summaryrefslogtreecommitdiffstats
path: root/arch/x86/events/intel/ds.c
blob: 2c8db2c19328bcbf95e8c14b4f58e0d2d6d7d7ba (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
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
// SPDX-License-Identifier: GPL-2.0
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/slab.h>

#include <asm/cpu_entry_area.h>
#include <asm/perf_event.h>
#include <asm/tlbflush.h>
#include <asm/insn.h>

#include "../perf_event.h"

/* Waste a full page so it can be mapped into the cpu_entry_area */
DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);

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

#define PEBS_FIXUP_SIZE		PAGE_SIZE

/*
 * pebs_record_32 for p4 and core not supported

struct pebs_record_32 {
	u32 flags, ip;
	u32 ax, bc, cx, dx;
	u32 si, di, bp, sp;
};

 */

union intel_x86_pebs_dse {
	u64 val;
	struct {
		unsigned int ld_dse:4;
		unsigned int ld_stlb_miss:1;
		unsigned int ld_locked:1;
		unsigned int ld_reserved:26;
	};
	struct {
		unsigned int st_l1d_hit:1;
		unsigned int st_reserved1:3;
		unsigned int st_stlb_miss:1;
		unsigned int st_locked:1;
		unsigned int st_reserved2:26;
	};
};


/*
 * Map PEBS Load Latency Data Source encodings to generic
 * memory data source information
 */
#define P(a, b) PERF_MEM_S(a, b)
#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
#define LEVEL(x) P(LVLNUM, x)
#define REM P(REMOTE, REMOTE)
#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))

/* Version for Sandy Bridge and later */
static u64 pebs_data_source[] = {
	P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
	OP_LH | P(LVL, L1)  | LEVEL(L1) | P(SNOOP, NONE),  /* 0x01: L1 local */
	OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */
	OP_LH | P(LVL, L2)  | LEVEL(L2) | P(SNOOP, NONE),  /* 0x03: L2 hit */
	OP_LH | P(LVL, L3)  | LEVEL(L3) | P(SNOOP, NONE),  /* 0x04: L3 hit */
	OP_LH | P(LVL, L3)  | LEVEL(L3) | P(SNOOP, MISS),  /* 0x05: L3 hit, snoop miss */
	OP_LH | P(LVL, L3)  | LEVEL(L3) | P(SNOOP, HIT),   /* 0x06: L3 hit, snoop hit */
	OP_LH | P(LVL, L3)  | LEVEL(L3) | P(SNOOP, HITM),  /* 0x07: L3 hit, snoop hitm */
	OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HIT),  /* 0x08: L3 miss snoop hit */
	OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/
	OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | P(SNOOP, HIT),       /* 0x0a: L3 miss, shared */
	OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT),  /* 0x0b: L3 miss, shared */
	OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | SNOOP_NONE_MISS,     /* 0x0c: L3 miss, excl */
	OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* 0x0d: L3 miss, excl */
	OP_LH | P(LVL, IO)  | LEVEL(NA) | P(SNOOP, NONE), /* 0x0e: I/O */
	OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* 0x0f: uncached */
};

/* Patch up minor differences in the bits */
void __init intel_pmu_pebs_data_source_nhm(void)
{
	pebs_data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
	pebs_data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
	pebs_data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
}

void __init intel_pmu_pebs_data_source_skl(bool pmem)
{
	u64 pmem_or_l4 = pmem ? LEVEL(PMEM) : LEVEL(L4);

	pebs_data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT);
	pebs_data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT);
	pebs_data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE);
	pebs_data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD);
	pebs_data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM);
}

static u64 precise_store_data(u64 status)
{
	union intel_x86_pebs_dse dse;
	u64 val = P(OP, STORE) | P(SNOOP, NA) | P(LVL, L1) | P(TLB, L2);

	dse.val = status;

	/*
	 * bit 4: TLB access
	 * 1 = stored missed 2nd level TLB
	 *
	 * so it either hit the walker or the OS
	 * otherwise hit 2nd level TLB
	 */
	if (dse.st_stlb_miss)
		val |= P(TLB, MISS);
	else
		val |= P(TLB, HIT);

	/*
	 * bit 0: hit L1 data cache
	 * if not set, then all we know is that
	 * it missed L1D
	 */
	if (dse.st_l1d_hit)
		val |= P(LVL, HIT);
	else
		val |= P(LVL, MISS);

	/*
	 * bit 5: Locked prefix
	 */
	if (dse.st_locked)
		val |= P(LOCK, LOCKED);

	return val;
}

static u64 precise_datala_hsw(struct perf_event *event, u64 status)
{
	union perf_mem_data_src dse;

	dse.val = PERF_MEM_NA;

	if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
		dse.mem_op = PERF_MEM_OP_STORE;
	else if (event->hw.flags & PERF_X86_EVENT_PEBS_LD_HSW)
		dse.mem_op = PERF_MEM_OP_LOAD;

	/*
	 * L1 info only valid for following events:
	 *
	 * MEM_UOPS_RETIRED.STLB_MISS_STORES
	 * MEM_UOPS_RETIRED.LOCK_STORES
	 * MEM_UOPS_RETIRED.SPLIT_STORES
	 * MEM_UOPS_RETIRED.ALL_STORES
	 */
	if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) {
		if (status & 1)
			dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
		else
			dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS;
	}
	return dse.val;
}

static u64 load_latency_data(u64 status)
{
	union intel_x86_pebs_dse dse;
	u64 val;

	dse.val = status;

	/*
	 * use the mapping table for bit 0-3
	 */
	val = pebs_data_source[dse.ld_dse];

	/*
	 * Nehalem models do not support TLB, Lock infos
	 */
	if (x86_pmu.pebs_no_tlb) {
		val |= P(TLB, NA) | P(LOCK, NA);
		return val;
	}
	/*
	 * bit 4: TLB access
	 * 0 = did not miss 2nd level TLB
	 * 1 = missed 2nd level TLB
	 */
	if (dse.ld_stlb_miss)
		val |= P(TLB, MISS) | P(TLB, L2);
	else
		val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);

	/*
	 * bit 5: locked prefix
	 */
	if (dse.ld_locked)
		val |= P(LOCK, LOCKED);

	return val;
}

struct pebs_record_core {
	u64 flags, ip;
	u64 ax, bx, cx, dx;
	u64 si, di, bp, sp;
	u64 r8,  r9,  r10, r11;
	u64 r12, r13, r14, r15;
};

struct pebs_record_nhm {
	u64 flags, ip;
	u64 ax, bx, cx, dx;
	u64 si, di, bp, sp;
	u64 r8,  r9,  r10, r11;
	u64 r12, r13, r14, r15;
	u64 status, dla, dse, lat;
};

