Bootlin logo

Elixir Cross Referencer

   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
#include "builtin.h"
#include "perf.h"

#include "util/evsel.h"
#include "util/evlist.h"
#include "util/util.h"
#include "util/cache.h"
#include "util/symbol.h"
#include "util/thread.h"
#include "util/header.h"
#include "util/session.h"
#include "util/intlist.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
#include "util/debug.h"
#include <lk/debugfs.h>
#include "util/tool.h"
#include "util/stat.h"
#include "util/top.h"
#include "util/data.h"

#include <sys/prctl.h>
#ifdef HAVE_TIMERFD_SUPPORT
#include <sys/timerfd.h>
#endif

#include <termios.h>
#include <semaphore.h>
#include <pthread.h>
#include <math.h>

#if defined(__i386__) || defined(__x86_64__)
#include <asm/svm.h>
#include <asm/vmx.h>
#include <asm/kvm.h>

struct event_key {
	#define INVALID_KEY     (~0ULL)
	u64 key;
	int info;
};

struct kvm_event_stats {
	u64 time;
	struct stats stats;
};

struct kvm_event {
	struct list_head hash_entry;
	struct rb_node rb;

	struct event_key key;

	struct kvm_event_stats total;

	#define DEFAULT_VCPU_NUM 8
	int max_vcpu;
	struct kvm_event_stats *vcpu;
};

typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);

struct kvm_event_key {
	const char *name;
	key_cmp_fun key;
};


struct perf_kvm_stat;

struct kvm_events_ops {
	bool (*is_begin_event)(struct perf_evsel *evsel,
			       struct perf_sample *sample,
			       struct event_key *key);
	bool (*is_end_event)(struct perf_evsel *evsel,
			     struct perf_sample *sample, struct event_key *key);
	void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
			   char decode[20]);
	const char *name;
};

struct exit_reasons_table {
	unsigned long exit_code;
	const char *reason;
};

#define EVENTS_BITS		12
#define EVENTS_CACHE_SIZE	(1UL << EVENTS_BITS)

struct perf_kvm_stat {
	struct perf_tool    tool;
	struct perf_record_opts opts;
	struct perf_evlist  *evlist;
	struct perf_session *session;

	const char *file_name;
	const char *report_event;
	const char *sort_key;
	int trace_vcpu;

	struct exit_reasons_table *exit_reasons;
	int exit_reasons_size;
	const char *exit_reasons_isa;

	struct kvm_events_ops *events_ops;
	key_cmp_fun compare;
	struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];

	u64 total_time;
	u64 total_count;
	u64 lost_events;
	u64 duration;

	const char *pid_str;
	struct intlist *pid_list;

	struct rb_root result;

	int timerfd;
	unsigned int display_time;
	bool live;
};


static void exit_event_get_key(struct perf_evsel *evsel,
			       struct perf_sample *sample,
			       struct event_key *key)
{
	key->info = 0;
	key->key = perf_evsel__intval(evsel, sample, "exit_reason");
}

static bool kvm_exit_event(struct perf_evsel *evsel)
{
	return !strcmp(evsel->name, "kvm:kvm_exit");
}

static bool exit_event_begin(struct perf_evsel *evsel,
			     struct perf_sample *sample, struct event_key *key)
{
	if (kvm_exit_event(evsel)) {
		exit_event_get_key(evsel, sample, key);
		return true;
	}

	return false;
}

static bool kvm_entry_event(struct perf_evsel *evsel)
{
	return !strcmp(evsel->name, "kvm:kvm_entry");
}

static bool exit_event_end(struct perf_evsel *evsel,
			   struct perf_sample *sample __maybe_unused,
			   struct event_key *key __maybe_unused)
{
	return kvm_entry_event(evsel);
}

static struct exit_reasons_table vmx_exit_reasons[] = {
	VMX_EXIT_REASONS
};

static struct exit_reasons_table svm_exit_reasons[] = {
	SVM_EXIT_REASONS
};

static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code)
{
	int i = kvm->exit_reasons_size;
	struct exit_reasons_table *tbl = kvm->exit_reasons;

	while (i--) {
		if (tbl->exit_code == exit_code)
			return tbl->reason;
		tbl++;
	}

	pr_err("unknown kvm exit code:%lld on %s\n",
		(unsigned long long)exit_code, kvm->exit_reasons_isa);
	return "UNKNOWN";
}

static void exit_event_decode_key(struct perf_kvm_stat *kvm,
				  struct event_key *key,
				  char decode[20])
{
	const char *exit_reason = get_exit_reason(kvm, key->key);

	scnprintf(decode, 20, "%s", exit_reason);
}

static struct kvm_events_ops exit_events = {
	.is_begin_event = exit_event_begin,
	.is_end_event = exit_event_end,
	.decode_key = exit_event_decode_key,
	.name = "VM-EXIT"
};

/*
 * For the mmio events, we treat:
 * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
 * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
 */
static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
			       struct event_key *key)
{
	key->key  = perf_evsel__intval(evsel, sample, "gpa");
	key->info = perf_evsel__intval(evsel, sample, "type");
}

#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
#define KVM_TRACE_MMIO_READ 1
#define KVM_TRACE_MMIO_WRITE 2

static bool mmio_event_begin(struct perf_evsel *evsel,
			     struct perf_sample *sample, struct event_key *key)
{
	/* MMIO read begin event in kernel. */
	if (kvm_exit_event(evsel))
		return true;

	/* MMIO write begin event in kernel. */
	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
		mmio_event_get_key(evsel, sample, key);
		return true;
	}

	return false;
}

static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
			   struct event_key *key)
{
	/* MMIO write end event in kernel. */
	if (kvm_entry_event(evsel))
		return true;

