summaryrefslogtreecommitdiffstats
path: root/arch/x86/events/intel/lbr.c
blob: 4f70fb6c2c1eb78e35f717ffb3085ee9f459e145 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
// SPDX-License-Identifier: GPL-2.0
#include <linux/perf_event.h>
#include <linux/types.h>

#include <asm/perf_event.h>
#include <asm/msr.h>
#include <asm/insn.h>

#include "../perf_event.h"

/*
 * Intel LBR_SELECT bits
 * Intel Vol3a, April 2011, Section 16.7 Table 16-10
 *
 * Hardware branch filter (not available on all CPUs)
 */
#define LBR_KERNEL_BIT		0 /* do not capture at ring0 */
#define LBR_USER_BIT		1 /* do not capture at ring > 0 */
#define LBR_JCC_BIT		2 /* do not capture conditional branches */
#define LBR_REL_CALL_BIT	3 /* do not capture relative calls */
#define LBR_IND_CALL_BIT	4 /* do not capture indirect calls */
#define LBR_RETURN_BIT		5 /* do not capture near returns */
#define LBR_IND_JMP_BIT		6 /* do not capture indirect jumps */
#define LBR_REL_JMP_BIT		7 /* do not capture relative jumps */
#define LBR_FAR_BIT		8 /* do not capture far branches */
#define LBR_CALL_STACK_BIT	9 /* enable call stack */

/*
 * Following bit only exists in Linux; we mask it out before writing it to
 * the actual MSR. But it helps the constraint perf code to understand
 * that this is a separate configuration.
 */
#define LBR_NO_INFO_BIT	       63 /* don't read LBR_INFO. */

#define LBR_KERNEL	(1 << LBR_KERNEL_BIT)
#define LBR_USER	(1 << LBR_USER_BIT)
#define LBR_JCC		(1 << LBR_JCC_BIT)
#define LBR_REL_CALL	(1 << LBR_REL_CALL_BIT)
#define LBR_IND_CALL	(1 << LBR_IND_CALL_BIT)
#define LBR_RETURN	(1 << LBR_RETURN_BIT)
#define LBR_REL_JMP	(1 << LBR_REL_JMP_BIT)
#define LBR_IND_JMP	(1 << LBR_IND_JMP_BIT)
#define LBR_FAR		(1 << LBR_FAR_BIT)
#define LBR_CALL_STACK	(1 << LBR_CALL_STACK_BIT)
#define LBR_NO_INFO	(1ULL << LBR_NO_INFO_BIT)

#define LBR_PLM (LBR_KERNEL | LBR_USER)

#define LBR_SEL_MASK	0x3ff	/* valid bits in LBR_SELECT */
#define LBR_NOT_SUPP	-1	/* LBR filter not supported */
#define LBR_IGN		0	/* ignored */

#define LBR_ANY		 \
	(LBR_JCC	|\
	 LBR_REL_CALL	|\
	 LBR_IND_CALL	|\
	 LBR_RETURN	|\
	 LBR_REL_JMP	|\
	 LBR_IND_JMP	|\
	 LBR_FAR)

#define LBR_FROM_FLAG_MISPRED	BIT_ULL(63)
#define LBR_FROM_FLAG_IN_TX	BIT_ULL(62)
#define LBR_FROM_FLAG_ABORT	BIT_ULL(61)

#define LBR_FROM_SIGNEXT_2MSB	(BIT_ULL(60) | BIT_ULL(59))

/*
 * x86control flow change classification
 * x86control flow changes include branches, interrupts, traps, faults
 */
enum {
	X86_BR_NONE		= 0,      /* unknown */

	X86_BR_USER		= 1 << 0, /* branch target is user */
	X86_BR_KERNEL		= 1 << 1, /* branch target is kernel */

	X86_BR_CALL		= 1 << 2, /* call */
	X86_BR_RET		= 1 << 3, /* return */
	X86_BR_SYSCALL		= 1 << 4, /* syscall */
	X86_BR_SYSRET		= 1 << 5, /* syscall return */
	X86_BR_INT		= 1 << 6, /* sw interrupt */
	X86_BR_IRET		= 1 << 7, /* return from interrupt */
	X86_BR_JCC		= 1 << 8, /* conditional */
	X86_BR_JMP		= 1 << 9, /* jump */
	X86_BR_IRQ		= 1 << 10,/* hw interrupt or trap or fault */
	X86_BR_IND_CALL		= 1 << 11,/* indirect calls */
	X86_BR_ABORT		= 1 << 12,/* transaction abort */
	X86_BR_IN_TX		= 1 << 13,/* in transaction */
	X86_BR_NO_TX		= 1 << 14,/* not in transaction */
	X86_BR_ZERO_CALL	= 1 << 15,/* zero length call */
	X86_BR_CALL_STACK	= 1 << 16,/* call stack */
	X86_BR_IND_JMP		= 1 << 17,/* indirect jump */

	X86_BR_TYPE_SAVE	= 1 << 18,/* indicate to save branch type */

};

#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
#define X86_BR_ANYTX (X86_BR_NO_TX | X86_BR_IN_TX)

#define X86_BR_ANY       \
	(X86_BR_CALL    |\
	 X86_BR_RET     |\
	 X86_BR_SYSCALL |\
	 X86_BR_SYSRET  |\
	 X86_BR_INT     |\
	 X86_BR_IRET    |\
	 X86_BR_JCC     |\
	 X86_BR_JMP	 |\
	 X86_BR_IRQ	 |\
	 X86_BR_ABORT	 |\
	 X86_BR_IND_CALL |\
	 X86_BR_IND_JMP  |\
	 X86_BR_ZERO_CALL)

#define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)

#define X86_BR_ANY_CALL		 \
	(X86_BR_CALL		|\
	 X86_BR_IND_CALL	|\
	 X86_BR_ZERO_CALL	|\
	 X86_BR_SYSCALL		|\
	 X86_BR_IRQ		|\
	 X86_BR_INT)

/*
 * Intel LBR_CTL bits
 *
 * Hardware branch filter for Arch LBR
 */
#define ARCH_LBR_KERNEL_BIT		1  /* capture at ring0 */
#define ARCH_LBR_USER_BIT		2  /* capture at ring > 0 */
#define ARCH_LBR_CALL_STACK_BIT		3  /* enable call stack */
#define ARCH_LBR_JCC_BIT		16 /* capture conditional branches */
#define ARCH_LBR_REL_JMP_BIT		17 /* capture relative jumps */
#define ARCH_LBR_IND_JMP_BIT		18 /* capture indirect jumps */
#define ARCH_LBR_REL_CALL_BIT		19 /* capture relative calls */
#define ARCH_LBR_IND_CALL_BIT		20 /* capture indirect calls */
#define ARCH_LBR_RETURN_BIT		21 /* capture near returns */
#define ARCH_LBR_OTHER_BRANCH_BIT	22 /* capture other branches */

#define ARCH_LBR_KERNEL			(1ULL << ARCH_LBR_KERNEL_BIT)
#define ARCH_LBR_USER			(1ULL << ARCH_LBR_USER_BIT)
#define ARCH_LBR_CALL_STACK		(1ULL << ARCH_LBR_CALL_STACK_BIT)
#define ARCH_LBR_JCC			(1ULL << ARCH_LBR_JCC_BIT)
#define ARCH_LBR_REL_JMP		(1ULL << ARCH_LBR_REL_JMP_BIT)
#define ARCH_LBR_IND_JMP		(1ULL << ARCH_LBR_IND_JMP_BIT)
#define ARCH_LBR_REL_CALL		(1ULL << ARCH_LBR_REL_CALL_BIT)
#define ARCH_LBR_IND_CALL		(1ULL << ARCH_LBR_IND_CALL_BIT)
#define ARCH_LBR_RETURN			(1ULL << ARCH_LBR_RETURN_BIT)
#define ARCH_LBR_OTHER_BRANCH		(1ULL << ARCH_LBR_OTHER_BRANCH_BIT)

