aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/perf_event.c
blob: 53ea4cf1a8784f23893ed5cab38c560d34ca634a (plain) (blame)
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
/*
 * Performance events x86 architecture code
 *
 *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
 *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
 *  Copyright (C) 2009 Jaswinder Singh Rajput
 *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
 *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
 *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
 *  Copyright (C) 2009 Google, Inc., Stephane Eranian
 *
 *  For licencing details see kernel-base/COPYING
 */

#include <linux/perf_event.h>
#include <linux/capability.h>
#include <linux/notifier.h>
#include <linux/hardirq.h>
#include <linux/kprobes.h>
#include <linux/module.h>
#include <linux/kdebug.h>
#include <linux/sched.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
#include <linux/cpu.h>
#include <linux/bitops.h>

#include <asm/apic.h>
#include <asm/stacktrace.h>
#include <asm/nmi.h>
#include <asm/compat.h>

static u64 perf_event_mask __read_mostly;

/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS	4

/* The size of a BTS record in bytes: */
#define BTS_RECORD_SIZE		24

/* The size of a per-cpu BTS buffer in bytes: */
#define BTS_BUFFER_SIZE		(BTS_RECORD_SIZE * 2048)

/* The BTS overflow threshold in bytes from the end of the buffer: */
#define BTS_OVFL_TH		(BTS_RECORD_SIZE * 128)


/*
 * Bits in the debugctlmsr controlling branch tracing.
 */
#define X86_DEBUGCTL_TR			(1 << 6)
#define X86_DEBUGCTL_BTS		(1 << 7)
#define X86_DEBUGCTL_BTINT		(1 << 8)
#define X86_DEBUGCTL_BTS_OFF_OS		(1 << 9)
#define X86_DEBUGCTL_BTS_OFF_USR	(1 << 10)

/*
 * A debug store configuration.
 *
 * We only support architectures that use 64bit fields.
 */
struct debug_store {
	u64	bts_buffer_base;
	u64	bts_index;
	u64	bts_absolute_maximum;
	u64	bts_interrupt_threshold;
	u64	pebs_buffer_base;
	u64	pebs_index;
	u64	pebs_absolute_maximum;
	u64	pebs_interrupt_threshold;
	u64	pebs_event_reset[MAX_PEBS_EVENTS];
};

struct event_constraint {
	union {
		unsigned long	idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
		u64		idxmsk64;
	};
	u64	code;
	u64	cmask;
	int	weight;
};

struct amd_nb {
	int nb_id;  /* NorthBridge id */
	int refcnt; /* reference count */
	struct perf_event *owners[X86_PMC_IDX_MAX];
	struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};

struct cpu_hw_events {
	struct perf_event	*events[X86_PMC_IDX_MAX]; /* in counter order */
	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
	unsigned long		interrupts;
	int			enabled;
	struct debug_store	*ds;

	int			n_events;
	int			n_added;
	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
	u64			tags[X86_PMC_IDX_MAX];
	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
	struct amd_nb		*amd_nb;
};

#define __EVENT_CONSTRAINT(c, n, m, w) {\
	{ .idxmsk64 = (n) },		\
	.code = (c),			\
	.cmask = (m),			\
	.weight = (w),			\
}

#define EVENT_CONSTRAINT(c, n, m)	\
	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n))

#define INTEL_EVENT_CONSTRAINT(c, n)	\
	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK)

#define FIXED_EVENT_CONSTRAINT(c, n)	\
	EVENT_CONSTRAINT(c, (1ULL << (32+n)), INTEL_ARCH_FIXED_MASK)

#define EVENT_CONSTRAINT_END		\
	EVENT_CONSTRAINT(0, 0, 0)

#define for_each_event_constraint(e, c)	\
	for ((e) = (c); (e)->cmask; (e)++)

/*
 * struct x86_pmu - generic x86 pmu
 */
struct x86_pmu {
	const char	*name;
	int		version;
	int		(*handle_irq)(struct pt_regs *);
	void		(*disable_all)(void);
	void		(*enable_all)(void);
	void		(*enable)(struct perf_event *);
	void		(*disable)(struct perf_event *);
	unsigned	eventsel;
	unsigned	perfctr;
	u64		(*event_map)(int);
	u64		(*raw_event)(u64);
	int		max_events;
	int		num_events;
	int		num_events_fixed;
	int		event_bits;
	u64		event_mask;
	int		apic;
	u64		max_period;
	u64		intel_ctrl;
	void		(*enable_bts)(u64 config);
	void		(*disable_bts)(void);

	struct event_constraint *
			(*get_event_constraints)(struct cpu_hw_events *cpuc,
						 struct perf_event *event);

	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
						 struct perf_event *event);
	struct event_constraint *event_constraints;

	int		(*cpu_prepare)(int cpu);
	void		(*cpu_starting)(int cpu);
	void		(*cpu_dying)(int cpu);
	void		(*cpu_dead)(int cpu);
};

static struct x86_pmu x86_pmu __read_mostly;

static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
	.enabled = 1,
};

static int x86_perf_event_set_period(struct perf_event *event);

/*
 * Generalized hw caching related hw_event table, filled
 * in on a per model basis. A value of 0 means
 * 'not supported', -1 means 'hw_event makes no sense on
 * this CPU', any other value means the raw hw_event
 * ID.
 */

