]>
Commit | Line | Data |
---|---|---|
08ce5f16 SH |
1 | /* |
2 | * dev_cgroup.c - device cgroup subsystem | |
3 | * | |
4 | * Copyright 2007 IBM Corp | |
5 | */ | |
6 | ||
7 | #include <linux/device_cgroup.h> | |
8 | #include <linux/cgroup.h> | |
9 | #include <linux/ctype.h> | |
10 | #include <linux/list.h> | |
11 | #include <linux/uaccess.h> | |
12 | ||
13 | #define ACC_MKNOD 1 | |
14 | #define ACC_READ 2 | |
15 | #define ACC_WRITE 4 | |
16 | #define ACC_MASK (ACC_MKNOD | ACC_READ | ACC_WRITE) | |
17 | ||
18 | #define DEV_BLOCK 1 | |
19 | #define DEV_CHAR 2 | |
20 | #define DEV_ALL 4 /* this represents all devices */ | |
21 | ||
22 | /* | |
23 | * whitelist locking rules: | |
24 | * cgroup_lock() cannot be taken under dev_cgroup->lock. | |
25 | * dev_cgroup->lock can be taken with or without cgroup_lock(). | |
26 | * | |
27 | * modifications always require cgroup_lock | |
28 | * modifications to a list which is visible require the | |
29 | * dev_cgroup->lock *and* cgroup_lock() | |
30 | * walking the list requires dev_cgroup->lock or cgroup_lock(). | |
31 | * | |
32 | * reasoning: dev_whitelist_copy() needs to kmalloc, so needs | |
33 | * a mutex, which the cgroup_lock() is. Since modifying | |
34 | * a visible list requires both locks, either lock can be | |
35 | * taken for walking the list. | |
36 | */ | |
37 | ||
38 | struct dev_whitelist_item { | |
39 | u32 major, minor; | |
40 | short type; | |
41 | short access; | |
42 | struct list_head list; | |
43 | }; | |
44 | ||
45 | struct dev_cgroup { | |
46 | struct cgroup_subsys_state css; | |
47 | struct list_head whitelist; | |
48 | spinlock_t lock; | |
49 | }; | |
50 | ||
51 | static inline struct dev_cgroup *cgroup_to_devcgroup(struct cgroup *cgroup) | |
52 | { | |
53 | return container_of(cgroup_subsys_state(cgroup, devices_subsys_id), | |
54 | struct dev_cgroup, css); | |
55 | } | |
56 | ||
57 | struct cgroup_subsys devices_subsys; | |
58 | ||
59 | static int devcgroup_can_attach(struct cgroup_subsys *ss, | |
60 | struct cgroup *new_cgroup, struct task_struct *task) | |
61 | { | |
62 | if (current != task && !capable(CAP_SYS_ADMIN)) | |
63 | return -EPERM; | |
64 | ||
65 | return 0; | |
66 | } | |
67 | ||
68 | /* | |
69 | * called under cgroup_lock() | |
70 | */ | |
71 | static int dev_whitelist_copy(struct list_head *dest, struct list_head *orig) | |
72 | { | |
73 | struct dev_whitelist_item *wh, *tmp, *new; | |
74 | ||
75 | list_for_each_entry(wh, orig, list) { | |
76 | new = kmalloc(sizeof(*wh), GFP_KERNEL); | |
77 | if (!new) | |
78 | goto free_and_exit; | |
79 | new->major = wh->major; | |
80 | new->minor = wh->minor; | |
81 | new->type = wh->type; | |
82 | new->access = wh->access; | |
83 | list_add_tail(&new->list, dest); | |
84 | } | |
85 | ||
86 | return 0; | |
87 | ||
88 | free_and_exit: | |
89 | list_for_each_entry_safe(wh, tmp, dest, list) { | |
90 | list_del(&wh->list); | |
91 | kfree(wh); | |
92 | } | |
93 | return -ENOMEM; | |
94 | } | |
95 | ||
96 | /* Stupid prototype - don't bother combining existing entries */ | |
97 | /* | |
98 | * called under cgroup_lock() | |
