commoncap.c 14.3 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9
/* 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.
 *
 */

10
#include <linux/capability.h>
L
Linus Torvalds 已提交
11 12 13 14 15 16 17 18 19 20 21 22 23 24
#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>
25
#include <linux/mount.h>
L
Linus Torvalds 已提交
26

27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45
#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
/*
 * Because of the reduced scope of CAP_SETPCAP when filesystem
 * capabilities are in effect, it is safe to allow this capability to
 * be available in the default configuration.
 */
# define CAP_INIT_BSET  CAP_FULL_SET
#else /* ie. ndef CONFIG_SECURITY_FILE_CAPABILITIES */
# define CAP_INIT_BSET  CAP_INIT_EFF_SET
#endif /* def CONFIG_SECURITY_FILE_CAPABILITIES */

kernel_cap_t cap_bset = CAP_INIT_BSET;    /* systemwide capability bound */
EXPORT_SYMBOL(cap_bset);

/* Global security state */

unsigned securebits = SECUREBITS_DEFAULT; /* systemwide security settings */
EXPORT_SYMBOL(securebits);

L
Linus Torvalds 已提交
46 47 48 49 50 51
int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
{
	NETLINK_CB(skb).eff_cap = current->cap_effective;
	return 0;
}

52
int cap_netlink_recv(struct sk_buff *skb, int cap)
L
Linus Torvalds 已提交
53
{
54
	if (!cap_raised(NETLINK_CB(skb).eff_cap, cap))
L
Linus Torvalds 已提交
55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78
		return -EPERM;
	return 0;
}

EXPORT_SYMBOL(cap_netlink_recv);

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. */
79 80
	if (!cap_issubset(child->cap_permitted, parent->cap_permitted) &&
	    !__capable(parent, CAP_SYS_PTRACE))
L
Linus Torvalds 已提交
81 82 83 84 85 86 87 88 89 90 91 92 93 94
		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 = cap_t (target->cap_effective);
	*inheritable = cap_t (target->cap_inheritable);
	*permitted = cap_t (target->cap_permitted);
	return 0;
}

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
#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.
	 */
	return !cap_capable(current, CAP_SETPCAP);
}

#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 */

L
Linus Torvalds 已提交
122 123 124
int cap_capset_check (struct task_struct *target, kernel_cap_t *effective,
		      kernel_cap_t *inheritable, kernel_cap_t *permitted)
{
125 126 127 128 129 130 131 132
	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 */
L
Linus Torvalds 已提交
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
		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;
}

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
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(__le32 *caps, struct linux_binprm *bprm,
				int size)
{
	__u32 magic_etc;

	if (size != XATTR_CAPS_SZ)
		return -EINVAL;

	magic_etc = le32_to_cpu(caps[0]);

	switch ((magic_etc & VFS_CAP_REVISION_MASK)) {
	case VFS_CAP_REVISION:
		if (magic_etc & VFS_CAP_FLAGS_EFFECTIVE)
			bprm->cap_effective = true;
		else
			bprm->cap_effective = false;
		bprm->cap_permitted = to_cap_t( le32_to_cpu(caps[1]) );
		bprm->cap_inheritable = to_cap_t( le32_to_cpu(caps[2]) );
		return 0;
	default:
		return -EINVAL;
	}
}

/* Locate any VFS capabilities: */
static int get_file_caps(struct linux_binprm *bprm)
{
	struct dentry *dentry;
	int rc = 0;
	__le32 v1caps[XATTR_CAPS_SZ];
	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, &v1caps,
							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(v1caps, bprm, rc);
	if (rc)
		printk(KERN_NOTICE "%s: cap_from_disk returned %d for %s\n",
			__FUNCTION__, 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

L
Linus Torvalds 已提交
275 276
int cap_bprm_set_security (struct linux_binprm *bprm)
{
277
	int ret;
L
Linus Torvalds 已提交
278

279 280 281 282
	ret = get_file_caps(bprm);
	if (ret)
		printk(KERN_NOTICE "%s: get_file_caps returned %d for %s\n",
			__FUNCTION__, ret, bprm->filename);
L
Linus Torvalds 已提交
283 284 285 286 287 288 289 290 291 292 293 294 295 296 297