#define ARCH_LBR_ANY			 \
	(ARCH_LBR_JCC			|\
	 ARCH_LBR_REL_JMP		|\
	 ARCH_LBR_IND_JMP		|\
	 ARCH_LBR_REL_CALL		|\
	 ARCH_LBR_IND_CALL		|\
	 ARCH_LBR_RETURN		|\
	 ARCH_LBR_OTHER_BRANCH)

#define ARCH_LBR_CTL_MASK			0x7f000e

static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);

static __always_inline bool is_lbr_call_stack_bit_set(u64 config)
{
	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
		return !!(config & ARCH_LBR_CALL_STACK);

	return !!(config & LBR_CALL_STACK);
}

/*
 * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
 * otherwise it becomes near impossible to get a reliable stack.
 */

static void __intel_pmu_lbr_enable(bool pmi)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	u64 debugctl, lbr_select = 0, orig_debugctl;

	/*
	 * No need to unfreeze manually, as v4 can do that as part
	 * of the GLOBAL_STATUS ack.
	 */
	if (pmi && x86_pmu.version >= 4)
		return;

	/*
	 * No need to reprogram LBR_SELECT in a PMI, as it
	 * did not change.
	 */
	if (cpuc->lbr_sel)
		lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask;
	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && !pmi && cpuc->lbr_sel)
		wrmsrl(MSR_LBR_SELECT, lbr_select);

	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
	orig_debugctl = debugctl;

	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
		debugctl |= DEBUGCTLMSR_LBR;
	/*
	 * LBR callstack does not work well with FREEZE_LBRS_ON_PMI.
	 * If FREEZE_LBRS_ON_PMI is set, PMI near call/return instructions
	 * may cause superfluous increase/decrease of LBR_TOS.
	 */
	if (is_lbr_call_stack_bit_set(lbr_select))
		debugctl &= ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
	else
		debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;

	if (orig_debugctl != debugctl)
		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);

	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
		wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
}

void intel_pmu_lbr_reset_32(void)
{
	int i;

	for (i = 0; i < x86_pmu.lbr_nr; i++)
		wrmsrl(x86_pmu.lbr_from + i, 0);
}

void intel_pmu_lbr_reset_64(void)
{
	int i;

	for (i = 0; i < x86_pmu.lbr_nr; i++) {
		wrmsrl(x86_pmu.lbr_from + i, 0);
		wrmsrl(x86_pmu.lbr_to   + i, 0);
		if (x86_pmu.lbr_has_info)
			wrmsrl(x86_pmu.lbr_info + i, 0);
	}
}

static void intel_pmu_arch_lbr_reset(void)
{
	/* Write to ARCH_LBR_DEPTH MSR, all LBR entries are reset to 0 */
	wrmsrl(MSR_ARCH_LBR_DEPTH, x86_pmu.lbr_nr);
}

void intel_pmu_lbr_reset(void)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

	if (!x86_pmu.lbr_nr)
		return;

	x86_pmu.lbr_reset();

	cpuc->last_task_ctx = NULL;
	cpuc->last_log_id = 0;
	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && cpuc->lbr_select)
		wrmsrl(MSR_LBR_SELECT, 0);
}

/*
 * TOS = most recently recorded branch
 */
static inline u64 intel_pmu_lbr_tos(void)
{
	u64 tos;

	rdmsrl(x86_pmu.lbr_tos, tos);
	return tos;
}

enum {
	LBR_NONE,
	LBR_VALID,
};

/*
 * For format LBR_FORMAT_EIP_FLAGS2, bits 61:62 in MSR_LAST_BRANCH_FROM_x
 * are the TSX flags when TSX is supported, but when TSX is not supported
 * they have no consistent behavior:
 *
 *   - For wrmsr(), bits 61:62 are considered part of the sign extension.
 *   - For HW updates (branch captures) bits 61:62 are always OFF and are not
 *     part of the sign extension.
 *
 * Therefore, if:
 *
 *   1) LBR format LBR_FORMAT_EIP_FLAGS2
 *   2) CPU has no TSX support enabled
 *
 * ... then any value passed to wrmsr() must be sign extended to 63 bits and any
 * value from rdmsr() must be converted to have a 61 bits sign extension,
 * ignoring the TSX flags.
 */
static inline bool lbr_from_signext_quirk_needed(void)
{
	bool tsx_support = boot_cpu_has(X86_FEATURE_HLE) ||
			   boot_cpu_has(X86_FEATURE_RTM);

	return !tsx_support;
}

static DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key);

/* If quirk is enabled, ensure sign extension is 63 bits: */
inline u64 lbr_from_signext_quirk_wr(u64 val)
{
	if (static_branch_unlikely(&lbr_from_quirk_key)) {
		/*
		 * Sign extend into bits 61:62 while preserving bit 63.
		 *
		 * Quirk is enabled when TSX is disabled. Therefore TSX bits
		 * in val are always OFF and must be changed to be sign
		 * extension bits. Since bits 59:60 are guaranteed to be
		 * part of the sign extension bits, we can just copy them
		 * to 61:62.
		 */
		val |= (LBR_FROM_SIGNEXT_2MSB & val) << 2;
	}
	return val;
}

/*
 * If quirk is needed, ensure sign extension is 61 bits:
 */
static u64 lbr_from_signext_quirk_rd(u64 val)
{
	if (static_branch_unlikely(&lbr_from_quirk_key)) {
		/*
		 * Quirk is on when TSX is not enabled. Therefore TSX
		 * flags must be read as OFF.
		 */
		val &= ~(LBR_FROM_FLAG_IN_TX | LBR_FROM_FLAG_ABORT);
	}
	return val;
}

static __always_inline void wrlbr_from(unsigned int idx, u64 val)
{
	val = lbr_from_signext_quirk_wr(val);
	wrmsrl(x86_pmu.lbr_from + idx, val);
}

static __always_inline void wrlbr_to(unsigned int idx, u64 val)
{
	wrmsrl(x86_pmu.lbr_to + idx, val);
}

static __always_inline void wrlbr_info(unsigned int idx, u64 val)
{
	wrmsrl(x86_pmu.lbr_info + idx, val);
}

static __always_inline u64 rdlbr_from(unsigned int idx, struct lbr_entry *lbr)
{
	u64 val;

	if (lbr)
		return lbr->from;

	rdmsrl(x86_pmu.lbr_from + idx, val);

	return lbr_from_signext_quirk_rd(val);
}

static __always_inline u64 rdlbr_to(unsigned int idx, struct lbr_entry *lbr)
{
	u64 val;

	if (lbr)
		return lbr->to;

	rdmsrl(x86_pmu.lbr_to + idx, val);

	return val;
}

static __always_inline u64 rdlbr_info(unsigned int idx, struct lbr_entry *lbr)
{
	u64 val;

	if (lbr)
		return lbr->info;

	rdmsrl(x86_pmu.lbr_info + idx, val);

	return val;
}

static inline void
wrlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info)
{
	wrlbr_from(idx, lbr->from);
	wrlbr_to(idx, lbr->to);
	if (need_info)
		wrlbr_info(idx, lbr->info);
}

static inline bool
rdlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info)
{
	u64 from = rdlbr_from(idx, NULL);

