summaryrefslogtreecommitdiff
path: root/tools/perf/util/session.c
blob: 3c1b30103d547725ca0ec1a48ea117052ae641cc (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
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
#include <linux/kernel.h>
#include <traceevent/event-parse.h>

#include <byteswap.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/mman.h>

#include "evlist.h"
#include "evsel.h"
#include "session.h"
#include "tool.h"
#include "sort.h"
#include "util.h"
#include "cpumap.h"
#include "perf_regs.h"
#include "vdso.h"

static int perf_session__open(struct perf_session *self)
{
	struct perf_data_file *file = self->file;

	if (perf_session__read_header(self) < 0) {
		pr_err("incompatible file format (rerun with -v to learn more)");
		return -1;
	}

	if (perf_data_file__is_pipe(file))
		return 0;

	if (!perf_evlist__valid_sample_type(self->evlist)) {
		pr_err("non matching sample_type");
		return -1;
	}

	if (!perf_evlist__valid_sample_id_all(self->evlist)) {
		pr_err("non matching sample_id_all");
		return -1;
	}

	if (!perf_evlist__valid_read_format(self->evlist)) {
		pr_err("non matching read_format");
		return -1;
	}

	return 0;
}

void perf_session__set_id_hdr_size(struct perf_session *session)
{
	u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist);

	machines__set_id_hdr_size(&session->machines, id_hdr_size);
}

int perf_session__create_kernel_maps(struct perf_session *self)
{
	int ret = machine__create_kernel_maps(&self->machines.host);

	if (ret >= 0)
		ret = machines__create_guest_kernel_maps(&self->machines);
	return ret;
}

static void perf_session__destroy_kernel_maps(struct perf_session *self)
{
	machines__destroy_kernel_maps(&self->machines);
}

struct perf_session *perf_session__new(struct perf_data_file *file,
				       bool repipe, struct perf_tool *tool)
{
	struct perf_session *self;

	self = zalloc(sizeof(*self));
	if (!self)
		goto out;

	self->repipe = repipe;
	INIT_LIST_HEAD(&self->ordered_samples.samples);
	INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
	INIT_LIST_HEAD(&self->ordered_samples.to_free);
	machines__init(&self->machines);

	if (file) {
		if (perf_data_file__open(file))
			goto out_delete;

		self->file = file;

		if (perf_data_file__is_read(file)) {
			if (perf_session__open(self) < 0)
				goto out_close;

			perf_session__set_id_hdr_size(self);
		}
	}

	if (!file || perf_data_file__is_write(file)) {
		/*
		 * In O_RDONLY mode this will be performed when reading the
		 * kernel MMAP event, in perf_event__process_mmap().
		 */
		if (perf_session__create_kernel_maps(self) < 0)
			goto out_delete;
	}

	if (tool && tool->ordering_requires_timestamps &&
	    tool->ordered_samples && !perf_evlist__sample_id_all(self->evlist)) {
		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
		tool->ordered_samples = false;
	}

	return self;

 out_close:
	perf_data_file__close(file);
 out_delete:
	perf_session__delete(self);
 out:
	return NULL;
}

static void perf_session__delete_dead_threads(struct perf_session *session)
{
	machine__delete_dead_threads(&session->machines.host);
}

static void perf_session__delete_threads(struct perf_session *session)
{
	machine__delete_threads(&session->machines.host);
}

static void perf_session_env__delete(struct perf_session_env *env)
{
	free(env->hostname);
	free(env->os_release);
	free(env->version);
	free(env->arch);
	free(env->cpu_desc);
	free(env->cpuid);

	free(env->cmdline);
	free(env->sibling_cores);
	free(env->sibling_threads);
	free(env->numa_nodes);
	free(env->pmu_mappings);
}

void perf_session__delete(struct perf_session *self)
{
	perf_session__destroy_kernel_maps(self);
	perf_session__delete_dead_threads(self);
	perf_session__delete_threads(self);
	perf_session_env__delete(&self->header.env);
	machines__exit(&self->machines);
	if (self->file)
		perf_data_file__close(self->file);
	free(self);
	vdso__exit();
}

static int process_event_synth_tracing_data_stub(struct perf_tool *tool
						 __maybe_unused,
						 union perf_event *event
						 __maybe_unused,
						 struct perf_session *session
						__maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused,
					 union perf_event *event __maybe_unused,
					 struct perf_evlist **pevlist
					 __maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
				     union perf_event *event __maybe_unused,
				     struct perf_sample *sample __maybe_unused,
				     struct perf_evsel *evsel __maybe_unused,
				     struct machine *machine __maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_event_stub(struct perf_tool *tool __maybe_unused,
			      union perf_event *event __maybe_unused,
			      struct perf_sample *sample __maybe_unused,
			      struct machine *machine __maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
				       union perf_event *event __maybe_unused,
				       struct perf_session *perf_session
				       __maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_finished_round(struct perf_tool *tool,
				  union perf_event *event,
				  struct perf_session *session);

void perf_tool__fill_defaults(struct perf_tool *tool)
{
	if (tool->sample == NULL)
		tool->sample = process_event_sample_stub;
	if (tool->mmap == NULL)
		tool->mmap = process_event_stub;
	if (tool->mmap2 == NULL)
		tool->mmap2 = process_event_stub;
	if (tool->comm == NULL)
		tool->comm = process_event_stub;
	if (tool->fork == NULL)
		tool->fork = process_event_stub;
	if (tool->exit == NULL)
		tool->exit = process_event_stub;
	if (tool->lost == NULL)
		tool->lost = perf_event__process_lost;
	if (tool->read == NULL)
		tool->read = process_event_sample_stub;
	if (tool->throttle == NULL)
		tool->throttle = process_event_stub;
	if (tool->unthrottle == NULL)
		tool->unthrottle = process_event_stub;
	if (tool->attr == NULL)
		tool->attr = process_event_synth_attr_stub;
	if (tool->tracing_data == NULL)
		tool->tracing_data = process_event_synth_tracing_data_stub;
	if (tool->build_id == NULL)
		tool->build_id = process_finished_round_stub;
	if (tool->finished_round == NULL) {
		if (tool->ordered_samples)
			tool->finished_round = process_finished_round;
		else
			tool->finished_round = process_finished_round_stub;
	}
}
 
