aboutsummaryrefslogtreecommitdiff
path: root/security/commoncap.c
blob: e8c3f5e467055ce93275ac1c901fda861674e402 (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
/* Common capabilities, needed by capability.o and root_plug.o
 *
 *	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; either version 2 of the License, or
 *	(at your option) any later version.
 *
 */

#include <linux/capability.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/security.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/ptrace.h>
#include <linux/xattr.h>
#include <linux/hugetlb.h>
#include <linux/mount.h>
#include <linux/sched.h>
#include <linux/prctl.h>
#include <linux/securebits.h>

int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
{
	NETLINK_CB(skb).eff_cap = current->cap_effective;
	return 0;
}

int cap_netlink_recv(struct sk_buff *skb, int cap)
{
	if (!cap_raised(NETLINK_CB(skb).eff_cap, cap))
		return -EPERM;
	return 0;
}

EXPORT_SYMBOL(cap_netlink_recv);

/*
 * NOTE WELL: cap_capable() cannot be used like the kernel's capable()
 * function.  That is, it has the reverse semantics: cap_capable()
 * returns 0 when a task has a capability, but the kernel's capable()
 * returns 1 for this case.
 */
int cap_capable (struct task_struct *tsk, int cap)
{
	/* Derived from include/linux/sched.h:capable. */
	if (cap_raised(tsk->cap_effective, cap))
		return 0;
	return -EPERM;
}

int cap_settime(struct timespec *ts, struct timezone *tz)
{
	if (!capable(CAP_SYS_TIME))
		return -EPERM;
	return 0;
}

int cap_ptrace (struct task_struct *parent, struct task_struct *child)
{
	/* Derived from arch/i386/kernel/ptrace.c:sys_ptrace. */
	if (!cap_issubset(child->cap_permitted, parent->cap_permitted) &&
	    !__capable(parent, CAP_SYS_PTRACE))
		return -EPERM;
	return 0;
}

int cap_capget (struct task_struct *target, kernel_cap_t *effective,
		kernel_cap_t *inheritable, kernel_cap_t *permitted)
{
	/* Derived from kernel/capability.c:sys_capget. */
	*effective = target->cap_effective;
	*inheritable = target->cap_inheritable;
	*permitted = target->cap_permitted;
	return 0;
}

#ifdef CONFIG_SECURITY_FILE_CAPABILITIES

static inline int cap_block_setpcap(struct task_struct *target)
{
	/*
	 * No support for remote process capability manipulation with
	 * filesystem capability support.
	 */
	return (target != current);
}

static inline int cap_inh_is_capped(void)
{
	/*
	 * Return 1 if changes to the inheritable set are limited
	 * to the old permitted set. That is, if the current task
	 * does *not* possess the CAP_SETPCAP capability.
	 */
	return (cap_capable(current, CAP_SETPCAP) != 0);
}

#else /* ie., ndef CONFIG_SECURITY_FILE_CAPABILITIES */

static inline int cap_block_setpcap(struct task_struct *t) { return 0; }
static inline int cap_inh_is_capped(void) { return 1; }

#endif /* def CONFIG_SECURITY_FILE_CAPABILITIES */

int cap_capset_check (struct task_struct *target, kernel_cap_t *effective,
		      kernel_cap_t *inheritable, kernel_cap_t *permitted)
{
	if (cap_block_setpcap(target)) {
		return -EPERM;
	}
	if (cap_inh_is_capped()
	    && !cap_issubset(*inheritable,
			     cap_combine(target->cap_inheritable,
					 current->cap_permitted))) {
		/* incapable of using this inheritable set */
		return -EPERM;
	}
	if (!cap_issubset(*inheritable,
			   cap_combine(target->cap_inheritable,
				       current->cap_bset))) {
		/* no new pI capabilities outside bounding set */
		return -EPERM;
	}

	/* verify restrictions on target's new Permitted set */
	if (!cap_issubset (*permitted,
			   cap_combine (target->cap_permitted,
					current->cap_permitted))) {
		return -EPERM;
	}

