summaryrefslogtreecommitdiffstats
path: root/security/device_cgroup.c
blob: 16c9e1069be6bb23a24116a32b7b658207c2a124 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
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
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
/*
 * device_cgroup.c - device cgroup subsystem
 *
 * 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>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/rcupdate.h>
#include <linux/mutex.h>

#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 */

static DEFINE_MUTEX(devcgroup_mutex);

enum devcg_behavior {
	DEVCG_DEFAULT_NONE,
	DEVCG_DEFAULT_ALLOW,
	DEVCG_DEFAULT_DENY,
};

/*
 * exception list locking rules:
 * hold devcgroup_mutex for update/read.
 * hold rcu_read_lock() for read.
 */

struct dev_exception_item {
	u32 major, minor;
	short type;
	short access;
	struct list_head list;
	struct rcu_head rcu;
};

struct dev_cgroup {
	struct cgroup_subsys_state css;
	struct list_head exceptions;
	enum devcg_behavior behavior;
};

static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s)
{
	return container_of(s, struct dev_cgroup, css);
}

static inline struct dev_cgroup *cgroup_to_devcgroup(struct cgroup *cgroup)
{
	return css_to_devcgroup(cgroup_subsys_state(cgroup, devices_subsys_id));
}

static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
{
	return css_to_devcgroup(task_subsys_state(task, devices_subsys_id));
}

struct cgroup_subsys devices_subsys;

static int devcgroup_can_attach(struct cgroup *new_cgrp,
				struct cgroup_taskset *set)
{
	struct task_struct *task = cgroup_taskset_first(set);

	if (current != task && !capable(CAP_SYS_ADMIN))
		return -EPERM;
	return 0;
}

/*
 * called under devcgroup_mutex
 */
static int dev_exceptions_copy(struct list_head *dest, struct list_head *orig)
{
	struct dev_exception_item *ex, *tmp, *new;

	lockdep_assert_held(&devcgroup_mutex);

	list_for_each_entry(ex, orig, list) {
		new = kmemdup(ex, sizeof(*ex), GFP_KERNEL);
		if (!new)
			goto free_and_exit;
		list_add_tail(&new->list, dest);
	}

	return 0;

free_and_exit:
	list_for_each_entry_safe(ex, tmp, dest, list) {
		list_del(&ex->list);
		kfree(ex);
	}
	return -ENOMEM;
}

/*
 * called under devcgroup_mutex
 */
static int dev_exception_add(struct dev_cgroup *dev_cgroup,
			     struct dev_exception_item *ex)
{
	struct dev_exception_item *excopy, *walk;

	lockdep_assert_held(&devcgroup_mutex);

	excopy = kmemdup(ex, sizeof(*ex), GFP_KERNEL);
	if (!excopy)
		return -ENOMEM;

	list_for_each_entry(walk, &dev_cgroup->exceptions, list) {
		if (walk->type != ex->type)
			continue;
		if (walk->major != ex->major)
			continue;
		if (walk->minor != ex->minor)
			continue;

		walk->access |= ex->access;
		kfree(excopy);
		excopy = NULL;
	}

	if (excopy != NULL)
		list_add_tail_rcu(&excopy->list, &dev_cgroup->exceptions);
	return 0;
}

/*
 * called under devcgroup_mutex
 */
static void dev_exception_rm(struct dev_cgroup *dev_cgroup,
			     struct dev_exception_item *ex)
{
	struct dev_exception_item *walk, *tmp;

	lockdep_assert_held(&devcgroup_mutex);

	list_for_each_entry_safe(walk, tmp, &dev_cgroup->exceptions, list) {
		if (walk->type != ex->type)
			continue;
		if (walk->major != ex->major)
			continue;
		if (walk->minor != ex->minor)
			continue;

		walk->access &= ~ex->access;
		if (!walk->access) {
			list_del_rcu(&walk->list);
			kfree_rcu(walk, rcu);
		}
	}
}

static void __dev_exception_clean(struct dev_cgroup *dev_cgroup)
{
	struct dev_exception_item *ex, *tmp;

	list_for_each_entry_safe(ex, tmp, &dev_cgroup->exceptions, list) {
		list_del_rcu(&ex->list);
		kfree_rcu(ex, rcu);
	}
}

/**
 * dev_exception_clean - frees all entries of the exception list
 * @dev_cgroup: dev_cgroup with the exception list to be cleaned
 *
 * called under devcgroup_mutex
 */
static void dev_exception_clean(struct dev_cgroup *dev_cgroup)
{
	lockdep_assert_held(&devcgroup_mutex);

