summaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace_functions_graph.c
blob: 45e6c01b2e4d96fc3eb9d4ef8b7a96bd7b60e30b (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
/*
 *
 * Function graph tracer.
 * Copyright (c) 2008-2009 Frederic Weisbecker <fweisbec@gmail.com>
 * Mostly borrowed from function tracer which
 * is Copyright (c) Steven Rostedt <srostedt@redhat.com>
 *
 */
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/fs.h>

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

struct fgraph_data {
	pid_t		last_pid;
	int		depth;
};

#define TRACE_GRAPH_INDENT	2

/* Flag options */
#define TRACE_GRAPH_PRINT_OVERRUN	0x1
#define TRACE_GRAPH_PRINT_CPU		0x2
#define TRACE_GRAPH_PRINT_OVERHEAD	0x4
#define TRACE_GRAPH_PRINT_PROC		0x8
#define TRACE_GRAPH_PRINT_DURATION	0x10
#define TRACE_GRAPH_PRINT_ABS_TIME	0X20

static struct tracer_opt trace_opts[] = {
	/* Display overruns? (for self-debug purpose) */
	{ TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) },
	/* Display CPU ? */
	{ TRACER_OPT(funcgraph-cpu, TRACE_GRAPH_PRINT_CPU) },
	/* Display Overhead ? */
	{ TRACER_OPT(funcgraph-overhead, TRACE_GRAPH_PRINT_OVERHEAD) },
	/* Display proc name/pid */
	{ TRACER_OPT(funcgraph-proc, TRACE_GRAPH_PRINT_PROC) },
	/* Display duration of execution */
	{ TRACER_OPT(funcgraph-duration, TRACE_GRAPH_PRINT_DURATION) },
	/* Display absolute time of an entry */
	{ TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) },
	{ } /* Empty entry */
};

static struct tracer_flags tracer_flags = {
	/* Don't display overruns and proc by default */
	.val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD |
	       TRACE_GRAPH_PRINT_DURATION,
	.opts = trace_opts
};

static struct trace_array *graph_array;


/* Add a function return address to the trace stack on thread info.*/
int
ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
			 unsigned long frame_pointer)
{
	unsigned long long calltime;
	int index;

	if (!current->ret_stack)
		return -EBUSY;

	/*
	 * We must make sure the ret_stack is tested before we read
	 * anything else.
	 */
	smp_rmb();

	/* The return trace stack is full */
	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
		atomic_inc(&current->trace_overrun);
		return -EBUSY;
	}

	calltime = trace_clock_local();

	index = ++current->curr_ret_stack;
	barrier();
	current->ret_stack[index].ret = ret;
	current->ret_stack[index].func = func;
	current->ret_stack[index].calltime = calltime;
	current->ret_stack[index].subtime = 0;
	current->ret_stack[index].fp = frame_pointer;
	*depth = index;

	return 0;
}

/* Retrieve a function return address to the trace stack on thread info.*/
static void
ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
			unsigned long frame_pointer)
{
	int index;

	index = current->curr_ret_stack;

	if (unlikely(index < 0)) {
		ftrace_graph_stop();
		WARN_ON(1);
		/* Might as well panic, otherwise we have no where to go */
		*ret = (unsigned long)panic;
		return;
	}

#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
	/*
	 * The arch may choose to record the frame pointer used
	 * and check it here to make sure that it is what we expect it
	 * to be. If gcc does not set the place holder of the return
	 * address in the frame pointer, and does a copy instead, then
	 * the function graph trace will fail. This test detects this
	 * case.
	 *
	 * Currently, x86_32 with optimize for size (-Os) makes the latest
	 * gcc do the above.
	 */
	if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
		ftrace_graph_stop();
		WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
		     "  from func %ps return to %lx\n",
		     current->ret_stack[index].fp,
		     frame_pointer,
		     (void *)current->ret_stack[index].func,
		     current->ret_stack[index].ret);
		*ret = (unsigned long)panic;
		return;
	}
#endif

