Free Electrons

Embedded Linux Experts

   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
/*
 * PMU support
 *
 * Copyright (C) 2012 ARM Limited
 * Author: Will Deacon <will.deacon@arm.com>
 *
 * This code is based heavily on the ARMv7 perf event code.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
#define pr_fmt(fmt) "hw perfevents: " fmt

#include <linux/bitmap.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/perf_event.h>
#include <linux/platform_device.h>
#include <linux/spinlock.h>
#include <linux/uaccess.h>

#include <asm/cputype.h>
#include <asm/irq.h>
#include <asm/irq_regs.h>
#include <asm/pmu.h>
#include <asm/stacktrace.h>

/*
 * ARMv8 supports a maximum of 32 events.
 * The cycle counter is included in this total.
 */
#define ARMPMU_MAX_HWEVENTS		32

static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);

#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))

/* Set at runtime when we know what CPU type we are. */
static struct arm_pmu *cpu_pmu;

int
armpmu_get_max_events(void)
{
	int max_events = 0;

	if (cpu_pmu != NULL)
		max_events = cpu_pmu->num_events;

	return max_events;
}
EXPORT_SYMBOL_GPL(armpmu_get_max_events);

int perf_num_counters(void)
{
	return armpmu_get_max_events();
}
EXPORT_SYMBOL_GPL(perf_num_counters);

#define HW_OP_UNSUPPORTED		0xFFFF

#define C(_x) \
	PERF_COUNT_HW_CACHE_##_x

#define CACHE_OP_UNSUPPORTED		0xFFFF

static int
armpmu_map_cache_event(const unsigned (*cache_map)
				      [PERF_COUNT_HW_CACHE_MAX]
				      [PERF_COUNT_HW_CACHE_OP_MAX]
				      [PERF_COUNT_HW_CACHE_RESULT_MAX],
		       u64 config)
{
	unsigned int cache_type, cache_op, cache_result, ret;

	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;

	ret = (int)(*cache_map)[cache_type][cache_op][cache_result];

	if (ret == CACHE_OP_UNSUPPORTED)
		return -ENOENT;

	return ret;
}

static int
armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
{
	int mapping;

	if (config >= PERF_COUNT_HW_MAX)
		return -EINVAL;

	mapping = (*event_map)[config];
	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
}

static int
armpmu_map_raw_event(u32 raw_event_mask, u64 config)
{
	return (int)(config & raw_event_mask);
}

static int map_cpu_event(struct perf_event *event,
			 const unsigned (*event_map)[PERF_COUNT_HW_MAX],
			 const unsigned (*cache_map)
					[PERF_COUNT_HW_CACHE_MAX]
					[PERF_COUNT_HW_CACHE_OP_MAX]
					[PERF_COUNT_HW_CACHE_RESULT_MAX],
			 u32 raw_event_mask)
{
	u64 config = event->attr.config;

	switch (event->attr.type) {
	case PERF_TYPE_HARDWARE:
		return armpmu_map_event(event_map, config);
	case PERF_TYPE_HW_CACHE:
		return armpmu_map_cache_event(cache_map, config);
	case PERF_TYPE_RAW:
		return armpmu_map_raw_event(raw_event_mask, config);
	}

	return -ENOENT;
}

int
armpmu_event_set_period(struct perf_event *event,
			struct hw_perf_event *hwc,
			int idx)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	s64 left = local64_read(&hwc->period_left);
	s64 period = hwc->sample_period;
	int ret = 0;

	if (unlikely(left <= -period)) {
		left = period;
		local64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}

	if (unlikely(left <= 0)) {
		left += period;
		local64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}

	if (left > (s64)armpmu->max_period)
		left = armpmu->max_period;

	local64_set(&hwc->prev_count, (u64)-left);

	armpmu->write_counter(idx, (u64)(-left) & 0xffffffff);

	perf_event_update_userpage(event);

	return ret;
}

u64
armpmu_event_update(struct perf_event *event,
		    struct hw_perf_event *hwc,
		    int idx)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	u64 delta, prev_raw_count, new_raw_count;

again:
	prev_raw_count = local64_read(&hwc->prev_count);
	new_raw_count = armpmu->read_counter(idx);

	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
			     new_raw_count) != prev_raw_count)
		goto again;

	delta = (new_raw_count - prev_raw_count) & armpmu->max_period;

	local64_add(delta, &event->count);
	local64_sub(delta, &hwc->period_left);

	return new_raw_count;
}

static void
armpmu_read(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;

