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
|
/*
* Performance events x86 architecture header
*
* Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
* Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
* Copyright (C) 2009 Jaswinder Singh Rajput
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
* Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
* Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
* Copyright (C) 2009 Google, Inc., Stephane Eranian
*
* For licencing details see kernel-base/COPYING
*/
#include <linux/perf_event.h>
#include <asm/fpu/xstate.h>
#include <asm/intel_ds.h>
#include <asm/cpu.h>
/* To enable MSR tracing please use the generic trace points. */
/*
* | NHM/WSM | SNB |
* register -------------------------------
* | HT | no HT | HT | no HT |
*-----------------------------------------
* offcore | core | core | cpu | core |
* lbr_sel | core | core | cpu | core |
* ld_lat | cpu | core | cpu | core |
*-----------------------------------------
*
* Given that there is a small number of shared regs,
* we can pre-allocate their slot in the per-cpu
* per-core reg tables.
*/
enum extra_reg_type {
EXTRA_REG_NONE = -1, /* not used */
EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */
EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */
EXTRA_REG_LBR = 2, /* lbr_select */
EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */
EXTRA_REG_FE = 4, /* fe_* */
EXTRA_REG_MAX /* number of entries needed */
};
struct event_constraint {
union {
unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
u64 idxmsk64;
};
u64 code;
u64 cmask;
int weight;
int overlap;
int flags;
unsigned int size;
};
static inline bool constraint_match(struct event_constraint *c, u64 ecode)
{
return ((ecode & c->cmask) - c->code) <= (u64)c->size;
}
/*
* struct hw_perf_event.flags flags
*/
#define PERF_X86_EVENT_PEBS_LDLAT 0x00001 /* ld+ldlat data address sampling */
#define PERF_X86_EVENT_PEBS_ST 0x00002 /* st data address sampling */
#define PERF_X86_EVENT_PEBS_ST_HSW 0x00004 /* haswell style datala, store */
#define PERF_X86_EVENT_PEBS_LD_HSW 0x00008 /* haswell style datala, load */
#define PERF_X86_EVENT_PEBS_NA_HSW 0x00010 /* haswell style datala, unknown */
#define PERF_X86_EVENT_EXCL 0x00020 /* HT exclusivity on counter */
#define PERF_X86_EVENT_DYNAMIC 0x00040 /* dynamic alloc'd constraint */
#define PERF_X86_EVENT_EXCL_ACCT 0x00100 /* accounted EXCL event */
#define PERF_X86_EVENT_AUTO_RELOAD 0x00200 /* use PEBS auto-reload */
#define PERF_X86_EVENT_LARGE_PEBS 0x00400 /* use large PEBS */
#define PERF_X86_EVENT_PEBS_VIA_PT 0x00800 /* use PT buffer for PEBS */
#define PERF_X86_EVENT_PAIR 0x01000 /* Large Increment per Cycle */
#define PERF_X86_EVENT_LBR_SELECT 0x02000 /* Save/Restore MSR_LBR_SELECT */
#define PERF_X86_EVENT_TOPDOWN 0x04000 /* Count Topdown slots/metrics events */
#define PERF_X86_EVENT_PEBS_STLAT 0x08000 /* st+stlat data address sampling */
#define PERF_X86_EVENT_AMD_BRS 0x10000 /* AMD Branch Sampling */
static inline bool is_topdown_count(struct perf_event *event)
{
return event->hw.flags & PERF_X86_EVENT_TOPDOWN;
}
static inline bool is_metric_event(struct perf_event *event)
{
u64 config = event->attr.config;
return ((config & ARCH_PERFMON_EVENTSEL_EVENT) == 0) &&
((config & INTEL_ARCH_EVENT_MASK) >= INTEL_TD_METRIC_RETIRING) &&
((config & INTEL_ARCH_EVENT_MASK) <= INTEL_TD_METRIC_MAX);
}
static inline bool is_slots_event(struct perf_event *event)
{
return (event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_TD_SLOTS;
}
static inline bool is_topdown_event(struct perf_event *event)
{
return is_metric_event(event) || is_slots_event(event);
}
struct amd_nb {
int nb_id; /* NorthBridge id */
int refcnt; /* reference count */
struct perf_event *owners[X86_PMC_IDX_MAX];
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};
#define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1)
#define PEBS_PMI_AFTER_EACH_RECORD BIT_ULL(60)
#define PEBS_OUTPUT_OFFSET 61
#define PEBS_OUTPUT_MASK (3ull << PEBS_OUTPUT_OFFSET)
#define PEBS_OUTPUT_PT (1ull << PEBS_OUTPUT_OFFSET)
#define PEBS_VIA_PT_MASK (PEBS_OUTPUT_PT | PEBS_PMI_AFTER_EACH_RECORD)
/*
* Flags PEBS can handle without an PMI.
*
* TID can only be handled by flushing at context switch.
* REGS_USER can be handled for events limited to ring 3.