	*ret = current->ret_stack[index].ret;
	trace->func = current->ret_stack[index].func;
	trace->calltime = current->ret_stack[index].calltime;
	trace->overrun = atomic_read(&current->trace_overrun);
	trace->depth = index;
}

/*
 * Send the trace to the ring-buffer.
 * @return the original return address.
 */
unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
{
	struct ftrace_graph_ret trace;
	unsigned long ret;

	ftrace_pop_return_trace(&trace, &ret, frame_pointer);
	trace.rettime = trace_clock_local();
	ftrace_graph_return(&trace);
	barrier();
	current->curr_ret_stack--;

	if (unlikely(!ret)) {
		ftrace_graph_stop();
		WARN_ON(1);
		/* Might as well panic. What else to do? */
		ret = (unsigned long)panic;
	}

	return ret;
}

static int __trace_graph_entry(struct trace_array *tr,
				struct ftrace_graph_ent *trace,
				unsigned long flags,
				int pc)
{
	struct ftrace_event_call *call = &event_funcgraph_entry;
	struct ring_buffer_event *event;
	struct ring_buffer *buffer = tr->buffer;
	struct ftrace_graph_ent_entry *entry;

	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
		return 0;

	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
					  sizeof(*entry), flags, pc);
	if (!event)
		return 0;
	entry	= ring_buffer_event_data(event);
	entry->graph_ent			= *trace;
	if (!filter_current_check_discard(buffer, call, entry, event))
		ring_buffer_unlock_commit(buffer, event);

	return 1;
}

int trace_graph_entry(struct ftrace_graph_ent *trace)
{
	struct trace_array *tr = graph_array;
	struct trace_array_cpu *data;
	unsigned long flags;
	long disabled;
	int ret;
	int cpu;
	int pc;

	if (unlikely(!tr))
		return 0;

	if (!ftrace_trace_task(current))
		return 0;

	if (!ftrace_graph_addr(trace->func))
		return 0;

	local_irq_save(flags);
	cpu = raw_smp_processor_id();
	data = tr->data[cpu];
	disabled = atomic_inc_return(&data->disabled);
	if (likely(disabled == 1)) {
		pc = preempt_count();
		ret = __trace_graph_entry(tr, trace, flags, pc);
	} else {
		ret = 0;
	}
	/* Only do the atomic if it is not already set */
	if (!test_tsk_trace_graph(current))
		set_tsk_trace_graph(current);

	atomic_dec(&data->disabled);
	local_irq_restore(flags);

	return ret;
}

static void __trace_graph_return(struct trace_array *tr,
				struct ftrace_graph_ret *trace,
				unsigned long flags,
				int pc)
{
	struct ftrace_event_call *call = &event_funcgraph_exit;
	struct ring_buffer_event *event;
	struct ring_buffer *buffer = tr->buffer;
	struct ftrace_graph_ret_entry *entry;

	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
		return;

	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
					  sizeof(*entry), flags, pc);
	if (!event)
		return;
	entry	= ring_buffer_event_data(event);
	entry->ret				= *trace;
	if (!filter_current_check_discard(buffer, call, entry, event))
		ring_buffer_unlock_commit(buffer, event);
}

void trace_graph_return(struct ftrace_graph_ret *trace)
{
	struct trace_array *tr = graph_array;
	struct trace_array_cpu *data;
	unsigned long flags;
	long disabled;
	int cpu;
	int pc;

	local_irq_save(flags);
	cpu = raw_smp_processor_id();
	data = tr->data[cpu];
	disabled = atomic_inc_return(&data->disabled);
	if (likely(disabled == 1)) {
		pc = preempt_count();
		__trace_graph_return(tr, trace, flags, pc);
	}
	if (!trace->depth)
		clear_tsk_trace_graph(current);
	atomic_dec(&data->disabled);
	local_irq_restore(flags);
}

static int graph_trace_init(struct trace_array *tr)
{
	int ret;

	graph_array = tr;
	ret = register_ftrace_graph(&trace_graph_return,
				    &trace_graph_entry);
	if (ret)
		return ret;
	tracing_start_cmdline_record();

	return 0;
}

void set_graph_array(struct trace_array *tr)
{
	graph_array = tr;
}

static void graph_trace_reset(struct trace_array *tr)
{
	tracing_stop_cmdline_record();
	unregister_ftrace_graph();
}

static int max_bytes_for_cpu;

static enum print_line_t
print_graph_cpu(struct trace_seq *s, int cpu)
{
	int ret;

