summaryrefslogtreecommitdiff
path: root/kernel/auditsc.c
blob: 4193811d4fe1ea5b008d10768cf3469abd11896a (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
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
/* auditsc.c -- System-call auditing support
 * Handles all system-call specific auditing features.
 *
 * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
 * All Rights Reserved.
 *
 * 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.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 * Written by Rickard E. (Rik) Faith <faith@redhat.com>
 *
 * Many of the ideas implemented here are from Stephen C. Tweedie,
 * especially the idea of avoiding a copy by using getname.
 *
 * The method for actual interception of syscall entry and exit (not in
 * this file -- see entry.S) is based on a GPL'd patch written by
 * okir@suse.de and Copyright 2003 SuSE Linux AG.
 *
 */

#include <linux/init.h>
#include <asm/atomic.h>
#include <asm/types.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/socket.h>
#include <linux/audit.h>
#include <linux/personality.h>
#include <linux/time.h>
#include <asm/unistd.h>

/* 0 = no checking
   1 = put_count checking
   2 = verbose put_count checking
*/
#define AUDIT_DEBUG 0

/* No syscall auditing will take place unless audit_enabled != 0. */
extern int audit_enabled;

/* AUDIT_NAMES is the number of slots we reserve in the audit_context
 * for saving names from getname(). */
#define AUDIT_NAMES    20

/* AUDIT_NAMES_RESERVED is the number of slots we reserve in the
 * audit_context from being used for nameless inodes from
 * path_lookup. */
#define AUDIT_NAMES_RESERVED 7

/* At task start time, the audit_state is set in the audit_context using
   a per-task filter.  At syscall entry, the audit_state is augmented by
   the syscall filter. */
enum audit_state {
	AUDIT_DISABLED,		/* Do not create per-task audit_context.
				 * No syscall-specific audit records can
				 * be generated. */
	AUDIT_SETUP_CONTEXT,	/* Create the per-task audit_context,
				 * but don't necessarily fill it in at
				 * syscall entry time (i.e., filter
				 * instead). */
	AUDIT_BUILD_CONTEXT,	/* Create the per-task audit_context,
				 * and always fill it in at syscall
				 * entry time.  This makes a full
				 * syscall record available if some
				 * other part of the kernel decides it
				 * should be recorded. */
	AUDIT_RECORD_CONTEXT	/* Create the per-task audit_context,
				 * always fill it in at syscall entry
				 * time, and always write out the audit
				 * record at syscall exit time.  */
};

/* When fs/namei.c:getname() is called, we store the pointer in name and
 * we don't let putname() free it (instead we free all of the saved
 * pointers at syscall exit time).
 *
 * Further, in fs/namei.c:path_lookup() we store the inode and device. */
struct audit_names {
	const char	*name;
	unsigned long	ino;
	dev_t		dev;
	umode_t		mode;
	uid_t		uid;
	gid_t		gid;
	dev_t		rdev;
};

struct audit_aux_data {
	struct audit_aux_data	*next;
	int			type;
};

#define AUDIT_AUX_IPCPERM	0

struct audit_aux_data_ipcctl {
	struct audit_aux_data	d;
	struct ipc_perm		p;
	unsigned long		qbytes;
	uid_t			uid;
	gid_t			gid;
	mode_t			mode;
};

struct audit_aux_data_socketcall {
	struct audit_aux_data	d;
	int			nargs;
	unsigned long		args[0];
};

struct audit_aux_data_sockaddr {
	struct audit_aux_data	d;
	int			len;
	char			a[0];
};

struct audit_aux_data_path {
	struct audit_aux_data	d;
	struct dentry		*dentry;
	struct vfsmount		*mnt;
};

/* The per-task audit context. */
struct audit_context {
	int		    in_syscall;	/* 1 if task is in a syscall */
	enum audit_state    state;
	unsigned int	    serial;     /* serial number for record */
	struct timespec	    ctime;      /* time of syscall entry */
	uid_t		    loginuid;   /* login uid (identity) */
	int		    major;      /* syscall number */
	unsigned long	    argv[4];    /* syscall arguments */
	int		    return_valid; /* return code is valid */
	long		    return_code;/* syscall return code */
	int		    auditable;  /* 1 if record should be written */
	int		    name_count;
	struct audit_names  names[AUDIT_NAMES];
	struct audit_context *previous; /* For nested syscalls */
	struct audit_aux_data *aux;

				/* Save things to print about task_struct */
	pid_t		    pid;
	uid_t		    uid, euid, suid, fsuid;
	gid_t		    gid, egid, sgid, fsgid;
	unsigned long	    personality;
	int		    arch;