void mem_bswap_32(void *src, int byte_size)
{
	u32 *m = src;
	while (byte_size > 0) {
		*m = bswap_32(*m);
		byte_size -= sizeof(u32);
		++m;
	}
}

void mem_bswap_64(void *src, int byte_size)
{
	u64 *m = src;

	while (byte_size > 0) {
		*m = bswap_64(*m);
		byte_size -= sizeof(u64);
		++m;
	}
}

static void swap_sample_id_all(union perf_event *event, void *data)
{
	void *end = (void *) event + event->header.size;
	int size = end - data;

	BUG_ON(size % sizeof(u64));
	mem_bswap_64(data, size);
}

static void perf_event__all64_swap(union perf_event *event,
				   bool sample_id_all __maybe_unused)
{
	struct perf_event_header *hdr = &event->header;
	mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
}

static void perf_event__comm_swap(union perf_event *event, bool sample_id_all)
{
	event->comm.pid = bswap_32(event->comm.pid);
	event->comm.tid = bswap_32(event->comm.tid);

	if (sample_id_all) {
		void *data = &event->comm.comm;

		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
		swap_sample_id_all(event, data);
	}
}

static void perf_event__mmap_swap(union perf_event *event,
				  bool sample_id_all)
{
	event->mmap.pid	  = bswap_32(event->mmap.pid);
	event->mmap.tid	  = bswap_32(event->mmap.tid);
	event->mmap.start = bswap_64(event->mmap.start);
	event->mmap.len	  = bswap_64(event->mmap.len);
	event->mmap.pgoff = bswap_64(event->mmap.pgoff);

	if (sample_id_all) {
		void *data = &event->mmap.filename;

		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
		swap_sample_id_all(event, data);
	}
}

static void perf_event__mmap2_swap(union perf_event *event,
				  bool sample_id_all)
{
	event->mmap2.pid   = bswap_32(event->mmap2.pid);
	event->mmap2.tid   = bswap_32(event->mmap2.tid);
	event->mmap2.start = bswap_64(event->mmap2.start);
	event->mmap2.len   = bswap_64(event->mmap2.len);
	event->mmap2.pgoff = bswap_64(event->mmap2.pgoff);
	event->mmap2.maj   = bswap_32(event->mmap2.maj);
	event->mmap2.min   = bswap_32(event->mmap2.min);
	event->mmap2.ino   = bswap_64(event->mmap2.ino);

	if (sample_id_all) {
		void *data = &event->mmap2.filename;

		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
		swap_sample_id_all(event, data);
	}
}
static void perf_event__task_swap(union perf_event *event, bool sample_id_all)
{
	event->fork.pid	 = bswap_32(event->fork.pid);
	event->fork.tid	 = bswap_32(event->fork.tid);
	event->fork.ppid = bswap_32(event->fork.ppid);
	event->fork.ptid = bswap_32(event->fork.ptid);
	event->fork.time = bswap_64(event->fork.time);

	if (sample_id_all)
		swap_sample_id_all(event, &event->fork + 1);
}

static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
{
	event->read.pid		 = bswap_32(event->read.pid);
	event->read.tid		 = bswap_32(event->read.tid);
	event->read.value	 = bswap_64(event->read.value);
	event->read.time_enabled = bswap_64(event->read.time_enabled);
	event->read.time_running = bswap_64(event->read.time_running);
	event->read.id		 = bswap_64(event->read.id);

	if (sample_id_all)
		swap_sample_id_all(event, &event->read + 1);
}

static void perf_event__throttle_swap(union perf_event *event,
				      bool sample_id_all)
{
	event->throttle.time	  = bswap_64(event->throttle.time);
	event->throttle.id	  = bswap_64(event->throttle.id);
	event->throttle.stream_id = bswap_64(event->throttle.stream_id);

	if (sample_id_all)
		swap_sample_id_all(event, &event->throttle + 1);
}

static u8 revbyte(u8 b)
{
	int rev = (b >> 4) | ((b & 0xf) << 4);
	rev = ((rev & 0xcc) >> 2) | ((rev & 0x33) << 2);
	rev = ((rev & 0xaa) >> 1) | ((rev & 0x55) << 1);
	return (u8) rev;
}

/*
 * XXX this is hack in attempt to carry flags bitfield
 * throught endian village. ABI says:
 *
 * Bit-fields are allocated from right to left (least to most significant)
 * on little-endian implementations and from left to right (most to least
 * significant) on big-endian implementations.
 *
 * The above seems to be byte specific, so we need to reverse each
 * byte of the bitfield. 'Internet' also says this might be implementation
 * specific and we probably need proper fix and carry perf_event_attr
 * bitfield flags in separate data file FEAT_ section. Thought this seems
 * to work for now.
 */
static void swap_bitfield(u8 *p, unsigned len)
{
	unsigned i;