	/*
	 * Start with a space character - to make it stand out
	 * to the right a bit when trace output is pasted into
	 * email:
	 */
	ret = trace_seq_printf(s, " %*d) ", max_bytes_for_cpu, cpu);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	return TRACE_TYPE_HANDLED;
}

#define TRACE_GRAPH_PROCINFO_LENGTH	14

static enum print_line_t
print_graph_proc(struct trace_seq *s, pid_t pid)
{
	char comm[TASK_COMM_LEN];
	/* sign + log10(MAX_INT) + '\0' */
	char pid_str[11];
	int spaces = 0;
	int ret;
	int len;
	int i;

	trace_find_cmdline(pid, comm);
	comm[7] = '\0';
	sprintf(pid_str, "%d", pid);

	/* 1 stands for the "-" character */
	len = strlen(comm) + strlen(pid_str) + 1;

	if (len < TRACE_GRAPH_PROCINFO_LENGTH)
		spaces = TRACE_GRAPH_PROCINFO_LENGTH - len;

	/* First spaces to align center */
	for (i = 0; i < spaces / 2; i++) {
		ret = trace_seq_printf(s, " ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	ret = trace_seq_printf(s, "%s-%s", comm, pid_str);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	/* Last spaces to align center */
	for (i = 0; i < spaces - (spaces / 2); i++) {
		ret = trace_seq_printf(s, " ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}
	return TRACE_TYPE_HANDLED;
}


static enum print_line_t
print_graph_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
{
	if (!trace_seq_putc(s, ' '))
		return 0;

	return trace_print_lat_fmt(s, entry);
}

/* If the pid changed since the last trace, output this event */
static enum print_line_t
verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
{
	pid_t prev_pid;
	pid_t *last_pid;
	int ret;

	if (!data)
		return TRACE_TYPE_HANDLED;

	last_pid = &(per_cpu_ptr(data, cpu)->last_pid);

	if (*last_pid == pid)
		return TRACE_TYPE_HANDLED;

	prev_pid = *last_pid;
	*last_pid = pid;

	if (prev_pid == -1)
		return TRACE_TYPE_HANDLED;
/*
 * Context-switch trace line:

 ------------------------------------------
 | 1)  migration/0--1  =>  sshd-1755
 ------------------------------------------

 */
	ret = trace_seq_printf(s,
		" ------------------------------------------\n");
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	ret = print_graph_cpu(s, cpu);
	if (ret == TRACE_TYPE_PARTIAL_LINE)
		return TRACE_TYPE_PARTIAL_LINE;

	ret = print_graph_proc(s, prev_pid);
	if (ret == TRACE_TYPE_PARTIAL_LINE)
		return TRACE_TYPE_PARTIAL_LINE;

	ret = trace_seq_printf(s, " => ");
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	ret = print_graph_proc(s, pid);
	if (ret == TRACE_TYPE_PARTIAL_LINE)
		return TRACE_TYPE_PARTIAL_LINE;

	ret = trace_seq_printf(s,
		"\n ------------------------------------------\n\n");
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	return TRACE_TYPE_HANDLED;
}

static struct ftrace_graph_ret_entry *
get_return_for_leaf(struct trace_iterator *iter,
		struct ftrace_graph_ent_entry *curr)
{
	struct ring_buffer_iter *ring_iter;
	struct ring_buffer_event *event;
	struct ftrace_graph_ret_entry *next;

	ring_iter = iter->buffer_iter[iter->cpu];

