aboutsummaryrefslogtreecommitdiff
path: root/kernel/audit.c
blob: ac26d4d960d3366d0473ede3533ab89446b75dc3 (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
/* audit.c -- Auditing support -*- linux-c -*-
 * Gateway between the kernel (e.g., selinux) and the user-space audit daemon.
 * System-call specific features have moved to auditsc.c
 *
 * 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>
 *
 * Goals: 1) Integrate fully with SELinux.
 *	  2) Minimal run-time overhead:
 *	     a) Minimal when syscall auditing is disabled (audit_enable=0).
 *	     b) Small when syscall auditing is enabled and no audit record
 *		is generated (defer as much work as possible to record
 *		generation time):
 *		i) context is allocated,
 *		ii) names from getname are stored without a copy, and
 *		iii) inode information stored from path_lookup.
 *	  3) Ability to disable syscall auditing at boot time (audit=0).
 *	  4) Usable by other parts of the kernel (if audit_log* is called,
 *	     then a syscall record will be generated automatically for the
 *	     current syscall).
 *	  5) Netlink interface to user-space.
 *	  6) Support low-overhead kernel-based filtering to minimize the
 *	     information that must be passed to user-space.
 *
 * Example user-space utilities: http://people.redhat.com/faith/audit/
 */

#include <linux/init.h>
#include <asm/atomic.h>
#include <asm/types.h>
#include <linux/mm.h>
#include <linux/module.h>

#include <linux/audit.h>

#include <net/sock.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>

/* No auditing will take place until audit_initialized != 0.
 * (Initialization happens after skb_init is called.) */
static int	audit_initialized;

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

/* Default state when kernel boots without any parameters. */
static int	audit_default;

/* If auditing cannot proceed, audit_failure selects what happens. */
static int	audit_failure = AUDIT_FAIL_PRINTK;

/* If audit records are to be written to the netlink socket, audit_pid
 * contains the (non-zero) pid. */
static int	audit_pid;

/* If audit_limit is non-zero, limit the rate of sending audit records
 * to that number per second.  This prevents DoS attacks, but results in
 * audit records being dropped. */
static int	audit_rate_limit;

/* Number of outstanding audit_buffers allowed. */
static int	audit_backlog_limit = 64;
static atomic_t	audit_backlog	    = ATOMIC_INIT(0);

/* Records can be lost in several ways:
   0) [suppressed in audit_alloc]
   1) out of memory in audit_log_start [kmalloc of struct audit_buffer]
   2) out of memory in audit_log_move [alloc_skb]
   3) suppressed due to audit_rate_limit
   4) suppressed due to audit_backlog_limit
*/
static atomic_t    audit_lost = ATOMIC_INIT(0);

/* The netlink socket. */
static struct sock *audit_sock;

/* There are two lists of audit buffers.  The txlist contains audit
 * buffers that cannot be sent immediately to the netlink device because
 * we are in an irq context (these are sent later in a tasklet).
 *
 * The second list is a list of pre-allocated audit buffers (if more
 * than AUDIT_MAXFREE are in use, the audit buffer is freed instead of
 * being placed on the freelist). */
static DEFINE_SPINLOCK(audit_txlist_lock);
static DEFINE_SPINLOCK(audit_freelist_lock);
static int	   audit_freelist_count = 0;
static LIST_HEAD(audit_txlist);
static LIST_HEAD(audit_freelist);

/* 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);

/* The netlink socket is only to be read by 1 CPU, which lets us assume
 * that list additions and deletions never happen simultaneiously in
 * auditsc.c */
static DECLARE_MUTEX(audit_netlink_sem);

/* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting
 * audit records.  Since printk uses a 1024 byte buffer, this buffer
 * should be at least that large. */
#define AUDIT_BUFSIZ 1024

/* AUDIT_MAXFREE is the number of empty audit_buffers we keep on the
 * audit_freelist.  Doing so eliminates many kmalloc/kfree calls. */
#define AUDIT_MAXFREE  (2*NR_CPUS)

/* The audit_buffer is used when formatting an audit record.  The caller
 * locks briefly to get the record off the freelist or to allocate the
 * buffer, and locks briefly to send the buffer to the netlink layer or
 * to place it on a transmit queue.  Multiple audit_buffers can be in
 * use simultaneously. */
struct audit_buffer {
	struct list_head     list;
	struct sk_buff_head  sklist;	/* formatted skbs ready to send */
	struct audit_context *ctx;	/* NULL or associated context */
	int		     len;	/* used area of tmp */
	char		     tmp[AUDIT_BUFSIZ];

