summaryrefslogtreecommitdiffstats
path: root/tools/perf/builtin-record.c
blob: 20b56eb987f89f21fe20e53decf8ee1fbe275a2e (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
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
/*
 * builtin-record.c
 *
 * Builtin record command: Record the profile of a workload
 * (or a CPU, or a PID) into the perf.data output file - for
 * later analysis via perf report.
 */
#include "builtin.h"

#include "perf.h"

#include "util/build-id.h"
#include "util/util.h"
#include "util/parse-options.h"
#include "util/parse-events.h"

#include "util/callchain.h"
#include "util/cgroup.h"
#include "util/header.h"
#include "util/event.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
#include "util/session.h"
#include "util/tool.h"
#include "util/symbol.h"
#include "util/cpumap.h"
#include "util/thread_map.h"
#include "util/data.h"
#include "util/auxtrace.h"
#include "util/parse-branch-options.h"

#include <unistd.h>
#include <sched.h>
#include <sys/mman.h>


struct record {
	struct perf_tool	tool;
	struct record_opts	opts;
	u64			bytes_written;
	struct perf_data_file	file;
	struct auxtrace_record	*itr;
	struct perf_evlist	*evlist;
	struct perf_session	*session;
	const char		*progname;
	int			realtime_prio;
	bool			no_buildid;
	bool			no_buildid_cache;
	long			samples;
};

static int record__write(struct record *rec, void *bf, size_t size)
{
	if (perf_data_file__write(rec->session->file, bf, size) < 0) {
		pr_err("failed to write perf data, error: %m\n");
		return -1;
	}

	rec->bytes_written += size;
	return 0;
}

static int process_synthesized_event(struct perf_tool *tool,
				     union perf_event *event,
				     struct perf_sample *sample __maybe_unused,
				     struct machine *machine __maybe_unused)
{
	struct record *rec = container_of(tool, struct record, tool);
	return record__write(rec, event, event->header.size);
}

static int record__mmap_read(struct record *rec, int idx)
{
	struct perf_mmap *md = &rec->evlist->mmap[idx];
	u64 head = perf_mmap__read_head(md);
	u64 old = md->prev;
	unsigned char *data = md->base + page_size;
	unsigned long size;
	void *buf;
	int rc = 0;

	if (old == head)
		return 0;

	rec->samples++;

	size = head - old;

	if ((old & md->mask) + size != (head & md->mask)) {
		buf = &data[old & md->mask];
		size = md->mask + 1 - (old & md->mask);
		old += size;

		if (record__write(rec, buf, size) < 0) {
			rc = -1;
			goto out;
		}
	}

	buf = &data[old & md->mask];
	size = head - old;
	old += size;

	if (record__write(rec, buf, size) < 0) {
		rc = -1;
		goto out;
	}

	md->prev = old;
	perf_evlist__mmap_consume(rec->evlist, idx);
out:
	return rc;
}

static volatile int done;
static volatile int signr = -1;
static volatile int child_finished;
static volatile int auxtrace_snapshot_enabled;
static volatile int auxtrace_snapshot_err;
static volatile int auxtrace_record__snapshot_started;

static void sig_handler(int sig)
{
	if (sig == SIGCHLD)
		child_finished = 1;
	else
		signr = sig;

	done = 1;
}

static void record__sig_exit(void)
{
	if (signr == -1)
		return;

	signal(signr, SIG_DFL);
	raise(signr);
}

#ifdef HAVE_AUXTRACE_SUPPORT

static int record__process_auxtrace(struct perf_tool *tool,
				    union perf_event *event, void *data1,
				    size_t len1, void *data2, size_t len2)
{
	struct record *rec = container_of(tool, struct record, tool);
	struct perf_data_file *file = &rec->file;
	size_t padding;
	u8 pad[8] = {0};

	if (!perf_data_file__is_pipe(file)) {
		off_t file_offset;
		int fd = perf_data_file__fd(file);
		int err;

		file_offset = lseek(fd, 0, SEEK_CUR);
		if (file_offset == -1)
			return -1;
		err = auxtrace_index__auxtrace_event(&rec->session->auxtrace_index,
						     event, file_offset);
		if (err)
			return err;
	}

