summaryrefslogtreecommitdiffstats
path: root/include/linux/perf_event.h
blob: 40150f345982cd4fd40e8b80470505e569f05b03 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
/*
 * Performance events:
 *
 *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
 *    Copyright (C) 2008-2009, Red Hat, Inc., Ingo Molnar
 *    Copyright (C) 2008-2009, 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 <linux/types.h>
#include <linux/ioctl.h>
#include <asm/byteorder.h>

/*
 * User-space ABI bits:
 */

/*
 * attr.type
 */
enum perf_type_id {
	PERF_TYPE_HARDWARE			= 0,
	PERF_TYPE_SOFTWARE			= 1,
	PERF_TYPE_TRACEPOINT			= 2,
	PERF_TYPE_HW_CACHE			= 3,
	PERF_TYPE_RAW				= 4,
	PERF_TYPE_BREAKPOINT			= 5,

	PERF_TYPE_MAX,				/* non-ABI */
};

/*
 * Generalized performance event event_id types, used by the
 * attr.event_id parameter of the sys_perf_event_open()
 * syscall:
 */
enum perf_hw_id {
	/*
	 * Common hardware events, generalized by the kernel:
	 */
	PERF_COUNT_HW_CPU_CYCLES		= 0,
	PERF_COUNT_HW_INSTRUCTIONS		= 1,
	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
	PERF_COUNT_HW_CACHE_MISSES		= 3,
	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
	PERF_COUNT_HW_BRANCH_MISSES		= 5,
	PERF_COUNT_HW_BUS_CYCLES		= 6,

	PERF_COUNT_HW_MAX,			/* non-ABI */
};

/*
 * Generalized hardware cache events:
 *
 *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU } x
 *       { read, write, prefetch } x
 *       { accesses, misses }
 */
enum perf_hw_cache_id {
	PERF_COUNT_HW_CACHE_L1D			= 0,
	PERF_COUNT_HW_CACHE_L1I			= 1,
	PERF_COUNT_HW_CACHE_LL			= 2,
	PERF_COUNT_HW_CACHE_DTLB		= 3,
	PERF_COUNT_HW_CACHE_ITLB		= 4,
	PERF_COUNT_HW_CACHE_BPU			= 5,

	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
};

enum perf_hw_cache_op_id {
	PERF_COUNT_HW_CACHE_OP_READ		= 0,
	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,

	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
};

enum perf_hw_cache_op_result_id {
	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,

	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
};

/*
 * Special "software" events provided by the kernel, even if the hardware
 * does not support performance events. These events measure various
 * physical and sw events of the kernel (and allow the profiling of them as
 * well):
 */
enum perf_sw_ids {
	PERF_COUNT_SW_CPU_CLOCK			= 0,
	PERF_COUNT_SW_TASK_CLOCK		= 1,
	PERF_COUNT_SW_PAGE_FAULTS		= 2,
	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
	PERF_COUNT_SW_EMULATION_FAULTS		= 8,

	PERF_COUNT_SW_MAX,			/* non-ABI */
};

/*
 * Bits that can be set in attr.sample_type to request information
 * in the overflow packets.
 */
enum perf_event_sample_format {
	PERF_SAMPLE_IP				= 1U << 0,
	PERF_SAMPLE_TID				= 1U << 1,
	PERF_SAMPLE_TIME			= 1U << 2,
	PERF_SAMPLE_ADDR			= 1U << 3,
	PERF_SAMPLE_READ			= 1U << 4,
	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
	PERF_SAMPLE_ID				= 1U << 6,
	PERF_SAMPLE_CPU				= 1U << 7,
	PERF_SAMPLE_PERIOD			= 1U << 8,
	PERF_SAMPLE_STREAM_ID			= 1U << 9,
	PERF_SAMPLE_RAW				= 1U << 10,

	PERF_SAMPLE_MAX = 1U << 11,		/* non-ABI */
};

/*
 * The format of the data returned by read() on a perf event fd,
 * as specified by attr.read_format:
 *
 * struct read_format {
 *	{ u64		value;
 *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
 *	  { u64		time_running; } && PERF_FORMAT_RUNNING
 *	  { u64		id;           } && PERF_FORMAT_ID
 *	} && !PERF_FORMAT_GROUP
 *
 *	{ u64		nr;
 *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
 *	  { u64		time_running; } && PERF_FORMAT_RUNNING
 *	  { u64		value;
 *	    { u64	id;           } && PERF_FORMAT_ID
 *	  }		cntr[nr];
 *	} && PERF_FORMAT_GROUP
 * };
 */
enum perf_event_read_format {
	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
	PERF_FORMAT_ID				= 1U << 2,
	PERF_FORMAT_GROUP			= 1U << 3,