#if AUDIT_DEBUG
	int		    put_count;
	int		    ino_count;
#endif
};

				/* Public API */
/* There are three lists of rules -- one to search at task creation
 * time, one to search at syscall entry time, and another to search at
 * syscall exit time. */
static LIST_HEAD(audit_tsklist);
static LIST_HEAD(audit_entlist);
static LIST_HEAD(audit_extlist);

struct audit_entry {
	struct list_head  list;
	struct rcu_head   rcu;
	struct audit_rule rule;
};

extern int audit_pid;

/* Check to see if two rules are identical.  It is called from
 * audit_del_rule during AUDIT_DEL. */
static int audit_compare_rule(struct audit_rule *a, struct audit_rule *b)
{
	int i;

	if (a->flags != b->flags)
		return 1;

	if (a->action != b->action)
		return 1;

	if (a->field_count != b->field_count)
		return 1;

	for (i = 0; i < a->field_count; i++) {
		if (a->fields[i] != b->fields[i]
		    || a->values[i] != b->values[i])
			return 1;
	}

	for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
		if (a->mask[i] != b->mask[i])
			return 1;

	return 0;
}

/* Note that audit_add_rule and audit_del_rule are called via
 * audit_receive() in audit.c, and are protected by
 * audit_netlink_sem. */
static inline int audit_add_rule(struct audit_entry *entry,
				 struct list_head *list)
{
	if (entry->rule.flags & AUDIT_PREPEND) {
		entry->rule.flags &= ~AUDIT_PREPEND;
		list_add_rcu(&entry->list, list);
	} else {
		list_add_tail_rcu(&entry->list, list);
	}
	return 0;
}

static void audit_free_rule(struct rcu_head *head)
{
	struct audit_entry *e = container_of(head, struct audit_entry, rcu);
	kfree(e);
}

/* Note that audit_add_rule and audit_del_rule are called via
 * audit_receive() in audit.c, and are protected by
 * audit_netlink_sem. */
static inline int audit_del_rule(struct audit_rule *rule,
				 struct list_head *list)
{
	struct audit_entry  *e;

	/* Do not use the _rcu iterator here, since this is the only
	 * deletion routine. */
	list_for_each_entry(e, list, list) {
		if (!audit_compare_rule(rule, &e->rule)) {
			list_del_rcu(&e->list);
			call_rcu(&e->rcu, audit_free_rule);
			return 0;
		}
	}
	return -EFAULT;		/* No matching rule */
}

/* Copy rule from user-space to kernel-space.  Called during
 * AUDIT_ADD. */
static int audit_copy_rule(struct audit_rule *d, struct audit_rule *s)
{
	int i;

	if (s->action != AUDIT_NEVER
	    && s->action != AUDIT_POSSIBLE
	    && s->action != AUDIT_ALWAYS)
		return -1;
	if (s->field_count < 0 || s->field_count > AUDIT_MAX_FIELDS)
		return -1;

	d->flags	= s->flags;
	d->action	= s->action;
	d->field_count	= s->field_count;
	for (i = 0; i < d->field_count; i++) {
		d->fields[i] = s->fields[i];
		d->values[i] = s->values[i];
	}
	for (i = 0; i < AUDIT_BITMASK_SIZE; i++) d->mask[i] = s->mask[i];
	return 0;
}

int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
							uid_t loginuid)
{
	u32		   flags;
	struct audit_entry *entry;
	int		   err = 0;

