• Eric Paris's avatar
    SELinux: do not destroy the avc_cache_nodep · 5224ee08
    Eric Paris authored
    
    The security_ops reset done when SELinux is disabled at run time is done
    after the avc cache is freed and after the kmem_cache for the avc is also
    freed.  This means that between the time the selinux disable code destroys
    the avc_node_cachep another process could make a security request and could
    try to allocate from the cache.  We are just going to leave the cachep around,
    like we always have.
    
    SELinux:  Disabled at runtime.
    BUG: unable to handle kernel NULL pointer dereference at (null)
    IP: [<ffffffff81122537>] kmem_cache_alloc+0x9a/0x185
    PGD 0
    Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
    last sysfs file:
    CPU 1
    Modules linked in:
    Pid: 12, comm: khelper Not tainted 2.6.31-tip-05525-g0eeacc6-dirty #14819
    System Product Name
    RIP: 0010:[<ffffffff81122537>]  [<ffffffff81122537>]
    kmem_cache_alloc+0x9a/0x185
    RSP: 0018:ffff88003f9258b0  EFLAGS: 00010086
    RAX: 0000000000000001 RBX: 0000000000000000 RCX: 0000000078c0129e
    RDX: 0000000000000000 RSI: ffffffff8130b626 RDI: ffffffff81122528
    RBP: ffff88003f925900 R08: 0000000078c0129e R09: 0000000000000001
    R10: 0000000000000000 R11: 0000000078c0129e R12: 0000000000000246
    R13: 0000000000008020 R14: ffff88003f8586d8 R15: 0000000000000001
    FS:  0000000000000000(0000) GS:ffff880002b00000(0000)
    knlGS:0000000000000000
    CS:  0010 DS: 0018 ES: 0018 CR0: 000000008005003b
    CR2: 0000000000000000 CR3: 0000000001001000 CR4: 00000000000006e0
    DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
    DR3: ffffffff827bd420 DR6: 00000000ffff0ff0 DR7: 0000000000000400
    Process khelper (pid: 12, threadinfo ffff88003f924000, task
    ffff88003f928000)
    Stack:
     0000000000000246 0000802000000246 ffffffff8130b626 0000000000000001
    <0> 0000000078c0129e 0000000000000000 ffff88003f925a70 0000000000000002
    <0> 0000000000000001 0000000000000001 ffff88003f925960 ffffffff8130b626
    Call Trace:
     [<ffffffff8130b626>] ? avc_alloc_node+0x36/0x273
     [<ffffffff8130b626>] avc_alloc_node+0x36/0x273
     [<ffffffff8130b545>] ? avc_latest_notif_update+0x7d/0x9e
     [<ffffffff8130b8b4>] avc_insert+0x51/0x18d
     [<ffffffff8130bcce>] avc_has_perm_noaudit+0x9d/0x128
     [<ffffffff8130bf20>] avc_has_perm+0x45/0x88
     [<ffffffff8130f99d>] current_has_perm+0x52/0x6d
     [<ffffffff8130fbb2>] selinux_task_create+0x2f/0x45
     [<ffffffff81303bf7>] security_task_create+0x29/0x3f
     [<ffffffff8105c6ba>] copy_process+0x82/0xdf0