	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
};

#define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */

/*
 * Hardware event_id to monitor via a performance monitoring event:
 */
struct perf_event_attr {

	/*
	 * Major type: hardware/software/tracepoint/etc.
	 */
	__u32			type;

	/*
	 * Size of the attr structure, for fwd/bwd compat.
	 */
	__u32			size;

	/*
	 * Type specific configuration information.
	 */
	__u64			config;

	union {
		__u64		sample_period;
		__u64		sample_freq;
	};

	__u64			sample_type;
	__u64			read_format;

	__u64			disabled       :  1, /* off by default        */
				inherit	       :  1, /* children inherit it   */
				pinned	       :  1, /* must always be on PMU */
				exclusive      :  1, /* only group on PMU     */
				exclude_user   :  1, /* don't count user      */
				exclude_kernel :  1, /* ditto kernel          */
				exclude_hv     :  1, /* ditto hypervisor      */
				exclude_idle   :  1, /* don't count when idle */
				mmap           :  1, /* include mmap data     */
				comm	       :  1, /* include comm data     */
				freq           :  1, /* use freq, not period  */
				inherit_stat   :  1, /* per task counts       */
				enable_on_exec :  1, /* next exec enables     */
				task           :  1, /* trace fork/exit       */
				watermark      :  1, /* wakeup_watermark      */
				/*
				 * precise_ip:
				 *
				 *  0 - SAMPLE_IP can have arbitrary skid
				 *  1 - SAMPLE_IP must have constant skid
				 *  2 - SAMPLE_IP requested to have 0 skid
				 *  3 - SAMPLE_IP must have 0 skid
				 *
				 *  See also PERF_RECORD_MISC_EXACT_IP
				 */
				precise_ip     :  2, /* skid constraint       */
				mmap_data      :  1, /* non-exec mmap data    */

				__reserved_1   : 46;

	union {
		__u32		wakeup_events;	  /* wakeup every n events */
		__u32		wakeup_watermark; /* bytes before wakeup   */
	};

	__u32			bp_type;
	__u64			bp_addr;
	__u64			bp_len;
};

/*
 * Ioctls that can be done on a perf event fd:
 */
#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)

enum perf_event_ioc_flags {
	PERF_IOC_FLAG_GROUP		= 1U << 0,
};

/*
 * Structure of the page that can be mapped via mmap
 */
struct perf_event_mmap_page {
	__u32	version;		/* version number of this structure */
	__u32	compat_version;		/* lowest version this is compat with */

	/*
	 * Bits needed to read the hw events in user-space.
	 *
	 *   u32 seq;
	 *   s64 count;
	 *
	 *   do {
	 *     seq = pc->lock;
	 *
	 *     barrier()
	 *     if (pc->index) {
	 *       count = pmc_read(pc->index - 1);
	 *       count += pc->offset;
	 *     } else
	 *       goto regular_read;
	 *
	 *     barrier();
	 *   } while (pc->lock != seq);
	 *
	 * NOTE: for obvious reason this only works on self-monitoring
	 *       processes.
	 */
	__u32	lock;			/* seqlock for synchronization */
	__u32	index;			/* hardware event identifier */
	__s64	offset;			/* add to hardware event value */
	__u64	time_enabled;		/* time event active */
	__u64	time_running;		/* time event on cpu */

		/*
		 * Hole for extension of the self monitor capabilities
		 */

	__u64	__reserved[123];	/* align to 1k */

	/*
	 * Control data for the mmap() data buffer.
	 *
	 * User-space reading the @data_head value should issue an rmb(), on
	 * SMP capable platforms, after reading this value -- see
	 * perf_event_wakeup().
	 *
	 * When the mapping is PROT_WRITE the @data_tail value should be
	 * written by userspace to reflect the last read data. In this case
	 * the kernel will not over-write unread data.
	 */
	__u64   data_head;		/* head in the data section */
	__u64	data_tail;		/* user-space written tail */
};

#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
#define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
#define PERF_RECORD_MISC_KERNEL			(1 << 0)
#define PERF_RECORD_MISC_USER			(2 << 0)
#define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)