	/* verify the _new_Effective_ is a subset of the _new_Permitted_ */
	if (!cap_issubset (*effective, *permitted)) {
		return -EPERM;
	}

	return 0;
}

void cap_capset_set (struct task_struct *target, kernel_cap_t *effective,
		     kernel_cap_t *inheritable, kernel_cap_t *permitted)
{
	target->cap_effective = *effective;
	target->cap_inheritable = *inheritable;
	target->cap_permitted = *permitted;
}

static inline void bprm_clear_caps(struct linux_binprm *bprm)
{
	cap_clear(bprm->cap_inheritable);
	cap_clear(bprm->cap_permitted);
	bprm->cap_effective = false;
}

#ifdef CONFIG_SECURITY_FILE_CAPABILITIES

int cap_inode_need_killpriv(struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;
	int error;

	if (!inode->i_op || !inode->i_op->getxattr)
	       return 0;

	error = inode->i_op->getxattr(dentry, XATTR_NAME_CAPS, NULL, 0);
	if (error <= 0)
		return 0;
	return 1;
}

int cap_inode_killpriv(struct dentry *dentry)
{
	struct inode *inode = dentry->d_inode;

	if (!inode->i_op || !inode->i_op->removexattr)
	       return 0;

	return inode->i_op->removexattr(dentry, XATTR_NAME_CAPS);
}

static inline int cap_from_disk(struct vfs_cap_data *caps,
				struct linux_binprm *bprm, unsigned size)
{
	__u32 magic_etc;
	unsigned tocopy, i;

	if (size < sizeof(magic_etc))
		return -EINVAL;

	magic_etc = le32_to_cpu(caps->magic_etc);

	switch ((magic_etc & VFS_CAP_REVISION_MASK)) {
	case VFS_CAP_REVISION_1:
		if (size != XATTR_CAPS_SZ_1)
			return -EINVAL;
		tocopy = VFS_CAP_U32_1;
		break;
	case VFS_CAP_REVISION_2:
		if (size != XATTR_CAPS_SZ_2)
			return -EINVAL;
		tocopy = VFS_CAP_U32_2;
		break;
	default:
		return -EINVAL;
	}

	if (magic_etc & VFS_CAP_FLAGS_EFFECTIVE) {
		bprm->cap_effective = true;
	} else {
		bprm->cap_effective = false;
	}

	for (i = 0; i < tocopy; ++i) {
		bprm->cap_permitted.cap[i] =
			le32_to_cpu(caps->data[i].permitted);
		bprm->cap_inheritable.cap[i] =
			le32_to_cpu(caps->data[i].inheritable);
	}
	while (i < VFS_CAP_U32) {
		bprm->cap_permitted.cap[i] = 0;
		bprm->cap_inheritable.cap[i] = 0;
		i++;
	}

	return 0;
}

/* Locate any VFS capabilities: */
static int get_file_caps(struct linux_binprm *bprm)
{
	struct dentry *dentry;
	int rc = 0;
	struct vfs_cap_data vcaps;
	struct inode *inode;

	if (bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID) {
		bprm_clear_caps(bprm);
		return 0;
	}

	dentry = dget(bprm->file->f_dentry);
	inode = dentry->d_inode;
	if (!inode->i_op || !inode->i_op->getxattr)
		goto out;

	rc = inode->i_op->getxattr(dentry, XATTR_NAME_CAPS, &vcaps,
				   XATTR_CAPS_SZ);
	if (rc == -ENODATA || rc == -EOPNOTSUPP) {
		/* no data, that's ok */
		rc = 0;
		goto out;
	}
	if (rc < 0)
		goto out;

	rc = cap_from_disk(&vcaps, bprm, rc);
	if (rc)
		printk(KERN_NOTICE "%s: cap_from_disk returned %d for %s\n",
			__func__, rc, bprm->filename);

out:
	dput(dentry);
	if (rc)
		bprm_clear_caps(bprm);

	return rc;
}

#else
int cap_inode_need_killpriv(struct dentry *dentry)
{
	return 0;
}

int cap_inode_killpriv(struct dentry *dentry)
{
	return 0;
}

static inline int get_file_caps(struct linux_binprm *bprm)
{
	bprm_clear_caps(bprm);
	return 0;
}
#endif

int cap_bprm_set_security (struct linux_binprm *bprm)
{
	int ret;

	ret = get_file_caps(bprm);
	if (ret)
		printk(KERN_NOTICE "%s: get_file_caps returned %d for %s\n",
			__func__, ret, bprm->filename);