	switch (type) {
	case AUDIT_LIST:
		/* The *_rcu iterators not needed here because we are
		   always called with audit_netlink_sem held. */
		list_for_each_entry(entry, &audit_tsklist, list)
			audit_send_reply(pid, seq, AUDIT_LIST, 0, 1,
					 &entry->rule, sizeof(entry->rule));
		list_for_each_entry(entry, &audit_entlist, list)
			audit_send_reply(pid, seq, AUDIT_LIST, 0, 1,
					 &entry->rule, sizeof(entry->rule));
		list_for_each_entry(entry, &audit_extlist, list)
			audit_send_reply(pid, seq, AUDIT_LIST, 0, 1,
					 &entry->rule, sizeof(entry->rule));
		audit_send_reply(pid, seq, AUDIT_LIST, 1, 1, NULL, 0);
		break;
	case AUDIT_ADD:
		if (!(entry = kmalloc(sizeof(*entry), GFP_KERNEL)))
			return -ENOMEM;
		if (audit_copy_rule(&entry->rule, data)) {
			kfree(entry);
			return -EINVAL;
		}
		flags = entry->rule.flags;
		if (!err && (flags & AUDIT_PER_TASK))
			err = audit_add_rule(entry, &audit_tsklist);
		if (!err && (flags & AUDIT_AT_ENTRY))
			err = audit_add_rule(entry, &audit_entlist);
		if (!err && (flags & AUDIT_AT_EXIT))
			err = audit_add_rule(entry, &audit_extlist);
		audit_log(NULL, AUDIT_CONFIG_CHANGE, 
				"auid %u added an audit rule\n", loginuid);
		break;
	case AUDIT_DEL:
		flags =((struct audit_rule *)data)->flags;
		if (!err && (flags & AUDIT_PER_TASK))
			err = audit_del_rule(data, &audit_tsklist);
		if (!err && (flags & AUDIT_AT_ENTRY))
			err = audit_del_rule(data, &audit_entlist);
		if (!err && (flags & AUDIT_AT_EXIT))
			err = audit_del_rule(data, &audit_extlist);
		audit_log(NULL, AUDIT_CONFIG_CHANGE,
				"auid %u removed an audit rule\n", loginuid);
		break;
	default:
		return -EINVAL;
	}

	return err;
}

/* Compare a task_struct with an audit_rule.  Return 1 on match, 0
 * otherwise. */
static int audit_filter_rules(struct task_struct *tsk,
			      struct audit_rule *rule,
			      struct audit_context *ctx,
			      enum audit_state *state)
{
	int i, j;

	for (i = 0; i < rule->field_count; i++) {
		u32 field  = rule->fields[i] & ~AUDIT_NEGATE;
		u32 value  = rule->values[i];
		int result = 0;

		switch (field) {
		case AUDIT_PID:
			result = (tsk->pid == value);
			break;
		case AUDIT_UID:
			result = (tsk->uid == value);
			break;
		case AUDIT_EUID:
			result = (tsk->euid == value);
			break;
		case AUDIT_SUID:
			result = (tsk->suid == value);
			break;
		case AUDIT_FSUID:
			result = (tsk->fsuid == value);
			break;
		case AUDIT_GID:
			result = (tsk->gid == value);
			break;
		case AUDIT_EGID:
			result = (tsk->egid == value);
			break;
		case AUDIT_SGID:
			result = (tsk->sgid == value);
			break;
		case AUDIT_FSGID:
			result = (tsk->fsgid == value);
			break;
		case AUDIT_PERS:
			result = (tsk->personality == value);
			break;
		case AUDIT_ARCH:
			if (ctx) 
				result = (ctx->arch == value);
			break;

		case AUDIT_EXIT:
			if (ctx && ctx->return_valid)
				result = (ctx->return_code == value);
			break;
		case AUDIT_SUCCESS:
			if (ctx && ctx->return_valid)
				result = (ctx->return_valid == AUDITSC_SUCCESS);
			break;
		case AUDIT_DEVMAJOR:
			if (ctx) {
				for (j = 0; j < ctx->name_count; j++) {
					if (MAJOR(ctx->names[j].dev)==value) {
						++result;
						break;
					}
				}
			}
			break;
		case AUDIT_DEVMINOR:
			if (ctx) {
				for (j = 0; j < ctx->name_count; j++) {
					if (MINOR(ctx->names[j].dev)==value) {
						++result;
						break;
					}
				}
			}
			break;
		case AUDIT_INODE:
			if (ctx) {
				for (j = 0; j < ctx->name_count; j++) {
					if (ctx->names[j].ino == value) {
						++result;
						break;
					}
				}
			}
			break;
		case AUDIT_LOGINUID:
			result = 0;
			if (ctx)
				result = (ctx->loginuid == value);
			break;
		case AUDIT_ARG0:
		case AUDIT_ARG1:
		case AUDIT_ARG2:
		case AUDIT_ARG3:
			if (ctx)
				result = (ctx->argv[field-AUDIT_ARG0]==value);
			break;
		}

		if (rule->fields[i] & AUDIT_NEGATE)
			result = !result;
		if (!result)
			return 0;
	}
	switch (rule->action) {
	case AUDIT_NEVER:    *state = AUDIT_DISABLED;	    break;
	case AUDIT_POSSIBLE: *state = AUDIT_BUILD_CONTEXT;  break;
	case AUDIT_ALWAYS:   *state = AUDIT_RECORD_CONTEXT; break;
	}
	return 1;
}