*
*/
#define LARGE_PEBS_FLAGS \
(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
PERF_SAMPLE_PERIOD | PERF_SAMPLE_CODE_PAGE_SIZE)
#define PEBS_GP_REGS \
((1ULL << PERF_REG_X86_AX) | \
(1ULL << PERF_REG_X86_BX) | \
(1ULL << PERF_REG_X86_CX) | \
(1ULL << PERF_REG_X86_DX) | \
(1ULL << PERF_REG_X86_DI) | \
(1ULL << PERF_REG_X86_SI) | \
(1ULL << PERF_REG_X86_SP) | \
(1ULL << PERF_REG_X86_BP) | \
(1ULL << PERF_REG_X86_IP) | \
(1ULL << PERF_REG_X86_FLAGS) | \
(1ULL << PERF_REG_X86_R8) | \
(1ULL << PERF_REG_X86_R9) | \
(1ULL << PERF_REG_X86_R10) | \
(1ULL << PERF_REG_X86_R11) | \
(1ULL << PERF_REG_X86_R12) | \
(1ULL << PERF_REG_X86_R13) | \
(1ULL << PERF_REG_X86_R14) | \
(1ULL << PERF_REG_X86_R15))
/*
* Per register state.
*/
struct er_account {
raw_spinlock_t lock; /* per-core: protect structure */
u64 config; /* extra MSR config */
u64 reg; /* extra MSR number */
atomic_t ref; /* reference count */
};
/*
* Per core/cpu state
*
* Used to coordinate shared registers between HT threads or
* among events on a single PMU.
*/
struct intel_shared_regs {
struct er_account regs[EXTRA_REG_MAX];
int refcnt; /* per-core: #HT threads */
unsigned core_id; /* per-core: core id */
};
enum intel_excl_state_type {
INTEL_EXCL_UNUSED = 0, /* counter is unused */
INTEL_EXCL_SHARED = 1, /* counter can be used by both threads */
INTEL_EXCL_EXCLUSIVE = 2, /* counter can be used by one thread only */
};
struct intel_excl_states {
enum intel_excl_state_type state[X86_PMC_IDX_MAX];
bool sched_started; /* true if scheduling has started */
};
struct intel_excl_cntrs {
raw_spinlock_t lock;
struct intel_excl_states states[2];
union {
u16 has_exclusive[2];
u32 exclusive_present;
};
int refcnt; /* per-core: #HT threads */
unsigned core_id; /* per-core: core id */
};
struct x86_perf_task_context;
#define MAX_LBR_ENTRIES 32
enum {
LBR_FORMAT_32 = 0x00,
LBR_FORMAT_LIP = 0x01,
LBR_FORMAT_EIP = 0x02,
LBR_FORMAT_EIP_FLAGS = 0x03,
LBR_FORMAT_EIP_FLAGS2 = 0x04,
LBR_FORMAT_INFO = 0x05,
LBR_FORMAT_TIME = 0x06,
LBR_FORMAT_INFO2 = 0x07,
LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_INFO2,
};
enum {
X86_PERF_KFREE_SHARED = 0,
X86_PERF_KFREE_EXCL = 1,
X86_PERF_KFREE_MAX
};
struct cpu_hw_events {
/*
* Generic x86 PMC bits
*/
struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */
unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
unsigned long dirty[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
int enabled;
int n_events; /* the # of events in the below arrays */
int n_added; /* the # last events in the below arrays;
they've never been enabled yet */
int n_txn; /* the # last events in the below arrays;
added in the current transaction */
int n_txn_pair;
int n_txn_metric;
int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
u64 tags[X86_PMC_IDX_MAX];
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
struct event_constraint *event_constraint[X86_PMC_IDX_MAX];
int n_excl; /* the number of exclusive events */
unsigned int txn_flags;
int is_fake;
/*
* Intel DebugStore bits
*/
struct debug_store *ds;
void *ds_pebs_vaddr;
void *ds_bts_vaddr;
u64 pebs_enabled;
int n_pebs;
int n_large_pebs;
int n_pebs_via_pt;
int pebs_output;
/* Current super set of events hardware configuration */
u64 pebs_data_cfg;
u64 active_pebs_data_cfg;
int pebs_record_size;
/*
* Intel LBR bits
*/
int lbr_users;
int lbr_pebs_users;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
union {
struct er_account *lbr_sel;
struct er_account *lbr_ctl;
};
u64 br_sel;
void *last_task_ctx;
int last_log_id;
int lbr_select;
void *lbr_xsave;
/*
* Intel host/guest exclude bits
*/
u64 intel_ctrl_guest_mask;
u64 intel_ctrl_host_mask;
struct perf_guest_switch_msr guest_switch_msrs[X86_PMC_IDX_MAX];
/*
* Intel checkpoint mask
*/
u64 intel_cp_status;
/*
* manage shared (per-core, per-cpu) registers
* used on Intel NHM/WSM/SNB
*/
struct intel_shared_regs *shared_regs;
/*
* manage exclusive counter access between hyperthread
*/
struct event_constraint *constraint_list; /* in enable order */
struct intel_excl_cntrs *excl_cntrs;
int excl_thread_id; /* 0 or 1 */
/*
* SKL TSX_FORCE_ABORT shadow
*/
u64 tfa_shadow;
/*
* Perf Metrics
*/
/* number of accepted metrics events */
int n_metric;
/*
* AMD specific bits
*/
struct amd_nb *amd_nb;
int brs_active; /* BRS is enabled */
/* Inverted mask of bits to clear in the perf_ctr ctrl registers */
u64 perf_ctr_virt_mask;
int n_pair; /* Large increment events */
void *kfree_on_online[X86_PERF_KFREE_MAX];
struct pmu *pmu;
};
#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \
{ .idxmsk64 = (n) }, \
.code = (c), \
.size = (e) - (c), \
.cmask = (m), \
.weight = (w), \
.overlap = (o), \
.flags = f, \
}
#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
__EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
#define EVENT_CONSTRAINT(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
/*
* The constraint_match() function only works for 'simple' event codes
* and not for extended (AMD64_EVENTSEL_EVENT) events codes.