/*
 * Same as pebs_record_nhm, with two additional fields.
 */
struct pebs_record_hsw {
	u64 flags, ip;
	u64 ax, bx, cx, dx;
	u64 si, di, bp, sp;
	u64 r8,  r9,  r10, r11;
	u64 r12, r13, r14, r15;
	u64 status, dla, dse, lat;
	u64 real_ip, tsx_tuning;
};

union hsw_tsx_tuning {
	struct {
		u32 cycles_last_block     : 32,
		    hle_abort		  : 1,
		    rtm_abort		  : 1,
		    instruction_abort     : 1,
		    non_instruction_abort : 1,
		    retry		  : 1,
		    data_conflict	  : 1,
		    capacity_writes	  : 1,
		    capacity_reads	  : 1;
	};
	u64	    value;
};

#define PEBS_HSW_TSX_FLAGS	0xff00000000ULL

/* Same as HSW, plus TSC */

struct pebs_record_skl {
	u64 flags, ip;
	u64 ax, bx, cx, dx;
	u64 si, di, bp, sp;
	u64 r8,  r9,  r10, r11;
	u64 r12, r13, r14, r15;
	u64 status, dla, dse, lat;
	u64 real_ip, tsx_tuning;
	u64 tsc;
};

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

	if (!ds)
		return;

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

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

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

static DEFINE_PER_CPU(void *, insn_buffer);

static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot)
{
	unsigned long start = (unsigned long)cea;
	phys_addr_t pa;
	size_t msz = 0;

	pa = virt_to_phys(addr);

	preempt_disable();
	for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE)
		cea_set_pte(cea, pa, prot);

	/*
	 * This is a cross-CPU update of the cpu_entry_area, we must shoot down
	 * all TLB entries for it.
	 */
	flush_tlb_kernel_range(start, start + size);
	preempt_enable();
}

static void ds_clear_cea(void *cea, size_t size)
{
	unsigned long start = (unsigned long)cea;
	size_t msz = 0;

	preempt_disable();
	for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE)
		cea_set_pte(cea, 0, PAGE_NONE);

	flush_tlb_kernel_range(start, start + size);
	preempt_enable();
}

static void *dsalloc_pages(size_t size, gfp_t flags, int cpu)
{
	unsigned int order = get_order(size);
	int node = cpu_to_node(cpu);
	struct page *page;

	page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
	return page ? page_address(page) : NULL;
}

static void dsfree_pages(const void *buffer, size_t size)
{
	if (buffer)
		free_pages((unsigned long)buffer, get_order(size));
}

static int alloc_pebs_buffer(int cpu)
{
	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
	struct debug_store *ds = hwev->ds;
	size_t bsiz = x86_pmu.pebs_buffer_size;
	int max, node = cpu_to_node(cpu);
	void *buffer, *insn_buff, *cea;

	if (!x86_pmu.pebs)
		return 0;

	buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
	if (unlikely(!buffer))
		return -ENOMEM;

	/*
	 * HSW+ already provides us the eventing ip; no need to allocate this
	 * buffer then.
	 */
	if (x86_pmu.intel_cap.pebs_format < 2) {
		insn_buff = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
		if (!insn_buff) {
			dsfree_pages(buffer, bsiz);
			return -ENOMEM;
		}
		per_cpu(insn_buffer, cpu) = insn_buff;
	}
	hwev->ds_pebs_vaddr = buffer;
	/* Update the cpu entry area mapping */
	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
	ds->pebs_buffer_base = (unsigned long) cea;
	ds_update_cea(cea, buffer, bsiz, PAGE_KERNEL);
	ds->pebs_index = ds->pebs_buffer_base;
	max = x86_pmu.pebs_record_size * (bsiz / x86_pmu.pebs_record_size);
	ds->pebs_absolute_maximum = ds->pebs_buffer_base + max;
	return 0;
}

static void release_pebs_buffer(int cpu)
{
	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
	void *cea;

	if (!x86_pmu.pebs)
		return;

	kfree(per_cpu(insn_buffer, cpu));
	per_cpu(insn_buffer, cpu) = NULL;

	/* Clear the fixmap */
	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
	ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
	dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size);
	hwev->ds_pebs_vaddr = NULL;
}

static int alloc_bts_buffer(int cpu)
{
	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
	struct debug_store *ds = hwev->ds;
	void *buffer, *cea;
	int max;

	if (!x86_pmu.bts)
		return 0;

	buffer = dsalloc_pages(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, cpu);
	if (unlikely(!buffer)) {
		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
		return -ENOMEM;
	}
	hwev->ds_bts_vaddr = buffer;
	/* Update the fixmap */
	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
	ds->bts_buffer_base = (unsigned long) cea;
	ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
	ds->bts_index = ds->bts_buffer_base;
	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
	ds->bts_absolute_maximum = ds->bts_buffer_base +
					max * BTS_RECORD_SIZE;
	ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
					(max / 16) * BTS_RECORD_SIZE;
	return 0;
}

static void release_bts_buffer(int cpu)
{
	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
	void *cea;

	if (!x86_pmu.bts)
		return;

	/* Clear the fixmap */
	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
	ds_clear_cea(cea, BTS_BUFFER_SIZE);
	dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE);
	hwev->ds_bts_vaddr = NULL;
}

static int alloc_ds_buffer(int cpu)
{
	struct debug_store *ds = &get_cpu_entry_area(cpu)->cpu_debug_store;

	memset(ds, 0, sizeof(*ds));
	per_cpu(cpu_hw_events, cpu).ds = ds;
	return 0;
}

static void release_ds_buffer(int cpu)
{
	per_cpu(cpu_hw_events, cpu).ds = NULL;
}

void release_ds_buffers(void)
{
	int cpu;

	if (!x86_pmu.bts && !x86_pmu.pebs)
		return;

	for_each_possible_cpu(cpu)
		release_ds_buffer(cpu);

	for_each_possible_cpu(cpu) {
		/*
		 * Again, ignore errors from offline CPUs, they will no longer
		 * observe cpu_hw_events.ds and not program the DS_AREA when
		 * they come up.
		 */
		fini_debug_store_on_cpu(cpu);
	}

	for_each_possible_cpu(cpu) {
		release_pebs_buffer(cpu);
		release_bts_buffer(cpu);
	}
}

void reserve_ds_buffers(void)
{
	int bts_err = 0, pebs_err = 0;
	int cpu;

	x86_pmu.bts_active = 0;
	x86_pmu.pebs_active = 0;

	if (!x86_pmu.bts && !x86_pmu.pebs)
		return;

	if (!x86_pmu.bts)
		bts_err = 1;

	if (!x86_pmu.pebs)
		pebs_err = 1;

	for_each_possible_cpu(cpu) {
		if (alloc_ds_buffer(cpu)) {
			bts_err = 1;
			pebs_err = 1;
		}