/*
 * Indicates that the content of PERF_SAMPLE_IP points to
 * the actual instruction that triggered the event. See also
 * perf_event_attr::precise_ip.
 */
#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
/*
 * Reserve the last bit to indicate some extended misc field
 */
#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)

struct perf_event_header {
	__u32	type;
	__u16	misc;
	__u16	size;
};

enum perf_event_type {

	/*
	 * The MMAP events record the PROT_EXEC mappings so that we can
	 * correlate userspace IPs to code. They have the following structure:
	 *
	 * struct {
	 *	struct perf_event_header	header;
	 *
	 *	u32				pid, tid;
	 *	u64				addr;
	 *	u64				len;
	 *	u64				pgoff;
	 *	char				filename[];
	 * };
	 */
	PERF_RECORD_MMAP			= 1,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *	u64				id;
	 *	u64				lost;
	 * };
	 */
	PERF_RECORD_LOST			= 2,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *
	 *	u32				pid, tid;
	 *	char				comm[];
	 * };
	 */
	PERF_RECORD_COMM			= 3,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *	u32				pid, ppid;
	 *	u32				tid, ptid;
	 *	u64				time;
	 * };
	 */
	PERF_RECORD_EXIT			= 4,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *	u64				time;
	 *	u64				id;
	 *	u64				stream_id;
	 * };
	 */
	PERF_RECORD_THROTTLE			= 5,
	PERF_RECORD_UNTHROTTLE			= 6,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *	u32				pid, ppid;
	 *	u32				tid, ptid;
	 *	u64				time;
	 * };
	 */
	PERF_RECORD_FORK			= 7,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *	u32				pid, tid;
	 *
	 *	struct read_format		values;
	 * };
	 */
	PERF_RECORD_READ			= 8,

	/*
	 * struct {
	 *	struct perf_event_header	header;
	 *
	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
	 *	{ u64			time;     } && PERF_SAMPLE_TIME
	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
	 *	{ u64			id;	  } && PERF_SAMPLE_ID
	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
	 *	{ u64			period;   } && PERF_SAMPLE_PERIOD
	 *
	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
	 *
	 *	{ u64			nr,
	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
	 *
	 *	#
	 *	# The RAW record below is opaque data wrt the ABI
	 *	#
	 *	# That is, the ABI doesn't make any promises wrt to
	 *	# the stability of its content, it may vary depending
	 *	# on event, hardware, kernel version and phase of
	 *	# the moon.
	 *	#
	 *	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
	 *	#
	 *
	 *	{ u32			size;
	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
	 * };
	 */
	PERF_RECORD_SAMPLE			= 9,

	PERF_RECORD_MAX,			/* non-ABI */
};

enum perf_callchain_context {
	PERF_CONTEXT_HV			= (__u64)-32,
	PERF_CONTEXT_KERNEL		= (__u64)-128,
	PERF_CONTEXT_USER		= (__u64)-512,

	PERF_CONTEXT_GUEST		= (__u64)-2048,
	PERF_CONTEXT_GUEST_KERNEL	= (__u64)-2176,
	PERF_CONTEXT_GUEST_USER		= (__u64)-2560,

	PERF_CONTEXT_MAX		= (__u64)-4095,
};

#define PERF_FLAG_FD_NO_GROUP	(1U << 0)
#define PERF_FLAG_FD_OUTPUT	(1U << 1)

#ifdef __KERNEL__
/*
 * Kernel-internal data types and definitions:
 */

#ifdef CONFIG_PERF_EVENTS
# include <asm/perf_event.h>
# include <asm/local64.h>
#endif

struct perf_guest_info_callbacks {
	int (*is_in_guest) (void);
	int (*is_user_mode) (void);
	unsigned long (*get_guest_ip) (void);
};

#ifdef CONFIG_HAVE_HW_BREAKPOINT
#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/jump_label_ref.h>
#include <asm/atomic.h>
#include <asm/local.h>

#define PERF_MAX_STACK_DEPTH		255

struct perf_callchain_entry {
	__u64				nr;
	__u64				ip[PERF_MAX_STACK_DEPTH];
};

struct perf_raw_record {
	u32				size;
	void				*data;
};

struct perf_branch_entry {
	__u64				from;
	__u64				to;
	__u64				flags;
};

struct perf_branch_stack {
	__u64				nr;
	struct perf_branch_entry	entries[0];
};

struct task_struct;

