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
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
|
/*
* Performance events:
*
* Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
* Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
* Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
*
* Data type definitions, declarations, prototypes.
*
* Started by: Thomas Gleixner and Ingo Molnar
*
* For licencing details see kernel-base/COPYING
*/
#ifndef _LINUX_PERF_EVENT_H
#define _LINUX_PERF_EVENT_H
#include <uapi/linux/perf_event.h>
#include <uapi/linux/bpf_perf_event.h>
/*
* Kernel-internal data types and definitions:
*/
#ifdef CONFIG_PERF_EVENTS
# include <asm/perf_event.h>
# include <asm/local64.h>
#endif
#define PERF_GUEST_ACTIVE 0x01
#define PERF_GUEST_USER 0x02
struct perf_guest_info_callbacks {
unsigned int (*state)(void);
unsigned long (*get_ip)(void);
unsigned int (*handle_intel_pt_intr)(void);
};
#ifdef CONFIG_HAVE_HW_BREAKPOINT
#include <linux/rhashtable-types.h>
#include <asm/hw_breakpoint.h>
#endif
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>
#include <linux/spinlock.h>
#include <linux/hrtimer.h>
#include <linux/fs.h>
#include <linux/pid_namespace.h>
#include <linux/workqueue.h>
#include <linux/ftrace.h>
#include <linux/cpu.h>
#include <linux/irq_work.h>
#include <linux/static_key.h>
#include <linux/jump_label_ratelimit.h>
#include <linux/atomic.h>
#include <linux/sysfs.h>
#include <linux/perf_regs.h>
#include <linux/cgroup.h>
#include <linux/refcount.h>
#include <linux/security.h>
#include <linux/static_call.h>
#include <linux/lockdep.h>
#include <asm/local.h>
struct perf_callchain_entry {
__u64 nr;
__u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */
};
struct perf_callchain_entry_ctx {
struct perf_callchain_entry *entry;
u32 max_stack;
u32 nr;
short contexts;
bool contexts_maxed;
};
typedef unsigned long (*perf_copy_f)(void *dst, const void *src,
unsigned long off, unsigned long len);
struct perf_raw_frag {
union {
struct perf_raw_frag *next;
unsigned long pad;
};
perf_copy_f copy;
void *data;
u32 size;
} __packed;
struct perf_raw_record {
struct perf_raw_frag frag;
u32 size;
};
static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag)
{
return frag->pad < sizeof(u64);
}
/*
* branch stack layout:
* nr: number of taken branches stored in entries[]
* hw_idx: The low level index of raw branch records
* for the most recent branch.
* -1ULL means invalid/unknown.
*
* Note that nr can vary from sample to sample
* branches (to, from) are stored from most recent
* to least recent, i.e., entries[0] contains the most
* recent branch.
* The entries[] is an abstraction of raw branch records,
* which may not be stored in age order in HW, e.g. Intel LBR.
* The hw_idx is to expose the low level index of raw
* branch record for the most recent branch aka entries[0].
* The hw_idx index is between -1 (unknown) and max depth,
* which can be retrieved in /sys/devices/cpu/caps/branches.
* For the architectures whose raw branch records are
* already stored in age order, the hw_idx should be 0.
*/
struct perf_branch_stack {
__u64 nr;
__u64 hw_idx;
struct perf_branch_entry entries[];
};
struct task_struct;
/*
* extra PMU register associated with an event
*/
struct hw_perf_event_extra {
u64 config; /* register value */
unsigned int reg; /* register address or index */
int alloc; /* extra register already allocated */
int idx; /* index in shared_regs->regs[] */
};
/**
* hw_perf_event::flag values
*
* PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific
* usage.
*/
#define PERF_EVENT_FLAG_ARCH 0x000fffff
#define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000
static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0);
/**
* struct hw_perf_event - performance event hardware details:
*/
struct hw_perf_event {
#ifdef CONFIG_PERF_EVENTS
union {
struct { /* hardware */
u64 config;
u64 last_tag;
unsigned long config_base;
unsigned long event_base;
int event_base_rdpmc;
int idx;
int last_cpu;
int flags;
struct hw_perf_event_extra extra_reg;
struct hw_perf_event_extra branch_reg;
};
struct { /* software */
struct hrtimer hrtimer;
};
struct { /* tracepoint */
/* for tp_event->class */
struct list_head tp_list;
};
struct { /* amd_power */
u64 pwr_acc;
u64 ptsc;
};
#ifdef CONFIG_HAVE_HW_BREAKPOINT
struct { /* breakpoint */
/*
* Crufty hack to avoid the chicken and egg
* problem hw_breakpoint has with context
* creation and event initalization.
*/
struct arch_hw_breakpoint info;
struct rhlist_head bp_list;
};
#endif
struct { /* amd_iommu */
u8 iommu_bank;
u8 iommu_cntr;
u16 padding;
u64 conf;
u64 conf1;
};
};
/*
* If the event is a per task event, this will point to the task in
* question. See the comment in perf_event_alloc().
*/
struct task_struct *target;
/*
* PMU would store hardware filter configuration
* here.
*/
void *addr_filters;
/* Last sync'ed generation of filters */
unsigned long addr_filters_gen;
/*
* hw_perf_event::state flags; used to track the PERF_EF_* state.
*/
#define PERF_HES_STOPPED 0x01 /* the counter is stopped */
#define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */
#define PERF_HES_ARCH 0x04
int state;
/*
* The last observed hardware counter value, updated with a
* local64_cmpxchg() such that pmu::read() can be called nested.
*/
local64_t prev_count;
/*
* The period to start the next sample with.
*/
u64 sample_period;
union {
struct { /* Sampling */
/*
* The period we started this sample with.
*/
u64 last_period;
/*
* However much is left of the current period;
* note that this is a full 64bit value and
* allows for generation of periods longer
* than hardware might allow.
*/
local64_t period_left;
};
struct { /* Topdown events counting for context switch */
u64 saved_metric;
u64 saved_slots;
};
};
/*
* State for throttling the event, see __perf_event_overflow() and
* perf_adjust_freq_unthr_context().
*/
u64 interrupts_seq;
u64 interrupts;
/*
* State for freq target events, see __perf_event_overflow() and
* perf_adjust_freq_unthr_context().