#define C(x) PERF_COUNT_HW_CACHE_##x

static u64 __read_mostly hw_cache_event_ids
				[PERF_COUNT_HW_CACHE_MAX]
				[PERF_COUNT_HW_CACHE_OP_MAX]
				[PERF_COUNT_HW_CACHE_RESULT_MAX];

/*
 * Propagate event elapsed time into the generic event.
 * Can only be executed on the CPU where the event is active.
 * Returns the delta events processed.
 */
static u64
x86_perf_event_update(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	int shift = 64 - x86_pmu.event_bits;
	u64 prev_raw_count, new_raw_count;
	int idx = hwc->idx;
	s64 delta;

	if (idx == X86_PMC_IDX_FIXED_BTS)
		return 0;

	/*
	 * Careful: an NMI might modify the previous event value.
	 *
	 * Our tactic to handle this is to first atomically read and
	 * exchange a new raw count - then add that new-prev delta
	 * count to the generic event atomically:
	 */
again:
	prev_raw_count = atomic64_read(&hwc->prev_count);
	rdmsrl(hwc->event_base + idx, new_raw_count);

	if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
					new_raw_count) != prev_raw_count)
		goto again;

	/*
	 * Now we have the new raw value and have updated the prev
	 * timestamp already. We can now calculate the elapsed delta
	 * (event-)time and add that to the generic event.
	 *
	 * Careful, not all hw sign-extends above the physical width
	 * of the count.
	 */
	delta = (new_raw_count << shift) - (prev_raw_count << shift);
	delta >>= shift;

	atomic64_add(delta, &event->count);
	atomic64_sub(delta, &hwc->period_left);

	return new_raw_count;
}

static atomic_t active_events;
static DEFINE_MUTEX(pmc_reserve_mutex);

static bool reserve_pmc_hardware(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
	int i;

	if (nmi_watchdog == NMI_LOCAL_APIC)
		disable_lapic_nmi_watchdog();

	for (i = 0; i < x86_pmu.num_events; i++) {
		if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
			goto perfctr_fail;
	}

	for (i = 0; i < x86_pmu.num_events; i++) {
		if (!reserve_evntsel_nmi(x86_pmu.eventsel + i))
			goto eventsel_fail;
	}
#endif

	return true;

#ifdef CONFIG_X86_LOCAL_APIC
eventsel_fail:
	for (i--; i >= 0; i--)
		release_evntsel_nmi(x86_pmu.eventsel + i);

	i = x86_pmu.num_events;

perfctr_fail:
	for (i--; i >= 0; i--)
		release_perfctr_nmi(x86_pmu.perfctr + i);

	if (nmi_watchdog == NMI_LOCAL_APIC)
		enable_lapic_nmi_watchdog();

	return false;
#endif
}

static void release_pmc_hardware(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
	int i;

	for (i = 0; i < x86_pmu.num_events; i++) {
		release_perfctr_nmi(x86_pmu.perfctr + i);
		release_evntsel_nmi(x86_pmu.eventsel + i);
	}

	if (nmi_watchdog == NMI_LOCAL_APIC)
		enable_lapic_nmi_watchdog();
#endif
}

static inline bool bts_available(void)
{
	return x86_pmu.enable_bts != NULL;
}

static void init_debug_store_on_cpu(int cpu)
{
	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;

	if (!ds)
		return;

	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA,
		     (u32)((u64)(unsigned long)ds),
		     (u32)((u64)(unsigned long)ds >> 32));
}

static void fini_debug_store_on_cpu(int cpu)
{
	if (!per_cpu(cpu_hw_events, cpu).ds)
		return;

	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
}

static void release_bts_hardware(void)
{
	int cpu;

	if (!bts_available())
		return;

	get_online_cpus();

	for_each_online_cpu(cpu)
		fini_debug_store_on_cpu(cpu);

	for_each_possible_cpu(cpu) {
		struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;

		if (!ds)
			continue;

		per_cpu(cpu_hw_events, cpu).ds = NULL;

		kfree((void *)(unsigned long)ds->bts_buffer_base);
		kfree(ds);
	}

	put_online_cpus();
}

static int reserve_bts_hardware(void)
{
	int cpu, err = 0;

	if (!bts_available())
		return 0;

	get_online_cpus();

	for_each_possible_cpu(cpu) {
		struct debug_store *ds;
		void *buffer;

		err = -ENOMEM;
		buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
		if (unlikely(!buffer))
			break;

		ds = kzalloc(sizeof(*ds), GFP_KERNEL);
		if (unlikely(!ds)) {
			kfree(buffer);
			break;
		}

		ds->bts_buffer_base = (u64)(unsigned long)buffer;
		ds->bts_index = ds->bts_buffer_base;
		ds->bts_absolute_maximum =
			ds->bts_buffer_base + BTS_BUFFER_SIZE;
		ds->bts_interrupt_threshold =
			ds->bts_absolute_maximum - BTS_OVFL_TH;

		per_cpu(cpu_hw_events, cpu).ds = ds;
		err = 0;
	}

	if (err)
		release_bts_hardware();
	else {
		for_each_online_cpu(cpu)
			init_debug_store_on_cpu(cpu);
	}

	put_online_cpus();

	return err;
}

static void hw_perf_event_destroy(struct perf_event *event)
{
	if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) {
		release_pmc_hardware();
		release_bts_hardware();
		mutex_unlock(&pmc_reserve_mutex);
	}
}