/* At process creation time, we can determine if system-call auditing is
 * completely disabled for this task.  Since we only have the task
 * structure at this point, we can only check uid and gid.
 */
static enum audit_state audit_filter_task(struct task_struct *tsk)
{
	struct audit_entry *e;
	enum audit_state   state;

	rcu_read_lock();
	list_for_each_entry_rcu(e, &audit_tsklist, list) {
		if (audit_filter_rules(tsk, &e->rule, NULL, &state)) {
			rcu_read_unlock();
			return state;
		}
	}
	rcu_read_unlock();
	return AUDIT_BUILD_CONTEXT;
}

/* At syscall entry and exit time, this filter is called if the
 * audit_state is not low enough that auditing cannot take place, but is
 * also not high enough that we already know we have to write an audit
 * record (i.e., the state is AUDIT_SETUP_CONTEXT or  AUDIT_BUILD_CONTEXT).
 */
static enum audit_state audit_filter_syscall(struct task_struct *tsk,
					     struct audit_context *ctx,
					     struct list_head *list)
{
	struct audit_entry *e;
	enum audit_state   state;
	int		   word = AUDIT_WORD(ctx->major);
	int		   bit  = AUDIT_BIT(ctx->major);

	rcu_read_lock();
	list_for_each_entry_rcu(e, list, list) {
		if ((e->rule.mask[word] & bit) == bit
 		    && audit_filter_rules(tsk, &e->rule, ctx, &state)) {
			rcu_read_unlock();
			return state;
		}
	}
	rcu_read_unlock();
	return AUDIT_BUILD_CONTEXT;
}

/* This should be called with task_lock() held. */
static inline struct audit_context *audit_get_context(struct task_struct *tsk,
						      int return_valid,
						      int return_code)
{
	struct audit_context *context = tsk->audit_context;

	if (likely(!context))
		return NULL;
	context->return_valid = return_valid;
	context->return_code  = return_code;

	if (context->in_syscall && !context->auditable) {
		enum audit_state state;
		state = audit_filter_syscall(tsk, context, &audit_extlist);
		if (state == AUDIT_RECORD_CONTEXT)
			context->auditable = 1;
	}

	context->pid = tsk->pid;
	context->uid = tsk->uid;
	context->gid = tsk->gid;
	context->euid = tsk->euid;
	context->suid = tsk->suid;
	context->fsuid = tsk->fsuid;
	context->egid = tsk->egid;
	context->sgid = tsk->sgid;
	context->fsgid = tsk->fsgid;
	context->personality = tsk->personality;
	tsk->audit_context = NULL;
	return context;
}

static inline void audit_free_names(struct audit_context *context)
{
	int i;

#if AUDIT_DEBUG == 2
	if (context->auditable
	    ||context->put_count + context->ino_count != context->name_count) {
		printk(KERN_ERR "audit.c:%d(:%d): major=%d in_syscall=%d"
		       " name_count=%d put_count=%d"
		       " ino_count=%d [NOT freeing]\n",
		       __LINE__,
		       context->serial, context->major, context->in_syscall,
		       context->name_count, context->put_count,
		       context->ino_count);
		for (i = 0; i < context->name_count; i++)
			printk(KERN_ERR "names[%d] = %p = %s\n", i,
			       context->names[i].name,
			       context->names[i].name);
		dump_stack();
		return;
	}
#endif
#if AUDIT_DEBUG
	context->put_count  = 0;
	context->ino_count  = 0;
#endif

	for (i = 0; i < context->name_count; i++)
		if (context->names[i].name)
			__putname(context->names[i].name);
	context->name_count = 0;
}

static inline void audit_free_aux(struct audit_context *context)
{
	struct audit_aux_data *aux;

	while ((aux = context->aux)) {
		if (aux->type == AUDIT_AVC_PATH) {
			struct audit_aux_data_path *axi = (void *)aux;
			dput(axi->dentry);
			mntput(axi->mnt);
		}
		context->aux = aux->next;
		kfree(aux);
	}
}

static inline void audit_zero_context(struct audit_context *context,
				      enum audit_state state)
{
	uid_t loginuid = context->loginuid;

	memset(context, 0, sizeof(*context));
	context->state      = state;
	context->loginuid   = loginuid;
}

static inline struct audit_context *audit_alloc_context(enum audit_state state)
{
	struct audit_context *context;

	if (!(context = kmalloc(sizeof(*context), GFP_KERNEL)))
		return NULL;
	audit_zero_context(context, state);
	return context;
}