				/* Pointer to header and contents */
	struct nlmsghdr      *nlh;
	int		     total;
	int		     type;
	int		     pid;
	int		     count; /* Times requeued */
};

void audit_set_type(struct audit_buffer *ab, int type)
{
	ab->type = type;
}

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

static void audit_log_end_irq(struct audit_buffer *ab);
static void audit_log_end_fast(struct audit_buffer *ab);

static void audit_panic(const char *message)
{
	switch (audit_failure)
	{
	case AUDIT_FAIL_SILENT:
		break;
	case AUDIT_FAIL_PRINTK:
		printk(KERN_ERR "audit: %s\n", message);
		break;
	case AUDIT_FAIL_PANIC:
		panic("audit: %s\n", message);
		break;
	}
}

static inline int audit_rate_check(void)
{
	static unsigned long	last_check = 0;
	static int		messages   = 0;
	static DEFINE_SPINLOCK(lock);
	unsigned long		flags;
	unsigned long		now;
	unsigned long		elapsed;
	int			retval	   = 0;

	if (!audit_rate_limit) return 1;

	spin_lock_irqsave(&lock, flags);
	if (++messages < audit_rate_limit) {
		retval = 1;
	} else {
		now     = jiffies;
		elapsed = now - last_check;
		if (elapsed > HZ) {
			last_check = now;
			messages   = 0;
			retval     = 1;
		}
	}
	spin_unlock_irqrestore(&lock, flags);

	return retval;
}

/* Emit at least 1 message per second, even if audit_rate_check is
 * throttling. */
void audit_log_lost(const char *message)
{
	static unsigned long	last_msg = 0;
	static DEFINE_SPINLOCK(lock);
	unsigned long		flags;
	unsigned long		now;
	int			print;

	atomic_inc(&audit_lost);

	print = (audit_failure == AUDIT_FAIL_PANIC || !audit_rate_limit);

	if (!print) {
		spin_lock_irqsave(&lock, flags);
		now = jiffies;
		if (now - last_msg > HZ) {
			print = 1;
			last_msg = now;
		}
		spin_unlock_irqrestore(&lock, flags);
	}

	if (print) {
		printk(KERN_WARNING
		       "audit: audit_lost=%d audit_backlog=%d"
		       " audit_rate_limit=%d audit_backlog_limit=%d\n",
		       atomic_read(&audit_lost),
		       atomic_read(&audit_backlog),
		       audit_rate_limit,
		       audit_backlog_limit);
		audit_panic(message);
	}

}

static int audit_set_rate_limit(int limit)
{
	int old		 = audit_rate_limit;
	audit_rate_limit = limit;
	audit_log(current->audit_context, "audit_rate_limit=%d old=%d",
		  audit_rate_limit, old);
	return old;
}

static int audit_set_backlog_limit(int limit)
{
	int old		 = audit_backlog_limit;
	audit_backlog_limit = limit;
	audit_log(current->audit_context, "audit_backlog_limit=%d old=%d",
		  audit_backlog_limit, old);
	return old;
}

static int audit_set_enabled(int state)
{
	int old		 = audit_enabled;
	if (state != 0 && state != 1)
		return -EINVAL;
	audit_enabled = state;
	audit_log(current->audit_context, "audit_enabled=%d old=%d",
		  audit_enabled, old);
	return old;
}

static int audit_set_failure(int state)
{
	int old		 = audit_failure;
	if (state != AUDIT_FAIL_SILENT
	    && state != AUDIT_FAIL_PRINTK
	    && state != AUDIT_FAIL_PANIC)
		return -EINVAL;
	audit_failure = state;
	audit_log(current->audit_context, "audit_failure=%d old=%d",
		  audit_failure, old);
	return old;
}