99 | * since the list is visible to other tasks, we need the spinlock also | |
100 | */ | |
101 | static int dev_whitelist_add(struct dev_cgroup *dev_cgroup, | |
102 | struct dev_whitelist_item *wh) | |
103 | { | |
104 | struct dev_whitelist_item *whcopy; | |
105 | ||
106 | whcopy = kmalloc(sizeof(*whcopy), GFP_KERNEL); | |
107 | if (!whcopy) | |
108 | return -ENOMEM; | |
109 | ||
110 | memcpy(whcopy, wh, sizeof(*whcopy)); | |
111 | spin_lock(&dev_cgroup->lock); | |
112 | list_add_tail(&whcopy->list, &dev_cgroup->whitelist); | |
113 | spin_unlock(&dev_cgroup->lock); | |
114 | return 0; | |
115 | } | |
116 | ||
117 | /* | |
118 | * called under cgroup_lock() | |
119 | * since the list is visible to other tasks, we need the spinlock also | |
120 | */ | |
121 | static void dev_whitelist_rm(struct dev_cgroup *dev_cgroup, | |
122 | struct dev_whitelist_item *wh) | |
123 | { | |
124 | struct dev_whitelist_item *walk, *tmp; | |
125 | ||
126 | spin_lock(&dev_cgroup->lock); | |
127 | list_for_each_entry_safe(walk, tmp, &dev_cgroup->whitelist, list) { | |
128 | if (walk->type == DEV_ALL) | |
129 | goto remove; | |
130 | if (walk->type != wh->type) | |
131 | continue; | |
132 | if (walk->major != ~0 && walk->major != wh->major) | |
133 | continue; | |
134 | if (walk->minor != ~0 && walk->minor != wh->minor) | |
135 | continue; | |
136 | ||
137 | remove: | |
138 | walk->access &= ~wh->access; | |
139 | if (!walk->access) { | |
140 | list_del(&walk->list); | |
141 | kfree(walk); | |
142 | } | |
143 | } | |
144 | spin_unlock(&dev_cgroup->lock); | |
145 | } | |
146 | ||
147 | /* | |
148 | * called from kernel/cgroup.c with cgroup_lock() held. | |
149 | */ | |
150 | static struct cgroup_subsys_state *devcgroup_create(struct cgroup_subsys *ss, | |
151 | struct cgroup *cgroup) | |
152 | { | |
153 | struct dev_cgroup *dev_cgroup, *parent_dev_cgroup; | |
154 | struct cgroup *parent_cgroup; | |
155 | int ret; | |
156 | ||
157 | dev_cgroup = kzalloc(sizeof(*dev_cgroup), GFP_KERNEL); | |
158 | if (!dev_cgroup) | |
159 | return ERR_PTR(-ENOMEM); | |
160 | INIT_LIST_HEAD(&dev_cgroup->whitelist); | |
161 | parent_cgroup = cgroup->parent; | |
162 | ||
163 | if (parent_cgroup == NULL) { | |
164 | struct dev_whitelist_item *wh; | |
165 | wh = kmalloc(sizeof(*wh), GFP_KERNEL); | |
166 | if (!wh) { | |
167 | kfree(dev_cgroup); | |
168 | return ERR_PTR(-ENOMEM); | |
169 | } | |
170 | wh->minor = wh->major = ~0; | |
171 | wh->type = DEV_ALL; | |
172 | wh->access = ACC_MKNOD | ACC_READ | ACC_WRITE; | |
173 | list_add(&wh->list, &dev_cgroup->whitelist); | |
174 | } else { | |
175 | parent_dev_cgroup = cgroup_to_devcgroup(parent_cgroup); | |
176 | ret = dev_whitelist_copy(&dev_cgroup->whitelist, | |
177 | &parent_dev_cgroup->whitelist); | |
178 | if (ret) { | |
179 | kfree(dev_cgroup); | |
180 | return ERR_PTR(ret); | |
181 | } | |
182 | } | |
183 | ||
184 | spin_lock_init(&dev_cgroup->lock); | |
185 | return &dev_cgroup->css; | |
186 | } | |
187 | ||
188 | static void devcgroup_destroy(struct cgroup_subsys *ss, | |
189 | struct cgroup *cgroup) | |
190 | { | |
191 | struct dev_cgroup *dev_cgroup; | |