*/
u64 freq_time_stamp;
u64 freq_count_stamp;
#endif
};
struct perf_event;
struct perf_event_pmu_context;
/*
* Common implementation detail of pmu::{start,commit,cancel}_txn
*/
#define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */
#define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */
/**
* pmu::capabilities flags
*/
#define PERF_PMU_CAP_NO_INTERRUPT 0x0001
#define PERF_PMU_CAP_NO_NMI 0x0002
#define PERF_PMU_CAP_AUX_NO_SG 0x0004
#define PERF_PMU_CAP_EXTENDED_REGS 0x0008
#define PERF_PMU_CAP_EXCLUSIVE 0x0010
#define PERF_PMU_CAP_ITRACE 0x0020
#define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x0040
#define PERF_PMU_CAP_NO_EXCLUDE 0x0080
#define PERF_PMU_CAP_AUX_OUTPUT 0x0100
#define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0200
struct perf_output_handle;
/**
* struct pmu - generic performance monitoring unit
*/
struct pmu {
struct list_head entry;
struct module *module;
struct device *dev;
struct device *parent;
const struct attribute_group **attr_groups;
const struct attribute_group **attr_update;
const char *name;
int type;
/*
* various common per-pmu feature flags
*/
int capabilities;
int __percpu *pmu_disable_count;
struct perf_cpu_pmu_context __percpu *cpu_pmu_context;
atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */
int task_ctx_nr;
int hrtimer_interval_ms;
/* number of address filters this PMU can do */
unsigned int nr_addr_filters;
/*
* Fully disable/enable this PMU, can be used to protect from the PMI
* as well as for lazy/batch writing of the MSRs.
*/
void (*pmu_enable) (struct pmu *pmu); /* optional */
void (*pmu_disable) (struct pmu *pmu); /* optional */
/*
* Try and initialize the event for this PMU.
*
* Returns:
* -ENOENT -- @event is not for this PMU
*
* -ENODEV -- @event is for this PMU but PMU not present
* -EBUSY -- @event is for this PMU but PMU temporarily unavailable
* -EINVAL -- @event is for this PMU but @event is not valid
* -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported
* -EACCES -- @event is for this PMU, @event is valid, but no privileges
*
* 0 -- @event is for this PMU and valid
*
* Other error return values are allowed.
*/
int (*event_init) (struct perf_event *event);
/*
* Notification that the event was mapped or unmapped. Called
* in the context of the mapping task.
*/
void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */
void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */
/*
* Flags for ->add()/->del()/ ->start()/->stop(). There are
* matching hw_perf_event::state flags.
*/
#define PERF_EF_START 0x01 /* start the counter when adding */
#define PERF_EF_RELOAD 0x02 /* reload the counter when starting */
#define PERF_EF_UPDATE 0x04 /* update the counter when stopping */
/*
* Adds/Removes a counter to/from the PMU, can be done inside a
* transaction, see the ->*_txn() methods.
*
* The add/del callbacks will reserve all hardware resources required
* to service the event, this includes any counter constraint
* scheduling etc.
*
* Called with IRQs disabled and the PMU disabled on the CPU the event
* is on.
*
* ->add() called without PERF_EF_START should result in the same state
* as ->add() followed by ->stop().
*
* ->del() must always PERF_EF_UPDATE stop an event. If it calls
* ->stop() that must deal with already being stopped without
* PERF_EF_UPDATE.
*/
int (*add) (struct perf_event *event, int flags);
void (*del) (struct perf_event *event, int flags);
/*
* Starts/Stops a counter present on the PMU.
*
* The PMI handler should stop the counter when perf_event_overflow()
* returns !0. ->start() will be used to continue.
*
* Also used to change the sample period.
*
* Called with IRQs disabled and the PMU disabled on the CPU the event
* is on -- will be called from NMI context with the PMU generates
* NMIs.
*
* ->stop() with PERF_EF_UPDATE will read the counter and update
* period/count values like ->read() would.
*
* ->start() with PERF_EF_RELOAD will reprogram the counter
* value, must be preceded by a ->stop() with PERF_EF_UPDATE.
*/
void (*start) (struct perf_event *event, int flags);
void (*stop) (struct perf_event *event, int flags);
/*
* Updates the counter value of the event.
*
* For sampling capable PMUs this will also update the software period
* hw_perf_event::period_left field.
*/
void (*read) (struct perf_event *event);
/*
* Group events scheduling is treated as a transaction, add
* group events as a whole and perform one schedulability test.
* If the test fails, roll back the whole group
*
* Start the transaction, after this ->add() doesn't need to
* do schedulability tests.
*
* Optional.
*/
void (*start_txn) (struct pmu *pmu, unsigned int txn_flags);
/*
* If ->start_txn() disabled the ->add() schedulability test
* then ->commit_txn() is required to perform one. On success
* the transaction is closed. On error the transaction is kept
* open until ->cancel_txn() is called.
*
* Optional.
*/
int (*commit_txn) (struct pmu *pmu);
/*
* Will cancel the transaction, assumes ->del() is called
* for each successful ->add() during the transaction.
*
* Optional.
*/
void (*cancel_txn) (struct pmu *pmu);
/*
* Will return the value for perf_event_mmap_page::index for this event,
* if no implementation is provided it will default to: event->hw.idx + 1.
*/
int (*event_idx) (struct perf_event *event); /*optional */
/*
* context-switches callback
*/
void (*sched_task) (struct perf_event_pmu_context *pmu_ctx,
bool sched_in);
/*
* Kmem cache of PMU specific data
*/
struct kmem_cache *task_ctx_cache;
/*
* PMU specific parts of task perf event context (i.e. ctx->task_ctx_data)
* can be synchronized using this function. See Intel LBR callstack support
* implementation and Perf core context switch handling callbacks for usage
* examples.
*/
void (*swap_task_ctx) (struct perf_event_pmu_context *prev_epc,
struct perf_event_pmu_context *next_epc);
/* optional */
/*
* Set up pmu-private data structures for an AUX area
*/
void *(*setup_aux) (struct perf_event *event, void **pages,
int nr_pages, bool overwrite);
/* optional */
/*
* Free pmu-private AUX data structures
*/
void (*free_aux) (void *aux); /* optional */
/*
* Take a snapshot of the AUX buffer without touching the event
* state, so that preempting ->start()/->stop() callbacks does
* not interfere with their logic. Called in PMI context.