static inline int x86_pmu_initialized(void)
{
	return x86_pmu.handle_irq != NULL;
}

static inline int
set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
{
	unsigned int cache_type, cache_op, cache_result;
	u64 config, val;

	config = attr->config;

	cache_type = (config >>  0) & 0xff;
	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
		return -EINVAL;

	cache_op = (config >>  8) & 0xff;
	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
		return -EINVAL;

	cache_result = (config >> 16) & 0xff;
	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
		return -EINVAL;

	val = hw_cache_event_ids[cache_type][cache_op][cache_result];

	if (val == 0)
		return -ENOENT;

	if (val == -1)
		return -EINVAL;

	hwc->config |= val;

	return 0;
}

/*
 * Setup the hardware configuration for a given attr_type
 */
static int __hw_perf_event_init(struct perf_event *event)
{
	struct perf_event_attr *attr = &event->attr;
	struct hw_perf_event *hwc = &event->hw;
	u64 config;
	int err;

	if (!x86_pmu_initialized())
		return -ENODEV;

	err = 0;
	if (!atomic_inc_not_zero(&active_events)) {
		mutex_lock(&pmc_reserve_mutex);
		if (atomic_read(&active_events) == 0) {
			if (!reserve_pmc_hardware())
				err = -EBUSY;
			else
				err = reserve_bts_hardware();
		}
		if (!err)
			atomic_inc(&active_events);
		mutex_unlock(&pmc_reserve_mutex);
	}
	if (err)
		return err;

	event->destroy = hw_perf_event_destroy;

	/*
	 * Generate PMC IRQs:
	 * (keep 'enabled' bit clear for now)
	 */
	hwc->config = ARCH_PERFMON_EVENTSEL_INT;

	hwc->idx = -1;
	hwc->last_cpu = -1;
	hwc->last_tag = ~0ULL;

	/*
	 * Count user and OS events unless requested not to.
	 */
	if (!attr->exclude_user)
		hwc->config |= ARCH_PERFMON_EVENTSEL_USR;
	if (!attr->exclude_kernel)
		hwc->config |= ARCH_PERFMON_EVENTSEL_OS;

	if (!hwc->sample_period) {
		hwc->sample_period = x86_pmu.max_period;
		hwc->last_period = hwc->sample_period;
		atomic64_set(&hwc->period_left, hwc->sample_period);
	} else {
		/*
		 * If we have a PMU initialized but no APIC
		 * interrupts, we cannot sample hardware
		 * events (user-space has to fall back and
		 * sample via a hrtimer based software event):
		 */
		if (!x86_pmu.apic)
			return -EOPNOTSUPP;
	}

	/*
	 * Raw hw_event type provide the config in the hw_event structure
	 */
	if (attr->type == PERF_TYPE_RAW) {
		hwc->config |= x86_pmu.raw_event(attr->config);
		if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) &&
		    perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
			return -EACCES;
		return 0;
	}

	if (attr->type == PERF_TYPE_HW_CACHE)
		return set_ext_hw_attr(hwc, attr);

	if (attr->config >= x86_pmu.max_events)
		return -EINVAL;

	/*
	 * The generic map:
	 */
	config = x86_pmu.event_map(attr->config);

	if (config == 0)
		return -ENOENT;

	if (config == -1LL)
		return -EINVAL;

	/*
	 * Branch tracing:
	 */
	if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
	    (hwc->sample_period == 1)) {
		/* BTS is not supported by this architecture. */
		if (!bts_available())
			return -EOPNOTSUPP;

		/* BTS is currently only allowed for user-mode. */
		if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
			return -EOPNOTSUPP;
	}

	hwc->config |= config;

	return 0;
}

static void x86_pmu_disable_all(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	int idx;

	for (idx = 0; idx < x86_pmu.num_events; idx++) {
		u64 val;

		if (!test_bit(idx, cpuc->active_mask))
			continue;
		rdmsrl(x86_pmu.eventsel + idx, val);
		if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
			continue;
		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
		wrmsrl(x86_pmu.eventsel + idx, val);
	}
}

void hw_perf_disable(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);

	if (!x86_pmu_initialized())
		return;

	if (!cpuc->enabled)
		return;

	cpuc->n_added = 0;
	cpuc->enabled = 0;
	barrier();

	x86_pmu.disable_all();
}

static void x86_pmu_enable_all(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	int idx;

	for (idx = 0; idx < x86_pmu.num_events; idx++) {
		struct perf_event *event = cpuc->events[idx];
		u64 val;

		if (!test_bit(idx, cpuc->active_mask))
			continue;

		val = event->hw.config;
		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
		wrmsrl(x86_pmu.eventsel + idx, val);
	}
}

static const struct pmu pmu;

static inline int is_x86_event(struct perf_event *event)
{
	return event->pmu == &pmu;
}

static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
{
	struct event_constraint *c, *constraints[X86_PMC_IDX_MAX];
	unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
	int i, j, w, wmax, num = 0;
	struct hw_perf_event *hwc;

	bitmap_zero(used_mask, X86_PMC_IDX_MAX);

	for (i = 0; i < n; i++) {
		c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
		constraints[i] = c;
	}

	/*
	 * fastpath, try to reuse previous register
	 */
	for (i = 0; i < n; i++) {
		hwc = &cpuc->event_list[i]->hw;
		c = constraints[i];