	/* Don't read disabled counters! */
	if (hwc->idx < 0)
		return;

	armpmu_event_update(event, hwc, hwc->idx);
}

static void
armpmu_stop(struct perf_event *event, int flags)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;

	/*
	 * ARM pmu always has to update the counter, so ignore
	 * PERF_EF_UPDATE, see comments in armpmu_start().
	 */
	if (!(hwc->state & PERF_HES_STOPPED)) {
		armpmu->disable(hwc, hwc->idx);
		barrier(); /* why? */
		armpmu_event_update(event, hwc, hwc->idx);
		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
	}
}

static void
armpmu_start(struct perf_event *event, int flags)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;

	/*
	 * ARM pmu always has to reprogram the period, so ignore
	 * PERF_EF_RELOAD, see the comment below.
	 */
	if (flags & PERF_EF_RELOAD)
		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));

	hwc->state = 0;
	/*
	 * Set the period again. Some counters can't be stopped, so when we
	 * were stopped we simply disabled the IRQ source and the counter
	 * may have been left counting. If we don't do this step then we may
	 * get an interrupt too soon or *way* too late if the overflow has
	 * happened since disabling.
	 */
	armpmu_event_set_period(event, hwc, hwc->idx);
	armpmu->enable(hwc, hwc->idx);
}

static void
armpmu_del(struct perf_event *event, int flags)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;

	WARN_ON(idx < 0);

	armpmu_stop(event, PERF_EF_UPDATE);
	hw_events->events[idx] = NULL;
	clear_bit(idx, hw_events->used_mask);

	perf_event_update_userpage(event);
}

static int
armpmu_add(struct perf_event *event, int flags)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
	struct hw_perf_event *hwc = &event->hw;
	int idx;
	int err = 0;

	perf_pmu_disable(event->pmu);

	/* If we don't have a space for the counter then finish early. */
	idx = armpmu->get_event_idx(hw_events, hwc);
	if (idx < 0) {
		err = idx;
		goto out;
	}

	/*
	 * If there is an event in the counter we are going to use then make
	 * sure it is disabled.
	 */
	event->hw.idx = idx;
	armpmu->disable(hwc, idx);
	hw_events->events[idx] = event;

	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
	if (flags & PERF_EF_START)
		armpmu_start(event, PERF_EF_RELOAD);

	/* Propagate our changes to the userspace mapping. */
	perf_event_update_userpage(event);

out:
	perf_pmu_enable(event->pmu);
	return err;
}

static int
validate_event(struct pmu_hw_events *hw_events,
	       struct perf_event *event)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct hw_perf_event fake_event = event->hw;
	struct pmu *leader_pmu = event->group_leader->pmu;

	if (is_software_event(event))
		return 1;

	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
		return 1;

	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
		return 1;

	return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
}

static int
validate_group(struct perf_event *event)
{
	struct perf_event *sibling, *leader = event->group_leader;
	struct pmu_hw_events fake_pmu;
	DECLARE_BITMAP(fake_used_mask, ARMPMU_MAX_HWEVENTS);

	/*
	 * Initialise the fake PMU. We only need to populate the
	 * used_mask for the purposes of validation.
	 */
	memset(fake_used_mask, 0, sizeof(fake_used_mask));
	fake_pmu.used_mask = fake_used_mask;

	if (!validate_event(&fake_pmu, leader))
		return -EINVAL;

	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
		if (!validate_event(&fake_pmu, sibling))
			return -EINVAL;
	}

	if (!validate_event(&fake_pmu, event))
		return -EINVAL;

	return 0;
}

static void
armpmu_release_hardware(struct arm_pmu *armpmu)
{
	int i, irq, irqs;
	struct platform_device *pmu_device = armpmu->plat_device;

	irqs = min(pmu_device->num_resources, num_possible_cpus());

	for (i = 0; i < irqs; ++i) {
		if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
			continue;
		irq = platform_get_irq(pmu_device, i);
		if (irq >= 0)
			free_irq(irq, armpmu);
	}
}

static int
armpmu_reserve_hardware(struct arm_pmu *armpmu)
{
	int i, err, irq, irqs;
	struct platform_device *pmu_device = armpmu->plat_device;

	if (!pmu_device) {
		pr_err("no PMU device registered\n");
		return -ENODEV;
	}

	irqs = min(pmu_device->num_resources, num_possible_cpus());
	if (irqs < 1) {
		pr_err("no irqs for PMUs defined\n");
		return -ENODEV;
	}

	for (i = 0; i < irqs; ++i) {
		err = 0;
		irq = platform_get_irq(pmu_device, i);
		if (irq < 0)
			continue;