		if (!bts_err && alloc_bts_buffer(cpu))
			bts_err = 1;

		if (!pebs_err && alloc_pebs_buffer(cpu))
			pebs_err = 1;

		if (bts_err && pebs_err)
			break;
	}

	if (bts_err) {
		for_each_possible_cpu(cpu)
			release_bts_buffer(cpu);
	}

	if (pebs_err) {
		for_each_possible_cpu(cpu)
			release_pebs_buffer(cpu);
	}

	if (bts_err && pebs_err) {
		for_each_possible_cpu(cpu)
			release_ds_buffer(cpu);
	} else {
		if (x86_pmu.bts && !bts_err)
			x86_pmu.bts_active = 1;

		if (x86_pmu.pebs && !pebs_err)
			x86_pmu.pebs_active = 1;

		for_each_possible_cpu(cpu) {
			/*
			 * Ignores wrmsr_on_cpu() errors for offline CPUs they
			 * will get this call through intel_pmu_cpu_starting().
			 */
			init_debug_store_on_cpu(cpu);
		}
	}
}

/*
 * BTS
 */

struct event_constraint bts_constraint =
	EVENT_CONSTRAINT(0, 1ULL << INTEL_PMC_IDX_FIXED_BTS, 0);

void intel_pmu_enable_bts(u64 config)
{
	unsigned long debugctlmsr;

	debugctlmsr = get_debugctlmsr();

	debugctlmsr |= DEBUGCTLMSR_TR;
	debugctlmsr |= DEBUGCTLMSR_BTS;
	if (config & ARCH_PERFMON_EVENTSEL_INT)
		debugctlmsr |= DEBUGCTLMSR_BTINT;

	if (!(config & ARCH_PERFMON_EVENTSEL_OS))
		debugctlmsr |= DEBUGCTLMSR_BTS_OFF_OS;

	if (!(config & ARCH_PERFMON_EVENTSEL_USR))
		debugctlmsr |= DEBUGCTLMSR_BTS_OFF_USR;

	update_debugctlmsr(debugctlmsr);
}

void intel_pmu_disable_bts(void)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	unsigned long debugctlmsr;

	if (!cpuc->ds)
		return;

	debugctlmsr = get_debugctlmsr();

	debugctlmsr &=
		~(DEBUGCTLMSR_TR | DEBUGCTLMSR_BTS | DEBUGCTLMSR_BTINT |
		  DEBUGCTLMSR_BTS_OFF_OS | DEBUGCTLMSR_BTS_OFF_USR);

	update_debugctlmsr(debugctlmsr);
}

int intel_pmu_drain_bts_buffer(void)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct debug_store *ds = cpuc->ds;
	struct bts_record {
		u64	from;
		u64	to;
		u64	flags;
	};
	struct perf_event *event = cpuc->events[INTEL_PMC_IDX_FIXED_BTS];
	struct bts_record *at, *base, *top;
	struct perf_output_handle handle;
	struct perf_event_header header;
	struct perf_sample_data data;
	unsigned long skip = 0;
	struct pt_regs regs;

	if (!event)
		return 0;

	if (!x86_pmu.bts_active)
		return 0;

	base = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
	top  = (struct bts_record *)(unsigned long)ds->bts_index;

	if (top <= base)
		return 0;

	memset(&regs, 0, sizeof(regs));

	ds->bts_index = ds->bts_buffer_base;

	perf_sample_data_init(&data, 0, event->hw.last_period);

	/*
	 * BTS leaks kernel addresses in branches across the cpl boundary,
	 * such as traps or system calls, so unless the user is asking for
	 * kernel tracing (and right now it's not possible), we'd need to
	 * filter them out. But first we need to count how many of those we
	 * have in the current batch. This is an extra O(n) pass, however,
	 * it's much faster than the other one especially considering that
	 * n <= 2560 (BTS_BUFFER_SIZE / BTS_RECORD_SIZE * 15/16; see the
	 * alloc_bts_buffer()).
	 */
	for (at = base; at < top; at++) {
		/*
		 * Note that right now *this* BTS code only works if
		 * attr::exclude_kernel is set, but let's keep this extra
		 * check here in case that changes.
		 */
		if (event->attr.exclude_kernel &&
		    (kernel_ip(at->from) || kernel_ip(at->to)))
			skip++;
	}

	/*
	 * Prepare a generic sample, i.e. fill in the invariant fields.
	 * We will overwrite the from and to address before we output
	 * the sample.
	 */
	rcu_read_lock();
	perf_prepare_sample(&header, &data, event, &regs);

	if (perf_output_begin(&handle, event, header.size *
			      (top - base - skip)))
		goto unlock;

	for (at = base; at < top; at++) {
		/* Filter out any records that contain kernel addresses. */
		if (event->attr.exclude_kernel &&
		    (kernel_ip(at->from) || kernel_ip(at->to)))
			continue;

		data.ip		= at->from;
		data.addr	= at->to;

		perf_output_sample(&handle, &header, &data, event);
	}

	perf_output_end(&handle);

	/* There's new data available. */
	event->hw.interrupts++;
	event->pending_kill = POLL_IN;
unlock:
	rcu_read_unlock();
	return 1;
}

static inline void intel_pmu_drain_pebs_buffer(void)
{
	struct pt_regs regs;

	x86_pmu.drain_pebs(&regs);
}

/*
 * PEBS
 */
struct event_constraint intel_core2_pebs_event_constraints[] = {
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01),
	EVENT_CONSTRAINT_END
};

struct event_constraint intel_atom_pebs_event_constraints[] = {
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01),
	/* Allow all events as PEBS with no flags */
	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
	EVENT_CONSTRAINT_END
};

struct event_constraint intel_slm_pebs_event_constraints[] = {
	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x1),
	/* Allow all events as PEBS with no flags */
	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
	EVENT_CONSTRAINT_END
};

struct event_constraint intel_glm_pebs_event_constraints[] = {
	/* Allow all events as PEBS with no flags */
	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
	EVENT_CONSTRAINT_END
};

struct event_constraint intel_nehalem_pebs_event_constraints[] = {
	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf),    /* INST_RETIRED.ANY */
	INTEL_EVENT_CONSTRAINT(0xc2, 0xf),    /* UOPS_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf),    /* SSEX_UOPS_RETIRED.* */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
	EVENT_CONSTRAINT_END
};

struct event_constraint intel_westmere_pebs_event_constraints[] = {
	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf),    /* INSTR_RETIRED.* */
	INTEL_EVENT_CONSTRAINT(0xc2, 0xf),    /* UOPS_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf),    /* SSEX_UOPS_RETIRED.* */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
	EVENT_CONSTRAINT_END
};