	/* Don't read invalid entry */
	if (!from)
		return false;

	lbr->from = from;
	lbr->to = rdlbr_to(idx, NULL);
	if (need_info)
		lbr->info = rdlbr_info(idx, NULL);

	return true;
}

void intel_pmu_lbr_restore(void *ctx)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct x86_perf_task_context *task_ctx = ctx;
	bool need_info = x86_pmu.lbr_has_info;
	u64 tos = task_ctx->tos;
	unsigned lbr_idx, mask;
	int i;

	mask = x86_pmu.lbr_nr - 1;
	for (i = 0; i < task_ctx->valid_lbrs; i++) {
		lbr_idx = (tos - i) & mask;
		wrlbr_all(&task_ctx->lbr[i], lbr_idx, need_info);
	}

	for (; i < x86_pmu.lbr_nr; i++) {
		lbr_idx = (tos - i) & mask;
		wrlbr_from(lbr_idx, 0);
		wrlbr_to(lbr_idx, 0);
		if (need_info)
			wrlbr_info(lbr_idx, 0);
	}

	wrmsrl(x86_pmu.lbr_tos, tos);

	if (cpuc->lbr_select)
		wrmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
}

static void intel_pmu_arch_lbr_restore(void *ctx)
{
	struct x86_perf_task_context_arch_lbr *task_ctx = ctx;
	struct lbr_entry *entries = task_ctx->entries;
	int i;

	/* Fast reset the LBRs before restore if the call stack is not full. */
	if (!entries[x86_pmu.lbr_nr - 1].from)
		intel_pmu_arch_lbr_reset();

	for (i = 0; i < x86_pmu.lbr_nr; i++) {
		if (!entries[i].from)
			break;
		wrlbr_all(&entries[i], i, true);
	}
}

/*
 * Restore the Architecture LBR state from the xsave area in the perf
 * context data for the task via the XRSTORS instruction.
 */
static void intel_pmu_arch_lbr_xrstors(void *ctx)
{
	struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx;

	xrstors(&task_ctx->xsave, XFEATURE_MASK_LBR);
}

static __always_inline bool lbr_is_reset_in_cstate(void *ctx)
{
	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
		return x86_pmu.lbr_deep_c_reset && !rdlbr_from(0, NULL);

	return !rdlbr_from(((struct x86_perf_task_context *)ctx)->tos, NULL);
}

static void __intel_pmu_lbr_restore(void *ctx)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

	if (task_context_opt(ctx)->lbr_callstack_users == 0 ||
	    task_context_opt(ctx)->lbr_stack_state == LBR_NONE) {
		intel_pmu_lbr_reset();
		return;
	}

	/*
	 * Does not restore the LBR registers, if
	 * - No one else touched them, and
	 * - Was not cleared in Cstate
	 */
	if ((ctx == cpuc->last_task_ctx) &&
	    (task_context_opt(ctx)->log_id == cpuc->last_log_id) &&
	    !lbr_is_reset_in_cstate(ctx)) {
		task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
		return;
	}

	x86_pmu.lbr_restore(ctx);

	task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
}

void intel_pmu_lbr_save(void *ctx)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct x86_perf_task_context *task_ctx = ctx;
	bool need_info = x86_pmu.lbr_has_info;
	unsigned lbr_idx, mask;
	u64 tos;
	int i;

	mask = x86_pmu.lbr_nr - 1;
	tos = intel_pmu_lbr_tos();
	for (i = 0; i < x86_pmu.lbr_nr; i++) {
		lbr_idx = (tos - i) & mask;
		if (!rdlbr_all(&task_ctx->lbr[i], lbr_idx, need_info))
			break;
	}
	task_ctx->valid_lbrs = i;
	task_ctx->tos = tos;

	if (cpuc->lbr_select)
		rdmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
}

static void intel_pmu_arch_lbr_save(void *ctx)
{
	struct x86_perf_task_context_arch_lbr *task_ctx = ctx;
	struct lbr_entry *entries = task_ctx->entries;
	int i;

	for (i = 0; i < x86_pmu.lbr_nr; i++) {
		if (!rdlbr_all(&entries[i], i, true))
			break;
	}

	/* LBR call stack is not full. Reset is required in restore. */
	if (i < x86_pmu.lbr_nr)
		entries[x86_pmu.lbr_nr - 1].from = 0;
}

/*
 * Save the Architecture LBR state to the xsave area in the perf
 * context data for the task via the XSAVES instruction.
 */
static void intel_pmu_arch_lbr_xsaves(void *ctx)
{
	struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx;

	xsaves(&task_ctx->xsave, XFEATURE_MASK_LBR);
}

static void __intel_pmu_lbr_save(void *ctx)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

	if (task_context_opt(ctx)->lbr_callstack_users == 0) {
		task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
		return;
	}

	x86_pmu.lbr_save(ctx);

	task_context_opt(ctx)->lbr_stack_state = LBR_VALID;

	cpuc->last_task_ctx = ctx;
	cpuc->last_log_id = ++task_context_opt(ctx)->log_id;
}

void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
				 struct perf_event_context *next)
{
	void *prev_ctx_data, *next_ctx_data;

	swap(prev->task_ctx_data, next->task_ctx_data);

	/*
	 * Architecture specific synchronization makes sense in
	 * case both prev->task_ctx_data and next->task_ctx_data
	 * pointers are allocated.
	 */

	prev_ctx_data = next->task_ctx_data;
	next_ctx_data = prev->task_ctx_data;

	if (!prev_ctx_data || !next_ctx_data)
		return;

	swap(task_context_opt(prev_ctx_data)->lbr_callstack_users,
	     task_context_opt(next_ctx_data)->lbr_callstack_users);
}

void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	void *task_ctx;

	if (!cpuc->lbr_users)
		return;

	/*
	 * If LBR callstack feature is enabled and the stack was saved when
	 * the task was scheduled out, restore the stack. Otherwise flush
	 * the LBR stack.
	 */
	task_ctx = ctx ? ctx->task_ctx_data : NULL;
	if (task_ctx) {
		if (sched_in)
			__intel_pmu_lbr_restore(task_ctx);
		else
			__intel_pmu_lbr_save(task_ctx);
		return;
	}

	/*
	 * Since a context switch can flip the address space and LBR entries
	 * are not tagged with an identifier, we need to wipe the LBR, even for
	 * per-cpu events. You simply cannot resolve the branches from the old
	 * address space.
	 */
	if (sched_in)
		intel_pmu_lbr_reset();
}

static inline bool branch_user_callstack(unsigned br_sel)
{
	return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK);
}

void intel_pmu_lbr_add(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

	if (!x86_pmu.lbr_nr)
		return;

	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
		cpuc->lbr_select = 1;

	cpuc->br_sel = event->hw.branch_reg.reg;

	if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data)
		task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users++;

	/*
	 * Request pmu::sched_task() callback, which will fire inside the
	 * regular perf event scheduling, so that call will:
	 *
	 *  - restore or wipe; when LBR-callstack,
	 *  - wipe; otherwise,
	 *
	 * when this is from __perf_event_task_sched_in().
	 *
	 * However, if this is from perf_install_in_context(), no such callback
	 * will follow and we'll need to reset the LBR here if this is the
	 * first LBR event.
	 *
	 * The problem is, we cannot tell these cases apart... but we can
	 * exclude the biggest chunk of cases by looking at
	 * event->total_time_running. An event that has accrued runtime cannot
	 * be 'new'. Conversely, a new event can get installed through the
	 * context switch path for the first time.
	 */
	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
		cpuc->lbr_pebs_users++;
	perf_sched_cb_inc(event->ctx->pmu);
	if (!cpuc->lbr_users++ && !event->total_time_running)
		intel_pmu_lbr_reset();
}

void release_lbr_buffers(void)
{
	struct kmem_cache *kmem_cache;
	struct cpu_hw_events *cpuc;
	int cpu;