192 | struct dev_whitelist_item *wh, *tmp; | |
193 | ||
194 | dev_cgroup = cgroup_to_devcgroup(cgroup); | |
195 | list_for_each_entry_safe(wh, tmp, &dev_cgroup->whitelist, list) { | |
196 | list_del(&wh->list); | |
197 | kfree(wh); | |
198 | } | |
199 | kfree(dev_cgroup); | |
200 | } | |
201 | ||
202 | #define DEVCG_ALLOW 1 | |
203 | #define DEVCG_DENY 2 | |
204 | ||
205 | static void set_access(char *acc, short access) | |
206 | { | |
207 | int idx = 0; | |
208 | memset(acc, 0, 4); | |
209 | if (access & ACC_READ) | |
210 | acc[idx++] = 'r'; | |
211 | if (access & ACC_WRITE) | |
212 | acc[idx++] = 'w'; | |
213 | if (access & ACC_MKNOD) | |
214 | acc[idx++] = 'm'; | |
215 | } | |
216 | ||
217 | static char type_to_char(short type) | |
218 | { | |
219 | if (type == DEV_ALL) | |
220 | return 'a'; | |
221 | if (type == DEV_CHAR) | |
222 | return 'c'; | |
223 | if (type == DEV_BLOCK) | |
224 | return 'b'; | |
225 | return 'X'; | |
226 | } | |
227 | ||
228 | static void set_majmin(char *str, int len, unsigned m) | |
229 | { | |
230 | memset(str, 0, len); | |
231 | if (m == ~0) | |
232 | sprintf(str, "*"); | |
233 | else | |
234 | snprintf(str, len, "%d", m); | |
235 | } | |
236 | ||
237 | static char *print_whitelist(struct dev_cgroup *devcgroup, int *len) | |
238 | { | |
239 | char *buf, *s, acc[4]; | |
240 | struct dev_whitelist_item *wh; | |
241 | int ret; | |
242 | int count = 0; | |
243 | char maj[10], min[10]; | |
244 | ||
245 | buf = kmalloc(4096, GFP_KERNEL); | |
246 | if (!buf) | |
247 | return ERR_PTR(-ENOMEM); | |
248 | s = buf; | |
249 | *s = '\0'; | |
250 | *len = 0; | |
251 | ||
252 | spin_lock(&devcgroup->lock); | |
253 | list_for_each_entry(wh, &devcgroup->whitelist, list) { | |
254 | set_access(acc, wh->access); | |
255 | set_majmin(maj, 10, wh->major); | |
256 | set_majmin(min, 10, wh->minor); | |
257 | ret = snprintf(s, 4095-(s-buf), "%c %s:%s %s\n", | |
258 | type_to_char(wh->type), maj, min, acc); | |
259 | if (s+ret >= buf+4095) { | |
260 | kfree(buf); | |
261 | buf = ERR_PTR(-ENOMEM); | |
262 | break; | |
263 | } | |
264 | s += ret; | |
265 | *len += ret; | |
266 | count++; | |
267 | } | |
268 | spin_unlock(&devcgroup->lock); | |
269 | ||
270 | return buf; | |
271 | } | |
272 | ||
273 | static ssize_t devcgroup_access_read(struct cgroup *cgroup, | |
274 | struct cftype *cft, struct file *file, | |
275 | char __user *userbuf, size_t nbytes, loff_t *ppos) | |
276 | { | |
277 | struct dev_cgroup *devcgroup = cgroup_to_devcgroup(cgroup); | |
278 | int filetype = cft->private; | |
279 | char *buffer; | |
280 | int uninitialized_var(len); | |
281 | int retval; | |
282 | ||
283 | if (filetype != DEVCG_ALLOW) | |
284 | return -EINVAL; | |
285 | buffer = print_whitelist(devcgroup, &len); | |
286 | if (IS_ERR(buffer)) | |
287 | return PTR_ERR(buffer); | |
288 | ||
289 | retval = simple_read_from_buffer(userbuf, nbytes, ppos, buffer, len); | |
290 | kfree(buffer); | |
291 | return retval; | |
292 | } | |
293 | ||
294 | /* | |
295 | * may_access_whitelist: | |
296 | * does the access granted to dev_cgroup c contain the access | |
297 | * requested in whitelist item refwh. | |
