aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace_syscalls.c
blob: e4b6d11bdf78f35a2a6d8e831cd3ec21d97d9c00 (plain) (blame)
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
#include <trace/syscall.h>
#include <trace/events/syscalls.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/module.h>	/* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */
#include <linux/ftrace.h>
#include <linux/perf_event.h>
#include <asm/syscall.h>

#include "trace_output.h"
#include "trace.h"

static DEFINE_MUTEX(syscall_trace_lock);

static int syscall_enter_register(struct ftrace_event_call *event,
				 enum trace_reg type, void *data);
static int syscall_exit_register(struct ftrace_event_call *event,
				 enum trace_reg type, void *data);

static struct list_head *
syscall_get_enter_fields(struct ftrace_event_call *call)
{
	struct syscall_metadata *entry = call->data;

	return &entry->enter_fields;
}

extern struct syscall_metadata *__start_syscalls_metadata[];
extern struct syscall_metadata *__stop_syscalls_metadata[];

static struct syscall_metadata **syscalls_metadata;

#ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME
static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
{
	/*
	 * Only compare after the "sys" prefix. Archs that use
	 * syscall wrappers may have syscalls symbols aliases prefixed
	 * with ".SyS" or ".sys" instead of "sys", leading to an unwanted
	 * mismatch.
	 */
	return !strcmp(sym + 3, name + 3);
}
#endif

#ifdef ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
/*
 * Some architectures that allow for 32bit applications
 * to run on a 64bit kernel, do not map the syscalls for
 * the 32bit tasks the same as they do for 64bit tasks.
 *
 *     *cough*x86*cough*
 *
 * In such a case, instead of reporting the wrong syscalls,
 * simply ignore them.
 *
 * For an arch to ignore the compat syscalls it needs to
 * define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS as well as
 * define the function arch_trace_is_compat_syscall() to let
 * the tracing system know that it should ignore it.
 */
static int
trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
{
	if (unlikely(arch_trace_is_compat_syscall(regs)))
		return -1;

	return syscall_get_nr(task, regs);
}
#else
static inline int
trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
{
	return syscall_get_nr(task, regs);
}
#endif /* ARCH_TRACE_IGNORE_COMPAT_SYSCALLS */

static __init struct syscall_metadata *
find_syscall_meta(unsigned long syscall)
{
	struct syscall_metadata **start;
	struct syscall_metadata **stop;
	char str[KSYM_SYMBOL_LEN];


	start = __start_syscalls_metadata;
	stop = __stop_syscalls_metadata;
	kallsyms_lookup(syscall, NULL, NULL, NULL, str);

	if (arch_syscall_match_sym_name(str, "sys_ni_syscall"))
		return NULL;

	for ( ; start < stop; start++) {
		if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name))
			return *start;
	}
	return NULL;
}

static struct syscall_metadata *syscall_nr_to_meta(int nr)
{
	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
		return NULL;

	return syscalls_metadata[nr];
}

static enum print_line_t
print_syscall_enter(struct trace_iterator *iter, int flags,
		    struct trace_event *event)
{
	struct trace_seq *s = &iter->seq;
	struct trace_entry *ent = iter->ent;
	struct syscall_trace_enter *trace;
	struct syscall_metadata *entry;
	int i, ret, syscall;

	trace = (typeof(trace))ent;
	syscall = trace->nr;
	entry = syscall_nr_to_meta(syscall);

	if (!entry)
		goto end;

	if (entry->enter_event->event.type != ent->type) {
		WARN_ON_ONCE(1);
		goto end;
	}

	ret = trace_seq_printf(s, "%s(", entry->name);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	for (i = 0; i < entry->nb_args; i++) {
		/* parameter types */
		if (trace_flags & TRACE_ITER_VERBOSE) {
			ret = trace_seq_printf(s, "%s ", entry->types[i]);
			if (!ret)
				return TRACE_TYPE_PARTIAL_LINE;
		}
		/* parameter values */
		ret = trace_seq_printf(s, "%s: %lx%s", entry->args[i],
				       trace->args[i],
				       i == entry->nb_args - 1 ? "" : ", ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	ret = trace_seq_putc(s, ')');
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