/* Filter on the task information and allocate a per-task audit context
 * if necessary.  Doing so turns on system call auditing for the
 * specified task.  This is called from copy_process, so no lock is
 * needed. */
int audit_alloc(struct task_struct *tsk)
{
	struct audit_context *context;
	enum audit_state     state;

	if (likely(!audit_enabled))
		return 0; /* Return if not auditing. */

	state = audit_filter_task(tsk);
	if (likely(state == AUDIT_DISABLED))
		return 0;

	if (!(context = audit_alloc_context(state))) {
		audit_log_lost("out of memory in audit_alloc");
		return -ENOMEM;
	}

				/* Preserve login uid */
	context->loginuid = -1;
	if (current->audit_context)
		context->loginuid = current->audit_context->loginuid;

	tsk->audit_context  = context;
	set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
	return 0;
}

static inline void audit_free_context(struct audit_context *context)
{
	struct audit_context *previous;
	int		     count = 0;

	do {
		previous = context->previous;
		if (previous || (count &&  count < 10)) {
			++count;
			printk(KERN_ERR "audit(:%d): major=%d name_count=%d:"
			       " freeing multiple contexts (%d)\n",
			       context->serial, context->major,
			       context->name_count, count);
		}
		audit_free_names(context);
		audit_free_aux(context);
		kfree(context);
		context  = previous;
	} while (context);
	if (count >= 10)
		printk(KERN_ERR "audit: freed %d contexts\n", count);
}

static void audit_log_task_info(struct audit_buffer *ab)
{
	char name[sizeof(current->comm)];
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;

	get_task_comm(name, current);
	audit_log_format(ab, " comm=%s", name);

	if (!mm)
		return;

	down_read(&mm->mmap_sem);
	vma = mm->mmap;
	while (vma) {
		if ((vma->vm_flags & VM_EXECUTABLE) &&
		    vma->vm_file) {
			audit_log_d_path(ab, "exe=",
					 vma->vm_file->f_dentry,
					 vma->vm_file->f_vfsmnt);
			break;
		}
		vma = vma->vm_next;
	}
	up_read(&mm->mmap_sem);
}

static void audit_log_exit(struct audit_context *context)
{
	int i;
	struct audit_buffer *ab;

	ab = audit_log_start(context, AUDIT_SYSCALL);
	if (!ab)
		return;		/* audit_panic has been called */
	audit_log_format(ab, "syscall=%d", context->major);
	if (context->personality != PER_LINUX)
		audit_log_format(ab, " per=%lx", context->personality);
	audit_log_format(ab, " arch=%x", context->arch);
	if (context->return_valid)
		audit_log_format(ab, " success=%s exit=%ld", 
				 (context->return_valid==AUDITSC_SUCCESS)?"yes":"no",
				 context->return_code);
	audit_log_format(ab,
		  " a0=%lx a1=%lx a2=%lx a3=%lx items=%d"
		  " pid=%d auid=%u uid=%u gid=%u"
		  " euid=%u suid=%u fsuid=%u"
		  " egid=%u sgid=%u fsgid=%u",
		  context->argv[0],
		  context->argv[1],
		  context->argv[2],
		  context->argv[3],
		  context->name_count,
		  context->pid,
		  context->loginuid,
		  context->uid,
		  context->gid,
		  context->euid, context->suid, context->fsuid,
		  context->egid, context->sgid, context->fsgid);
	audit_log_task_info(ab);
	audit_log_end(ab);
	while (context->aux) {
		struct audit_aux_data *aux;

		aux = context->aux;

		ab = audit_log_start(context, aux->type);
		if (!ab)
			continue; /* audit_panic has been called */

		switch (aux->type) {
		case AUDIT_IPC: {
			struct audit_aux_data_ipcctl *axi = (void *)aux;
			audit_log_format(ab, 
					 " qbytes=%lx iuid=%u igid=%u mode=%x",
					 axi->qbytes, axi->uid, axi->gid, axi->mode);
			break; }

		case AUDIT_SOCKETCALL: {
			int i;
			struct audit_aux_data_socketcall *axs = (void *)aux;
			audit_log_format(ab, "nargs=%d", axs->nargs);
			for (i=0; i<axs->nargs; i++)
				audit_log_format(ab, " a%d=%lx", i, axs->args[i]);
			break; }

		case AUDIT_SOCKADDR: {
			struct audit_aux_data_sockaddr *axs = (void *)aux;

			audit_log_format(ab, "saddr=");
			audit_log_hex(ab, axs->a, axs->len);
			break; }

		case AUDIT_AVC_PATH: {
			struct audit_aux_data_path *axi = (void *)aux;
			audit_log_d_path(ab, "path=", axi->dentry, axi->mnt);
			dput(axi->dentry);
			mntput(axi->mnt);
			break; }