	__dev_exception_clean(dev_cgroup);
}

/**
 * devcgroup_online - initializes devcgroup's behavior and exceptions based on
 * 		      parent's
 * @cgroup: cgroup getting online
 * returns 0 in case of success, error code otherwise
 */
static int devcgroup_online(struct cgroup *cgroup)
{
	struct dev_cgroup *dev_cgroup, *parent_dev_cgroup = NULL;
	int ret = 0;

	mutex_lock(&devcgroup_mutex);
	dev_cgroup = cgroup_to_devcgroup(cgroup);
	if (cgroup->parent)
		parent_dev_cgroup = cgroup_to_devcgroup(cgroup->parent);

	if (parent_dev_cgroup == NULL)
		dev_cgroup->behavior = DEVCG_DEFAULT_ALLOW;
	else {
		ret = dev_exceptions_copy(&dev_cgroup->exceptions,
					  &parent_dev_cgroup->exceptions);
		if (!ret)
			dev_cgroup->behavior = parent_dev_cgroup->behavior;
	}
	mutex_unlock(&devcgroup_mutex);

	return ret;
}

static void devcgroup_offline(struct cgroup *cgroup)
{
	struct dev_cgroup *dev_cgroup = cgroup_to_devcgroup(cgroup);

	mutex_lock(&devcgroup_mutex);
	dev_cgroup->behavior = DEVCG_DEFAULT_NONE;
	mutex_unlock(&devcgroup_mutex);
}

/*
 * called from kernel/cgroup.c with cgroup_lock() held.
 */
static struct cgroup_subsys_state *devcgroup_css_alloc(struct cgroup *cgroup)
{
	struct dev_cgroup *dev_cgroup;
	struct cgroup *parent_cgroup;

	dev_cgroup = kzalloc(sizeof(*dev_cgroup), GFP_KERNEL);
	if (!dev_cgroup)
		return ERR_PTR(-ENOMEM);
	INIT_LIST_HEAD(&dev_cgroup->exceptions);
	dev_cgroup->behavior = DEVCG_DEFAULT_NONE;
	parent_cgroup = cgroup->parent;

	return &dev_cgroup->css;
}

static void devcgroup_css_free(struct cgroup *cgroup)
{
	struct dev_cgroup *dev_cgroup;

	dev_cgroup = cgroup_to_devcgroup(cgroup);
	__dev_exception_clean(dev_cgroup);
	kfree(dev_cgroup);
}

#define DEVCG_ALLOW 1
#define DEVCG_DENY 2
#define DEVCG_LIST 3

#define MAJMINLEN 13
#define ACCLEN 4

static void set_access(char *acc, short access)
{
	int idx = 0;
	memset(acc, 0, ACCLEN);
	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';
}

static void set_majmin(char *str, unsigned m)
{
	if (m == ~0)
		strcpy(str, "*");
	else
		sprintf(str, "%u", m);
}

static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
				struct seq_file *m)
{
	struct dev_cgroup *devcgroup = cgroup_to_devcgroup(cgroup);
	struct dev_exception_item *ex;
	char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];

	rcu_read_lock();
	/*
	 * To preserve the compatibility:
	 * - Only show the "all devices" when the default policy is to allow
	 * - List the exceptions in case the default policy is to deny
	 * This way, the file remains as a "whitelist of devices"
	 */
	if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
		set_access(acc, ACC_MASK);
		set_majmin(maj, ~0);
		set_majmin(min, ~0);
		seq_printf(m, "%c %s:%s %s\n", type_to_char(DEV_ALL),
			   maj, min, acc);
	} else {
		list_for_each_entry_rcu(ex, &devcgroup->exceptions, list) {
			set_access(acc, ex->access);
			set_majmin(maj, ex->major);
			set_majmin(min, ex->minor);
			seq_printf(m, "%c %s:%s %s\n", type_to_char(ex->type),
				   maj, min, acc);
		}
	}
	rcu_read_unlock();

	return 0;
}

/**
 * may_access - verifies if a new exception is part of what is allowed
 *		by a dev cgroup based on the default policy +
 *		exceptions. This is used to make sure a child cgroup
 *		won't have more privileges than its parent or to
 *		verify if a certain access is allowed.
 * @dev_cgroup: dev cgroup to be tested against
 * @refex: new exception
 * @behavior: behavior of the exception
 */
static bool may_access(struct dev_cgroup *dev_cgroup,
		       struct dev_exception_item *refex,
		       enum devcg_behavior behavior)
{
	struct dev_exception_item *ex;
	bool match = false;

	rcu_lockdep_assert(rcu_read_lock_held() ||
			   lockdep_is_held(&devcgroup_mutex),
			   "device_cgroup::may_access() called without proper synchronization");

	list_for_each_entry_rcu(ex, &dev_cgroup->exceptions, list) {
		if ((refex->type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
			continue;
		if ((refex->type & DEV_CHAR) && !(ex->type & DEV_CHAR))
			continue;
		if (ex->major != ~0 && ex->major != refex->major)
			continue;
		if (ex->minor != ~0 && ex->minor != refex->minor)
			continue;
		if (refex->access & (~ex->access))
			continue;
		match = true;
		break;
	}