     [<ffffffff81091578>] ? register_lock_class+0x2f/0x36c
     [<ffffffff81091a13>] ? mark_lock+0x2e/0x1e1
     [<ffffffff8105d596>] do_fork+0x16e/0x382
     [<ffffffff81091578>] ? register_lock_class+0x2f/0x36c
     [<ffffffff810d9166>] ? probe_workqueue_execution+0x57/0xf9
     [<ffffffff81091a13>] ? mark_lock+0x2e/0x1e1
     [<ffffffff810d9166>] ? probe_workqueue_execution+0x57/0xf9
     [<ffffffff8100cdb2>] kernel_thread+0x82/0xe0
     [<ffffffff81078b1f>] ? ____call_usermodehelper+0x0/0x139
     [<ffffffff8100ce10>] ? child_rip+0x0/0x20
     [<ffffffff81078aea>] ? __call_usermodehelper+0x65/0x9a
     [<ffffffff8107a5c7>] run_workqueue+0x171/0x27e
     [<ffffffff8107a573>] ? run_workqueue+0x11d/0x27e
     [<ffffffff81078a85>] ? __call_usermodehelper+0x0/0x9a
     [<ffffffff8107a7bc>] worker_thread+0xe8/0x10f
     [<ffffffff810808e2>] ? autoremove_wake_function+0x0/0x63
     [<ffffffff8107a6d4>] ? worker_thread+0x0/0x10f
     [<ffffffff8108042e>] kthread+0x91/0x99
     [<ffffffff8100ce1a>] child_rip+0xa/0x20
     [<ffffffff8100c754>] ? restore_args+0x0/0x30
     [<ffffffff8108039d>] ? kthread+0x0/0x99
     [<ffffffff8100ce10>] ? child_rip+0x0/0x20
    Code: 0f 85 99 00 00 00 9c 58 66 66 90 66 90 49 89 c4 fa 66 66 90 66 66 90
    e8 83 34 fb ff e8 d7 e9 26 00 48 98 49 8b 94 c6 10 01 00 00 <48> 8b 1a 44
    8b 7a 18 48 85 db 74 0f 8b 42 14 48 8b 04 c3 ff 42
    RIP  [<ffffffff81122537>] kmem_cache_alloc+0x9a/0x185
     RSP <ffff88003f9258b0>
    CR2: 0000000000000000
    ---[ end trace 42f41a982344e606 ]---
    Reported-by: default avatarIngo Molnar <mingo@elte.hu>
    Signed-off-by: default avatarEric Paris <eparis@redhat.com>
    Signed-off-by: default avatarJames Morris <jmorris@namei.org>
    5224ee08
avc.c 22.1 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886
/*
 * Implementation of the kernel access vector cache (AVC).
 *
 * Authors:  Stephen Smalley, <sds@epoch.ncsc.mil>
 *	     James Morris <jmorris@redhat.com>
 *
 * Update:   KaiGai, Kohei <kaigai@ak.jp.nec.com>
 *	Replaced the avc_lock spinlock by RCU.
 *
 * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com>
 *
 *	This program is free software; you can redistribute it and/or modify
 *	it under the terms of the GNU General Public License version 2,
 *	as published by the Free Software Foundation.
 */
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/dcache.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/percpu.h>
#include <net/sock.h>
#include <linux/un.h>
#include <net/af_unix.h>
#include <linux/ip.h>
#include <linux/audit.h>
#include <linux/ipv6.h>
#include <net/ipv6.h>
#include "avc.h"
#include "avc_ss.h"