	for (i = 0; i < len; i++) {
		*p = revbyte(*p);
		p++;
	}
}

/* exported for swapping attributes in file header */
void perf_event__attr_swap(struct perf_event_attr *attr)
{
	attr->type		= bswap_32(attr->type);
	attr->size		= bswap_32(attr->size);
	attr->config		= bswap_64(attr->config);
	attr->sample_period	= bswap_64(attr->sample_period);
	attr->sample_type	= bswap_64(attr->sample_type);
	attr->read_format	= bswap_64(attr->read_format);
	attr->wakeup_events	= bswap_32(attr->wakeup_events);
	attr->bp_type		= bswap_32(attr->bp_type);
	attr->bp_addr		= bswap_64(attr->bp_addr);
	attr->bp_len		= bswap_64(attr->bp_len);
	attr->branch_sample_type = bswap_64(attr->branch_sample_type);
	attr->sample_regs_user	 = bswap_64(attr->sample_regs_user);
	attr->sample_stack_user  = bswap_32(attr->sample_stack_user);

	swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
}

static void perf_event__hdr_attr_swap(union perf_event *event,
				      bool sample_id_all __maybe_unused)
{
	size_t size;

	perf_event__attr_swap(&event->attr.attr);

	size = event->header.size;
	size -= (void *)&event->attr.id - (void *)event;
	mem_bswap_64(event->attr.id, size);
}

static void perf_event__event_type_swap(union perf_event *event,
					bool sample_id_all __maybe_unused)
{
	event->event_type.event_type.event_id =
		bswap_64(event->event_type.event_type.event_id);
}

static void perf_event__tracing_data_swap(union perf_event *event,
					  bool sample_id_all __maybe_unused)
{
	event->tracing_data.size = bswap_32(event->tracing_data.size);
}

typedef void (*perf_event__swap_op)(union perf_event *event,
				    bool sample_id_all);

static perf_event__swap_op perf_event__swap_ops[] = {
	[PERF_RECORD_MMAP]		  = perf_event__mmap_swap,
	[PERF_RECORD_MMAP2]		  = perf_event__mmap2_swap,
	[PERF_RECORD_COMM]		  = perf_event__comm_swap,
	[PERF_RECORD_FORK]		  = perf_event__task_swap,
	[PERF_RECORD_EXIT]		  = perf_event__task_swap,
	[PERF_RECORD_LOST]		  = perf_event__all64_swap,
	[PERF_RECORD_READ]		  = perf_event__read_swap,
	[PERF_RECORD_THROTTLE]		  = perf_event__throttle_swap,
	[PERF_RECORD_UNTHROTTLE]	  = perf_event__throttle_swap,
	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
	[PERF_RECORD_HEADER_MAX]	  = NULL,
};

struct sample_queue {
	u64			timestamp;
	u64			file_offset;
	union perf_event	*event;
	struct list_head	list;
};

static void perf_session_free_sample_buffers(struct perf_session *session)
{
	struct ordered_samples *os = &session->ordered_samples;

	while (!list_empty(&os->to_free)) {
		struct sample_queue *sq;

		sq = list_entry(os->to_free.next, struct sample_queue, list);
		list_del(&sq->list);
		free(sq);
	}
}

static int perf_session_deliver_event(struct perf_session *session,
				      union perf_event *event,
				      struct perf_sample *sample,
				      struct perf_tool *tool,
				      u64 file_offset);

static int flush_sample_queue(struct perf_session *s,
		       struct perf_tool *tool)
{
	struct ordered_samples *os = &s->ordered_samples;
	struct list_head *head = &os->samples;
	struct sample_queue *tmp, *iter;
	struct perf_sample sample;
	u64 limit = os->next_flush;
	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
	bool show_progress = limit == ULLONG_MAX;
	struct ui_progress prog;
	int ret;

	if (!tool->ordered_samples || !limit)
		return 0;

	if (show_progress)
		ui_progress__init(&prog, os->nr_samples, "Processing time ordered events...");

	list_for_each_entry_safe(iter, tmp, head, list) {
		if (session_done())
			return 0;

		if (iter->timestamp > limit)
			break;

		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
		if (ret)
			pr_err("Can't parse sample, err = %d\n", ret);
		else {
			ret = perf_session_deliver_event(s, iter->event, &sample, tool,
							 iter->file_offset);
			if (ret)
				return ret;
		}

		os->last_flush = iter->timestamp;
		list_del(&iter->list);
		list_add(&iter->list, &os->sample_cache);

		if (show_progress)
			ui_progress__update(&prog, 1);
	}

	if (list_empty(head)) {
		os->last_sample = NULL;
	} else if (last_ts <= limit) {
		os->last_sample =
			list_entry(head->prev, struct sample_queue, list);
	}

	os->nr_samples = 0;

	return 0;
}

/*
 * When perf record finishes a pass on every buffers, it records this pseudo
 * event.
 * We record the max timestamp t found in the pass n.
 * Assuming these timestamps are monotonic across cpus, we know that if
 * a buffer still has events with timestamps below t, they will be all
 * available and then read in the pass n + 1.
 * Hence when we start to read the pass n + 2, we can safely flush every
 * events with timestamps below t.
 *
 *    ============ PASS n =================
 *       CPU 0         |   CPU 1
 *                     |
 *    cnt1 timestamps  |   cnt2 timestamps
 *          1          |         2
 *          2          |         3
 *          -          |         4  <--- max recorded
 *
 *    ============ PASS n + 1 ==============
 *       CPU 0         |   CPU 1
 *                     |
 *    cnt1 timestamps  |   cnt2 timestamps
 *          3          |         5
 *          4          |         6
 *          5          |         7 <---- max recorded
 *
 *      Flush every events below timestamp 4
 *
 *    ============ PASS n + 2 ==============
 *       CPU 0         |   CPU 1
 *                     |
 *    cnt1 timestamps  |   cnt2 timestamps
 *          6          |         8
 *          7          |         9
 *          -          |         10
 *
 *      Flush every events below timestamp 7
 *      etc...
 */
static int process_finished_round(struct perf_tool *tool,
				  union perf_event *event __maybe_unused,
				  struct perf_session *session)
{
	int ret = flush_sample_queue(session, tool);
	if (!ret)
		session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;

	return ret;
}

/* The queue is ordered by time */
static void __queue_event(struct sample_queue *new, struct perf_session *s)
{
	struct ordered_samples *os = &s->ordered_samples;
	struct sample_queue *sample = os->last_sample;
	u64 timestamp = new->timestamp;
	struct list_head *p;

