Blame view
security/device_cgroup.c
11.6 KB
08ce5f16e
|
1 |
/* |
47c59803b
|
2 |
* device_cgroup.c - device cgroup subsystem |
08ce5f16e
|
3 4 5 6 7 8 9 10 11 |
* * Copyright 2007 IBM Corp */ #include <linux/device_cgroup.h> #include <linux/cgroup.h> #include <linux/ctype.h> #include <linux/list.h> #include <linux/uaccess.h> |
29486df32
|
12 |
#include <linux/seq_file.h> |
47c59803b
|
13 |
#include <linux/rcupdate.h> |
08ce5f16e
|
14 15 16 17 18 19 20 21 22 23 24 25 |
#define ACC_MKNOD 1 #define ACC_READ 2 #define ACC_WRITE 4 #define ACC_MASK (ACC_MKNOD | ACC_READ | ACC_WRITE) #define DEV_BLOCK 1 #define DEV_CHAR 2 #define DEV_ALL 4 /* this represents all devices */ /* * whitelist locking rules: |
47c59803b
|
26 27 |
* hold cgroup_lock() for update/read. * hold rcu_read_lock() for read. |
08ce5f16e
|
28 29 30 31 32 33 34 |
*/ struct dev_whitelist_item { u32 major, minor; short type; short access; struct list_head list; |
4efd1a1b2
|
35 |
struct rcu_head rcu; |
08ce5f16e
|
36 37 38 39 40 |
}; struct dev_cgroup { struct cgroup_subsys_state css; struct list_head whitelist; |
08ce5f16e
|
41 |
}; |
b66862f76
|
42 43 44 45 |
static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s) { return container_of(s, struct dev_cgroup, css); } |
08ce5f16e
|
46 47 |
static inline struct dev_cgroup *cgroup_to_devcgroup(struct cgroup *cgroup) { |
b66862f76
|
48 |
return css_to_devcgroup(cgroup_subsys_state(cgroup, devices_subsys_id)); |
08ce5f16e
|
49 |
} |
f92523e3a
|
50 51 52 53 |
static inline struct dev_cgroup *task_devcgroup(struct task_struct *task) { return css_to_devcgroup(task_subsys_state(task, devices_subsys_id)); } |
08ce5f16e
|
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
struct cgroup_subsys devices_subsys; static int devcgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup, struct task_struct *task) { if (current != task && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * called under cgroup_lock() */ static int dev_whitelist_copy(struct list_head *dest, struct list_head *orig) { struct dev_whitelist_item *wh, *tmp, *new; list_for_each_entry(wh, orig, list) { |
2cdc7241a
|
73 |
new = kmemdup(wh, sizeof(*wh), GFP_KERNEL); |
08ce5f16e
|
74 75 |
if (!new) goto free_and_exit; |
08ce5f16e
|
76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
list_add_tail(&new->list, dest); } return 0; free_and_exit: list_for_each_entry_safe(wh, tmp, dest, list) { list_del(&wh->list); kfree(wh); } return -ENOMEM; } /* Stupid prototype - don't bother combining existing entries */ /* * called under cgroup_lock() |
08ce5f16e
|
92 93 94 95 |
*/ static int dev_whitelist_add(struct dev_cgroup *dev_cgroup, struct dev_whitelist_item *wh) { |
d1ee2971f
|
96 |
struct dev_whitelist_item *whcopy, *walk; |
08ce5f16e
|
97 |
|
2cdc7241a
|
98 |
whcopy = kmemdup(wh, sizeof(*wh), GFP_KERNEL); |
08ce5f16e
|
99 100 |
if (!whcopy) return -ENOMEM; |
d1ee2971f
|
101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