	/* event.auxtrace.size includes padding, see __auxtrace_mmap__read() */
	padding = (len1 + len2) & 7;
	if (padding)
		padding = 8 - padding;

	record__write(rec, event, event->header.size);
	record__write(rec, data1, len1);
	if (len2)
		record__write(rec, data2, len2);
	record__write(rec, &pad, padding);

	return 0;
}

static int record__auxtrace_mmap_read(struct record *rec,
				      struct auxtrace_mmap *mm)
{
	int ret;

	ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
				  record__process_auxtrace);
	if (ret < 0)
		return ret;

	if (ret)
		rec->samples++;

	return 0;
}

static int record__auxtrace_mmap_read_snapshot(struct record *rec,
					       struct auxtrace_mmap *mm)
{
	int ret;

	ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool,
					   record__process_auxtrace,
					   rec->opts.auxtrace_snapshot_size);
	if (ret < 0)
		return ret;

	if (ret)
		rec->samples++;

	return 0;
}

static int record__auxtrace_read_snapshot_all(struct record *rec)
{
	int i;
	int rc = 0;

	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
		struct auxtrace_mmap *mm =
				&rec->evlist->mmap[i].auxtrace_mmap;

		if (!mm->base)
			continue;

		if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) {
			rc = -1;
			goto out;
		}
	}
out:
	return rc;
}

static void record__read_auxtrace_snapshot(struct record *rec)
{
	pr_debug("Recording AUX area tracing snapshot\n");
	if (record__auxtrace_read_snapshot_all(rec) < 0) {
		auxtrace_snapshot_err = -1;
	} else {
		auxtrace_snapshot_err = auxtrace_record__snapshot_finish(rec->itr);
		if (!auxtrace_snapshot_err)
			auxtrace_snapshot_enabled = 1;
	}
}

#else

static inline
int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
			       struct auxtrace_mmap *mm __maybe_unused)
{
	return 0;
}

static inline
void record__read_auxtrace_snapshot(struct record *rec __maybe_unused)
{
}

static inline
int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
{
	return 0;
}

#endif

static int record__open(struct record *rec)
{
	char msg[512];
	struct perf_evsel *pos;
	struct perf_evlist *evlist = rec->evlist;
	struct perf_session *session = rec->session;
	struct record_opts *opts = &rec->opts;
	int rc = 0;

	perf_evlist__config(evlist, opts);

	evlist__for_each(evlist, pos) {
try_again:
		if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
			if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
				if (verbose)
					ui__warning("%s\n", msg);
				goto try_again;
			}

			rc = -errno;
			perf_evsel__open_strerror(pos, &opts->target,
						  errno, msg, sizeof(msg));
			ui__error("%s\n", msg);
			goto out;
		}
	}

	if (perf_evlist__apply_filters(evlist, &pos)) {
		error("failed to set filter \"%s\" on event %s with %d (%s)\n",
			pos->filter, perf_evsel__name(pos), errno,
			strerror_r(errno, msg, sizeof(msg)));
		rc = -1;
		goto out;
	}

	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
				 opts->auxtrace_mmap_pages,
				 opts->auxtrace_snapshot_mode) < 0) {
		if (errno == EPERM) {
			pr_err("Permission error mapping pages.\n"
			       "Consider increasing "
			       "/proc/sys/kernel/perf_event_mlock_kb,\n"
			       "or try again with a smaller value of -m/--mmap_pages.\n"
			       "(current value: %u,%u)\n",
			       opts->mmap_pages, opts->auxtrace_mmap_pages);
			rc = -errno;
		} else {
			pr_err("failed to mmap with %d (%s)\n", errno,
				strerror_r(errno, msg, sizeof(msg)));
			rc = -errno;
		}
		goto out;
	}

	session->evlist = evlist;
	perf_session__set_id_hdr_size(session);
out:
	return rc;
}

static int process_sample_event(struct perf_tool *tool,
				union perf_event *event,
				struct perf_sample *sample,
				struct perf_evsel *evsel,
				struct machine *machine)
{
	struct record *rec = container_of(tool, struct record, tool);

	rec->samples++;

	return build_id__mark_dso_hit(tool, event, sample, evsel, machine);
}

static int process_buildids(struct record *rec)
{
	struct perf_data_file *file  = &rec->file;
	struct perf_session *session = rec->session;

	if (file->size == 0)
		return 0;