298 | * return 1 if yes, 0 if no. | |
299 | * call with c->lock held | |
300 | */ | |
301 | static int may_access_whitelist(struct dev_cgroup *c, | |
302 | struct dev_whitelist_item *refwh) | |
303 | { | |
304 | struct dev_whitelist_item *whitem; | |
305 | ||
306 | list_for_each_entry(whitem, &c->whitelist, list) { | |
307 | if (whitem->type & DEV_ALL) | |
308 | return 1; | |
309 | if ((refwh->type & DEV_BLOCK) && !(whitem->type & DEV_BLOCK)) | |
310 | continue; | |
311 | if ((refwh->type & DEV_CHAR) && !(whitem->type & DEV_CHAR)) | |
312 | continue; | |
313 | if (whitem->major != ~0 && whitem->major != refwh->major) | |
314 | continue; | |
315 | if (whitem->minor != ~0 && whitem->minor != refwh->minor) | |
316 | continue; | |
317 | if (refwh->access & (~(whitem->access | ACC_MASK))) | |
318 | continue; | |
319 | return 1; | |
320 | } | |
321 | return 0; | |
322 | } | |
323 | ||
324 | /* | |
325 | * parent_has_perm: | |
326 | * when adding a new allow rule to a device whitelist, the rule | |
327 | * must be allowed in the parent device | |
328 | */ | |
329 | static int parent_has_perm(struct cgroup *childcg, | |
330 | struct dev_whitelist_item *wh) | |
331 | { | |
332 | struct cgroup *pcg = childcg->parent; | |
333 | struct dev_cgroup *parent; | |
334 | int ret; | |
335 | ||
336 | if (!pcg) | |
337 | return 1; | |
338 | parent = cgroup_to_devcgroup(pcg); | |
339 | spin_lock(&parent->lock); | |
340 | ret = may_access_whitelist(parent, wh); | |
341 | spin_unlock(&parent->lock); | |
342 | return ret; | |
343 | } | |
344 | ||
345 | /* | |
346 | * Modify the whitelist using allow/deny rules. | |
347 | * CAP_SYS_ADMIN is needed for this. It's at least separate from CAP_MKNOD | |
348 | * so we can give a container CAP_MKNOD to let it create devices but not | |
349 | * modify the whitelist. | |
350 | * It seems likely we'll want to add a CAP_CONTAINER capability to allow | |
351 | * us to also grant CAP_SYS_ADMIN to containers without giving away the | |
352 | * device whitelist controls, but for now we'll stick with CAP_SYS_ADMIN | |
353 | * | |
354 | * Taking rules away is always allowed (given CAP_SYS_ADMIN). Granting | |
355 | * new access is only allowed if you're in the top-level cgroup, or your | |
356 | * parent cgroup has the access you're asking for. | |
357 | */ | |
358 | static ssize_t devcgroup_access_write(struct cgroup *cgroup, struct cftype *cft, | |
359 | struct file *file, const char __user *userbuf, | |
360 | size_t nbytes, loff_t *ppos) | |
361 | { | |
362 | struct cgroup *cur_cgroup; | |
363 | struct dev_cgroup *devcgroup, *cur_devcgroup; | |
364 | int filetype = cft->private; | |
365 | char *buffer, *b; | |
366 | int retval = 0, count; | |
367 | struct dev_whitelist_item wh; | |
368 | ||
369 | if (!capable(CAP_SYS_ADMIN)) | |
370 | return -EPERM; | |
371 | ||
372 | devcgroup = cgroup_to_devcgroup(cgroup); | |
373 | cur_cgroup = task_cgroup(current, devices_subsys.subsys_id); | |
374 | cur_devcgroup = cgroup_to_devcgroup(cur_cgroup); | |
375 | ||
376 | buffer = kmalloc(nbytes+1, GFP_KERNEL); | |
377 | if (!buffer) | |