	++os->nr_samples;
	os->last_sample = new;

	if (!sample) {
		list_add(&new->list, &os->samples);
		os->max_timestamp = timestamp;
		return;
	}

	/*
	 * last_sample might point to some random place in the list as it's
	 * the last queued event. We expect that the new event is close to
	 * this.
	 */
	if (sample->timestamp <= timestamp) {
		while (sample->timestamp <= timestamp) {
			p = sample->list.next;
			if (p == &os->samples) {
				list_add_tail(&new->list, &os->samples);
				os->max_timestamp = timestamp;
				return;
			}
			sample = list_entry(p, struct sample_queue, list);
		}
		list_add_tail(&new->list, &sample->list);
	} else {
		while (sample->timestamp > timestamp) {
			p = sample->list.prev;
			if (p == &os->samples) {
				list_add(&new->list, &os->samples);
				return;
			}
			sample = list_entry(p, struct sample_queue, list);
		}
		list_add(&new->list, &sample->list);
	}
}

#define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct sample_queue))

int perf_session_queue_event(struct perf_session *s, union perf_event *event,
				    struct perf_sample *sample, u64 file_offset)
{
	struct ordered_samples *os = &s->ordered_samples;
	struct list_head *sc = &os->sample_cache;
	u64 timestamp = sample->time;
	struct sample_queue *new;

	if (!timestamp || timestamp == ~0ULL)
		return -ETIME;

	if (timestamp < s->ordered_samples.last_flush) {
		printf("Warning: Timestamp below last timeslice flush\n");
		return -EINVAL;
	}

	if (!list_empty(sc)) {
		new = list_entry(sc->next, struct sample_queue, list);
		list_del(&new->list);
	} else if (os->sample_buffer) {
		new = os->sample_buffer + os->sample_buffer_idx;
		if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
			os->sample_buffer = NULL;
	} else {
		os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
		if (!os->sample_buffer)
			return -ENOMEM;
		list_add(&os->sample_buffer->list, &os->to_free);
		os->sample_buffer_idx = 2;
		new = os->sample_buffer + 1;
	}

	new->timestamp = timestamp;
	new->file_offset = file_offset;
	new->event = event;

	__queue_event(new, s);

	return 0;
}

static void callchain__printf(struct perf_sample *sample)
{
	unsigned int i;

	printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr);

	for (i = 0; i < sample->callchain->nr; i++)
		printf("..... %2d: %016" PRIx64 "\n",
		       i, sample->callchain->ips[i]);
}

static void branch_stack__printf(struct perf_sample *sample)
{
	uint64_t i;

	printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);

	for (i = 0; i < sample->branch_stack->nr; i++)
		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n",
			i, sample->branch_stack->entries[i].from,
			sample->branch_stack->entries[i].to);
}

static void regs_dump__printf(u64 mask, u64 *regs)
{
	unsigned rid, i = 0;

	for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) {
		u64 val = regs[i++];

		printf(".... %-5s 0x%" PRIx64 "\n",
		       perf_reg_name(rid), val);
	}
}

static void regs_user__printf(struct perf_sample *sample, u64 mask)
{
	struct regs_dump *user_regs = &sample->user_regs;

	if (user_regs->regs) {
		printf("... user regs: mask 0x%" PRIx64 "\n", mask);
		regs_dump__printf(mask, user_regs->regs);
	}
}

static void stack_user__printf(struct stack_dump *dump)
{
	printf("... ustack: size %" PRIu64 ", offset 0x%x\n",
	       dump->size, dump->offset);
}

static void perf_session__print_tstamp(struct perf_session *session,
				       union perf_event *event,
				       struct perf_sample *sample)
{
	u64 sample_type = __perf_evlist__combined_sample_type(session->evlist);

	if (event->header.type != PERF_RECORD_SAMPLE &&
	    !perf_evlist__sample_id_all(session->evlist)) {
		fputs("-1 -1 ", stdout);
		return;
	}

	if ((sample_type & PERF_SAMPLE_CPU))
		printf("%u ", sample->cpu);

	if (sample_type & PERF_SAMPLE_TIME)
		printf("%" PRIu64 " ", sample->time);
}

static void sample_read__printf(struct perf_sample *sample, u64 read_format)
{
	printf("... sample_read:\n");

	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
		printf("...... time enabled %016" PRIx64 "\n",
		       sample->read.time_enabled);

	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
		printf("...... time running %016" PRIx64 "\n",
		       sample->read.time_running);

	if (read_format & PERF_FORMAT_GROUP) {
		u64 i;

		printf(".... group nr %" PRIu64 "\n", sample->read.group.nr);

		for (i = 0; i < sample->read.group.nr; i++) {
			struct sample_read_value *value;

			value = &sample->read.group.values[i];
			printf("..... id %016" PRIx64
			       ", value %016" PRIx64 "\n",
			       value->id, value->value);
		}
	} else
		printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n",
			sample->read.one.id, sample->read.one.value);
}

static void dump_event(struct perf_session *session, union perf_event *event,
		       u64 file_offset, struct perf_sample *sample)
{
	if (!dump_trace)
		return;

	printf("\n%#" PRIx64 " [%#x]: event: %d\n",
	       file_offset, event->header.size, event->header.type);

	trace_event(event);

	if (sample)
		perf_session__print_tstamp(session, event, sample);

	printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
	       event->header.size, perf_event__name(event->header.type));
}

static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
			struct perf_sample *sample)
{
	u64 sample_type;

	if (!dump_trace)
		return;

	printf("(IP, %d): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n",
	       event->header.misc, sample->pid, sample->tid, sample->ip,
	       sample->period, sample->addr);

	sample_type = evsel->attr.sample_type;

	if (sample_type & PERF_SAMPLE_CALLCHAIN)
		callchain__printf(sample);