end:
	ret =  trace_seq_putc(s, '\n');
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	return TRACE_TYPE_HANDLED;
}

static enum print_line_t
print_syscall_exit(struct trace_iterator *iter, int flags,
		   struct trace_event *event)
{
	struct trace_seq *s = &iter->seq;
	struct trace_entry *ent = iter->ent;
	struct syscall_trace_exit *trace;
	int syscall;
	struct syscall_metadata *entry;
	int ret;

	trace = (typeof(trace))ent;
	syscall = trace->nr;
	entry = syscall_nr_to_meta(syscall);

	if (!entry) {
		trace_seq_putc(s, '\n');
		return TRACE_TYPE_HANDLED;
	}

	if (entry->exit_event->event.type != ent->type) {
		WARN_ON_ONCE(1);
		return TRACE_TYPE_UNHANDLED;
	}

	ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
				trace->ret);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	return TRACE_TYPE_HANDLED;
}

extern char *__bad_type_size(void);

#define SYSCALL_FIELD(type, name)					\
	sizeof(type) != sizeof(trace.name) ?				\
		__bad_type_size() :					\
		#type, #name, offsetof(typeof(trace), name),		\
		sizeof(trace.name), is_signed_type(type)

static int __init
__set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
{
	int i;
	int pos = 0;

	/* When len=0, we just calculate the needed length */
#define LEN_OR_ZERO (len ? len - pos : 0)

	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
	for (i = 0; i < entry->nb_args; i++) {
		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s",
				entry->args[i], sizeof(unsigned long),
				i == entry->nb_args - 1 ? "" : ", ");
	}
	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");

	for (i = 0; i < entry->nb_args; i++) {
		pos += snprintf(buf + pos, LEN_OR_ZERO,
				", ((unsigned long)(REC->%s))", entry->args[i]);
	}

#undef LEN_OR_ZERO

	/* return the length of print_fmt */
	return pos;
}

static int __init set_syscall_print_fmt(struct ftrace_event_call *call)
{
	char *print_fmt;
	int len;
	struct syscall_metadata *entry = call->data;

	if (entry->enter_event != call) {
		call->print_fmt = "\"0x%lx\", REC->ret";
		return 0;
	}

	/* First: called with 0 length to calculate the needed length */
	len = __set_enter_print_fmt(entry, NULL, 0);

	print_fmt = kmalloc(len + 1, GFP_KERNEL);
	if (!print_fmt)
		return -ENOMEM;

	/* Second: actually write the @print_fmt */
	__set_enter_print_fmt(entry, print_fmt, len + 1);
	call->print_fmt = print_fmt;

	return 0;
}

static void __init free_syscall_print_fmt(struct ftrace_event_call *call)
{
	struct syscall_metadata *entry = call->data;

	if (entry->enter_event == call)
		kfree(call->print_fmt);
}

static int __init syscall_enter_define_fields(struct ftrace_event_call *call)
{
	struct syscall_trace_enter trace;
	struct syscall_metadata *meta = call->data;
	int ret;
	int i;
	int offset = offsetof(typeof(trace), args);

	ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
	if (ret)
		return ret;

	for (i = 0; i < meta->nb_args; i++) {
		ret = trace_define_field(call, meta->types[i],
					 meta->args[i], offset,
					 sizeof(unsigned long), 0,
					 FILTER_OTHER);
		offset += sizeof(unsigned long);
	}

	return ret;
}

static int __init syscall_exit_define_fields(struct ftrace_event_call *call)
{
	struct syscall_trace_exit trace;
	int ret;

	ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
	if (ret)
		return ret;

	ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
				 FILTER_OTHER);

	return ret;
}

static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
{
	struct trace_array *tr = data;
	struct ftrace_event_file *ftrace_file;
	struct syscall_trace_enter *entry;
	struct syscall_metadata *sys_data;
	struct ring_buffer_event *event;
	struct ring_buffer *buffer;
	unsigned long irq_flags;
	int pc;
	int syscall_nr;
	int size;

	syscall_nr = trace_get_syscall_nr(current, regs);
	if (syscall_nr < 0)
		return;

	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
	ftrace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
	if (!ftrace_file)
		return;

	if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
		return;

	sys_data = syscall_nr_to_meta(syscall_nr);
	if (!sys_data)
		return;