static const struct av_perm_to_string av_perm_to_string[] = {
#define S_(c, v, s) { c, v, s },
#include "av_perm_to_string.h"
#undef S_
};

static const char *class_to_string[] = {
#define S_(s) s,
#include "class_to_string.h"
#undef S_
};

#define TB_(s) static const char *s[] = {
#define TE_(s) };
#define S_(s) s,
#include "common_perm_to_string.h"
#undef TB_
#undef TE_
#undef S_

static const struct av_inherit av_inherit[] = {
#define S_(c, i, b) {	.tclass = c,\
			.common_pts = common_##i##_perm_to_string,\
			.common_base =  b },
#include "av_inherit.h"
#undef S_
};

const struct selinux_class_perm selinux_class_perm = {
	.av_perm_to_string = av_perm_to_string,
	.av_pts_len = ARRAY_SIZE(av_perm_to_string),
	.class_to_string = class_to_string,
	.cts_len = ARRAY_SIZE(class_to_string),
	.av_inherit = av_inherit,
	.av_inherit_len = ARRAY_SIZE(av_inherit)
};

#define AVC_CACHE_SLOTS			512
#define AVC_DEF_CACHE_THRESHOLD		512
#define AVC_CACHE_RECLAIM		16

#ifdef CONFIG_SECURITY_SELINUX_AVC_STATS
#define avc_cache_stats_incr(field)				\
do {								\
	per_cpu(avc_cache_stats, get_cpu()).field++;		\
	put_cpu();						\
} while (0)
#else
#define avc_cache_stats_incr(field)	do {} while (0)
#endif

struct avc_entry {
	u32			ssid;
	u32			tsid;
	u16			tclass;
	struct av_decision	avd;
};

struct avc_node {
	struct avc_entry	ae;
	struct hlist_node	list; /* anchored in avc_cache->slots[i] */
	struct rcu_head		rhead;
};

struct avc_cache {
	struct hlist_head	slots[AVC_CACHE_SLOTS]; /* head for avc_node->list */
	spinlock_t		slots_lock[AVC_CACHE_SLOTS]; /* lock for writes */
	atomic_t		lru_hint;	/* LRU hint for reclaim scan */
	atomic_t		active_nodes;
	u32			latest_notif;	/* latest revocation notification */
};

struct avc_callback_node {
	int (*callback) (u32 event, u32 ssid, u32 tsid,
			 u16 tclass, u32 perms,
			 u32 *out_retained);
	u32 events;
	u32 ssid;
	u32 tsid;
	u16 tclass;
	u32 perms;
	struct avc_callback_node *next;
};

/* Exported via selinufs */
unsigned int avc_cache_threshold = AVC_DEF_CACHE_THRESHOLD;

#ifdef CONFIG_SECURITY_SELINUX_AVC_STATS
DEFINE_PER_CPU(struct avc_cache_stats, avc_cache_stats) = { 0 };
#endif

static struct avc_cache avc_cache;
static struct avc_callback_node *avc_callbacks;
static struct kmem_cache *avc_node_cachep;

static inline int avc_hash(u32 ssid, u32 tsid, u16 tclass)
{
	return (ssid ^ (tsid<<2) ^ (tclass<<4)) & (AVC_CACHE_SLOTS - 1);
}

/**
 * avc_dump_av - Display an access vector in human-readable form.
 * @tclass: target security class
 * @av: access vector
 */
static void avc_dump_av(struct audit_buffer *ab, u16 tclass, u32 av)
{
	const char **common_pts = NULL;
	u32 common_base = 0;
	int i, i2, perm;

	if (av == 0) {
		audit_log_format(ab, " null");
		return;
	}

	for (i = 0; i < ARRAY_SIZE(av_inherit); i++) {
		if (av_inherit[i].tclass == tclass) {
			common_pts = av_inherit[i].common_pts;
			common_base = av_inherit[i].common_base;
			break;
		}
	}

	audit_log_format(ab, " {");
	i = 0;
	perm = 1;
	while (perm < common_base) {
		if (perm & av) {
			audit_log_format(ab, " %s", common_pts[i]);
			av &= ~perm;
		}
		i++;
		perm <<= 1;
	}

	while (i < sizeof(av) * 8) {
		if (perm & av) {
			for (i2 = 0; i2 < ARRAY_SIZE(av_perm_to_string); i2++) {
				if ((av_perm_to_string[i2].tclass == tclass) &&
				    (av_perm_to_string[i2].value == perm))
					break;
			}
			if (i2 < ARRAY_SIZE(av_perm_to_string)) {
				audit_log_format(ab, " %s",
						 av_perm_to_string[i2].name);
				av &= ~perm;
			}
		}
		i++;
		perm <<= 1;
	}

	if (av)
		audit_log_format(ab, " 0x%x", av);

	audit_log_format(ab, " }");
}

/**
 * avc_dump_query - Display a SID pair and a class in human-readable form.
 * @ssid: source security identifier
 * @tsid: target security identifier
 * @tclass: target security class
 */
static void avc_dump_query(struct audit_buffer *ab, u32 ssid, u32 tsid, u16 tclass)
{
	int rc;
	char *scontext;
	u32 scontext_len;

	rc = security_sid_to_context(ssid, &scontext, &scontext_len);
	if (rc)
		audit_log_format(ab, "ssid=%d", ssid);
	else {
		audit_log_format(ab, "scontext=%s", scontext);
		kfree(scontext);
	}

	rc = security_sid_to_context(tsid, &scontext, &scontext_len);
	if (rc)
		audit_log_format(ab, " tsid=%d", tsid);
	else {
		audit_log_format(ab, " tcontext=%s", scontext);
		kfree(scontext);
	}