	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
		branch_stack__printf(sample);

	if (sample_type & PERF_SAMPLE_REGS_USER)
		regs_user__printf(sample, evsel->attr.sample_regs_user);

	if (sample_type & PERF_SAMPLE_STACK_USER)
		stack_user__printf(&sample->user_stack);

	if (sample_type & PERF_SAMPLE_WEIGHT)
		printf("... weight: %" PRIu64 "\n", sample->weight);

	if (sample_type & PERF_SAMPLE_DATA_SRC)
		printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);

	if (sample_type & PERF_SAMPLE_TRANSACTION)
		printf("... transaction: %" PRIx64 "\n", sample->transaction);

	if (sample_type & PERF_SAMPLE_READ)
		sample_read__printf(sample, evsel->attr.read_format);
}

static struct machine *
	perf_session__find_machine_for_cpumode(struct perf_session *session,
					       union perf_event *event,
					       struct perf_sample *sample)
{
	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;

	if (perf_guest &&
	    ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
	     (cpumode == PERF_RECORD_MISC_GUEST_USER))) {
		u32 pid;

		if (event->header.type == PERF_RECORD_MMAP
		    || event->header.type == PERF_RECORD_MMAP2)
			pid = event->mmap.pid;
		else
			pid = sample->pid;

		return perf_session__findnew_machine(session, pid);
	}

	return &session->machines.host;
}

static int deliver_sample_value(struct perf_session *session,
				struct perf_tool *tool,
				union perf_event *event,
				struct perf_sample *sample,
				struct sample_read_value *v,
				struct machine *machine)
{
	struct perf_sample_id *sid;

	sid = perf_evlist__id2sid(session->evlist, v->id);
	if (sid) {
		sample->id     = v->id;
		sample->period = v->value - sid->period;
		sid->period    = v->value;
	}

	if (!sid || sid->evsel == NULL) {
		++session->stats.nr_unknown_id;
		return 0;
	}

	return tool->sample(tool, event, sample, sid->evsel, machine);
}

static int deliver_sample_group(struct perf_session *session,
				struct perf_tool *tool,
				union  perf_event *event,
				struct perf_sample *sample,
				struct machine *machine)
{
	int ret = -EINVAL;
	u64 i;

	for (i = 0; i < sample->read.group.nr; i++) {
		ret = deliver_sample_value(session, tool, event, sample,
					   &sample->read.group.values[i],
					   machine);
		if (ret)
			break;
	}

	return ret;
}

static int
perf_session__deliver_sample(struct perf_session *session,
			     struct perf_tool *tool,
			     union  perf_event *event,
			     struct perf_sample *sample,
			     struct perf_evsel *evsel,
			     struct machine *machine)
{
	/* We know evsel != NULL. */
	u64 sample_type = evsel->attr.sample_type;
	u64 read_format = evsel->attr.read_format;

	/* Standard sample delievery. */
	if (!(sample_type & PERF_SAMPLE_READ))
		return tool->sample(tool, event, sample, evsel, machine);

	/* For PERF_SAMPLE_READ we have either single or group mode. */
	if (read_format & PERF_FORMAT_GROUP)
		return deliver_sample_group(session, tool, event, sample,
					    machine);
	else
		return deliver_sample_value(session, tool, event, sample,
					    &sample->read.one, machine);
}

static int perf_session_deliver_event(struct perf_session *session,
				      union perf_event *event,
				      struct perf_sample *sample,
				      struct perf_tool *tool,
				      u64 file_offset)
{
	struct perf_evsel *evsel;
	struct machine *machine;

	dump_event(session, event, file_offset, sample);

	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
	if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) {
		/*
		 * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here
		 * because the tools right now may apply filters, discarding
		 * some of the samples. For consistency, in the future we
		 * should have something like nr_filtered_samples and remove
		 * the sample->period from total_sample_period, etc, KISS for
		 * now tho.
		 *
		 * Also testing against NULL allows us to handle files without
		 * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the
		 * future probably it'll be a good idea to restrict event
		 * processing via perf_session to files with both set.
		 */
		hists__inc_nr_events(&evsel->hists, event->header.type);
	}

	machine = perf_session__find_machine_for_cpumode(session, event,
							 sample);

	switch (event->header.type) {
	case PERF_RECORD_SAMPLE:
		dump_sample(evsel, event, sample);
		if (evsel == NULL) {
			++session->stats.nr_unknown_id;
			return 0;
		}
		if (machine == NULL) {
			++session->stats.nr_unprocessable_samples;
			return 0;
		}
		return perf_session__deliver_sample(session, tool, event,
						    sample, evsel, machine);
	case PERF_RECORD_MMAP:
		return tool->mmap(tool, event, sample, machine);
	case PERF_RECORD_MMAP2:
		return tool->mmap2(tool, event, sample, machine);
	case PERF_RECORD_COMM:
		return tool->comm(tool, event, sample, machine);
	case PERF_RECORD_FORK:
		return tool->fork(tool, event, sample, machine);
	case PERF_RECORD_EXIT:
		return tool->exit(tool, event, sample, machine);
	case PERF_RECORD_LOST:
		if (tool->lost == perf_event__process_lost)
			session->stats.total_lost += event->lost.lost;
		return tool->lost(tool, event, sample, machine);
	case PERF_RECORD_READ:
		return tool->read(tool, event, sample, evsel, machine);
	case PERF_RECORD_THROTTLE:
		return tool->throttle(tool, event, sample, machine);
	case PERF_RECORD_UNTHROTTLE:
		return tool->unthrottle(tool, event, sample, machine);
	default:
		++session->stats.nr_unknown_events;
		return -1;
	}
}

static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
					    struct perf_tool *tool, u64 file_offset)
{
	int fd = perf_data_file__fd(session->file);
	int err;

	dump_event(session, event, file_offset, NULL);

