summaryrefslogtreecommitdiff
path: root/kernel/audit_tree.c
blob: 1b7a2f04179369d05d37d308d567a64a19da4cb8 (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
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
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
// SPDX-License-Identifier: GPL-2.0
#include "audit.h"
#include <linux/fsnotify_backend.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/kthread.h>
#include <linux/refcount.h>
#include <linux/slab.h>

struct audit_tree;
struct audit_chunk;

struct audit_tree {
	refcount_t count;
	int goner;
	struct audit_chunk *root;
	struct list_head chunks;
	struct list_head rules;
	struct list_head list;
	struct list_head same_root;
	struct rcu_head head;
	char pathname[];
};

struct audit_chunk {
	struct list_head hash;
	unsigned long key;
	struct fsnotify_mark *mark;
	struct list_head trees;		/* with root here */
	int count;
	atomic_long_t refs;
	struct rcu_head head;
	struct node {
		struct list_head list;
		struct audit_tree *owner;
		unsigned index;		/* index; upper bit indicates 'will prune' */
	} owners[];
};

struct audit_tree_mark {
	struct fsnotify_mark mark;
	struct audit_chunk *chunk;
};

static LIST_HEAD(tree_list);
static LIST_HEAD(prune_list);
static struct task_struct *prune_thread;

/*
 * One struct chunk is attached to each inode of interest through
 * audit_tree_mark (fsnotify mark). We replace struct chunk on tagging /
 * untagging, the mark is stable as long as there is chunk attached. The
 * association between mark and chunk is protected by hash_lock and
 * audit_tree_group->mark_mutex. Thus as long as we hold
 * audit_tree_group->mark_mutex and check that the mark is alive by
 * FSNOTIFY_MARK_FLAG_ATTACHED flag check, we are sure the mark points to
 * the current chunk.
 *
 * Rules have pointer to struct audit_tree.
 * Rules have struct list_head rlist forming a list of rules over
 * the same tree.
 * References to struct chunk are collected at audit_inode{,_child}()
 * time and used in AUDIT_TREE rule matching.
 * These references are dropped at the same time we are calling
 * audit_free_names(), etc.
 *
 * Cyclic lists galore:
 * tree.chunks anchors chunk.owners[].list			hash_lock
 * tree.rules anchors rule.rlist				audit_filter_mutex
 * chunk.trees anchors tree.same_root				hash_lock
 * chunk.hash is a hash with middle bits of watch.inode as
 * a hash function.						RCU, hash_lock
 *
 * tree is refcounted; one reference for "some rules on rules_list refer to
 * it", one for each chunk with pointer to it.
 *
 * chunk is refcounted by embedded .refs. Mark associated with the chunk holds
 * one chunk reference. This reference is dropped either when a mark is going
 * to be freed (corresponding inode goes away) or when chunk attached to the
 * mark gets replaced. This reference must be dropped using
 * audit_mark_put_chunk() to make sure the reference is dropped only after RCU
 * grace period as it protects RCU readers of the hash table.
 *
 * node.index allows to get from node.list to containing chunk.
 * MSB of that sucker is stolen to mark taggings that we might have to
 * revert - several operations have very unpleasant cleanup logics and
 * that makes a difference.  Some.
 */

static struct fsnotify_group *audit_tree_group;
static struct kmem_cache *audit_tree_mark_cachep __read_mostly;

static struct audit_tree *alloc_tree(const char *s)
{
	struct audit_tree *tree;

	tree = kmalloc(sizeof(struct audit_tree) + strlen(s) + 1, GFP_KERNEL);
	if (tree) {
		refcount_set(&tree->count, 1);
		tree->goner = 0;
		INIT_LIST_HEAD(&tree->chunks);
		INIT_LIST_HEAD(&tree->rules);
		INIT_LIST_HEAD(&tree->list);
		INIT_LIST_HEAD(&tree->same_root);
		tree->root = NULL;
		strcpy(tree->pathname, s);
	}
	return tree;
}

static inline void get_tree(struct audit_tree *tree)
{
	refcount_inc(&tree->count);
}

static inline void put_tree(struct audit_tree *tree)
{
	if (refcount_dec_and_test(&tree->count))
		kfree_rcu(tree, head);
}