*/
#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
__EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
#define INTEL_EXCLEVT_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
0, PERF_X86_EVENT_EXCL)
/*
* The overlap flag marks event constraints with overlapping counter
* masks. This is the case if the counter mask of such an event is not
* a subset of any other counter mask of a constraint with an equal or
* higher weight, e.g.:
*
* c_overlaps = EVENT_CONSTRAINT_OVERLAP(0, 0x09, 0);
* c_another1 = EVENT_CONSTRAINT(0, 0x07, 0);
* c_another2 = EVENT_CONSTRAINT(0, 0x38, 0);
*
* The event scheduler may not select the correct counter in the first
* cycle because it needs to know which subsequent events will be
* scheduled. It may fail to schedule the events then. So we set the
* overlap flag for such constraints to give the scheduler a hint which
* events to select for counter rescheduling.
*
* Care must be taken as the rescheduling algorithm is O(n!) which
* will increase scheduling cycles for an over-committed system
* dramatically. The number of such EVENT_CONSTRAINT_OVERLAP() macros
* and its counter masks must be kept at a minimum.
*/
#define EVENT_CONSTRAINT_OVERLAP(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1, 0)
/*
* Constraint on the Event code.
*/
#define INTEL_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
/*
* Constraint on a range of Event codes
*/
#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \
EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
/*
* Constraint on the Event code + UMask + fixed-mask
*
* filter mask to validate fixed counter events.
* the following filters disqualify for fixed counters:
* - inv
* - edge
* - cnt-mask
* - in_tx
* - in_tx_checkpointed
* The other filters are supported by fixed counters.
* The any-thread option is supported starting with v3.
*/
#define FIXED_EVENT_FLAGS (X86_RAW_EVENT_MASK|HSW_IN_TX|HSW_IN_TX_CHECKPOINTED)
#define FIXED_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, (1ULL << (32+n)), FIXED_EVENT_FLAGS)
/*
* The special metric counters do not actually exist. They are calculated from
* the combination of the FxCtr3 + MSR_PERF_METRICS.
*
* The special metric counters are mapped to a dummy offset for the scheduler.
* The sharing between multiple users of the same metric without multiplexing
* is not allowed, even though the hardware supports that in principle.
*/
#define METRIC_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, (1ULL << (INTEL_PMC_IDX_METRIC_BASE + n)), \
INTEL_ARCH_EVENT_MASK)
/*
* Constraint on the Event code + UMask
*/
#define INTEL_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
/* Constraint on specific umask bit only + event */
#define INTEL_UBIT_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c))
/* Like UEVENT_CONSTRAINT, but match flags too */
#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
#define INTEL_EXCLUEVT_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
HWEIGHT(n), 0, PERF_X86_EVENT_EXCL)
#define INTEL_PLD_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
#define INTEL_PSD_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_STLAT)
#define INTEL_PST_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
/* Event constraint, but match on all event flags too. */
#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \
EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
/* Check only flags, but allow all event/umask */
#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \
EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
/* Check flags and event code, and set the HSW store flag */
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_ST(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
/* Check flags and event code, and set the HSW load flag */
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
__EVENT_CONSTRAINT_RANGE(code, end, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, \
PERF_X86_EVENT_PEBS_LD_HSW|PERF_X86_EVENT_EXCL)
/* Check flags and event code/umask, and set the HSW store flag */
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(code, n) \
__EVENT_CONSTRAINT(code, n, \
INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(code, n) \
__EVENT_CONSTRAINT(code, n, \
INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, \
PERF_X86_EVENT_PEBS_ST_HSW|PERF_X86_EVENT_EXCL)
/* Check flags and event code/umask, and set the HSW load flag */
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(code, n) \
__EVENT_CONSTRAINT(code, n, \
INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(code, n) \
__EVENT_CONSTRAINT(code, n, \
INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, \
PERF_X86_EVENT_PEBS_LD_HSW|PERF_X86_EVENT_EXCL)
/* Check flags and event code/umask, and set the HSW N/A flag */
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
__EVENT_CONSTRAINT(code, n, \
INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
/*
* We define the end marker as having a weight of -1
* to enable blacklisting of events using a counter bitmask
* of zero and thus a weight of zero.
* The end marker has a weight that cannot possibly be
* obtained from counting the bits in the bitmask.
*/
#define EVENT_CONSTRAINT_END { .weight = -1 }
/*
* Check for end marker with weight == -1
*/
#define for_each_event_constraint(e, c) \
for ((e) = (c); (e)->weight != -1; (e)++)
/*
* Extra registers for specific events.
