Blame view
kernel/user_namespace.c
25.7 KB
acce292c8
|
1 2 3 4 5 6 |
/* * 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. */ |
9984de1a5
|
7 |
#include <linux/export.h> |
acce292c8
|
8 |
#include <linux/nsproxy.h> |
1aeb272cf
|
9 |
#include <linux/slab.h> |
acce292c8
|
10 |
#include <linux/user_namespace.h> |
0bb80f240
|
11 |
#include <linux/proc_ns.h> |
5c1469de7
|
12 |
#include <linux/highuid.h> |
18b6e0414
|
13 |
#include <linux/cred.h> |
973c59142
|
14 |
#include <linux/securebits.h> |
22d917d80
|
15 16 17 18 19 20 21 |
#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> |
f76d207a6
|
22 |
#include <linux/projid.h> |
e66eded83
|
23 |
#include <linux/fs_struct.h> |
acce292c8
|
24 |
|
6164281ab
|
25 |
static struct kmem_cache *user_ns_cachep __read_mostly; |
f0d62aec9
|
26 |
static DEFINE_MUTEX(userns_state_mutex); |
6164281ab
|
27 |
|
6708075f1
|
28 29 |
static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, |
22d917d80
|
30 |
struct uid_gid_map *map); |
cde1975bc
|
31 32 33 34 35 36 37 38 39 |
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; |
58319057b
|
40 |
cred->cap_ambient = CAP_EMPTY_SET; |
cde1975bc
|
41 42 43 44 45 46 47 48 |
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; } |
77ec739d8
|
49 |
/* |
18b6e0414
|
50 51 52 53 54 55 |
* 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. |
77ec739d8
|
56 |
*/ |
18b6e0414
|
57 |
int create_user_ns(struct cred *new) |
77ec739d8
|
58 |
{ |
0093ccb68
|
59 |
struct user_namespace *ns, *parent_ns = new->user_ns; |
078de5f70
|
60 61 |
kuid_t owner = new->euid; kgid_t group = new->egid; |
98f842e67
|
62 |
int ret; |
783291e69
|
63 |
|
8742f229b
|
64 65 |
if (parent_ns->level > 32) return -EUSERS; |
3151527ee
|
66 67 68 69 70 71 72 73 |
/* * 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. */ if (current_chrooted()) return -EPERM; |
783291e69
|
74 75 76 77 78 79 80 |
/* 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; |
77ec739d8
|
81 |
|
22d917d80
|
82 |
ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL); |
77ec739d8
|
83 |
if (!ns) |
18b6e0414
|
84 |
return -ENOMEM; |
77ec739d8
|
85 |
|
6344c433a
|
86 |
ret = ns_alloc_inum(&ns->ns); |
98f842e67
|
87 88 89 90 |
if (ret) { kmem_cache_free(user_ns_cachep, ns); return ret; } |
33c429405
|
91 |
ns->ns.ops = &userns_operations; |
98f842e67
|
92 |
|
c61a2810a
|
93 |
atomic_set(&ns->count, 1); |
cde1975bc
|
94 |
/* Leave the new->user_ns reference with the new user namespace. */ |
aeb3ae9da
|
95 |
ns->parent = parent_ns; |
8742f229b
|
96 |
ns->level = parent_ns->level + 1; |
783291e69
|
97 98 |
ns->owner = owner; ns->group = group; |
22d917d80
|
99 |
|
9cc46516d
|
100 101 102 103 |
/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ mutex_lock(&userns_state_mutex); ns->flags = parent_ns->flags; mutex_unlock(&userns_state_mutex); |
cde1975bc
|
104 |
set_cred_user_ns(new, ns); |
0093ccb68
|
105 |
|
f36f8c75a
|
106 107 108 |
#ifdef CONFIG_PERSISTENT_KEYRINGS init_rwsem(&ns->persistent_keyring_register_sem); #endif |
18b6e0414
|
109 |
return 0; |
acce292c8
|
110 |
} |
b2e0d9870
|
111 112 113 |
int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { struct cred *cred; |
6160968ce
|
114 |
int err = -ENOMEM; |
b2e0d9870
|
115 116 117 118 119 |
if (!(unshare_flags & CLONE_NEWUSER)) return 0; cred = prepare_creds(); |
6160968ce
|
120 121 122 123 124 125 126 |
if (cred) { err = create_user_ns(cred); if (err) put_cred(cred); else *new_cred = cred; } |
b2e0d9870
|
127 |
|
6160968ce
|
128 |
return err; |
b2e0d9870
|
129 |
} |
c61a2810a
|
130 |
void free_user_ns(struct user_namespace *ns) |
acce292c8
|
131 |
{ |
c61a2810a
|
132 |
struct user_namespace *parent; |
783291e69
|
133 |
|
c61a2810a
|
134 135 |
do { parent = ns->parent; |
f36f8c75a
|
136 137 138 |
#ifdef CONFIG_PERSISTENT_KEYRINGS key_put(ns->persistent_keyring_register); #endif |
6344c433a
|
139 |
ns_free_inum(&ns->ns); |
c61a2810a
|
140 141 142 |
kmem_cache_free(user_ns_cachep, ns); ns = parent; } while (atomic_dec_and_test(&parent->count)); |
acce292c8
|
143 |
} |
6a3fd92e7
|
144 |
EXPORT_SYMBOL(free_user_ns); |
5c1469de7
|
145 |