		/* never assigned */
		if (hwc->idx == -1)
			break;

		/* constraint still honored */
		if (!test_bit(hwc->idx, c->idxmsk))
			break;

		/* not already used */
		if (test_bit(hwc->idx, used_mask))
			break;

		__set_bit(hwc->idx, used_mask);
		if (assign)
			assign[i] = hwc->idx;
	}
	if (i == n)
		goto done;

	/*
	 * begin slow path
	 */

	bitmap_zero(used_mask, X86_PMC_IDX_MAX);

	/*
	 * weight = number of possible counters
	 *
	 * 1    = most constrained, only works on one counter
	 * wmax = least constrained, works on any counter
	 *
	 * assign events to counters starting with most
	 * constrained events.
	 */
	wmax = x86_pmu.num_events;

	/*
	 * when fixed event counters are present,
	 * wmax is incremented by 1 to account
	 * for one more choice
	 */
	if (x86_pmu.num_events_fixed)
		wmax++;

	for (w = 1, num = n; num && w <= wmax; w++) {
		/* for each event */
		for (i = 0; num && i < n; i++) {
			c = constraints[i];
			hwc = &cpuc->event_list[i]->hw;

			if (c->weight != w)
				continue;

			for_each_set_bit(j, c->idxmsk, X86_PMC_IDX_MAX) {
				if (!test_bit(j, used_mask))
					break;
			}

			if (j == X86_PMC_IDX_MAX)
				break;

			__set_bit(j, used_mask);

			if (assign)
				assign[i] = j;
			num--;
		}
	}
done:
	/*
	 * scheduling failed or is just a simulation,
	 * free resources if necessary
	 */
	if (!assign || num) {
		for (i = 0; i < n; i++) {
			if (x86_pmu.put_event_constraints)
				x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
		}
	}
	return num ? -ENOSPC : 0;
}

/*
 * dogrp: true if must collect siblings events (group)
 * returns total number of events and error code
 */
static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp)
{
	struct perf_event *event;
	int n, max_count;

	max_count = x86_pmu.num_events + x86_pmu.num_events_fixed;

	/* current number of events already accepted */
	n = cpuc->n_events;

	if (is_x86_event(leader)) {
		if (n >= max_count)
			return -ENOSPC;
		cpuc->event_list[n] = leader;
		n++;
	}
	if (!dogrp)
		return n;

	list_for_each_entry(event, &leader->sibling_list, group_entry) {
		if (!is_x86_event(event) ||
		    event->state <= PERF_EVENT_STATE_OFF)
			continue;

		if (n >= max_count)
			return -ENOSPC;

		cpuc->event_list[n] = event;
		n++;
	}
	return n;
}

static inline void x86_assign_hw_event(struct perf_event *event,
				struct cpu_hw_events *cpuc, int i)
{
	struct hw_perf_event *hwc = &event->hw;

	hwc->idx = cpuc->assign[i];
	hwc->last_cpu = smp_processor_id();
	hwc->last_tag = ++cpuc->tags[i];

	if (hwc->idx == X86_PMC_IDX_FIXED_BTS) {
		hwc->config_base = 0;
		hwc->event_base	= 0;
	} else if (hwc->idx >= X86_PMC_IDX_FIXED) {
		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
		/*
		 * We set it so that event_base + idx in wrmsr/rdmsr maps to
		 * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2:
		 */
		hwc->event_base =
			MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED;
	} else {
		hwc->config_base = x86_pmu.eventsel;
		hwc->event_base  = x86_pmu.perfctr;
	}
}

static inline int match_prev_assignment(struct hw_perf_event *hwc,
					struct cpu_hw_events *cpuc,
					int i)
{
	return hwc->idx == cpuc->assign[i] &&
		hwc->last_cpu == smp_processor_id() &&
		hwc->last_tag == cpuc->tags[i];
}

static int x86_pmu_start(struct perf_event *event);
static void x86_pmu_stop(struct perf_event *event);

void hw_perf_enable(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct perf_event *event;
	struct hw_perf_event *hwc;
	int i;

	if (!x86_pmu_initialized())
		return;

	if (cpuc->enabled)
		return;

	if (cpuc->n_added) {
		int n_running = cpuc->n_events - cpuc->n_added;
		/*
		 * apply assignment obtained either from
		 * hw_perf_group_sched_in() or x86_pmu_enable()
		 *
		 * step1: save events moving to new counters
		 * step2: reprogram moved events into new counters
		 */
		for (i = 0; i < n_running; i++) {
			event = cpuc->event_list[i];
			hwc = &event->hw;

			/*
			 * we can avoid reprogramming counter if:
			 * - assigned same counter as last time
			 * - running on same CPU as last time
			 * - no other event has used the counter since
			 */
			if (hwc->idx == -1 ||
			    match_prev_assignment(hwc, cpuc, i))
				continue;

			x86_pmu_stop(event);
		}

		for (i = 0; i < cpuc->n_events; i++) {
			event = cpuc->event_list[i];
			hwc = &event->hw;

			if (!match_prev_assignment(hwc, cpuc, i))
				x86_assign_hw_event(event, cpuc, i);
			else if (i < n_running)
				continue;

			x86_pmu_start(event);
		}
		cpuc->n_added = 0;
		perf_events_lapic_init();
	}

	cpuc->enabled = 1;
	barrier();

	x86_pmu.enable_all();
}

static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc)
{
	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
			      hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE);
}

static inline void x86_pmu_disable_event(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	(void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config);
}

static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);

