user_namespace.c 27.5 KB
Newer Older
1 2 3 4 5 6 7
/*
 *  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.
 */

8
#include <linux/export.h>
9
#include <linux/nsproxy.h>
10
#include <linux/slab.h>
11
#include <linux/sched/signal.h>
12
#include <linux/user_namespace.h>
13
#include <linux/proc_ns.h>
14
#include <linux/highuid.h>
15
#include <linux/cred.h>
16
#include <linux/securebits.h>
17 18 19 20 21 22 23
#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>
24
#include <linux/projid.h>
25
#include <linux/fs_struct.h>
26

27
static struct kmem_cache *user_ns_cachep __read_mostly;
28
static DEFINE_MUTEX(userns_state_mutex);
29

30 31
static bool new_idmap_permitted(const struct file *file,
				struct user_namespace *ns, int cap_setid,
32
				struct uid_gid_map *map);
33
static void free_user_ns(struct work_struct *work);
34

35 36 37 38 39 40 41 42 43 44
static struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid)
{
	return inc_ucount(ns, uid, UCOUNT_USER_NAMESPACES);
}

static void dec_user_namespaces(struct ucounts *ucounts)
{
	return dec_ucount(ucounts, UCOUNT_USER_NAMESPACES);
}

45 46 47 48 49 50 51 52 53
static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns)
{
	/* Start with the same capabilities as init but useless for doing
	 * anything as the capabilities are bound to the new user namespace.
	 */
	cred->securebits = SECUREBITS_DEFAULT;
	cred->cap_inheritable = CAP_EMPTY_SET;
	cred->cap_permitted = CAP_FULL_SET;
	cred->cap_effective = CAP_FULL_SET;
54
	cred->cap_ambient = CAP_EMPTY_SET;
55 56 57 58 59 60 61 62 63
	cred->cap_bset = CAP_FULL_SET;
#ifdef CONFIG_KEYS
	key_put(cred->request_key_auth);
	cred->request_key_auth = NULL;
#endif
	/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
	cred->user_ns = user_ns;
}

Serge E. Hallyn's avatar
Serge E. Hallyn committed
64
/*
65 66 67 68 69 70
 * 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.
Serge E. Hallyn's avatar
Serge E. Hallyn committed
71
 */
72
int create_user_ns(struct cred *new)
Serge E. Hallyn's avatar
Serge E. Hallyn committed
73
{
74
	struct user_namespace *ns, *parent_ns = new->user_ns;
75 76
	kuid_t owner = new->euid;
	kgid_t group = new->egid;
77
	struct ucounts *ucounts;
78
	int ret, i;
79

80
	ret = -ENOSPC;
81
	if (parent_ns->level > 32)
82 83
		goto fail;

84 85
	ucounts = inc_user_namespaces(parent_ns, owner);
	if (!ucounts)
86
		goto fail;
87

88 89 90 91 92 93
	/*
	 * Verify that we can not violate the policy of which files
	 * may be accessed that is specified by the root directory,
	 * by verifing that the root directory is at the root of the
	 * mount namespace which allows all files to be accessed.
	 */
94
	ret = -EPERM;
95
	if (current_chrooted())
96
		goto fail_dec;
97

98 99 100 101
	/* 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.
	 */
102
	ret = -EPERM;
103 104
	if (!kuid_has_mapping(parent_ns, owner) ||
	    !kgid_has_mapping(parent_ns, group))
105
		goto fail_dec;
Serge E. Hallyn's avatar
Serge E. Hallyn committed
106

107
	ret = -ENOMEM;
108
	ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL);
Serge E. Hallyn's avatar
Serge E. Hallyn committed
109
	if (!ns)
110
		goto fail_dec;
Serge E. Hallyn's avatar
Serge E. Hallyn committed
111

112
	ret = ns_alloc_inum(&ns->ns);
113 114
	if (ret)
		goto fail_free;
115
	ns->ns.ops = &userns_operations;
116