	BUG_ON(tclass >= ARRAY_SIZE(class_to_string) || !class_to_string[tclass]);
	audit_log_format(ab, " tclass=%s", class_to_string[tclass]);
}

/**
 * avc_init - Initialize the AVC.
 *
 * Initialize the access vector cache.
 */
void __init avc_init(void)
{
	int i;

	for (i = 0; i < AVC_CACHE_SLOTS; i++) {
		INIT_HLIST_HEAD(&avc_cache.slots[i]);
		spin_lock_init(&avc_cache.slots_lock[i]);
	}
	atomic_set(&avc_cache.active_nodes, 0);
	atomic_set(&avc_cache.lru_hint, 0);

	avc_node_cachep = kmem_cache_create("avc_node", sizeof(struct avc_node),
					     0, SLAB_PANIC, NULL);

	audit_log(current->audit_context, GFP_KERNEL, AUDIT_KERNEL, "AVC INITIALIZED\n");
}

int avc_get_hash_stats(char *page)
{
	int i, chain_len, max_chain_len, slots_used;
	struct avc_node *node;
	struct hlist_head *head;

	rcu_read_lock();

	slots_used = 0;
	max_chain_len = 0;
	for (i = 0; i < AVC_CACHE_SLOTS; i++) {
		head = &avc_cache.slots[i];
		if (!hlist_empty(head)) {
			struct hlist_node *next;

			slots_used++;
			chain_len = 0;
			hlist_for_each_entry_rcu(node, next, head, list)
				chain_len++;
			if (chain_len > max_chain_len)
				max_chain_len = chain_len;
		}
	}

	rcu_read_unlock();

	return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n"
			 "longest chain: %d\n",
			 atomic_read(&avc_cache.active_nodes),
			 slots_used, AVC_CACHE_SLOTS, max_chain_len);
}

static void avc_node_free(struct rcu_head *rhead)
{
	struct avc_node *node = container_of(rhead, struct avc_node, rhead);
	kmem_cache_free(avc_node_cachep, node);
	avc_cache_stats_incr(frees);
}

static void avc_node_delete(struct avc_node *node)
{
	hlist_del_rcu(&node->list);
	call_rcu(&node->rhead, avc_node_free);
	atomic_dec(&avc_cache.active_nodes);
}

static void avc_node_kill(struct avc_node *node)
{
	kmem_cache_free(avc_node_cachep, node);
	avc_cache_stats_incr(frees);
	atomic_dec(&avc_cache.active_nodes);
}

static void avc_node_replace(struct avc_node *new, struct avc_node *old)
{
	hlist_replace_rcu(&old->list, &new->list);
	call_rcu(&old->rhead, avc_node_free);
	atomic_dec(&avc_cache.active_nodes);
}

static inline int avc_reclaim_node(void)
{
	struct avc_node *node;
	int hvalue, try, ecx;
	unsigned long flags;
	struct hlist_head *head;
	struct hlist_node *next;
	spinlock_t *lock;

	for (try = 0, ecx = 0; try < AVC_CACHE_SLOTS; try++) {
		hvalue = atomic_inc_return(&avc_cache.lru_hint) & (AVC_CACHE_SLOTS - 1);
		head = &avc_cache.slots[hvalue];
		lock = &avc_cache.slots_lock[hvalue];

		if (!spin_trylock_irqsave(lock, flags))
			continue;

		rcu_read_lock();
		hlist_for_each_entry(node, next, head, list) {
			avc_node_delete(node);
			avc_cache_stats_incr(reclaims);
			ecx++;
			if (ecx >= AVC_CACHE_RECLAIM) {
				rcu_read_unlock();
				spin_unlock_irqrestore(lock, flags);
				goto out;
			}
		}
		rcu_read_unlock();
		spin_unlock_irqrestore(lock, flags);
	}
out:
	return ecx;
}

static struct avc_node *avc_alloc_node(void)
{
	struct avc_node *node;

	node = kmem_cache_zalloc(avc_node_cachep, GFP_ATOMIC);
	if (!node)
		goto out;