	/* MMIO read end event in kernel.*/
	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
		mmio_event_get_key(evsel, sample, key);
		return true;
	}

	return false;
}

static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
				  struct event_key *key,
				  char decode[20])
{
	scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key,
				key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
}

static struct kvm_events_ops mmio_events = {
	.is_begin_event = mmio_event_begin,
	.is_end_event = mmio_event_end,
	.decode_key = mmio_event_decode_key,
	.name = "MMIO Access"
};

 /* The time of emulation pio access is from kvm_pio to kvm_entry. */
static void ioport_event_get_key(struct perf_evsel *evsel,
				 struct perf_sample *sample,
				 struct event_key *key)
{
	key->key  = perf_evsel__intval(evsel, sample, "port");
	key->info = perf_evsel__intval(evsel, sample, "rw");
}

static bool ioport_event_begin(struct perf_evsel *evsel,
			       struct perf_sample *sample,
			       struct event_key *key)
{
	if (!strcmp(evsel->name, "kvm:kvm_pio")) {
		ioport_event_get_key(evsel, sample, key);
		return true;
	}

	return false;
}

static bool ioport_event_end(struct perf_evsel *evsel,
			     struct perf_sample *sample __maybe_unused,
			     struct event_key *key __maybe_unused)
{
	return kvm_entry_event(evsel);
}

static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
				    struct event_key *key,
				    char decode[20])
{
	scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key,
				key->info ? "POUT" : "PIN");
}

static struct kvm_events_ops ioport_events = {
	.is_begin_event = ioport_event_begin,
	.is_end_event = ioport_event_end,
	.decode_key = ioport_event_decode_key,
	.name = "IO Port Access"
};

static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
{
	bool ret = true;

	if (!strcmp(kvm->report_event, "vmexit"))
		kvm->events_ops = &exit_events;
	else if (!strcmp(kvm->report_event, "mmio"))
		kvm->events_ops = &mmio_events;
	else if (!strcmp(kvm->report_event, "ioport"))
		kvm->events_ops = &ioport_events;
	else {
		pr_err("Unknown report event:%s\n", kvm->report_event);
		ret = false;
	}

	return ret;
}

struct vcpu_event_record {
	int vcpu_id;
	u64 start_time;
	struct kvm_event *last_event;
};


static void init_kvm_event_record(struct perf_kvm_stat *kvm)
{
	unsigned int i;

	for (i = 0; i < EVENTS_CACHE_SIZE; i++)
		INIT_LIST_HEAD(&kvm->kvm_events_cache[i]);
}

#ifdef HAVE_TIMERFD_SUPPORT
static void clear_events_cache_stats(struct list_head *kvm_events_cache)
{
	struct list_head *head;
	struct kvm_event *event;
	unsigned int i;
	int j;

	for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
		head = &kvm_events_cache[i];
		list_for_each_entry(event, head, hash_entry) {
			/* reset stats for event */
			event->total.time = 0;
			init_stats(&event->total.stats);

			for (j = 0; j < event->max_vcpu; ++j) {
				event->vcpu[j].time = 0;
				init_stats(&event->vcpu[j].stats);
			}
		}
	}
}
#endif

static int kvm_events_hash_fn(u64 key)
{
	return key & (EVENTS_CACHE_SIZE - 1);
}

static bool kvm_event_expand(struct kvm_event *event, int vcpu_id)
{
	int old_max_vcpu = event->max_vcpu;
	void *prev;

	if (vcpu_id < event->max_vcpu)
		return true;

	while (event->max_vcpu <= vcpu_id)
		event->max_vcpu += DEFAULT_VCPU_NUM;

	prev = event->vcpu;
	event->vcpu = realloc(event->vcpu,
			      event->max_vcpu * sizeof(*event->vcpu));
	if (!event->vcpu) {
		free(prev);
		pr_err("Not enough memory\n");
		return false;
	}

	memset(event->vcpu + old_max_vcpu, 0,
	       (event->max_vcpu - old_max_vcpu) * sizeof(*event->vcpu));
	return true;
}

static struct kvm_event *kvm_alloc_init_event(struct event_key *key)
{
	struct kvm_event *event;

	event = zalloc(sizeof(*event));
	if (!event) {
		pr_err("Not enough memory\n");
		return NULL;
	}

	event->key = *key;
	return event;
}

static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm,
					       struct event_key *key)
{
	struct kvm_event *event;
	struct list_head *head;

	BUG_ON(key->key == INVALID_KEY);

	head = &kvm->kvm_events_cache[kvm_events_hash_fn(key->key)];
	list_for_each_entry(event, head, hash_entry) {
		if (event->key.key == key->key && event->key.info == key->info)
			return event;
	}

	event = kvm_alloc_init_event(key);
	if (!event)
		return NULL;

	list_add(&event->hash_entry, head);
	return event;
}

static bool handle_begin_event(struct perf_kvm_stat *kvm,
			       struct vcpu_event_record *vcpu_record,
			       struct event_key *key, u64 timestamp)
{
	struct kvm_event *event = NULL;

	if (key->key != INVALID_KEY)
		event = find_create_kvm_event(kvm, key);

	vcpu_record->last_event = event;
	vcpu_record->start_time = timestamp;
	return true;
}

static void
kvm_update_event_stats(struct kvm_event_stats *kvm_stats, u64 time_diff)
{
	kvm_stats->time += time_diff;
	update_stats(&kvm_stats->stats, time_diff);
}

static double kvm_event_rel_stddev(int vcpu_id, struct kvm_event *event)
{
	struct kvm_event_stats *kvm_stats = &event->total;

	if (vcpu_id != -1)
		kvm_stats = &event->vcpu[vcpu_id];

	return rel_stddev_stats(stddev_stats(&kvm_stats->stats),
				avg_stats(&kvm_stats->stats));
}

static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
			     u64 time_diff)
{
	if (vcpu_id == -1) {
		kvm_update_event_stats(&event->total, time_diff);
		return true;
	}

	if (!kvm_event_expand(event, vcpu_id))
		return false;

	kvm_update_event_stats(&event->vcpu[vcpu_id], time_diff);
	return true;
}

static bool handle_end_event(struct perf_kvm_stat *kvm,
			     struct vcpu_event_record *vcpu_record,
			     struct event_key *key,
			     struct perf_sample *sample)
{
	struct kvm_event *event;
	u64 time_begin, time_diff;
	int vcpu;

	if (kvm->trace_vcpu == -1)
		vcpu = -1;
	else
		vcpu = vcpu_record->vcpu_id;

	event = vcpu_record->last_event;
	time_begin = vcpu_record->start_time;