|
22d917d80
|
146 |
static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) |
5c1469de7
|
147 |
{ |
22d917d80
|
148 149 |
unsigned idx, extents; u32 first, last, id2; |
5c1469de7
|
150 |
|
22d917d80
|
151 |
id2 = id + count - 1; |
5c1469de7
|
152 |
|
22d917d80
|
153 154 |
/* Find the matching extent */ extents = map->nr_extents; |
e79323bd8
|
155 |
smp_rmb(); |
22d917d80
|
156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 |
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; |
e79323bd8
|
179 |
smp_rmb(); |
22d917d80
|
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 |
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; |
e79323bd8
|
202 |
smp_rmb(); |
22d917d80
|
203 204 205 206 207 |
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; |
5c1469de7
|
208 |
} |
22d917d80
|
209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 |
/* 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 |
b080e047a
|
228 |
* for and handle INVALID_UID being returned. INVALID_UID |
22d917d80
|
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 |
* 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 |
68a9a435e
|
289 |
* @gid: group identifier |
22d917d80
|
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 |
* * 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); |
f76d207a6
|
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 |
/** * 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); |
22d917d80
|
419 420 421 422 423 424 |
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; |
5c1469de7
|
425 |
|
c450f371d
|
426 |
lower_ns = seq_user_ns(seq); |
22d917d80
|
427 428 429 430 431 432 433 434 435 436 437 438 |
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 ", extent->first, lower, extent->count); return 0; |
5c1469de7
|
439 |
} |
22d917d80
|
440 |
static int gid_m_show(struct seq_file *seq, void *v) |
5c1469de7
|
441 |
{ |
22d917d80
|
442 443 444 445 |
struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; gid_t lower; |
5c1469de7
|
446 |
|
c450f371d
|
447 |
lower_ns = seq_user_ns(seq); |
22d917d80
|
448 449 |
if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; |
5c1469de7
|
450 |
|
22d917d80
|
451 452 453 454 455 456 457 458 459 460 |
lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u ", extent->first, lower, extent->count); return 0; } |
f76d207a6
|
461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 |
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 ", extent->first, lower, extent->count); return 0; } |
68a9a435e
|
482 483 |
static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map) |
22d917d80
|
484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 |
{ 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); } |
f76d207a6
|
507 508 509 510 511 512 |
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); } |
22d917d80
|
513 514 515 516 517 518 519 520 521 522 |
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; } |
ccf94f1b4
|
523 |
const struct seq_operations proc_uid_seq_operations = { |
22d917d80
|
524 525 526 527 528 |
.start = uid_m_start, .stop = m_stop, .next = m_next, .show = uid_m_show, }; |
ccf94f1b4
|
529 |
const struct seq_operations proc_gid_seq_operations = { |
22d917d80
|
530 531 532 533 534 |
.start = gid_m_start, .stop = m_stop, .next = m_next, .show = gid_m_show, }; |
ccf94f1b4
|
535 |
const struct seq_operations proc_projid_seq_operations = { |
f76d207a6
|
536 537 538 539 540 |
.start = projid_m_start, .stop = m_stop, .next = m_next, .show = projid_m_show, }; |
68a9a435e
|
541 542 |
static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent *extent) |
0bd14b4fd
|
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 |
{ 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; } |
22d917d80
|
576 577 578 579 580 581 582 583 584 585 |
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; |
0bd14b4fd
|
586 |
struct uid_gid_extent *extent = NULL; |
70f6cbb6f
|
587 |
char *kbuf = NULL, *pos, *next_line; |
22d917d80
|
588 589 590 |
ssize_t ret = -EINVAL; /* |
f0d62aec9
|
591 |
* The userns_state_mutex serializes all writes to any given map. |