*
* Returns the size of AUX data copied to the output handle.
*
* Optional.
*/
long (*snapshot_aux) (struct perf_event *event,
struct perf_output_handle *handle,
unsigned long size);
/*
* Validate address range filters: make sure the HW supports the
* requested configuration and number of filters; return 0 if the
* supplied filters are valid, -errno otherwise.
*
* Runs in the context of the ioctl()ing process and is not serialized
* with the rest of the PMU callbacks.
*/
int (*addr_filters_validate) (struct list_head *filters);
/* optional */
/*
* Synchronize address range filter configuration:
* translate hw-agnostic filters into hardware configuration in
* event::hw::addr_filters.
*
* Runs as a part of filter sync sequence that is done in ->start()
* callback by calling perf_event_addr_filters_sync().
*
* May (and should) traverse event::addr_filters::list, for which its
* caller provides necessary serialization.
*/
void (*addr_filters_sync) (struct perf_event *event);
/* optional */
/*
* Check if event can be used for aux_output purposes for
* events of this PMU.
*
* Runs from perf_event_open(). Should return 0 for "no match"
* or non-zero for "match".
*/
int (*aux_output_match) (struct perf_event *event);
/* optional */
/*
* Skip programming this PMU on the given CPU. Typically needed for
* big.LITTLE things.
*/
bool (*filter) (struct pmu *pmu, int cpu); /* optional */
/*
* Check period value for PERF_EVENT_IOC_PERIOD ioctl.
*/
int (*check_period) (struct perf_event *event, u64 value); /* optional */
};
enum perf_addr_filter_action_t {
PERF_ADDR_FILTER_ACTION_STOP = 0,
PERF_ADDR_FILTER_ACTION_START,
PERF_ADDR_FILTER_ACTION_FILTER,
};
/**
* struct perf_addr_filter - address range filter definition
* @entry: event's filter list linkage
* @path: object file's path for file-based filters
* @offset: filter range offset
* @size: filter range size (size==0 means single address trigger)
* @action: filter/start/stop
*
* This is a hardware-agnostic filter configuration as specified by the user.
*/
struct perf_addr_filter {
struct list_head entry;
struct path path;
unsigned long offset;
unsigned long size;
enum perf_addr_filter_action_t action;
};
/**
* struct perf_addr_filters_head - container for address range filters
* @list: list of filters for this event
* @lock: spinlock that serializes accesses to the @list and event's
* (and its children's) filter generations.
* @nr_file_filters: number of file-based filters
*
* A child event will use parent's @list (and therefore @lock), so they are
* bundled together; see perf_event_addr_filters().
*/
struct perf_addr_filters_head {
struct list_head list;
raw_spinlock_t lock;
unsigned int nr_file_filters;
};
struct perf_addr_filter_range {
unsigned long start;
unsigned long size;
};
/**
* enum perf_event_state - the states of an event:
*/
enum perf_event_state {
PERF_EVENT_STATE_DEAD = -4,
PERF_EVENT_STATE_EXIT = -3,
PERF_EVENT_STATE_ERROR = -2,
PERF_EVENT_STATE_OFF = -1,
PERF_EVENT_STATE_INACTIVE = 0,
PERF_EVENT_STATE_ACTIVE = 1,
};
struct file;
struct perf_sample_data;
typedef void (*perf_overflow_handler_t)(struct perf_event *,
struct perf_sample_data *,
struct pt_regs *regs);
/*
* Event capabilities. For event_caps and groups caps.
*
* PERF_EV_CAP_SOFTWARE: Is a software event.
* PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read
* from any CPU in the package where it is active.
* PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and
* cannot be a group leader. If an event with this flag is detached from the
* group it is scheduled out and moved into an unrecoverable ERROR state.
*/
#define PERF_EV_CAP_SOFTWARE BIT(0)
#define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1)
#define PERF_EV_CAP_SIBLING BIT(2)
#define SWEVENT_HLIST_BITS 8
#define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS)
struct swevent_hlist {
struct hlist_head heads[SWEVENT_HLIST_SIZE];
struct rcu_head rcu_head;
};
#define PERF_ATTACH_CONTEXT 0x01
#define PERF_ATTACH_GROUP 0x02
#define PERF_ATTACH_TASK 0x04
#define PERF_ATTACH_TASK_DATA 0x08
#define PERF_ATTACH_ITRACE 0x10
#define PERF_ATTACH_SCHED_CB 0x20
#define PERF_ATTACH_CHILD 0x40
struct bpf_prog;
struct perf_cgroup;
struct perf_buffer;
struct pmu_event_list {
raw_spinlock_t lock;
struct list_head list;
};
/*
* event->sibling_list is modified whole holding both ctx->lock and ctx->mutex
* as such iteration must hold either lock. However, since ctx->lock is an IRQ
* safe lock, and is only held by the CPU doing the modification, having IRQs
* disabled is sufficient since it will hold-off the IPIs.
*/
#ifdef CONFIG_PROVE_LOCKING
#define lockdep_assert_event_ctx(event) \
WARN_ON_ONCE(__lockdep_enabled && \
(this_cpu_read(hardirqs_enabled) && \
lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD))
#else
#define lockdep_assert_event_ctx(event)
#endif
#define for_each_sibling_event(sibling, event) \
lockdep_assert_event_ctx(event); \
if ((event)->group_leader == (event)) \
list_for_each_entry((sibling), &(event)->sibling_list, sibling_list)
/**
* struct perf_event - performance event kernel representation:
*/
struct perf_event {
#ifdef CONFIG_PERF_EVENTS
/*
* entry onto perf_event_context::event_list;
* modifications require ctx->lock
* RCU safe iterations.
*/
struct list_head event_entry;
/*
* Locked for modification by both ctx->mutex and ctx->lock; holding
* either sufficies for read.
*/
struct list_head sibling_list;
struct list_head active_list;
/*
* Node on the pinned or flexible tree located at the event context;
*/
struct rb_node group_node;
u64 group_index;
/*
* We need storage to track the entries in perf_pmu_migrate_context; we
* cannot use the event_entry because of RCU and we want to keep the
* group in tact which avoids us using the other two entries.