		}
		audit_log_end(ab);

		context->aux = aux->next;
		kfree(aux);
	}

	for (i = 0; i < context->name_count; i++) {
		ab = audit_log_start(context, AUDIT_PATH);
		if (!ab)
			continue; /* audit_panic has been called */
		audit_log_format(ab, "item=%d", i);
		if (context->names[i].name) {
			audit_log_format(ab, " name=");
			audit_log_untrustedstring(ab, context->names[i].name);
		}
		if (context->names[i].ino != (unsigned long)-1)
			audit_log_format(ab, " inode=%lu dev=%02x:%02x mode=%#o"
					     " ouid=%u ogid=%u rdev=%02x:%02x",
					 context->names[i].ino,
					 MAJOR(context->names[i].dev),
					 MINOR(context->names[i].dev),
					 context->names[i].mode,
					 context->names[i].uid,
					 context->names[i].gid,
					 MAJOR(context->names[i].rdev),
					 MINOR(context->names[i].rdev));
		audit_log_end(ab);
	}
}

/* Free a per-task audit context.  Called from copy_process and
 * __put_task_struct. */
void audit_free(struct task_struct *tsk)
{
	struct audit_context *context;

	task_lock(tsk);
	context = audit_get_context(tsk, 0, 0);
	task_unlock(tsk);

	if (likely(!context))
		return;

	/* Check for system calls that do not go through the exit
	 * function (e.g., exit_group), then free context block. */
	if (context->in_syscall && context->auditable && context->pid != audit_pid)
		audit_log_exit(context);

	audit_free_context(context);
}

/* Compute a serial number for the audit record.  Audit records are
 * written to user-space as soon as they are generated, so a complete
 * audit record may be written in several pieces.  The timestamp of the
 * record and this serial number are used by the user-space tools to
 * determine which pieces belong to the same audit record.  The
 * (timestamp,serial) tuple is unique for each syscall and is live from
 * syscall entry to syscall exit.
 *
 * Atomic values are only guaranteed to be 24-bit, so we count down.
 *
 * NOTE: Another possibility is to store the formatted records off the
 * audit context (for those records that have a context), and emit them
 * all at syscall exit.  However, this could delay the reporting of
 * significant errors until syscall exit (or never, if the system
 * halts). */
static inline unsigned int audit_serial(void)
{
	static atomic_t serial = ATOMIC_INIT(0xffffff);
	unsigned int a, b;

	do {
		a = atomic_read(&serial);
		if (atomic_dec_and_test(&serial))
			atomic_set(&serial, 0xffffff);
		b = atomic_read(&serial);
	} while (b != a - 1);

	return 0xffffff - b;
}

/* Fill in audit context at syscall entry.  This only happens if the
 * audit context was created when the task was created and the state or
 * filters demand the audit context be built.  If the state from the
 * per-task filter or from the per-syscall filter is AUDIT_RECORD_CONTEXT,
 * then the record will be written at syscall exit time (otherwise, it
 * will only be written if another part of the kernel requests that it
 * be written). */
void audit_syscall_entry(struct task_struct *tsk, int arch, int major,
			 unsigned long a1, unsigned long a2,
			 unsigned long a3, unsigned long a4)
{
	struct audit_context *context = tsk->audit_context;
	enum audit_state     state;

	BUG_ON(!context);

	/* This happens only on certain architectures that make system
	 * calls in kernel_thread via the entry.S interface, instead of
	 * with direct calls.  (If you are porting to a new
	 * architecture, hitting this condition can indicate that you
	 * got the _exit/_leave calls backward in entry.S.)
	 *
	 * i386     no
	 * x86_64   no
	 * ppc64    yes (see arch/ppc64/kernel/misc.S)
	 *
	 * This also happens with vm86 emulation in a non-nested manner
	 * (entries without exits), so this case must be caught.
	 */
	if (context->in_syscall) {
		struct audit_context *newctx;