struct event_constraint intel_snb_pebs_event_constraints[] = {
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
        INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
        INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
        INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
        INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
	/* Allow all events as PEBS with no flags */
	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
	EVENT_CONSTRAINT_END
};

struct event_constraint intel_ivb_pebs_event_constraints[] = {
        INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
        INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
	INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
	/* Allow all events as PEBS with no flags */
	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
        EVENT_CONSTRAINT_END
};

struct event_constraint intel_hsw_pebs_event_constraints[] = {
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(0xd2, 0xf),    /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(0xd3, 0xf),    /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */
	/* Allow all events as PEBS with no flags */
	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
	EVENT_CONSTRAINT_END
};

struct event_constraint intel_bdw_pebs_event_constraints[] = {
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf),    /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf),    /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */
	/* Allow all events as PEBS with no flags */
	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
	EVENT_CONSTRAINT_END
};


struct event_constraint intel_skl_pebs_event_constraints[] = {
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
	/* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
	INTEL_PLD_CONSTRAINT(0x1cd, 0xf),		      /* MEM_TRANS_RETIRED.* */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x22d0, 0xf), /* MEM_INST_RETIRED.LOCK_STORES */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */
	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf),    /* MEM_LOAD_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf),    /* MEM_LOAD_L3_HIT_RETIRED.* */
	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf),    /* MEM_LOAD_L3_MISS_RETIRED.* */
	/* Allow all events as PEBS with no flags */
	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
	EVENT_CONSTRAINT_END
};

struct event_constraint intel_icl_pebs_event_constraints[] = {
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL),	/* SLOTS */

	INTEL_PLD_CONSTRAINT(0x1cd, 0xff),			/* MEM_TRANS_RETIRED.LOAD_LATENCY */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf),	/* MEM_INST_RETIRED.LOAD */
	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf),	/* MEM_INST_RETIRED.STORE */

	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */

	INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf),		/* MEM_INST_RETIRED.* */

	/*
	 * Everything else is handled by PMU_FL_PEBS_ALL, because we
	 * need the full constraints from the main table.
	 */

	EVENT_CONSTRAINT_END
};

struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
	struct event_constraint *c;

	if (!event->attr.precise_ip)
		return NULL;

	if (x86_pmu.pebs_constraints) {
		for_each_event_constraint(c, x86_pmu.pebs_constraints) {
			if (constraint_match(c, event->hw.config)) {
				event->hw.flags |= c->flags;
				return c;
			}
		}
	}

	/*
	 * Extended PEBS support
	 * Makes the PEBS code search the normal constraints.
	 */
	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
		return NULL;

	return &emptyconstraint;
}

/*
 * We need the sched_task callback even for per-cpu events when we use
 * the large interrupt threshold, such that we can provide PID and TID
 * to PEBS samples.
 */
static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
{
	return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
}

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

	if (!sched_in && pebs_needs_sched_cb(cpuc))
		intel_pmu_drain_pebs_buffer();
}

static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
{
	struct debug_store *ds = cpuc->ds;
	u64 threshold;
	int reserved;

	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
		reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
	else
		reserved = x86_pmu.max_pebs_events;

	if (cpuc->n_pebs == cpuc->n_large_pebs) {
		threshold = ds->pebs_absolute_maximum -
			reserved * cpuc->pebs_record_size;
	} else {
		threshold = ds->pebs_buffer_base + cpuc->pebs_record_size;
	}

	ds->pebs_interrupt_threshold = threshold;
}

static void adaptive_pebs_record_size_update(void)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	u64 pebs_data_cfg = cpuc->pebs_data_cfg;
	int sz = sizeof(struct pebs_basic);

	if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
		sz += sizeof(struct pebs_meminfo);
	if (pebs_data_cfg & PEBS_DATACFG_GP)
		sz += sizeof(struct pebs_gprs);
	if (pebs_data_cfg & PEBS_DATACFG_XMMS)
		sz += sizeof(struct pebs_xmm);
	if (pebs_data_cfg & PEBS_DATACFG_LBRS)
		sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);

	cpuc->pebs_record_size = sz;
}

#define PERF_PEBS_MEMINFO_TYPE	(PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC |   \
				PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
				PERF_SAMPLE_TRANSACTION)

static u64 pebs_update_adaptive_cfg(struct perf_event *event)
{
	struct perf_event_attr *attr = &event->attr;
	u64 sample_type = attr->sample_type;
	u64 pebs_data_cfg = 0;
	bool gprs, tsx_weight;

	if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
	    attr->precise_ip > 1)
		return pebs_data_cfg;

	if (sample_type & PERF_PEBS_MEMINFO_TYPE)
		pebs_data_cfg |= PEBS_DATACFG_MEMINFO;

	/*
	 * We need GPRs when:
	 * + user requested them
	 * + precise_ip < 2 for the non event IP
	 * + For RTM TSX weight we need GPRs for the abort code.
	 */
	gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
	       (attr->sample_regs_intr & PEBS_GP_REGS);

	tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
		     ((attr->config & INTEL_ARCH_EVENT_MASK) ==
		      x86_pmu.rtm_abort_event);

	if (gprs || (attr->precise_ip < 2) || tsx_weight)
		pebs_data_cfg |= PEBS_DATACFG_GP;

	if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
	    (attr->sample_regs_intr & PERF_REG_EXTENDED_MASK))
		pebs_data_cfg |= PEBS_DATACFG_XMMS;

	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
		/*
		 * For now always log all LBRs. Could configure this
		 * later.
		 */
		pebs_data_cfg |= PEBS_DATACFG_LBRS |
			((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
	}

	return pebs_data_cfg;
}

static void
pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
		  struct perf_event *event, bool add)
{
	struct pmu *pmu = event->ctx->pmu;
	/*
	 * Make sure we get updated with the first PEBS
	 * event. It will trigger also during removal, but
	 * that does not hurt:
	 */
	bool update = cpuc->n_pebs == 1;

	if (needed_cb != pebs_needs_sched_cb(cpuc)) {
		if (!needed_cb)
			perf_sched_cb_inc(pmu);
		else
			perf_sched_cb_dec(pmu);

		update = true;
	}

	/*
	 * The PEBS record doesn't shrink on pmu::del(). Doing so would require
	 * iterating all remaining PEBS events to reconstruct the config.
	 */
	if (x86_pmu.intel_cap.pebs_baseline && add) {
		u64 pebs_data_cfg;

		/* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
		if (cpuc->n_pebs == 1) {
			cpuc->pebs_data_cfg = 0;
			cpuc->pebs_record_size = sizeof(struct pebs_basic);
		}

		pebs_data_cfg = pebs_update_adaptive_cfg(event);