*/
struct list_head migrate_entry;
struct hlist_node hlist_entry;
struct list_head active_entry;
int nr_siblings;
/* Not serialized. Only written during event initialization. */
int event_caps;
/* The cumulative AND of all event_caps for events in this group. */
int group_caps;
struct perf_event *group_leader;
/*
* event->pmu will always point to pmu in which this event belongs.
* Whereas event->pmu_ctx->pmu may point to other pmu when group of
* different pmu events is created.
*/
struct pmu *pmu;
void *pmu_private;
enum perf_event_state state;
unsigned int attach_state;
local64_t count;
atomic64_t child_count;
/*
* These are the total time in nanoseconds that the event
* has been enabled (i.e. eligible to run, and the task has
* been scheduled in, if this is a per-task event)
* and running (scheduled onto the CPU), respectively.
*/
u64 total_time_enabled;
u64 total_time_running;
u64 tstamp;
struct perf_event_attr attr;
u16 header_size;
u16 id_header_size;
u16 read_size;
struct hw_perf_event hw;
struct perf_event_context *ctx;
/*
* event->pmu_ctx points to perf_event_pmu_context in which the event
* is added. This pmu_ctx can be of other pmu for sw event when that
* sw event is part of a group which also contains non-sw events.
*/
struct perf_event_pmu_context *pmu_ctx;
atomic_long_t refcount;
/*
* These accumulate total time (in nanoseconds) that children
* events have been enabled and running, respectively.
*/
atomic64_t child_total_time_enabled;
atomic64_t child_total_time_running;
/*
* Protect attach/detach and child_list:
*/
struct mutex child_mutex;
struct list_head child_list;
struct perf_event *parent;
int oncpu;
int cpu;
struct list_head owner_entry;
struct task_struct *owner;
/* mmap bits */
struct mutex mmap_mutex;
atomic_t mmap_count;
struct perf_buffer *rb;
struct list_head rb_entry;
unsigned long rcu_batches;
int rcu_pending;
/* poll related */
wait_queue_head_t waitq;
struct fasync_struct *fasync;
/* delayed work for NMIs and such */
unsigned int pending_wakeup;
unsigned int pending_kill;
unsigned int pending_disable;
unsigned int pending_sigtrap;
unsigned long pending_addr; /* SIGTRAP */
struct irq_work pending_irq;
struct callback_head pending_task;
unsigned int pending_work;
atomic_t event_limit;
/* address range filters */
struct perf_addr_filters_head addr_filters;
/* vma address array for file-based filders */
struct perf_addr_filter_range *addr_filter_ranges;
unsigned long addr_filters_gen;
/* for aux_output events */
struct perf_event *aux_event;
void (*destroy)(struct perf_event *);
struct rcu_head rcu_head;
struct pid_namespace *ns;
u64 id;
atomic64_t lost_samples;
u64 (*clock)(void);
perf_overflow_handler_t overflow_handler;
void *overflow_handler_context;
#ifdef CONFIG_BPF_SYSCALL
perf_overflow_handler_t orig_overflow_handler;
struct bpf_prog *prog;
u64 bpf_cookie;
#endif
#ifdef CONFIG_EVENT_TRACING
struct trace_event_call *tp_event;
struct event_filter *filter;
#ifdef CONFIG_FUNCTION_TRACER
struct ftrace_ops ftrace_ops;
#endif
#endif
#ifdef CONFIG_CGROUP_PERF
struct perf_cgroup *cgrp; /* cgroup event is attach to */
#endif
#ifdef CONFIG_SECURITY
void *security;
#endif
struct list_head sb_list;
#endif /* CONFIG_PERF_EVENTS */
};
/*
* ,-----------------------[1:n]----------------------.
* V V
* perf_event_context <-[1:n]-> perf_event_pmu_context <--- perf_event
* ^ ^ | |
* `--------[1:n]---------' `-[n:1]-> pmu <-[1:n]-'
*
*
* struct perf_event_pmu_context lifetime is refcount based and RCU freed
* (similar to perf_event_context). Locking is as if it were a member of
* perf_event_context; specifically:
*
* modification, both: ctx->mutex && ctx->lock
* reading, either: ctx->mutex || ctx->lock
*
* There is one exception to this; namely put_pmu_ctx() isn't always called
* with ctx->mutex held; this means that as long as we can guarantee the epc
* has events the above rules hold.
*
* Specificially, sys_perf_event_open()'s group_leader case depends on
* ctx->mutex pinning the configuration. Since we hold a reference on
* group_leader (through the filedesc) it can't go away, therefore it's
* associated pmu_ctx must exist and cannot change due to ctx->mutex.
*/
struct perf_event_pmu_context {
struct pmu *pmu;
struct perf_event_context *ctx;
struct list_head pmu_ctx_entry;
struct list_head pinned_active;
struct list_head flexible_active;
/* Used to avoid freeing per-cpu perf_event_pmu_context */
unsigned int embedded : 1;
unsigned int nr_events;
atomic_t refcount; /* event <-> epc */
struct rcu_head rcu_head;
void *task_ctx_data; /* pmu specific data */
/*
* Set when one or more (plausibly active) event can't be scheduled
* due to pmu overcommit or pmu constraints, except tolerant to
* events not necessary to be active due to scheduling constraints,
* such as cgroups.
*/
int rotate_necessary;
};
struct perf_event_groups {
struct rb_root tree;
u64 index;
};
/**
* struct perf_event_context - event context structure
*
* Used as a container for task events and CPU events as well:
*/
struct perf_event_context {
/*
* Protect the states of the events in the list,
* nr_active, and the list:
*/
raw_spinlock_t lock;
/*
* Protect the list of events. Locking either mutex or lock
* is sufficient to ensure the list doesn't change; to change
* the list you need to lock both the mutex and the spinlock.
*/
struct mutex mutex;
struct list_head pmu_ctx_list;
struct perf_event_groups pinned_groups;
struct perf_event_groups flexible_groups;
struct list_head event_list;
int nr_events;
int nr_user;
int is_active;
int nr_task_data;
int nr_stat;
int nr_freq;
int rotate_disable;
refcount_t refcount; /* event <-> ctx */
struct task_struct *task;
/*
* Context clock, runs when context enabled.