	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
		return;

	for_each_possible_cpu(cpu) {
		cpuc = per_cpu_ptr(&cpu_hw_events, cpu);
		kmem_cache = x86_get_pmu(cpu)->task_ctx_cache;
		if (kmem_cache && cpuc->lbr_xsave) {
			kmem_cache_free(kmem_cache, cpuc->lbr_xsave);
			cpuc->lbr_xsave = NULL;
		}
	}
}

void reserve_lbr_buffers(void)
{
	struct kmem_cache *kmem_cache;
	struct cpu_hw_events *cpuc;
	int cpu;

	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
		return;

	for_each_possible_cpu(cpu) {
		cpuc = per_cpu_ptr(&cpu_hw_events, cpu);
		kmem_cache = x86_get_pmu(cpu)->task_ctx_cache;
		if (!kmem_cache || cpuc->lbr_xsave)
			continue;

		cpuc->lbr_xsave = kmem_cache_alloc_node(kmem_cache,
							GFP_KERNEL | __GFP_ZERO,
							cpu_to_node(cpu));
	}
}

void intel_pmu_lbr_del(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

	if (!x86_pmu.lbr_nr)
		return;

	if (branch_user_callstack(cpuc->br_sel) &&
	    event->ctx->task_ctx_data)
		task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users--;

	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
		cpuc->lbr_select = 0;

	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
		cpuc->lbr_pebs_users--;
	cpuc->lbr_users--;
	WARN_ON_ONCE(cpuc->lbr_users < 0);
	WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
	perf_sched_cb_dec(event->ctx->pmu);
}

static inline bool vlbr_exclude_host(void)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

	return test_bit(INTEL_PMC_IDX_FIXED_VLBR,
		(unsigned long *)&cpuc->intel_ctrl_guest_mask);
}

void intel_pmu_lbr_enable_all(bool pmi)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

	if (cpuc->lbr_users && !vlbr_exclude_host())
		__intel_pmu_lbr_enable(pmi);
}

void intel_pmu_lbr_disable_all(void)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

	if (cpuc->lbr_users && !vlbr_exclude_host()) {
		if (static_cpu_has(X86_FEATURE_ARCH_LBR))
			return __intel_pmu_arch_lbr_disable();

		__intel_pmu_lbr_disable();
	}
}

void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
{
	unsigned long mask = x86_pmu.lbr_nr - 1;
	struct perf_branch_entry *br = cpuc->lbr_entries;
	u64 tos = intel_pmu_lbr_tos();
	int i;

	for (i = 0; i < x86_pmu.lbr_nr; i++) {
		unsigned long lbr_idx = (tos - i) & mask;
		union {
			struct {
				u32 from;
				u32 to;
			};
			u64     lbr;
		} msr_lastbranch;

		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);

		perf_clear_branch_entry_bitfields(br);

		br->from	= msr_lastbranch.from;
		br->to		= msr_lastbranch.to;
		br++;
	}
	cpuc->lbr_stack.nr = i;
	cpuc->lbr_stack.hw_idx = tos;
}

/*
 * Due to lack of segmentation in Linux the effective address (offset)
 * is the same as the linear address, allowing us to merge the LIP and EIP
 * LBR formats.
 */
void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
{
	bool need_info = false, call_stack = false;
	unsigned long mask = x86_pmu.lbr_nr - 1;
	struct perf_branch_entry *br = cpuc->lbr_entries;
	u64 tos = intel_pmu_lbr_tos();
	int i;
	int out = 0;
	int num = x86_pmu.lbr_nr;

	if (cpuc->lbr_sel) {
		need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
		if (cpuc->lbr_sel->config & LBR_CALL_STACK)
			call_stack = true;
	}

	for (i = 0; i < num; i++) {
		unsigned long lbr_idx = (tos - i) & mask;
		u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0;
		u16 cycles = 0;

		from = rdlbr_from(lbr_idx, NULL);
		to   = rdlbr_to(lbr_idx, NULL);

		/*
		 * Read LBR call stack entries
		 * until invalid entry (0s) is detected.
		 */
		if (call_stack && !from)
			break;

		if (x86_pmu.lbr_has_info) {
			if (need_info) {
				u64 info;

				info = rdlbr_info(lbr_idx, NULL);
				mis = !!(info & LBR_INFO_MISPRED);
				pred = !mis;
				cycles = (info & LBR_INFO_CYCLES);
				if (x86_pmu.lbr_has_tsx) {
					in_tx = !!(info & LBR_INFO_IN_TX);
					abort = !!(info & LBR_INFO_ABORT);
				}
			}
		} else {
			int skip = 0;

			if (x86_pmu.lbr_from_flags) {
				mis = !!(from & LBR_FROM_FLAG_MISPRED);
				pred = !mis;
				skip = 1;
			}
			if (x86_pmu.lbr_has_tsx) {
				in_tx = !!(from & LBR_FROM_FLAG_IN_TX);
				abort = !!(from & LBR_FROM_FLAG_ABORT);
				skip = 3;
			}
			from = (u64)((((s64)from) << skip) >> skip);

			if (x86_pmu.lbr_to_cycles) {
				cycles = ((to >> 48) & LBR_INFO_CYCLES);
				to = (u64)((((s64)to) << 16) >> 16);
			}
		}

		/*
		 * Some CPUs report duplicated abort records,
		 * with the second entry not having an abort bit set.
		 * Skip them here. This loop runs backwards,
		 * so we need to undo the previous record.
		 * If the abort just happened outside the window
		 * the extra entry cannot be removed.
		 */
		if (abort && x86_pmu.lbr_double_abort && out > 0)
			out--;

		perf_clear_branch_entry_bitfields(br+out);
		br[out].from	 = from;
		br[out].to	 = to;
		br[out].mispred	 = mis;
		br[out].predicted = pred;
		br[out].in_tx	 = in_tx;
		br[out].abort	 = abort;
		br[out].cycles	 = cycles;
		out++;
	}
	cpuc->lbr_stack.nr = out;
	cpuc->lbr_stack.hw_idx = tos;
}

static DEFINE_STATIC_KEY_FALSE(x86_lbr_mispred);
static DEFINE_STATIC_KEY_FALSE(x86_lbr_cycles);
static DEFINE_STATIC_KEY_FALSE(x86_lbr_type);

static __always_inline int get_lbr_br_type(u64 info)
{
	int type = 0;

	if (static_branch_likely(&x86_lbr_type))
		type = (info & LBR_INFO_BR_TYPE) >> LBR_INFO_BR_TYPE_OFFSET;

	return type;
}

static __always_inline bool get_lbr_mispred(u64 info)
{
	bool mispred = 0;

	if (static_branch_likely(&x86_lbr_mispred))
		mispred = !!(info & LBR_INFO_MISPRED);

	return mispred;
}

static __always_inline u16 get_lbr_cycles(u64 info)
{
	u16 cycles = info & LBR_INFO_CYCLES;

	if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
	    (!static_branch_likely(&x86_lbr_cycles) ||
	     !(info & LBR_INFO_CYC_CNT_VALID)))
		cycles = 0;

	return cycles;
}

static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
				struct lbr_entry *entries)
{
	struct perf_branch_entry *e;
	struct lbr_entry *lbr;
	u64 from, to, info;
	int i;

	for (i = 0; i < x86_pmu.lbr_nr; i++) {
		lbr = entries ? &entries[i] : NULL;
		e = &cpuc->lbr_entries[i];

		from = rdlbr_from(i, lbr);
		/*
		 * Read LBR entries until invalid entry (0s) is detected.
		 */
		if (!from)
			break;

		to = rdlbr_to(i, lbr);
		info = rdlbr_info(i, lbr);