	/* First peek to compare current entry and the next one */
	if (ring_iter)
		event = ring_buffer_iter_peek(ring_iter, NULL);
	else {
	/* We need to consume the current entry to see the next one */
		ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
		event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
					NULL);
	}

	if (!event)
		return NULL;

	next = ring_buffer_event_data(event);

	if (next->ent.type != TRACE_GRAPH_RET)
		return NULL;

	if (curr->ent.pid != next->ent.pid ||
			curr->graph_ent.func != next->ret.func)
		return NULL;

	/* this is a leaf, now advance the iterator */
	if (ring_iter)
		ring_buffer_read(ring_iter, NULL);

	return next;
}

/* Signal a overhead of time execution to the output */
static int
print_graph_overhead(unsigned long long duration, struct trace_seq *s)
{
	/* If duration disappear, we don't need anything */
	if (!(tracer_flags.val & TRACE_GRAPH_PRINT_DURATION))
		return 1;

	/* Non nested entry or return */
	if (duration == -1)
		return trace_seq_printf(s, "  ");

	if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
		/* Duration exceeded 100 msecs */
		if (duration > 100000ULL)
			return trace_seq_printf(s, "! ");

		/* Duration exceeded 10 msecs */
		if (duration > 10000ULL)
			return trace_seq_printf(s, "+ ");
	}

	return trace_seq_printf(s, "  ");
}

static int print_graph_abs_time(u64 t, struct trace_seq *s)
{
	unsigned long usecs_rem;

	usecs_rem = do_div(t, NSEC_PER_SEC);
	usecs_rem /= 1000;

	return trace_seq_printf(s, "%5lu.%06lu |  ",
			(unsigned long)t, usecs_rem);
}

static enum print_line_t
print_graph_irq(struct trace_iterator *iter, unsigned long addr,
		enum trace_type type, int cpu, pid_t pid)
{
	int ret;
	struct trace_seq *s = &iter->seq;

	if (addr < (unsigned long)__irqentry_text_start ||
		addr >= (unsigned long)__irqentry_text_end)
		return TRACE_TYPE_UNHANDLED;

	/* Absolute time */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
		ret = print_graph_abs_time(iter->ts, s);
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* Cpu */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
		ret = print_graph_cpu(s, cpu);
		if (ret == TRACE_TYPE_PARTIAL_LINE)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* Proc */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
		ret = print_graph_proc(s, pid);
		if (ret == TRACE_TYPE_PARTIAL_LINE)
			return TRACE_TYPE_PARTIAL_LINE;
		ret = trace_seq_printf(s, " | ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* No overhead */
	ret = print_graph_overhead(-1, s);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	if (type == TRACE_GRAPH_ENT)
		ret = trace_seq_printf(s, "==========>");
	else
		ret = trace_seq_printf(s, "<==========");

	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	/* Don't close the duration column if haven't one */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
		trace_seq_printf(s, " |");
	ret = trace_seq_printf(s, "\n");

	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;
	return TRACE_TYPE_HANDLED;
}

enum print_line_t
trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
{
	unsigned long nsecs_rem = do_div(duration, 1000);
	/* log10(ULONG_MAX) + '\0' */
	char msecs_str[21];
	char nsecs_str[5];
	int ret, len;
	int i;

	sprintf(msecs_str, "%lu", (unsigned long) duration);

	/* Print msecs */
	ret = trace_seq_printf(s, "%s", msecs_str);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	len = strlen(msecs_str);

	/* Print nsecs (we don't want to exceed 7 numbers) */
	if (len < 7) {
		snprintf(nsecs_str, 8 - len, "%03lu", nsecs_rem);
		ret = trace_seq_printf(s, ".%s", nsecs_str);
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
		len += strlen(nsecs_str);
	}

	ret = trace_seq_printf(s, " us ");
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	/* Print remaining spaces to fit the row's width */
	for (i = len; i < 7; i++) {
		ret = trace_seq_printf(s, " ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}
	return TRACE_TYPE_HANDLED;
}

static enum print_line_t
print_graph_duration(unsigned long long duration, struct trace_seq *s)
{
	int ret;

	ret = trace_print_graph_duration(duration, s);
	if (ret != TRACE_TYPE_HANDLED)
		return ret;

	ret = trace_seq_printf(s, "|  ");
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	return TRACE_TYPE_HANDLED;
}

