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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright IBM Corp. 2018
* Auxtrace support for s390 CPU-Measurement Sampling Facility
*
* Author(s): Thomas Richter <tmricht@linux.ibm.com>
*
* Auxiliary traces are collected during 'perf record' using rbd000 event.
* Several PERF_RECORD_XXX are generated during recording:
*
* PERF_RECORD_AUX:
* Records that new data landed in the AUX buffer part.
* PERF_RECORD_AUXTRACE:
* Defines auxtrace data. Followed by the actual data. The contents of
* the auxtrace data is dependent on the event and the CPU.
* This record is generated by perf record command. For details
* see Documentation/perf.data-file-format.txt.
* PERF_RECORD_AUXTRACE_INFO:
* Defines a table of contains for PERF_RECORD_AUXTRACE records. This
* record is generated during 'perf record' command. Each record contains
* up to 256 entries describing offset and size of the AUXTRACE data in the
* perf.data file.
* PERF_RECORD_AUXTRACE_ERROR:
* Indicates an error during AUXTRACE collection such as buffer overflow.
* PERF_RECORD_FINISHED_ROUND:
* Perf events are not necessarily in time stamp order, as they can be
* collected in parallel on different CPUs. If the events should be
* processed in time order they need to be sorted first.
* Perf report guarantees that there is no reordering over a
* PERF_RECORD_FINISHED_ROUND boundary event. All perf records with a
* time stamp lower than this record are processed (and displayed) before
* the succeeding perf record are processed.
*
* These records are evaluated during perf report command.
*
* 1. PERF_RECORD_AUXTRACE_INFO is used to set up the infrastructure for
* auxiliary trace data processing. See s390_cpumsf_process_auxtrace_info()
* below.
* Auxiliary trace data is collected per CPU. To merge the data into the report
* an auxtrace_queue is created for each CPU. It is assumed that the auxtrace
* data is in ascending order.
*
* Each queue has a double linked list of auxtrace_buffers. This list contains
* the offset and size of a CPU's auxtrace data. During auxtrace processing
* the data portion is mmap()'ed.
*
* To sort the queues in chronological order, all queue access is controlled
* by the auxtrace_heap. This is basicly a stack, each stack element has two
* entries, the queue number and a time stamp. However the stack is sorted by
* the time stamps. The highest time stamp is at the bottom the lowest
* (nearest) time stamp is at the top. That sort order is maintained at all
* times!
*
* After the auxtrace infrastructure has been setup, the auxtrace queues are
* filled with data (offset/size pairs) and the auxtrace_heap is populated.
*
* 2. PERF_RECORD_XXX processing triggers access to the auxtrace_queues.
* Each record is handled by s390_cpumsf_process_event(). The time stamp of
* the perf record is compared with the time stamp located on the auxtrace_heap
* top element. If that time stamp is lower than the time stamp from the
* record sample, the auxtrace queues will be processed. As auxtrace queues
* control many auxtrace_buffers and each buffer can be quite large, the
* auxtrace buffer might be processed only partially. In this case the
* position in the auxtrace_buffer of that queue is remembered and the time
* stamp of the last processed entry of the auxtrace_buffer replaces the
* current auxtrace_heap top.
*
* 3. Auxtrace_queues might run of out data and are feeded by the
* PERF_RECORD_AUXTRACE handling, see s390_cpumsf_process_auxtrace_event().
*
* Event Generation
* Each sampling-data entry in the auxilary trace data generates a perf sample.
* This sample is filled
* with data from the auxtrace such as PID/TID, instruction address, CPU state,
* etc. This sample is processed with perf_session__deliver_synth_event() to
* be included into the GUI.
*
* 4. PERF_RECORD_FINISHED_ROUND event is used to process all the remaining
* auxiliary traces entries until the time stamp of this record is reached
* auxtrace_heap top. This is triggered by ordered_event->deliver().
*
*
* Perf event processing.
* Event processing of PERF_RECORD_XXX entries relies on time stamp entries.
* This is the function call sequence:
*
* __cmd_report()
* |
* perf_session__process_events()
* |
* __perf_session__process_events()
* |
* perf_session__process_event()
* | This functions splits the PERF_RECORD_XXX records.
* | - Those generated by perf record command (type number equal or higher
* | than PERF_RECORD_USER_TYPE_START) are handled by
* | perf_session__process_user_event(see below)
* | - Those generated by the kernel are handled by
* | perf_evlist__parse_sample_timestamp()
* |
* perf_evlist__parse_sample_timestamp()
* | Extract time stamp from sample data.
* |
* perf_session__queue_event()
* | If timestamp is positive the sample is entered into an ordered_event
* | list, sort order is the timestamp. The event processing is deferred until
* | later (see perf_session__process_user_event()).
* | Other timestamps (0 or -1) are handled immediately by
* | perf_session__deliver_event(). These are events generated at start up
* | of command perf record. They create PERF_RECORD_COMM and PERF_RECORD_MMAP*
* | records. They are needed to create a list of running processes and its
* | memory mappings and layout. They are needed at the beginning to enable
* | command perf report to create process trees and memory mappings.
* |
* perf_session__deliver_event()
* | Delivers a PERF_RECORD_XXX entry for handling.
* |
* auxtrace__process_event()
* | The timestamp of the PERF_RECORD_XXX entry is taken to correlate with
* | time stamps from the auxiliary trace buffers. This enables
* | synchronization between auxiliary trace data and the events on the
* | perf.data file.
* |
* machine__deliver_event()
* | Handles the PERF_RECORD_XXX event. This depends on the record type.
* It might update the process tree, update a process memory map or enter
* a sample with IP and call back chain data into GUI data pool.
*
*
* Deferred processing determined by perf_session__process_user_event() is
* finally processed when a PERF_RECORD_FINISHED_ROUND is encountered. These
* are generated during command perf record.
* The timestamp of PERF_RECORD_FINISHED_ROUND event is taken to process all
* PERF_RECORD_XXX entries stored in the ordered_event list. This list was
* built up while reading the perf.data file.
* Each event is now processed by calling perf_session__deliver_event().
* This enables time synchronization between the data in the perf.data file and
* the data in the auxiliary trace buffers.
*/
#include <endian.h>
#include <errno.h>
#include <byteswap.h>
#include <inttypes.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/log2.h>
#include <linux/zalloc.h>
#include <sys/stat.h>
#include <sys/types.h>
#include "cpumap.h"
#include "color.h"
#include "evsel.h"
#include "evlist.h"
#include "machine.h"
#include "session.h"
#include "thread.h"
#include "debug.h"
#include "auxtrace.h"
#include "s390-cpumsf.h"
#include "s390-cpumsf-kernel.h"
#include "s390-cpumcf-kernel.h"
#include "config.h"
struct s390_cpumsf {
struct auxtrace auxtrace;
struct auxtrace_queues queues;
struct auxtrace_heap heap;
struct perf_session *session;
struct machine *machine;
u32 auxtrace_type;
u32 pmu_type;
u16 machine_type;
bool data_queued;
bool use_logfile;
char *logdir;
};
struct s390_cpumsf_queue {
struct s390_cpumsf *sf;
unsigned int queue_nr;
struct auxtrace_buffer *buffer;
int cpu;
FILE *logfile;
FILE *logfile_ctr;
};
/* Check if the raw data should be dumped to file. If this is the case and
* the file to dump to has not been opened for writing, do so.
*
* Return 0 on success and greater zero on error so processing continues.
*/
static int s390_cpumcf_dumpctr(struct s390_cpumsf *sf,
struct perf_sample *sample)
{
|