*/
u64 time;
u64 timestamp;
u64 timeoffset;
/*
* These fields let us detect when two contexts have both
* been cloned (inherited) from a common ancestor.
*/
struct perf_event_context *parent_ctx;
u64 parent_gen;
u64 generation;
int pin_count;
#ifdef CONFIG_CGROUP_PERF
int nr_cgroups; /* cgroup evts */
#endif
struct rcu_head rcu_head;
/*
* Sum (event->pending_sigtrap + event->pending_work)
*
* The SIGTRAP is targeted at ctx->task, as such it won't do changing
* that until the signal is delivered.
*/
local_t nr_pending;
};
/*
* Number of contexts where an event can trigger:
* task, softirq, hardirq, nmi.
*/
#define PERF_NR_CONTEXTS 4
struct perf_cpu_pmu_context {
struct perf_event_pmu_context epc;
struct perf_event_pmu_context *task_epc;
struct list_head sched_cb_entry;
int sched_cb_usage;
int active_oncpu;
int exclusive;
raw_spinlock_t hrtimer_lock;
struct hrtimer hrtimer;
ktime_t hrtimer_interval;
unsigned int hrtimer_active;
};
/**
* struct perf_event_cpu_context - per cpu event context structure
*/
struct perf_cpu_context {
struct perf_event_context ctx;
struct perf_event_context *task_ctx;
int online;
#ifdef CONFIG_CGROUP_PERF
struct perf_cgroup *cgrp;
#endif
/*
* Per-CPU storage for iterators used in visit_groups_merge. The default
* storage is of size 2 to hold the CPU and any CPU event iterators.
*/
int heap_size;
struct perf_event **heap;
struct perf_event *heap_default[2];
};
struct perf_output_handle {
struct perf_event *event;
struct perf_buffer *rb;
unsigned long wakeup;
unsigned long size;
u64 aux_flags;
union {
void *addr;
unsigned long head;
};
int page;
};
struct bpf_perf_event_data_kern {
bpf_user_pt_regs_t *regs;
struct perf_sample_data *data;
struct perf_event *event;
};
#ifdef CONFIG_CGROUP_PERF
/*
* perf_cgroup_info keeps track of time_enabled for a cgroup.
* This is a per-cpu dynamically allocated data structure.
*/
struct perf_cgroup_info {
u64 time;
u64 timestamp;
u64 timeoffset;
int active;
};
struct perf_cgroup {
struct cgroup_subsys_state css;
struct perf_cgroup_info __percpu *info;
};
/*
* Must ensure cgroup is pinned (css_get) before calling
* this function. In other words, we cannot call this function
* if there is no cgroup event for the current CPU context.
*/
static inline struct perf_cgroup *
perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx)
{
return container_of(task_css_check(task, perf_event_cgrp_id,
ctx ? lockdep_is_held(&ctx->lock)
: true),
struct perf_cgroup, css);
}
#endif /* CONFIG_CGROUP_PERF */
#ifdef CONFIG_PERF_EVENTS
extern struct perf_event_context *perf_cpu_task_ctx(void);
extern void *perf_aux_output_begin(struct perf_output_handle *handle,
struct perf_event *event);
extern void perf_aux_output_end(struct perf_output_handle *handle,
unsigned long size);
extern int perf_aux_output_skip(struct perf_output_handle *handle,
unsigned long size);
extern void *perf_get_aux(struct perf_output_handle *handle);
extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags);
extern void perf_event_itrace_started(struct perf_event *event);
extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
extern void perf_pmu_unregister(struct pmu *pmu);
extern void __perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task);
extern void __perf_event_task_sched_out(struct task_struct *prev,
struct task_struct *next);
extern int perf_event_init_task(struct task_struct *child, u64 clone_flags);
extern void perf_event_exit_task(struct task_struct *child);
extern void perf_event_free_task(struct task_struct *task);
extern void perf_event_delayed_put(struct task_struct *task);
extern struct file *perf_event_get(unsigned int fd);
extern const struct perf_event *perf_get_event(struct file *file);
extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event);
extern void perf_event_print_debug(void);
extern void perf_pmu_disable(struct pmu *pmu);
extern void perf_pmu_enable(struct pmu *pmu);
extern void perf_sched_cb_dec(struct pmu *pmu);
extern void perf_sched_cb_inc(struct pmu *pmu);
extern int perf_event_task_disable(void);
extern int perf_event_task_enable(void);
extern void perf_pmu_resched(struct pmu *pmu);
extern int perf_event_refresh(struct perf_event *event, int refresh);
extern void perf_event_update_userpage(struct perf_event *event);
extern int perf_event_release_kernel(struct perf_event *event);
extern struct perf_event *
perf_event_create_kernel_counter(struct perf_event_attr *attr,
int cpu,
struct task_struct *task,
perf_overflow_handler_t callback,
void *context);
extern void perf_pmu_migrate_context(struct pmu *pmu,
int src_cpu, int dst_cpu);
int perf_event_read_local(struct perf_event *event, u64 *value,
u64 *enabled, u64 *running);
extern u64 perf_event_read_value(struct perf_event *event,
u64 *enabled, u64 *running);
extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
static inline bool branch_sample_no_flags(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS;
}
static inline bool branch_sample_no_cycles(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES;
}
static inline bool branch_sample_type(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE;
}
static inline bool branch_sample_hw_index(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
}
static inline bool branch_sample_priv(const struct perf_event *event)
{
return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;
}
struct perf_sample_data {
/*
* Fields set by perf_sample_data_init() unconditionally,
* group so as to minimize the cachelines touched.
*/
u64 sample_flags;
u64 period;
u64 dyn_size;
/*
* Fields commonly set by __perf_event_header__init_id(),
* group so as to minimize the cachelines touched.
*/
u64 type;
struct {
u32 pid;
u32 tid;
} tid_entry;
u64 time;
u64 id;
struct {
u32 cpu;
u32 reserved;
} cpu_entry;
/*
* The other fields, optionally {set,used} by
* perf_{prepare,output}_sample().