/* to avoid bringing the entire thing in audit.h */
const char *audit_tree_path(struct audit_tree *tree)
{
	return tree->pathname;
}

static void free_chunk(struct audit_chunk *chunk)
{
	int i;

	for (i = 0; i < chunk->count; i++) {
		if (chunk->owners[i].owner)
			put_tree(chunk->owners[i].owner);
	}
	kfree(chunk);
}

void audit_put_chunk(struct audit_chunk *chunk)
{
	if (atomic_long_dec_and_test(&chunk->refs))
		free_chunk(chunk);
}

static void __put_chunk(struct rcu_head *rcu)
{
	struct audit_chunk *chunk = container_of(rcu, struct audit_chunk, head);
	audit_put_chunk(chunk);
}

/*
 * Drop reference to the chunk that was held by the mark. This is the reference
 * that gets dropped after we've removed the chunk from the hash table and we
 * use it to make sure chunk cannot be freed before RCU grace period expires.
 */
static void audit_mark_put_chunk(struct audit_chunk *chunk)
{
	call_rcu(&chunk->head, __put_chunk);
}

static inline struct audit_tree_mark *audit_mark(struct fsnotify_mark *mark)
{
	return container_of(mark, struct audit_tree_mark, mark);
}

static struct audit_chunk *mark_chunk(struct fsnotify_mark *mark)
{
	return audit_mark(mark)->chunk;
}

static void audit_tree_destroy_watch(struct fsnotify_mark *mark)
{
	kmem_cache_free(audit_tree_mark_cachep, audit_mark(mark));
}

static struct fsnotify_mark *alloc_mark(void)
{
	struct audit_tree_mark *amark;

	amark = kmem_cache_zalloc(audit_tree_mark_cachep, GFP_KERNEL);
	if (!amark)
		return NULL;
	fsnotify_init_mark(&amark->mark, audit_tree_group);
	amark->mark.mask = FS_IN_IGNORED;
	return &amark->mark;
}

static struct audit_chunk *alloc_chunk(int count)
{
	struct audit_chunk *chunk;
	int i;

	chunk = kzalloc(struct_size(chunk, owners, count), GFP_KERNEL);
	if (!chunk)
		return NULL;

	INIT_LIST_HEAD(&chunk->hash);
	INIT_LIST_HEAD(&chunk->trees);
	chunk->count = count;
	atomic_long_set(&chunk->refs, 1);
	for (i = 0; i < count; i++) {
		INIT_LIST_HEAD(&chunk->owners[i].list);
		chunk->owners[i].index = i;
	}
	return chunk;
}

enum {HASH_SIZE = 128};
static struct list_head chunk_hash_heads[HASH_SIZE];
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(hash_lock);

/* Function to return search key in our hash from inode. */
static unsigned long inode_to_key(const struct inode *inode)
{
	/* Use address pointed to by connector->obj as the key */
	return (unsigned long)&inode->i_fsnotify_marks;
}

static inline struct list_head *chunk_hash(unsigned long key)
{
	unsigned long n = key / L1_CACHE_BYTES;
	return chunk_hash_heads + n % HASH_SIZE;
}

/* hash_lock & mark->group->mark_mutex is held by caller */
static void insert_hash(struct audit_chunk *chunk)
{
	struct list_head *list;

	/*
	 * Make sure chunk is fully initialized before making it visible in the
	 * hash. Pairs with a data dependency barrier in READ_ONCE() in
	 * audit_tree_lookup().
	 */
	smp_wmb();
	WARN_ON_ONCE(!chunk->key);
	list = chunk_hash(chunk->key);
	list_add_rcu(&chunk->hash, list);
}