		/* Update pebs_record_size if new event requires more data. */
		if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
			cpuc->pebs_data_cfg |= pebs_data_cfg;
			adaptive_pebs_record_size_update();
			update = true;
		}
	}

	if (update)
		pebs_update_threshold(cpuc);
}

void intel_pmu_pebs_add(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;
	bool needed_cb = pebs_needs_sched_cb(cpuc);

	cpuc->n_pebs++;
	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
		cpuc->n_large_pebs++;

	pebs_update_state(needed_cb, cpuc, event, true);
}

void intel_pmu_pebs_enable(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;
	struct debug_store *ds = cpuc->ds;

	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;

	cpuc->pebs_enabled |= 1ULL << hwc->idx;

	if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5))
		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
		cpuc->pebs_enabled |= 1ULL << 63;

	if (x86_pmu.intel_cap.pebs_baseline) {
		hwc->config |= ICL_EVENTSEL_ADAPTIVE;
		if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
			wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
			cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
		}
	}

	/*
	 * Use auto-reload if possible to save a MSR write in the PMI.
	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
	 */
	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
		unsigned int idx = hwc->idx;

		if (idx >= INTEL_PMC_IDX_FIXED)
			idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
		ds->pebs_event_reset[idx] =
			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
	} else {
		ds->pebs_event_reset[hwc->idx] = 0;
	}
}

void intel_pmu_pebs_del(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;
	bool needed_cb = pebs_needs_sched_cb(cpuc);

	cpuc->n_pebs--;
	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
		cpuc->n_large_pebs--;

	pebs_update_state(needed_cb, cpuc, event, false);
}

void intel_pmu_pebs_disable(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;

	if (cpuc->n_pebs == cpuc->n_large_pebs)
		intel_pmu_drain_pebs_buffer();

	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);

	if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
	    (x86_pmu.version < 5))
		cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
		cpuc->pebs_enabled &= ~(1ULL << 63);

	if (cpuc->enabled)
		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);

	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
}

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

	if (cpuc->pebs_enabled)
		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
}

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

	if (cpuc->pebs_enabled)
		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
}

static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	unsigned long from = cpuc->lbr_entries[0].from;
	unsigned long old_to, to = cpuc->lbr_entries[0].to;
	unsigned long ip = regs->ip;
	int is_64bit = 0;
	void *kaddr;
	int size;

	/*
	 * We don't need to fixup if the PEBS assist is fault like
	 */
	if (!x86_pmu.intel_cap.pebs_trap)
		return 1;

	/*
	 * No LBR entry, no basic block, no rewinding
	 */
	if (!cpuc->lbr_stack.nr || !from || !to)
		return 0;

	/*
	 * Basic blocks should never cross user/kernel boundaries
	 */
	if (kernel_ip(ip) != kernel_ip(to))
		return 0;

	/*
	 * unsigned math, either ip is before the start (impossible) or
	 * the basic block is larger than 1 page (sanity)
	 */
	if ((ip - to) > PEBS_FIXUP_SIZE)
		return 0;

	/*
	 * We sampled a branch insn, rewind using the LBR stack
	 */
	if (ip == to) {
		set_linear_ip(regs, from);
		return 1;
	}

	size = ip - to;
	if (!kernel_ip(ip)) {
		int bytes;
		u8 *buf = this_cpu_read(insn_buffer);

		/* 'size' must fit our buffer, see above */
		bytes = copy_from_user_nmi(buf, (void __user *)to, size);
		if (bytes != 0)
			return 0;

		kaddr = buf;
	} else {
		kaddr = (void *)to;
	}

	do {
		struct insn insn;

		old_to = to;

#ifdef CONFIG_X86_64
		is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
#endif
		insn_init(&insn, kaddr, size, is_64bit);
		insn_get_length(&insn);
		/*
		 * Make sure there was not a problem decoding the
		 * instruction and getting the length.  This is
		 * doubly important because we have an infinite
		 * loop if insn.length=0.
		 */
		if (!insn.length)
			break;

		to += insn.length;
		kaddr += insn.length;
		size -= insn.length;
	} while (to < ip);

	if (to == ip) {
		set_linear_ip(regs, old_to);
		return 1;
	}

	/*
	 * Even though we decoded the basic block, the instruction stream
	 * never matched the given IP, either the TO or the IP got corrupted.
	 */
	return 0;
}

static inline u64 intel_get_tsx_weight(u64 tsx_tuning)
{
	if (tsx_tuning) {
		union hsw_tsx_tuning tsx = { .value = tsx_tuning };
		return tsx.cycles_last_block;
	}
	return 0;
}

static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
{
	u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;

	/* For RTM XABORTs also log the abort code from AX */
	if ((txn & PERF_TXN_TRANSACTION) && (ax & 1))
		txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
	return txn;
}

static inline u64 get_pebs_status(void *n)
{
	if (x86_pmu.intel_cap.pebs_format < 4)
		return ((struct pebs_record_nhm *)n)->status;
	return ((struct pebs_basic *)n)->applicable_counters;
}

#define PERF_X86_EVENT_PEBS_HSW_PREC \
		(PERF_X86_EVENT_PEBS_ST_HSW | \
		 PERF_X86_EVENT_PEBS_LD_HSW | \
		 PERF_X86_EVENT_PEBS_NA_HSW)

static u64 get_data_src(struct perf_event *event, u64 aux)
{
	u64 val = PERF_MEM_NA;
	int fl = event->hw.flags;
	bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);

	if (fl & PERF_X86_EVENT_PEBS_LDLAT)
		val = load_latency_data(aux);
	else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
		val = precise_datala_hsw(event, aux);
	else if (fst)
		val = precise_store_data(aux);
	return val;
}

static void setup_pebs_fixed_sample_data(struct perf_event *event,
				   struct pt_regs *iregs, void *__pebs,
				   struct perf_sample_data *data,
				   struct pt_regs *regs)
{
	/*
	 * We cast to the biggest pebs_record but are careful not to
	 * unconditionally access the 'extra' entries.
	 */
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct pebs_record_skl *pebs = __pebs;
	u64 sample_type;
	int fll;

	if (pebs == NULL)
		return;

	sample_type = event->attr.sample_type;
	fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;

	perf_sample_data_init(data, 0, event->hw.last_period);

	data->period = event->hw.last_period;

	/*
	 * Use latency for weight (only avail with PEBS-LL)
	 */
	if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
		data->weight = pebs->lat;

	/*
	 * data.data_src encodes the data source
	 */
	if (sample_type & PERF_SAMPLE_DATA_SRC)
		data->data_src.val = get_data_src(event, pebs->dse);

	/*
	 * We must however always use iregs for the unwinder to stay sane; the
	 * record BP,SP,IP can point into thin air when the record is from a
	 * previous PMI context or an (I)RET happened between the record and
	 * PMI.
	 */
	if (sample_type & PERF_SAMPLE_CALLCHAIN)
		data->callchain = perf_callchain(event, iregs);