22d917d80
|
592 593 594 595 596 597 598 599 600 601 602 603 604 605 |
* * 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 |
e79323bd8
|
606 607 |
* order and smp_rmb() is guaranteed that we don't have crazy * architectures returning stale data. |
22d917d80
|
608 |
*/ |
f0d62aec9
|
609 |
mutex_lock(&userns_state_mutex); |
22d917d80
|
610 611 612 613 614 |
ret = -EPERM; /* Only allow one successful write to the map */ if (map->nr_extents != 0) goto out; |
41c21e351
|
615 616 |
/* * Adjusting namespace settings requires capabilities on the target. |
5c1469de7
|
617 |
*/ |
41c21e351
|
618 |
if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN)) |
22d917d80
|
619 |
goto out; |
36476beac
|
620 |
/* Only allow < page size writes at the beginning of the file */ |
22d917d80
|
621 622 623 624 625 |
ret = -EINVAL; if ((*ppos != 0) || (count >= PAGE_SIZE)) goto out; /* Slurp in the user data */ |
70f6cbb6f
|
626 627 628 629 |
kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) { ret = PTR_ERR(kbuf); kbuf = NULL; |
22d917d80
|
630 |
goto out; |
70f6cbb6f
|
631 |
} |
22d917d80
|
632 633 634 635 636 |
/* Parse the user data */ ret = -EINVAL; pos = kbuf; new_map.nr_extents = 0; |
68a9a435e
|
637 |
for (; pos; pos = next_line) { |
22d917d80
|
638 639 640 641 642 643 644 645 646 647 |
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, ' '); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; |
5c1469de7
|
648 |
} |
22d917d80
|
649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 |
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) || |
68a9a435e
|
672 |
(extent->lower_first == (u32) -1)) |
22d917d80
|
673 |
goto out; |
68a9a435e
|
674 675 676 |
/* Verify count is not zero and does not cause the * extent to wrap */ |
22d917d80
|
677 678 |
if ((extent->first + extent->count) <= extent->first) goto out; |
68a9a435e
|
679 680 |
if ((extent->lower_first + extent->count) <= extent->lower_first) |
22d917d80
|
681 |
goto out; |
0bd14b4fd
|
682 683 |
/* Do the ranges in extent overlap any previous extents? */ if (mappings_overlap(&new_map, extent)) |
22d917d80
|
684 685 686 |
goto out; new_map.nr_extents++; |
22d917d80
|
687 688 689 690 691 |
/* Fail if the file contains too many extents */ if ((new_map.nr_extents == UID_GID_MAP_MAX_EXTENTS) && (next_line != NULL)) goto out; |
5c1469de7
|
692 |
} |
22d917d80
|
693 694 695 696 697 698 |
/* 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. */ |
6708075f1
|
699 |
if (!new_idmap_permitted(file, ns, cap_setid, &new_map)) |
22d917d80
|
700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 |
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: |
f0d62aec9
|
731 |
mutex_unlock(&userns_state_mutex); |
70f6cbb6f
|
732 |
kfree(kbuf); |
22d917d80
|
733 734 |
return ret; } |
68a9a435e
|
735 736 |
ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) |
22d917d80
|
737 738 739 |
{ struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; |
c450f371d
|
740 |
struct user_namespace *seq_ns = seq_user_ns(seq); |
22d917d80
|
741 742 743 |
if (!ns->parent) return -EPERM; |
c450f371d
|
744 745 |
if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; |
22d917d80
|
746 747 748 |
return map_write(file, buf, size, ppos, CAP_SETUID, &ns->uid_map, &ns->parent->uid_map); } |
68a9a435e
|
749 750 |
ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) |
22d917d80
|
751 752 753 |
{ struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; |
c450f371d
|
754 |
struct user_namespace *seq_ns = seq_user_ns(seq); |
22d917d80
|
755 756 757 |
if (!ns->parent) return -EPERM; |
c450f371d
|
758 759 |
if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; |
22d917d80
|
760 761 762 |
return map_write(file, buf, size, ppos, CAP_SETGID, &ns->gid_map, &ns->parent->gid_map); } |
68a9a435e
|
763 764 |
ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) |
f76d207a6
|
765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 |
{ 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); } |
68a9a435e
|
780 |
static bool new_idmap_permitted(const struct file *file, |
6708075f1
|
781 |