/* called under rcu_read_lock */
struct audit_chunk *audit_tree_lookup(const struct inode *inode)
{
	unsigned long key = inode_to_key(inode);
	struct list_head *list = chunk_hash(key);
	struct audit_chunk *p;

	list_for_each_entry_rcu(p, list, hash) {
		/*
		 * We use a data dependency barrier in READ_ONCE() to make sure
		 * the chunk we see is fully initialized.
		 */
		if (READ_ONCE(p->key) == key) {
			atomic_long_inc(&p->refs);
			return p;
		}
	}
	return NULL;
}

bool audit_tree_match(struct audit_chunk *chunk, struct audit_tree *tree)
{
	int n;
	for (n = 0; n < chunk->count; n++)
		if (chunk->owners[n].owner == tree)
			return true;
	return false;
}

/* tagging and untagging inodes with trees */

static struct audit_chunk *find_chunk(struct node *p)
{
	int index = p->index & ~(1U<<31);
	p -= index;
	return container_of(p, struct audit_chunk, owners[0]);
}

static void replace_mark_chunk(struct fsnotify_mark *mark,
			       struct audit_chunk *chunk)
{
	struct audit_chunk *old;

	assert_spin_locked(&hash_lock);
	old = mark_chunk(mark);
	audit_mark(mark)->chunk = chunk;
	if (chunk)
		chunk->mark = mark;
	if (old)
		old->mark = NULL;
}

static void replace_chunk(struct audit_chunk *new, struct audit_chunk *old)
{
	struct audit_tree *owner;
	int i, j;

	new->key = old->key;
	list_splice_init(&old->trees, &new->trees);
	list_for_each_entry(owner, &new->trees, same_root)
		owner->root = new;
	for (i = j = 0; j < old->count; i++, j++) {
		if (!old->owners[j].owner) {
			i--;
			continue;
		}
		owner = old->owners[j].owner;
		new->owners[i].owner = owner;
		new->owners[i].index = old->owners[j].index - j + i;
		if (!owner) /* result of earlier fallback */
			continue;
		get_tree(owner);
		list_replace_init(&old->owners[j].list, &new->owners[i].list);
	}
	replace_mark_chunk(old->mark, new);
	/*
	 * Make sure chunk is fully initialized before making it visible in the
	 * hash. Pairs with a data dependency barrier in READ_ONCE() in
	 * audit_tree_lookup().
	 */
	smp_wmb();
	list_replace_rcu(&old->hash, &new->hash);
}

static void remove_chunk_node(struct audit_chunk *chunk, struct node *p)
{
	struct audit_tree *owner = p->owner;

	if (owner->root == chunk) {
		list_del_init(&owner->same_root);
		owner->root = NULL;
	}
	list_del_init(&p->list);
	p->owner = NULL;
	put_tree(owner);
}

static int chunk_count_trees(struct audit_chunk *chunk)
{
	int i;
	int ret = 0;

	for (i = 0; i < chunk->count; i++)
		if (chunk->owners[i].owner)
			ret++;
	return ret;
}

static void untag_chunk(struct audit_chunk *chunk, struct fsnotify_mark *mark)
{
	struct audit_chunk *new;
	int size;

	mutex_lock(&audit_tree_group->mark_mutex);
	/*
	 * mark_mutex stabilizes chunk attached to the mark so we can check
	 * whether it didn't change while we've dropped hash_lock.
	 */
	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) ||
	    mark_chunk(mark) != chunk)
		goto out_mutex;

	size = chunk_count_trees(chunk);
	if (!size) {
		spin_lock(&hash_lock);
		list_del_init(&chunk->trees);
		list_del_rcu(&chunk->hash);
		replace_mark_chunk(mark, NULL);
		spin_unlock(&hash_lock);
		fsnotify_detach_mark(mark);
		mutex_unlock(&audit_tree_group->mark_mutex);
		audit_mark_put_chunk(chunk);
		fsnotify_free_mark(mark);
		return;
	}

	new = alloc_chunk(size);
	if (!new)
		goto out_mutex;

	spin_lock(&hash_lock);
	/*
	 * This has to go last when updating chunk as once replace_chunk() is
	 * called, new RCU readers can see the new chunk.
	 */
	replace_chunk(new, chunk);
	spin_unlock(&hash_lock);
	mutex_unlock(&audit_tree_group->mark_mutex);
	audit_mark_put_chunk(chunk);
	return;