	/*
	 * During this process, it'll load kernel map and replace the
	 * dso->long_name to a real pathname it found.  In this case
	 * we prefer the vmlinux path like
	 *   /lib/modules/3.16.4/build/vmlinux
	 *
	 * rather than build-id path (in debug directory).
	 *   $HOME/.debug/.build-id/f0/6e17aa50adf4d00b88925e03775de107611551
	 */
	symbol_conf.ignore_vmlinux_buildid = true;

	return perf_session__process_events(session);
}

static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
{
	int err;
	struct perf_tool *tool = data;
	/*
	 *As for guest kernel when processing subcommand record&report,
	 *we arrange module mmap prior to guest kernel mmap and trigger
	 *a preload dso because default guest module symbols are loaded
	 *from guest kallsyms instead of /lib/modules/XXX/XXX. This
	 *method is used to avoid symbol missing when the first addr is
	 *in module instead of in guest kernel.
	 */
	err = perf_event__synthesize_modules(tool, process_synthesized_event,
					     machine);
	if (err < 0)
		pr_err("Couldn't record guest kernel [%d]'s reference"
		       " relocation symbol.\n", machine->pid);

	/*
	 * We use _stext for guest kernel because guest kernel's /proc/kallsyms
	 * have no _text sometimes.
	 */
	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
						 machine);
	if (err < 0)
		pr_err("Couldn't record guest kernel [%d]'s reference"
		       " relocation symbol.\n", machine->pid);
}

static struct perf_event_header finished_round_event = {
	.size = sizeof(struct perf_event_header),
	.type = PERF_RECORD_FINISHED_ROUND,
};

static int record__mmap_read_all(struct record *rec)
{
	u64 bytes_written = rec->bytes_written;
	int i;
	int rc = 0;

	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
		struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;

		if (rec->evlist->mmap[i].base) {
			if (record__mmap_read(rec, i) != 0) {
				rc = -1;
				goto out;
			}
		}

		if (mm->base && !rec->opts.auxtrace_snapshot_mode &&
		    record__auxtrace_mmap_read(rec, mm) != 0) {
			rc = -1;
			goto out;
		}
	}

	/*
	 * Mark the round finished in case we wrote
	 * at least one event.
	 */
	if (bytes_written != rec->bytes_written)
		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));

out:
	return rc;
}

static void record__init_features(struct record *rec)
{
	struct perf_session *session = rec->session;
	int feat;

	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
		perf_header__set_feat(&session->header, feat);

	if (rec->no_buildid)
		perf_header__clear_feat(&session->header, HEADER_BUILD_ID);

	if (!have_tracepoints(&rec->evlist->entries))
		perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);

	if (!rec->opts.branch_stack)
		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);

	if (!rec->opts.full_auxtrace)
		perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
}

static volatile int workload_exec_errno;

/*
 * perf_evlist__prepare_workload will send a SIGUSR1
 * if the fork fails, since we asked by setting its
 * want_signal to true.
 */
static void workload_exec_failed_signal(int signo __maybe_unused,
					siginfo_t *info,
					void *ucontext __maybe_unused)
{
	workload_exec_errno = info->si_value.sival_int;
	done = 1;
	child_finished = 1;
}

static void snapshot_sig_handler(int sig);

static int __cmd_record(struct record *rec, int argc, const char **argv)
{
	int err;
	int status = 0;
	unsigned long waking = 0;
	const bool forks = argc > 0;
	struct machine *machine;
	struct perf_tool *tool = &rec->tool;
	struct record_opts *opts = &rec->opts;
	struct perf_data_file *file = &rec->file;
	struct perf_session *session;
	bool disabled = false, draining = false;
	int fd;