	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;

	local_save_flags(irq_flags);
	pc = preempt_count();

	buffer = tr->trace_buffer.buffer;
	event = trace_buffer_lock_reserve(buffer,
			sys_data->enter_event->event.type, size, irq_flags, pc);
	if (!event)
		return;

	entry = ring_buffer_event_data(event);
	entry->nr = syscall_nr;
	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);

	if (!filter_check_discard(ftrace_file, entry, buffer, event))
		trace_current_buffer_unlock_commit(buffer, event,
						   irq_flags, pc);
}

static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
{
	struct trace_array *tr = data;
	struct ftrace_event_file *ftrace_file;
	struct syscall_trace_exit *entry;
	struct syscall_metadata *sys_data;
	struct ring_buffer_event *event;
	struct ring_buffer *buffer;
	unsigned long irq_flags;
	int pc;
	int syscall_nr;

	syscall_nr = trace_get_syscall_nr(current, regs);
	if (syscall_nr < 0)
		return;

	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
	ftrace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]);
	if (!ftrace_file)
		return;

	if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
		return;

	sys_data = syscall_nr_to_meta(syscall_nr);
	if (!sys_data)
		return;

	local_save_flags(irq_flags);
	pc = preempt_count();

	buffer = tr->trace_buffer.buffer;
	event = trace_buffer_lock_reserve(buffer,
			sys_data->exit_event->event.type, sizeof(*entry),
			irq_flags, pc);
	if (!event)
		return;

	entry = ring_buffer_event_data(event);
	entry->nr = syscall_nr;
	entry->ret = syscall_get_return_value(current, regs);

	if (!filter_check_discard(ftrace_file, entry, buffer, event))
		trace_current_buffer_unlock_commit(buffer, event,
						   irq_flags, pc);
}

static int reg_event_syscall_enter(struct ftrace_event_file *file,
				   struct ftrace_event_call *call)
{
	struct trace_array *tr = file->tr;
	int ret = 0;
	int num;

	num = ((struct syscall_metadata *)call->data)->syscall_nr;
	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
		return -ENOSYS;
	mutex_lock(&syscall_trace_lock);
	if (!tr->sys_refcount_enter)
		ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
	if (!ret) {
		rcu_assign_pointer(tr->enter_syscall_files[num], file);
		tr->sys_refcount_enter++;
	}
	mutex_unlock(&syscall_trace_lock);
	return ret;
}

static void unreg_event_syscall_enter(struct ftrace_event_file *file,
				      struct ftrace_event_call *call)
{
	struct trace_array *tr = file->tr;
	int num;

	num = ((struct syscall_metadata *)call->data)->syscall_nr;
	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
		return;
	mutex_lock(&syscall_trace_lock);
	tr->sys_refcount_enter--;
	rcu_assign_pointer(tr->enter_syscall_files[num], NULL);
	if (!tr->sys_refcount_enter)
		unregister_trace_sys_enter(ftrace_syscall_enter, tr);
	mutex_unlock(&syscall_trace_lock);
	/*
	 * Callers expect the event to be completely disabled on
	 * return, so wait for current handlers to finish.
	 */
	synchronize_sched();
}

static int reg_event_syscall_exit(struct ftrace_event_file *file,
				  struct ftrace_event_call *call)
{
	struct trace_array *tr = file->tr;
	int ret = 0;
	int num;

	num = ((struct syscall_metadata *)call->data)->syscall_nr;
	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
		return -ENOSYS;
	mutex_lock(&syscall_trace_lock);
	if (!tr->sys_refcount_exit)
		ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
	if (!ret) {
		rcu_assign_pointer(tr->exit_syscall_files[num], file);
		tr->sys_refcount_exit++;
	}
	mutex_unlock(&syscall_trace_lock);
	return ret;
}

static void unreg_event_syscall_exit(struct ftrace_event_file *file,
				     struct ftrace_event_call *call)
{
	struct trace_array *tr = file->tr;
	int num;