	/* These events are processed right away */
	switch (event->header.type) {
	case PERF_RECORD_HEADER_ATTR:
		err = tool->attr(tool, event, &session->evlist);
		if (err == 0)
			perf_session__set_id_hdr_size(session);
		return err;
	case PERF_RECORD_HEADER_TRACING_DATA:
		/* setup for reading amidst mmap */
		lseek(fd, file_offset, SEEK_SET);
		return tool->tracing_data(tool, event, session);
	case PERF_RECORD_HEADER_BUILD_ID:
		return tool->build_id(tool, event, session);
	case PERF_RECORD_FINISHED_ROUND:
		return tool->finished_round(tool, event, session);
	default:
		return -EINVAL;
	}
}

static void event_swap(union perf_event *event, bool sample_id_all)
{
	perf_event__swap_op swap;

	swap = perf_event__swap_ops[event->header.type];
	if (swap)
		swap(event, sample_id_all);
}

static int perf_session__process_event(struct perf_session *session,
				       union perf_event *event,
				       struct perf_tool *tool,
				       u64 file_offset)
{
	struct perf_sample sample;
	int ret;

	if (session->header.needs_swap)
		event_swap(event, perf_evlist__sample_id_all(session->evlist));

	if (event->header.type >= PERF_RECORD_HEADER_MAX)
		return -EINVAL;

	events_stats__inc(&session->stats, event->header.type);

	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
		return perf_session__process_user_event(session, event, tool, file_offset);

	/*
	 * For all kernel events we get the sample data
	 */
	ret = perf_evlist__parse_sample(session->evlist, event, &sample);
	if (ret)
		return ret;

	if (tool->ordered_samples) {
		ret = perf_session_queue_event(session, event, &sample,
					       file_offset);
		if (ret != -ETIME)
			return ret;
	}

	return perf_session_deliver_event(session, event, &sample, tool,
					  file_offset);
}

void perf_event_header__bswap(struct perf_event_header *self)
{
	self->type = bswap_32(self->type);
	self->misc = bswap_16(self->misc);
	self->size = bswap_16(self->size);
}

struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
{
	return machine__findnew_thread(&session->machines.host, 0, pid);
}

static struct thread *perf_session__register_idle_thread(struct perf_session *self)
{
	struct thread *thread = perf_session__findnew(self, 0);

	if (thread == NULL || thread__set_comm(thread, "swapper", 0)) {
		pr_err("problem inserting idle task.\n");
		thread = NULL;
	}

	return thread;
}

static void perf_session__warn_about_errors(const struct perf_session *session,
					    const struct perf_tool *tool)
{
	if (tool->lost == perf_event__process_lost &&
	    session->stats.nr_events[PERF_RECORD_LOST] != 0) {
		ui__warning("Processed %d events and lost %d chunks!\n\n"
			    "Check IO/CPU overload!\n\n",
			    session->stats.nr_events[0],
			    session->stats.nr_events[PERF_RECORD_LOST]);
	}

	if (session->stats.nr_unknown_events != 0) {
		ui__warning("Found %u unknown events!\n\n"
			    "Is this an older tool processing a perf.data "
			    "file generated by a more recent tool?\n\n"
			    "If that is not the case, consider "
			    "reporting to linux-kernel@vger.kernel.org.\n\n",
			    session->stats.nr_unknown_events);
	}

	if (session->stats.nr_unknown_id != 0) {
		ui__warning("%u samples with id not present in the header\n",
			    session->stats.nr_unknown_id);
	}

 	if (session->stats.nr_invalid_chains != 0) {
 		ui__warning("Found invalid callchains!\n\n"
 			    "%u out of %u events were discarded for this reason.\n\n"
 			    "Consider reporting to linux-kernel@vger.kernel.org.\n\n",
 			    session->stats.nr_invalid_chains,
 			    session->stats.nr_events[PERF_RECORD_SAMPLE]);
 	}

	if (session->stats.nr_unprocessable_samples != 0) {
		ui__warning("%u unprocessable samples recorded.\n"
			    "Do you have a KVM guest running and not using 'perf kvm'?\n",
			    session->stats.nr_unprocessable_samples);
	}
}

volatile int session_done;

static int __perf_session__process_pipe_events(struct perf_session *self,
					       struct perf_tool *tool)
{
	int fd = perf_data_file__fd(self->file);
	union perf_event *event;
	uint32_t size, cur_size = 0;
	void *buf = NULL;
	int skip = 0;
	u64 head;
	int err;
	void *p;

	perf_tool__fill_defaults(tool);

	head = 0;
	cur_size = sizeof(union perf_event);

	buf = malloc(cur_size);
	if (!buf)
		return -errno;
more:
	event = buf;
	err = readn(fd, event, sizeof(struct perf_event_header));
	if (err <= 0) {
		if (err == 0)
			goto done;

		pr_err("failed to read event header\n");
		goto out_err;
	}

	if (self->header.needs_swap)
		perf_event_header__bswap(&event->header);

	size = event->header.size;
	if (size < sizeof(struct perf_event_header)) {
		pr_err("bad event header size\n");
		goto out_err;
	}

	if (size > cur_size) {
		void *new = realloc(buf, size);
		if (!new) {
			pr_err("failed to allocate memory to read event\n");
			goto out_err;
		}
		buf = new;
		cur_size = size;
		event = buf;
	}
	p = event;
	p += sizeof(struct perf_event_header);