/**
 * 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		idx;
			int		last_cpu;
		};
		struct { /* software */
			struct hrtimer	hrtimer;
		};
#ifdef CONFIG_HAVE_HW_BREAKPOINT
		struct { /* breakpoint */
			struct arch_hw_breakpoint	info;
			struct list_head		bp_list;
			/*
			 * Crufty hack to avoid the chicken and egg
			 * problem hw_breakpoint has with context
			 * creation and event initalization.
			 */
			struct task_struct		*bp_target;
		};
#endif
	};
	int				state;
	local64_t			prev_count;
	u64				sample_period;
	u64				last_period;
	local64_t			period_left;
	u64				interrupts;

	u64				freq_time_stamp;
	u64				freq_count_stamp;
#endif
};

/*
 * hw_perf_event::state flags
 */
#define PERF_HES_STOPPED	0x01 /* the counter is stopped */
#define PERF_HES_UPTODATE	0x02 /* event->count up-to-date */
#define PERF_HES_ARCH		0x04

struct perf_event;

/*
 * Common implementation detail of pmu::{start,commit,cancel}_txn
 */
#define PERF_EVENT_TXN 0x1

/**
 * struct pmu - generic performance monitoring unit
 */
struct pmu {
	struct list_head		entry;

	int * __percpu			pmu_disable_count;
	struct perf_cpu_context * __percpu pmu_cpu_context;
	int				task_ctx_nr;

	/*
	 * 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.
	 * Should return -ENOENT when the @event doesn't match this PMU.
	 */
	int (*event_init)		(struct perf_event *event);

#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.
	 */
	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.
	 */
	void (*start)			(struct perf_event *event, int flags);
	void (*stop)			(struct perf_event *event, int flags);

	/*
	 * Updates the counter value of the event.
	 */
	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.
	 */
	void (*start_txn)	(struct pmu *pmu); /* optional */
	/*
	 * 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.
	 */
	int  (*commit_txn)	(struct pmu *pmu); /* optional */
	/*
	 * Will cancel the transaction, assumes ->del() is called
	 * for each successfull ->add() during the transaction.
	 */
	void (*cancel_txn)	(struct pmu *pmu); /* optional */
};

/**
 * enum perf_event_active_state - the states of a event
 */
enum perf_event_active_state {
	PERF_EVENT_STATE_ERROR		= -2,
	PERF_EVENT_STATE_OFF		= -1,
	PERF_EVENT_STATE_INACTIVE	=  0,
	PERF_EVENT_STATE_ACTIVE		=  1,
};

struct file;

#define PERF_BUFFER_WRITABLE		0x01

struct perf_buffer {
	atomic_t			refcount;
	struct rcu_head			rcu_head;
#ifdef CONFIG_PERF_USE_VMALLOC
	struct work_struct		work;
	int				page_order;	/* allocation order  */
#endif
	int				nr_pages;	/* nr of data pages  */
	int				writable;	/* are we writable   */

	atomic_t			poll;		/* POLL_ for wakeups */

	local_t				head;		/* write position    */
	local_t				nest;		/* nested writers    */
	local_t				events;		/* event limit       */
	local_t				wakeup;		/* wakeup stamp      */
	local_t				lost;		/* nr records lost   */

	long				watermark;	/* wakeup watermark  */

	struct perf_event_mmap_page	*user_page;
	void				*data_pages[0];
};

struct perf_sample_data;

typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
					struct perf_sample_data *,
					struct pt_regs *regs);

enum perf_group_flag {
	PERF_GROUP_SOFTWARE = 0x1,
};

#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

/**
 * struct perf_event - performance event kernel representation:
 */
struct perf_event {
#ifdef CONFIG_PERF_EVENTS
	struct list_head		group_entry;
	struct list_head		event_entry;
	struct list_head		sibling_list;
	struct hlist_node		hlist_entry;
	int				nr_siblings;
	int				group_flags;
	struct perf_event		*group_leader;
	struct pmu			*pmu;

	enum perf_event_active_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.
	 *
	 * They are computed from tstamp_enabled, tstamp_running and
	 * tstamp_stopped when the event is in INACTIVE or ACTIVE state.
	 */
	u64				total_time_enabled;
	u64				total_time_running;

	/*
	 * These are timestamps used for computing total_time_enabled
	 * and total_time_running when the event is in INACTIVE or
	 * ACTIVE state, measured in nanoseconds from an arbitrary point
	 * in time.
	 * tstamp_enabled: the notional time when the event was enabled
	 * tstamp_running: the notional time when the event was scheduled on
	 * tstamp_stopped: in INACTIVE state, the notional time when the
	 *	event was scheduled off.
	 */
	u64				tstamp_enabled;
	u64				tstamp_running;
	u64				tstamp_stopped;