*
* Some events need large masks and require external MSRs.
* Those extra MSRs end up being shared for all events on
* a PMU and sometimes between PMU of sibling HT threads.
* In either case, the kernel needs to handle conflicting
* accesses to those extra, shared, regs. The data structure
* to manage those registers is stored in cpu_hw_event.
*/
struct extra_reg {
unsigned int event;
unsigned int msr;
u64 config_mask;
u64 valid_mask;
int idx; /* per_xxx->regs[] reg index */
bool extra_msr_access;
};
#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \
.event = (e), \
.msr = (ms), \
.config_mask = (m), \
.valid_mask = (vm), \
.idx = EXTRA_REG_##i, \
.extra_msr_access = true, \
}
#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \
EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx)
#define INTEL_UEVENT_EXTRA_REG(event, msr, vm, idx) \
EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT | \
ARCH_PERFMON_EVENTSEL_UMASK, vm, idx)
#define INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(c) \
INTEL_UEVENT_EXTRA_REG(c, \
MSR_PEBS_LD_LAT_THRESHOLD, \
0xffff, \
LDLAT)
#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0)
union perf_capabilities {
struct {
u64 lbr_format:6;
u64 pebs_trap:1;
u64 pebs_arch_reg:1;
u64 pebs_format:4;
u64 smm_freeze:1;
/*
* PMU supports separate counter range for writing
* values > 32bit.
*/
u64 full_width_write:1;
u64 pebs_baseline:1;
u64 perf_metrics:1;
u64 pebs_output_pt_available:1;
u64 anythread_deprecated:1;
};
u64 capabilities;
};
struct x86_pmu_quirk {
struct x86_pmu_quirk *next;
void (*func)(void);
};
union x86_pmu_config {
struct {
u64 event:8,
umask:8,
usr:1,
os:1,
edge:1,
pc:1,
interrupt:1,
__reserved1:1,
en:1,
inv:1,
cmask:8,
event2:4,
__reserved2:4,
go:1,
ho:1;
} bits;
u64 value;
};
#define X86_CONFIG(args...) ((union x86_pmu_config){.bits = {args}}).value
enum {
x86_lbr_exclusive_lbr,
x86_lbr_exclusive_bts,
x86_lbr_exclusive_pt,
x86_lbr_exclusive_max,
};
struct x86_hybrid_pmu {
struct pmu pmu;
const char *name;
u8 cpu_type;
cpumask_t supported_cpus;
union perf_capabilities intel_cap;
u64 intel_ctrl;
int max_pebs_events;
int num_counters;
int num_counters_fixed;
struct event_constraint unconstrained;
u64 hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
u64 hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
struct event_constraint *event_constraints;
struct event_constraint *pebs_constraints;
struct extra_reg *extra_regs;
unsigned int late_ack :1,
mid_ack :1,
enabled_ack :1;
};
static __always_inline struct x86_hybrid_pmu *hybrid_pmu(struct pmu *pmu)
{
return container_of(pmu, struct x86_hybrid_pmu, pmu);
}
extern struct static_key_false perf_is_hybrid;
#define is_hybrid() static_branch_unlikely(&perf_is_hybrid)
#define hybrid(_pmu, _field) \
(*({ \
typeof(&x86_pmu._field) __Fp = &x86_pmu._field; \
\
if (is_hybrid() && (_pmu)) \
__Fp = &hybrid_pmu(_pmu)->_field; \
\
__Fp; \
}))
#define hybrid_var(_pmu, _var) \
(*({ \
typeof(&_var) __Fp = &_var; \
\
if (is_hybrid() && (_pmu)) \
__Fp = &hybrid_pmu(_pmu)->_var; \
\
__Fp; \
}))
#define hybrid_bit(_pmu, _field) \
({ \
bool __Fp = x86_pmu._field; \
\
if (is_hybrid() && (_pmu)) \
__Fp = hybrid_pmu(_pmu)->_field; \
\
__Fp; \
})
enum hybrid_pmu_type {
hybrid_big = 0x40,
hybrid_small = 0x20,
hybrid_big_small = hybrid_big | hybrid_small,
};
#define X86_HYBRID_PMU_ATOM_IDX 0
#define X86_HYBRID_PMU_CORE_IDX 1
#define X86_HYBRID_NUM_PMUS 2
/*
* struct x86_pmu - generic x86 pmu
*/
struct x86_pmu {
/*
* Generic x86 PMC bits
*/
const char *name;
int version;
int (*handle_irq)(struct pt_regs *);
void (*disable_all)(void);
void (*enable_all)(int added);
void (*enable)(struct perf_event *);
void (*disable)(struct perf_event *);
void (*assign)(struct perf_event *event, int idx);
void (*add)(struct perf_event *);
void (*del)(struct perf_event *);
void (*read)(struct perf_event *event);
int (*hw_config)(struct perf_event *event);
int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
unsigned eventsel;
unsigned perfctr;
int (*addr_offset)(int index, bool eventsel);
int (*rdpmc_index)(int index);
u64 (*event_map)(int);
int max_events;
int num_counters;
int num_counters_fixed;
int cntval_bits;
u64 cntval_mask;
union {
unsigned long events_maskl;
unsigned long events_mask[BITS_TO_LONGS(ARCH_PERFMON_EVENTS_COUNT)];