	/* The begin event is not caught. */
	if (!time_begin)
		return true;

	/*
	 * In some case, the 'begin event' only records the start timestamp,
	 * the actual event is recognized in the 'end event' (e.g. mmio-event).
	 */

	/* Both begin and end events did not get the key. */
	if (!event && key->key == INVALID_KEY)
		return true;

	if (!event)
		event = find_create_kvm_event(kvm, key);

	if (!event)
		return false;

	vcpu_record->last_event = NULL;
	vcpu_record->start_time = 0;

	/* seems to happen once in a while during live mode */
	if (sample->time < time_begin) {
		pr_debug("End time before begin time; skipping event.\n");
		return true;
	}

	time_diff = sample->time - time_begin;

	if (kvm->duration && time_diff > kvm->duration) {
		char decode[32];

		kvm->events_ops->decode_key(kvm, &event->key, decode);
		if (strcmp(decode, "HLT")) {
			pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n",
				 sample->time, sample->pid, vcpu_record->vcpu_id,
				 decode, time_diff/1000);
		}
	}

	return update_kvm_event(event, vcpu, time_diff);
}

static
struct vcpu_event_record *per_vcpu_record(struct thread *thread,
					  struct perf_evsel *evsel,
					  struct perf_sample *sample)
{
	/* Only kvm_entry records vcpu id. */
	if (!thread->priv && kvm_entry_event(evsel)) {
		struct vcpu_event_record *vcpu_record;

		vcpu_record = zalloc(sizeof(*vcpu_record));
		if (!vcpu_record) {
			pr_err("%s: Not enough memory\n", __func__);
			return NULL;
		}

		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id");
		thread->priv = vcpu_record;
	}

	return thread->priv;
}

static bool handle_kvm_event(struct perf_kvm_stat *kvm,
			     struct thread *thread,
			     struct perf_evsel *evsel,
			     struct perf_sample *sample)
{
	struct vcpu_event_record *vcpu_record;
	struct event_key key = {.key = INVALID_KEY};

	vcpu_record = per_vcpu_record(thread, evsel, sample);
	if (!vcpu_record)
		return true;

	/* only process events for vcpus user cares about */
	if ((kvm->trace_vcpu != -1) &&
	    (kvm->trace_vcpu != vcpu_record->vcpu_id))
		return true;

	if (kvm->events_ops->is_begin_event(evsel, sample, &key))
		return handle_begin_event(kvm, vcpu_record, &key, sample->time);

	if (kvm->events_ops->is_end_event(evsel, sample, &key))
		return handle_end_event(kvm, vcpu_record, &key, sample);

	return true;
}

#define GET_EVENT_KEY(func, field)					\
static u64 get_event_ ##func(struct kvm_event *event, int vcpu)		\
{									\
	if (vcpu == -1)							\
		return event->total.field;				\
									\
	if (vcpu >= event->max_vcpu)					\
		return 0;						\
									\
	return event->vcpu[vcpu].field;					\
}

#define COMPARE_EVENT_KEY(func, field)					\
GET_EVENT_KEY(func, field)						\
static int compare_kvm_event_ ## func(struct kvm_event *one,		\
					struct kvm_event *two, int vcpu)\
{									\
	return get_event_ ##func(one, vcpu) >				\
				get_event_ ##func(two, vcpu);		\
}

GET_EVENT_KEY(time, time);
COMPARE_EVENT_KEY(count, stats.n);
COMPARE_EVENT_KEY(mean, stats.mean);
GET_EVENT_KEY(max, stats.max);
GET_EVENT_KEY(min, stats.min);

#define DEF_SORT_NAME_KEY(name, compare_key)				\
	{ #name, compare_kvm_event_ ## compare_key }

static struct kvm_event_key keys[] = {
	DEF_SORT_NAME_KEY(sample, count),
	DEF_SORT_NAME_KEY(time, mean),
	{ NULL, NULL }
};

static bool select_key(struct perf_kvm_stat *kvm)
{
	int i;

	for (i = 0; keys[i].name; i++) {
		if (!strcmp(keys[i].name, kvm->sort_key)) {
			kvm->compare = keys[i].key;
			return true;
		}
	}

	pr_err("Unknown compare key:%s\n", kvm->sort_key);
	return false;
}

static void insert_to_result(struct rb_root *result, struct kvm_event *event,
			     key_cmp_fun bigger, int vcpu)
{
	struct rb_node **rb = &result->rb_node;
	struct rb_node *parent = NULL;
	struct kvm_event *p;

	while (*rb) {
		p = container_of(*rb, struct kvm_event, rb);
		parent = *rb;

		if (bigger(event, p, vcpu))
			rb = &(*rb)->rb_left;
		else
			rb = &(*rb)->rb_right;
	}

	rb_link_node(&event->rb, parent, rb);
	rb_insert_color(&event->rb, result);
}

static void
update_total_count(struct perf_kvm_stat *kvm, struct kvm_event *event)
{
	int vcpu = kvm->trace_vcpu;

	kvm->total_count += get_event_count(event, vcpu);
	kvm->total_time += get_event_time(event, vcpu);
}

static bool event_is_valid(struct kvm_event *event, int vcpu)
{
	return !!get_event_count(event, vcpu);
}

static void sort_result(struct perf_kvm_stat *kvm)
{
	unsigned int i;
	int vcpu = kvm->trace_vcpu;
	struct kvm_event *event;

	for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
		list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry) {
			if (event_is_valid(event, vcpu)) {
				update_total_count(kvm, event);
				insert_to_result(&kvm->result, event,
						 kvm->compare, vcpu);
			}
		}
	}
}