		/*
		 * If we have a single PMU interrupt that we can't shift,
		 * assume that we're running on a uniprocessor machine and
		 * continue. Otherwise, continue without this interrupt.
		 */
		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
				    irq, i);
			continue;
		}

		err = request_irq(irq, armpmu->handle_irq,
				  IRQF_NOBALANCING,
				  "arm-pmu", armpmu);
		if (err) {
			pr_err("unable to request IRQ%d for ARM PMU counters\n",
				irq);
			armpmu_release_hardware(armpmu);
			return err;
		}

		cpumask_set_cpu(i, &armpmu->active_irqs);
	}

	return 0;
}

static void
hw_perf_event_destroy(struct perf_event *event)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	atomic_t *active_events	 = &armpmu->active_events;
	struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex;

	if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) {
		armpmu_release_hardware(armpmu);
		mutex_unlock(pmu_reserve_mutex);
	}
}

static int
event_requires_mode_exclusion(struct perf_event_attr *attr)
{
	return attr->exclude_idle || attr->exclude_user ||
	       attr->exclude_kernel || attr->exclude_hv;
}

static int
__hw_perf_event_init(struct perf_event *event)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	int mapping, err;

	mapping = armpmu->map_event(event);

	if (mapping < 0) {
		pr_debug("event %x:%llx not supported\n", event->attr.type,
			 event->attr.config);
		return mapping;
	}

	/*
	 * We don't assign an index until we actually place the event onto
	 * hardware. Use -1 to signify that we haven't decided where to put it
	 * yet. For SMP systems, each core has it's own PMU so we can't do any
	 * clever allocation or constraints checking at this point.
	 */
	hwc->idx		= -1;
	hwc->config_base	= 0;
	hwc->config		= 0;
	hwc->event_base		= 0;

	/*
	 * Check whether we need to exclude the counter from certain modes.
	 */
	if ((!armpmu->set_event_filter ||
	     armpmu->set_event_filter(hwc, &event->attr)) &&
	     event_requires_mode_exclusion(&event->attr)) {
		pr_debug("ARM performance counters do not support mode exclusion\n");
		return -EPERM;
	}

	/*
	 * Store the event encoding into the config_base field.
	 */
	hwc->config_base	    |= (unsigned long)mapping;

	if (!hwc->sample_period) {
		/*
		 * For non-sampling runs, limit the sample_period to half
		 * of the counter width. That way, the new counter value
		 * is far less likely to overtake the previous one unless
		 * you have some serious IRQ latency issues.
		 */
		hwc->sample_period  = armpmu->max_period >> 1;
		hwc->last_period    = hwc->sample_period;
		local64_set(&hwc->period_left, hwc->sample_period);
	}

	err = 0;
	if (event->group_leader != event) {
		err = validate_group(event);
		if (err)
			return -EINVAL;
	}

	return err;
}

static int armpmu_event_init(struct perf_event *event)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	int err = 0;
	atomic_t *active_events = &armpmu->active_events;

	if (armpmu->map_event(event) == -ENOENT)
		return -ENOENT;

	event->destroy = hw_perf_event_destroy;

	if (!atomic_inc_not_zero(active_events)) {
		mutex_lock(&armpmu->reserve_mutex);
		if (atomic_read(active_events) == 0)
			err = armpmu_reserve_hardware(armpmu);

		if (!err)
			atomic_inc(active_events);
		mutex_unlock(&armpmu->reserve_mutex);
	}

	if (err)
		return err;

	err = __hw_perf_event_init(event);
	if (err)
		hw_perf_event_destroy(event);

	return err;
}

static void armpmu_enable(struct pmu *pmu)
{
	struct arm_pmu *armpmu = to_arm_pmu(pmu);
	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
	int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);

	if (enabled)
		armpmu->start();
}

static void armpmu_disable(struct pmu *pmu)
{
	struct arm_pmu *armpmu = to_arm_pmu(pmu);
	armpmu->stop();
}

static void __init armpmu_init(struct arm_pmu *armpmu)
{
	atomic_set(&armpmu->active_events, 0);
	mutex_init(&armpmu->reserve_mutex);

	armpmu->pmu = (struct pmu) {
		.pmu_enable	= armpmu_enable,
		.pmu_disable	= armpmu_disable,
		.event_init	= armpmu_event_init,
		.add		= armpmu_add,
		.del		= armpmu_del,
		.start		= armpmu_start,
		.stop		= armpmu_stop,
		.read		= armpmu_read,
	};
}

int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type)
{
	armpmu_init(armpmu);
	return perf_pmu_register(&armpmu->pmu, name, type);
}