	/*  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)
298
			bprm->cap_effective = true;
L
Linus Torvalds 已提交
299
	}
300 301

	return ret;
L
Linus Torvalds 已提交
302 303 304 305 306 307 308 309 310 311 312 313 314 315
}

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, 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)) {
316
		set_dumpable(current->mm, suid_dumpable);
317
		current->pdeath_signal = 0;
L
Linus Torvalds 已提交
318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336

		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 */
337
	if (!is_init(current)) {
L
Linus Torvalds 已提交
338
		current->cap_permitted = new_permitted;
339 340
		current->cap_effective = bprm->cap_effective ?
				new_permitted : 0;
L
Linus Torvalds 已提交
341 342 343 344 345 346 347 348 349
	}

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

	current->keep_capabilities = 0;
}

int cap_bprm_secureexec (struct linux_binprm *bprm)
{
350 351 352 353 354 355 356 357 358
	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;
	}

L
Linus Torvalds 已提交
359 360 361 362 363 364 365
	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)
{
366 367 368 369 370
	if (!strcmp(name, XATTR_NAME_CAPS)) {
		if (!capable(CAP_SETFCAP))
			return -EPERM;
		return 0;
	} else if (!strncmp(name, XATTR_SECURITY_PREFIX,
L
Linus Torvalds 已提交
371 372 373 374 375 376 377 378
		     sizeof(XATTR_SECURITY_PREFIX) - 1)  &&
	    !capable(CAP_SYS_ADMIN))
		return -EPERM;
	return 0;
}

int cap_inode_removexattr(struct dentry *dentry, char *name)
{
379 380 381 382 383
	if (!strcmp(name, XATTR_NAME_CAPS)) {
		if (!capable(CAP_SETFCAP))
			return -EPERM;
		return 0;
	} else if (!strncmp(name, XATTR_SECURITY_PREFIX,
L
Linus Torvalds 已提交
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
		     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) &&
	    !current->keep_capabilities) {
		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) {
					cap_t (current->cap_effective) &=
					    ~CAP_FS_MASK;
				}
				if (old_fsuid != 0 && current->fsuid == 0) {
					cap_t (current->cap_effective) |=
					    (cap_t (current->cap_permitted) &
					     CAP_FS_MASK);
				}
			}
			break;
		}
	default:
		return -EINVAL;
	}

	return 0;
}

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
#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);
}

int cap_task_kill(struct task_struct *p, struct siginfo *info,
				int sig, u32 secid)
{
	if (info != SEND_SIG_NOINFO && (is_si_special(info) || SI_FROMKERNEL(info)))
		return 0;

	if (secid)
		/*
		 * Signal sent as a particular user.
		 * Capabilities are ignored.  May be wrong, but it's the
		 * only thing we can do at the moment.
		 * Used only by usb drivers?
		 */
		return 0;
	if (cap_issubset(p->cap_permitted, current->cap_permitted))
		return 0;
	if (capable(CAP_KILL))
		return 0;

	return -EPERM;
}
#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;
}
int cap_task_kill(struct task_struct *p, struct siginfo *info,
				int sig, u32 secid)
{
	return 0;
}
#endif

L
Linus Torvalds 已提交
557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572
void cap_task_reparent_to_init (struct task_struct *p)
{
	p->cap_effective = CAP_INIT_EFF_SET;
	p->cap_inheritable = CAP_INIT_INH_SET;
	p->cap_permitted = CAP_FULL_SET;
	p->keep_capabilities = 0;
	return;
}

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

573
int cap_vm_enough_memory(struct mm_struct *mm, long pages)
L
Linus Torvalds 已提交
574 575 576 577 578
{
	int cap_sys_admin = 0;

	if (cap_capable(current, CAP_SYS_ADMIN) == 0)
		cap_sys_admin = 1;
579
	return __vm_enough_memory(mm, pages, cap_sys_admin);
L
Linus Torvalds 已提交
580 581
}