out_mutex:
	mutex_unlock(&audit_tree_group->mark_mutex);
}

/* Call with group->mark_mutex held, releases it */
static int create_chunk(struct inode *inode, struct audit_tree *tree)
{
	struct fsnotify_mark *mark;
	struct audit_chunk *chunk = alloc_chunk(1);

	if (!chunk) {
		mutex_unlock(&audit_tree_group->mark_mutex);
		return -ENOMEM;
	}

	mark = alloc_mark();
	if (!mark) {
		mutex_unlock(&audit_tree_group->mark_mutex);
		kfree(chunk);
		return -ENOMEM;
	}

	if (fsnotify_add_inode_mark_locked(mark, inode, 0)) {
		mutex_unlock(&audit_tree_group->mark_mutex);
		fsnotify_put_mark(mark);
		kfree(chunk);
		return -ENOSPC;
	}

	spin_lock(&hash_lock);
	if (tree->goner) {
		spin_unlock(&hash_lock);
		fsnotify_detach_mark(mark);
		mutex_unlock(&audit_tree_group->mark_mutex);
		fsnotify_free_mark(mark);
		fsnotify_put_mark(mark);
		kfree(chunk);
		return 0;
	}
	replace_mark_chunk(mark, chunk);
	chunk->owners[0].index = (1U << 31);
	chunk->owners[0].owner = tree;
	get_tree(tree);
	list_add(&chunk->owners[0].list, &tree->chunks);
	if (!tree->root) {
		tree->root = chunk;
		list_add(&tree->same_root, &chunk->trees);
	}
	chunk->key = inode_to_key(inode);
	/*
	 * Inserting into the hash table has to go last as once we do that RCU
	 * readers can see the chunk.
	 */
	insert_hash(chunk);
	spin_unlock(&hash_lock);
	mutex_unlock(&audit_tree_group->mark_mutex);
	/*
	 * Drop our initial reference. When mark we point to is getting freed,
	 * we get notification through ->freeing_mark callback and cleanup
	 * chunk pointing to this mark.
	 */
	fsnotify_put_mark(mark);
	return 0;
}

/* the first tagged inode becomes root of tree */
static int tag_chunk(struct inode *inode, struct audit_tree *tree)
{
	struct fsnotify_mark *mark;
	struct audit_chunk *chunk, *old;
	struct node *p;
	int n;

	mutex_lock(&audit_tree_group->mark_mutex);
	mark = fsnotify_find_mark(&inode->i_fsnotify_marks, audit_tree_group);
	if (!mark)
		return create_chunk(inode, tree);

	/*
	 * Found mark is guaranteed to be attached and mark_mutex protects mark
	 * from getting detached and thus it makes sure there is chunk attached
	 * to the mark.
	 */
	/* are we already there? */
	spin_lock(&hash_lock);
	old = mark_chunk(mark);
	for (n = 0; n < old->count; n++) {
		if (old->owners[n].owner == tree) {
			spin_unlock(&hash_lock);
			mutex_unlock(&audit_tree_group->mark_mutex);
			fsnotify_put_mark(mark);
			return 0;
		}
	}
	spin_unlock(&hash_lock);

	chunk = alloc_chunk(old->count + 1);
	if (!chunk) {
		mutex_unlock(&audit_tree_group->mark_mutex);
		fsnotify_put_mark(mark);
		return -ENOMEM;
	}

	spin_lock(&hash_lock);
	if (tree->goner) {
		spin_unlock(&hash_lock);
		mutex_unlock(&audit_tree_group->mark_mutex);
		fsnotify_put_mark(mark);
		kfree(chunk);
		return 0;
	}
	p = &chunk->owners[chunk->count - 1];
	p->index = (chunk->count - 1) | (1U<<31);
	p->owner = tree;
	get_tree(tree);
	list_add(&p->list, &tree->chunks);
	if (!tree->root) {
		tree->root = chunk;
		list_add(&tree->same_root, &chunk->trees);
	}
	/*
	 * This has to go last when updating chunk as once replace_chunk() is
	 * called, new RCU readers can see the new chunk.
	 */
	replace_chunk(chunk, old);
	spin_unlock(&hash_lock);
	mutex_unlock(&audit_tree_group->mark_mutex);
	fsnotify_put_mark(mark); /* pair to fsnotify_find_mark */
	audit_mark_put_chunk(old);