#ifdef CONFIG_NET
void audit_send_reply(int pid, int seq, int type, int done, int multi,
		      void *payload, int size)
{
	struct sk_buff	*skb;
	struct nlmsghdr	*nlh;
	int		len = NLMSG_SPACE(size);
	void		*data;
	int		flags = multi ? NLM_F_MULTI : 0;
	int		t     = done  ? NLMSG_DONE  : type;

	skb = alloc_skb(len, GFP_KERNEL);
	if (!skb)
		goto nlmsg_failure;

	nlh		 = NLMSG_PUT(skb, pid, seq, t, len - sizeof(*nlh));
	nlh->nlmsg_flags = flags;
	data		 = NLMSG_DATA(nlh);
	memcpy(data, payload, size);
	netlink_unicast(audit_sock, skb, pid, MSG_DONTWAIT);
	return;

nlmsg_failure:			/* Used by NLMSG_PUT */
	if (skb)
		kfree_skb(skb);
}

/*
 * Check for appropriate CAP_AUDIT_ capabilities on incoming audit
 * control messages.
 */
static int audit_netlink_ok(kernel_cap_t eff_cap, u16 msg_type)
{
	int err = 0;

	switch (msg_type) {
	case AUDIT_GET:
	case AUDIT_LIST:
	case AUDIT_SET:
	case AUDIT_ADD:
	case AUDIT_DEL:
		if (!cap_raised(eff_cap, CAP_AUDIT_CONTROL))
			err = -EPERM;
		break;
	case AUDIT_USER:
		if (!cap_raised(eff_cap, CAP_AUDIT_WRITE))
			err = -EPERM;
		break;
	default:  /* bad msg */
		err = -EINVAL;
	}

	return err;
}

static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
	u32			uid, pid, seq;
	void			*data;
	struct audit_status	*status_get, status_set;
	int			err;
	struct audit_buffer	*ab;
	u16			msg_type = nlh->nlmsg_type;

	err = audit_netlink_ok(NETLINK_CB(skb).eff_cap, msg_type);
	if (err)
		return err;

	pid  = NETLINK_CREDS(skb)->pid;
	uid  = NETLINK_CREDS(skb)->uid;
	seq  = nlh->nlmsg_seq;
	data = NLMSG_DATA(nlh);

	switch (msg_type) {
	case AUDIT_GET:
		status_set.enabled	 = audit_enabled;
		status_set.failure	 = audit_failure;
		status_set.pid		 = audit_pid;
		status_set.rate_limit	 = audit_rate_limit;
		status_set.backlog_limit = audit_backlog_limit;
		status_set.lost		 = atomic_read(&audit_lost);
		status_set.backlog	 = atomic_read(&audit_backlog);
		audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_GET, 0, 0,
				 &status_set, sizeof(status_set));
		break;
	case AUDIT_SET:
		if (nlh->nlmsg_len < sizeof(struct audit_status))
			return -EINVAL;
		status_get   = (struct audit_status *)data;
		if (status_get->mask & AUDIT_STATUS_ENABLED) {
			err = audit_set_enabled(status_get->enabled);
			if (err < 0) return err;
		}
		if (status_get->mask & AUDIT_STATUS_FAILURE) {
			err = audit_set_failure(status_get->failure);
			if (err < 0) return err;
		}
		if (status_get->mask & AUDIT_STATUS_PID) {
			int old   = audit_pid;
			audit_pid = status_get->pid;
			audit_log(current->audit_context,
				  "audit_pid=%d old=%d", audit_pid, old);
		}
		if (status_get->mask & AUDIT_STATUS_RATE_LIMIT)
			audit_set_rate_limit(status_get->rate_limit);
		if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
			audit_set_backlog_limit(status_get->backlog_limit);
		break;
	case AUDIT_USER:
		ab = audit_log_start(NULL);
		if (!ab)
			break;	/* audit_panic has been called */
		audit_log_format(ab,
				 "user pid=%d uid=%d length=%d msg='%.1024s'",
				 pid, uid,
				 (int)(nlh->nlmsg_len
				       - ((char *)data - (char *)nlh)),
				 (char *)data);
		ab->type = AUDIT_USER;
		ab->pid  = pid;
		audit_log_end(ab);
		break;
	case AUDIT_ADD:
	case AUDIT_DEL:
		if (nlh->nlmsg_len < sizeof(struct audit_rule))
			return -EINVAL;
		/* fallthrough */
	case AUDIT_LIST:
#ifdef CONFIG_AUDITSYSCALL
		err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid,
					   uid, seq, data);
#else
		err = -EOPNOTSUPP;
#endif
		break;
	default:
		err = -EINVAL;
		break;
	}

	return err < 0 ? err : 0;
}

/* Get message from skb (based on rtnetlink_rcv_skb).  Each message is
 * processed by audit_receive_msg.  Malformed skbs with wrong length are
 * discarded silently.  */
static void audit_receive_skb(struct sk_buff *skb)
{
	int		err;
	struct nlmsghdr	*nlh;
	u32		rlen;

	while (skb->len >= NLMSG_SPACE(0)) {
		nlh = (struct nlmsghdr *)skb->data;
		if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
			return;
		rlen = NLMSG_ALIGN(nlh->nlmsg_len);
		if (rlen > skb->len)
			rlen = skb->len;
		if ((err = audit_receive_msg(skb, nlh))) {
			netlink_ack(skb, nlh, err);
		} else if (nlh->nlmsg_flags & NLM_F_ACK)
			netlink_ack(skb, nlh, 0);
		skb_pull(skb, rlen);
	}
}