		perf_clear_branch_entry_bitfields(e);

		e->from		= from;
		e->to		= to;
		e->mispred	= get_lbr_mispred(info);
		e->predicted	= !e->mispred;
		e->in_tx	= !!(info & LBR_INFO_IN_TX);
		e->abort	= !!(info & LBR_INFO_ABORT);
		e->cycles	= get_lbr_cycles(info);
		e->type		= get_lbr_br_type(info);
	}

	cpuc->lbr_stack.nr = i;
}

static void intel_pmu_arch_lbr_read(struct cpu_hw_events *cpuc)
{
	intel_pmu_store_lbr(cpuc, NULL);
}

static void intel_pmu_arch_lbr_read_xsave(struct cpu_hw_events *cpuc)
{
	struct x86_perf_task_context_arch_lbr_xsave *xsave = cpuc->lbr_xsave;

	if (!xsave) {
		intel_pmu_store_lbr(cpuc, NULL);
		return;
	}
	xsaves(&xsave->xsave, XFEATURE_MASK_LBR);

	intel_pmu_store_lbr(cpuc, xsave->lbr.entries);
}

void intel_pmu_lbr_read(void)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

	/*
	 * Don't read when all LBRs users are using adaptive PEBS.
	 *
	 * This could be smarter and actually check the event,
	 * but this simple approach seems to work for now.
	 */
	if (!cpuc->lbr_users || vlbr_exclude_host() ||
	    cpuc->lbr_users == cpuc->lbr_pebs_users)
		return;

	x86_pmu.lbr_read(cpuc);

	intel_pmu_lbr_filter(cpuc);
}

/*
 * SW filter is used:
 * - in case there is no HW filter
 * - in case the HW filter has errata or limitations
 */
static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
{
	u64 br_type = event->attr.branch_sample_type;
	int mask = 0;

	if (br_type & PERF_SAMPLE_BRANCH_USER)
		mask |= X86_BR_USER;

	if (br_type & PERF_SAMPLE_BRANCH_KERNEL)
		mask |= X86_BR_KERNEL;

	/* we ignore BRANCH_HV here */

	if (br_type & PERF_SAMPLE_BRANCH_ANY)
		mask |= X86_BR_ANY;

	if (br_type & PERF_SAMPLE_BRANCH_ANY_CALL)
		mask |= X86_BR_ANY_CALL;

	if (br_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
		mask |= X86_BR_RET | X86_BR_IRET | X86_BR_SYSRET;

	if (br_type & PERF_SAMPLE_BRANCH_IND_CALL)
		mask |= X86_BR_IND_CALL;

	if (br_type & PERF_SAMPLE_BRANCH_ABORT_TX)
		mask |= X86_BR_ABORT;

	if (br_type & PERF_SAMPLE_BRANCH_IN_TX)
		mask |= X86_BR_IN_TX;

	if (br_type & PERF_SAMPLE_BRANCH_NO_TX)
		mask |= X86_BR_NO_TX;

	if (br_type & PERF_SAMPLE_BRANCH_COND)
		mask |= X86_BR_JCC;

	if (br_type & PERF_SAMPLE_BRANCH_CALL_STACK) {
		if (!x86_pmu_has_lbr_callstack())
			return -EOPNOTSUPP;
		if (mask & ~(X86_BR_USER | X86_BR_KERNEL))
			return -EINVAL;
		mask |= X86_BR_CALL | X86_BR_IND_CALL | X86_BR_RET |
			X86_BR_CALL_STACK;
	}

	if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP)
		mask |= X86_BR_IND_JMP;

	if (br_type & PERF_SAMPLE_BRANCH_CALL)
		mask |= X86_BR_CALL | X86_BR_ZERO_CALL;

	if (br_type & PERF_SAMPLE_BRANCH_TYPE_SAVE)
		mask |= X86_BR_TYPE_SAVE;

	/*
	 * stash actual user request into reg, it may
	 * be used by fixup code for some CPU
	 */
	event->hw.branch_reg.reg = mask;
	return 0;
}

/*
 * setup the HW LBR filter
 * Used only when available, may not be enough to disambiguate
 * all branches, may need the help of the SW filter
 */
static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
{
	struct hw_perf_event_extra *reg;
	u64 br_type = event->attr.branch_sample_type;
	u64 mask = 0, v;
	int i;

	for (i = 0; i < PERF_SAMPLE_BRANCH_MAX_SHIFT; i++) {
		if (!(br_type & (1ULL << i)))
			continue;

		v = x86_pmu.lbr_sel_map[i];
		if (v == LBR_NOT_SUPP)
			return -EOPNOTSUPP;

		if (v != LBR_IGN)
			mask |= v;
	}

	reg = &event->hw.branch_reg;
	reg->idx = EXTRA_REG_LBR;

	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
		reg->config = mask;
		return 0;
	}

	/*
	 * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate
	 * in suppress mode. So LBR_SELECT should be set to
	 * (~mask & LBR_SEL_MASK) | (mask & ~LBR_SEL_MASK)
	 * But the 10th bit LBR_CALL_STACK does not operate
	 * in suppress mode.
	 */
	reg->config = mask ^ (x86_pmu.lbr_sel_mask & ~LBR_CALL_STACK);

	if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) &&
	    (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) &&
	    x86_pmu.lbr_has_info)
		reg->config |= LBR_NO_INFO;

	return 0;
}

int intel_pmu_setup_lbr_filter(struct perf_event *event)
{
	int ret = 0;

	/*
	 * no LBR on this PMU
	 */
	if (!x86_pmu.lbr_nr)
		return -EOPNOTSUPP;

	/*
	 * setup SW LBR filter
	 */
	ret = intel_pmu_setup_sw_lbr_filter(event);
	if (ret)
		return ret;

	/*
	 * setup HW LBR filter, if any
	 */
	if (x86_pmu.lbr_sel_map)
		ret = intel_pmu_setup_hw_lbr_filter(event);

	return ret;
}

/*
 * return the type of control flow change at address "from"
 * instruction is not necessarily a branch (in case of interrupt).
 *
 * The branch type returned also includes the priv level of the
 * target of the control flow change (X86_BR_USER, X86_BR_KERNEL).
 *
 * If a branch type is unknown OR the instruction cannot be
 * decoded (e.g., text page not present), then X86_BR_NONE is
 * returned.
 */
static int branch_type(unsigned long from, unsigned long to, int abort)
{
	struct insn insn;
	void *addr;
	int bytes_read, bytes_left;
	int ret = X86_BR_NONE;
	int ext, to_plm, from_plm;
	u8 buf[MAX_INSN_SIZE];
	int is64 = 0;

	to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
	from_plm = kernel_ip(from) ? X86_BR_KERNEL : X86_BR_USER;

	/*
	 * maybe zero if lbr did not fill up after a reset by the time
	 * we get a PMU interrupt
	 */
	if (from == 0 || to == 0)
		return X86_BR_NONE;

	if (abort)
		return X86_BR_ABORT | to_plm;

	if (from_plm == X86_BR_USER) {
		/*
		 * can happen if measuring at the user level only
		 * and we interrupt in a kernel thread, e.g., idle.
		 */
		if (!current->mm)
			return X86_BR_NONE;