117
	atomic_set(&ns->count, 1);
118
	/* Leave the new->user_ns reference with the new user namespace. */
119
	ns->parent = parent_ns;
120
	ns->level = parent_ns->level + 1;
121 122
	ns->owner = owner;
	ns->group = group;
123
	INIT_WORK(&ns->work, free_user_ns);
124 125 126
	for (i = 0; i < UCOUNT_COUNTS; i++) {
		ns->ucount_max[i] = INT_MAX;
	}
127
	ns->ucounts = ucounts;
128

129 130 131 132 133
	/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
	mutex_lock(&userns_state_mutex);
	ns->flags = parent_ns->flags;
	mutex_unlock(&userns_state_mutex);

134 135 136
#ifdef CONFIG_PERSISTENT_KEYRINGS
	init_rwsem(&ns->persistent_keyring_register_sem);
#endif
137 138 139 140 141
	ret = -ENOMEM;
	if (!setup_userns_sysctls(ns))
		goto fail_keyring;

	set_cred_user_ns(new, ns);
142
	return 0;
143 144 145 146 147
fail_keyring:
#ifdef CONFIG_PERSISTENT_KEYRINGS
	key_put(ns->persistent_keyring_register);
#endif
	ns_free_inum(&ns->ns);
148
fail_free:
149
	kmem_cache_free(user_ns_cachep, ns);
150
fail_dec:
151
	dec_user_namespaces(ucounts);
152
fail:
153
	return ret;
154 155
}

156 157 158
int unshare_userns(unsigned long unshare_flags, struct cred **new_cred)
{
	struct cred *cred;
159
	int err = -ENOMEM;
160 161 162 163 164

	if (!(unshare_flags & CLONE_NEWUSER))
		return 0;

	cred = prepare_creds();
165 166 167 168 169 170 171
	if (cred) {
		err = create_user_ns(cred);
		if (err)
			put_cred(cred);
		else
			*new_cred = cred;
	}
172

173
	return err;
174 175
}

176
static void free_user_ns(struct work_struct *work)
177
{
178 179
	struct user_namespace *parent, *ns =
		container_of(work, struct user_namespace, work);
180

181
	do {
182
		struct ucounts *ucounts = ns->ucounts;
183
		parent = ns->parent;
184
		retire_userns_sysctls(ns);
185 186 187
#ifdef CONFIG_PERSISTENT_KEYRINGS
		key_put(ns->persistent_keyring_register);
#endif
188
		ns_free_inum(&ns->ns);
189
		kmem_cache_free(user_ns_cachep, ns);
190
		dec_user_namespaces(ucounts);
191 192
		ns = parent;
	} while (atomic_dec_and_test(&parent->count));
193
}
194 195 196 197 198 199

void __put_user_ns(struct user_namespace *ns)
{
	schedule_work(&ns->work);
}
EXPORT_SYMBOL(__put_user_ns);
200

201
static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
202
{
203 204
	unsigned idx, extents;
	u32 first, last, id2;
205

206
	id2 = id + count - 1;
207

208 209
	/* Find the matching extent */
	extents = map->nr_extents;
210
	smp_rmb();
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233
	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;
234
	smp_rmb();
235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
	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;
257
	smp_rmb();
258 259 260 261 262
	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;
263
	}
264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282
	/* 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
283
 *	for and handle INVALID_UID being returned.  INVALID_UID
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
 *	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
344
 *	@gid: group identifier
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
 *
 *	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);

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
/**
 *	make_kprojid - Map a user-namespace projid pair into a kprojid.
 *	@ns:  User namespace that the projid is in
 *	@projid: Project 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 projid
 *	pair INVALID_PROJID is returned.  Callers are expected to test
 *	for and handle handle INVALID_PROJID being returned.  INVALID_PROJID
 *	may be tested for using projid_valid().
 */
kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid)
{
	/* Map the uid to a global kernel uid */
	return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid));
}
EXPORT_SYMBOL(make_kprojid);