/* Case of a leaf function on its call entry */
static enum print_line_t
print_graph_entry_leaf(struct trace_iterator *iter,
		struct ftrace_graph_ent_entry *entry,
		struct ftrace_graph_ret_entry *ret_entry, struct trace_seq *s)
{
	struct fgraph_data *data = iter->private;
	struct ftrace_graph_ret *graph_ret;
	struct ftrace_graph_ent *call;
	unsigned long long duration;
	int ret;
	int i;

	graph_ret = &ret_entry->ret;
	call = &entry->graph_ent;
	duration = graph_ret->rettime - graph_ret->calltime;

	if (data) {
		int cpu = iter->cpu;
		int *depth = &(per_cpu_ptr(data, cpu)->depth);

		/*
		 * Comments display at + 1 to depth. Since
		 * this is a leaf function, keep the comments
		 * equal to this depth.
		 */
		*depth = call->depth - 1;
	}

	/* Overhead */
	ret = print_graph_overhead(duration, s);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	/* Duration */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
		ret = print_graph_duration(duration, s);
		if (ret == TRACE_TYPE_PARTIAL_LINE)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* Function */
	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
		ret = trace_seq_printf(s, " ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	ret = trace_seq_printf(s, "%ps();\n", (void *)call->func);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	return TRACE_TYPE_HANDLED;
}

static enum print_line_t
print_graph_entry_nested(struct trace_iterator *iter,
			 struct ftrace_graph_ent_entry *entry,
			 struct trace_seq *s, int cpu)
{
	struct ftrace_graph_ent *call = &entry->graph_ent;
	struct fgraph_data *data = iter->private;
	int ret;
	int i;

	if (data) {
		int cpu = iter->cpu;
		int *depth = &(per_cpu_ptr(data, cpu)->depth);

		*depth = call->depth;
	}

	/* No overhead */
	ret = print_graph_overhead(-1, s);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	/* No time */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
		ret = trace_seq_printf(s, "            |  ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* Function */
	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
		ret = trace_seq_printf(s, " ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	ret = trace_seq_printf(s, "%ps() {\n", (void *)call->func);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	/*
	 * we already consumed the current entry to check the next one
	 * and see if this is a leaf.
	 */
	return TRACE_TYPE_NO_CONSUME;
}

static enum print_line_t
print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
		     int type, unsigned long addr)
{
	struct fgraph_data *data = iter->private;
	struct trace_entry *ent = iter->ent;
	int cpu = iter->cpu;
	int ret;

	/* Pid */
	if (verif_pid(s, ent->pid, cpu, data) == TRACE_TYPE_PARTIAL_LINE)
		return TRACE_TYPE_PARTIAL_LINE;

	if (type) {
		/* Interrupt */
		ret = print_graph_irq(iter, addr, type, cpu, ent->pid);
		if (ret == TRACE_TYPE_PARTIAL_LINE)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* Absolute time */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
		ret = print_graph_abs_time(iter->ts, s);
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* Cpu */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
		ret = print_graph_cpu(s, cpu);
		if (ret == TRACE_TYPE_PARTIAL_LINE)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* Proc */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
		ret = print_graph_proc(s, ent->pid);
		if (ret == TRACE_TYPE_PARTIAL_LINE)
			return TRACE_TYPE_PARTIAL_LINE;

		ret = trace_seq_printf(s, " | ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* Latency format */
	if (trace_flags & TRACE_ITER_LATENCY_FMT) {
		ret = print_graph_lat_fmt(s, ent);
		if (ret == TRACE_TYPE_PARTIAL_LINE)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	return 0;
}

static enum print_line_t
print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
			struct trace_iterator *iter)
{
	int cpu = iter->cpu;
	struct ftrace_graph_ent *call = &field->graph_ent;
	struct ftrace_graph_ret_entry *leaf_ret;

	if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func))
		return TRACE_TYPE_PARTIAL_LINE;

	leaf_ret = get_return_for_leaf(iter, field);
	if (leaf_ret)
		return print_graph_entry_leaf(iter, field, leaf_ret, s);
	else
		return print_graph_entry_nested(iter, field, s, cpu);