	return 0;
}

static void audit_tree_log_remove_rule(struct audit_context *context,
				       struct audit_krule *rule)
{
	struct audit_buffer *ab;

	if (!audit_enabled)
		return;
	ab = audit_log_start(context, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
	if (unlikely(!ab))
		return;
	audit_log_format(ab, "op=remove_rule dir=");
	audit_log_untrustedstring(ab, rule->tree->pathname);
	audit_log_key(ab, rule->filterkey);
	audit_log_format(ab, " list=%d res=1", rule->listnr);
	audit_log_end(ab);
}

static void kill_rules(struct audit_context *context, struct audit_tree *tree)
{
	struct audit_krule *rule, *next;
	struct audit_entry *entry;

	list_for_each_entry_safe(rule, next, &tree->rules, rlist) {
		entry = container_of(rule, struct audit_entry, rule);

		list_del_init(&rule->rlist);
		if (rule->tree) {
			/* not a half-baked one */
			audit_tree_log_remove_rule(context, rule);
			if (entry->rule.exe)
				audit_remove_mark(entry->rule.exe);
			rule->tree = NULL;
			list_del_rcu(&entry->list);
			list_del(&entry->rule.list);
			call_rcu(&entry->rcu, audit_free_rule_rcu);
		}
	}
}

/*
 * Remove tree from chunks. If 'tagged' is set, remove tree only from tagged
 * chunks. The function expects tagged chunks are all at the beginning of the
 * chunks list.
 */
static void prune_tree_chunks(struct audit_tree *victim, bool tagged)
{
	spin_lock(&hash_lock);
	while (!list_empty(&victim->chunks)) {
		struct node *p;
		struct audit_chunk *chunk;
		struct fsnotify_mark *mark;

		p = list_first_entry(&victim->chunks, struct node, list);
		/* have we run out of marked? */
		if (tagged && !(p->index & (1U<<31)))
			break;
		chunk = find_chunk(p);
		mark = chunk->mark;
		remove_chunk_node(chunk, p);
		/* Racing with audit_tree_freeing_mark()? */
		if (!mark)
			continue;
		fsnotify_get_mark(mark);
		spin_unlock(&hash_lock);

		untag_chunk(chunk, mark);
		fsnotify_put_mark(mark);

		spin_lock(&hash_lock);
	}
	spin_unlock(&hash_lock);
	put_tree(victim);
}

/*
 * finish killing struct audit_tree
 */
static void prune_one(struct audit_tree *victim)
{
	prune_tree_chunks(victim, false);
}

/* trim the uncommitted chunks from tree */

static void trim_marked(struct audit_tree *tree)
{
	struct list_head *p, *q;
	spin_lock(&hash_lock);
	if (tree->goner) {
		spin_unlock(&hash_lock);
		return;
	}
	/* reorder */
	for (p = tree->chunks.next; p != &tree->chunks; p = q) {
		struct node *node = list_entry(p, struct node, list);
		q = p->next;
		if (node->index & (1U<<31)) {
			list_del_init(p);
			list_add(p, &tree->chunks);
		}
	}
	spin_unlock(&hash_lock);

	prune_tree_chunks(tree, true);

	spin_lock(&hash_lock);
	if (!tree->root && !tree->goner) {
		tree->goner = 1;
		spin_unlock(&hash_lock);
		mutex_lock(&audit_filter_mutex);
		kill_rules(audit_context(), tree);
		list_del_init(&tree->list);
		mutex_unlock(&audit_filter_mutex);
		prune_one(tree);
	} else {
		spin_unlock(&hash_lock);
	}
}

static void audit_schedule_prune(void);