/**
 *	from_kprojid - Create a projid from a kprojid user-namespace pair.
 *	@targ: The user namespace we want a projid in.
 *	@kprojid: The kernel internal project identifier to start with.
 *
 *	Map @kprojid into the user-namespace specified by @targ and
 *	return the resulting projid.
 *
 *	There is always a mapping into the initial user_namespace.
 *
 *	If @kprojid has no mapping in @targ (projid_t)-1 is returned.
 */
projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid)
{
	/* Map the uid from a global kernel uid */
	return map_id_up(&targ->projid_map, __kprojid_val(kprojid));
}
EXPORT_SYMBOL(from_kprojid);

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

	if (projid == (projid_t) -1)
		projid = OVERFLOW_PROJID;
	return projid;
}
EXPORT_SYMBOL(from_kprojid_munged);


477 478 479 480 481 482
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;
483

484
	lower_ns = seq_user_ns(seq);
485 486 487 488 489 490 491 492 493 494 495
	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;
496 497
}

498
static int gid_m_show(struct seq_file *seq, void *v)
499
{
500 501 502 503
	struct user_namespace *ns = seq->private;
	struct uid_gid_extent *extent = v;
	struct user_namespace *lower_ns;
	gid_t lower;
504

505
	lower_ns = seq_user_ns(seq);
506 507
	if ((lower_ns == ns) && lower_ns->parent)
		lower_ns = lower_ns->parent;
508

509 510 511 512 513 514 515 516 517 518
	lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first));

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

	return 0;
}

519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539
static int projid_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;
	projid_t lower;

	lower_ns = seq_user_ns(seq);
	if ((lower_ns == ns) && lower_ns->parent)
		lower_ns = lower_ns->parent;

	lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first));

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

	return 0;
}

540 541
static void *m_start(struct seq_file *seq, loff_t *ppos,
		     struct uid_gid_map *map)
542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565
{
	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);
}

566 567 568 569 570 571 572
static void *projid_m_start(struct seq_file *seq, loff_t *ppos)
{
	struct user_namespace *ns = seq->private;

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

573 574 575 576 577 578 579 580 581 582 583
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;
}

584
const struct seq_operations proc_uid_seq_operations = {
585 586 587 588 589 590
	.start = uid_m_start,
	.stop = m_stop,
	.next = m_next,
	.show = uid_m_show,
};

591
const struct seq_operations proc_gid_seq_operations = {
592 593 594 595 596 597
	.start = gid_m_start,
	.stop = m_stop,
	.next = m_next,
	.show = gid_m_show,
};

598
const struct seq_operations proc_projid_seq_operations = {
599 600 601 602 603 604
	.start = projid_m_start,
	.stop = m_stop,
	.next = m_next,
	.show = projid_m_show,
};

605 606
static bool mappings_overlap(struct uid_gid_map *new_map,
			     struct uid_gid_extent *extent)
607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640
{
	u32 upper_first, lower_first, upper_last, lower_last;
	unsigned idx;

	upper_first = extent->first;
	lower_first = extent->lower_first;
	upper_last = upper_first + extent->count - 1;
	lower_last = lower_first + extent->count - 1;

	for (idx = 0; idx < new_map->nr_extents; idx++) {
		u32 prev_upper_first, prev_lower_first;
		u32 prev_upper_last, prev_lower_last;
		struct uid_gid_extent *prev;

		prev = &new_map->extent[idx];

		prev_upper_first = prev->first;
		prev_lower_first = prev->lower_first;
		prev_upper_last = prev_upper_first + prev->count - 1;
		prev_lower_last = prev_lower_first + prev->count - 1;

		/* Does the upper range intersect a previous extent? */
		if ((prev_upper_first <= upper_last) &&
		    (prev_upper_last >= upper_first))
			return true;

		/* Does the lower range intersect a previous extent? */
		if ((prev_lower_first <= lower_last) &&
		    (prev_lower_last >= lower_first))
			return true;
	}
	return false;
}