	rec->progname = argv[0];

	atexit(record__sig_exit);
	signal(SIGCHLD, sig_handler);
	signal(SIGINT, sig_handler);
	signal(SIGTERM, sig_handler);
	if (rec->opts.auxtrace_snapshot_mode)
		signal(SIGUSR2, snapshot_sig_handler);
	else
		signal(SIGUSR2, SIG_IGN);

	session = perf_session__new(file, false, tool);
	if (session == NULL) {
		pr_err("Perf session creation failed.\n");
		return -1;
	}

	fd = perf_data_file__fd(file);
	rec->session = session;

	record__init_features(rec);

	if (forks) {
		err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
						    argv, file->is_pipe,
						    workload_exec_failed_signal);
		if (err < 0) {
			pr_err("Couldn't run the workload!\n");
			status = err;
			goto out_delete_session;
		}
	}

	if (record__open(rec) != 0) {
		err = -1;
		goto out_child;
	}

	/*
	 * Normally perf_session__new would do this, but it doesn't have the
	 * evlist.
	 */
	if (rec->tool.ordered_events && !perf_evlist__sample_id_all(rec->evlist)) {
		pr_warning("WARNING: No sample_id_all support, falling back to unordered processing\n");
		rec->tool.ordered_events = false;
	}

	if (!rec->evlist->nr_groups)
		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);

	if (file->is_pipe) {
		err = perf_header__write_pipe(fd);
		if (err < 0)
			goto out_child;
	} else {
		err = perf_session__write_header(session, rec->evlist, fd, false);
		if (err < 0)
			goto out_child;
	}

	if (!rec->no_buildid
	    && !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
		pr_err("Couldn't generate buildids. "
		       "Use --no-buildid to profile anyway.\n");
		err = -1;
		goto out_child;
	}

	machine = &session->machines.host;

	if (file->is_pipe) {
		err = perf_event__synthesize_attrs(tool, session,
						   process_synthesized_event);
		if (err < 0) {
			pr_err("Couldn't synthesize attrs.\n");
			goto out_child;
		}

		if (have_tracepoints(&rec->evlist->entries)) {
			/*
			 * FIXME err <= 0 here actually means that
			 * there were no tracepoints so its not really
			 * an error, just that we don't need to
			 * synthesize anything.  We really have to
			 * return this more properly and also
			 * propagate errors that now are calling die()
			 */
			err = perf_event__synthesize_tracing_data(tool,	fd, rec->evlist,
								  process_synthesized_event);
			if (err <= 0) {
				pr_err("Couldn't record tracing data.\n");
				goto out_child;
			}
			rec->bytes_written += err;
		}
	}

	if (rec->opts.full_auxtrace) {
		err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
					session, process_synthesized_event);
		if (err)
			goto out_delete_session;
	}

	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
						 machine);
	if (err < 0)
		pr_err("Couldn't record kernel reference relocation symbol\n"
		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
		       "Check /proc/kallsyms permission or run as root.\n");

	err = perf_event__synthesize_modules(tool, process_synthesized_event,
					     machine);
	if (err < 0)
		pr_err("Couldn't record kernel module information.\n"
		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
		       "Check /proc/modules permission or run as root.\n");

	if (perf_guest) {
		machines__process_guests(&session->machines,
					 perf_event__synthesize_guest_os, tool);
	}

	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
					    process_synthesized_event, opts->sample_address,
					    opts->proc_map_timeout);
	if (err != 0)
		goto out_child;

	if (rec->realtime_prio) {
		struct sched_param param;

		param.sched_priority = rec->realtime_prio;
		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
			pr_err("Could not set realtime priority.\n");
			err = -1;
			goto out_child;
		}
	}