	/*
	 * We use the interrupt regs as a base because the PEBS record does not
	 * contain a full regs set, specifically it seems to lack segment
	 * descriptors, which get used by things like user_mode().
	 *
	 * In the simple case fix up only the IP for PERF_SAMPLE_IP.
	 */
	*regs = *iregs;

	/*
	 * Initialize regs_>flags from PEBS,
	 * Clear exact bit (which uses x86 EFLAGS Reserved bit 3),
	 * i.e., do not rely on it being zero:
	 */
	regs->flags = pebs->flags & ~PERF_EFLAGS_EXACT;

	if (sample_type & PERF_SAMPLE_REGS_INTR) {
		regs->ax = pebs->ax;
		regs->bx = pebs->bx;
		regs->cx = pebs->cx;
		regs->dx = pebs->dx;
		regs->si = pebs->si;
		regs->di = pebs->di;

		regs->bp = pebs->bp;
		regs->sp = pebs->sp;

#ifndef CONFIG_X86_32
		regs->r8 = pebs->r8;
		regs->r9 = pebs->r9;
		regs->r10 = pebs->r10;
		regs->r11 = pebs->r11;
		regs->r12 = pebs->r12;
		regs->r13 = pebs->r13;
		regs->r14 = pebs->r14;
		regs->r15 = pebs->r15;
#endif
	}

	if (event->attr.precise_ip > 1) {
		/*
		 * Haswell and later processors have an 'eventing IP'
		 * (real IP) which fixes the off-by-1 skid in hardware.
		 * Use it when precise_ip >= 2 :
		 */
		if (x86_pmu.intel_cap.pebs_format >= 2) {
			set_linear_ip(regs, pebs->real_ip);
			regs->flags |= PERF_EFLAGS_EXACT;
		} else {
			/* Otherwise, use PEBS off-by-1 IP: */
			set_linear_ip(regs, pebs->ip);

			/*
			 * With precise_ip >= 2, try to fix up the off-by-1 IP
			 * using the LBR. If successful, the fixup function
			 * corrects regs->ip and calls set_linear_ip() on regs:
			 */
			if (intel_pmu_pebs_fixup_ip(regs))
				regs->flags |= PERF_EFLAGS_EXACT;
		}
	} else {
		/*
		 * When precise_ip == 1, return the PEBS off-by-1 IP,
		 * no fixup attempted:
		 */
		set_linear_ip(regs, pebs->ip);
	}


	if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) &&
	    x86_pmu.intel_cap.pebs_format >= 1)
		data->addr = pebs->dla;

	if (x86_pmu.intel_cap.pebs_format >= 2) {
		/* Only set the TSX weight when no memory weight. */
		if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
			data->weight = intel_get_tsx_weight(pebs->tsx_tuning);

		if (sample_type & PERF_SAMPLE_TRANSACTION)
			data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
							      pebs->ax);
	}

	/*
	 * v3 supplies an accurate time stamp, so we use that
	 * for the time stamp.
	 *
	 * We can only do this for the default trace clock.
	 */
	if (x86_pmu.intel_cap.pebs_format >= 3 &&
		event->attr.use_clockid == 0)
		data->time = native_sched_clock_from_tsc(pebs->tsc);

	if (has_branch_stack(event))
		data->br_stack = &cpuc->lbr_stack;
}

static void adaptive_pebs_save_regs(struct pt_regs *regs,
				    struct pebs_gprs *gprs)
{
	regs->ax = gprs->ax;
	regs->bx = gprs->bx;
	regs->cx = gprs->cx;
	regs->dx = gprs->dx;
	regs->si = gprs->si;
	regs->di = gprs->di;
	regs->bp = gprs->bp;
	regs->sp = gprs->sp;
#ifndef CONFIG_X86_32
	regs->r8 = gprs->r8;
	regs->r9 = gprs->r9;
	regs->r10 = gprs->r10;
	regs->r11 = gprs->r11;
	regs->r12 = gprs->r12;
	regs->r13 = gprs->r13;
	regs->r14 = gprs->r14;
	regs->r15 = gprs->r15;
#endif
}

/*
 * With adaptive PEBS the layout depends on what fields are configured.
 */

static void setup_pebs_adaptive_sample_data(struct perf_event *event,
					    struct pt_regs *iregs, void *__pebs,
					    struct perf_sample_data *data,
					    struct pt_regs *regs)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct pebs_basic *basic = __pebs;
	void *next_record = basic + 1;
	u64 sample_type;
	u64 format_size;
	struct pebs_meminfo *meminfo = NULL;
	struct pebs_gprs *gprs = NULL;
	struct x86_perf_regs *perf_regs;

	if (basic == NULL)
		return;

	perf_regs = container_of(regs, struct x86_perf_regs, regs);
	perf_regs->xmm_regs = NULL;

	sample_type = event->attr.sample_type;
	format_size = basic->format_size;
	perf_sample_data_init(data, 0, event->hw.last_period);
	data->period = event->hw.last_period;

	if (event->attr.use_clockid == 0)
		data->time = native_sched_clock_from_tsc(basic->tsc);

	/*
	 * We must however always use iregs for the unwinder to stay sane; the
	 * record BP,SP,IP can point into thin air when the record is from a
	 * previous PMI context or an (I)RET happened between the record and
	 * PMI.
	 */
	if (sample_type & PERF_SAMPLE_CALLCHAIN)
		data->callchain = perf_callchain(event, iregs);

	*regs = *iregs;
	/* The ip in basic is EventingIP */
	set_linear_ip(regs, basic->ip);
	regs->flags = PERF_EFLAGS_EXACT;

	/*
	 * The record for MEMINFO is in front of GP
	 * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
	 * Save the pointer here but process later.
	 */
	if (format_size & PEBS_DATACFG_MEMINFO) {
		meminfo = next_record;
		next_record = meminfo + 1;
	}

	if (format_size & PEBS_DATACFG_GP) {
		gprs = next_record;
		next_record = gprs + 1;

		if (event->attr.precise_ip < 2) {
			set_linear_ip(regs, gprs->ip);
			regs->flags &= ~PERF_EFLAGS_EXACT;
		}

		if (sample_type & PERF_SAMPLE_REGS_INTR)
			adaptive_pebs_save_regs(regs, gprs);
	}

	if (format_size & PEBS_DATACFG_MEMINFO) {
		if (sample_type & PERF_SAMPLE_WEIGHT)
			data->weight = meminfo->latency ?:
				intel_get_tsx_weight(meminfo->tsx_tuning);

		if (sample_type & PERF_SAMPLE_DATA_SRC)
			data->data_src.val = get_data_src(event, meminfo->aux);

		if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
			data->addr = meminfo->address;

		if (sample_type & PERF_SAMPLE_TRANSACTION)
			data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
							  gprs ? gprs->ax : 0);
	}

	if (format_size & PEBS_DATACFG_XMMS) {
		struct pebs_xmm *xmm = next_record;

		next_record = xmm + 1;
		perf_regs->xmm_regs = xmm->xmm;
	}

	if (format_size & PEBS_DATACFG_LBRS) {
		struct pebs_lbr *lbr = next_record;
		int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
					& 0xff) + 1;
		next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);

		if (has_branch_stack(event)) {
			intel_pmu_store_pebs_lbrs(lbr);
			data->br_stack = &cpuc->lbr_stack;
		}
	}