list_for_each_entry(walk, &dev_cgroup->whitelist, list) { if (walk->type != wh->type) continue; if (walk->major != wh->major) continue; if (walk->minor != wh->minor) continue; walk->access |= wh->access; kfree(whcopy); whcopy = NULL; } if (whcopy != NULL) |
4efd1a1b2
|
115 |
list_add_tail_rcu(&whcopy->list, &dev_cgroup->whitelist); |
08ce5f16e
|
116 117 |
return 0; } |
4efd1a1b2
|
118 119 120 121 122 123 124 |
static void whitelist_item_free(struct rcu_head *rcu) { struct dev_whitelist_item *item; item = container_of(rcu, struct dev_whitelist_item, rcu); kfree(item); } |
08ce5f16e
|
125 126 |
/* * called under cgroup_lock() |
08ce5f16e
|
127 128 129 130 131 |
*/ static void dev_whitelist_rm(struct dev_cgroup *dev_cgroup, struct dev_whitelist_item *wh) { struct dev_whitelist_item *walk, *tmp; |
08ce5f16e
|
132 133 134 135 136 137 138 139 140 141 142 143 144 |
list_for_each_entry_safe(walk, tmp, &dev_cgroup->whitelist, list) { if (walk->type == DEV_ALL) goto remove; if (walk->type != wh->type) continue; if (walk->major != ~0 && walk->major != wh->major) continue; if (walk->minor != ~0 && walk->minor != wh->minor) continue; remove: walk->access &= ~wh->access; if (!walk->access) { |
4efd1a1b2
|
145 146 |
list_del_rcu(&walk->list); call_rcu(&walk->rcu, whitelist_item_free); |
08ce5f16e
|
147 148 |
} } |
08ce5f16e
|
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 |
} /* * called from kernel/cgroup.c with cgroup_lock() held. */ static struct cgroup_subsys_state *devcgroup_create(struct cgroup_subsys *ss, struct cgroup *cgroup) { struct dev_cgroup *dev_cgroup, *parent_dev_cgroup; struct cgroup *parent_cgroup; int ret; dev_cgroup = kzalloc(sizeof(*dev_cgroup), GFP_KERNEL); if (!dev_cgroup) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&dev_cgroup->whitelist); parent_cgroup = cgroup->parent; if (parent_cgroup == NULL) { struct dev_whitelist_item *wh; wh = kmalloc(sizeof(*wh), GFP_KERNEL); if (!wh) { kfree(dev_cgroup); return ERR_PTR(-ENOMEM); } wh->minor = wh->major = ~0; wh->type = DEV_ALL; |
7759fc9d1
|
176 |
wh->access = ACC_MASK; |
08ce5f16e
|
177 178 179 180 181 182 183 184 185 186 |
list_add(&wh->list, &dev_cgroup->whitelist); } else { parent_dev_cgroup = cgroup_to_devcgroup(parent_cgroup); ret = dev_whitelist_copy(&dev_cgroup->whitelist, &parent_dev_cgroup->whitelist); if (ret) { kfree(dev_cgroup); return ERR_PTR(ret); } } |
08ce5f16e
|
187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 |
return &dev_cgroup->css; } static void devcgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgroup) { struct dev_cgroup *dev_cgroup; struct dev_whitelist_item *wh, *tmp; dev_cgroup = cgroup_to_devcgroup(cgroup); list_for_each_entry_safe(wh, tmp, &dev_cgroup->whitelist, list) { list_del(&wh->list); kfree(wh); } kfree(dev_cgroup); } #define DEVCG_ALLOW 1 #define DEVCG_DENY 2 |
29486df32
|
206 |
#define DEVCG_LIST 3 |
17d213f80
|
207 |
#define MAJMINLEN 13 |
29486df32
|
208 |
#define ACCLEN 4 |
08ce5f16e
|
209 210 211 212 |
static void set_access(char *acc, short access) { int idx = 0; |
29486df32
|
213 |
memset(acc, 0, ACCLEN); |
08ce5f16e
|
214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 |