/*
 * ARMv8 PMUv3 Performance Events handling code.
 * Common event types.
 */
enum armv8_pmuv3_perf_types {
	/* Required events. */
	ARMV8_PMUV3_PERFCTR_PMNC_SW_INCR			= 0x00,
	ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL			= 0x03,
	ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS			= 0x04,
	ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED			= 0x10,
	ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES			= 0x11,
	ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED			= 0x12,

	/* At least one of the following is required. */
	ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED			= 0x08,
	ARMV8_PMUV3_PERFCTR_OP_SPEC				= 0x1B,

	/* Common architectural events. */
	ARMV8_PMUV3_PERFCTR_MEM_READ				= 0x06,
	ARMV8_PMUV3_PERFCTR_MEM_WRITE				= 0x07,
	ARMV8_PMUV3_PERFCTR_EXC_TAKEN				= 0x09,
	ARMV8_PMUV3_PERFCTR_EXC_EXECUTED			= 0x0A,
	ARMV8_PMUV3_PERFCTR_CID_WRITE				= 0x0B,
	ARMV8_PMUV3_PERFCTR_PC_WRITE				= 0x0C,
	ARMV8_PMUV3_PERFCTR_PC_IMM_BRANCH			= 0x0D,
	ARMV8_PMUV3_PERFCTR_PC_PROC_RETURN			= 0x0E,
	ARMV8_PMUV3_PERFCTR_MEM_UNALIGNED_ACCESS		= 0x0F,
	ARMV8_PMUV3_PERFCTR_TTBR_WRITE				= 0x1C,

	/* Common microarchitectural events. */
	ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL			= 0x01,
	ARMV8_PMUV3_PERFCTR_ITLB_REFILL				= 0x02,
	ARMV8_PMUV3_PERFCTR_DTLB_REFILL				= 0x05,
	ARMV8_PMUV3_PERFCTR_MEM_ACCESS				= 0x13,
	ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS			= 0x14,
	ARMV8_PMUV3_PERFCTR_L1_DCACHE_WB			= 0x15,
	ARMV8_PMUV3_PERFCTR_L2_CACHE_ACCESS			= 0x16,
	ARMV8_PMUV3_PERFCTR_L2_CACHE_REFILL			= 0x17,
	ARMV8_PMUV3_PERFCTR_L2_CACHE_WB				= 0x18,
	ARMV8_PMUV3_PERFCTR_BUS_ACCESS				= 0x19,
	ARMV8_PMUV3_PERFCTR_MEM_ERROR				= 0x1A,
	ARMV8_PMUV3_PERFCTR_BUS_CYCLES				= 0x1D,
};

/* PMUv3 HW events mapping. */
static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
};

static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
						[PERF_COUNT_HW_CACHE_OP_MAX]
						[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
	[C(L1D)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(L1I)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(LL)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(DTLB)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(ITLB)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(BPU)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
			[C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(NODE)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
};

/*
 * Perf Events' indices
 */
#define	ARMV8_IDX_CYCLE_COUNTER	0
#define	ARMV8_IDX_COUNTER0	1
#define	ARMV8_IDX_COUNTER_LAST	(ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)

#define	ARMV8_MAX_COUNTERS	32
#define	ARMV8_COUNTER_MASK	(ARMV8_MAX_COUNTERS - 1)

/*
 * ARMv8 low level PMU access
 */

/*
 * Perf Event to low level counters mapping
 */
#define	ARMV8_IDX_TO_COUNTER(x)	\
	(((x) - ARMV8_IDX_COUNTER0) & ARMV8_COUNTER_MASK)

/*
 * Per-CPU PMCR: config reg
 */
#define ARMV8_PMCR_E		(1 << 0) /* Enable all counters */
#define ARMV8_PMCR_P		(1 << 1) /* Reset all counters */
#define ARMV8_PMCR_C		(1 << 2) /* Cycle counter reset */
#define ARMV8_PMCR_D		(1 << 3) /* CCNT counts every 64th cpu cycle */
#define ARMV8_PMCR_X		(1 << 4) /* Export to ETM */
#define ARMV8_PMCR_DP		(1 << 5) /* Disable CCNT if non-invasive debug*/
#define	ARMV8_PMCR_N_SHIFT	11	 /* Number of counters supported */
#define	ARMV8_PMCR_N_MASK	0x1f
#define	ARMV8_PMCR_MASK		0x3f	 /* Mask for writable bits */