/* returns left most element of result, and erase it */
static struct kvm_event *pop_from_result(struct rb_root *result)
{
	struct rb_node *node = rb_first(result);

	if (!node)
		return NULL;

	rb_erase(node, result);
	return container_of(node, struct kvm_event, rb);
}

static void print_vcpu_info(struct perf_kvm_stat *kvm)
{
	int vcpu = kvm->trace_vcpu;

	pr_info("Analyze events for ");

	if (kvm->live) {
		if (kvm->opts.target.system_wide)
			pr_info("all VMs, ");
		else if (kvm->opts.target.pid)
			pr_info("pid(s) %s, ", kvm->opts.target.pid);
		else
			pr_info("dazed and confused on what is monitored, ");
	}

	if (vcpu == -1)
		pr_info("all VCPUs:\n\n");
	else
		pr_info("VCPU %d:\n\n", vcpu);
}

static void show_timeofday(void)
{
	char date[64];
	struct timeval tv;
	struct tm ltime;

	gettimeofday(&tv, NULL);
	if (localtime_r(&tv.tv_sec, &ltime)) {
		strftime(date, sizeof(date), "%H:%M:%S", &ltime);
		pr_info("%s.%06ld", date, tv.tv_usec);
	} else
		pr_info("00:00:00.000000");

	return;
}

static void print_result(struct perf_kvm_stat *kvm)
{
	char decode[20];
	struct kvm_event *event;
	int vcpu = kvm->trace_vcpu;

	if (kvm->live) {
		puts(CONSOLE_CLEAR);
		show_timeofday();
	}

	pr_info("\n\n");
	print_vcpu_info(kvm);
	pr_info("%20s ", kvm->events_ops->name);
	pr_info("%10s ", "Samples");
	pr_info("%9s ", "Samples%");

	pr_info("%9s ", "Time%");
	pr_info("%10s ", "Min Time");
	pr_info("%10s ", "Max Time");
	pr_info("%16s ", "Avg time");
	pr_info("\n\n");

	while ((event = pop_from_result(&kvm->result))) {
		u64 ecount, etime, max, min;

		ecount = get_event_count(event, vcpu);
		etime = get_event_time(event, vcpu);
		max = get_event_max(event, vcpu);
		min = get_event_min(event, vcpu);

		kvm->events_ops->decode_key(kvm, &event->key, decode);
		pr_info("%20s ", decode);
		pr_info("%10llu ", (unsigned long long)ecount);
		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
		pr_info("%8" PRIu64 "us ", min / 1000);
		pr_info("%8" PRIu64 "us ", max / 1000);
		pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
			kvm_event_rel_stddev(vcpu, event));
		pr_info("\n");
	}

	pr_info("\nTotal Samples:%" PRIu64 ", Total events handled time:%.2fus.\n\n",
		kvm->total_count, kvm->total_time / 1e3);

	if (kvm->lost_events)
		pr_info("\nLost events: %" PRIu64 "\n\n", kvm->lost_events);
}

#ifdef HAVE_TIMERFD_SUPPORT
static int process_lost_event(struct perf_tool *tool,
			      union perf_event *event __maybe_unused,
			      struct perf_sample *sample __maybe_unused,
			      struct machine *machine __maybe_unused)
{
	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat, tool);

	kvm->lost_events++;
	return 0;
}
#endif

static bool skip_sample(struct perf_kvm_stat *kvm,
			struct perf_sample *sample)
{
	if (kvm->pid_list && intlist__find(kvm->pid_list, sample->pid) == NULL)
		return true;

	return false;
}

static int process_sample_event(struct perf_tool *tool,
				union perf_event *event,
				struct perf_sample *sample,
				struct perf_evsel *evsel,
				struct machine *machine)
{
	struct thread *thread;
	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
						 tool);

	if (skip_sample(kvm, sample))
		return 0;

	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
	if (thread == NULL) {
		pr_debug("problem processing %d event, skipping it.\n",
			event->header.type);
		return -1;
	}

	if (!handle_kvm_event(kvm, thread, evsel, sample))
		return -1;

	return 0;
}

static int cpu_isa_config(struct perf_kvm_stat *kvm)
{
	char buf[64], *cpuid;
	int err, isa;

	if (kvm->live) {
		err = get_cpuid(buf, sizeof(buf));
		if (err != 0) {
			pr_err("Failed to look up CPU type (Intel or AMD)\n");
			return err;
		}
		cpuid = buf;
	} else
		cpuid = kvm->session->header.env.cpuid;

	if (strstr(cpuid, "Intel"))
		isa = 1;
	else if (strstr(cpuid, "AMD"))
		isa = 0;
	else {
		pr_err("CPU %s is not supported.\n", cpuid);
		return -ENOTSUP;
	}

	if (isa == 1) {
		kvm->exit_reasons = vmx_exit_reasons;
		kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons);
		kvm->exit_reasons_isa = "VMX";
	}

	return 0;
}

static bool verify_vcpu(int vcpu)
{
	if (vcpu != -1 && vcpu < 0) {
		pr_err("Invalid vcpu:%d.\n", vcpu);
		return false;
	}

	return true;
}

#ifdef HAVE_TIMERFD_SUPPORT
/* keeping the max events to a modest level to keep
 * the processing of samples per mmap smooth.
 */
#define PERF_KVM__MAX_EVENTS_PER_MMAP  25

static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
				   u64 *mmap_time)
{
	union perf_event *event;
	struct perf_sample sample;
	s64 n = 0;
	int err;