/* called with audit_filter_mutex */
int audit_remove_tree_rule(struct audit_krule *rule)
{
	struct audit_tree *tree;
	tree = rule->tree;
	if (tree) {
		spin_lock(&hash_lock);
		list_del_init(&rule->rlist);
		if (list_empty(&tree->rules) && !tree->goner) {
			tree->root = NULL;
			list_del_init(&tree->same_root);
			tree->goner = 1;
			list_move(&tree->list, &prune_list);
			rule->tree = NULL;
			spin_unlock(&hash_lock);
			audit_schedule_prune();
			return 1;
		}
		rule->tree = NULL;
		spin_unlock(&hash_lock);
		return 1;
	}
	return 0;
}

static int compare_root(struct vfsmount *mnt, void *arg)
{
	return inode_to_key(d_backing_inode(mnt->mnt_root)) ==
	       (unsigned long)arg;
}

void audit_trim_trees(void)
{
	struct list_head cursor;

	mutex_lock(&audit_filter_mutex);
	list_add(&cursor, &tree_list);
	while (cursor.next != &tree_list) {
		struct audit_tree *tree;
		struct path path;
		struct vfsmount *root_mnt;
		struct node *node;
		int err;

		tree = container_of(cursor.next, struct audit_tree, list);
		get_tree(tree);
		list_del(&cursor);
		list_add(&cursor, &tree->list);
		mutex_unlock(&audit_filter_mutex);

		err = kern_path(tree->pathname, 0, &path);
		if (err)
			goto skip_it;

		root_mnt = collect_mounts(&path);
		path_put(&path);
		if (IS_ERR(root_mnt))
			goto skip_it;

		spin_lock(&hash_lock);
		list_for_each_entry(node, &tree->chunks, list) {
			struct audit_chunk *chunk = find_chunk(node);
			/* this could be NULL if the watch is dying else where... */
			node->index |= 1U<<31;
			if (iterate_mounts(compare_root,
					   (void *)(chunk->key),
					   root_mnt))
				node->index &= ~(1U<<31);
		}
		spin_unlock(&hash_lock);
		trim_marked(tree);
		drop_collected_mounts(root_mnt);
skip_it:
		put_tree(tree);
		mutex_lock(&audit_filter_mutex);
	}
	list_del(&cursor);
	mutex_unlock(&audit_filter_mutex);
}

int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op)
{

	if (pathname[0] != '/' ||
	    rule->listnr != AUDIT_FILTER_EXIT ||
	    op != Audit_equal ||
	    rule->inode_f || rule->watch || rule->tree)
		return -EINVAL;
	rule->tree = alloc_tree(pathname);
	if (!rule->tree)
		return -ENOMEM;
	return 0;
}

void audit_put_tree(struct audit_tree *tree)
{
	put_tree(tree);
}

static int tag_mount(struct vfsmount *mnt, void *arg)
{
	return tag_chunk(d_backing_inode(mnt->mnt_root), arg);
}

/*
 * That gets run when evict_chunk() ends up needing to kill audit_tree.
 * Runs from a separate thread.
 */
static int prune_tree_thread(void *unused)
{
	for (;;) {
		if (list_empty(&prune_list)) {
			set_current_state(TASK_INTERRUPTIBLE);
			schedule();
		}

		audit_ctl_lock();
		mutex_lock(&audit_filter_mutex);

		while (!list_empty(&prune_list)) {
			struct audit_tree *victim;

			victim = list_entry(prune_list.next,
					struct audit_tree, list);
			list_del_init(&victim->list);

			mutex_unlock(&audit_filter_mutex);

			prune_one(victim);

			mutex_lock(&audit_filter_mutex);
		}

		mutex_unlock(&audit_filter_mutex);
		audit_ctl_unlock();
	}
	return 0;
}

static int audit_launch_prune(void)
{
	if (prune_thread)
		return 0;
	prune_thread = kthread_run(prune_tree_thread, NULL,
				"audit_prune_tree");
	if (IS_ERR(prune_thread)) {
		pr_err("cannot start thread audit_prune_tree");
		prune_thread = NULL;
		return -ENOMEM;
	}
	return 0;
}