	/*  To support inheritance of root-permissions and suid-root
	 *  executables under compatibility mode, we raise all three
	 *  capability sets for the file.
	 *
	 *  If only the real uid is 0, we only raise the inheritable
	 *  and permitted sets of the executable file.
	 */

	if (!issecure (SECURE_NOROOT)) {
		if (bprm->e_uid == 0 || current->uid == 0) {
			cap_set_full (bprm->cap_inheritable);
			cap_set_full (bprm->cap_permitted);
		}
		if (bprm->e_uid == 0)
			bprm->cap_effective = true;
	}

	return ret;
}

void cap_bprm_apply_creds (struct linux_binprm *bprm, int unsafe)
{
	/* Derived from fs/exec.c:compute_creds. */
	kernel_cap_t new_permitted, working;

	new_permitted = cap_intersect(bprm->cap_permitted,
				 current->cap_bset);
	working = cap_intersect(bprm->cap_inheritable,
				 current->cap_inheritable);
	new_permitted = cap_combine(new_permitted, working);

	if (bprm->e_uid != current->uid || bprm->e_gid != current->gid ||
	    !cap_issubset (new_permitted, current->cap_permitted)) {
		set_dumpable(current->mm, suid_dumpable);
		current->pdeath_signal = 0;

		if (unsafe & ~LSM_UNSAFE_PTRACE_CAP) {
			if (!capable(CAP_SETUID)) {
				bprm->e_uid = current->uid;
				bprm->e_gid = current->gid;
			}
			if (!capable (CAP_SETPCAP)) {
				new_permitted = cap_intersect (new_permitted,
							current->cap_permitted);
			}
		}
	}

	current->suid = current->euid = current->fsuid = bprm->e_uid;
	current->sgid = current->egid = current->fsgid = bprm->e_gid;

	/* For init, we want to retain the capabilities set
	 * in the init_task struct. Thus we skip the usual
	 * capability rules */
	if (!is_global_init(current)) {
		current->cap_permitted = new_permitted;
		if (bprm->cap_effective)
			current->cap_effective = new_permitted;
		else
			cap_clear(current->cap_effective);
	}

	/* AUD: Audit candidate if current->cap_effective is set */

	current->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
}

int cap_bprm_secureexec (struct linux_binprm *bprm)
{
	if (current->uid != 0) {
		if (bprm->cap_effective)
			return 1;
		if (!cap_isclear(bprm->cap_permitted))
			return 1;
		if (!cap_isclear(bprm->cap_inheritable))
			return 1;
	}

	return (current->euid != current->uid ||
		current->egid != current->gid);
}

int cap_inode_setxattr(struct dentry *dentry, char *name, void *value,
		       size_t size, int flags)
{
	if (!strcmp(name, XATTR_NAME_CAPS)) {
		if (!capable(CAP_SETFCAP))
			return -EPERM;
		return 0;
	} else if (!strncmp(name, XATTR_SECURITY_PREFIX,
		     sizeof(XATTR_SECURITY_PREFIX) - 1)  &&
	    !capable(CAP_SYS_ADMIN))
		return -EPERM;
	return 0;
}

int cap_inode_removexattr(struct dentry *dentry, char *name)
{
	if (!strcmp(name, XATTR_NAME_CAPS)) {
		if (!capable(CAP_SETFCAP))
			return -EPERM;
		return 0;
	} else if (!strncmp(name, XATTR_SECURITY_PREFIX,
		     sizeof(XATTR_SECURITY_PREFIX) - 1)  &&
	    !capable(CAP_SYS_ADMIN))
		return -EPERM;
	return 0;
}