if (access & ACC_READ) acc[idx++] = 'r'; if (access & ACC_WRITE) acc[idx++] = 'w'; if (access & ACC_MKNOD) acc[idx++] = 'm'; } static char type_to_char(short type) { if (type == DEV_ALL) return 'a'; if (type == DEV_CHAR) return 'c'; if (type == DEV_BLOCK) return 'b'; return 'X'; } |
29486df32
|
232 |
static void set_majmin(char *str, unsigned m) |
08ce5f16e
|
233 |
{ |
08ce5f16e
|
234 |
if (m == ~0) |
7759fc9d1
|
235 |
strcpy(str, "*"); |
08ce5f16e
|
236 |
else |
7759fc9d1
|
237 |
sprintf(str, "%u", m); |
08ce5f16e
|
238 |
} |
29486df32
|
239 240 |
static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft, struct seq_file *m) |
08ce5f16e
|
241 |
{ |
29486df32
|
242 |
struct dev_cgroup *devcgroup = cgroup_to_devcgroup(cgroup); |
08ce5f16e
|
243 |
struct dev_whitelist_item *wh; |
29486df32
|
244 |
char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN]; |
08ce5f16e
|
245 |
|
4efd1a1b2
|
246 247 |
rcu_read_lock(); list_for_each_entry_rcu(wh, &devcgroup->whitelist, list) { |
08ce5f16e
|
248 |
set_access(acc, wh->access); |
29486df32
|
249 250 251 252 253 |
set_majmin(maj, wh->major); set_majmin(min, wh->minor); seq_printf(m, "%c %s:%s %s ", type_to_char(wh->type), maj, min, acc); |
08ce5f16e
|
254 |
} |
4efd1a1b2
|
255 |
rcu_read_unlock(); |
08ce5f16e
|
256 |
|
29486df32
|
257 |
return 0; |
08ce5f16e
|
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 |
} /* * may_access_whitelist: * does the access granted to dev_cgroup c contain the access * requested in whitelist item refwh. * return 1 if yes, 0 if no. * call with c->lock held */ static int may_access_whitelist(struct dev_cgroup *c, struct dev_whitelist_item *refwh) { struct dev_whitelist_item *whitem; list_for_each_entry(whitem, &c->whitelist, list) { if (whitem->type & DEV_ALL) return 1; if ((refwh->type & DEV_BLOCK) && !(whitem->type & DEV_BLOCK)) continue; if ((refwh->type & DEV_CHAR) && !(whitem->type & DEV_CHAR)) continue; if (whitem->major != ~0 && whitem->major != refwh->major) continue; if (whitem->minor != ~0 && whitem->minor != refwh->minor) continue; |
ec229e830
|
283 |
if (refwh->access & (~whitem->access)) |
08ce5f16e
|
284 285 286 287 288 289 290 291 292 293 294 |
continue; return 1; } return 0; } /* * parent_has_perm: * when adding a new allow rule to a device whitelist, the rule * must be allowed in the parent device */ |
f92523e3a
|
295 |
static int parent_has_perm(struct dev_cgroup *childcg, |
08ce5f16e
|
296 297 |
struct dev_whitelist_item *wh) { |
f92523e3a
|
298 |
struct cgroup *pcg = childcg->css.cgroup->parent; |
08ce5f16e
|
299 |
struct dev_cgroup *parent; |
08ce5f16e
|
300 301 302 303 |
if (!pcg) return 1; parent = cgroup_to_devcgroup(pcg); |
47c59803b
|
304 |
return may_access_whitelist(parent, wh); |
08ce5f16e
|
305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 |