	INIT_RCU_HEAD(&node->rhead);
	INIT_HLIST_NODE(&node->list);
	avc_cache_stats_incr(allocations);

	if (atomic_inc_return(&avc_cache.active_nodes) > avc_cache_threshold)
		avc_reclaim_node();

out:
	return node;
}

static void avc_node_populate(struct avc_node *node, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd)
{
	node->ae.ssid = ssid;
	node->ae.tsid = tsid;
	node->ae.tclass = tclass;
	memcpy(&node->ae.avd, avd, sizeof(node->ae.avd));
}

static inline struct avc_node *avc_search_node(u32 ssid, u32 tsid, u16 tclass)
{
	struct avc_node *node, *ret = NULL;
	int hvalue;
	struct hlist_head *head;
	struct hlist_node *next;

	hvalue = avc_hash(ssid, tsid, tclass);
	head = &avc_cache.slots[hvalue];
	hlist_for_each_entry_rcu(node, next, head, list) {
		if (ssid == node->ae.ssid &&
		    tclass == node->ae.tclass &&
		    tsid == node->ae.tsid) {
			ret = node;
			break;
		}
	}

	return ret;
}

/**
 * avc_lookup - Look up an AVC entry.
 * @ssid: source security identifier
 * @tsid: target security identifier
 * @tclass: target security class
 *
 * Look up an AVC entry that is valid for the
 * (@ssid, @tsid), interpreting the permissions
 * based on @tclass.  If a valid AVC entry exists,
 * then this function return the avc_node.
 * Otherwise, this function returns NULL.
 */
static struct avc_node *avc_lookup(u32 ssid, u32 tsid, u16 tclass)
{
	struct avc_node *node;

	avc_cache_stats_incr(lookups);
	node = avc_search_node(ssid, tsid, tclass);

	if (node)
		avc_cache_stats_incr(hits);
	else
		avc_cache_stats_incr(misses);

	return node;
}

static int avc_latest_notif_update(int seqno, int is_insert)
{
	int ret = 0;
	static DEFINE_SPINLOCK(notif_lock);
	unsigned long flag;

	spin_lock_irqsave(&notif_lock, flag);
	if (is_insert) {
		if (seqno < avc_cache.latest_notif) {
			printk(KERN_WARNING "SELinux: avc:  seqno %d < latest_notif %d\n",
			       seqno, avc_cache.latest_notif);
			ret = -EAGAIN;
		}
	} else {
		if (seqno > avc_cache.latest_notif)
			avc_cache.latest_notif = seqno;
	}
	spin_unlock_irqrestore(&notif_lock, flag);

	return ret;
}

/**
 * avc_insert - Insert an AVC entry.
 * @ssid: source security identifier
 * @tsid: target security identifier
 * @tclass: target security class
 * @avd: resulting av decision
 *
 * Insert an AVC entry for the SID pair
 * (@ssid, @tsid) and class @tclass.
 * The access vectors and the sequence number are
 * normally provided by the security server in
 * response to a security_compute_av() call.  If the
 * sequence number @avd->seqno is not less than the latest
 * revocation notification, then the function copies
 * the access vectors into a cache entry, returns
 * avc_node inserted. Otherwise, this function returns NULL.
 */
static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd)
{
	struct avc_node *pos, *node = NULL;
	int hvalue;
	unsigned long flag;

	if (avc_latest_notif_update(avd->seqno, 1))
		goto out;

	node = avc_alloc_node();
	if (node) {
		struct hlist_head *head;
		struct hlist_node *next;
		spinlock_t *lock;

		hvalue = avc_hash(ssid, tsid, tclass);
		avc_node_populate(node, ssid, tsid, tclass, avd);

		head = &avc_cache.slots[hvalue];
		lock = &avc_cache.slots_lock[hvalue];

		spin_lock_irqsave(lock, flag);
		hlist_for_each_entry(pos, next, head, list) {
			if (pos->ae.ssid == ssid &&
			    pos->ae.tsid == tsid &&
			    pos->ae.tclass == tclass) {
				avc_node_replace(node, pos);
				goto found;
			}
		}
		hlist_add_head_rcu(&node->list, head);
found:
		spin_unlock_irqrestore(lock, flag);
	}
out:
	return node;
}