	*mmap_time = ULLONG_MAX;
	while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
		err = perf_evlist__parse_sample(kvm->evlist, event, &sample);
		if (err) {
			perf_evlist__mmap_consume(kvm->evlist, idx);
			pr_err("Failed to parse sample\n");
			return -1;
		}

		err = perf_session_queue_event(kvm->session, event, &sample, 0);
		/*
		 * FIXME: Here we can't consume the event, as perf_session_queue_event will
		 *        point to it, and it'll get possibly overwritten by the kernel.
		 */
		perf_evlist__mmap_consume(kvm->evlist, idx);

		if (err) {
			pr_err("Failed to enqueue sample: %d\n", err);
			return -1;
		}

		/* save time stamp of our first sample for this mmap */
		if (n == 0)
			*mmap_time = sample.time;

		/* limit events per mmap handled all at once */
		n++;
		if (n == PERF_KVM__MAX_EVENTS_PER_MMAP)
			break;
	}

	return n;
}

static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
{
	int i, err, throttled = 0;
	s64 n, ntotal = 0;
	u64 flush_time = ULLONG_MAX, mmap_time;

	for (i = 0; i < kvm->evlist->nr_mmaps; i++) {
		n = perf_kvm__mmap_read_idx(kvm, i, &mmap_time);
		if (n < 0)
			return -1;

		/* flush time is going to be the minimum of all the individual
		 * mmap times. Essentially, we flush all the samples queued up
		 * from the last pass under our minimal start time -- that leaves
		 * a very small race for samples to come in with a lower timestamp.
		 * The ioctl to return the perf_clock timestamp should close the
		 * race entirely.
		 */
		if (mmap_time < flush_time)
			flush_time = mmap_time;

		ntotal += n;
		if (n == PERF_KVM__MAX_EVENTS_PER_MMAP)
			throttled = 1;
	}

	/* flush queue after each round in which we processed events */
	if (ntotal) {
		kvm->session->ordered_samples.next_flush = flush_time;
		err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session);
		if (err) {
			if (kvm->lost_events)
				pr_info("\nLost events: %" PRIu64 "\n\n",
					kvm->lost_events);
			return err;
		}
	}

	return throttled;
}

static volatile int done;

static void sig_handler(int sig __maybe_unused)
{
	done = 1;
}

static int perf_kvm__timerfd_create(struct perf_kvm_stat *kvm)
{
	struct itimerspec new_value;
	int rc = -1;

	kvm->timerfd = timerfd_create(CLOCK_MONOTONIC, TFD_NONBLOCK);
	if (kvm->timerfd < 0) {
		pr_err("timerfd_create failed\n");
		goto out;
	}

	new_value.it_value.tv_sec = kvm->display_time;
	new_value.it_value.tv_nsec = 0;
	new_value.it_interval.tv_sec = kvm->display_time;
	new_value.it_interval.tv_nsec = 0;

	if (timerfd_settime(kvm->timerfd, 0, &new_value, NULL) != 0) {
		pr_err("timerfd_settime failed: %d\n", errno);
		close(kvm->timerfd);
		goto out;
	}

	rc = 0;
out:
	return rc;
}

static int perf_kvm__handle_timerfd(struct perf_kvm_stat *kvm)
{
	uint64_t c;
	int rc;

	rc = read(kvm->timerfd, &c, sizeof(uint64_t));
	if (rc < 0) {
		if (errno == EAGAIN)
			return 0;

		pr_err("Failed to read timer fd: %d\n", errno);
		return -1;
	}

	if (rc != sizeof(uint64_t)) {
		pr_err("Error reading timer fd - invalid size returned\n");
		return -1;
	}

	if (c != 1)
		pr_debug("Missed timer beats: %" PRIu64 "\n", c-1);

	/* update display */
	sort_result(kvm);
	print_result(kvm);

	/* reset counts */
	clear_events_cache_stats(kvm->kvm_events_cache);
	kvm->total_count = 0;
	kvm->total_time = 0;
	kvm->lost_events = 0;

	return 0;
}

static int fd_set_nonblock(int fd)
{
	long arg = 0;

	arg = fcntl(fd, F_GETFL);
	if (arg < 0) {
		pr_err("Failed to get current flags for fd %d\n", fd);
		return -1;
	}

	if (fcntl(fd, F_SETFL, arg | O_NONBLOCK) < 0) {
		pr_err("Failed to set non-block option on fd %d\n", fd);
		return -1;
	}

	return 0;
}

static
int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save)
{
	int c;

	tcsetattr(0, TCSANOW, tc_now);
	c = getc(stdin);
	tcsetattr(0, TCSAFLUSH, tc_save);

	if (c == 'q')
		return 1;

	return 0;
}

static int kvm_events_live_report(struct perf_kvm_stat *kvm)
{
	struct pollfd *pollfds = NULL;
	int nr_fds, nr_stdin, ret, err = -EINVAL;
	struct termios tc, save;

	/* live flag must be set first */
	kvm->live = true;

	ret = cpu_isa_config(kvm);
	if (ret < 0)
		return ret;

	if (!verify_vcpu(kvm->trace_vcpu) ||
	    !select_key(kvm) ||
	    !register_kvm_events_ops(kvm)) {
		goto out;
	}

	init_kvm_event_record(kvm);

	tcgetattr(0, &save);
	tc = save;
	tc.c_lflag &= ~(ICANON | ECHO);
	tc.c_cc[VMIN] = 0;
	tc.c_cc[VTIME] = 0;

	signal(SIGINT, sig_handler);
	signal(SIGTERM, sig_handler);

	/* copy pollfds -- need to add timerfd and stdin */
	nr_fds = kvm->evlist->nr_fds;
	pollfds = zalloc(sizeof(struct pollfd) * (nr_fds + 2));
	if (!pollfds) {
		err = -ENOMEM;
		goto out;
	}
	memcpy(pollfds, kvm->evlist->pollfd,
		sizeof(struct pollfd) * kvm->evlist->nr_fds);