/*
 * PMOVSR: counters overflow flag status reg
 */
#define	ARMV8_OVSR_MASK		0xffffffff	/* Mask for writable bits */
#define	ARMV8_OVERFLOWED_MASK	ARMV8_OVSR_MASK

/*
 * PMXEVTYPER: Event selection reg
 */
#define	ARMV8_EVTYPE_MASK	0xc80000ff	/* Mask for writable bits */
#define	ARMV8_EVTYPE_EVENT	0xff		/* Mask for EVENT bits */

/*
 * Event filters for PMUv3
 */
#define	ARMV8_EXCLUDE_EL1	(1 << 31)
#define	ARMV8_EXCLUDE_EL0	(1 << 30)
#define	ARMV8_INCLUDE_EL2	(1 << 27)

static inline u32 armv8pmu_pmcr_read(void)
{
	u32 val;
	asm volatile("mrs %0, pmcr_el0" : "=r" (val));
	return val;
}

static inline void armv8pmu_pmcr_write(u32 val)
{
	val &= ARMV8_PMCR_MASK;
	isb();
	asm volatile("msr pmcr_el0, %0" :: "r" (val));
}

static inline int armv8pmu_has_overflowed(u32 pmovsr)
{
	return pmovsr & ARMV8_OVERFLOWED_MASK;
}

static inline int armv8pmu_counter_valid(int idx)
{
	return idx >= ARMV8_IDX_CYCLE_COUNTER && idx <= ARMV8_IDX_COUNTER_LAST;
}

static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
{
	int ret = 0;
	u32 counter;

	if (!armv8pmu_counter_valid(idx)) {
		pr_err("CPU%u checking wrong counter %d overflow status\n",
			smp_processor_id(), idx);
	} else {
		counter = ARMV8_IDX_TO_COUNTER(idx);
		ret = pmnc & BIT(counter);
	}

	return ret;
}

static inline int armv8pmu_select_counter(int idx)
{
	u32 counter;

	if (!armv8pmu_counter_valid(idx)) {
		pr_err("CPU%u selecting wrong PMNC counter %d\n",
			smp_processor_id(), idx);
		return -EINVAL;
	}

	counter = ARMV8_IDX_TO_COUNTER(idx);
	asm volatile("msr pmselr_el0, %0" :: "r" (counter));
	isb();

	return idx;
}

static inline u32 armv8pmu_read_counter(int idx)
{
	u32 value = 0;

	if (!armv8pmu_counter_valid(idx))
		pr_err("CPU%u reading wrong counter %d\n",
			smp_processor_id(), idx);
	else if (idx == ARMV8_IDX_CYCLE_COUNTER)
		asm volatile("mrs %0, pmccntr_el0" : "=r" (value));
	else if (armv8pmu_select_counter(idx) == idx)
		asm volatile("mrs %0, pmxevcntr_el0" : "=r" (value));

	return value;
}

static inline void armv8pmu_write_counter(int idx, u32 value)
{
	if (!armv8pmu_counter_valid(idx))
		pr_err("CPU%u writing wrong counter %d\n",
			smp_processor_id(), idx);
	else if (idx == ARMV8_IDX_CYCLE_COUNTER)
		asm volatile("msr pmccntr_el0, %0" :: "r" (value));
	else if (armv8pmu_select_counter(idx) == idx)
		asm volatile("msr pmxevcntr_el0, %0" :: "r" (value));
}

static inline void armv8pmu_write_evtype(int idx, u32 val)
{
	if (armv8pmu_select_counter(idx) == idx) {
		val &= ARMV8_EVTYPE_MASK;
		asm volatile("msr pmxevtyper_el0, %0" :: "r" (val));
	}
}

static inline int armv8pmu_enable_counter(int idx)
{
	u32 counter;

	if (!armv8pmu_counter_valid(idx)) {
		pr_err("CPU%u enabling wrong PMNC counter %d\n",
			smp_processor_id(), idx);
		return -EINVAL;
	}

	counter = ARMV8_IDX_TO_COUNTER(idx);
	asm volatile("msr pmcntenset_el0, %0" :: "r" (BIT(counter)));
	return idx;
}

static inline int armv8pmu_disable_counter(int idx)
{
	u32 counter;

	if (!armv8pmu_counter_valid(idx)) {
		pr_err("CPU%u disabling wrong PMNC counter %d\n",
			smp_processor_id(), idx);
		return -EINVAL;
	}