	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) {
		if (behavior == DEVCG_DEFAULT_ALLOW) {
			/* the exception will deny access to certain devices */
			return true;
		} else {
			/* the exception will allow access to certain devices */
			if (match)
				/*
				 * a new exception allowing access shouldn't
				 * match an parent's exception
				 */
				return false;
			return true;
		}
	} else {
		/* only behavior == DEVCG_DEFAULT_DENY allowed here */
		if (match)
			/* parent has an exception that matches the proposed */
			return true;
		else
			return false;
	}
	return false;
}

/*
 * parent_has_perm:
 * when adding a new allow rule to a device exception list, the rule
 * must be allowed in the parent device
 */
static int parent_has_perm(struct dev_cgroup *childcg,
				  struct dev_exception_item *ex)
{
	struct cgroup *pcg = childcg->css.cgroup->parent;
	struct dev_cgroup *parent;

	if (!pcg)
		return 1;
	parent = cgroup_to_devcgroup(pcg);
	return may_access(parent, ex, childcg->behavior);
}

/**
 * may_allow_all - checks if it's possible to change the behavior to
 *		   allow based on parent's rules.
 * @parent: device cgroup's parent
 * returns: != 0 in case it's allowed, 0 otherwise
 */
static inline int may_allow_all(struct dev_cgroup *parent)
{
	if (!parent)
		return 1;
	return parent->behavior == DEVCG_DEFAULT_ALLOW;
}

/*
 * Modify the exception list 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 exception list.
 * 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 exception list 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.
 */
static int devcgroup_update_access(struct dev_cgroup *devcgroup,
				   int filetype, const char *buffer)
{
	const char *b;
	char temp[12];		/* 11 + 1 characters needed for a u32 */
	int count, rc = 0;
	struct dev_exception_item ex;
	struct cgroup *p = devcgroup->css.cgroup;
	struct dev_cgroup *parent = NULL;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (p->parent)
		parent = cgroup_to_devcgroup(p->parent);

	memset(&ex, 0, sizeof(ex));
	b = buffer;

	switch (*b) {
	case 'a':
		switch (filetype) {
		case DEVCG_ALLOW:
			if (!may_allow_all(parent))
				return -EPERM;
			dev_exception_clean(devcgroup);
			devcgroup->behavior = DEVCG_DEFAULT_ALLOW;
			if (!parent)
				break;

			rc = dev_exceptions_copy(&devcgroup->exceptions,
						 &parent->exceptions);
			if (rc)
				return rc;
			break;
		case DEVCG_DENY:
			dev_exception_clean(devcgroup);
			devcgroup->behavior = DEVCG_DEFAULT_DENY;
			break;
		default:
			return -EINVAL;
		}
		return 0;
	case 'b':
		ex.type = DEV_BLOCK;
		break;
	case 'c':
		ex.type = DEV_CHAR;
		break;
	default:
		return -EINVAL;
	}
	b++;
	if (!isspace(*b))
		return -EINVAL;
	b++;
	if (*b == '*') {
		ex.major = ~0;
		b++;
	} else if (isdigit(*b)) {
		memset(temp, 0, sizeof(temp));
		for (count = 0; count < sizeof(temp) - 1; count++) {
			temp[count] = *b;
			b++;
			if (!isdigit(*b))
				break;
		}
		rc = kstrtou32(temp, 10, &ex.major);
		if (rc)
			return -EINVAL;
	} else {
		return -EINVAL;
	}
	if (*b != ':')
		return -EINVAL;
	b++;