	num = ((struct syscall_metadata *)call->data)->syscall_nr;
	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
		return;
	mutex_lock(&syscall_trace_lock);
	tr->sys_refcount_exit--;
	rcu_assign_pointer(tr->exit_syscall_files[num], NULL);
	if (!tr->sys_refcount_exit)
		unregister_trace_sys_exit(ftrace_syscall_exit, tr);
	mutex_unlock(&syscall_trace_lock);
	/*
	 * Callers expect the event to be completely disabled on
	 * return, so wait for current handlers to finish.
	 */
	synchronize_sched();
}

static int __init init_syscall_trace(struct ftrace_event_call *call)
{
	int id;
	int num;

	num = ((struct syscall_metadata *)call->data)->syscall_nr;
	if (num < 0 || num >= NR_syscalls) {
		pr_debug("syscall %s metadata not mapped, disabling ftrace event\n",
				((struct syscall_metadata *)call->data)->name);
		return -ENOSYS;
	}

	if (set_syscall_print_fmt(call) < 0)
		return -ENOMEM;

	id = trace_event_raw_init(call);

	if (id < 0) {
		free_syscall_print_fmt(call);
		return id;
	}

	return id;
}

struct trace_event_functions enter_syscall_print_funcs = {
	.trace		= print_syscall_enter,
};

struct trace_event_functions exit_syscall_print_funcs = {
	.trace		= print_syscall_exit,
};

struct ftrace_event_class __refdata event_class_syscall_enter = {
	.system		= "syscalls",
	.reg		= syscall_enter_register,
	.define_fields	= syscall_enter_define_fields,
	.get_fields	= syscall_get_enter_fields,
	.raw_init	= init_syscall_trace,
};

struct ftrace_event_class __refdata event_class_syscall_exit = {
	.system		= "syscalls",
	.reg		= syscall_exit_register,
	.define_fields	= syscall_exit_define_fields,
	.fields		= LIST_HEAD_INIT(event_class_syscall_exit.fields),
	.raw_init	= init_syscall_trace,
};

unsigned long __init __weak arch_syscall_addr(int nr)
{
	return (unsigned long)sys_call_table[nr];
}

static int __init init_ftrace_syscalls(void)
{
	struct syscall_metadata *meta;
	unsigned long addr;
	int i;

	syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata),
				    GFP_KERNEL);
	if (!syscalls_metadata) {
		WARN_ON(1);
		return -ENOMEM;
	}

	for (i = 0; i < NR_syscalls; i++) {
		addr = arch_syscall_addr(i);
		meta = find_syscall_meta(addr);
		if (!meta)
			continue;

		meta->syscall_nr = i;
		syscalls_metadata[i] = meta;
	}

	return 0;
}
early_initcall(init_ftrace_syscalls);

#ifdef CONFIG_PERF_EVENTS

static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
static int sys_perf_refcount_enter;
static int sys_perf_refcount_exit;

static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
{
	struct syscall_metadata *sys_data;
	struct syscall_trace_enter *rec;
	struct hlist_head *head;
	int syscall_nr;
	int rctx;
	int size;

	syscall_nr = trace_get_syscall_nr(current, regs);
	if (syscall_nr < 0)
		return;
	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
		return;

	sys_data = syscall_nr_to_meta(syscall_nr);
	if (!sys_data)
		return;

	head = this_cpu_ptr(sys_data->enter_event->perf_events);
	if (hlist_empty(head))
		return;

	/* get the size after alignment with the u32 buffer size field */
	size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
	size = ALIGN(size + sizeof(u32), sizeof(u64));
	size -= sizeof(u32);

	rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
				sys_data->enter_event->event.type, regs, &rctx);
	if (!rec)
		return;

	rec->nr = syscall_nr;
	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
			       (unsigned long *)&rec->args);
	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
}

static int perf_sysenter_enable(struct ftrace_event_call *call)
{
	int ret = 0;
	int num;

	num = ((struct syscall_metadata *)call->data)->syscall_nr;

	mutex_lock(&syscall_trace_lock);
	if (!sys_perf_refcount_enter)
		ret = register_trace_sys_enter(perf_syscall_enter, NULL);
	if (ret) {
		pr_info("event trace: Could not activate"
				"syscall entry trace point");
	} else {
		set_bit(num, enabled_perf_enter_syscalls);
		sys_perf_refcount_enter++;
	}
	mutex_unlock(&syscall_trace_lock);
	return ret;
}