/*
 * Set the next IRQ period, based on the hwc->period_left value.
 * To be called with the event disabled in hw:
 */
static int
x86_perf_event_set_period(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	s64 left = atomic64_read(&hwc->period_left);
	s64 period = hwc->sample_period;
	int err, ret = 0, idx = hwc->idx;

	if (idx == X86_PMC_IDX_FIXED_BTS)
		return 0;

	/*
	 * If we are way outside a reasonable range then just skip forward:
	 */
	if (unlikely(left <= -period)) {
		left = period;
		atomic64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}

	if (unlikely(left <= 0)) {
		left += period;
		atomic64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}
	/*
	 * Quirk: certain CPUs dont like it if just 1 hw_event is left:
	 */
	if (unlikely(left < 2))
		left = 2;

	if (left > x86_pmu.max_period)
		left = x86_pmu.max_period;

	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;

	/*
	 * The hw event starts counting from this event offset,
	 * mark it to be able to extra future deltas:
	 */
	atomic64_set(&hwc->prev_count, (u64)-left);

	err = checking_wrmsrl(hwc->event_base + idx,
			     (u64)(-left) & x86_pmu.event_mask);

	perf_event_update_userpage(event);

	return ret;
}

static void x86_pmu_enable_event(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	if (cpuc->enabled)
		__x86_pmu_enable_event(&event->hw);
}

/*
 * activate a single event
 *
 * The event is added to the group of enabled events
 * but only if it can be scehduled with existing events.
 *
 * Called with PMU disabled. If successful and return value 1,
 * then guaranteed to call perf_enable() and hw_perf_enable()
 */
static int x86_pmu_enable(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct hw_perf_event *hwc;
	int assign[X86_PMC_IDX_MAX];
	int n, n0, ret;

	hwc = &event->hw;

	n0 = cpuc->n_events;
	n = collect_events(cpuc, event, false);
	if (n < 0)
		return n;

	ret = x86_schedule_events(cpuc, n, assign);
	if (ret)
		return ret;
	/*
	 * copy new assignment, now we know it is possible
	 * will be used by hw_perf_enable()
	 */
	memcpy(cpuc->assign, assign, n*sizeof(int));

	cpuc->n_events = n;
	cpuc->n_added += n - n0;

	return 0;
}

static int x86_pmu_start(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	int idx = event->hw.idx;

	if (idx == -1)
		return -EAGAIN;

	x86_perf_event_set_period(event);
	cpuc->events[idx] = event;
	__set_bit(idx, cpuc->active_mask);
	x86_pmu.enable(event);
	perf_event_update_userpage(event);

	return 0;
}

static void x86_pmu_unthrottle(struct perf_event *event)
{
	int ret = x86_pmu_start(event);
	WARN_ON_ONCE(ret);
}

void perf_event_print_debug(void)
{
	u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
	struct cpu_hw_events *cpuc;
	unsigned long flags;
	int cpu, idx;

	if (!x86_pmu.num_events)
		return;

	local_irq_save(flags);

	cpu = smp_processor_id();
	cpuc = &per_cpu(cpu_hw_events, cpu);

	if (x86_pmu.version >= 2) {
		rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
		rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
		rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow);
		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed);

		pr_info("\n");
		pr_info("CPU#%d: ctrl:       %016llx\n", cpu, ctrl);
		pr_info("CPU#%d: status:     %016llx\n", cpu, status);
		pr_info("CPU#%d: overflow:   %016llx\n", cpu, overflow);
		pr_info("CPU#%d: fixed:      %016llx\n", cpu, fixed);
	}
	pr_info("CPU#%d: active:       %016llx\n", cpu, *(u64 *)cpuc->active_mask);

	for (idx = 0; idx < x86_pmu.num_events; idx++) {
		rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
		rdmsrl(x86_pmu.perfctr  + idx, pmc_count);

		prev_left = per_cpu(pmc_prev_left[idx], cpu);

		pr_info("CPU#%d:   gen-PMC%d ctrl:  %016llx\n",
			cpu, idx, pmc_ctrl);
		pr_info("CPU#%d:   gen-PMC%d count: %016llx\n",
			cpu, idx, pmc_count);
		pr_info("CPU#%d:   gen-PMC%d left:  %016llx\n",
			cpu, idx, prev_left);
	}
	for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);

		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
			cpu, idx, pmc_count);
	}
	local_irq_restore(flags);
}

static void x86_pmu_stop(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;

	if (!__test_and_clear_bit(idx, cpuc->active_mask))
		return;

	x86_pmu.disable(event);

	/*
	 * Drain the remaining delta count out of a event
	 * that we are disabling:
	 */
	x86_perf_event_update(event);

	cpuc->events[idx] = NULL;
}

static void x86_pmu_disable(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	int i;

	x86_pmu_stop(event);

	for (i = 0; i < cpuc->n_events; i++) {
		if (event == cpuc->event_list[i]) {

			if (x86_pmu.put_event_constraints)
				x86_pmu.put_event_constraints(cpuc, event);

			while (++i < cpuc->n_events)
				cpuc->event_list[i-1] = cpuc->event_list[i];