	/* read minor */
	if (*b == '*') {
		ex.minor = ~0;
		b++;
	} else if (isdigit(*b)) {
		memset(temp, 0, sizeof(temp));
		for (count = 0; count < sizeof(temp) - 1; count++) {
			temp[count] = *b;
			b++;
			if (!isdigit(*b))
				break;
		}
		rc = kstrtou32(temp, 10, &ex.minor);
		if (rc)
			return -EINVAL;
	} else {
		return -EINVAL;
	}
	if (!isspace(*b))
		return -EINVAL;
	for (b++, count = 0; count < 3; count++, b++) {
		switch (*b) {
		case 'r':
			ex.access |= ACC_READ;
			break;
		case 'w':
			ex.access |= ACC_WRITE;
			break;
		case 'm':
			ex.access |= ACC_MKNOD;
			break;
		case '\n':
		case '\0':
			count = 3;
			break;
		default:
			return -EINVAL;
		}
	}

	switch (filetype) {
	case DEVCG_ALLOW:
		if (!parent_has_perm(devcgroup, &ex))
			return -EPERM;
		/*
		 * If the default policy is to allow by default, try to remove
		 * an matching exception instead. And be silent about it: we
		 * don't want to break compatibility
		 */
		if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
			dev_exception_rm(devcgroup, &ex);
			return 0;
		}
		return dev_exception_add(devcgroup, &ex);
	case DEVCG_DENY:
		/*
		 * If the default policy is to deny by default, try to remove
		 * an matching exception instead. And be silent about it: we
		 * don't want to break compatibility
		 */
		if (devcgroup->behavior == DEVCG_DEFAULT_DENY) {
			dev_exception_rm(devcgroup, &ex);
			return 0;
		}
		return dev_exception_add(devcgroup, &ex);
	default:
		return -EINVAL;
	}
	return 0;
}

static int devcgroup_access_write(struct cgroup *cgrp, struct cftype *cft,
				  const char *buffer)
{
	int retval;

	mutex_lock(&devcgroup_mutex);
	retval = devcgroup_update_access(cgroup_to_devcgroup(cgrp),
					 cft->private, buffer);
	mutex_unlock(&devcgroup_mutex);
	return retval;
}

static struct cftype dev_cgroup_files[] = {
	{
		.name = "allow",
		.write_string  = devcgroup_access_write,
		.private = DEVCG_ALLOW,
	},
	{
		.name = "deny",
		.write_string = devcgroup_access_write,
		.private = DEVCG_DENY,
	},
	{
		.name = "list",
		.read_seq_string = devcgroup_seq_read,
		.private = DEVCG_LIST,
	},
	{ }	/* terminate */
};

struct cgroup_subsys devices_subsys = {
	.name = "devices",
	.can_attach = devcgroup_can_attach,
	.css_alloc = devcgroup_css_alloc,
	.css_free = devcgroup_css_free,
	.css_online = devcgroup_online,
	.css_offline = devcgroup_offline,
	.subsys_id = devices_subsys_id,
	.base_cftypes = dev_cgroup_files,

	/*
	 * While devices cgroup has the rudimentary hierarchy support which
	 * checks the parent's restriction, it doesn't properly propagates
	 * config changes in ancestors to their descendents.  A child
	 * should only be allowed to add more restrictions to the parent's
	 * configuration.  Fix it and remove the following.
	 */
	.broken_hierarchy = true,
};

/**
 * __devcgroup_check_permission - checks if an inode operation is permitted
 * @dev_cgroup: the dev cgroup to be tested against
 * @type: device type
 * @major: device major number
 * @minor: device minor number
 * @access: combination of ACC_WRITE, ACC_READ and ACC_MKNOD
 *
 * returns 0 on success, -EPERM case the operation is not permitted
 */
static int __devcgroup_check_permission(short type, u32 major, u32 minor,
				        short access)
{
	struct dev_cgroup *dev_cgroup;
	struct dev_exception_item ex;
	int rc;

	memset(&ex, 0, sizeof(ex));
	ex.type = type;
	ex.major = major;
	ex.minor = minor;
	ex.access = access;

	rcu_read_lock();
	dev_cgroup = task_devcgroup(current);
	rc = may_access(dev_cgroup, &ex, dev_cgroup->behavior);
	rcu_read_unlock();

	if (!rc)
		return -EPERM;

	return 0;
}

int __devcgroup_inode_permission(struct inode *inode, int mask)
{
	short type, access = 0;

	if (S_ISBLK(inode->i_mode))
		type = DEV_BLOCK;
	if (S_ISCHR(inode->i_mode))
		type = DEV_CHAR;
	if (mask & MAY_WRITE)
		access |= ACC_WRITE;
	if (mask & MAY_READ)
		access |= ACC_READ;

	return __devcgroup_check_permission(type, imajor(inode), iminor(inode),
			access);
}

int devcgroup_inode_mknod(int mode, dev_t dev)
{
	short type;

	if (!S_ISBLK(mode) && !S_ISCHR(mode))
		return 0;

	if (S_ISBLK(mode))
		type = DEV_BLOCK;
	else
		type = DEV_CHAR;

	return __devcgroup_check_permission(type, MAJOR(dev), MINOR(dev),
			ACC_MKNOD);

}