struct user_namespace *ns, int cap_setid, |
22d917d80
|
782 783 |
struct uid_gid_map *new_map) { |
f95d7918b
|
784 |
const struct cred *cred = file->f_cred; |
0542f17bf
|
785 786 787 |
/* Don't allow mappings that would allow anything that wouldn't * be allowed without the establishment of unprivileged mappings. */ |
f95d7918b
|
788 789 |
if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && uid_eq(ns->owner, cred->euid)) { |
37657da3c
|
790 791 792 |
u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); |
f95d7918b
|
793 |
if (uid_eq(uid, cred->euid)) |
37657da3c
|
794 |
return true; |
68a9a435e
|
795 |
} else if (cap_setid == CAP_SETGID) { |
37657da3c
|
796 |
kgid_t gid = make_kgid(ns->parent, id); |
66d2f338e
|
797 798 |
if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && gid_eq(gid, cred->egid)) |
37657da3c
|
799 800 801 |
return true; } } |
f76d207a6
|
802 803 804 |
/* Allow anyone to set a mapping that doesn't require privilege */ if (!cap_valid(cap_setid)) return true; |
22d917d80
|
805 806 |
/* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. |
6708075f1
|
807 |
* And the opener of the id file also had the approprpiate capability. |
22d917d80
|
808 |
*/ |
6708075f1
|
809 810 |
if (ns_capable(ns->parent, cap_setid) && file_ns_capable(file, ns->parent, cap_setid)) |
22d917d80
|
811 |
return true; |
5c1469de7
|
812 |
|
22d917d80
|
813 |
return false; |
5c1469de7
|
814 |
} |
6164281ab
|
815 |
|
9cc46516d
|
816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 |
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 ", (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; } |
273d2c67c
|
894 895 896 |
bool userns_may_setgroups(const struct user_namespace *ns) { bool allowed; |
f0d62aec9
|
897 |
mutex_lock(&userns_state_mutex); |
273d2c67c
|
898 899 900 901 |
/* 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; |
9cc46516d
|
902 903 |
/* Is setgroups allowed? */ allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); |
f0d62aec9
|
904 |
mutex_unlock(&userns_state_mutex); |
273d2c67c
|
905 906 907 |
return allowed; } |
d07b846f6
|
908 909 910 911 912 913 914 915 916 917 918 919 920 |
/* * Returns true if @ns is the same namespace as or a descendant of * @target_ns. */ bool current_in_userns(const struct user_namespace *target_ns) { struct user_namespace *ns; for (ns = current_user_ns(); ns; ns = ns->parent) { if (ns == target_ns) return true; } return false; } |
3c0411846
|
921 922 923 924 |
static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); } |
64964528b
|
925 |
static struct ns_common *userns_get(struct task_struct *task) |
cde1975bc
|
926 927 928 929 930 931 |
{ struct user_namespace *user_ns; rcu_read_lock(); user_ns = get_user_ns(__task_cred(task)->user_ns); rcu_read_unlock(); |
3c0411846
|
932 |
return user_ns ? &user_ns->ns : NULL; |
cde1975bc
|
933 |
} |
64964528b
|
934 |
static void userns_put(struct ns_common *ns) |
cde1975bc
|
935 |
{ |
3c0411846
|
936 |
put_user_ns(to_user_ns(ns)); |
cde1975bc
|
937 |
} |
64964528b
|
938 |
static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns) |
cde1975bc
|
939 |
{ |
3c0411846
|
940 |
struct user_namespace *user_ns = to_user_ns(ns); |
cde1975bc
|
941 942 943 944 945 946 947 |
struct cred *cred; /* Don't allow gaining capabilities by reentering * the same user namespace. */ if (user_ns == current_user_ns()) return -EINVAL; |
faf00da54
|
948 949 |
/* Tasks that share a thread group must share a user namespace */ if (!thread_group_empty(current)) |
cde1975bc
|
950 |
return -EINVAL; |
e66eded83
|
951 952 |
if (current->fs->users != 1) return -EINVAL; |
cde1975bc
|
953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 |
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); } const struct proc_ns_operations userns_operations = { .name = "user", .type = CLONE_NEWUSER, .get = userns_get, .put = userns_put, .install = userns_install, }; |
6164281ab
|
973 974 975 976 977 |
static __init int user_namespaces_init(void) { user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC); return 0; } |
c96d6660d
|
978 |
subsys_initcall(user_namespaces_init); |