} /* * Modify the whitelist using allow/deny rules. * CAP_SYS_ADMIN is needed for this. It's at least separate from CAP_MKNOD * so we can give a container CAP_MKNOD to let it create devices but not * modify the whitelist. * It seems likely we'll want to add a CAP_CONTAINER capability to allow * us to also grant CAP_SYS_ADMIN to containers without giving away the * device whitelist controls, but for now we'll stick with CAP_SYS_ADMIN * * Taking rules away is always allowed (given CAP_SYS_ADMIN). Granting * new access is only allowed if you're in the top-level cgroup, or your * parent cgroup has the access you're asking for. */ |
f92523e3a
|
320 321 |
static int devcgroup_update_access(struct dev_cgroup *devcgroup, int filetype, const char *buffer) |
08ce5f16e
|
322 |
{ |
f92523e3a
|
323 |
const char *b; |
7759fc9d1
|
324 |
char *endp; |
c012a54ae
|
325 |
int count; |
08ce5f16e
|
326 327 328 329 |
struct dev_whitelist_item wh; if (!capable(CAP_SYS_ADMIN)) return -EPERM; |
08ce5f16e
|
330 331 332 333 334 335 336 |
memset(&wh, 0, sizeof(wh)); b = buffer; switch (*b) { case 'a': wh.type = DEV_ALL; wh.access = ACC_MASK; |
d823f6bfe
|
337 338 |
wh.major = ~0; wh.minor = ~0; |
08ce5f16e
|
339 340 341 342 343 344 345 346 |
goto handle; case 'b': wh.type = DEV_BLOCK; break; case 'c': wh.type = DEV_CHAR; break; default: |
f92523e3a
|
347 |
return -EINVAL; |
08ce5f16e
|
348 349 |
} b++; |
f92523e3a
|
350 351 |
if (!isspace(*b)) return -EINVAL; |
08ce5f16e
|
352 353 354 355 356 |
b++; if (*b == '*') { wh.major = ~0; b++; } else if (isdigit(*b)) { |
7759fc9d1
|
357 358 |
wh.major = simple_strtoul(b, &endp, 10); b = endp; |
08ce5f16e
|
359 |
} else { |
f92523e3a
|
360 |
return -EINVAL; |
08ce5f16e
|
361 |
} |
f92523e3a
|
362 363 |
if (*b != ':') return -EINVAL; |
08ce5f16e
|
364 365 366 367 368 369 370 |
b++; /* read minor */ if (*b == '*') { wh.minor = ~0; b++; } else if (isdigit(*b)) { |
7759fc9d1
|
371 372 |
wh.minor = simple_strtoul(b, &endp, 10); b = endp; |
08ce5f16e
|
373 |
} else { |
f92523e3a
|
374 |
return -EINVAL; |
08ce5f16e
|
375 |
} |
f92523e3a
|
376 377 |
if (!isspace(*b)) return -EINVAL; |
08ce5f16e
|
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 |
for (b++, count = 0; count < 3; count++, b++) { switch (*b) { case 'r': wh.access |= ACC_READ; break; case 'w': wh.access |= ACC_WRITE; break; case 'm': wh.access |= ACC_MKNOD; break; case ' ': case '\0': count = 3; break; default: |
f92523e3a
|
395 |
return -EINVAL; |
08ce5f16e
|
396 397 398 399 |
} } handle: |
08ce5f16e
|
400 401 |
switch (filetype) { case DEVCG_ALLOW: |
f92523e3a
|
402 403 404 |
if (!parent_has_perm(devcgroup, &wh)) return -EPERM; return dev_whitelist_add(devcgroup, &wh); |
08ce5f16e
|
405 406 407 408 |
case DEVCG_DENY: dev_whitelist_rm(devcgroup, &wh); break; default: |
f92523e3a
|
409 |
return -EINVAL; |
08ce5f16e
|
410 |
} |
f92523e3a
|
411 412 |
return 0; } |
08ce5f16e
|
413 |
|
f92523e3a
|
414 415 416 417 418 419 420 421 |
static int devcgroup_access_write(struct cgroup *cgrp, struct cftype *cft, const char *buffer) { int retval; if (!cgroup_lock_live_group(cgrp)) return -ENODEV; retval = devcgroup_update_access(cgroup_to_devcgroup(cgrp), cft->private, buffer); |
08ce5f16e
|
422 |
cgroup_unlock(); |
08ce5f16e
|
423 424 425 426 427 428 |