};
int events_mask_len;
int apic;
u64 max_period;
struct event_constraint *
(*get_event_constraints)(struct cpu_hw_events *cpuc,
int idx,
struct perf_event *event);
void (*put_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
void (*start_scheduling)(struct cpu_hw_events *cpuc);
void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
void (*stop_scheduling)(struct cpu_hw_events *cpuc);
struct event_constraint *event_constraints;
struct x86_pmu_quirk *quirks;
int perfctr_second_write;
u64 (*limit_period)(struct perf_event *event, u64 l);
/* PMI handler bits */
unsigned int late_ack :1,
mid_ack :1,
enabled_ack :1;
/*
* sysfs attrs
*/
int attr_rdpmc_broken;
int attr_rdpmc;
struct attribute **format_attrs;
ssize_t (*events_sysfs_show)(char *page, u64 config);
const struct attribute_group **attr_update;
unsigned long attr_freeze_on_smi;
/*
* CPU Hotplug hooks
*/
int (*cpu_prepare)(int cpu);
void (*cpu_starting)(int cpu);
void (*cpu_dying)(int cpu);
void (*cpu_dead)(int cpu);
void (*check_microcode)(void);
void (*sched_task)(struct perf_event_context *ctx,
bool sched_in);
/*
* Intel Arch Perfmon v2+
*/
u64 intel_ctrl;
union perf_capabilities intel_cap;
/*
* Intel DebugStore bits
*/
unsigned int bts :1,
bts_active :1,
pebs :1,
pebs_active :1,
pebs_broken :1,
pebs_prec_dist :1,
pebs_no_tlb :1,
pebs_no_isolation :1,
pebs_block :1;
int pebs_record_size;
int pebs_buffer_size;
int max_pebs_events;
void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
unsigned long large_pebs_flags;
u64 rtm_abort_event;
/*
* Intel LBR
*/
unsigned int lbr_tos, lbr_from, lbr_to,
lbr_info, lbr_nr; /* LBR base regs and size */
union {
u64 lbr_sel_mask; /* LBR_SELECT valid bits */
u64 lbr_ctl_mask; /* LBR_CTL valid bits */
};
union {
const int *lbr_sel_map; /* lbr_select mappings */
int *lbr_ctl_map; /* LBR_CTL mappings */
};
bool lbr_double_abort; /* duplicated lbr aborts */
bool lbr_pt_coexist; /* (LBR|BTS) may coexist with PT */
unsigned int lbr_has_info:1;
unsigned int lbr_has_tsx:1;
unsigned int lbr_from_flags:1;
unsigned int lbr_to_cycles:1;
/*
* Intel Architectural LBR CPUID Enumeration
*/
unsigned int lbr_depth_mask:8;
unsigned int lbr_deep_c_reset:1;
unsigned int lbr_lip:1;
unsigned int lbr_cpl:1;
unsigned int lbr_filter:1;
unsigned int lbr_call_stack:1;
unsigned int lbr_mispred:1;
unsigned int lbr_timed_lbr:1;
unsigned int lbr_br_type:1;
void (*lbr_reset)(void);
void (*lbr_read)(struct cpu_hw_events *cpuc);
void (*lbr_save)(void *ctx);
void (*lbr_restore)(void *ctx);
/*
* Intel PT/LBR/BTS are exclusive
*/
atomic_t lbr_exclusive[x86_lbr_exclusive_max];
/*
* Intel perf metrics
*/
int num_topdown_events;
u64 (*update_topdown_event)(struct perf_event *event);
int (*set_topdown_event_period)(struct perf_event *event);
/*
* perf task context (i.e. struct perf_event_context::task_ctx_data)
* switch helper to bridge calls from perf/core to perf/x86.
* See struct pmu::swap_task_ctx() usage for examples;
*/
void (*swap_task_ctx)(struct perf_event_context *prev,
struct perf_event_context *next);
/*
* AMD bits
*/
unsigned int amd_nb_constraints : 1;
u64 perf_ctr_pair_en;
/*
* Extra registers for events
*/
struct extra_reg *extra_regs;
unsigned int flags;
/*
* Intel host/guest support (KVM)
*/
struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
/*
* Check period value for PERF_EVENT_IOC_PERIOD ioctl.
*/
int (*check_period) (struct perf_event *event, u64 period);
int (*aux_output_match) (struct perf_event *event);
int (*filter_match)(struct perf_event *event);
/*
* Hybrid support
*
* Most PMU capabilities are the same among different hybrid PMUs.
* The global x86_pmu saves the architecture capabilities, which
* are available for all PMUs. The hybrid_pmu only includes the
* unique capabilities.
*/
int num_hybrid_pmus;
struct x86_hybrid_pmu *hybrid_pmu;
u8 (*get_hybrid_cpu_type) (void);
};
struct x86_perf_task_context_opt {
int lbr_callstack_users;
int lbr_stack_state;
int log_id;
};
struct x86_perf_task_context {
u64 lbr_sel;
int tos;
int valid_lbrs;
struct x86_perf_task_context_opt opt;
struct lbr_entry lbr[MAX_LBR_ENTRIES];
};
struct x86_perf_task_context_arch_lbr {
struct x86_perf_task_context_opt opt;
struct lbr_entry entries[];
};
/*
* Add padding to guarantee the 64-byte alignment of the state buffer.