	/*
	 * When perf is starting the traced process, all the events
	 * (apart from group members) have enable_on_exec=1 set,
	 * so don't spoil it by prematurely enabling them.
	 */
	if (!target__none(&opts->target) && !opts->initial_delay)
		perf_evlist__enable(rec->evlist);

	/*
	 * Let the child rip
	 */
	if (forks)
		perf_evlist__start_workload(rec->evlist);

	if (opts->initial_delay) {
		usleep(opts->initial_delay * 1000);
		perf_evlist__enable(rec->evlist);
	}

	auxtrace_snapshot_enabled = 1;
	for (;;) {
		int hits = rec->samples;

		if (record__mmap_read_all(rec) < 0) {
			auxtrace_snapshot_enabled = 0;
			err = -1;
			goto out_child;
		}

		if (auxtrace_record__snapshot_started) {
			auxtrace_record__snapshot_started = 0;
			if (!auxtrace_snapshot_err)
				record__read_auxtrace_snapshot(rec);
			if (auxtrace_snapshot_err) {
				pr_err("AUX area tracing snapshot failed\n");
				err = -1;
				goto out_child;
			}
		}

		if (hits == rec->samples) {
			if (done || draining)
				break;
			err = perf_evlist__poll(rec->evlist, -1);
			/*
			 * Propagate error, only if there's any. Ignore positive
			 * number of returned events and interrupt error.
			 */
			if (err > 0 || (err < 0 && errno == EINTR))
				err = 0;
			waking++;

			if (perf_evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0)
				draining = true;
		}

		/*
		 * When perf is starting the traced process, at the end events
		 * die with the process and we wait for that. Thus no need to
		 * disable events in this case.
		 */
		if (done && !disabled && !target__none(&opts->target)) {
			auxtrace_snapshot_enabled = 0;
			perf_evlist__disable(rec->evlist);
			disabled = true;
		}
	}
	auxtrace_snapshot_enabled = 0;

	if (forks && workload_exec_errno) {
		char msg[STRERR_BUFSIZE];
		const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
		pr_err("Workload failed: %s\n", emsg);
		err = -1;
		goto out_child;
	}

	if (!quiet)
		fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);

out_child:
	if (forks) {
		int exit_status;

		if (!child_finished)
			kill(rec->evlist->workload.pid, SIGTERM);

		wait(&exit_status);

		if (err < 0)
			status = err;
		else if (WIFEXITED(exit_status))
			status = WEXITSTATUS(exit_status);
		else if (WIFSIGNALED(exit_status))
			signr = WTERMSIG(exit_status);
	} else
		status = err;

	/* this will be recalculated during process_buildids() */
	rec->samples = 0;

	if (!err && !file->is_pipe) {
		rec->session->header.data_size += rec->bytes_written;
		file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);

		if (!rec->no_buildid) {
			process_buildids(rec);
			/*
			 * We take all buildids when the file contains
			 * AUX area tracing data because we do not decode the
			 * trace because it would take too long.
			 */
			if (rec->opts.full_auxtrace)
				dsos__hit_all(rec->session);
		}
		perf_session__write_header(rec->session, rec->evlist, fd, true);
	}

	if (!err && !quiet) {
		char samples[128];

		if (rec->samples && !rec->opts.full_auxtrace)
			scnprintf(samples, sizeof(samples),
				  " (%" PRIu64 " samples)", rec->samples);
		else
			samples[0] = '\0';

		fprintf(stderr,	"[ perf record: Captured and wrote %.3f MB %s%s ]\n",
			perf_data_file__size(file) / 1024.0 / 1024.0,
			file->path, samples);
	}

out_delete_session:
	perf_session__delete(session);
	return status;
}

static void callchain_debug(void)
{
	static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF", "LBR" };

	pr_debug("callchain: type %s\n", str[callchain_param.record_mode]);

	if (callchain_param.record_mode == CALLCHAIN_DWARF)
		pr_debug("callchain: stack dump size %d\n",
			 callchain_param.dump_size);
}

int record_parse_callchain_opt(const struct option *opt __maybe_unused,
			       const char *arg,
			       int unset)
{
	int ret;

	callchain_param.enabled = !unset;