			--cpuc->n_events;
			break;
		}
	}
	perf_event_update_userpage(event);
}

static int x86_pmu_handle_irq(struct pt_regs *regs)
{
	struct perf_sample_data data;
	struct cpu_hw_events *cpuc;
	struct perf_event *event;
	struct hw_perf_event *hwc;
	int idx, handled = 0;
	u64 val;

	perf_sample_data_init(&data, 0);

	cpuc = &__get_cpu_var(cpu_hw_events);

	for (idx = 0; idx < x86_pmu.num_events; idx++) {
		if (!test_bit(idx, cpuc->active_mask))
			continue;

		event = cpuc->events[idx];
		hwc = &event->hw;

		val = x86_perf_event_update(event);
		if (val & (1ULL << (x86_pmu.event_bits - 1)))
			continue;

		/*
		 * event overflow
		 */
		handled		= 1;
		data.period	= event->hw.last_period;

		if (!x86_perf_event_set_period(event))
			continue;

		if (perf_event_overflow(event, 1, &data, regs))
			x86_pmu_stop(event);
	}

	if (handled)
		inc_irq_stat(apic_perf_irqs);

	return handled;
}

void smp_perf_pending_interrupt(struct pt_regs *regs)
{
	irq_enter();
	ack_APIC_irq();
	inc_irq_stat(apic_pending_irqs);
	perf_event_do_pending();
	irq_exit();
}

void set_perf_event_pending(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
	if (!x86_pmu.apic || !x86_pmu_initialized())
		return;

	apic->send_IPI_self(LOCAL_PENDING_VECTOR);
#endif
}

void perf_events_lapic_init(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
	if (!x86_pmu.apic || !x86_pmu_initialized())
		return;

	/*
	 * Always use NMI for PMU
	 */
	apic_write(APIC_LVTPC, APIC_DM_NMI);
#endif
}

static int __kprobes
perf_event_nmi_handler(struct notifier_block *self,
			 unsigned long cmd, void *__args)
{
	struct die_args *args = __args;
	struct pt_regs *regs;

	if (!atomic_read(&active_events))
		return NOTIFY_DONE;

	switch (cmd) {
	case DIE_NMI:
	case DIE_NMI_IPI:
		break;

	default:
		return NOTIFY_DONE;
	}

	regs = args->regs;

#ifdef CONFIG_X86_LOCAL_APIC
	apic_write(APIC_LVTPC, APIC_DM_NMI);
#endif
	/*
	 * Can't rely on the handled return value to say it was our NMI, two
	 * events could trigger 'simultaneously' raising two back-to-back NMIs.
	 *
	 * If the first NMI handles both, the latter will be empty and daze
	 * the CPU.
	 */
	x86_pmu.handle_irq(regs);

	return NOTIFY_STOP;
}

static __read_mostly struct notifier_block perf_event_nmi_notifier = {
	.notifier_call		= perf_event_nmi_handler,
	.next			= NULL,
	.priority		= 1
};

static struct event_constraint unconstrained;
static struct event_constraint emptyconstraint;

static struct event_constraint *
x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
{
	struct event_constraint *c;

	if (x86_pmu.event_constraints) {
		for_each_event_constraint(c, x86_pmu.event_constraints) {
			if ((event->hw.config & c->cmask) == c->code)
				return c;
		}
	}

	return &unconstrained;
}

static int x86_event_sched_in(struct perf_event *event,
			  struct perf_cpu_context *cpuctx)
{
	int ret = 0;

	event->state = PERF_EVENT_STATE_ACTIVE;
	event->oncpu = smp_processor_id();
	event->tstamp_running += event->ctx->time - event->tstamp_stopped;

	if (!is_x86_event(event))
		ret = event->pmu->enable(event);

	if (!ret && !is_software_event(event))
		cpuctx->active_oncpu++;

	if (!ret && event->attr.exclusive)
		cpuctx->exclusive = 1;

	return ret;
}

static void x86_event_sched_out(struct perf_event *event,
			    struct perf_cpu_context *cpuctx)
{
	event->state = PERF_EVENT_STATE_INACTIVE;
	event->oncpu = -1;

	if (!is_x86_event(event))
		event->pmu->disable(event);

	event->tstamp_running -= event->ctx->time - event->tstamp_stopped;

	if (!is_software_event(event))
		cpuctx->active_oncpu--;

	if (event->attr.exclusive || !cpuctx->active_oncpu)
		cpuctx->exclusive = 0;
}

/*
 * Called to enable a whole group of events.
 * Returns 1 if the group was enabled, or -EAGAIN if it could not be.
 * Assumes the caller has disabled interrupts and has
 * frozen the PMU with hw_perf_save_disable.
 *
 * called with PMU disabled. If successful and return value 1,
 * then guaranteed to call perf_enable() and hw_perf_enable()
 */
int hw_perf_group_sched_in(struct perf_event *leader,
	       struct perf_cpu_context *cpuctx,
	       struct perf_event_context *ctx)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct perf_event *sub;
	int assign[X86_PMC_IDX_MAX];
	int n0, n1, ret;