	counter = ARMV8_IDX_TO_COUNTER(idx);
	asm volatile("msr pmcntenclr_el0, %0" :: "r" (BIT(counter)));
	return idx;
}

static inline int armv8pmu_enable_intens(int idx)
{
	u32 counter;

	if (!armv8pmu_counter_valid(idx)) {
		pr_err("CPU%u enabling wrong PMNC counter IRQ enable %d\n",
			smp_processor_id(), idx);
		return -EINVAL;
	}

	counter = ARMV8_IDX_TO_COUNTER(idx);
	asm volatile("msr pmintenset_el1, %0" :: "r" (BIT(counter)));
	return idx;
}

static inline int armv8pmu_disable_intens(int idx)
{
	u32 counter;

	if (!armv8pmu_counter_valid(idx)) {
		pr_err("CPU%u disabling wrong PMNC counter IRQ enable %d\n",
			smp_processor_id(), idx);
		return -EINVAL;
	}

	counter = ARMV8_IDX_TO_COUNTER(idx);
	asm volatile("msr pmintenclr_el1, %0" :: "r" (BIT(counter)));
	isb();
	/* Clear the overflow flag in case an interrupt is pending. */
	asm volatile("msr pmovsclr_el0, %0" :: "r" (BIT(counter)));
	isb();
	return idx;
}

static inline u32 armv8pmu_getreset_flags(void)
{
	u32 value;

	/* Read */
	asm volatile("mrs %0, pmovsclr_el0" : "=r" (value));

	/* Write to clear flags */
	value &= ARMV8_OVSR_MASK;
	asm volatile("msr pmovsclr_el0, %0" :: "r" (value));

	return value;
}

static void armv8pmu_enable_event(struct hw_perf_event *hwc, int idx)
{
	unsigned long flags;
	struct pmu_hw_events *events = cpu_pmu->get_hw_events();

	/*
	 * Enable counter and interrupt, and set the counter to count
	 * the event that we're interested in.
	 */
	raw_spin_lock_irqsave(&events->pmu_lock, flags);

	/*
	 * Disable counter
	 */
	armv8pmu_disable_counter(idx);

	/*
	 * Set event (if destined for PMNx counters).
	 */
	armv8pmu_write_evtype(idx, hwc->config_base);

	/*
	 * Enable interrupt for this counter
	 */
	armv8pmu_enable_intens(idx);

	/*
	 * Enable counter
	 */
	armv8pmu_enable_counter(idx);

	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}

static void armv8pmu_disable_event(struct hw_perf_event *hwc, int idx)
{
	unsigned long flags;
	struct pmu_hw_events *events = cpu_pmu->get_hw_events();

	/*
	 * Disable counter and interrupt
	 */
	raw_spin_lock_irqsave(&events->pmu_lock, flags);

	/*
	 * Disable counter
	 */
	armv8pmu_disable_counter(idx);

	/*
	 * Disable interrupt for this counter
	 */
	armv8pmu_disable_intens(idx);

	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}

static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev)
{
	u32 pmovsr;
	struct perf_sample_data data;
	struct pmu_hw_events *cpuc;
	struct pt_regs *regs;
	int idx;

	/*
	 * Get and reset the IRQ flags
	 */
	pmovsr = armv8pmu_getreset_flags();

	/*
	 * Did an overflow occur?
	 */
	if (!armv8pmu_has_overflowed(pmovsr))
		return IRQ_NONE;

	/*
	 * Handle the counter(s) overflow(s)
	 */
	regs = get_irq_regs();

	cpuc = &__get_cpu_var(cpu_hw_events);
	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
		struct perf_event *event = cpuc->events[idx];
		struct hw_perf_event *hwc;

		/* Ignore if we don't have an event. */
		if (!event)
			continue;

		/*
		 * We have a single interrupt for all counters. Check that
		 * each counter has overflowed before we process it.
		 */
		if (!armv8pmu_counter_has_overflowed(pmovsr, idx))
			continue;

		hwc = &event->hw;
		armpmu_event_update(event, hwc, idx);
		perf_sample_data_init(&data, 0, hwc->last_period);
		if (!armpmu_event_set_period(event, hwc, idx))
			continue;

		if (perf_event_overflow(event, &data, regs))
			cpu_pmu->disable(hwc, idx);
	}

	/*
	 * Handle the pending perf events.
	 *
	 * Note: this call *must* be run with interrupts disabled. For
	 * platforms that can have the PMU interrupts raised as an NMI, this
	 * will not work.
	 */
	irq_work_run();