/* moved from kernel/sys.c. */
/* 
 * cap_emulate_setxuid() fixes the effective / permitted capabilities of
 * a process after a call to setuid, setreuid, or setresuid.
 *
 *  1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of
 *  {r,e,s}uid != 0, the permitted and effective capabilities are
 *  cleared.
 *
 *  2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective
 *  capabilities of the process are cleared.
 *
 *  3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective
 *  capabilities are set to the permitted capabilities.
 *
 *  fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should 
 *  never happen.
 *
 *  -astor 
 *
 * cevans - New behaviour, Oct '99
 * A process may, via prctl(), elect to keep its capabilities when it
 * calls setuid() and switches away from uid==0. Both permitted and
 * effective sets will be retained.
 * Without this change, it was impossible for a daemon to drop only some
 * of its privilege. The call to setuid(!=0) would drop all privileges!
 * Keeping uid 0 is not an option because uid 0 owns too many vital
 * files..
 * Thanks to Olaf Kirch and Peter Benie for spotting this.
 */
static inline void cap_emulate_setxuid (int old_ruid, int old_euid,
					int old_suid)
{
	if ((old_ruid == 0 || old_euid == 0 || old_suid == 0) &&
	    (current->uid != 0 && current->euid != 0 && current->suid != 0) &&
	    !issecure(SECURE_KEEP_CAPS)) {
		cap_clear (current->cap_permitted);
		cap_clear (current->cap_effective);
	}
	if (old_euid == 0 && current->euid != 0) {
		cap_clear (current->cap_effective);
	}
	if (old_euid != 0 && current->euid == 0) {
		current->cap_effective = current->cap_permitted;
	}
}

int cap_task_post_setuid (uid_t old_ruid, uid_t old_euid, uid_t old_suid,
			  int flags)
{
	switch (flags) {
	case LSM_SETID_RE:
	case LSM_SETID_ID:
	case LSM_SETID_RES:
		/* Copied from kernel/sys.c:setreuid/setuid/setresuid. */
		if (!issecure (SECURE_NO_SETUID_FIXUP)) {
			cap_emulate_setxuid (old_ruid, old_euid, old_suid);
		}
		break;
	case LSM_SETID_FS:
		{
			uid_t old_fsuid = old_ruid;

			/* Copied from kernel/sys.c:setfsuid. */

			/*
			 * FIXME - is fsuser used for all CAP_FS_MASK capabilities?
			 *          if not, we might be a bit too harsh here.
			 */

			if (!issecure (SECURE_NO_SETUID_FIXUP)) {
				if (old_fsuid == 0 && current->fsuid != 0) {
					current->cap_effective =
						cap_drop_fs_set(
						    current->cap_effective);
				}
				if (old_fsuid != 0 && current->fsuid == 0) {
					current->cap_effective =
						cap_raise_fs_set(
						    current->cap_effective,
						    current->cap_permitted);
				}
			}
			break;
		}
	default:
		return -EINVAL;
	}

	return 0;
}

#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
/*
 * Rationale: code calling task_setscheduler, task_setioprio, and
 * task_setnice, assumes that
 *   . if capable(cap_sys_nice), then those actions should be allowed
 *   . if not capable(cap_sys_nice), but acting on your own processes,
 *   	then those actions should be allowed
 * This is insufficient now since you can call code without suid, but
 * yet with increased caps.
 * So we check for increased caps on the target process.
 */
static inline int cap_safe_nice(struct task_struct *p)
{
	if (!cap_issubset(p->cap_permitted, current->cap_permitted) &&
	    !__capable(current, CAP_SYS_NICE))
		return -EPERM;
	return 0;
}

int cap_task_setscheduler (struct task_struct *p, int policy,
			   struct sched_param *lp)
{
	return cap_safe_nice(p);
}

int cap_task_setioprio (struct task_struct *p, int ioprio)
{
	return cap_safe_nice(p);
}

int cap_task_setnice (struct task_struct *p, int nice)
{
	return cap_safe_nice(p);
}

/*
 * called from kernel/sys.c for prctl(PR_CABSET_DROP)
 * done without task_capability_lock() because it introduces
 * no new races - i.e. only another task doing capget() on
 * this task could get inconsistent info.  There can be no
 * racing writer bc a task can only change its own caps.
 */
static long cap_prctl_drop(unsigned long cap)
{
	if (!capable(CAP_SETPCAP))
		return -EPERM;
	if (!cap_valid(cap))
		return -EINVAL;
	cap_lower(current->cap_bset, cap);
	return 0;
}