#if defined(__NR_vm86) && defined(__NR_vm86old)
		/* vm86 mode should only be entered once */
		if (major == __NR_vm86 || major == __NR_vm86old)
			return;
#endif
#if AUDIT_DEBUG
		printk(KERN_ERR
		       "audit(:%d) pid=%d in syscall=%d;"
		       " entering syscall=%d\n",
		       context->serial, tsk->pid, context->major, major);
#endif
		newctx = audit_alloc_context(context->state);
		if (newctx) {
			newctx->previous   = context;
			context		   = newctx;
			tsk->audit_context = newctx;
		} else	{
			/* If we can't alloc a new context, the best we
			 * can do is to leak memory (any pending putname
			 * will be lost).  The only other alternative is
			 * to abandon auditing. */
			audit_zero_context(context, context->state);
		}
	}
	BUG_ON(context->in_syscall || context->name_count);

	if (!audit_enabled)
		return;

	context->arch	    = arch;
	context->major      = major;
	context->argv[0]    = a1;
	context->argv[1]    = a2;
	context->argv[2]    = a3;
	context->argv[3]    = a4;

	state = context->state;
	if (state == AUDIT_SETUP_CONTEXT || state == AUDIT_BUILD_CONTEXT)
		state = audit_filter_syscall(tsk, context, &audit_entlist);
	if (likely(state == AUDIT_DISABLED))
		return;

	context->serial     = audit_serial();
	context->ctime      = CURRENT_TIME;
	context->in_syscall = 1;
	context->auditable  = !!(state == AUDIT_RECORD_CONTEXT);
}

/* Tear down after system call.  If the audit context has been marked as
 * auditable (either because of the AUDIT_RECORD_CONTEXT state from
 * filtering, or because some other part of the kernel write an audit
 * message), then write out the syscall information.  In call cases,
 * free the names stored from getname(). */
void audit_syscall_exit(struct task_struct *tsk, int valid, long return_code)
{
	struct audit_context *context;

	get_task_struct(tsk);
	task_lock(tsk);
	context = audit_get_context(tsk, valid, return_code);
	task_unlock(tsk);

	/* Not having a context here is ok, since the parent may have
	 * called __put_task_struct. */
	if (likely(!context))
		return;

	if (context->in_syscall && context->auditable && context->pid != audit_pid)
		audit_log_exit(context);

	context->in_syscall = 0;
	context->auditable  = 0;

	if (context->previous) {
		struct audit_context *new_context = context->previous;
		context->previous  = NULL;
		audit_free_context(context);
		tsk->audit_context = new_context;
	} else {
		audit_free_names(context);
		audit_free_aux(context);
		audit_zero_context(context, context->state);
		tsk->audit_context = context;
	}
	put_task_struct(tsk);
}

/* Add a name to the list.  Called from fs/namei.c:getname(). */
void audit_getname(const char *name)
{
	struct audit_context *context = current->audit_context;

	if (!context || IS_ERR(name) || !name)
		return;

	if (!context->in_syscall) {
#if AUDIT_DEBUG == 2
		printk(KERN_ERR "%s:%d(:%d): ignoring getname(%p)\n",
		       __FILE__, __LINE__, context->serial, name);
		dump_stack();
#endif
		return;
	}
	BUG_ON(context->name_count >= AUDIT_NAMES);
	context->names[context->name_count].name = name;
	context->names[context->name_count].ino  = (unsigned long)-1;
	++context->name_count;
}

/* Intercept a putname request.  Called from
 * include/linux/fs.h:putname().  If we have stored the name from
 * getname in the audit context, then we delay the putname until syscall
 * exit. */
void audit_putname(const char *name)
{
	struct audit_context *context = current->audit_context;

	BUG_ON(!context);
	if (!context->in_syscall) {
#if AUDIT_DEBUG == 2
		printk(KERN_ERR "%s:%d(:%d): __putname(%p)\n",
		       __FILE__, __LINE__, context->serial, name);
		if (context->name_count) {
			int i;
			for (i = 0; i < context->name_count; i++)
				printk(KERN_ERR "name[%d] = %p = %s\n", i,
				       context->names[i].name,
				       context->names[i].name);
		}
#endif
		__putname(name);
	}
#if AUDIT_DEBUG
	else {
		++context->put_count;
		if (context->put_count > context->name_count) {
			printk(KERN_ERR "%s:%d(:%d): major=%d"
			       " in_syscall=%d putname(%p) name_count=%d"
			       " put_count=%d\n",
			       __FILE__, __LINE__,
			       context->serial, context->major,
			       context->in_syscall, name, context->name_count,
			       context->put_count);
			dump_stack();
		}
	}
#endif
}