/* Receive messages from netlink socket. */
static void audit_receive(struct sock *sk, int length)
{
	struct sk_buff  *skb;
	unsigned int qlen;

	down(&audit_netlink_sem);

	for (qlen = skb_queue_len(&sk->sk_receive_queue); qlen; qlen--) {
		skb = skb_dequeue(&sk->sk_receive_queue);
		audit_receive_skb(skb);
		kfree_skb(skb);
	}
	up(&audit_netlink_sem);
}

/* Move data from tmp buffer into an skb.  This is an extra copy, and
 * that is unfortunate.  However, the copy will only occur when a record
 * is being written to user space, which is already a high-overhead
 * operation.  (Elimination of the copy is possible, for example, by
 * writing directly into a pre-allocated skb, at the cost of wasting
 * memory. */
static void audit_log_move(struct audit_buffer *ab)
{
	struct sk_buff	*skb;
	char		*start;
	int		extra = ab->nlh ? 0 : NLMSG_SPACE(0);

	/* possible resubmission */
	if (ab->len == 0)
		return;

	skb = skb_peek(&ab->sklist);
	if (!skb || skb_tailroom(skb) <= ab->len + extra) {
		skb = alloc_skb(2 * ab->len + extra, GFP_ATOMIC);
		if (!skb) {
			ab->len = 0; /* Lose information in ab->tmp */
			audit_log_lost("out of memory in audit_log_move");
			return;
		}
		__skb_queue_tail(&ab->sklist, skb);
		if (!ab->nlh)
			ab->nlh = (struct nlmsghdr *)skb_put(skb,
							     NLMSG_SPACE(0));
	}
	start = skb_put(skb, ab->len);
	memcpy(start, ab->tmp, ab->len);
	ab->len = 0;
}

/* Iterate over the skbuff in the audit_buffer, sending their contents
 * to user space. */
static inline int audit_log_drain(struct audit_buffer *ab)
{
	struct sk_buff *skb;

	while ((skb = skb_dequeue(&ab->sklist))) {
		int retval = 0;

		if (audit_pid) {
			if (ab->nlh) {
				ab->nlh->nlmsg_len   = ab->total;
				ab->nlh->nlmsg_type  = ab->type;
				ab->nlh->nlmsg_flags = 0;
				ab->nlh->nlmsg_seq   = 0;
				ab->nlh->nlmsg_pid   = ab->pid;
			}
			skb_get(skb); /* because netlink_* frees */
			retval = netlink_unicast(audit_sock, skb, audit_pid,
						 MSG_DONTWAIT);
		}
		if (retval == -EAGAIN && ab->count < 5) {
			++ab->count;
			skb_queue_tail(&ab->sklist, skb);
			audit_log_end_irq(ab);
			return 1;
		}
		if (retval < 0) {
			if (retval == -ECONNREFUSED) {
				printk(KERN_ERR
				       "audit: *NO* daemon at audit_pid=%d\n",
				       audit_pid);
				audit_pid = 0;
			} else
				audit_log_lost("netlink socket too busy");
		}
		if (!audit_pid) { /* No daemon */
			int offset = ab->nlh ? NLMSG_SPACE(0) : 0;
			int len    = skb->len - offset;
			printk(KERN_ERR "%*.*s\n",
			       len, len, skb->data + offset);
		}
		kfree_skb(skb);
		ab->nlh = NULL;
	}
	return 0;
}

/* Initialize audit support at boot time. */
static int __init audit_init(void)
{
	printk(KERN_INFO "audit: initializing netlink socket (%s)\n",
	       audit_default ? "enabled" : "disabled");
	audit_sock = netlink_kernel_create(NETLINK_AUDIT, audit_receive);
	if (!audit_sock)
		audit_panic("cannot initialize netlink socket");

	audit_initialized = 1;
	audit_enabled = audit_default;
	audit_log(NULL, "initialized");
	return 0;
}