#else
int cap_task_setscheduler (struct task_struct *p, int policy,
			   struct sched_param *lp)
{
	return 0;
}
int cap_task_setioprio (struct task_struct *p, int ioprio)
{
	return 0;
}
int cap_task_setnice (struct task_struct *p, int nice)
{
	return 0;
}
#endif

int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
		   unsigned long arg4, unsigned long arg5, long *rc_p)
{
	long error = 0;

	switch (option) {
	case PR_CAPBSET_READ:
		if (!cap_valid(arg2))
			error = -EINVAL;
		else
			error = !!cap_raised(current->cap_bset, arg2);
		break;
#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
	case PR_CAPBSET_DROP:
		error = cap_prctl_drop(arg2);
		break;

	/*
	 * The next four prctl's remain to assist with transitioning a
	 * system from legacy UID=0 based privilege (when filesystem
	 * capabilities are not in use) to a system using filesystem
	 * capabilities only - as the POSIX.1e draft intended.
	 *
	 * Note:
	 *
	 *  PR_SET_SECUREBITS =
	 *      issecure_mask(SECURE_KEEP_CAPS_LOCKED)
	 *    | issecure_mask(SECURE_NOROOT)
	 *    | issecure_mask(SECURE_NOROOT_LOCKED)
	 *    | issecure_mask(SECURE_NO_SETUID_FIXUP)
	 *    | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED)
	 *
	 * will ensure that the current process and all of its
	 * children will be locked into a pure
	 * capability-based-privilege environment.
	 */
	case PR_SET_SECUREBITS:
		if ((((current->securebits & SECURE_ALL_LOCKS) >> 1)
		     & (current->securebits ^ arg2))                  /*[1]*/
		    || ((current->securebits & SECURE_ALL_LOCKS
			 & ~arg2))                                    /*[2]*/
		    || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/
		    || (cap_capable(current, CAP_SETPCAP) != 0)) {    /*[4]*/
			/*
			 * [1] no changing of bits that are locked
			 * [2] no unlocking of locks
			 * [3] no setting of unsupported bits
			 * [4] doing anything requires privilege (go read about
			 *     the "sendmail capabilities bug")
			 */
			error = -EPERM;  /* cannot change a locked bit */
		} else {
			current->securebits = arg2;
		}
		break;
	case PR_GET_SECUREBITS:
		error = current->securebits;
		break;

#endif /* def CONFIG_SECURITY_FILE_CAPABILITIES */

	case PR_GET_KEEPCAPS:
		if (issecure(SECURE_KEEP_CAPS))
			error = 1;
		break;
	case PR_SET_KEEPCAPS:
		if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */
			error = -EINVAL;
		else if (issecure(SECURE_KEEP_CAPS_LOCKED))
			error = -EPERM;
		else if (arg2)
			current->securebits |= issecure_mask(SECURE_KEEP_CAPS);
		else
			current->securebits &=
				~issecure_mask(SECURE_KEEP_CAPS);
		break;

	default:
		/* No functionality available - continue with default */
		return 0;
	}

	/* Functionality provided */
	*rc_p = error;
	return 1;
}

void cap_task_reparent_to_init (struct task_struct *p)
{
	cap_set_init_eff(p->cap_effective);
	cap_clear(p->cap_inheritable);
	cap_set_full(p->cap_permitted);
	p->securebits = SECUREBITS_DEFAULT;
	return;
}

int cap_syslog (int type)
{
	if ((type != 3 && type != 10) && !capable(CAP_SYS_ADMIN))
		return -EPERM;
	return 0;
}

int cap_vm_enough_memory(struct mm_struct *mm, long pages)
{
	int cap_sys_admin = 0;

	if (cap_capable(current, CAP_SYS_ADMIN) == 0)
		cap_sys_admin = 1;
	return __vm_enough_memory(mm, pages, cap_sys_admin);
}