	if (size - sizeof(struct perf_event_header)) {
		err = readn(fd, p, size - sizeof(struct perf_event_header));
		if (err <= 0) {
			if (err == 0) {
				pr_err("unexpected end of event stream\n");
				goto done;
			}

			pr_err("failed to read event data\n");
			goto out_err;
		}
	}

	if ((skip = perf_session__process_event(self, event, tool, head)) < 0) {
		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
		       head, event->header.size, event->header.type);
		err = -EINVAL;
		goto out_err;
	}

	head += size;

	if (skip > 0)
		head += skip;

	if (!session_done())
		goto more;
done:
	/* do the final flush for ordered samples */
	self->ordered_samples.next_flush = ULLONG_MAX;
	err = flush_sample_queue(self, tool);
out_err:
	free(buf);
	perf_session__warn_about_errors(self, tool);
	perf_session_free_sample_buffers(self);
	return err;
}

static union perf_event *
fetch_mmaped_event(struct perf_session *session,
		   u64 head, size_t mmap_size, char *buf)
{
	union perf_event *event;

	/*
	 * Ensure we have enough space remaining to read
	 * the size of the event in the headers.
	 */
	if (head + sizeof(event->header) > mmap_size)
		return NULL;

	event = (union perf_event *)(buf + head);

	if (session->header.needs_swap)
		perf_event_header__bswap(&event->header);

	if (head + event->header.size > mmap_size) {
		/* We're not fetching the event so swap back again */
		if (session->header.needs_swap)
			perf_event_header__bswap(&event->header);
		return NULL;
	}

	return event;
}

/*
 * On 64bit we can mmap the data file in one go. No need for tiny mmap
 * slices. On 32bit we use 32MB.
 */
#if BITS_PER_LONG == 64
#define MMAP_SIZE ULLONG_MAX
#define NUM_MMAPS 1
#else
#define MMAP_SIZE (32 * 1024 * 1024ULL)
#define NUM_MMAPS 128
#endif

int __perf_session__process_events(struct perf_session *session,
				   u64 data_offset, u64 data_size,
				   u64 file_size, struct perf_tool *tool)
{
	int fd = perf_data_file__fd(session->file);
	u64 head, page_offset, file_offset, file_pos;
	int err, mmap_prot, mmap_flags, map_idx = 0;
	size_t	mmap_size;
	char *buf, *mmaps[NUM_MMAPS];
	union perf_event *event;
	uint32_t size;
	struct ui_progress prog;

	perf_tool__fill_defaults(tool);

	page_offset = page_size * (data_offset / page_size);
	file_offset = page_offset;
	head = data_offset - page_offset;

	if (data_size && (data_offset + data_size < file_size))
		file_size = data_offset + data_size;

	ui_progress__init(&prog, file_size, "Processing events...");

	mmap_size = MMAP_SIZE;
	if (mmap_size > file_size)
		mmap_size = file_size;

	memset(mmaps, 0, sizeof(mmaps));

	mmap_prot  = PROT_READ;
	mmap_flags = MAP_SHARED;

	if (session->header.needs_swap) {
		mmap_prot  |= PROT_WRITE;
		mmap_flags = MAP_PRIVATE;
	}
remap:
	buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd,
		   file_offset);
	if (buf == MAP_FAILED) {
		pr_err("failed to mmap file\n");
		err = -errno;
		goto out_err;
	}
	mmaps[map_idx] = buf;
	map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
	file_pos = file_offset + head;

more:
	event = fetch_mmaped_event(session, head, mmap_size, buf);
	if (!event) {
		if (mmaps[map_idx]) {
			munmap(mmaps[map_idx], mmap_size);
			mmaps[map_idx] = NULL;
		}

		page_offset = page_size * (head / page_size);
		file_offset += page_offset;
		head -= page_offset;
		goto remap;
	}

	size = event->header.size;

	if (size < sizeof(struct perf_event_header) ||
	    perf_session__process_event(session, event, tool, file_pos) < 0) {
		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
		       file_offset + head, event->header.size,
		       event->header.type);
		err = -EINVAL;
		goto out_err;
	}

	head += size;
	file_pos += size;

	ui_progress__update(&prog, size);

	if (session_done())
		goto out;

	if (file_pos < file_size)
		goto more;

out:
	/* do the final flush for ordered samples */
	session->ordered_samples.next_flush = ULLONG_MAX;
	err = flush_sample_queue(session, tool);
out_err:
	ui_progress__finish();
	perf_session__warn_about_errors(session, tool);
	perf_session_free_sample_buffers(session);
	return err;
}

int perf_session__process_events(struct perf_session *self,
				 struct perf_tool *tool)
{
	u64 size = perf_data_file__size(self->file);
	int err;

	if (perf_session__register_idle_thread(self) == NULL)
		return -ENOMEM;

	if (!perf_data_file__is_pipe(self->file))
		err = __perf_session__process_events(self,
						     self->header.data_offset,
						     self->header.data_size,
						     size, tool);
	else
		err = __perf_session__process_pipe_events(self, tool);

	return err;
}

bool perf_session__has_traces(struct perf_session *session, const char *msg)
{
	struct perf_evsel *evsel;

	list_for_each_entry(evsel, &session->evlist->entries, node) {
		if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
			return true;
	}

	pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
	return false;
}

int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
				     const char *symbol_name, u64 addr)
{
	char *bracket;
	enum map_type i;
	struct ref_reloc_sym *ref;

	ref = zalloc(sizeof(struct ref_reloc_sym));
	if (ref == NULL)
		return -ENOMEM;

	ref->name = strdup(symbol_name);
	if (ref->name == NULL) {
		free(ref);
		return -ENOMEM;
	}