	WARN_ONCE(next_record != __pebs + (format_size >> 48),
			"PEBS record size %llu, expected %llu, config %llx\n",
			format_size >> 48,
			(u64)(next_record - __pebs),
			basic->format_size);
}

static inline void *
get_next_pebs_record_by_bit(void *base, void *top, int bit)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	void *at;
	u64 pebs_status;

	/*
	 * fmt0 does not have a status bitfield (does not use
	 * perf_record_nhm format)
	 */
	if (x86_pmu.intel_cap.pebs_format < 1)
		return base;

	if (base == NULL)
		return NULL;

	for (at = base; at < top; at += cpuc->pebs_record_size) {
		unsigned long status = get_pebs_status(at);

		if (test_bit(bit, (unsigned long *)&status)) {
			/* PEBS v3 has accurate status bits */
			if (x86_pmu.intel_cap.pebs_format >= 3)
				return at;

			if (status == (1 << bit))
				return at;

			/* clear non-PEBS bit and re-check */
			pebs_status = status & cpuc->pebs_enabled;
			pebs_status &= PEBS_COUNTER_MASK;
			if (pebs_status == (1 << bit))
				return at;
		}
	}
	return NULL;
}

void intel_pmu_auto_reload_read(struct perf_event *event)
{
	WARN_ON(!(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD));

	perf_pmu_disable(event->pmu);
	intel_pmu_drain_pebs_buffer();
	perf_pmu_enable(event->pmu);
}

/*
 * Special variant of intel_pmu_save_and_restart() for auto-reload.
 */
static int
intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
{
	struct hw_perf_event *hwc = &event->hw;
	int shift = 64 - x86_pmu.cntval_bits;
	u64 period = hwc->sample_period;
	u64 prev_raw_count, new_raw_count;
	s64 new, old;

	WARN_ON(!period);

	/*
	 * drain_pebs() only happens when the PMU is disabled.
	 */
	WARN_ON(this_cpu_read(cpu_hw_events.enabled));

	prev_raw_count = local64_read(&hwc->prev_count);
	rdpmcl(hwc->event_base_rdpmc, new_raw_count);
	local64_set(&hwc->prev_count, new_raw_count);

	/*
	 * Since the counter increments a negative counter value and
	 * overflows on the sign switch, giving the interval:
	 *
	 *   [-period, 0]
	 *
	 * the difference between two consequtive reads is:
	 *
	 *   A) value2 - value1;
	 *      when no overflows have happened in between,
	 *
	 *   B) (0 - value1) + (value2 - (-period));
	 *      when one overflow happened in between,
	 *
	 *   C) (0 - value1) + (n - 1) * (period) + (value2 - (-period));
	 *      when @n overflows happened in between.
	 *
	 * Here A) is the obvious difference, B) is the extension to the
	 * discrete interval, where the first term is to the top of the
	 * interval and the second term is from the bottom of the next
	 * interval and C) the extension to multiple intervals, where the
	 * middle term is the whole intervals covered.
	 *
	 * An equivalent of C, by reduction, is:
	 *
	 *   value2 - value1 + n * period
	 */
	new = ((s64)(new_raw_count << shift) >> shift);
	old = ((s64)(prev_raw_count << shift) >> shift);
	local64_add(new - old + count * period, &event->count);

	perf_event_update_userpage(event);

	return 0;
}

static void __intel_pmu_pebs_event(struct perf_event *event,
				   struct pt_regs *iregs,
				   void *base, void *top,
				   int bit, int count,
				   void (*setup_sample)(struct perf_event *,
						struct pt_regs *,
						void *,
						struct perf_sample_data *,
						struct pt_regs *))
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;
	struct perf_sample_data data;
	struct x86_perf_regs perf_regs;
	struct pt_regs *regs = &perf_regs.regs;
	void *at = get_next_pebs_record_by_bit(base, top, bit);

	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
		/*
		 * Now, auto-reload is only enabled in fixed period mode.
		 * The reload value is always hwc->sample_period.
		 * May need to change it, if auto-reload is enabled in
		 * freq mode later.
		 */
		intel_pmu_save_and_restart_reload(event, count);
	} else if (!intel_pmu_save_and_restart(event))
		return;

	while (count > 1) {
		setup_sample(event, iregs, at, &data, regs);
		perf_event_output(event, &data, regs);
		at += cpuc->pebs_record_size;
		at = get_next_pebs_record_by_bit(at, top, bit);
		count--;
	}

	setup_sample(event, iregs, at, &data, regs);

	/*
	 * All but the last records are processed.
	 * The last one is left to be able to call the overflow handler.
	 */
	if (perf_event_overflow(event, &data, regs)) {
		x86_pmu_stop(event, 0);
		return;
	}

}

static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct debug_store *ds = cpuc->ds;
	struct perf_event *event = cpuc->events[0]; /* PMC0 only */
	struct pebs_record_core *at, *top;
	int n;

	if (!x86_pmu.pebs_active)
		return;

	at  = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base;
	top = (struct pebs_record_core *)(unsigned long)ds->pebs_index;

	/*
	 * Whatever else happens, drain the thing
	 */
	ds->pebs_index = ds->pebs_buffer_base;

	if (!test_bit(0, cpuc->active_mask))
		return;

	WARN_ON_ONCE(!event);

	if (!event->attr.precise_ip)
		return;

	n = top - at;
	if (n <= 0) {
		if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
			intel_pmu_save_and_restart_reload(event, 0);
		return;
	}

	__intel_pmu_pebs_event(event, iregs, at, top, 0, n,
			       setup_pebs_fixed_sample_data);
}

static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
{
	struct perf_event *event;
	int bit;