	/* add timer fd */
	if (perf_kvm__timerfd_create(kvm) < 0) {
		err = -1;
		goto out;
	}

	pollfds[nr_fds].fd = kvm->timerfd;
	pollfds[nr_fds].events = POLLIN;
	nr_fds++;

	pollfds[nr_fds].fd = fileno(stdin);
	pollfds[nr_fds].events = POLLIN;
	nr_stdin = nr_fds;
	nr_fds++;
	if (fd_set_nonblock(fileno(stdin)) != 0)
		goto out;

	/* everything is good - enable the events and process */
	perf_evlist__enable(kvm->evlist);

	while (!done) {
		int rc;

		rc = perf_kvm__mmap_read(kvm);
		if (rc < 0)
			break;

		err = perf_kvm__handle_timerfd(kvm);
		if (err)
			goto out;

		if (pollfds[nr_stdin].revents & POLLIN)
			done = perf_kvm__handle_stdin(&tc, &save);

		if (!rc && !done)
			err = poll(pollfds, nr_fds, 100);
	}

	perf_evlist__disable(kvm->evlist);

	if (err == 0) {
		sort_result(kvm);
		print_result(kvm);
	}

out:
	if (kvm->timerfd >= 0)
		close(kvm->timerfd);

	if (pollfds)
		free(pollfds);

	return err;
}

static int kvm_live_open_events(struct perf_kvm_stat *kvm)
{
	int err, rc = -1;
	struct perf_evsel *pos;
	struct perf_evlist *evlist = kvm->evlist;

	perf_evlist__config(evlist, &kvm->opts);

	/*
	 * Note: exclude_{guest,host} do not apply here.
	 *       This command processes KVM tracepoints from host only
	 */
	list_for_each_entry(pos, &evlist->entries, node) {
		struct perf_event_attr *attr = &pos->attr;

		/* make sure these *are* set */
		perf_evsel__set_sample_bit(pos, TID);
		perf_evsel__set_sample_bit(pos, TIME);
		perf_evsel__set_sample_bit(pos, CPU);
		perf_evsel__set_sample_bit(pos, RAW);
		/* make sure these are *not*; want as small a sample as possible */
		perf_evsel__reset_sample_bit(pos, PERIOD);
		perf_evsel__reset_sample_bit(pos, IP);
		perf_evsel__reset_sample_bit(pos, CALLCHAIN);
		perf_evsel__reset_sample_bit(pos, ADDR);
		perf_evsel__reset_sample_bit(pos, READ);
		attr->mmap = 0;
		attr->comm = 0;
		attr->task = 0;

		attr->sample_period = 1;

		attr->watermark = 0;
		attr->wakeup_events = 1000;

		/* will enable all once we are ready */
		attr->disabled = 1;
	}

	err = perf_evlist__open(evlist);
	if (err < 0) {
		printf("Couldn't create the events: %s\n", strerror(errno));
		goto out;
	}

	if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
		ui__error("Failed to mmap the events: %s\n", strerror(errno));
		perf_evlist__close(evlist);
		goto out;
	}

	rc = 0;

out:
	return rc;
}
#endif

static int read_events(struct perf_kvm_stat *kvm)
{
	int ret;

	struct perf_tool eops = {
		.sample			= process_sample_event,
		.comm			= perf_event__process_comm,
		.ordered_samples	= true,
	};
	struct perf_data_file file = {
		.path = input_name,
		.mode = PERF_DATA_MODE_READ,
	};

	kvm->tool = eops;
	kvm->session = perf_session__new(&file, false, &kvm->tool);
	if (!kvm->session) {
		pr_err("Initializing perf session failed\n");
		return -EINVAL;
	}

	if (!perf_session__has_traces(kvm->session, "kvm record"))
		return -EINVAL;

	/*
	 * Do not use 'isa' recorded in kvm_exit tracepoint since it is not
	 * traced in the old kernel.
	 */
	ret = cpu_isa_config(kvm);
	if (ret < 0)
		return ret;

	return perf_session__process_events(kvm->session, &kvm->tool);
}

static int parse_target_str(struct perf_kvm_stat *kvm)
{
	if (kvm->pid_str) {
		kvm->pid_list = intlist__new(kvm->pid_str);
		if (kvm->pid_list == NULL) {
			pr_err("Error parsing process id string\n");
			return -EINVAL;
		}
	}

	return 0;
}

static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm)
{
	int ret = -EINVAL;
	int vcpu = kvm->trace_vcpu;

	if (parse_target_str(kvm) != 0)
		goto exit;

	if (!verify_vcpu(vcpu))
		goto exit;

	if (!select_key(kvm))
		goto exit;

	if (!register_kvm_events_ops(kvm))
		goto exit;

	init_kvm_event_record(kvm);
	setup_pager();

	ret = read_events(kvm);
	if (ret)
		goto exit;

	sort_result(kvm);
	print_result(kvm);

exit:
	return ret;
}

static const char * const kvm_events_tp[] = {
	"kvm:kvm_entry",
	"kvm:kvm_exit",
	"kvm:kvm_mmio",
	"kvm:kvm_pio",
};

#define STRDUP_FAIL_EXIT(s)		\
	({	char *_p;		\
	_p = strdup(s);		\
		if (!_p)		\
			return -ENOMEM;	\
		_p;			\
	})

static int
kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
{
	unsigned int rec_argc, i, j;
	const char **rec_argv;
	const char * const record_args[] = {
		"record",
		"-R",
		"-m", "1024",
		"-c", "1",
	};

	rec_argc = ARRAY_SIZE(record_args) + argc + 2 +
		   2 * ARRAY_SIZE(kvm_events_tp);
	rec_argv = calloc(rec_argc + 1, sizeof(char *));

	if (rec_argv == NULL)
		return -ENOMEM;

	for (i = 0; i < ARRAY_SIZE(record_args); i++)
		rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]);

	for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {
		rec_argv[i++] = "-e";
		rec_argv[i++] = STRDUP_FAIL_EXIT(kvm_events_tp[j]);
	}

	rec_argv[i++] = STRDUP_FAIL_EXIT("-o");
	rec_argv[i++] = STRDUP_FAIL_EXIT(kvm->file_name);