	bracket = strchr(ref->name, ']');
	if (bracket)
		*bracket = '\0';

	ref->addr = addr;

	for (i = 0; i < MAP__NR_TYPES; ++i) {
		struct kmap *kmap = map__kmap(maps[i]);
		kmap->ref_reloc_sym = ref;
	}

	return 0;
}

size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp)
{
	return machines__fprintf_dsos(&self->machines, fp);
}

size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp,
					  bool (skip)(struct dso *dso, int parm), int parm)
{
	return machines__fprintf_dsos_buildid(&self->machines, fp, skip, parm);
}

size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
{
	struct perf_evsel *pos;
	size_t ret = fprintf(fp, "Aggregated stats:\n");

	ret += events_stats__fprintf(&session->stats, fp);

	list_for_each_entry(pos, &session->evlist->entries, node) {
		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
		ret += events_stats__fprintf(&pos->hists.stats, fp);
	}

	return ret;
}

size_t perf_session__fprintf(struct perf_session *session, FILE *fp)
{
	/*
	 * FIXME: Here we have to actually print all the machines in this
	 * session, not just the host...
	 */
	return machine__fprintf(&session->machines.host, fp);
}

struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
					      unsigned int type)
{
	struct perf_evsel *pos;

	list_for_each_entry(pos, &session->evlist->entries, node) {
		if (pos->attr.type == type)
			return pos;
	}
	return NULL;
}

void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
			  struct perf_sample *sample, struct machine *machine,
			  unsigned int print_opts, unsigned int stack_depth)
{
	struct addr_location al;
	struct callchain_cursor_node *node;
	int print_ip = print_opts & PRINT_IP_OPT_IP;
	int print_sym = print_opts & PRINT_IP_OPT_SYM;
	int print_dso = print_opts & PRINT_IP_OPT_DSO;
	int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
	int print_oneline = print_opts & PRINT_IP_OPT_ONELINE;
	char s = print_oneline ? ' ' : '\t';

	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
		error("problem processing %d event, skipping it.\n",
			event->header.type);
		return;
	}

	if (symbol_conf.use_callchain && sample->callchain) {

		if (machine__resolve_callchain(machine, evsel, al.thread,
					       sample, NULL, NULL,
					       PERF_MAX_STACK_DEPTH) != 0) {
			if (verbose)
				error("Failed to resolve callchain. Skipping\n");
			return;
		}
		callchain_cursor_commit(&callchain_cursor);

		while (stack_depth) {
			node = callchain_cursor_current(&callchain_cursor);
			if (!node)
				break;

			if (print_ip)
				printf("%c%16" PRIx64, s, node->ip);

			if (print_sym) {
				printf(" ");
				if (print_symoffset) {
					al.addr = node->ip;
					al.map  = node->map;
					symbol__fprintf_symname_offs(node->sym, &al, stdout);
				} else
					symbol__fprintf_symname(node->sym, stdout);
			}

			if (print_dso) {
				printf(" (");
				map__fprintf_dsoname(node->map, stdout);
				printf(")");
			}

			if (!print_oneline)
				printf("\n");

			callchain_cursor_advance(&callchain_cursor);

			stack_depth--;
		}

	} else {
		if (print_ip)
			printf("%16" PRIx64, sample->ip);

		if (print_sym) {
			printf(" ");
			if (print_symoffset)
				symbol__fprintf_symname_offs(al.sym, &al,
							     stdout);
			else
				symbol__fprintf_symname(al.sym, stdout);
		}

		if (print_dso) {
			printf(" (");
			map__fprintf_dsoname(al.map, stdout);
			printf(")");
		}
	}
}

int perf_session__cpu_bitmap(struct perf_session *session,
			     const char *cpu_list, unsigned long *cpu_bitmap)
{
	int i;
	struct cpu_map *map;

	for (i = 0; i < PERF_TYPE_MAX; ++i) {
		struct perf_evsel *evsel;

		evsel = perf_session__find_first_evtype(session, i);
		if (!evsel)
			continue;

		if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) {
			pr_err("File does not contain CPU events. "
			       "Remove -c option to proceed.\n");
			return -1;
		}
	}

	map = cpu_map__new(cpu_list);
	if (map == NULL) {
		pr_err("Invalid cpu_list\n");
		return -1;
	}

	for (i = 0; i < map->nr; i++) {
		int cpu = map->map[i];

		if (cpu >= MAX_NR_CPUS) {
			pr_err("Requested CPU %d too large. "
			       "Consider raising MAX_NR_CPUS\n", cpu);
			return -1;
		}

		set_bit(cpu, cpu_bitmap);
	}

	return 0;
}

void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
				bool full)
{
	int fd = perf_data_file__fd(session->file);
	struct stat st;
	int ret;

	if (session == NULL || fp == NULL)
		return;

	ret = fstat(fd, &st);
	if (ret == -1)
		return;

	fprintf(fp, "# ========\n");
	fprintf(fp, "# captured on: %s", ctime(&st.st_ctime));
	perf_header__fprintf_info(session, fp, full);
	fprintf(fp, "# ========\n#\n");
}


int __perf_session__set_tracepoints_handlers(struct perf_session *session,
					     const struct perf_evsel_str_handler *assocs,
					     size_t nr_assocs)
{
	struct perf_evsel *evsel;
	size_t i;
	int err;

	for (i = 0; i < nr_assocs; i++) {
		/*
		 * Adding a handler for an event not in the session,
		 * just ignore it.
		 */
		evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name);
		if (evsel == NULL)
			continue;

		err = -EEXIST;
		if (evsel->handler.func != NULL)
			goto out;
		evsel->handler.func = assocs[i].handler;
	}

	err = 0;
out:
	return err;
}