	return IRQ_HANDLED;
}

static void armv8pmu_start(void)
{
	unsigned long flags;
	struct pmu_hw_events *events = cpu_pmu->get_hw_events();

	raw_spin_lock_irqsave(&events->pmu_lock, flags);
	/* Enable all counters */
	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMCR_E);
	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}

static void armv8pmu_stop(void)
{
	unsigned long flags;
	struct pmu_hw_events *events = cpu_pmu->get_hw_events();

	raw_spin_lock_irqsave(&events->pmu_lock, flags);
	/* Disable all counters */
	armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMCR_E);
	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}

static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
				  struct hw_perf_event *event)
{
	int idx;
	unsigned long evtype = event->config_base & ARMV8_EVTYPE_EVENT;

	/* Always place a cycle counter into the cycle counter. */
	if (evtype == ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES) {
		if (test_and_set_bit(ARMV8_IDX_CYCLE_COUNTER, cpuc->used_mask))
			return -EAGAIN;

		return ARMV8_IDX_CYCLE_COUNTER;
	}

	/*
	 * For anything other than a cycle counter, try and use
	 * the events counters
	 */
	for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) {
		if (!test_and_set_bit(idx, cpuc->used_mask))
			return idx;
	}

	/* The counters are all in use. */
	return -EAGAIN;
}

/*
 * Add an event filter to a given event. This will only work for PMUv2 PMUs.
 */
static int armv8pmu_set_event_filter(struct hw_perf_event *event,
				     struct perf_event_attr *attr)
{
	unsigned long config_base = 0;

	if (attr->exclude_idle)
		return -EPERM;
	if (attr->exclude_user)
		config_base |= ARMV8_EXCLUDE_EL0;
	if (attr->exclude_kernel)
		config_base |= ARMV8_EXCLUDE_EL1;
	if (!attr->exclude_hv)
		config_base |= ARMV8_INCLUDE_EL2;

	/*
	 * Install the filter into config_base as this is used to
	 * construct the event type.
	 */
	event->config_base = config_base;

	return 0;
}

static void armv8pmu_reset(void *info)
{
	u32 idx, nb_cnt = cpu_pmu->num_events;

	/* The counter and interrupt enable registers are unknown at reset. */
	for (idx = ARMV8_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx)
		armv8pmu_disable_event(NULL, idx);

	/* Initialize & Reset PMNC: C and P bits. */
	armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C);

	/* Disable access from userspace. */
	asm volatile("msr pmuserenr_el0, %0" :: "r" (0));
}

static int armv8_pmuv3_map_event(struct perf_event *event)
{
	return map_cpu_event(event, &armv8_pmuv3_perf_map,
				&armv8_pmuv3_perf_cache_map, 0xFF);
}

static struct arm_pmu armv8pmu = {
	.handle_irq		= armv8pmu_handle_irq,
	.enable			= armv8pmu_enable_event,
	.disable		= armv8pmu_disable_event,
	.read_counter		= armv8pmu_read_counter,
	.write_counter		= armv8pmu_write_counter,
	.get_event_idx		= armv8pmu_get_event_idx,
	.start			= armv8pmu_start,
	.stop			= armv8pmu_stop,
	.reset			= armv8pmu_reset,
	.max_period		= (1LLU << 32) - 1,
};

static u32 __init armv8pmu_read_num_pmnc_events(void)
{
	u32 nb_cnt;

	/* Read the nb of CNTx counters supported from PMNC */
	nb_cnt = (armv8pmu_pmcr_read() >> ARMV8_PMCR_N_SHIFT) & ARMV8_PMCR_N_MASK;

	/* Add the CPU cycles counter and return */
	return nb_cnt + 1;
}

static struct arm_pmu *__init armv8_pmuv3_pmu_init(void)
{
	armv8pmu.name			= "arm/armv8-pmuv3";
	armv8pmu.map_event		= armv8_pmuv3_map_event;
	armv8pmu.num_events		= armv8pmu_read_num_pmnc_events();
	armv8pmu.set_event_filter	= armv8pmu_set_event_filter;
	return &armv8pmu;
}

/*
 * Ensure the PMU has sane values out of reset.
 * This requires SMP to be available, so exists as a separate initcall.
 */
static int __init
cpu_pmu_reset(void)
{
	if (cpu_pmu && cpu_pmu->reset)
		return on_each_cpu(cpu_pmu->reset, NULL, 1);
	return 0;
}
arch_initcall(cpu_pmu_reset);