*
* The structure is dynamically allocated. The size of the LBR state may vary
* based on the number of LBR registers.
*
* Do not put anything after the LBR state.
*/
struct x86_perf_task_context_arch_lbr_xsave {
struct x86_perf_task_context_opt opt;
union {
struct xregs_state xsave;
struct {
struct fxregs_state i387;
struct xstate_header header;
struct arch_lbr_state lbr;
} __attribute__ ((packed, aligned (XSAVE_ALIGNMENT)));
};
};
#define x86_add_quirk(func_) \
do { \
static struct x86_pmu_quirk __quirk __initdata = { \
.func = func_, \
}; \
__quirk.next = x86_pmu.quirks; \
x86_pmu.quirks = &__quirk; \
} while (0)
/*
* x86_pmu flags
*/
#define PMU_FL_NO_HT_SHARING 0x1 /* no hyper-threading resource sharing */
#define PMU_FL_HAS_RSP_1 0x2 /* has 2 equivalent offcore_rsp regs */
#define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */
#define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */
#define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */
#define PMU_FL_TFA 0x20 /* deal with TSX force abort */
#define PMU_FL_PAIR 0x40 /* merge counters for large incr. events */
#define PMU_FL_INSTR_LATENCY 0x80 /* Support Instruction Latency in PEBS Memory Info Record */
#define PMU_FL_MEM_LOADS_AUX 0x100 /* Require an auxiliary event for the complete memory info */
#define EVENT_VAR(_id) event_attr_##_id
#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
#define EVENT_ATTR(_name, _id) \
static struct perf_pmu_events_attr EVENT_VAR(_id) = { \
.attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \
.id = PERF_COUNT_HW_##_id, \
.event_str = NULL, \
};
#define EVENT_ATTR_STR(_name, v, str) \
static struct perf_pmu_events_attr event_attr_##v = { \
.attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \
.id = 0, \
.event_str = str, \
};
#define EVENT_ATTR_STR_HT(_name, v, noht, ht) \
static struct perf_pmu_events_ht_attr event_attr_##v = { \
.attr = __ATTR(_name, 0444, events_ht_sysfs_show, NULL),\
.id = 0, \
.event_str_noht = noht, \
.event_str_ht = ht, \
}
#define EVENT_ATTR_STR_HYBRID(_name, v, str, _pmu) \
static struct perf_pmu_events_hybrid_attr event_attr_##v = { \
.attr = __ATTR(_name, 0444, events_hybrid_sysfs_show, NULL),\
.id = 0, \
.event_str = str, \
.pmu_type = _pmu, \
}
#define FORMAT_HYBRID_PTR(_id) (&format_attr_hybrid_##_id.attr.attr)
#define FORMAT_ATTR_HYBRID(_name, _pmu) \
static struct perf_pmu_format_hybrid_attr format_attr_hybrid_##_name = {\
.attr = __ATTR_RO(_name), \
.pmu_type = _pmu, \
}
struct pmu *x86_get_pmu(unsigned int cpu);
extern struct x86_pmu x86_pmu __read_mostly;
static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
{
if (static_cpu_has(X86_FEATURE_ARCH_LBR))
return &((struct x86_perf_task_context_arch_lbr *)ctx)->opt;
return &((struct x86_perf_task_context *)ctx)->opt;
}
static inline bool x86_pmu_has_lbr_callstack(void)
{
return x86_pmu.lbr_sel_map &&
x86_pmu.lbr_sel_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] > 0;
}
DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
int x86_perf_event_set_period(struct perf_event *event);
/*
* Generalized hw caching related hw_event table, filled
* in on a per model basis. A value of 0 means
* 'not supported', -1 means 'hw_event makes no sense on
* this CPU', any other value means the raw hw_event
* ID.
*/
#define C(x) PERF_COUNT_HW_CACHE_##x
extern u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
extern u64 __read_mostly hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
u64 x86_perf_event_update(struct perf_event *event);
static inline unsigned int x86_pmu_config_addr(int index)
{
return x86_pmu.eventsel + (x86_pmu.addr_offset ?
x86_pmu.addr_offset(index, true) : index);
}
static inline unsigned int x86_pmu_event_addr(int index)
{
return x86_pmu.perfctr + (x86_pmu.addr_offset ?