*/
u64 ip;
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
union perf_sample_weight weight;
union perf_mem_data_src data_src;
u64 txn;
struct perf_regs regs_user;
struct perf_regs regs_intr;
u64 stack_user_size;
u64 stream_id;
u64 cgroup;
u64 addr;
u64 phys_addr;
u64 data_page_size;
u64 code_page_size;
u64 aux_size;
} ____cacheline_aligned;
/* default value for data source */
#define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\
PERF_MEM_S(LVL, NA) |\
PERF_MEM_S(SNOOP, NA) |\
PERF_MEM_S(LOCK, NA) |\
PERF_MEM_S(TLB, NA))
static inline void perf_sample_data_init(struct perf_sample_data *data,
u64 addr, u64 period)
{
/* remaining struct members initialized in perf_prepare_sample() */
data->sample_flags = PERF_SAMPLE_PERIOD;
data->period = period;
data->dyn_size = 0;
if (addr) {
data->addr = addr;
data->sample_flags |= PERF_SAMPLE_ADDR;
}
}
static inline void perf_sample_save_callchain(struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs)
{
int size = 1;
data->callchain = perf_callchain(event, regs);
size += data->callchain->nr;
data->dyn_size += size * sizeof(u64);
data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
}
static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
struct perf_raw_record *raw)
{
struct perf_raw_frag *frag = &raw->frag;
u32 sum = 0;
int size;
do {
sum += frag->size;
if (perf_raw_frag_last(frag))
break;
frag = frag->next;
} while (1);
size = round_up(sum + sizeof(u32), sizeof(u64));
raw->size = size - sizeof(u32);
frag->pad = raw->size - sum;
data->raw = raw;
data->dyn_size += size;
data->sample_flags |= PERF_SAMPLE_RAW;
}
static inline void perf_sample_save_brstack(struct perf_sample_data *data,
struct perf_event *event,
struct perf_branch_stack *brs)
{
int size = sizeof(u64); /* nr */
if (branch_sample_hw_index(event))
size += sizeof(u64);
size += brs->nr * sizeof(struct perf_branch_entry);
data->br_stack = brs;
data->dyn_size += size;
data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
}
static inline u32 perf_sample_data_size(struct perf_sample_data *data,
struct perf_event *event)
{
u32 size = sizeof(struct perf_event_header);
size += event->header_size + event->id_header_size;
size += data->dyn_size;
return size;
}
/*
* Clear all bitfields in the perf_branch_entry.
* The to and from fields are not cleared because they are
* systematically modified by caller.
*/
static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br)
{
br->mispred = 0;
br->predicted = 0;
br->in_tx = 0;
br->abort = 0;
br->cycles = 0;
br->type = 0;
br->spec = PERF_BR_SPEC_NA;
br->reserved = 0;
}
extern void perf_output_sample(struct perf_output_handle *handle,
struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event);
extern void perf_prepare_sample(struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs);
extern void perf_prepare_header(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event,
struct pt_regs *regs);
extern int perf_event_overflow(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs);
extern void perf_event_output_forward(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs);
extern void perf_event_output_backward(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs);
extern int perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs);
static inline bool
is_default_overflow_handler(struct perf_event *event)
{
if (likely(event->overflow_handler == perf_event_output_forward))
return true;
if (unlikely(event->overflow_handler == perf_event_output_backward))
return true;
return false;
}
extern void
perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event);
extern void
perf_event__output_id_sample(struct perf_event *event,
struct perf_output_handle *handle,
struct perf_sample_data *sample);
extern void
perf_log_lost_samples(struct perf_event *event, u64 lost);
static inline bool event_has_any_exclude_flag(struct perf_event *event)
{
struct perf_event_attr *attr = &event->attr;
return attr->exclude_idle || attr->exclude_user ||
attr->exclude_kernel || attr->exclude_hv ||
attr->exclude_guest || attr->exclude_host;
}
static inline bool is_sampling_event(struct perf_event *event)
{
return event->attr.sample_period != 0;
}
/*
* Return 1 for a software event, 0 for a hardware event
*/
static inline int is_software_event(struct perf_event *event)
{
return event->event_caps & PERF_EV_CAP_SOFTWARE;
}
/*
* Return 1 for event in sw context, 0 for event in hw context
*/
static inline int in_software_context(struct perf_event *event)
{
return event->pmu_ctx->pmu->task_ctx_nr == perf_sw_context;
}
static inline int is_exclusive_pmu(struct pmu *pmu)
{
return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE;
}
extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
#ifndef perf_arch_fetch_caller_regs
static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { }
#endif
/*
* When generating a perf sample in-line, instead of from an interrupt /
* exception, we lack a pt_regs. This is typically used from software events
* like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints.
*
* We typically don't need a full set, but (for x86) do require:
* - ip for PERF_SAMPLE_IP
* - cs for user_mode() tests
* - sp for PERF_SAMPLE_CALLCHAIN
* - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs())
*
* NOTE: assumes @regs is otherwise already 0 filled; this is important for
* things like PERF_SAMPLE_REGS_INTR.
*/
static inline void perf_fetch_caller_regs(struct pt_regs *regs)
{
perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
}
static __always_inline void
perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
{
if (static_key_false(&perf_swevent_enabled[event_id]))
__perf_sw_event(event_id, nr, regs, addr);
}
DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]);
/*
* 'Special' version for the scheduler, it hard assumes no recursion,
* which is guaranteed by us not actually scheduling inside other swevents
* because those disable preemption.