}

static enum print_line_t
print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
		   struct trace_entry *ent, struct trace_iterator *iter)
{
	unsigned long long duration = trace->rettime - trace->calltime;
	struct fgraph_data *data = iter->private;
	pid_t pid = ent->pid;
	int cpu = iter->cpu;
	int ret;
	int i;

	if (data) {
		int cpu = iter->cpu;
		int *depth = &(per_cpu_ptr(data, cpu)->depth);

		/*
		 * Comments display at + 1 to depth. This is the
		 * return from a function, we now want the comments
		 * to display at the same level of the bracket.
		 */
		*depth = trace->depth - 1;
	}

	if (print_graph_prologue(iter, s, 0, 0))
		return TRACE_TYPE_PARTIAL_LINE;

	/* Overhead */
	ret = print_graph_overhead(duration, s);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	/* Duration */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
		ret = print_graph_duration(duration, s);
		if (ret == TRACE_TYPE_PARTIAL_LINE)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* Closing brace */
	for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) {
		ret = trace_seq_printf(s, " ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	ret = trace_seq_printf(s, "}\n");
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	/* Overrun */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) {
		ret = trace_seq_printf(s, " (Overruns: %lu)\n",
					trace->overrun);
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET, cpu, pid);
	if (ret == TRACE_TYPE_PARTIAL_LINE)
		return TRACE_TYPE_PARTIAL_LINE;

	return TRACE_TYPE_HANDLED;
}

static enum print_line_t
print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
		    struct trace_iterator *iter)
{
	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
	struct fgraph_data *data = iter->private;
	struct trace_event *event;
	int depth = 0;
	int ret;
	int i;

	if (data)
		depth = per_cpu_ptr(data, iter->cpu)->depth;

	if (print_graph_prologue(iter, s, 0, 0))
		return TRACE_TYPE_PARTIAL_LINE;

	/* No overhead */
	ret = print_graph_overhead(-1, s);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	/* No time */
	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
		ret = trace_seq_printf(s, "            |  ");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

	/* Indentation */
	if (depth > 0)
		for (i = 0; i < (depth + 1) * TRACE_GRAPH_INDENT; i++) {
			ret = trace_seq_printf(s, " ");
			if (!ret)
				return TRACE_TYPE_PARTIAL_LINE;
		}

	/* The comment */
	ret = trace_seq_printf(s, "/* ");
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	switch (iter->ent->type) {
	case TRACE_BPRINT:
		ret = trace_print_bprintk_msg_only(iter);
		if (ret != TRACE_TYPE_HANDLED)
			return ret;
		break;
	case TRACE_PRINT:
		ret = trace_print_printk_msg_only(iter);
		if (ret != TRACE_TYPE_HANDLED)
			return ret;
		break;
	default:
		event = ftrace_find_event(ent->type);
		if (!event)
			return TRACE_TYPE_UNHANDLED;

		ret = event->trace(iter, sym_flags);
		if (ret != TRACE_TYPE_HANDLED)
			return ret;
	}