		/* may fail if text not present */
		bytes_left = copy_from_user_nmi(buf, (void __user *)from,
						MAX_INSN_SIZE);
		bytes_read = MAX_INSN_SIZE - bytes_left;
		if (!bytes_read)
			return X86_BR_NONE;

		addr = buf;
	} else {
		/*
		 * The LBR logs any address in the IP, even if the IP just
		 * faulted. This means userspace can control the from address.
		 * Ensure we don't blindly read any address by validating it is
		 * a known text address.
		 */
		if (kernel_text_address(from)) {
			addr = (void *)from;
			/*
			 * Assume we can get the maximum possible size
			 * when grabbing kernel data.  This is not
			 * _strictly_ true since we could possibly be
			 * executing up next to a memory hole, but
			 * it is very unlikely to be a problem.
			 */
			bytes_read = MAX_INSN_SIZE;
		} else {
			return X86_BR_NONE;
		}
	}

	/*
	 * decoder needs to know the ABI especially
	 * on 64-bit systems running 32-bit apps
	 */
#ifdef CONFIG_X86_64
	is64 = kernel_ip((unsigned long)addr) || any_64bit_mode(current_pt_regs());
#endif
	insn_init(&insn, addr, bytes_read, is64);
	if (insn_get_opcode(&insn))
		return X86_BR_ABORT;

	switch (insn.opcode.bytes[0]) {
	case 0xf:
		switch (insn.opcode.bytes[1]) {
		case 0x05: /* syscall */
		case 0x34: /* sysenter */
			ret = X86_BR_SYSCALL;
			break;
		case 0x07: /* sysret */
		case 0x35: /* sysexit */
			ret = X86_BR_SYSRET;
			break;
		case 0x80 ... 0x8f: /* conditional */
			ret = X86_BR_JCC;
			break;
		default:
			ret = X86_BR_NONE;
		}
		break;
	case 0x70 ... 0x7f: /* conditional */
		ret = X86_BR_JCC;
		break;
	case 0xc2: /* near ret */
	case 0xc3: /* near ret */
	case 0xca: /* far ret */
	case 0xcb: /* far ret */
		ret = X86_BR_RET;
		break;
	case 0xcf: /* iret */
		ret = X86_BR_IRET;
		break;
	case 0xcc ... 0xce: /* int */
		ret = X86_BR_INT;
		break;
	case 0xe8: /* call near rel */
		if (insn_get_immediate(&insn) || insn.immediate1.value == 0) {
			/* zero length call */
			ret = X86_BR_ZERO_CALL;
			break;
		}
		fallthrough;
	case 0x9a: /* call far absolute */
		ret = X86_BR_CALL;
		break;
	case 0xe0 ... 0xe3: /* loop jmp */
		ret = X86_BR_JCC;
		break;
	case 0xe9 ... 0xeb: /* jmp */
		ret = X86_BR_JMP;
		break;
	case 0xff: /* call near absolute, call far absolute ind */
		if (insn_get_modrm(&insn))
			return X86_BR_ABORT;

		ext = (insn.modrm.bytes[0] >> 3) & 0x7;
		switch (ext) {
		case 2: /* near ind call */
		case 3: /* far ind call */
			ret = X86_BR_IND_CALL;
			break;
		case 4:
		case 5:
			ret = X86_BR_IND_JMP;
			break;
		}
		break;
	default:
		ret = X86_BR_NONE;
	}
	/*
	 * interrupts, traps, faults (and thus ring transition) may
	 * occur on any instructions. Thus, to classify them correctly,
	 * we need to first look at the from and to priv levels. If they
	 * are different and to is in the kernel, then it indicates
	 * a ring transition. If the from instruction is not a ring
	 * transition instr (syscall, systenter, int), then it means
	 * it was a irq, trap or fault.
	 *
	 * we have no way of detecting kernel to kernel faults.
	 */
	if (from_plm == X86_BR_USER && to_plm == X86_BR_KERNEL
	    && ret != X86_BR_SYSCALL && ret != X86_BR_INT)
		ret = X86_BR_IRQ;

	/*
	 * branch priv level determined by target as
	 * is done by HW when LBR_SELECT is implemented
	 */
	if (ret != X86_BR_NONE)
		ret |= to_plm;

	return ret;
}

#define X86_BR_TYPE_MAP_MAX	16

static int branch_map[X86_BR_TYPE_MAP_MAX] = {
	PERF_BR_CALL,		/* X86_BR_CALL */
	PERF_BR_RET,		/* X86_BR_RET */
	PERF_BR_SYSCALL,	/* X86_BR_SYSCALL */
	PERF_BR_SYSRET,		/* X86_BR_SYSRET */
	PERF_BR_UNKNOWN,	/* X86_BR_INT */
	PERF_BR_ERET,		/* X86_BR_IRET */
	PERF_BR_COND,		/* X86_BR_JCC */
	PERF_BR_UNCOND,		/* X86_BR_JMP */
	PERF_BR_IRQ,		/* X86_BR_IRQ */
	PERF_BR_IND_CALL,	/* X86_BR_IND_CALL */
	PERF_BR_UNKNOWN,	/* X86_BR_ABORT */
	PERF_BR_UNKNOWN,	/* X86_BR_IN_TX */
	PERF_BR_UNKNOWN,	/* X86_BR_NO_TX */
	PERF_BR_CALL,		/* X86_BR_ZERO_CALL */
	PERF_BR_UNKNOWN,	/* X86_BR_CALL_STACK */
	PERF_BR_IND,		/* X86_BR_IND_JMP */
};

static int
common_branch_type(int type)
{
	int i;

	type >>= 2; /* skip X86_BR_USER and X86_BR_KERNEL */

	if (type) {
		i = __ffs(type);
		if (i < X86_BR_TYPE_MAP_MAX)
			return branch_map[i];
	}

	return PERF_BR_UNKNOWN;
}

enum {
	ARCH_LBR_BR_TYPE_JCC			= 0,
	ARCH_LBR_BR_TYPE_NEAR_IND_JMP		= 1,
	ARCH_LBR_BR_TYPE_NEAR_REL_JMP		= 2,
	ARCH_LBR_BR_TYPE_NEAR_IND_CALL		= 3,
	ARCH_LBR_BR_TYPE_NEAR_REL_CALL		= 4,
	ARCH_LBR_BR_TYPE_NEAR_RET		= 5,
	ARCH_LBR_BR_TYPE_KNOWN_MAX		= ARCH_LBR_BR_TYPE_NEAR_RET,

	ARCH_LBR_BR_TYPE_MAP_MAX		= 16,
};

static const int arch_lbr_br_type_map[ARCH_LBR_BR_TYPE_MAP_MAX] = {
	[ARCH_LBR_BR_TYPE_JCC]			= X86_BR_JCC,
	[ARCH_LBR_BR_TYPE_NEAR_IND_JMP]		= X86_BR_IND_JMP,
	[ARCH_LBR_BR_TYPE_NEAR_REL_JMP]		= X86_BR_JMP,
	[ARCH_LBR_BR_TYPE_NEAR_IND_CALL]	= X86_BR_IND_CALL,
	[ARCH_LBR_BR_TYPE_NEAR_REL_CALL]	= X86_BR_CALL,
	[ARCH_LBR_BR_TYPE_NEAR_RET]		= X86_BR_RET,
};

/*
 * implement actual branch filter based on user demand.
 * Hardware may not exactly satisfy that request, thus
 * we need to inspect opcodes. Mismatched branches are
 * discarded. Therefore, the number of branches returned
 * in PERF_SAMPLE_BRANCH_STACK sample may vary.
 */
static void
intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
{
	u64 from, to;
	int br_sel = cpuc->br_sel;
	int i, j, type, to_plm;
	bool compress = false;

	/* if sampling all branches, then nothing to filter */
	if (((br_sel & X86_BR_ALL) == X86_BR_ALL) &&
	    ((br_sel & X86_BR_TYPE_SAVE) != X86_BR_TYPE_SAVE))
		return;

	for (i = 0; i < cpuc->lbr_stack.nr; i++) {

		from = cpuc->lbr_entries[i].from;
		to = cpuc->lbr_entries[i].to;
		type = cpuc->lbr_entries[i].type;