/* Store the inode and device from a lookup.  Called from
 * fs/namei.c:path_lookup(). */
void audit_inode(const char *name, const struct inode *inode)
{
	int idx;
	struct audit_context *context = current->audit_context;

	if (!context->in_syscall)
		return;
	if (context->name_count
	    && context->names[context->name_count-1].name
	    && context->names[context->name_count-1].name == name)
		idx = context->name_count - 1;
	else if (context->name_count > 1
		 && context->names[context->name_count-2].name
		 && context->names[context->name_count-2].name == name)
		idx = context->name_count - 2;
	else {
		/* FIXME: how much do we care about inodes that have no
		 * associated name? */
		if (context->name_count >= AUDIT_NAMES - AUDIT_NAMES_RESERVED)
			return;
		idx = context->name_count++;
		context->names[idx].name = NULL;
#if AUDIT_DEBUG
		++context->ino_count;
#endif
	}
	context->names[idx].ino  = inode->i_ino;
	context->names[idx].dev	 = inode->i_sb->s_dev;
	context->names[idx].mode = inode->i_mode;
	context->names[idx].uid  = inode->i_uid;
	context->names[idx].gid  = inode->i_gid;
	context->names[idx].rdev = inode->i_rdev;
}

int audit_get_stamp(struct audit_context *ctx,
		     struct timespec *t, unsigned int *serial)
{
	if (ctx) {
		t->tv_sec  = ctx->ctime.tv_sec;
		t->tv_nsec = ctx->ctime.tv_nsec;
		*serial    = ctx->serial;
		ctx->auditable = 1;
		return 1;
	}
	return 0;
}

int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
{
	if (task->audit_context) {
		struct audit_buffer *ab;

		ab = audit_log_start(NULL, AUDIT_LOGIN);
		if (ab) {
			audit_log_format(ab, "login pid=%d uid=%u "
				"old auid=%u new auid=%u",
				task->pid, task->uid, 
				task->audit_context->loginuid, loginuid);
			audit_log_end(ab);
		}
		task->audit_context->loginuid = loginuid;
	}
	return 0;
}

uid_t audit_get_loginuid(struct audit_context *ctx)
{
	return ctx ? ctx->loginuid : -1;
}

int audit_ipc_perms(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
{
	struct audit_aux_data_ipcctl *ax;
	struct audit_context *context = current->audit_context;

	if (likely(!context))
		return 0;

	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
	if (!ax)
		return -ENOMEM;

	ax->qbytes = qbytes;
	ax->uid = uid;
	ax->gid = gid;
	ax->mode = mode;

	ax->d.type = AUDIT_IPC;
	ax->d.next = context->aux;
	context->aux = (void *)ax;
	return 0;
}

int audit_socketcall(int nargs, unsigned long *args)
{
	struct audit_aux_data_socketcall *ax;
	struct audit_context *context = current->audit_context;

	if (likely(!context))
		return 0;

	ax = kmalloc(sizeof(*ax) + nargs * sizeof(unsigned long), GFP_KERNEL);
	if (!ax)
		return -ENOMEM;

	ax->nargs = nargs;
	memcpy(ax->args, args, nargs * sizeof(unsigned long));

	ax->d.type = AUDIT_SOCKETCALL;
	ax->d.next = context->aux;
	context->aux = (void *)ax;
	return 0;
}

int audit_sockaddr(int len, void *a)
{
	struct audit_aux_data_sockaddr *ax;
	struct audit_context *context = current->audit_context;

	if (likely(!context))
		return 0;

	ax = kmalloc(sizeof(*ax) + len, GFP_KERNEL);
	if (!ax)
		return -ENOMEM;

	ax->len = len;
	memcpy(ax->a, a, len);

	ax->d.type = AUDIT_SOCKADDR;
	ax->d.next = context->aux;
	context->aux = (void *)ax;
	return 0;
}

int audit_avc_path(struct dentry *dentry, struct vfsmount *mnt)
{
	struct audit_aux_data_path *ax;
	struct audit_context *context = current->audit_context;

	if (likely(!context))
		return 0;

	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
	if (!ax)
		return -ENOMEM;

	ax->dentry = dget(dentry);
	ax->mnt = mntget(mnt);

	ax->d.type = AUDIT_AVC_PATH;
	ax->d.next = context->aux;
	context->aux = (void *)ax;
	return 0;
}

void audit_signal_info(int sig, struct task_struct *t)
{
	extern pid_t audit_sig_pid;
	extern uid_t audit_sig_uid;

	if (unlikely(audit_pid && t->pid == audit_pid)) {
		if (sig == SIGTERM || sig == SIGHUP) {
			struct audit_context *ctx = current->audit_context;
			audit_sig_pid = current->pid;
			if (ctx)
				audit_sig_uid = ctx->loginuid;
			else
				audit_sig_uid = current->uid;
		}
	}
}