*/
static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
{
struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
perf_fetch_caller_regs(regs);
___perf_sw_event(event_id, nr, regs, addr);
}
extern struct static_key_false perf_sched_events;
static __always_inline bool __perf_sw_enabled(int swevt)
{
return static_key_false(&perf_swevent_enabled[swevt]);
}
static inline void perf_event_task_migrate(struct task_struct *task)
{
if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS))
task->sched_migrated = 1;
}
static inline void perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task)
{
if (static_branch_unlikely(&perf_sched_events))
__perf_event_task_sched_in(prev, task);
if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) &&
task->sched_migrated) {
__perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
task->sched_migrated = 0;
}
}
static inline void perf_event_task_sched_out(struct task_struct *prev,
struct task_struct *next)
{
if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES))
__perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
#ifdef CONFIG_CGROUP_PERF
if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) &&
perf_cgroup_from_task(prev, NULL) !=
perf_cgroup_from_task(next, NULL))
__perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0);
#endif
if (static_branch_unlikely(&perf_sched_events))
__perf_event_task_sched_out(prev, next);
}
extern void perf_event_mmap(struct vm_area_struct *vma);
extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,
bool unregister, const char *sym);
extern void perf_event_bpf_event(struct bpf_prog *prog,
enum perf_bpf_event_type type,
u16 flags);
#ifdef CONFIG_GUEST_PERF_EVENTS
extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs;
DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state);
DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip);
DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr);
static inline unsigned int perf_guest_state(void)
{
return static_call(__perf_guest_state)();
}
static inline unsigned long perf_guest_get_ip(void)
{
return static_call(__perf_guest_get_ip)();
}
static inline unsigned int perf_guest_handle_intel_pt_intr(void)
{
return static_call(__perf_guest_handle_intel_pt_intr)();
}
extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs);
extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs);
#else
static inline unsigned int perf_guest_state(void) { return 0; }
static inline unsigned long perf_guest_get_ip(void) { return 0; }
static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; }
#endif /* CONFIG_GUEST_PERF_EVENTS */
extern void perf_event_exec(void);
extern void perf_event_comm(struct task_struct *tsk, bool exec);
extern void perf_event_namespaces(struct task_struct *tsk);
extern void perf_event_fork(struct task_struct *tsk);
extern void perf_event_text_poke(const void *addr,
const void *old_bytes, size_t old_len,
const void *new_bytes, size_t new_len);
/* Callchains */
DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
extern struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
u32 max_stack, bool crosstask, bool add_mark);
extern int get_callchain_buffers(int max_stack);
extern void put_callchain_buffers(void);
extern struct perf_callchain_entry *get_callchain_entry(int *rctx);
extern void put_callchain_entry(int rctx);
extern int sysctl_perf_event_max_stack;
extern int sysctl_perf_event_max_contexts_per_stack;
static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip)
{
if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) {
struct perf_callchain_entry *entry = ctx->entry;
entry->ip[entry->nr++] = ip;
++ctx->contexts;
return 0;
} else {
ctx->contexts_maxed = true;
return -1; /* no more room, stop walking the stack */
}
}
static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip)
{
if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) {
struct perf_callchain_entry *entry = ctx->entry;
entry->ip[entry->nr++] = ip;
++ctx->nr;
return 0;
} else {
return -1; /* no more room, stop walking the stack */
}
}
extern int sysctl_perf_event_paranoid;
extern int sysctl_perf_event_mlock;
extern int sysctl_perf_event_sample_rate;
extern int sysctl_perf_cpu_time_max_percent;
extern void perf_sample_event_took(u64 sample_len_ns);
int perf_proc_update_handler(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos);
int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos);
int perf_event_max_stack_handler(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos);
/* Access to perf_event_open(2) syscall. */
#define PERF_SECURITY_OPEN 0
/* Finer grained perf_event_open(2) access control. */
#define PERF_SECURITY_CPU 1
#define PERF_SECURITY_KERNEL 2
#define PERF_SECURITY_TRACEPOINT 3
static inline int perf_is_paranoid(void)
{
return sysctl_perf_event_paranoid > -1;
}
static inline int perf_allow_kernel(struct perf_event_attr *attr)
{
if (sysctl_perf_event_paranoid > 1 && !perfmon_capable())
return -EACCES;
return security_perf_event_open(attr, PERF_SECURITY_KERNEL);
}
static inline int perf_allow_cpu(struct perf_event_attr *attr)
{
if (sysctl_perf_event_paranoid > 0 && !perfmon_capable())
return -EACCES;
return security_perf_event_open(attr, PERF_SECURITY_CPU);
}
static inline int perf_allow_tracepoint(struct perf_event_attr *attr)
{
if (sysctl_perf_event_paranoid > -1 && !perfmon_capable())
return -EPERM;
return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT);
}
extern void perf_event_init(void);
extern void perf_tp_event(u16 event_type, u64 count, void *record,
int entry_size, struct pt_regs *regs,
struct hlist_head *head, int rctx,
struct task_struct *task);
extern void perf_bp_event(struct perf_event *event, void *data);
#ifndef perf_misc_flags
# define perf_misc_flags(regs) \
(user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL)
# define perf_instruction_pointer(regs) instruction_pointer(regs)
#endif
#ifndef perf_arch_bpf_user_pt_regs
# define perf_arch_bpf_user_pt_regs(regs) regs
#endif
static inline bool has_branch_stack(struct perf_event *event)
{
return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
}
static inline bool needs_branch_stack(struct perf_event *event)
{
return event->attr.branch_sample_type != 0;
}
static inline bool has_aux(struct perf_event *event)
{
return event->pmu->setup_aux;
}
static inline bool is_write_backward(struct perf_event *event)
{
return !!event->attr.write_backward;
}
static inline bool has_addr_filter(struct perf_event *event)
{
return event->pmu->nr_addr_filters;
}
/*
* An inherited event uses parent's filters
*/
static inline struct perf_addr_filters_head *
perf_event_addr_filters(struct perf_event *event)
{
struct perf_addr_filters_head *ifh = &event->addr_filters;
if (event->parent)
ifh = &event->parent->addr_filters;
return ifh;
}
extern void perf_event_addr_filters_sync(struct perf_event *event);
extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id);
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_sample_data *data,
struct perf_event *event, unsigned int size);
extern int perf_output_begin_forward(struct perf_output_handle *handle,
struct perf_sample_data *data,
struct perf_event *event,
unsigned int size);
extern int perf_output_begin_backward(struct perf_output_handle *handle,
struct perf_sample_data *data,
struct perf_event *event,
unsigned int size);