static void perf_sysenter_disable(struct ftrace_event_call *call)
{
	int num;

	num = ((struct syscall_metadata *)call->data)->syscall_nr;

	mutex_lock(&syscall_trace_lock);
	sys_perf_refcount_enter--;
	clear_bit(num, enabled_perf_enter_syscalls);
	if (!sys_perf_refcount_enter)
		unregister_trace_sys_enter(perf_syscall_enter, NULL);
	mutex_unlock(&syscall_trace_lock);
}

static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
{
	struct syscall_metadata *sys_data;
	struct syscall_trace_exit *rec;
	struct hlist_head *head;
	int syscall_nr;
	int rctx;
	int size;

	syscall_nr = trace_get_syscall_nr(current, regs);
	if (syscall_nr < 0)
		return;
	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
		return;

	sys_data = syscall_nr_to_meta(syscall_nr);
	if (!sys_data)
		return;

	head = this_cpu_ptr(sys_data->exit_event->perf_events);
	if (hlist_empty(head))
		return;

	/* We can probably do that at build time */
	size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
	size -= sizeof(u32);

	rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
				sys_data->exit_event->event.type, regs, &rctx);
	if (!rec)
		return;

	rec->nr = syscall_nr;
	rec->ret = syscall_get_return_value(current, regs);
	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
}

static int perf_sysexit_enable(struct ftrace_event_call *call)
{
	int ret = 0;
	int num;

	num = ((struct syscall_metadata *)call->data)->syscall_nr;

	mutex_lock(&syscall_trace_lock);
	if (!sys_perf_refcount_exit)
		ret = register_trace_sys_exit(perf_syscall_exit, NULL);
	if (ret) {
		pr_info("event trace: Could not activate"
				"syscall exit trace point");
	} else {
		set_bit(num, enabled_perf_exit_syscalls);
		sys_perf_refcount_exit++;
	}
	mutex_unlock(&syscall_trace_lock);
	return ret;
}

static void perf_sysexit_disable(struct ftrace_event_call *call)
{
	int num;

	num = ((struct syscall_metadata *)call->data)->syscall_nr;

	mutex_lock(&syscall_trace_lock);
	sys_perf_refcount_exit--;
	clear_bit(num, enabled_perf_exit_syscalls);
	if (!sys_perf_refcount_exit)
		unregister_trace_sys_exit(perf_syscall_exit, NULL);
	mutex_unlock(&syscall_trace_lock);
}

#endif /* CONFIG_PERF_EVENTS */

static int syscall_enter_register(struct ftrace_event_call *event,
				 enum trace_reg type, void *data)
{
	struct ftrace_event_file *file = data;

	switch (type) {
	case TRACE_REG_REGISTER:
		return reg_event_syscall_enter(file, event);
	case TRACE_REG_UNREGISTER:
		unreg_event_syscall_enter(file, event);
		return 0;

#ifdef CONFIG_PERF_EVENTS
	case TRACE_REG_PERF_REGISTER:
		return perf_sysenter_enable(event);
	case TRACE_REG_PERF_UNREGISTER:
		perf_sysenter_disable(event);
		return 0;
	case TRACE_REG_PERF_OPEN:
	case TRACE_REG_PERF_CLOSE:
	case TRACE_REG_PERF_ADD:
	case TRACE_REG_PERF_DEL:
		return 0;
#endif
	}
	return 0;
}

static int syscall_exit_register(struct ftrace_event_call *event,
				 enum trace_reg type, void *data)
{
	struct ftrace_event_file *file = data;

	switch (type) {
	case TRACE_REG_REGISTER:
		return reg_event_syscall_exit(file, event);
	case TRACE_REG_UNREGISTER:
		unreg_event_syscall_exit(file, event);
		return 0;

#ifdef CONFIG_PERF_EVENTS
	case TRACE_REG_PERF_REGISTER:
		return perf_sysexit_enable(event);
	case TRACE_REG_PERF_UNREGISTER:
		perf_sysexit_disable(event);
		return 0;
	case TRACE_REG_PERF_OPEN:
	case TRACE_REG_PERF_CLOSE:
	case TRACE_REG_PERF_ADD:
	case TRACE_REG_PERF_DEL:
		return 0;
#endif
	}
	return 0;
}