x86_pmu.addr_offset(index, false) : index);
}
static inline int x86_pmu_rdpmc_index(int index)
{
return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
}
bool check_hw_exists(struct pmu *pmu, int num_counters,
int num_counters_fixed);
int x86_add_exclusive(unsigned int what);
void x86_del_exclusive(unsigned int what);
int x86_reserve_hardware(void);
void x86_release_hardware(void);
int x86_pmu_max_precise(void);
void hw_perf_lbr_event_destroy(struct perf_event *event);
int x86_setup_perfctr(struct perf_event *event);
int x86_pmu_hw_config(struct perf_event *event);
void x86_pmu_disable_all(void);
static inline bool has_amd_brs(struct hw_perf_event *hwc)
{
return hwc->flags & PERF_X86_EVENT_AMD_BRS;
}
static inline bool is_counter_pair(struct hw_perf_event *hwc)
{
return hwc->flags & PERF_X86_EVENT_PAIR;
}
static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
u64 enable_mask)
{
u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
if (hwc->extra_reg.reg)
wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
/*
* Add enabled Merge event on next counter
* if large increment event being enabled on this counter
*/
if (is_counter_pair(hwc))
wrmsrl(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en);
wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
}
void x86_pmu_enable_all(int added);
int perf_assign_events(struct event_constraint **constraints, int n,
int wmin, int wmax, int gpmax, int *assign);
int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
void x86_pmu_stop(struct perf_event *event, int flags);
static inline void x86_pmu_disable_event(struct perf_event *event)
{
u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
struct hw_perf_event *hwc = &event->hw;
wrmsrl(hwc->config_base, hwc->config & ~disable_mask);
if (is_counter_pair(hwc))
wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0);
}
void x86_pmu_enable_event(struct perf_event *event);
int x86_pmu_handle_irq(struct pt_regs *regs);
void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
u64 intel_ctrl);
void x86_pmu_update_cpu_context(struct pmu *pmu, int cpu);
extern struct event_constraint emptyconstraint;
extern struct event_constraint unconstrained;
static inline bool kernel_ip(unsigned long ip)
{
#ifdef CONFIG_X86_32
return ip > PAGE_OFFSET;
#else
return (long)ip < 0;
#endif
}
/*
* Not all PMUs provide the right context information to place the reported IP
* into full context. Specifically segment registers are typically not
* supplied.
*
* Assuming the address is a linear address (it is for IBS), we fake the CS and
* vm86 mode using the known zero-based code segment and 'fix up' the registers
* to reflect this.
*
* Intel PEBS/LBR appear to typically provide the effective address, nothing
* much we can do about that but pray and treat it like a linear address.
*/
static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
{
regs->cs = kernel_ip(ip) ? __KERNEL_CS : __USER_CS;
if (regs->flags & X86_VM_MASK)
regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK);
regs->ip = ip;
}
ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
ssize_t intel_event_sysfs_show(char *page, u64 config);
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
ssize_t events_hybrid_sysfs_show(struct device *dev,
struct device_attribute *attr,
char *page);
static inline bool fixed_counter_disabled(int i, struct pmu *pmu)
{
u64 intel_ctrl = hybrid(pmu, intel_ctrl);
return !(intel_ctrl >> (i + INTEL_PMC_IDX_FIXED));
}
#ifdef CONFIG_CPU_SUP_AMD
int amd_pmu_init(void);
#ifdef CONFIG_PERF_EVENTS_AMD_BRS
int amd_brs_init(void);
void amd_brs_disable(void);
void amd_brs_enable(void);
void amd_brs_enable_all(void);
void amd_brs_disable_all(void);
void amd_brs_drain(void);
void amd_brs_lopwr_init(void);
void amd_brs_disable_all(void);
int amd_brs_setup_filter(struct perf_event *event);
void amd_brs_reset(void);
static inline void amd_pmu_brs_add(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
perf_sched_cb_inc(event->ctx->pmu);
cpuc->lbr_users++;
/*
* No need to reset BRS because it is reset
* on brs_enable() and it is saturating
*/
}
static inline void amd_pmu_brs_del(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);
perf_sched_cb_dec(event->ctx->pmu);
}
void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in);
#else
static inline int amd_brs_init(void)
{
return 0;
}
static inline void amd_brs_disable(void) {}
static inline void amd_brs_enable(void) {}
static inline void amd_brs_drain(void) {}
static inline void amd_brs_lopwr_init(void) {}
static inline void amd_brs_disable_all(void) {}
static inline int amd_brs_setup_filter(struct perf_event *event)
{
return 0;
}
static inline void amd_brs_reset(void) {}
static inline void amd_pmu_brs_add(struct perf_event *event)
{
}
static inline void amd_pmu_brs_del(struct perf_event *event)
{
}
static inline void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in)
{
}
static inline void amd_brs_enable_all(void)
{
}
#endif
#else /* CONFIG_CPU_SUP_AMD */
static inline int amd_pmu_init(void)
{
return 0;
}
static inline int amd_brs_init(void)
{
return -EOPNOTSUPP;
}
static inline void amd_brs_drain(void)
{
}
static inline void amd_brs_enable_all(void)
{
}
static inline void amd_brs_disable_all(void)
{
}
#endif /* CONFIG_CPU_SUP_AMD */
static inline int is_pebs_pt(struct perf_event *event)
{
return !!(event->hw.flags & PERF_X86_EVENT_PEBS_VIA_PT);