	/*
	 * timestamp shadows the actual context timing but it can
	 * be safely used in NMI interrupt context. It reflects the
	 * context time as it was when the event was last scheduled in.
	 *
	 * ctx_time already accounts for ctx->timestamp. Therefore to
	 * compute ctx_time for a sample, simply add perf_clock().
	 */
	u64				shadow_ctx_time;

	struct perf_event_attr		attr;
	struct hw_perf_event		hw;

	struct perf_event_context	*ctx;
	struct file			*filp;

	/*
	 * 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;
	int				mmap_locked;
	struct user_struct		*mmap_user;
	struct perf_buffer		*buffer;

	/* poll related */
	wait_queue_head_t		waitq;
	struct fasync_struct		*fasync;

	/* delayed work for NMIs and such */
	int				pending_wakeup;
	int				pending_kill;
	int				pending_disable;
	struct irq_work			pending;

	atomic_t			event_limit;

	void (*destroy)(struct perf_event *);
	struct rcu_head			rcu_head;

	struct pid_namespace		*ns;
	u64				id;

	perf_overflow_handler_t		overflow_handler;

#ifdef CONFIG_EVENT_TRACING
	struct ftrace_event_call	*tp_event;
	struct event_filter		*filter;
#endif

#endif /* CONFIG_PERF_EVENTS */
};

enum perf_event_context_type {
	task_context,
	cpu_context,
};

/**
 * struct perf_event_context - event context structure
 *
 * Used as a container for task events and CPU events as well:
 */
struct perf_event_context {
	enum perf_event_context_type	type;
	struct pmu			*pmu;
	/*
	 * 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		pinned_groups;
	struct list_head		flexible_groups;
	struct list_head		event_list;
	int				nr_events;
	int				nr_active;
	int				is_active;
	int				nr_stat;
	atomic_t			refcount;
	struct task_struct		*task;

	/*
	 * Context clock, runs when context enabled.
	 */
	u64				time;
	u64				timestamp;

	/*
	 * 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;
	struct rcu_head			rcu_head;
};

/*
 * Number of contexts where an event can trigger:
 * 	task, softirq, hardirq, nmi.
 */
#define PERF_NR_CONTEXTS	4

/**
 * 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				active_oncpu;
	int				exclusive;
	struct list_head		rotation_list;
	int				jiffies_interval;
};

struct perf_output_handle {
	struct perf_event		*event;
	struct perf_buffer		*buffer;
	unsigned long			wakeup;
	unsigned long			size;
	void				*addr;
	int				page;
	int				nmi;
	int				sample;
};

#ifdef CONFIG_PERF_EVENTS

extern int perf_pmu_register(struct pmu *pmu);
extern void perf_pmu_unregister(struct pmu *pmu);

extern int perf_num_counters(void);
extern const char *perf_pmu_name(void);
extern void __perf_event_task_sched_in(struct task_struct *task);
extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);

extern atomic_t perf_task_events;

static inline void perf_event_task_sched_in(struct task_struct *task)
{
	COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
}

static inline
void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
{
	COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
}

extern int perf_event_init_task(struct task_struct *child);
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 void perf_event_print_debug(void);
extern void perf_pmu_disable(struct pmu *pmu);
extern void perf_pmu_enable(struct pmu *pmu);
extern int perf_event_task_disable(void);
extern int perf_event_task_enable(void);
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);
extern u64 perf_event_read_value(struct perf_event *event,
				 u64 *enabled, u64 *running);

struct perf_sample_data {
	u64				type;

	u64				ip;
	struct {
		u32	pid;
		u32	tid;
	}				tid_entry;
	u64				time;
	u64				addr;
	u64				id;
	u64				stream_id;
	struct {
		u32	cpu;
		u32	reserved;
	}				cpu_entry;
	u64				period;
	struct perf_callchain_entry	*callchain;
	struct perf_raw_record		*raw;
};

static inline
void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
{
	data->addr = addr;
	data->raw  = NULL;
}

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_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, int nmi,
				 struct perf_sample_data *data,
				 struct pt_regs *regs);

/*
 * Return 1 for a software event, 0 for a hardware event
 */
static inline int is_software_event(struct perf_event *event)
{
	return event->pmu->task_ctx_nr == perf_sw_context;
}

extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];

extern void __perf_sw_event(u32, u64, int, 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