/**
 * avc_audit_pre_callback - SELinux specific information
 * will be called by generic audit code
 * @ab: the audit buffer
 * @a: audit_data
 */
static void avc_audit_pre_callback(struct audit_buffer *ab, void *a)
{
	struct common_audit_data *ad = a;
	audit_log_format(ab, "avc:  %s ",
			 ad->selinux_audit_data.denied ? "denied" : "granted");
	avc_dump_av(ab, ad->selinux_audit_data.tclass,
			ad->selinux_audit_data.audited);
	audit_log_format(ab, " for ");
}

/**
 * avc_audit_post_callback - SELinux specific information
 * will be called by generic audit code
 * @ab: the audit buffer
 * @a: audit_data
 */
static void avc_audit_post_callback(struct audit_buffer *ab, void *a)
{
	struct common_audit_data *ad = a;
	audit_log_format(ab, " ");
	avc_dump_query(ab, ad->selinux_audit_data.ssid,
			   ad->selinux_audit_data.tsid,
			   ad->selinux_audit_data.tclass);
}

/**
 * avc_audit - Audit the granting or denial of permissions.
 * @ssid: source security identifier
 * @tsid: target security identifier
 * @tclass: target security class
 * @requested: requested permissions
 * @avd: access vector decisions
 * @result: result from avc_has_perm_noaudit
 * @a:  auxiliary audit data
 *
 * Audit the granting or denial of permissions in accordance
 * with the policy.  This function is typically called by
 * avc_has_perm() after a permission check, but can also be
 * called directly by callers who use avc_has_perm_noaudit()
 * in order to separate the permission check from the auditing.
 * For example, this separation is useful when the permission check must
 * be performed under a lock, to allow the lock to be released
 * before calling the auditing code.
 */
void avc_audit(u32 ssid, u32 tsid,
	       u16 tclass, u32 requested,
	       struct av_decision *avd, int result, struct common_audit_data *a)
{
	struct common_audit_data stack_data;
	u32 denied, audited;
	denied = requested & ~avd->allowed;
	if (denied) {
		audited = denied;
		if (!(audited & avd->auditdeny))
			return;
	} else if (result) {
		audited = denied = requested;
	} else {
		audited = requested;
		if (!(audited & avd->auditallow))
			return;
	}
	if (!a) {
		a = &stack_data;
		memset(a, 0, sizeof(*a));
		a->type = LSM_AUDIT_NO_AUDIT;
	}
	a->selinux_audit_data.tclass = tclass;
	a->selinux_audit_data.requested = requested;
	a->selinux_audit_data.ssid = ssid;
	a->selinux_audit_data.tsid = tsid;
	a->selinux_audit_data.audited = audited;
	a->selinux_audit_data.denied = denied;
	a->lsm_pre_audit = avc_audit_pre_callback;
	a->lsm_post_audit = avc_audit_post_callback;
	common_lsm_audit(a);
}

/**
 * avc_add_callback - Register a callback for security events.
 * @callback: callback function
 * @events: security events
 * @ssid: source security identifier or %SECSID_WILD
 * @tsid: target security identifier or %SECSID_WILD
 * @tclass: target security class
 * @perms: permissions
 *
 * Register a callback function for events in the set @events
 * related to the SID pair (@ssid, @tsid) and
 * and the permissions @perms, interpreting
 * @perms based on @tclass.  Returns %0 on success or
 * -%ENOMEM if insufficient memory exists to add the callback.
 */
int avc_add_callback(int (*callback)(u32 event, u32 ssid, u32 tsid,
				     u16 tclass, u32 perms,
				     u32 *out_retained),
		     u32 events, u32 ssid, u32 tsid,
		     u16 tclass, u32 perms)
{
	struct avc_callback_node *c;
	int rc = 0;

	c = kmalloc(sizeof(*c), GFP_ATOMIC);
	if (!c) {
		rc = -ENOMEM;
		goto out;
	}

	c->callback = callback;
	c->events = events;
	c->ssid = ssid;
	c->tsid = tsid;
	c->perms = perms;
	c->next = avc_callbacks;
	avc_callbacks = c;
out:
	return rc;
}

static inline int avc_sidcmp(u32 x, u32 y)
{
	return (x == y || x == SECSID_WILD || y == SECSID_WILD);
}