		/*
		 * Parse the branch type recorded in LBR_x_INFO MSR.
		 * Doesn't support OTHER_BRANCH decoding for now.
		 * OTHER_BRANCH branch type still rely on software decoding.
		 */
		if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
		    type <= ARCH_LBR_BR_TYPE_KNOWN_MAX) {
			to_plm = kernel_ip(to) ? X86_BR_KERNEL : X86_BR_USER;
			type = arch_lbr_br_type_map[type] | to_plm;
		} else
			type = branch_type(from, to, cpuc->lbr_entries[i].abort);
		if (type != X86_BR_NONE && (br_sel & X86_BR_ANYTX)) {
			if (cpuc->lbr_entries[i].in_tx)
				type |= X86_BR_IN_TX;
			else
				type |= X86_BR_NO_TX;
		}

		/* if type does not correspond, then discard */
		if (type == X86_BR_NONE || (br_sel & type) != type) {
			cpuc->lbr_entries[i].from = 0;
			compress = true;
		}

		if ((br_sel & X86_BR_TYPE_SAVE) == X86_BR_TYPE_SAVE)
			cpuc->lbr_entries[i].type = common_branch_type(type);
	}

	if (!compress)
		return;

	/* remove all entries with from=0 */
	for (i = 0; i < cpuc->lbr_stack.nr; ) {
		if (!cpuc->lbr_entries[i].from) {
			j = i;
			while (++j < cpuc->lbr_stack.nr)
				cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j];
			cpuc->lbr_stack.nr--;
			if (!cpuc->lbr_entries[i].from)
				continue;
		}
		i++;
	}
}

void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);

	/* Cannot get TOS for large PEBS and Arch LBR */
	if (static_cpu_has(X86_FEATURE_ARCH_LBR) ||
	    (cpuc->n_pebs == cpuc->n_large_pebs))
		cpuc->lbr_stack.hw_idx = -1ULL;
	else
		cpuc->lbr_stack.hw_idx = intel_pmu_lbr_tos();

	intel_pmu_store_lbr(cpuc, lbr);
	intel_pmu_lbr_filter(cpuc);
}

/*
 * Map interface branch filters onto LBR filters
 */
static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_REL_JMP
						| LBR_IND_JMP | LBR_FAR,
	/*
	 * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
	 */
	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] =
	 LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
	/*
	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
	 */
	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
	[PERF_SAMPLE_BRANCH_COND_SHIFT]     = LBR_JCC,
	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
};

static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_FAR,
	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
						| LBR_FAR,
	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
	[PERF_SAMPLE_BRANCH_CALL_SHIFT]		= LBR_REL_CALL,
};

static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_FAR,
	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
						| LBR_FAR,
	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
						| LBR_RETURN | LBR_CALL_STACK,
	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
	[PERF_SAMPLE_BRANCH_CALL_SHIFT]		= LBR_REL_CALL,
};

static int arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= ARCH_LBR_ANY,
	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= ARCH_LBR_USER,
	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= ARCH_LBR_KERNEL,
	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= ARCH_LBR_RETURN |
						  ARCH_LBR_OTHER_BRANCH,
	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]     = ARCH_LBR_REL_CALL |
						  ARCH_LBR_IND_CALL |
						  ARCH_LBR_OTHER_BRANCH,
	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]     = ARCH_LBR_IND_CALL,
	[PERF_SAMPLE_BRANCH_COND_SHIFT]         = ARCH_LBR_JCC,
	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]   = ARCH_LBR_REL_CALL |
						  ARCH_LBR_IND_CALL |
						  ARCH_LBR_RETURN |
						  ARCH_LBR_CALL_STACK,
	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= ARCH_LBR_IND_JMP,
	[PERF_SAMPLE_BRANCH_CALL_SHIFT]		= ARCH_LBR_REL_CALL,
};

/* core */
void __init intel_pmu_lbr_init_core(void)
{
	x86_pmu.lbr_nr     = 4;
	x86_pmu.lbr_tos    = MSR_LBR_TOS;
	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;

	/*
	 * SW branch filter usage:
	 * - compensate for lack of HW filter
	 */
}

/* nehalem/westmere */
void __init intel_pmu_lbr_init_nhm(void)
{
	x86_pmu.lbr_nr     = 16;
	x86_pmu.lbr_tos    = MSR_LBR_TOS;
	x86_pmu.lbr_from   = MSR_LBR_NHM_FROM;
	x86_pmu.lbr_to     = MSR_LBR_NHM_TO;

	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
	x86_pmu.lbr_sel_map  = nhm_lbr_sel_map;

	/*
	 * SW branch filter usage:
	 * - workaround LBR_SEL errata (see above)
	 * - support syscall, sysret capture.
	 *   That requires LBR_FAR but that means far
	 *   jmp need to be filtered out
	 */
}

/* sandy bridge */
void __init intel_pmu_lbr_init_snb(void)
{
	x86_pmu.lbr_nr	 = 16;
	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;

	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;

	/*
	 * SW branch filter usage:
	 * - support syscall, sysret capture.
	 *   That requires LBR_FAR but that means far
	 *   jmp need to be filtered out
	 */
}

static inline struct kmem_cache *
create_lbr_kmem_cache(size_t size, size_t align)
{
	return kmem_cache_create("x86_lbr", size, align, 0, NULL);
}

/* haswell */
void intel_pmu_lbr_init_hsw(void)
{
	size_t size = sizeof(struct x86_perf_task_context);

	x86_pmu.lbr_nr	 = 16;
	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;

	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;

	x86_get_pmu(smp_processor_id())->task_ctx_cache = create_lbr_kmem_cache(size, 0);
}

/* skylake */
__init void intel_pmu_lbr_init_skl(void)
{
	size_t size = sizeof(struct x86_perf_task_context);

	x86_pmu.lbr_nr	 = 32;
	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
	x86_pmu.lbr_info = MSR_LBR_INFO_0;

	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
	x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;

	x86_get_pmu(smp_processor_id())->task_ctx_cache = create_lbr_kmem_cache(size, 0);

	/*
	 * SW branch filter usage:
	 * - support syscall, sysret capture.
	 *   That requires LBR_FAR but that means far
	 *   jmp need to be filtered out
	 */
}

/* atom */
void __init intel_pmu_lbr_init_atom(void)
{
	/*
	 * only models starting at stepping 10 seems
	 * to have an operational LBR which can freeze
	 * on PMU interrupt
	 */
	if (boot_cpu_data.x86_model == 28
	    && boot_cpu_data.x86_stepping < 10) {
		pr_cont("LBR disabled due to erratum");
		return;
	}

	x86_pmu.lbr_nr	   = 8;
	x86_pmu.lbr_tos    = MSR_LBR_TOS;
	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;

	/*
	 * SW branch filter usage:
	 * - compensate for lack of HW filter
	 */
}

/* slm */
void __init intel_pmu_lbr_init_slm(void)
{
	x86_pmu.lbr_nr	   = 8;
	x86_pmu.lbr_tos    = MSR_LBR_TOS;
	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;

	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
	x86_pmu.lbr_sel_map  = nhm_lbr_sel_map;

	/*
	 * SW branch filter usage:
	 * - compensate for lack of HW filter
	 */
	pr_cont("8-deep LBR, ");
}

/* Knights Landing */
void intel_pmu_lbr_init_knl(void)
{
	x86_pmu.lbr_nr	   = 8;
	x86_pmu.lbr_tos    = MSR_LBR_TOS;
	x86_pmu.lbr_from   = MSR_LBR_NHM_FROM;
	x86_pmu.lbr_to     = MSR_LBR_NHM_TO;