641 642 643 644 645 646 647 648 649 650
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;
651
	struct uid_gid_extent *extent = NULL;
652
	char *kbuf = NULL, *pos, *next_line;
653 654 655
	ssize_t ret = -EINVAL;

	/*
656
	 * The userns_state_mutex serializes all writes to any given map.
657 658 659 660 661 662 663 664 665 666 667 668 669 670
	 *
	 * 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
671 672
	 * order and smp_rmb() is guaranteed that we don't have crazy
	 * architectures returning stale data.
673
	 */
674
	mutex_lock(&userns_state_mutex);
675 676 677 678 679 680

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

681 682
	/*
	 * Adjusting namespace settings requires capabilities on the target.
683
	 */
684
	if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN))
685 686
		goto out;

687
	/* Only allow < page size writes at the beginning of the file */
688 689 690 691 692
	ret = -EINVAL;
	if ((*ppos != 0) || (count >= PAGE_SIZE))
		goto out;

	/* Slurp in the user data */
693 694 695 696
	kbuf = memdup_user_nul(buf, count);
	if (IS_ERR(kbuf)) {
		ret = PTR_ERR(kbuf);
		kbuf = NULL;
697
		goto out;
698
	}
699 700 701 702 703

	/* Parse the user data */
	ret = -EINVAL;
	pos = kbuf;
	new_map.nr_extents = 0;
704
	for (; pos; pos = next_line) {
705 706 707 708 709 710 711 712 713
		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;
714
		}
715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737

		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) ||
738
		    (extent->lower_first == (u32) -1))
739 740
			goto out;

741 742 743
		/* Verify count is not zero and does not cause the
		 * extent to wrap
		 */
744 745
		if ((extent->first + extent->count) <= extent->first)
			goto out;
746 747
		if ((extent->lower_first + extent->count) <=
		     extent->lower_first)
748 749
			goto out;

750 751
		/* Do the ranges in extent overlap any previous extents? */
		if (mappings_overlap(&new_map, extent))
752 753 754 755 756 757 758 759
			goto out;

		new_map.nr_extents++;

		/* Fail if the file contains too many extents */
		if ((new_map.nr_extents == UID_GID_MAP_MAX_EXTENTS) &&
		    (next_line != NULL))
			goto out;
760
	}
761 762 763 764 765 766
	/* 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. */
767
	if (!new_idmap_permitted(file, ns, cap_setid, &new_map))
768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798
		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:
799
	mutex_unlock(&userns_state_mutex);
800
	kfree(kbuf);
801 802 803
	return ret;
}

804 805
ssize_t proc_uid_map_write(struct file *file, const char __user *buf,
			   size_t size, loff_t *ppos)
806 807 808
{
	struct seq_file *seq = file->private_data;
	struct user_namespace *ns = seq->private;
809
	struct user_namespace *seq_ns = seq_user_ns(seq);
810 811 812 813

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

814 815 816
	if ((seq_ns != ns) && (seq_ns != ns->parent))
		return -EPERM;

817 818 819 820
	return map_write(file, buf, size, ppos, CAP_SETUID,
			 &ns->uid_map, &ns->parent->uid_map);
}

821 822
ssize_t proc_gid_map_write(struct file *file, const char __user *buf,
			   size_t size, loff_t *ppos)
823 824 825
{
	struct seq_file *seq = file->private_data;
	struct user_namespace *ns = seq->private;
826
	struct user_namespace *seq_ns = seq_user_ns(seq);
827 828 829 830

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

831 832 833
	if ((seq_ns != ns) && (seq_ns != ns->parent))
		return -EPERM;

834 835 836 837
	return map_write(file, buf, size, ppos, CAP_SETGID,
			 &ns->gid_map, &ns->parent->gid_map);
}