/**
 * avc_update_node Update an AVC entry
 * @event : Updating event
 * @perms : Permission mask bits
 * @ssid,@tsid,@tclass : identifier of an AVC entry
 * @seqno : sequence number when decision was made
 *
 * if a valid AVC entry doesn't exist,this function returns -ENOENT.
 * if kmalloc() called internal returns NULL, this function returns -ENOMEM.
 * otherwise, this function update the AVC entry. The original AVC-entry object
 * will release later by RCU.
 */
static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass,
			   u32 seqno)
{
	int hvalue, rc = 0;
	unsigned long flag;
	struct avc_node *pos, *node, *orig = NULL;
	struct hlist_head *head;
	struct hlist_node *next;
	spinlock_t *lock;

	node = avc_alloc_node();
	if (!node) {
		rc = -ENOMEM;
		goto out;
	}

	/* Lock the target slot */
	hvalue = avc_hash(ssid, tsid, tclass);

	head = &avc_cache.slots[hvalue];
	lock = &avc_cache.slots_lock[hvalue];

	spin_lock_irqsave(lock, flag);

	hlist_for_each_entry(pos, next, head, list) {
		if (ssid == pos->ae.ssid &&
		    tsid == pos->ae.tsid &&
		    tclass == pos->ae.tclass &&
		    seqno == pos->ae.avd.seqno){
			orig = pos;
			break;
		}
	}

	if (!orig) {
		rc = -ENOENT;
		avc_node_kill(node);
		goto out_unlock;
	}

	/*
	 * Copy and replace original node.
	 */

	avc_node_populate(node, ssid, tsid, tclass, &orig->ae.avd);

	switch (event) {
	case AVC_CALLBACK_GRANT:
		node->ae.avd.allowed |= perms;
		break;
	case AVC_CALLBACK_TRY_REVOKE:
	case AVC_CALLBACK_REVOKE:
		node->ae.avd.allowed &= ~perms;
		break;
	case AVC_CALLBACK_AUDITALLOW_ENABLE:
		node->ae.avd.auditallow |= perms;
		break;
	case AVC_CALLBACK_AUDITALLOW_DISABLE:
		node->ae.avd.auditallow &= ~perms;
		break;
	case AVC_CALLBACK_AUDITDENY_ENABLE:
		node->ae.avd.auditdeny |= perms;
		break;
	case AVC_CALLBACK_AUDITDENY_DISABLE:
		node->ae.avd.auditdeny &= ~perms;
		break;
	}
	avc_node_replace(node, orig);
out_unlock:
	spin_unlock_irqrestore(lock, flag);
out:
	return rc;
}

/**
 * avc_flush - Flush the cache
 */
static void avc_flush(void)
{
	struct hlist_head *head;
	struct hlist_node *next;
	struct avc_node *node;
	spinlock_t *lock;
	unsigned long flag;
	int i;

	for (i = 0; i < AVC_CACHE_SLOTS; i++) {
		head = &avc_cache.slots[i];
		lock = &avc_cache.slots_lock[i];

		spin_lock_irqsave(lock, flag);
		/*
		 * With preemptable RCU, the outer spinlock does not
		 * prevent RCU grace periods from ending.
		 */
		rcu_read_lock();
		hlist_for_each_entry(node, next, head, list)
			avc_node_delete(node);
		rcu_read_unlock();
		spin_unlock_irqrestore(lock, flag);
	}
}