/*
 * PMU platform driver and devicetree bindings.
 */
static struct of_device_id armpmu_of_device_ids[] = {
	{.compatible = "arm,armv8-pmuv3"},
	{},
};

static int armpmu_device_probe(struct platform_device *pdev)
{
	if (!cpu_pmu)
		return -ENODEV;

	cpu_pmu->plat_device = pdev;
	return 0;
}

static struct platform_driver armpmu_driver = {
	.driver		= {
		.name	= "arm-pmu",
		.of_match_table = armpmu_of_device_ids,
	},
	.probe		= armpmu_device_probe,
};

static int __init register_pmu_driver(void)
{
	return platform_driver_register(&armpmu_driver);
}
device_initcall(register_pmu_driver);

static struct pmu_hw_events *armpmu_get_cpu_events(void)
{
	return &__get_cpu_var(cpu_hw_events);
}

static void __init cpu_pmu_init(struct arm_pmu *armpmu)
{
	int cpu;
	for_each_possible_cpu(cpu) {
		struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
		events->events = per_cpu(hw_events, cpu);
		events->used_mask = per_cpu(used_mask, cpu);
		raw_spin_lock_init(&events->pmu_lock);
	}
	armpmu->get_hw_events = armpmu_get_cpu_events;
}

static int __init init_hw_perf_events(void)
{
	u64 dfr = read_cpuid(ID_AA64DFR0_EL1);

	switch ((dfr >> 8) & 0xf) {
	case 0x1:	/* PMUv3 */
		cpu_pmu = armv8_pmuv3_pmu_init();
		break;
	}

	if (cpu_pmu) {
		pr_info("enabled with %s PMU driver, %d counters available\n",
			cpu_pmu->name, cpu_pmu->num_events);
		cpu_pmu_init(cpu_pmu);
		armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW);
	} else {
		pr_info("no hardware support available\n");
	}

	return 0;
}
early_initcall(init_hw_perf_events);

/*
 * Callchain handling code.
 */
struct frame_tail {
	struct frame_tail   __user *fp;
	unsigned long	    lr;
} __attribute__((packed));

/*
 * Get the return address for a single stackframe and return a pointer to the
 * next frame tail.
 */
static struct frame_tail __user *
user_backtrace(struct frame_tail __user *tail,
	       struct perf_callchain_entry *entry)
{
	struct frame_tail buftail;
	unsigned long err;

	/* Also check accessibility of one struct frame_tail beyond */
	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
		return NULL;

	pagefault_disable();
	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
	pagefault_enable();

	if (err)
		return NULL;

	perf_callchain_store(entry, buftail.lr);

	/*
	 * Frame pointers should strictly progress back up the stack
	 * (towards higher addresses).
	 */
	if (tail >= buftail.fp)
		return NULL;

	return buftail.fp;
}

void perf_callchain_user(struct perf_callchain_entry *entry,
			 struct pt_regs *regs)
{
	struct frame_tail __user *tail;

	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
		/* We don't support guest os callchain now */
		return;
	}

	perf_callchain_store(entry, regs->pc);
	tail = (struct frame_tail __user *)regs->regs[29];

	while (entry->nr < PERF_MAX_STACK_DEPTH &&
	       tail && !((unsigned long)tail & 0xf))
		tail = user_backtrace(tail, entry);
}

/*
 * Gets called by walk_stackframe() for every stackframe. This will be called
 * whist unwinding the stackframe and is like a subroutine return so we use
 * the PC.
 */
static int callchain_trace(struct stackframe *frame, void *data)
{
	struct perf_callchain_entry *entry = data;
	perf_callchain_store(entry, frame->pc);
	return 0;
}

void perf_callchain_kernel(struct perf_callchain_entry *entry,
			   struct pt_regs *regs)
{
	struct stackframe frame;

	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
		/* We don't support guest os callchain now */
		return;
	}

	frame.fp = regs->regs[29];
	frame.sp = regs->sp;
	frame.pc = regs->pc;
	walk_stackframe(&frame, callchain_trace, entry);
}

unsigned long perf_instruction_pointer(struct pt_regs *regs)
{
	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
		return perf_guest_cbs->get_guest_ip();

	return instruction_pointer(regs);
}

unsigned long perf_misc_flags(struct pt_regs *regs)
{
	int misc = 0;

	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
		if (perf_guest_cbs->is_user_mode())
			misc |= PERF_RECORD_MISC_GUEST_USER;
		else
			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
	} else {
		if (user_mode(regs))
			misc |= PERF_RECORD_MISC_USER;
		else
			misc |= PERF_RECORD_MISC_KERNEL;
	}

	return misc;
}