838 839
ssize_t proc_projid_map_write(struct file *file, const char __user *buf,
			      size_t size, loff_t *ppos)
840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855
{
	struct seq_file *seq = file->private_data;
	struct user_namespace *ns = seq->private;
	struct user_namespace *seq_ns = seq_user_ns(seq);

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

	if ((seq_ns != ns) && (seq_ns != ns->parent))
		return -EPERM;

	/* Anyone can set any valid project id no capability needed */
	return map_write(file, buf, size, ppos, -1,
			 &ns->projid_map, &ns->parent->projid_map);
}

856
static bool new_idmap_permitted(const struct file *file,
857
				struct user_namespace *ns, int cap_setid,
858 859
				struct uid_gid_map *new_map)
{
860
	const struct cred *cred = file->f_cred;
861 862 863
	/* Don't allow mappings that would allow anything that wouldn't
	 * be allowed without the establishment of unprivileged mappings.
	 */
864 865
	if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) &&
	    uid_eq(ns->owner, cred->euid)) {
866 867 868
		u32 id = new_map->extent[0].lower_first;
		if (cap_setid == CAP_SETUID) {
			kuid_t uid = make_kuid(ns->parent, id);
869
			if (uid_eq(uid, cred->euid))
870
				return true;
871
		} else if (cap_setid == CAP_SETGID) {
872
			kgid_t gid = make_kgid(ns->parent, id);
873 874
			if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) &&
			    gid_eq(gid, cred->egid))
875 876 877 878
				return true;
		}
	}

879 880 881 882
	/* Allow anyone to set a mapping that doesn't require privilege */
	if (!cap_valid(cap_setid))
		return true;

883 884
	/* Allow the specified ids if we have the appropriate capability
	 * (CAP_SETUID or CAP_SETGID) over the parent user namespace.
885
	 * And the opener of the id file also had the approprpiate capability.
886
	 */
887 888
	if (ns_capable(ns->parent, cap_setid) &&
	    file_ns_capable(file, ns->parent, cap_setid))
889
		return true;
890

891
	return false;
892
}
893

894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971
int proc_setgroups_show(struct seq_file *seq, void *v)
{
	struct user_namespace *ns = seq->private;
	unsigned long userns_flags = ACCESS_ONCE(ns->flags);

	seq_printf(seq, "%s\n",
		   (userns_flags & USERNS_SETGROUPS_ALLOWED) ?
		   "allow" : "deny");
	return 0;
}

ssize_t proc_setgroups_write(struct file *file, const char __user *buf,
			     size_t count, loff_t *ppos)
{
	struct seq_file *seq = file->private_data;
	struct user_namespace *ns = seq->private;
	char kbuf[8], *pos;
	bool setgroups_allowed;
	ssize_t ret;

	/* Only allow a very narrow range of strings to be written */
	ret = -EINVAL;
	if ((*ppos != 0) || (count >= sizeof(kbuf)))
		goto out;

	/* What was written? */
	ret = -EFAULT;
	if (copy_from_user(kbuf, buf, count))
		goto out;
	kbuf[count] = '\0';
	pos = kbuf;

	/* What is being requested? */
	ret = -EINVAL;
	if (strncmp(pos, "allow", 5) == 0) {
		pos += 5;
		setgroups_allowed = true;
	}
	else if (strncmp(pos, "deny", 4) == 0) {
		pos += 4;
		setgroups_allowed = false;
	}
	else
		goto out;

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

	ret = -EPERM;
	mutex_lock(&userns_state_mutex);
	if (setgroups_allowed) {
		/* Enabling setgroups after setgroups has been disabled
		 * is not allowed.
		 */
		if (!(ns->flags & USERNS_SETGROUPS_ALLOWED))
			goto out_unlock;
	} else {
		/* Permanently disabling setgroups after setgroups has
		 * been enabled by writing the gid_map is not allowed.
		 */
		if (ns->gid_map.nr_extents != 0)
			goto out_unlock;
		ns->flags &= ~USERNS_SETGROUPS_ALLOWED;
	}
	mutex_unlock(&userns_state_mutex);