	/* Strip ending newline */
	if (s->buffer[s->len - 1] == '\n') {
		s->buffer[s->len - 1] = '\0';
		s->len--;
	}

	ret = trace_seq_printf(s, " */\n");
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	return TRACE_TYPE_HANDLED;
}


enum print_line_t
print_graph_function(struct trace_iterator *iter)
{
	struct trace_entry *entry = iter->ent;
	struct trace_seq *s = &iter->seq;

	switch (entry->type) {
	case TRACE_GRAPH_ENT: {
		/*
		 * print_graph_entry() may consume the current event,
		 * thus @field may become invalid, so we need to save it.
		 * sizeof(struct ftrace_graph_ent_entry) is very small,
		 * it can be safely saved at the stack.
		 */
		struct ftrace_graph_ent_entry *field, saved;
		trace_assign_type(field, entry);
		saved = *field;
		return print_graph_entry(&saved, s, iter);
	}
	case TRACE_GRAPH_RET: {
		struct ftrace_graph_ret_entry *field;
		trace_assign_type(field, entry);
		return print_graph_return(&field->ret, s, entry, iter);
	}
	default:
		return print_graph_comment(s, entry, iter);
	}

	return TRACE_TYPE_HANDLED;
}

static void print_lat_header(struct seq_file *s)
{
	static const char spaces[] = "                "	/* 16 spaces */
		"    "					/* 4 spaces */
		"                 ";			/* 17 spaces */
	int size = 0;

	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
		size += 16;
	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
		size += 4;
	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
		size += 17;

	seq_printf(s, "#%.*s  _-----=> irqs-off        \n", size, spaces);
	seq_printf(s, "#%.*s / _----=> need-resched    \n", size, spaces);
	seq_printf(s, "#%.*s| / _---=> hardirq/softirq \n", size, spaces);
	seq_printf(s, "#%.*s|| / _--=> preempt-depth   \n", size, spaces);
	seq_printf(s, "#%.*s||| / _-=> lock-depth      \n", size, spaces);
	seq_printf(s, "#%.*s|||| /                     \n", size, spaces);
}

static void print_graph_headers(struct seq_file *s)
{
	int lat = trace_flags & TRACE_ITER_LATENCY_FMT;

	if (lat)
		print_lat_header(s);

	/* 1st line */
	seq_printf(s, "#");
	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
		seq_printf(s, "     TIME       ");
	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
		seq_printf(s, " CPU");
	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
		seq_printf(s, "  TASK/PID       ");
	if (lat)
		seq_printf(s, "|||||");
	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
		seq_printf(s, "  DURATION   ");
	seq_printf(s, "               FUNCTION CALLS\n");

	/* 2nd line */
	seq_printf(s, "#");
	if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
		seq_printf(s, "      |         ");
	if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
		seq_printf(s, " |  ");
	if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
		seq_printf(s, "   |    |        ");
	if (lat)
		seq_printf(s, "|||||");
	if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
		seq_printf(s, "   |   |      ");
	seq_printf(s, "               |   |   |   |\n");
}

static void graph_trace_open(struct trace_iterator *iter)
{
	/* pid and depth on the last trace processed */
	struct fgraph_data *data = alloc_percpu(struct fgraph_data);
	int cpu;

	if (!data)
		pr_warning("function graph tracer: not enough memory\n");
	else
		for_each_possible_cpu(cpu) {
			pid_t *pid = &(per_cpu_ptr(data, cpu)->last_pid);
			int *depth = &(per_cpu_ptr(data, cpu)->depth);
			*pid = -1;
			*depth = 0;
		}

	iter->private = data;
}

static void graph_trace_close(struct trace_iterator *iter)
{
	free_percpu(iter->private);
}

static struct tracer graph_trace __read_mostly = {
	.name		= "function_graph",
	.open		= graph_trace_open,
	.close		= graph_trace_close,
	.wait_pipe	= poll_wait_pipe,
	.init		= graph_trace_init,
	.reset		= graph_trace_reset,
	.print_line	= print_graph_function,
	.print_header	= print_graph_headers,
	.flags		= &tracer_flags,
#ifdef CONFIG_FTRACE_SELFTEST
	.selftest	= trace_selftest_startup_function_graph,
#endif
};

static __init int init_graph_trace(void)
{
	max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);

	return register_tracer(&graph_trace);
}

device_initcall(init_graph_trace);