	/* --no-call-graph */
	if (unset) {
		callchain_param.record_mode = CALLCHAIN_NONE;
		pr_debug("callchain: disabled\n");
		return 0;
	}

	ret = parse_callchain_record_opt(arg);
	if (!ret)
		callchain_debug();

	return ret;
}

int record_callchain_opt(const struct option *opt __maybe_unused,
			 const char *arg __maybe_unused,
			 int unset __maybe_unused)
{
	callchain_param.enabled = true;

	if (callchain_param.record_mode == CALLCHAIN_NONE)
		callchain_param.record_mode = CALLCHAIN_FP;

	callchain_debug();
	return 0;
}

static int perf_record_config(const char *var, const char *value, void *cb)
{
	if (!strcmp(var, "record.call-graph"))
		var = "call-graph.record-mode"; /* fall-through */

	return perf_default_config(var, value, cb);
}

struct clockid_map {
	const char *name;
	int clockid;
};

#define CLOCKID_MAP(n, c)	\
	{ .name = n, .clockid = (c), }

#define CLOCKID_END	{ .name = NULL, }


/*
 * Add the missing ones, we need to build on many distros...
 */
#ifndef CLOCK_MONOTONIC_RAW
#define CLOCK_MONOTONIC_RAW 4
#endif
#ifndef CLOCK_BOOTTIME
#define CLOCK_BOOTTIME 7
#endif
#ifndef CLOCK_TAI
#define CLOCK_TAI 11
#endif

static const struct clockid_map clockids[] = {
	/* available for all events, NMI safe */
	CLOCKID_MAP("monotonic", CLOCK_MONOTONIC),
	CLOCKID_MAP("monotonic_raw", CLOCK_MONOTONIC_RAW),

	/* available for some events */
	CLOCKID_MAP("realtime", CLOCK_REALTIME),
	CLOCKID_MAP("boottime", CLOCK_BOOTTIME),
	CLOCKID_MAP("tai", CLOCK_TAI),

	/* available for the lazy */
	CLOCKID_MAP("mono", CLOCK_MONOTONIC),
	CLOCKID_MAP("raw", CLOCK_MONOTONIC_RAW),
	CLOCKID_MAP("real", CLOCK_REALTIME),
	CLOCKID_MAP("boot", CLOCK_BOOTTIME),

	CLOCKID_END,
};

static int parse_clockid(const struct option *opt, const char *str, int unset)
{
	struct record_opts *opts = (struct record_opts *)opt->value;
	const struct clockid_map *cm;
	const char *ostr = str;

	if (unset) {
		opts->use_clockid = 0;
		return 0;
	}

	/* no arg passed */
	if (!str)
		return 0;

	/* no setting it twice */
	if (opts->use_clockid)
		return -1;

	opts->use_clockid = true;

	/* if its a number, we're done */
	if (sscanf(str, "%d", &opts->clockid) == 1)
		return 0;

	/* allow a "CLOCK_" prefix to the name */
	if (!strncasecmp(str, "CLOCK_", 6))
		str += 6;

	for (cm = clockids; cm->name; cm++) {
		if (!strcasecmp(str, cm->name)) {
			opts->clockid = cm->clockid;
			return 0;
		}
	}

	opts->use_clockid = false;
	ui__warning("unknown clockid %s, check man page\n", ostr);
	return -1;
}

static int record__parse_mmap_pages(const struct option *opt,
				    const char *str,
				    int unset __maybe_unused)
{
	struct record_opts *opts = opt->value;
	char *s, *p;
	unsigned int mmap_pages;
	int ret;

	if (!str)
		return -EINVAL;

	s = strdup(str);
	if (!s)
		return -ENOMEM;

	p = strchr(s, ',');
	if (p)
		*p = '\0';

	if (*s) {
		ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s);
		if (ret)
			goto out_free;
		opts->mmap_pages = mmap_pages;
	}

	if (!p) {
		ret = 0;
		goto out_free;
	}

	ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1);
	if (ret)
		goto out_free;

	opts->auxtrace_mmap_pages = mmap_pages;

out_free:
	free(s);
	return ret;
}

static const char * const __record_usage[] = {
	"perf record [<options>] [<command>]",
	"perf record [<options>] -- <command> [<options>]",
	NULL
};
const char * const *record_usage = __record_usage;