	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;

	/* Knights Landing does have MISPREDICT bit */
	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
		x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
}

void intel_pmu_lbr_init(void)
{
	switch (x86_pmu.intel_cap.lbr_format) {
	case LBR_FORMAT_EIP_FLAGS2:
		x86_pmu.lbr_has_tsx = 1;
		x86_pmu.lbr_from_flags = 1;
		if (lbr_from_signext_quirk_needed())
			static_branch_enable(&lbr_from_quirk_key);
		break;

	case LBR_FORMAT_EIP_FLAGS:
		x86_pmu.lbr_from_flags = 1;
		break;

	case LBR_FORMAT_INFO:
		x86_pmu.lbr_has_tsx = 1;
		fallthrough;
	case LBR_FORMAT_INFO2:
		x86_pmu.lbr_has_info = 1;
		break;

	case LBR_FORMAT_TIME:
		x86_pmu.lbr_from_flags = 1;
		x86_pmu.lbr_to_cycles = 1;
		break;
	}

	if (x86_pmu.lbr_has_info) {
		/*
		 * Only used in combination with baseline pebs.
		 */
		static_branch_enable(&x86_lbr_mispred);
		static_branch_enable(&x86_lbr_cycles);
	}
}

/*
 * LBR state size is variable based on the max number of registers.
 * This calculates the expected state size, which should match
 * what the hardware enumerates for the size of XFEATURE_LBR.
 */
static inline unsigned int get_lbr_state_size(void)
{
	return sizeof(struct arch_lbr_state) +
	       x86_pmu.lbr_nr * sizeof(struct lbr_entry);
}

static bool is_arch_lbr_xsave_available(void)
{
	if (!boot_cpu_has(X86_FEATURE_XSAVES))
		return false;

	/*
	 * Check the LBR state with the corresponding software structure.
	 * Disable LBR XSAVES support if the size doesn't match.
	 */
	if (xfeature_size(XFEATURE_LBR) == 0)
		return false;

	if (WARN_ON(xfeature_size(XFEATURE_LBR) != get_lbr_state_size()))
		return false;

	return true;
}

void __init intel_pmu_arch_lbr_init(void)
{
	struct pmu *pmu = x86_get_pmu(smp_processor_id());
	union cpuid28_eax eax;
	union cpuid28_ebx ebx;
	union cpuid28_ecx ecx;
	unsigned int unused_edx;
	bool arch_lbr_xsave;
	size_t size;
	u64 lbr_nr;

	/* Arch LBR Capabilities */
	cpuid(28, &eax.full, &ebx.full, &ecx.full, &unused_edx);

	lbr_nr = fls(eax.split.lbr_depth_mask) * 8;
	if (!lbr_nr)
		goto clear_arch_lbr;

	/* Apply the max depth of Arch LBR */
	if (wrmsrl_safe(MSR_ARCH_LBR_DEPTH, lbr_nr))
		goto clear_arch_lbr;

	x86_pmu.lbr_depth_mask = eax.split.lbr_depth_mask;
	x86_pmu.lbr_deep_c_reset = eax.split.lbr_deep_c_reset;
	x86_pmu.lbr_lip = eax.split.lbr_lip;
	x86_pmu.lbr_cpl = ebx.split.lbr_cpl;
	x86_pmu.lbr_filter = ebx.split.lbr_filter;
	x86_pmu.lbr_call_stack = ebx.split.lbr_call_stack;
	x86_pmu.lbr_mispred = ecx.split.lbr_mispred;
	x86_pmu.lbr_timed_lbr = ecx.split.lbr_timed_lbr;
	x86_pmu.lbr_br_type = ecx.split.lbr_br_type;
	x86_pmu.lbr_nr = lbr_nr;

	if (x86_pmu.lbr_mispred)
		static_branch_enable(&x86_lbr_mispred);
	if (x86_pmu.lbr_timed_lbr)
		static_branch_enable(&x86_lbr_cycles);
	if (x86_pmu.lbr_br_type)
		static_branch_enable(&x86_lbr_type);

	arch_lbr_xsave = is_arch_lbr_xsave_available();
	if (arch_lbr_xsave) {
		size = sizeof(struct x86_perf_task_context_arch_lbr_xsave) +
		       get_lbr_state_size();
		pmu->task_ctx_cache = create_lbr_kmem_cache(size,
							    XSAVE_ALIGNMENT);
	}

	if (!pmu->task_ctx_cache) {
		arch_lbr_xsave = false;

		size = sizeof(struct x86_perf_task_context_arch_lbr) +
		       lbr_nr * sizeof(struct lbr_entry);
		pmu->task_ctx_cache = create_lbr_kmem_cache(size, 0);
	}

	x86_pmu.lbr_from = MSR_ARCH_LBR_FROM_0;
	x86_pmu.lbr_to = MSR_ARCH_LBR_TO_0;
	x86_pmu.lbr_info = MSR_ARCH_LBR_INFO_0;

	/* LBR callstack requires both CPL and Branch Filtering support */
	if (!x86_pmu.lbr_cpl ||
	    !x86_pmu.lbr_filter ||
	    !x86_pmu.lbr_call_stack)
		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_NOT_SUPP;

	if (!x86_pmu.lbr_cpl) {
		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_NOT_SUPP;
		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_NOT_SUPP;
	} else if (!x86_pmu.lbr_filter) {
		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_NOT_SUPP;
		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_NOT_SUPP;
		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_NOT_SUPP;
		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_NOT_SUPP;
		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_NOT_SUPP;
		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_NOT_SUPP;
		arch_lbr_ctl_map[PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_NOT_SUPP;
	}

	x86_pmu.lbr_ctl_mask = ARCH_LBR_CTL_MASK;
	x86_pmu.lbr_ctl_map  = arch_lbr_ctl_map;

	if (!x86_pmu.lbr_cpl && !x86_pmu.lbr_filter)
		x86_pmu.lbr_ctl_map = NULL;

	x86_pmu.lbr_reset = intel_pmu_arch_lbr_reset;
	if (arch_lbr_xsave) {
		x86_pmu.lbr_save = intel_pmu_arch_lbr_xsaves;
		x86_pmu.lbr_restore = intel_pmu_arch_lbr_xrstors;
		x86_pmu.lbr_read = intel_pmu_arch_lbr_read_xsave;
		pr_cont("XSAVE ");
	} else {
		x86_pmu.lbr_save = intel_pmu_arch_lbr_save;
		x86_pmu.lbr_restore = intel_pmu_arch_lbr_restore;
		x86_pmu.lbr_read = intel_pmu_arch_lbr_read;
	}

	pr_cont("Architectural LBR, ");

	return;

clear_arch_lbr:
	clear_cpu_cap(&boot_cpu_data, X86_FEATURE_ARCH_LBR);
}

/**
 * x86_perf_get_lbr - get the LBR records information
 *
 * @lbr: the caller's memory to store the LBR records information
 *
 * Returns: 0 indicates the LBR info has been successfully obtained
 */
int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
{
	int lbr_fmt = x86_pmu.intel_cap.lbr_format;

	lbr->nr = x86_pmu.lbr_nr;
	lbr->from = x86_pmu.lbr_from;
	lbr->to = x86_pmu.lbr_to;
	lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0;

	return 0;
}
EXPORT_SYMBOL_GPL(x86_perf_get_lbr);

struct event_constraint vlbr_constraint =
	__EVENT_CONSTRAINT(INTEL_FIXED_VLBR_EVENT, (1ULL << INTEL_PMC_IDX_FIXED_VLBR),
			  FIXED_EVENT_FLAGS, 1, 0, PERF_X86_EVENT_LBR_SELECT);