378 | return -ENOMEM; | |
379 | ||
380 | if (copy_from_user(buffer, userbuf, nbytes)) { | |
381 | retval = -EFAULT; | |
382 | goto out1; | |
383 | } | |
384 | buffer[nbytes] = 0; /* nul-terminate */ | |
385 | ||
386 | cgroup_lock(); | |
387 | if (cgroup_is_removed(cgroup)) { | |
388 | retval = -ENODEV; | |
389 | goto out2; | |
390 | } | |
391 | ||
392 | memset(&wh, 0, sizeof(wh)); | |
393 | b = buffer; | |
394 | ||
395 | switch (*b) { | |
396 | case 'a': | |
397 | wh.type = DEV_ALL; | |
398 | wh.access = ACC_MASK; | |
399 | goto handle; | |
400 | case 'b': | |
401 | wh.type = DEV_BLOCK; | |
402 | break; | |
403 | case 'c': | |
404 | wh.type = DEV_CHAR; | |
405 | break; | |
406 | default: | |
407 | retval = -EINVAL; | |
408 | goto out2; | |
409 | } | |
410 | b++; | |
411 | if (!isspace(*b)) { | |
412 | retval = -EINVAL; | |
413 | goto out2; | |
414 | } | |
415 | b++; | |
416 | if (*b == '*') { | |
417 | wh.major = ~0; | |
418 | b++; | |
419 | } else if (isdigit(*b)) { | |
420 | wh.major = 0; | |
421 | while (isdigit(*b)) { | |
422 | wh.major = wh.major*10+(*b-'0'); | |
423 | b++; | |
424 | } | |
425 | } else { | |
426 | retval = -EINVAL; | |
427 | goto out2; | |
428 | } | |
429 | if (*b != ':') { | |
430 | retval = -EINVAL; | |
431 | goto out2; | |
432 | } | |
433 | b++; | |
434 | ||
435 | /* read minor */ | |
436 | if (*b == '*') { | |
437 | wh.minor = ~0; | |
438 | b++; | |
439 | } else if (isdigit(*b)) { | |
440 | wh.minor = 0; | |
441 | while (isdigit(*b)) { | |
442 | wh.minor = wh.minor*10+(*b-'0'); | |
443 | b++; | |
444 | } | |
445 | } else { | |
446 | retval = -EINVAL; | |
447 | goto out2; | |
448 | } | |
449 | if (!isspace(*b)) { | |
450 | retval = -EINVAL; | |
451 | goto out2; | |
452 | } | |
453 | for (b++, count = 0; count < 3; count++, b++) { | |
454 | switch (*b) { | |
455 | case 'r': | |
456 | wh.access |= ACC_READ; | |
457 | break; | |
458 | case 'w': | |
459 | wh.access |= ACC_WRITE; | |
460 | break; | |
461 | case 'm': | |
462 | wh.access |= ACC_MKNOD; | |
463 | break; | |
464 | case '\n': | |
465 | case '\0': | |
466 | count = 3; | |
467 | break; | |
468 | default: | |
469 | retval = -EINVAL; | |
470 | goto out2; | |
471 | } | |
472 | } | |
473 | ||
474 | handle: | |
475 | retval = 0; | |
476 | switch (filetype) { | |
477 | case DEVCG_ALLOW: | |
478 | if (!parent_has_perm(cgroup, &wh)) | |
479 | retval = -EPERM; | |
480 | else | |
481 | retval = dev_whitelist_add(devcgroup, &wh); | |
482 | break; | |
483 | case DEVCG_DENY: | |
484 | dev_whitelist_rm(devcgroup, &wh); | |
485 | break; | |
486 | default: | |
487 | retval = -EINVAL; | |
488 | goto out2; | |
489 | } | |
490 | ||
491 | if (retval == 0) | |
492 | retval = nbytes; | |
493 | ||
494 | out2: | |
495 | cgroup_unlock(); | |
496 | out1: | |
497 | kfree(buffer); | |
498 | return retval; | |
499 | } | |
500 | ||
501 | static struct cftype dev_cgroup_files[] = { | |
502 | { | |
503 | .name = "allow", | |
504 | .read = devcgroup_access_read, | |
505 | .write = devcgroup_access_write, | |
506 | .private = DEVCG_ALLOW, | |
507 | }, | |
508 | { | |
509 | .name = "deny", | |
510 | .write = devcgroup_access_write, | |