/*
 * XXX Ideally would be local to cmd_record() and passed to a record__new
 * because we need to have access to it in record__exit, that is called
 * after cmd_record() exits, but since record_options need to be accessible to
 * builtin-script, leave it here.
 *
 * At least we don't ouch it in all the other functions here directly.
 *
 * Just say no to tons of global variables, sigh.
 */
static struct record record = {
	.opts = {
		.sample_time	     = true,
		.mmap_pages	     = UINT_MAX,
		.user_freq	     = UINT_MAX,
		.user_interval	     = ULLONG_MAX,
		.freq		     = 4000,
		.target		     = {
			.uses_mmap   = true,
			.default_per_cpu = true,
		},
		.proc_map_timeout     = 500,
	},
	.tool = {
		.sample		= process_sample_event,
		.fork		= perf_event__process_fork,
		.exit		= perf_event__process_exit,
		.comm		= perf_event__process_comm,
		.mmap		= perf_event__process_mmap,
		.mmap2		= perf_event__process_mmap2,
		.ordered_events	= true,
	},
};

#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "

#ifdef HAVE_DWARF_UNWIND_SUPPORT
const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf lbr";
#else
const char record_callchain_help[] = CALLCHAIN_HELP "fp lbr";
#endif

/*
 * XXX Will stay a global variable till we fix builtin-script.c to stop messing
 * with it and switch to use the library functions in perf_evlist that came
 * from builtin-record.c, i.e. use record_opts,
 * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
 * using pipes, etc.
 */
struct option __record_options[] = {
	OPT_CALLBACK('e', "event", &record.evlist, "event",
		     "event selector. use 'perf list' to list available events",
		     parse_events_option),
	OPT_CALLBACK(0, "filter", &record.evlist, "filter",
		     "event filter", parse_filter),
	OPT_STRING('p', "pid", &record.opts.target.pid, "pid",
		    "record events on existing process id"),
	OPT_STRING('t', "tid", &record.opts.target.tid, "tid",
		    "record events on existing thread id"),
	OPT_INTEGER('r', "realtime", &record.realtime_prio,
		    "collect data with this RT SCHED_FIFO priority"),
	OPT_BOOLEAN(0, "no-buffering", &record.opts.no_buffering,
		    "collect data without buffering"),
	OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples,
		    "collect raw sample records from all opened counters"),
	OPT_BOOLEAN('a', "all-cpus", &record.opts.target.system_wide,
			    "system-wide collection from all CPUs"),
	OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
		    "list of cpus to monitor"),
	OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
	OPT_STRING('o', "output", &record.file.path, "file",
		    "output file name"),
	OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
			&record.opts.no_inherit_set,
			"child tasks do not inherit counters"),
	OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
	OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
		     "number of mmap data pages and AUX area tracing mmap pages",
		     record__parse_mmap_pages),
	OPT_BOOLEAN(0, "group", &record.opts.group,
		    "put the counters into a counter group"),
	OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
			   NULL, "enables call-graph recording" ,
			   &record_callchain_opt),
	OPT_CALLBACK(0, "call-graph", &record.opts,
		     "mode[,dump_size]", record_callchain_help,
		     &record_parse_callchain_opt),
	OPT_INCR('v', "verbose", &verbose,
		    "be more verbose (show counter open errors, etc)"),
	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
	OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
		    "per thread counts"),
	OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
	OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Record the sample timestamps"),
	OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
		    "don't sample"),
	OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
		    "do not update the buildid cache"),
	OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
		    "do not collect buildids in perf.data"),
	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
		     "monitor event in cgroup name only",
		     parse_cgroups),
	OPT_UINTEGER('D', "delay", &record.opts.initial_delay,
		  "ms to wait before starting measurement after program start"),
	OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
		   "user to profile"),

	OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack,
		     "branch any", "sample any taken branches",
		     parse_branch_stack),

	OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack,
		     "branch filter mask", "branch stack filter modes",
		     parse_branch_stack),
	OPT_BOOLEAN('W', "weight", &record.opts.sample_weight,
		    "sample by weight (on special events only)"),
	OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
		    "sample transaction flags (special events only)"),
	OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
		    "use per-thread mmaps"),
	OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs,
		    "Sample machine registers on interrupt"),
	OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
		    "Record running/enabled time of read (:S) events"),
	OPT_CALLBACK('k', "clockid", &record.opts,
	"clockid", "clockid to use for events, see clock_gettime()",
	parse_clockid),
	OPT_STRING_OPTARG('S', "snapshot", &record.opts.auxtrace_snapshot_opts,
			  "opts", "AUX area tracing Snapshot Mode", ""),
	OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
			"per thread proc mmap processing timeout in ms"),
	OPT_END()
};

struct option *record_options = __record_options;

int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
{
	int err;
	struct record *rec = &record;
	char errbuf[BUFSIZ];

	rec->evlist = perf_evlist__new();
	if (rec->evlist == NULL)
		return -ENOMEM;

	perf_config(perf_record_config, rec);

	argc = parse_options(argc, argv, record_options, record_usage,
			    PARSE_OPT_STOP_AT_NON_OPTION);
	if (!argc && target__none(&rec->opts.target))
		usage_with_options(record_usage, record_options);

	if (nr_cgroups && !rec->opts.target.system_wide) {
		ui__error("cgroup monitoring only available in"
			  " system-wide mode\n");
		usage_with_options(record_usage, record_options);
	}

	if (!rec->itr) {
		rec->itr = auxtrace_record__init(rec->evlist, &err);
		if (err)
			return err;
	}

	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
					      rec->opts.auxtrace_snapshot_opts);
	if (err)
		return err;

	err = -ENOMEM;

	symbol__init(NULL);

	if (symbol_conf.kptr_restrict)
		pr_warning(
"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
"check /proc/sys/kernel/kptr_restrict.\n\n"
"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
"file is not found in the buildid cache or in the vmlinux path.\n\n"
"Samples in kernel modules won't be resolved at all.\n\n"
"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
"even with a suitable vmlinux or kallsyms file.\n\n");

	if (rec->no_buildid_cache || rec->no_buildid)
		disable_buildid_cache();

	if (rec->evlist->nr_entries == 0 &&
	    perf_evlist__add_default(rec->evlist) < 0) {
		pr_err("Not enough memory for event selector list\n");
		goto out_symbol_exit;
	}

	if (rec->opts.target.tid && !rec->opts.no_inherit_set)
		rec->opts.no_inherit = true;

	err = target__validate(&rec->opts.target);
	if (err) {
		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
		ui__warning("%s", errbuf);
	}

	err = target__parse_uid(&rec->opts.target);
	if (err) {
		int saved_errno = errno;

		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
		ui__error("%s", errbuf);

		err = -saved_errno;
		goto out_symbol_exit;
	}

	err = -ENOMEM;
	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
		usage_with_options(record_usage, record_options);

	err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
	if (err)
		goto out_symbol_exit;

	if (record_opts__config(&rec->opts)) {
		err = -EINVAL;
		goto out_symbol_exit;
	}

	err = __cmd_record(&record, argc, argv);
out_symbol_exit:
	perf_evlist__delete(rec->evlist);
	symbol__exit();
	auxtrace_record__free(rec->itr);
	return err;
}

static void snapshot_sig_handler(int sig __maybe_unused)
{
	if (!auxtrace_snapshot_enabled)
		return;
	auxtrace_snapshot_enabled = 0;
	auxtrace_snapshot_err = auxtrace_record__snapshot_start(record.itr);
	auxtrace_record__snapshot_started = 1;
}