return retval; } static struct cftype dev_cgroup_files[] = { { .name = "allow", |
f92523e3a
|
429 |
.write_string = devcgroup_access_write, |
08ce5f16e
|
430 431 432 433 |
.private = DEVCG_ALLOW, }, { .name = "deny", |
f92523e3a
|
434 |
.write_string = devcgroup_access_write, |
08ce5f16e
|
435 436 |
.private = DEVCG_DENY, }, |
29486df32
|
437 438 439 440 441 |
{ .name = "list", .read_seq_string = devcgroup_seq_read, .private = DEVCG_LIST, }, |
08ce5f16e
|
442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 |
}; static int devcgroup_populate(struct cgroup_subsys *ss, struct cgroup *cgroup) { return cgroup_add_files(cgroup, ss, dev_cgroup_files, ARRAY_SIZE(dev_cgroup_files)); } struct cgroup_subsys devices_subsys = { .name = "devices", .can_attach = devcgroup_can_attach, .create = devcgroup_create, .destroy = devcgroup_destroy, .populate = devcgroup_populate, .subsys_id = devices_subsys_id, }; int devcgroup_inode_permission(struct inode *inode, int mask) { |
08ce5f16e
|
462 463 464 465 466 467 468 469 |
struct dev_cgroup *dev_cgroup; struct dev_whitelist_item *wh; dev_t device = inode->i_rdev; if (!device) return 0; if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode)) return 0; |
08ce5f16e
|
470 |
|
4efd1a1b2
|
471 |
rcu_read_lock(); |
36fd71d29
|
472 473 |
dev_cgroup = task_devcgroup(current); |
4efd1a1b2
|
474 |
list_for_each_entry_rcu(wh, &dev_cgroup->whitelist, list) { |
08ce5f16e
|
475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 |
if (wh->type & DEV_ALL) goto acc_check; if ((wh->type & DEV_BLOCK) && !S_ISBLK(inode->i_mode)) continue; if ((wh->type & DEV_CHAR) && !S_ISCHR(inode->i_mode)) continue; if (wh->major != ~0 && wh->major != imajor(inode)) continue; if (wh->minor != ~0 && wh->minor != iminor(inode)) continue; acc_check: if ((mask & MAY_WRITE) && !(wh->access & ACC_WRITE)) continue; if ((mask & MAY_READ) && !(wh->access & ACC_READ)) continue; |
4efd1a1b2
|
490 |
rcu_read_unlock(); |
08ce5f16e
|
491 492 |
return 0; } |
36fd71d29
|
493 |
|
4efd1a1b2
|
494 |
rcu_read_unlock(); |
08ce5f16e
|
495 496 497 498 499 500 |
return -EPERM; } int devcgroup_inode_mknod(int mode, dev_t dev) { |
08ce5f16e
|
501 502 |
struct dev_cgroup *dev_cgroup; struct dev_whitelist_item *wh; |
0b82ac37b
|
503 504 |
if (!S_ISBLK(mode) && !S_ISCHR(mode)) return 0; |
4efd1a1b2
|
505 |
rcu_read_lock(); |
36fd71d29
|
506 507 |
dev_cgroup = task_devcgroup(current); |
116e05751
|
508 |
list_for_each_entry_rcu(wh, &dev_cgroup->whitelist, list) { |
08ce5f16e
|
509 510 511 512 513 514 515 516 517 518 519 520 521 |
if (wh->type & DEV_ALL) goto acc_check; if ((wh->type & DEV_BLOCK) && !S_ISBLK(mode)) continue; if ((wh->type & DEV_CHAR) && !S_ISCHR(mode)) continue; if (wh->major != ~0 && wh->major != MAJOR(dev)) continue; if (wh->minor != ~0 && wh->minor != MINOR(dev)) continue; acc_check: if (!(wh->access & ACC_MKNOD)) continue; |
4efd1a1b2
|
522 |
rcu_read_unlock(); |
08ce5f16e
|
523 524 |
return 0; } |
36fd71d29
|
525 |
|
4efd1a1b2
|
526 |
rcu_read_unlock(); |
36fd71d29
|
527 |
|
08ce5f16e
|
528 529 |
return -EPERM; } |