	/* n0 = total number of events */
	n0 = collect_events(cpuc, leader, true);
	if (n0 < 0)
		return n0;

	ret = x86_schedule_events(cpuc, n0, assign);
	if (ret)
		return ret;

	ret = x86_event_sched_in(leader, cpuctx);
	if (ret)
		return ret;

	n1 = 1;
	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
		if (sub->state > PERF_EVENT_STATE_OFF) {
			ret = x86_event_sched_in(sub, cpuctx);
			if (ret)
				goto undo;
			++n1;
		}
	}
	/*
	 * copy new assignment, now we know it is possible
	 * will be used by hw_perf_enable()
	 */
	memcpy(cpuc->assign, assign, n0*sizeof(int));

	cpuc->n_events  = n0;
	cpuc->n_added  += n1;
	ctx->nr_active += n1;

	/*
	 * 1 means successful and events are active
	 * This is not quite true because we defer
	 * actual activation until hw_perf_enable() but
	 * this way we* ensure caller won't try to enable
	 * individual events
	 */
	return 1;
undo:
	x86_event_sched_out(leader, cpuctx);
	n0  = 1;
	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
		if (sub->state == PERF_EVENT_STATE_ACTIVE) {
			x86_event_sched_out(sub, cpuctx);
			if (++n0 == n1)
				break;
		}
	}
	return ret;
}

#include "perf_event_amd.c"
#include "perf_event_p6.c"
#include "perf_event_intel.c"

static int __cpuinit
x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
{
	unsigned int cpu = (long)hcpu;
	int ret = NOTIFY_OK;

	switch (action & ~CPU_TASKS_FROZEN) {
	case CPU_UP_PREPARE:
		if (x86_pmu.cpu_prepare)
			ret = x86_pmu.cpu_prepare(cpu);
		break;

	case CPU_STARTING:
		if (x86_pmu.cpu_starting)
			x86_pmu.cpu_starting(cpu);
		break;

	case CPU_DYING:
		if (x86_pmu.cpu_dying)
			x86_pmu.cpu_dying(cpu);
		break;

	case CPU_UP_CANCELED:
	case CPU_DEAD:
		if (x86_pmu.cpu_dead)
			x86_pmu.cpu_dead(cpu);
		break;

	default:
		break;
	}

	return ret;
}

static void __init pmu_check_apic(void)
{
	if (cpu_has_apic)
		return;

	x86_pmu.apic = 0;
	pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n");
	pr_info("no hardware sampling interrupt available.\n");
}

void __init init_hw_perf_events(void)
{
	struct event_constraint *c;
	int err;

	pr_info("Performance Events: ");

	switch (boot_cpu_data.x86_vendor) {
	case X86_VENDOR_INTEL:
		err = intel_pmu_init();
		break;
	case X86_VENDOR_AMD:
		err = amd_pmu_init();
		break;
	default:
		return;
	}
	if (err != 0) {
		pr_cont("no PMU driver, software events only.\n");
		return;
	}

	pmu_check_apic();

	pr_cont("%s PMU driver.\n", x86_pmu.name);

	if (x86_pmu.num_events > X86_PMC_MAX_GENERIC) {
		WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
		     x86_pmu.num_events, X86_PMC_MAX_GENERIC);
		x86_pmu.num_events = X86_PMC_MAX_GENERIC;
	}
	perf_event_mask = (1 << x86_pmu.num_events) - 1;
	perf_max_events = x86_pmu.num_events;

	if (x86_pmu.num_events_fixed > X86_PMC_MAX_FIXED) {
		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
		     x86_pmu.num_events_fixed, X86_PMC_MAX_FIXED);
		x86_pmu.num_events_fixed = X86_PMC_MAX_FIXED;
	}

	perf_event_mask |=
		((1LL << x86_pmu.num_events_fixed)-1) << X86_PMC_IDX_FIXED;
	x86_pmu.intel_ctrl = perf_event_mask;

	perf_events_lapic_init();
	register_die_notifier(&perf_event_nmi_notifier);

	unconstrained = (struct event_constraint)
		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1,
				   0, x86_pmu.num_events);

	if (x86_pmu.event_constraints) {
		for_each_event_constraint(c, x86_pmu.event_constraints) {
			if (c->cmask != INTEL_ARCH_FIXED_MASK)
				continue;

			c->idxmsk64 |= (1ULL << x86_pmu.num_events) - 1;
			c->weight += x86_pmu.num_events;
		}
	}

	pr_info("... version:                %d\n",     x86_pmu.version);
	pr_info("... bit width:              %d\n",     x86_pmu.event_bits);
	pr_info("... generic registers:      %d\n",     x86_pmu.num_events);
	pr_info("... value mask:             %016Lx\n", x86_pmu.event_mask);
	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_events_fixed);
	pr_info("... event mask:             %016Lx\n", perf_event_mask);

	perf_cpu_notifier(x86_pmu_notifier);
}

static inline void x86_pmu_read(struct perf_event *event)
{
	x86_perf_event_update(event);
}

static const struct pmu pmu = {
	.enable		= x86_pmu_enable,
	.disable	= x86_pmu_disable,
	.start		= x86_pmu_start,
	.stop		= x86_pmu_stop,
	.read		= x86_pmu_read,
	.unthrottle	= x86_pmu_unthrottle,
};

/*
 * validate a single event group
 *
 * validation include:
 *	- check events are compatible which each other
 *	- events do not compete for the same counter
 *	- number of events <= number of counters
 *
 * validation ensures the group can be loaded onto the
 * PMU if it was the only group available.
 */
static int validate_group(struct perf_event *event)
{
	struct perf_event *leader = event->group_leader;
	struct cpu_hw_events *fake_cpuc;
	int ret, n;

	ret = -ENOMEM;
	fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO);
	if (!fake_cpuc)
		goto out;