	/*
	 * The drain_pebs() could be called twice in a short period
	 * for auto-reload event in pmu::read(). There are no
	 * overflows have happened in between.
	 * It needs to call intel_pmu_save_and_restart_reload() to
	 * update the event->count for this case.
	 */
	for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
		event = cpuc->events[bit];
		if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
			intel_pmu_save_and_restart_reload(event, 0);
	}
}

static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct debug_store *ds = cpuc->ds;
	struct perf_event *event;
	void *base, *at, *top;
	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
	short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
	int bit, i, size;
	u64 mask;

	if (!x86_pmu.pebs_active)
		return;

	base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
	top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;

	ds->pebs_index = ds->pebs_buffer_base;

	mask = (1ULL << x86_pmu.max_pebs_events) - 1;
	size = x86_pmu.max_pebs_events;
	if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
		mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
		size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
	}

	if (unlikely(base >= top)) {
		intel_pmu_pebs_event_update_no_drain(cpuc, size);
		return;
	}

	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
		struct pebs_record_nhm *p = at;
		u64 pebs_status;

		pebs_status = p->status & cpuc->pebs_enabled;
		pebs_status &= mask;

		/* PEBS v3 has more accurate status bits */
		if (x86_pmu.intel_cap.pebs_format >= 3) {
			for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
				counts[bit]++;

			continue;
		}

		/*
		 * On some CPUs the PEBS status can be zero when PEBS is
		 * racing with clearing of GLOBAL_STATUS.
		 *
		 * Normally we would drop that record, but in the
		 * case when there is only a single active PEBS event
		 * we can assume it's for that event.
		 */
		if (!pebs_status && cpuc->pebs_enabled &&
			!(cpuc->pebs_enabled & (cpuc->pebs_enabled-1)))
			pebs_status = cpuc->pebs_enabled;

		bit = find_first_bit((unsigned long *)&pebs_status,
					x86_pmu.max_pebs_events);
		if (bit >= x86_pmu.max_pebs_events)
			continue;

		/*
		 * The PEBS hardware does not deal well with the situation
		 * when events happen near to each other and multiple bits
		 * are set. But it should happen rarely.
		 *
		 * If these events include one PEBS and multiple non-PEBS
		 * events, it doesn't impact PEBS record. The record will
		 * be handled normally. (slow path)
		 *
		 * If these events include two or more PEBS events, the
		 * records for the events can be collapsed into a single
		 * one, and it's not possible to reconstruct all events
		 * that caused the PEBS record. It's called collision.
		 * If collision happened, the record will be dropped.
		 */
		if (p->status != (1ULL << bit)) {
			for_each_set_bit(i, (unsigned long *)&pebs_status, size)
				error[i]++;
			continue;
		}

		counts[bit]++;
	}

	for_each_set_bit(bit, (unsigned long *)&mask, size) {
		if ((counts[bit] == 0) && (error[bit] == 0))
			continue;

		event = cpuc->events[bit];
		if (WARN_ON_ONCE(!event))
			continue;

		if (WARN_ON_ONCE(!event->attr.precise_ip))
			continue;

		/* log dropped samples number */
		if (error[bit]) {
			perf_log_lost_samples(event, error[bit]);

			if (perf_event_account_interrupt(event))
				x86_pmu_stop(event, 0);
		}

		if (counts[bit]) {
			__intel_pmu_pebs_event(event, iregs, base,
					       top, bit, counts[bit],
					       setup_pebs_fixed_sample_data);
		}
	}
}

static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
{
	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct debug_store *ds = cpuc->ds;
	struct perf_event *event;
	void *base, *at, *top;
	int bit, size;
	u64 mask;

	if (!x86_pmu.pebs_active)
		return;

	base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base;
	top = (struct pebs_basic *)(unsigned long)ds->pebs_index;

	ds->pebs_index = ds->pebs_buffer_base;

	mask = ((1ULL << x86_pmu.max_pebs_events) - 1) |
	       (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
	size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;

	if (unlikely(base >= top)) {
		intel_pmu_pebs_event_update_no_drain(cpuc, size);
		return;
	}

	for (at = base; at < top; at += cpuc->pebs_record_size) {
		u64 pebs_status;

		pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
		pebs_status &= mask;

		for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
			counts[bit]++;
	}

	for_each_set_bit(bit, (unsigned long *)&mask, size) {
		if (counts[bit] == 0)
			continue;

		event = cpuc->events[bit];
		if (WARN_ON_ONCE(!event))
			continue;

		if (WARN_ON_ONCE(!event->attr.precise_ip))
			continue;

		__intel_pmu_pebs_event(event, iregs, base,
				       top, bit, counts[bit],
				       setup_pebs_adaptive_sample_data);
	}
}

/*
 * BTS, PEBS probe and setup
 */

void __init intel_ds_init(void)
{
	/*
	 * No support for 32bit formats
	 */
	if (!boot_cpu_has(X86_FEATURE_DTES64))
		return;

	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
	if (x86_pmu.version <= 4)
		x86_pmu.pebs_no_isolation = 1;

	if (x86_pmu.pebs) {
		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
		char *pebs_qual = "";
		int format = x86_pmu.intel_cap.pebs_format;

		if (format < 4)
			x86_pmu.intel_cap.pebs_baseline = 0;

		switch (format) {
		case 0:
			pr_cont("PEBS fmt0%c, ", pebs_type);
			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
			/*
			 * Using >PAGE_SIZE buffers makes the WRMSR to
			 * PERF_GLOBAL_CTRL in intel_pmu_enable_all()
			 * mysteriously hang on Core2.
			 *
			 * As a workaround, we don't do this.
			 */
			x86_pmu.pebs_buffer_size = PAGE_SIZE;
			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
			break;

		case 1:
			pr_cont("PEBS fmt1%c, ", pebs_type);
			x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
			break;

		case 2:
			pr_cont("PEBS fmt2%c, ", pebs_type);
			x86_pmu.pebs_record_size = sizeof(struct pebs_record_hsw);
			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
			break;

		case 3:
			pr_cont("PEBS fmt3%c, ", pebs_type);
			x86_pmu.pebs_record_size =
						sizeof(struct pebs_record_skl);
			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
			x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
			break;

		case 4:
			x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
			x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
			if (x86_pmu.intel_cap.pebs_baseline) {
				x86_pmu.large_pebs_flags |=
					PERF_SAMPLE_BRANCH_STACK |
					PERF_SAMPLE_TIME;
				x86_pmu.flags |= PMU_FL_PEBS_ALL;
				pebs_qual = "-baseline";
				x86_get_pmu()->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
			} else {
				/* Only basic record supported */
				x86_pmu.large_pebs_flags &=
					~(PERF_SAMPLE_ADDR |
					  PERF_SAMPLE_TIME |
					  PERF_SAMPLE_DATA_SRC |
					  PERF_SAMPLE_TRANSACTION |
					  PERF_SAMPLE_REGS_USER |
					  PERF_SAMPLE_REGS_INTR);
			}
			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
			break;

		default:
			pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
			x86_pmu.pebs = 0;
		}
	}
}

void perf_restore_debug_store(void)
{
	struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);

	if (!x86_pmu.bts && !x86_pmu.pebs)
		return;

	wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds);
}