#else
/* Without CONFIG_NET, we have no skbuffs.  For now, print what we have
 * in the buffer. */
static void audit_log_move(struct audit_buffer *ab)
{
	printk(KERN_ERR "%*.*s\n", ab->len, ab->len, ab->tmp);
	ab->len = 0;
}

static inline int audit_log_drain(struct audit_buffer *ab)
{
	return 0;
}

/* Initialize audit support at boot time. */
int __init audit_init(void)
{
	printk(KERN_INFO "audit: initializing WITHOUT netlink support\n");
	audit_sock = NULL;
	audit_pid  = 0;

	audit_initialized = 1;
	audit_enabled = audit_default;
	audit_log(NULL, "initialized");
	return 0;
}
#endif

__initcall(audit_init);

/* Process kernel command-line parameter at boot time.  audit=0 or audit=1. */
static int __init audit_enable(char *str)
{
	audit_default = !!simple_strtol(str, NULL, 0);
	printk(KERN_INFO "audit: %s%s\n",
	       audit_default ? "enabled" : "disabled",
	       audit_initialized ? "" : " (after initialization)");
	if (audit_initialized)
		audit_enabled = audit_default;
	return 0;
}

__setup("audit=", audit_enable);


/* Obtain an audit buffer.  This routine does locking to obtain the
 * audit buffer, but then no locking is required for calls to
 * audit_log_*format.  If the tsk is a task that is currently in a
 * syscall, then the syscall is marked as auditable and an audit record
 * will be written at syscall exit.  If there is no associated task, tsk
 * should be NULL. */
struct audit_buffer *audit_log_start(struct audit_context *ctx)
{
	struct audit_buffer	*ab	= NULL;
	unsigned long		flags;
	struct timespec		t;
	int			serial	= 0;

	if (!audit_initialized)
		return NULL;

	if (audit_backlog_limit
	    && atomic_read(&audit_backlog) > audit_backlog_limit) {
		if (audit_rate_check())
			printk(KERN_WARNING
			       "audit: audit_backlog=%d > "
			       "audit_backlog_limit=%d\n",
			       atomic_read(&audit_backlog),
			       audit_backlog_limit);
		audit_log_lost("backlog limit exceeded");
		return NULL;
	}

	spin_lock_irqsave(&audit_freelist_lock, flags);
	if (!list_empty(&audit_freelist)) {
		ab = list_entry(audit_freelist.next,
				struct audit_buffer, list);
		list_del(&ab->list);
		--audit_freelist_count;
	}
	spin_unlock_irqrestore(&audit_freelist_lock, flags);

	if (!ab)
		ab = kmalloc(sizeof(*ab), GFP_ATOMIC);
	if (!ab) {
		audit_log_lost("out of memory in audit_log_start");
		return NULL;
	}

	atomic_inc(&audit_backlog);
	skb_queue_head_init(&ab->sklist);

	ab->ctx   = ctx;
	ab->len   = 0;
	ab->nlh   = NULL;
	ab->total = 0;
	ab->type  = AUDIT_KERNEL;
	ab->pid   = 0;
	ab->count = 0;

#ifdef CONFIG_AUDITSYSCALL
	if (ab->ctx)
		audit_get_stamp(ab->ctx, &t, &serial);
	else
#endif
		t = CURRENT_TIME;

	audit_log_format(ab, "audit(%lu.%03lu:%u): ",
			 t.tv_sec, t.tv_nsec/1000000, serial);
	return ab;
}


/* Format an audit message into the audit buffer.  If there isn't enough
 * room in the audit buffer, more room will be allocated and vsnprint
 * will be called a second time.  Currently, we assume that a printk
 * can't format message larger than 1024 bytes, so we don't either. */
static void audit_log_vformat(struct audit_buffer *ab, const char *fmt,
			      va_list args)
{
	int len, avail;

	if (!ab)
		return;

	avail = sizeof(ab->tmp) - ab->len;
	if (avail <= 0) {
		audit_log_move(ab);
		avail = sizeof(ab->tmp) - ab->len;
	}
	len   = vsnprintf(ab->tmp + ab->len, avail, fmt, args);
	if (len >= avail) {
		/* The printk buffer is 1024 bytes long, so if we get
		 * here and AUDIT_BUFSIZ is at least 1024, then we can
		 * log everything that printk could have logged. */
		audit_log_move(ab);
		avail = sizeof(ab->tmp) - ab->len;
		len   = vsnprintf(ab->tmp + ab->len, avail, fmt, args);
	}
	ab->len   += (len < avail) ? len : avail;
	ab->total += (len < avail) ? len : avail;
}