	for (j = 1; j < (unsigned int)argc; j++, i++)
		rec_argv[i] = argv[j];

	return cmd_record(i, rec_argv, NULL);
}

static int
kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
{
	const struct option kvm_events_report_options[] = {
		OPT_STRING(0, "event", &kvm->report_event, "report event",
			    "event for reporting: vmexit, mmio, ioport"),
		OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
			    "vcpu id to report"),
		OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
			    "key for sorting: sample(sort by samples number)"
			    " time (sort by avg time)"),
		OPT_STRING('p', "pid", &kvm->pid_str, "pid",
			   "analyze events only for given process id(s)"),
		OPT_END()
	};

	const char * const kvm_events_report_usage[] = {
		"perf kvm stat report [<options>]",
		NULL
	};

	symbol__init();

	if (argc) {
		argc = parse_options(argc, argv,
				     kvm_events_report_options,
				     kvm_events_report_usage, 0);
		if (argc)
			usage_with_options(kvm_events_report_usage,
					   kvm_events_report_options);
	}

	return kvm_events_report_vcpu(kvm);
}

#ifdef HAVE_TIMERFD_SUPPORT
static struct perf_evlist *kvm_live_event_list(void)
{
	struct perf_evlist *evlist;
	char *tp, *name, *sys;
	unsigned int j;
	int err = -1;

	evlist = perf_evlist__new();
	if (evlist == NULL)
		return NULL;

	for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {

		tp = strdup(kvm_events_tp[j]);
		if (tp == NULL)
			goto out;

		/* split tracepoint into subsystem and name */
		sys = tp;
		name = strchr(tp, ':');
		if (name == NULL) {
			pr_err("Error parsing %s tracepoint: subsystem delimiter not found\n",
				kvm_events_tp[j]);
			free(tp);
			goto out;
		}
		*name = '\0';
		name++;

		if (perf_evlist__add_newtp(evlist, sys, name, NULL)) {
			pr_err("Failed to add %s tracepoint to the list\n", kvm_events_tp[j]);
			free(tp);
			goto out;
		}

		free(tp);
	}

	err = 0;

out:
	if (err) {
		perf_evlist__delete(evlist);
		evlist = NULL;
	}

	return evlist;
}

static int kvm_events_live(struct perf_kvm_stat *kvm,
			   int argc, const char **argv)
{
	char errbuf[BUFSIZ];
	int err;

	const struct option live_options[] = {
		OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid",
			"record events on existing process id"),
		OPT_CALLBACK('m', "mmap-pages", &kvm->opts.mmap_pages, "pages",
			"number of mmap data pages",
			perf_evlist__parse_mmap_pages),
		OPT_INCR('v', "verbose", &verbose,
			"be more verbose (show counter open errors, etc)"),
		OPT_BOOLEAN('a', "all-cpus", &kvm->opts.target.system_wide,
			"system-wide collection from all CPUs"),
		OPT_UINTEGER('d', "display", &kvm->display_time,
			"time in seconds between display updates"),
		OPT_STRING(0, "event", &kvm->report_event, "report event",
			"event for reporting: vmexit, mmio, ioport"),
		OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
			"vcpu id to report"),
		OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
			"key for sorting: sample(sort by samples number)"
			" time (sort by avg time)"),
		OPT_U64(0, "duration", &kvm->duration,
		    "show events other than HALT that take longer than duration usecs"),
		OPT_END()
	};
	const char * const live_usage[] = {
		"perf kvm stat live [<options>]",
		NULL
	};
	struct perf_data_file file = {
		.mode = PERF_DATA_MODE_WRITE,
	};


	/* event handling */
	kvm->tool.sample = process_sample_event;
	kvm->tool.comm   = perf_event__process_comm;
	kvm->tool.exit   = perf_event__process_exit;
	kvm->tool.fork   = perf_event__process_fork;
	kvm->tool.lost   = process_lost_event;
	kvm->tool.ordered_samples = true;
	perf_tool__fill_defaults(&kvm->tool);

	/* set defaults */
	kvm->display_time = 1;
	kvm->opts.user_interval = 1;
	kvm->opts.mmap_pages = 512;
	kvm->opts.target.uses_mmap = false;
	kvm->opts.target.uid_str = NULL;
	kvm->opts.target.uid = UINT_MAX;

	symbol__init();
	disable_buildid_cache();

	use_browser = 0;
	setup_browser(false);

	if (argc) {
		argc = parse_options(argc, argv, live_options,
				     live_usage, 0);
		if (argc)
			usage_with_options(live_usage, live_options);
	}

	kvm->duration *= NSEC_PER_USEC;   /* convert usec to nsec */

	/*
	 * target related setups
	 */
	err = target__validate(&kvm->opts.target);
	if (err) {
		target__strerror(&kvm->opts.target, err, errbuf, BUFSIZ);
		ui__warning("%s", errbuf);
	}

	if (target__none(&kvm->opts.target))
		kvm->opts.target.system_wide = true;


	/*
	 * generate the event list
	 */
	kvm->evlist = kvm_live_event_list();
	if (kvm->evlist == NULL) {
		err = -1;
		goto out;
	}

	symbol_conf.nr_events = kvm->evlist->nr_entries;

	if (perf_evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0)
		usage_with_options(live_usage, live_options);