	/* Report a successful write */
	*ppos = count;
	ret = count;
out:
	return ret;
out_unlock:
	mutex_unlock(&userns_state_mutex);
	goto out;
}

972 973 974 975
bool userns_may_setgroups(const struct user_namespace *ns)
{
	bool allowed;

976
	mutex_lock(&userns_state_mutex);
977 978 979 980
	/* It is not safe to use setgroups until a gid mapping in
	 * the user namespace has been established.
	 */
	allowed = ns->gid_map.nr_extents != 0;
981 982
	/* Is setgroups allowed? */
	allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED);
983
	mutex_unlock(&userns_state_mutex);
984 985 986 987

	return allowed;
}

988
/*
989 990
 * Returns true if @child is the same namespace or a descendant of
 * @ancestor.
991
 */
992 993 994 995 996 997 998 999 1000
bool in_userns(const struct user_namespace *ancestor,
	       const struct user_namespace *child)
{
	const struct user_namespace *ns;
	for (ns = child; ns->level > ancestor->level; ns = ns->parent)
		;
	return (ns == ancestor);
}

1001 1002
bool current_in_userns(const struct user_namespace *target_ns)
{
1003
	return in_userns(target_ns, current_user_ns());
1004 1005
}

1006 1007 1008 1009 1010
static inline struct user_namespace *to_user_ns(struct ns_common *ns)
{
	return container_of(ns, struct user_namespace, ns);
}

1011
static struct ns_common *userns_get(struct task_struct *task)
1012 1013 1014 1015 1016 1017 1018
{
	struct user_namespace *user_ns;

	rcu_read_lock();
	user_ns = get_user_ns(__task_cred(task)->user_ns);
	rcu_read_unlock();

1019
	return user_ns ? &user_ns->ns : NULL;
1020 1021
}

1022
static void userns_put(struct ns_common *ns)
1023
{
1024
	put_user_ns(to_user_ns(ns));
1025 1026
}

1027
static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns)
1028
{
1029
	struct user_namespace *user_ns = to_user_ns(ns);
1030 1031 1032 1033 1034 1035 1036 1037
	struct cred *cred;

	/* Don't allow gaining capabilities by reentering
	 * the same user namespace.
	 */
	if (user_ns == current_user_ns())
		return -EINVAL;

1038 1039
	/* Tasks that share a thread group must share a user namespace */
	if (!thread_group_empty(current))
1040 1041
		return -EINVAL;

1042 1043 1044
	if (current->fs->users != 1)
		return -EINVAL;

1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057
	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
		return -EPERM;

	cred = prepare_creds();
	if (!cred)
		return -ENOMEM;

	put_user_ns(cred->user_ns);
	set_cred_user_ns(cred, get_user_ns(user_ns));

	return commit_creds(cred);
}

1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080
struct ns_common *ns_get_owner(struct ns_common *ns)
{
	struct user_namespace *my_user_ns = current_user_ns();
	struct user_namespace *owner, *p;

	/* See if the owner is in the current user namespace */
	owner = p = ns->ops->owner(ns);
	for (;;) {
		if (!p)
			return ERR_PTR(-EPERM);
		if (p == my_user_ns)
			break;
		p = p->parent;
	}

	return &get_user_ns(owner)->ns;
}

static struct user_namespace *userns_owner(struct ns_common *ns)
{
	return to_user_ns(ns)->parent;
}

1081 1082 1083 1084 1085 1086
const struct proc_ns_operations userns_operations = {
	.name		= "user",
	.type		= CLONE_NEWUSER,
	.get		= userns_get,
	.put		= userns_put,
	.install	= userns_install,
1087
	.owner		= userns_owner,
1088
	.get_parent	= ns_get_owner,
1089 1090
};

1091 1092 1093 1094 1095
static __init int user_namespaces_init(void)
{
	user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC);
	return 0;
}
1096
subsys_initcall(user_namespaces_init);