/* called with audit_filter_mutex */
int audit_add_tree_rule(struct audit_krule *rule)
{
	struct audit_tree *seed = rule->tree, *tree;
	struct path path;
	struct vfsmount *mnt;
	int err;

	rule->tree = NULL;
	list_for_each_entry(tree, &tree_list, list) {
		if (!strcmp(seed->pathname, tree->pathname)) {
			put_tree(seed);
			rule->tree = tree;
			list_add(&rule->rlist, &tree->rules);
			return 0;
		}
	}
	tree = seed;
	list_add(&tree->list, &tree_list);
	list_add(&rule->rlist, &tree->rules);
	/* do not set rule->tree yet */
	mutex_unlock(&audit_filter_mutex);

	if (unlikely(!prune_thread)) {
		err = audit_launch_prune();
		if (err)
			goto Err;
	}

	err = kern_path(tree->pathname, 0, &path);
	if (err)
		goto Err;
	mnt = collect_mounts(&path);
	path_put(&path);
	if (IS_ERR(mnt)) {
		err = PTR_ERR(mnt);
		goto Err;
	}

	get_tree(tree);
	err = iterate_mounts(tag_mount, tree, mnt);
	drop_collected_mounts(mnt);

	if (!err) {
		struct node *node;
		spin_lock(&hash_lock);
		list_for_each_entry(node, &tree->chunks, list)
			node->index &= ~(1U<<31);
		spin_unlock(&hash_lock);
	} else {
		trim_marked(tree);
		goto Err;
	}

	mutex_lock(&audit_filter_mutex);
	if (list_empty(&rule->rlist)) {
		put_tree(tree);
		return -ENOENT;
	}
	rule->tree = tree;
	put_tree(tree);

	return 0;
Err:
	mutex_lock(&audit_filter_mutex);
	list_del_init(&tree->list);
	list_del_init(&tree->rules);
	put_tree(tree);
	return err;
}

int audit_tag_tree(char *old, char *new)
{
	struct list_head cursor, barrier;
	int failed = 0;
	struct path path1, path2;
	struct vfsmount *tagged;
	int err;

	err = kern_path(new, 0, &path2);
	if (err)
		return err;
	tagged = collect_mounts(&path2);
	path_put(&path2);
	if (IS_ERR(tagged))
		return PTR_ERR(tagged);

	err = kern_path(old, 0, &path1);
	if (err) {
		drop_collected_mounts(tagged);
		return err;
	}

	mutex_lock(&audit_filter_mutex);
	list_add(&barrier, &tree_list);
	list_add(&cursor, &barrier);

	while (cursor.next != &tree_list) {
		struct audit_tree *tree;
		int good_one = 0;

		tree = container_of(cursor.next, struct audit_tree, list);
		get_tree(tree);
		list_del(&cursor);
		list_add(&cursor, &tree->list);
		mutex_unlock(&audit_filter_mutex);

		err = kern_path(tree->pathname, 0, &path2);
		if (!err) {
			good_one = path_is_under(&path1, &path2);
			path_put(&path2);
		}

		if (!good_one) {
			put_tree(tree);
			mutex_lock(&audit_filter_mutex);
			continue;
		}

		failed = iterate_mounts(tag_mount, tree, tagged);
		if (failed) {
			put_tree(tree);
			mutex_lock(&audit_filter_mutex);
			break;
		}

		mutex_lock(&audit_filter_mutex);
		spin_lock(&hash_lock);
		if (!tree->goner) {
			list_del(&tree->list);
			list_add(&tree->list, &tree_list);
		}
		spin_unlock(&hash_lock);
		put_tree(tree);
	}

	while (barrier.prev != &tree_list) {
		struct audit_tree *tree;

		tree = container_of(barrier.prev, struct audit_tree, list);
		get_tree(tree);
		list_del(&tree->list);
		list_add(&tree->list, &barrier);
		mutex_unlock(&audit_filter_mutex);

		if (!failed) {
			struct node *node;
			spin_lock(&hash_lock);
			list_for_each_entry(node, &tree->chunks, list)
				node->index &= ~(1U<<31);
			spin_unlock(&hash_lock);
		} else {
			trim_marked(tree);
		}