	/*
	 * perf session
	 */
	kvm->session = perf_session__new(&file, false, &kvm->tool);
	if (kvm->session == NULL) {
		err = -ENOMEM;
		goto out;
	}
	kvm->session->evlist = kvm->evlist;
	perf_session__set_id_hdr_size(kvm->session);
	machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
				    kvm->evlist->threads, false);
	err = kvm_live_open_events(kvm);
	if (err)
		goto out;

	err = kvm_events_live_report(kvm);

out:
	exit_browser(0);

	if (kvm->session)
		perf_session__delete(kvm->session);
	kvm->session = NULL;
	if (kvm->evlist) {
		perf_evlist__delete_maps(kvm->evlist);
		perf_evlist__delete(kvm->evlist);
	}

	return err;
}
#endif

static void print_kvm_stat_usage(void)
{
	printf("Usage: perf kvm stat <command>\n\n");

	printf("# Available commands:\n");
	printf("\trecord: record kvm events\n");
	printf("\treport: report statistical data of kvm events\n");
	printf("\tlive:   live reporting of statistical data of kvm events\n");

	printf("\nOtherwise, it is the alias of 'perf stat':\n");
}

static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
{
	struct perf_kvm_stat kvm = {
		.file_name = file_name,

		.trace_vcpu	= -1,
		.report_event	= "vmexit",
		.sort_key	= "sample",

		.exit_reasons = svm_exit_reasons,
		.exit_reasons_size = ARRAY_SIZE(svm_exit_reasons),
		.exit_reasons_isa = "SVM",
	};

	if (argc == 1) {
		print_kvm_stat_usage();
		goto perf_stat;
	}

	if (!strncmp(argv[1], "rec", 3))
		return kvm_events_record(&kvm, argc - 1, argv + 1);

	if (!strncmp(argv[1], "rep", 3))
		return kvm_events_report(&kvm, argc - 1 , argv + 1);

#ifdef HAVE_TIMERFD_SUPPORT
	if (!strncmp(argv[1], "live", 4))
		return kvm_events_live(&kvm, argc - 1 , argv + 1);
#endif

perf_stat:
	return cmd_stat(argc, argv, NULL);
}
#endif

static int __cmd_record(const char *file_name, int argc, const char **argv)
{
	int rec_argc, i = 0, j;
	const char **rec_argv;

	rec_argc = argc + 2;
	rec_argv = calloc(rec_argc + 1, sizeof(char *));
	rec_argv[i++] = strdup("record");
	rec_argv[i++] = strdup("-o");
	rec_argv[i++] = strdup(file_name);
	for (j = 1; j < argc; j++, i++)
		rec_argv[i] = argv[j];

	BUG_ON(i != rec_argc);

	return cmd_record(i, rec_argv, NULL);
}

static int __cmd_report(const char *file_name, int argc, const char **argv)
{
	int rec_argc, i = 0, j;
	const char **rec_argv;

	rec_argc = argc + 2;
	rec_argv = calloc(rec_argc + 1, sizeof(char *));
	rec_argv[i++] = strdup("report");
	rec_argv[i++] = strdup("-i");
	rec_argv[i++] = strdup(file_name);
	for (j = 1; j < argc; j++, i++)
		rec_argv[i] = argv[j];

	BUG_ON(i != rec_argc);

	return cmd_report(i, rec_argv, NULL);
}

static int
__cmd_buildid_list(const char *file_name, int argc, const char **argv)
{
	int rec_argc, i = 0, j;
	const char **rec_argv;

	rec_argc = argc + 2;
	rec_argv = calloc(rec_argc + 1, sizeof(char *));
	rec_argv[i++] = strdup("buildid-list");
	rec_argv[i++] = strdup("-i");
	rec_argv[i++] = strdup(file_name);
	for (j = 1; j < argc; j++, i++)
		rec_argv[i] = argv[j];

	BUG_ON(i != rec_argc);

	return cmd_buildid_list(i, rec_argv, NULL);
}

int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
{
	const char *file_name = NULL;
	const struct option kvm_options[] = {
		OPT_STRING('i', "input", &file_name, "file",
			   "Input file name"),
		OPT_STRING('o', "output", &file_name, "file",
			   "Output file name"),
		OPT_BOOLEAN(0, "guest", &perf_guest,
			    "Collect guest os data"),
		OPT_BOOLEAN(0, "host", &perf_host,
			    "Collect host os data"),
		OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory",
			   "guest mount directory under which every guest os"
			   " instance has a subdir"),
		OPT_STRING(0, "guestvmlinux", &symbol_conf.default_guest_vmlinux_name,
			   "file", "file saving guest os vmlinux"),
		OPT_STRING(0, "guestkallsyms", &symbol_conf.default_guest_kallsyms,
			   "file", "file saving guest os /proc/kallsyms"),
		OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
			   "file", "file saving guest os /proc/modules"),
		OPT_END()
	};


	const char * const kvm_usage[] = {
		"perf kvm [<options>] {top|record|report|diff|buildid-list|stat}",
		NULL
	};

	perf_host  = 0;
	perf_guest = 1;

	argc = parse_options(argc, argv, kvm_options, kvm_usage,
			PARSE_OPT_STOP_AT_NON_OPTION);
	if (!argc)
		usage_with_options(kvm_usage, kvm_options);

	if (!perf_host)
		perf_guest = 1;

	if (!file_name) {
		if (perf_host && !perf_guest)
			file_name = strdup("perf.data.host");
		else if (!perf_host && perf_guest)
			file_name = strdup("perf.data.guest");
		else
			file_name = strdup("perf.data.kvm");

		if (!file_name) {
			pr_err("Failed to allocate memory for filename\n");
			return -ENOMEM;
		}
	}

	if (!strncmp(argv[0], "rec", 3))
		return __cmd_record(file_name, argc, argv);
	else if (!strncmp(argv[0], "rep", 3))
		return __cmd_report(file_name, argc, argv);
	else if (!strncmp(argv[0], "diff", 4))
		return cmd_diff(argc, argv, NULL);
	else if (!strncmp(argv[0], "top", 3))
		return cmd_top(argc, argv, NULL);
	else if (!strncmp(argv[0], "buildid-list", 12))
		return __cmd_buildid_list(file_name, argc, argv);
#if defined(__i386__) || defined(__x86_64__)
	else if (!strncmp(argv[0], "stat", 4))
		return kvm_cmd_stat(file_name, argc, argv);
#endif
	else
		usage_with_options(kvm_usage, kvm_options);

	return 0;
}