extent->first + extent->count) <= extent->first)
			goto out;
		if ((extent->lower_first + extent->count) <= extent->lower_first)
			goto out;

		/* For now only accept extents that are strictly in order */
		if (last &&
		    (((last->first + last->count) > extent->first) ||
		     ((last->lower_first + last->count) > extent->lower_first)))
			goto out;

		new_map.nr_extents++;
		last = extent;

		/* Fail if the file contains too many extents */
		if ((new_map.nr_extents == UID_GID_MAP_MAX_EXTENTS) &&
		    (next_line != NULL))
			goto out;
	}
	/* Be very certaint the new map actually exists */
	if (new_map.nr_extents == 0)
		goto out;

	ret = -EPERM;
	/* Validate the user is allowed to use user id's mapped to. */
	if (!new_idmap_permitted(ns, cap_setid, &new_map))
		goto out;

	/* Map the lower ids from the parent user namespace to the
	 * kernel global id space.
	 */
	for (idx = 0; idx < new_map.nr_extents; idx++) {
		u32 lower_first;
		extent = &new_map.extent[idx];

		lower_first = map_id_range_down(parent_map,
						extent->lower_first,
						extent->count);

		/* Fail if we can not map the specified extent to
		 * the kernel global id space.
		 */
		if (lower_first == (u32) -1)
			goto out;

		extent->lower_first = lower_first;
	}

	/* Install the map */
	memcpy(map->extent, new_map.extent,
		new_map.nr_extents*sizeof(new_map.extent[0]));
	smp_wmb();
	map->nr_extents = new_map.nr_extents;

	*ppos = count;
	ret = count;
out:
	mutex_unlock(&id_map_mutex);
	if (page)
		free_page(page);
	return ret;
}

ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos)
{
	struct seq_file *seq = file->private_data;
	struct user_namespace *ns = seq->private;

	if (!ns->parent)
		return -EPERM;

	return map_write(file, buf, size, ppos, CAP_SETUID,
			 &ns->uid_map, &ns->parent->uid_map);
}

ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos)
{
	struct seq_file *seq = file->private_data;
	struct user_namespace *ns = seq->private;

	if (!ns->parent)
		return -EPERM;

	return map_write(file, buf, size, ppos, CAP_SETGID,
			 &ns->gid_map, &ns->parent->gid_map);
}

static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
				struct uid_gid_map *new_map)
{
	/* Allow the specified ids if we have the appropriate capability
	 * (CAP_SETUID or CAP_SETGID) over the parent user namespace.
	 */
	if (ns_capable(ns->parent, cap_setid))
		return true;

	return false;
}

static __init int user_namespaces_init(void)
{
	user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC);
	return 0;
}
module_init(user_namespaces_init);