/* Format a message into the audit buffer.  All the work is done in
 * audit_log_vformat. */
void audit_log_format(struct audit_buffer *ab, const char *fmt, ...)
{
	va_list args;

	if (!ab)
		return;
	va_start(args, fmt);
	audit_log_vformat(ab, fmt, args);
	va_end(args);
}

/* This is a helper-function to print the d_path without using a static
 * buffer or allocating another buffer in addition to the one in
 * audit_buffer. */
void audit_log_d_path(struct audit_buffer *ab, const char *prefix,
		      struct dentry *dentry, struct vfsmount *vfsmnt)
{
	char *p;
	int  len, avail;

	if (prefix) audit_log_format(ab, " %s", prefix);

	if (ab->len > 128)
		audit_log_move(ab);
	avail = sizeof(ab->tmp) - ab->len;
	p = d_path(dentry, vfsmnt, ab->tmp + ab->len, avail);
	if (IS_ERR(p)) {
		/* FIXME: can we save some information here? */
		audit_log_format(ab, "<toolong>");
	} else {
				/* path isn't at start of buffer */
		len	   = (ab->tmp + sizeof(ab->tmp) - 1) - p;
		memmove(ab->tmp + ab->len, p, len);
		ab->len   += len;
		ab->total += len;
	}
}

/* Remove queued messages from the audit_txlist and send them to userspace. */
static void audit_tasklet_handler(unsigned long arg)
{
	LIST_HEAD(list);
	struct audit_buffer *ab;
	unsigned long	    flags;

	spin_lock_irqsave(&audit_txlist_lock, flags);
	list_splice_init(&audit_txlist, &list);
	spin_unlock_irqrestore(&audit_txlist_lock, flags);

	while (!list_empty(&list)) {
		ab = list_entry(list.next, struct audit_buffer, list);
		list_del(&ab->list);
		audit_log_end_fast(ab);
	}
}

static DECLARE_TASKLET(audit_tasklet, audit_tasklet_handler, 0);

/* The netlink_* functions cannot be called inside an irq context, so
 * the audit buffer is places on a queue and a tasklet is scheduled to
 * remove them from the queue outside the irq context.  May be called in
 * any context. */
static void audit_log_end_irq(struct audit_buffer *ab)
{
	unsigned long flags;

	if (!ab)
		return;
	spin_lock_irqsave(&audit_txlist_lock, flags);
	list_add_tail(&ab->list, &audit_txlist);
	spin_unlock_irqrestore(&audit_txlist_lock, flags);

	tasklet_schedule(&audit_tasklet);
}

/* Send the message in the audit buffer directly to user space.  May not
 * be called in an irq context. */
static void audit_log_end_fast(struct audit_buffer *ab)
{
	unsigned long flags;

	BUG_ON(in_irq());
	if (!ab)
		return;
	if (!audit_rate_check()) {
		audit_log_lost("rate limit exceeded");
	} else {
		audit_log_move(ab);
		if (audit_log_drain(ab))
			return;
	}

	atomic_dec(&audit_backlog);
	spin_lock_irqsave(&audit_freelist_lock, flags);
	if (++audit_freelist_count > AUDIT_MAXFREE)
		kfree(ab);
	else
		list_add(&ab->list, &audit_freelist);
	spin_unlock_irqrestore(&audit_freelist_lock, flags);
}

/* Send or queue the message in the audit buffer, depending on the
 * current context.  (A convenience function that may be called in any
 * context.) */
void audit_log_end(struct audit_buffer *ab)
{
	if (in_irq())
		audit_log_end_irq(ab);
	else
		audit_log_end_fast(ab);
}

/* Log an audit record.  This is a convenience function that calls
 * audit_log_start, audit_log_vformat, and audit_log_end.  It may be
 * called in any context. */
void audit_log(struct audit_context *ctx, const char *fmt, ...)
{
	struct audit_buffer *ab;
	va_list args;

	ab = audit_log_start(ctx);
	if (ab) {
		va_start(args, fmt);
		audit_log_vformat(ab, fmt, args);
		va_end(args);
		audit_log_end(ab);
	}
}