511 | .private = DEVCG_DENY, | |
512 | }, | |
513 | }; | |
514 | ||
515 | static int devcgroup_populate(struct cgroup_subsys *ss, | |
516 | struct cgroup *cgroup) | |
517 | { | |
518 | return cgroup_add_files(cgroup, ss, dev_cgroup_files, | |
519 | ARRAY_SIZE(dev_cgroup_files)); | |
520 | } | |
521 | ||
522 | struct cgroup_subsys devices_subsys = { | |
523 | .name = "devices", | |
524 | .can_attach = devcgroup_can_attach, | |
525 | .create = devcgroup_create, | |
526 | .destroy = devcgroup_destroy, | |
527 | .populate = devcgroup_populate, | |
528 | .subsys_id = devices_subsys_id, | |
529 | }; | |
530 | ||
531 | int devcgroup_inode_permission(struct inode *inode, int mask) | |
532 | { | |
533 | struct cgroup *cgroup; | |
534 | struct dev_cgroup *dev_cgroup; | |
535 | struct dev_whitelist_item *wh; | |
536 | ||
537 | dev_t device = inode->i_rdev; | |
538 | if (!device) | |
539 | return 0; | |
540 | if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode)) | |
541 | return 0; | |
542 | cgroup = task_cgroup(current, devices_subsys.subsys_id); | |
543 | dev_cgroup = cgroup_to_devcgroup(cgroup); | |
544 | if (!dev_cgroup) | |
545 | return 0; | |
546 | ||
547 | spin_lock(&dev_cgroup->lock); | |
548 | list_for_each_entry(wh, &dev_cgroup->whitelist, list) { | |
549 | if (wh->type & DEV_ALL) | |
550 | goto acc_check; | |
551 | if ((wh->type & DEV_BLOCK) && !S_ISBLK(inode->i_mode)) | |
552 | continue; | |
553 | if ((wh->type & DEV_CHAR) && !S_ISCHR(inode->i_mode)) | |
554 | continue; | |
555 | if (wh->major != ~0 && wh->major != imajor(inode)) | |
556 | continue; | |
557 | if (wh->minor != ~0 && wh->minor != iminor(inode)) | |
558 | continue; | |
559 | acc_check: | |
560 | if ((mask & MAY_WRITE) && !(wh->access & ACC_WRITE)) | |
561 | continue; | |
562 | if ((mask & MAY_READ) && !(wh->access & ACC_READ)) | |
563 | continue; | |
564 | spin_unlock(&dev_cgroup->lock); | |
565 | return 0; | |
566 | } | |
567 | spin_unlock(&dev_cgroup->lock); | |
568 | ||
569 | return -EPERM; | |
570 | } | |
571 | ||
572 | int devcgroup_inode_mknod(int mode, dev_t dev) | |
573 | { | |
574 | struct cgroup *cgroup; | |
575 | struct dev_cgroup *dev_cgroup; | |
576 | struct dev_whitelist_item *wh; | |
577 | ||
578 | cgroup = task_cgroup(current, devices_subsys.subsys_id); | |
579 | dev_cgroup = cgroup_to_devcgroup(cgroup); | |
580 | if (!dev_cgroup) | |
581 | return 0; | |
582 | ||
583 | spin_lock(&dev_cgroup->lock); | |
584 | list_for_each_entry(wh, &dev_cgroup->whitelist, list) { | |
585 | if (wh->type & DEV_ALL) | |
586 | goto acc_check; | |
587 | if ((wh->type & DEV_BLOCK) && !S_ISBLK(mode)) | |
588 | continue; | |
589 | if ((wh->type & DEV_CHAR) && !S_ISCHR(mode)) | |
590 | continue; | |
591 | if (wh->major != ~0 && wh->major != MAJOR(dev)) | |
592 | continue; | |
593 | if (wh->minor != ~0 && wh->minor != MINOR(dev)) | |
594 | continue; | |
595 | acc_check: | |
596 | if (!(wh->access & ACC_MKNOD)) | |
597 | continue; | |
598 | spin_unlock(&dev_cgroup->lock); | |
599 | return 0; | |
600 | } | |
601 | spin_unlock(&dev_cgroup->lock); | |
602 | return -EPERM; | |
603 | } |