}
#ifdef CONFIG_CPU_SUP_INTEL
static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period)
{
struct hw_perf_event *hwc = &event->hw;
unsigned int hw_event, bts_event;
if (event->attr.freq)
return false;
hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
return hw_event == bts_event && period == 1;
}
static inline bool intel_pmu_has_bts(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
return intel_pmu_has_bts_period(event, hwc->sample_period);
}
static __always_inline void __intel_pmu_pebs_disable_all(void)
{
wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
}
static __always_inline void __intel_pmu_arch_lbr_disable(void)
{
wrmsrl(MSR_ARCH_LBR_CTL, 0);
}
static __always_inline void __intel_pmu_lbr_disable(void)
{
u64 debugctl;
rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
}
int intel_pmu_save_and_restart(struct perf_event *event);
struct event_constraint *
x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event);
extern int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu);
extern void intel_cpuc_finish(struct cpu_hw_events *cpuc);
int intel_pmu_init(void);
void init_debug_store_on_cpu(int cpu);
void fini_debug_store_on_cpu(int cpu);
void release_ds_buffers(void);
void reserve_ds_buffers(void);
void release_lbr_buffers(void);
void reserve_lbr_buffers(void);
extern struct event_constraint bts_constraint;
extern struct event_constraint vlbr_constraint;
void intel_pmu_enable_bts(u64 config);
void intel_pmu_disable_bts(void);
int intel_pmu_drain_bts_buffer(void);
extern struct event_constraint intel_core2_pebs_event_constraints[];
extern struct event_constraint intel_atom_pebs_event_constraints[];
extern struct event_constraint intel_slm_pebs_event_constraints[];
extern struct event_constraint intel_glm_pebs_event_constraints[];
extern struct event_constraint intel_glp_pebs_event_constraints[];
extern struct event_constraint intel_grt_pebs_event_constraints[];
extern struct event_constraint intel_nehalem_pebs_event_constraints[];
extern struct event_constraint intel_westmere_pebs_event_constraints[];
extern struct event_constraint intel_snb_pebs_event_constraints[];
extern struct event_constraint intel_ivb_pebs_event_constraints[];
extern struct event_constraint intel_hsw_pebs_event_constraints[];
extern struct event_constraint intel_bdw_pebs_event_constraints[];
extern struct event_constraint intel_skl_pebs_event_constraints[];
extern struct event_constraint intel_icl_pebs_event_constraints[];
extern struct event_constraint intel_spr_pebs_event_constraints[];
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_add(struct perf_event *event);
void intel_pmu_pebs_del(struct perf_event *event);
void intel_pmu_pebs_enable(struct perf_event *event);
void intel_pmu_pebs_disable(struct perf_event *event);
void intel_pmu_pebs_enable_all(void);
void intel_pmu_pebs_disable_all(void);
void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
void intel_pmu_auto_reload_read(struct perf_event *event);
void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
void intel_ds_init(void);
void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
struct perf_event_context *next);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
u64 lbr_from_signext_quirk_wr(u64 val);
void intel_pmu_lbr_reset(void);
void intel_pmu_lbr_reset_32(void);
void intel_pmu_lbr_reset_64(void);
void intel_pmu_lbr_add(struct perf_event *event);
void intel_pmu_lbr_del(struct perf_event *event);
void intel_pmu_lbr_enable_all(bool pmi);
void intel_pmu_lbr_disable_all(void);
void intel_pmu_lbr_read(void);
void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc);
void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc);
void intel_pmu_lbr_save(void *ctx);
void intel_pmu_lbr_restore(void *ctx);
void intel_pmu_lbr_init_core(void);
void intel_pmu_lbr_init_nhm(void);
void intel_pmu_lbr_init_atom(void);
void intel_pmu_lbr_init_slm(void);
void intel_pmu_lbr_init_snb(void);
void intel_pmu_lbr_init_hsw(void);
void intel_pmu_lbr_init_skl(void);
void intel_pmu_lbr_init_knl(void);
void intel_pmu_lbr_init(void);
void intel_pmu_arch_lbr_init(void);
void intel_pmu_pebs_data_source_nhm(void);
void intel_pmu_pebs_data_source_skl(bool pmem);
int intel_pmu_setup_lbr_filter(struct perf_event *event);
void intel_pt_interrupt(void);
int intel_bts_interrupt(void);
void intel_bts_enable_local(void);
void intel_bts_disable_local(void);
int p4_pmu_init(void);
int p6_pmu_init(void);
int knc_pmu_init(void);
static inline int is_ht_workaround_enabled(void)
{
return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
}
#else /* CONFIG_CPU_SUP_INTEL */
static inline void reserve_ds_buffers(void)
{
}
static inline void release_ds_buffers(void)
{
}
static inline void release_lbr_buffers(void)
{
}
static inline void reserve_lbr_buffers(void)
{
}
static inline int intel_pmu_init(void)
{
return 0;
}
static inline int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
{
return 0;
}
static inline void intel_cpuc_finish(struct cpu_hw_events *cpuc)
{
}
static inline int is_ht_workaround_enabled(void)
{
return 0;
}
#endif /* CONFIG_CPU_SUP_INTEL */
#if ((defined CONFIG_CPU_SUP_CENTAUR) || (defined CONFIG_CPU_SUP_ZHAOXIN))
int zhaoxin_pmu_init(void);
#else
static inline int zhaoxin_pmu_init(void)
{
return 0;
}
#endif /*CONFIG_CPU_SUP_CENTAUR or CONFIG_CPU_SUP_ZHAOXIN*/
|