	/*
	 * the event is not yet connected with its
	 * siblings therefore we must first collect
	 * existing siblings, then add the new event
	 * before we can simulate the scheduling
	 */
	ret = -ENOSPC;
	n = collect_events(fake_cpuc, leader, true);
	if (n < 0)
		goto out_free;

	fake_cpuc->n_events = n;
	n = collect_events(fake_cpuc, event, false);
	if (n < 0)
		goto out_free;

	fake_cpuc->n_events = n;

	ret = x86_schedule_events(fake_cpuc, n, NULL);

out_free:
	kfree(fake_cpuc);
out:
	return ret;
}

const struct pmu *hw_perf_event_init(struct perf_event *event)
{
	const struct pmu *tmp;
	int err;

	err = __hw_perf_event_init(event);
	if (!err) {
		/*
		 * we temporarily connect event to its pmu
		 * such that validate_group() can classify
		 * it as an x86 event using is_x86_event()
		 */
		tmp = event->pmu;
		event->pmu = &pmu;

		if (event->group_leader != event)
			err = validate_group(event);

		event->pmu = tmp;
	}
	if (err) {
		if (event->destroy)
			event->destroy(event);
		return ERR_PTR(err);
	}

	return &pmu;
}

/*
 * callchain support
 */

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

static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);


static void
backtrace_warning_symbol(void *data, char *msg, unsigned long symbol)
{
	/* Ignore warnings */
}

static void backtrace_warning(void *data, char *msg)
{
	/* Ignore warnings */
}

static int backtrace_stack(void *data, char *name)
{
	return 0;
}

static void backtrace_address(void *data, unsigned long addr, int reliable)
{
	struct perf_callchain_entry *entry = data;

	if (reliable)
		callchain_store(entry, addr);
}

static const struct stacktrace_ops backtrace_ops = {
	.warning		= backtrace_warning,
	.warning_symbol		= backtrace_warning_symbol,
	.stack			= backtrace_stack,
	.address		= backtrace_address,
	.walk_stack		= print_context_stack_bp,
};

#include "../dumpstack.h"

static void
perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
	callchain_store(entry, PERF_CONTEXT_KERNEL);
	callchain_store(entry, regs->ip);

	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
}

/*
 * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
 */
static unsigned long
copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
{
	unsigned long offset, addr = (unsigned long)from;
	int type = in_nmi() ? KM_NMI : KM_IRQ0;
	unsigned long size, len = 0;
	struct page *page;
	void *map;
	int ret;

	do {
		ret = __get_user_pages_fast(addr, 1, 0, &page);
		if (!ret)
			break;

		offset = addr & (PAGE_SIZE - 1);
		size = min(PAGE_SIZE - offset, n - len);

		map = kmap_atomic(page, type);
		memcpy(to, map+offset, size);
		kunmap_atomic(map, type);
		put_page(page);

		len  += size;
		to   += size;
		addr += size;

	} while (len < n);

	return len;
}

#ifdef CONFIG_COMPAT
static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
	/* 32-bit process in 64-bit kernel. */
	struct stack_frame_ia32 frame;
	const void __user *fp;

	if (!test_thread_flag(TIF_IA32))
		return 0;

	fp = compat_ptr(regs->bp);
	while (entry->nr < PERF_MAX_STACK_DEPTH) {
		unsigned long bytes;
		frame.next_frame     = 0;
		frame.return_address = 0;

		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
		if (bytes != sizeof(frame))
			break;

		if (fp < compat_ptr(regs->sp))
			break;

		callchain_store(entry, frame.return_address);
		fp = compat_ptr(frame.next_frame);
	}
	return 1;
}
#else
static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
    return 0;
}
#endif

static void
perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
	struct stack_frame frame;
	const void __user *fp;

	if (!user_mode(regs))
		regs = task_pt_regs(current);

	fp = (void __user *)regs->bp;

	callchain_store(entry, PERF_CONTEXT_USER);
	callchain_store(entry, regs->ip);

	if (perf_callchain_user32(regs, entry))
		return;

	while (entry->nr < PERF_MAX_STACK_DEPTH) {
		unsigned long bytes;
		frame.next_frame	     = NULL;
		frame.return_address = 0;

		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
		if (bytes != sizeof(frame))
			break;

		if ((unsigned long)fp < regs->sp)
			break;

		callchain_store(entry, frame.return_address);
		fp = frame.next_frame;
	}
}

static void
perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
	int is_user;

	if (!regs)
		return;

	is_user = user_mode(regs);

	if (is_user && current->state != TASK_RUNNING)
		return;

	if (!is_user)
		perf_callchain_kernel(regs, entry);

	if (current->mm)
		perf_callchain_user(regs, entry);
}

struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
{
	struct perf_callchain_entry *entry;

	if (in_nmi())
		entry = &__get_cpu_var(pmc_nmi_entry);
	else
		entry = &__get_cpu_var(pmc_irq_entry);

	entry->nr = 0;

	perf_do_callchain(regs, entry);

	return entry;
}

void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
{
	regs->ip = ip;
	/*
	 * perf_arch_fetch_caller_regs adds another call, we need to increment
	 * the skip level
	 */
	regs->bp = rewind_frame_pointer(skip + 1);
	regs->cs = __KERNEL_CS;
	local_save_flags(regs->flags);
}