/**
 * avc_ss_reset - Flush the cache and revalidate migrated permissions.
 * @seqno: policy sequence number
 */
int avc_ss_reset(u32 seqno)
{
	struct avc_callback_node *c;
	int rc = 0, tmprc;

	avc_flush();

	for (c = avc_callbacks; c; c = c->next) {
		if (c->events & AVC_CALLBACK_RESET) {
			tmprc = c->callback(AVC_CALLBACK_RESET,
					    0, 0, 0, 0, NULL);
			/* save the first error encountered for the return
			   value and continue processing the callbacks */
			if (!rc)
				rc = tmprc;
		}
	}

	avc_latest_notif_update(seqno, 0);
	return rc;
}

/**
 * avc_has_perm_noaudit - Check permissions but perform no auditing.
 * @ssid: source security identifier
 * @tsid: target security identifier
 * @tclass: target security class
 * @requested: requested permissions, interpreted based on @tclass
 * @flags:  AVC_STRICT or 0
 * @avd: access vector decisions
 *
 * Check the AVC to determine whether the @requested permissions are granted
 * for the SID pair (@ssid, @tsid), interpreting the permissions
 * based on @tclass, and call the security server on a cache miss to obtain
 * a new decision and add it to the cache.  Return a copy of the decisions
 * in @avd.  Return %0 if all @requested permissions are granted,
 * -%EACCES if any permissions are denied, or another -errno upon
 * other errors.  This function is typically called by avc_has_perm(),
 * but may also be called directly to separate permission checking from
 * auditing, e.g. in cases where a lock must be held for the check but
 * should be released for the auditing.
 */
int avc_has_perm_noaudit(u32 ssid, u32 tsid,
			 u16 tclass, u32 requested,
			 unsigned flags,
			 struct av_decision *in_avd)
{
	struct avc_node *node;
	struct av_decision avd_entry, *avd;
	int rc = 0;
	u32 denied;

	BUG_ON(!requested);

	rcu_read_lock();

	node = avc_lookup(ssid, tsid, tclass);
	if (!node) {
		rcu_read_unlock();

		if (in_avd)
			avd = in_avd;
		else
			avd = &avd_entry;

		rc = security_compute_av(ssid, tsid, tclass, requested, avd);
		if (rc)
			goto out;
		rcu_read_lock();
		node = avc_insert(ssid, tsid, tclass, avd);
	} else {
		if (in_avd)
			memcpy(in_avd, &node->ae.avd, sizeof(*in_avd));
		avd = &node->ae.avd;
	}

	denied = requested & ~(avd->allowed);

	if (denied) {
		if (flags & AVC_STRICT)
			rc = -EACCES;
		else if (!selinux_enforcing || (avd->flags & AVD_FLAGS_PERMISSIVE))
			avc_update_node(AVC_CALLBACK_GRANT, requested, ssid,
					tsid, tclass, avd->seqno);
		else
			rc = -EACCES;
	}

	rcu_read_unlock();
out:
	return rc;
}

/**
 * avc_has_perm - Check permissions and perform any appropriate auditing.
 * @ssid: source security identifier
 * @tsid: target security identifier
 * @tclass: target security class
 * @requested: requested permissions, interpreted based on @tclass
 * @auditdata: auxiliary audit data
 *
 * Check the AVC to determine whether the @requested permissions are granted
 * for the SID pair (@ssid, @tsid), interpreting the permissions
 * based on @tclass, and call the security server on a cache miss to obtain
 * a new decision and add it to the cache.  Audit the granting or denial of
 * permissions in accordance with the policy.  Return %0 if all @requested
 * permissions are granted, -%EACCES if any permissions are denied, or
 * another -errno upon other errors.
 */
int avc_has_perm(u32 ssid, u32 tsid, u16 tclass,
		 u32 requested, struct common_audit_data *auditdata)
{
	struct av_decision avd;
	int rc;

	rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd);
	avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata);
	return rc;
}

u32 avc_policy_seqno(void)
{
	return avc_cache.latest_notif;
}

void avc_disable(void)
{
	/*
	 * If you are looking at this because you have realized that we are
	 * not destroying the avc_node_cachep it might be easy to fix, but
	 * I don't know the memory barrier semantics well enough to know.  It's
	 * possible that some other task dereferenced security_ops when
	 * it still pointed to selinux operations.  If that is the case it's
	 * possible that it is about to use the avc and is about to need the
	 * avc_node_cachep.  I know I could wrap the security.c security_ops call
	 * in an rcu_lock, but seriously, it's not worth it.  Instead I just flush
	 * the cache and get that memory back.
	 */
	if (avc_node_cachep) {
		avc_flush();
		/* kmem_cache_destroy(avc_node_cachep); */
	}
}