		put_tree(tree);
		mutex_lock(&audit_filter_mutex);
	}
	list_del(&barrier);
	list_del(&cursor);
	mutex_unlock(&audit_filter_mutex);
	path_put(&path1);
	drop_collected_mounts(tagged);
	return failed;
}


static void audit_schedule_prune(void)
{
	wake_up_process(prune_thread);
}

/*
 * ... and that one is done if evict_chunk() decides to delay until the end
 * of syscall.  Runs synchronously.
 */
void audit_kill_trees(struct audit_context *context)
{
	struct list_head *list = &context->killed_trees;

	audit_ctl_lock();
	mutex_lock(&audit_filter_mutex);

	while (!list_empty(list)) {
		struct audit_tree *victim;

		victim = list_entry(list->next, struct audit_tree, list);
		kill_rules(context, victim);
		list_del_init(&victim->list);

		mutex_unlock(&audit_filter_mutex);

		prune_one(victim);

		mutex_lock(&audit_filter_mutex);
	}

	mutex_unlock(&audit_filter_mutex);
	audit_ctl_unlock();
}

/*
 *  Here comes the stuff asynchronous to auditctl operations
 */

static void evict_chunk(struct audit_chunk *chunk)
{
	struct audit_tree *owner;
	struct list_head *postponed = audit_killed_trees();
	int need_prune = 0;
	int n;

	mutex_lock(&audit_filter_mutex);
	spin_lock(&hash_lock);
	while (!list_empty(&chunk->trees)) {
		owner = list_entry(chunk->trees.next,
				   struct audit_tree, same_root);
		owner->goner = 1;
		owner->root = NULL;
		list_del_init(&owner->same_root);
		spin_unlock(&hash_lock);
		if (!postponed) {
			kill_rules(audit_context(), owner);
			list_move(&owner->list, &prune_list);
			need_prune = 1;
		} else {
			list_move(&owner->list, postponed);
		}
		spin_lock(&hash_lock);
	}
	list_del_rcu(&chunk->hash);
	for (n = 0; n < chunk->count; n++)
		list_del_init(&chunk->owners[n].list);
	spin_unlock(&hash_lock);
	mutex_unlock(&audit_filter_mutex);
	if (need_prune)
		audit_schedule_prune();
}

static int audit_tree_handle_event(struct fsnotify_group *group,
				   struct inode *to_tell,
				   u32 mask, const void *data, int data_type,
				   const struct qstr *file_name, u32 cookie,
				   struct fsnotify_iter_info *iter_info)
{
	return 0;
}

static void audit_tree_freeing_mark(struct fsnotify_mark *mark,
				    struct fsnotify_group *group)
{
	struct audit_chunk *chunk;

	mutex_lock(&mark->group->mark_mutex);
	spin_lock(&hash_lock);
	chunk = mark_chunk(mark);
	replace_mark_chunk(mark, NULL);
	spin_unlock(&hash_lock);
	mutex_unlock(&mark->group->mark_mutex);
	if (chunk) {
		evict_chunk(chunk);
		audit_mark_put_chunk(chunk);
	}

	/*
	 * We are guaranteed to have at least one reference to the mark from
	 * either the inode or the caller of fsnotify_destroy_mark().
	 */
	BUG_ON(refcount_read(&mark->refcnt) < 1);
}

static const struct fsnotify_ops audit_tree_ops = {
	.handle_event = audit_tree_handle_event,
	.freeing_mark = audit_tree_freeing_mark,
	.free_mark = audit_tree_destroy_watch,
};

static int __init audit_tree_init(void)
{
	int i;

	audit_tree_mark_cachep = KMEM_CACHE(audit_tree_mark, SLAB_PANIC);

	audit_tree_group = fsnotify_alloc_group(&audit_tree_ops);
	if (IS_ERR(audit_tree_group))
		audit_panic("cannot initialize fsnotify group for rectree watches");

	for (i = 0; i < HASH_SIZE; i++)
		INIT_LIST_HEAD(&chunk_hash_heads[i]);

	return 0;
}
__initcall(audit_tree_init);