/*
 * Take a snapshot of the regs. Skip ip and frame pointer to
 * the nth caller. We only need a few of the regs:
 * - ip for PERF_SAMPLE_IP
 * - cs for user_mode() tests
 * - bp for callchains
 * - eflags, for future purposes, just in case
 */
static inline void perf_fetch_caller_regs(struct pt_regs *regs)
{
	memset(regs, 0, sizeof(*regs));

	perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
}

static __always_inline void
perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
{
	struct pt_regs hot_regs;

	JUMP_LABEL(&perf_swevent_enabled[event_id], have_event);
	return;

have_event:
	if (!regs) {
		perf_fetch_caller_regs(&hot_regs);
		regs = &hot_regs;
	}
	__perf_sw_event(event_id, nr, nmi, regs, addr);
}

extern void perf_event_mmap(struct vm_area_struct *vma);
extern struct perf_guest_info_callbacks *perf_guest_cbs;
extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);

extern void perf_event_comm(struct task_struct *tsk);
extern void perf_event_fork(struct task_struct *tsk);

/* Callchains */
DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);

extern void perf_callchain_user(struct perf_callchain_entry *entry,
				struct pt_regs *regs);
extern void perf_callchain_kernel(struct perf_callchain_entry *entry,
				  struct pt_regs *regs);


static inline void
perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
{
	if (entry->nr < PERF_MAX_STACK_DEPTH)
		entry->ip[entry->nr++] = ip;
}

extern int sysctl_perf_event_paranoid;
extern int sysctl_perf_event_mlock;
extern int sysctl_perf_event_sample_rate;

static inline bool perf_paranoid_tracepoint_raw(void)
{
	return sysctl_perf_event_paranoid > -1;
}

static inline bool perf_paranoid_cpu(void)
{
	return sysctl_perf_event_paranoid > 0;
}

static inline bool perf_paranoid_kernel(void)
{
	return sysctl_perf_event_paranoid > 1;
}

extern void perf_event_init(void);
extern void perf_tp_event(u64 addr, u64 count, void *record,
			  int entry_size, struct pt_regs *regs,
			  struct hlist_head *head, int rctx);
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

extern int perf_output_begin(struct perf_output_handle *handle,
			     struct perf_event *event, unsigned int size,
			     int nmi, int sample);
extern void perf_output_end(struct perf_output_handle *handle);
extern void perf_output_copy(struct perf_output_handle *handle,
			     const void *buf, unsigned int len);
extern int perf_swevent_get_recursion_context(void);
extern void perf_swevent_put_recursion_context(int rctx);
extern void perf_event_enable(struct perf_event *event);
extern void perf_event_disable(struct perf_event *event);
extern void perf_event_task_tick(void);
#else
static inline void
perf_event_task_sched_in(struct task_struct *task)			{ }
static inline void
perf_event_task_sched_out(struct task_struct *task,
			    struct task_struct *next)			{ }
static inline int perf_event_init_task(struct task_struct *child)	{ 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 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 void
perf_sw_event(u32 event_id, u64 nr, int nmi,
		     struct pt_regs *regs, u64 addr)			{ }
static inline void
perf_bp_event(struct perf_event *event, void *data)			{ }

static inline int perf_register_guest_info_callbacks
(struct perf_guest_info_callbacks *callbacks) { return 0; }
static inline int perf_unregister_guest_info_callbacks
(struct perf_guest_info_callbacks *callbacks) { return 0; }

static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
static inline void perf_event_comm(struct task_struct *tsk)		{ }
static inline void perf_event_fork(struct task_struct *tsk)		{ }
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 void perf_event_enable(struct perf_event *event)		{ }
static inline void perf_event_disable(struct perf_event *event)		{ }
static inline void perf_event_task_tick(void)				{ }
#endif

#define perf_output_put(handle, x) \
	perf_output_copy((handle), &(x), sizeof(x))

/*
 * This has to have a higher priority than migration_notifier in sched.c.
 */
#define perf_cpu_notifier(fn)					\
do {								\
	static struct notifier_block fn##_nb __cpuinitdata =	\
		{ .notifier_call = fn, .priority = CPU_PRI_PERF }; \
	fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,		\
		(void *)(unsigned long)smp_processor_id());	\
	fn(&fn##_nb, (unsigned long)CPU_STARTING,		\
		(void *)(unsigned long)smp_processor_id());	\
	fn(&fn##_nb, (unsigned long)CPU_ONLINE,			\
		(void *)(unsigned long)smp_processor_id());	\
	register_cpu_notifier(&fn##_nb);			\
} while (0)

#endif /* __KERNEL__ */
#endif /* _LINUX_PERF_EVENT_H */
OpenPOWER on IntegriCloud