extern void perf_output_end(struct perf_output_handle *handle);
extern unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len);
extern unsigned int perf_output_skip(struct perf_output_handle *handle,
unsigned int len);
extern long perf_output_copy_aux(struct perf_output_handle *aux_handle,
struct perf_output_handle *handle,
unsigned long from, unsigned long to);
extern int perf_swevent_get_recursion_context(void);
extern void perf_swevent_put_recursion_context(int rctx);
extern u64 perf_swevent_set_period(struct perf_event *event);
extern void perf_event_enable(struct perf_event *event);
extern void perf_event_disable(struct perf_event *event);
extern void perf_event_disable_local(struct perf_event *event);
extern void perf_event_disable_inatomic(struct perf_event *event);
extern void perf_event_task_tick(void);
extern int perf_event_account_interrupt(struct perf_event *event);
extern int perf_event_period(struct perf_event *event, u64 value);
extern u64 perf_event_pause(struct perf_event *event, bool reset);
#else /* !CONFIG_PERF_EVENTS: */
static inline void *
perf_aux_output_begin(struct perf_output_handle *handle,
struct perf_event *event) { return NULL; }
static inline void
perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
{ }
static inline int
perf_aux_output_skip(struct perf_output_handle *handle,
unsigned long size) { return -EINVAL; }
static inline void *
perf_get_aux(struct perf_output_handle *handle) { return NULL; }
static inline void
perf_event_task_migrate(struct task_struct *task) { }
static inline void
perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task) { }
static inline void
perf_event_task_sched_out(struct task_struct *prev,
struct task_struct *next) { }
static inline int perf_event_init_task(struct task_struct *child,
u64 clone_flags) { return 0; }
static inline void perf_event_exit_task(struct task_struct *child) { }
static inline void perf_event_free_task(struct task_struct *task) { }
static inline void perf_event_delayed_put(struct task_struct *task) { }
static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); }
static inline const struct perf_event *perf_get_event(struct file *file)
{
return ERR_PTR(-EINVAL);
}
static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
{
return ERR_PTR(-EINVAL);
}
static inline int perf_event_read_local(struct perf_event *event, u64 *value,
u64 *enabled, u64 *running)
{
return -EINVAL;
}
static inline void perf_event_print_debug(void) { }
static inline int perf_event_task_disable(void) { return -EINVAL; }
static inline int perf_event_task_enable(void) { return -EINVAL; }
static inline int perf_event_refresh(struct perf_event *event, int refresh)
{
return -EINVAL;
}
static inline void
perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { }
static inline void
perf_bp_event(struct perf_event *event, void *data) { }
static inline void perf_event_mmap(struct vm_area_struct *vma) { }
typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data);
static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,
bool unregister, const char *sym) { }
static inline void perf_event_bpf_event(struct bpf_prog *prog,
enum perf_bpf_event_type type,
u16 flags) { }
static inline void perf_event_exec(void) { }
static inline void perf_event_comm(struct task_struct *tsk, bool exec) { }
static inline void perf_event_namespaces(struct task_struct *tsk) { }
static inline void perf_event_fork(struct task_struct *tsk) { }
static inline void perf_event_text_poke(const void *addr,
const void *old_bytes,
size_t old_len,
const void *new_bytes,
size_t new_len) { }
static inline void perf_event_init(void) { }
static inline int perf_swevent_get_recursion_context(void) { return -1; }
static inline void perf_swevent_put_recursion_context(int rctx) { }
static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; }
static inline void perf_event_enable(struct perf_event *event) { }
static inline void perf_event_disable(struct perf_event *event) { }
static inline int __perf_event_disable(void *info) { return -1; }
static inline void perf_event_task_tick(void) { }
static inline int perf_event_release_kernel(struct perf_event *event) { return 0; }
static inline int perf_event_period(struct perf_event *event, u64 value)
{
return -EINVAL;
}
static inline u64 perf_event_pause(struct perf_event *event, bool reset)
{
return 0;
}
#endif
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
extern void perf_restore_debug_store(void);
#else
static inline void perf_restore_debug_store(void) { }
#endif
#define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x))
struct perf_pmu_events_attr {
struct device_attribute attr;
u64 id;
const char *event_str;
};
struct perf_pmu_events_ht_attr {
struct device_attribute attr;
u64 id;
const char *event_str_ht;
const char *event_str_noht;
};
struct perf_pmu_events_hybrid_attr {
struct device_attribute attr;
u64 id;
const char *event_str;
u64 pmu_type;
};
struct perf_pmu_format_hybrid_attr {
struct device_attribute attr;
u64 pmu_type;
};
ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
#define PMU_EVENT_ATTR(_name, _var, _id, _show) \
static struct perf_pmu_events_attr _var = { \
.attr = __ATTR(_name, 0444, _show, NULL), \
.id = _id, \
};
#define PMU_EVENT_ATTR_STRING(_name, _var, _str) \
static struct perf_pmu_events_attr _var = { \
.attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \
.id = 0, \
.event_str = _str, \
};
#define PMU_EVENT_ATTR_ID(_name, _show, _id) \
(&((struct perf_pmu_events_attr[]) { \
{ .attr = __ATTR(_name, 0444, _show, NULL), \
.id = _id, } \
})[0].attr.attr)
#define PMU_FORMAT_ATTR_SHOW(_name, _format) \
static ssize_t \
_name##_show(struct device *dev, \
struct device_attribute *attr, \
char *page) \
{ \
BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
return sprintf(page, _format "\n"); \
} \
#define PMU_FORMAT_ATTR(_name, _format) \
PMU_FORMAT_ATTR_SHOW(_name, _format) \
\
static struct device_attribute format_attr_##_name = __ATTR_RO(_name)
/* Performance counter hotplug functions */
#ifdef CONFIG_PERF_EVENTS
int perf_event_init_cpu(unsigned int cpu);
int perf_event_exit_cpu(unsigned int cpu);
#else
#define perf_event_init_cpu NULL
#define perf_event_exit_cpu NULL
#endif
extern void __weak arch_perf_update_userpage(struct perf_event *event,
struct perf_event_mmap_page *userpg,
u64 now);
#ifdef CONFIG_MMU
extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr);
#endif
/*
* Snapshot branch stack on software events.
*
* Branch stack can be very useful in understanding software events. For
* example, when a long function, e.g. sys_perf_event_open, returns an
* errno, it is not obvious why the function failed. Branch stack could
* provide very helpful information in this type of scenarios.
*
* On software event, it is necessary to stop the hardware branch recorder
* fast. Otherwise, the hardware register/buffer will be flushed with
* entries of the triggering event. Therefore, static call is used to
* stop the hardware recorder.
*/
/*
* cnt is the number of entries allocated for entries.
* Return number of entries copied to .
*/
typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries,
unsigned int cnt);
DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t);
#ifndef PERF_NEEDS_LOPWR_CB
static inline void perf_lopwr_cb(bool mode)
{
}
#endif
#endif /* _LINUX_PERF_EVENT_H */
|