summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/smpboot.c
blob: ac2909f0cab3478c9428fc2a609759c6dd5af3ef (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
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
// SPDX-License-Identifier: GPL-2.0-or-later
 /*
 *	x86 SMP booting functions
 *
 *	(c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk>
 *	(c) 1998, 1999, 2000, 2009 Ingo Molnar <mingo@redhat.com>
 *	Copyright 2001 Andi Kleen, SuSE Labs.
 *
 *	Much of the core SMP work is based on previous work by Thomas Radke, to
 *	whom a great many thanks are extended.
 *
 *	Thanks to Intel for making available several different Pentium,
 *	Pentium Pro and Pentium-II/Xeon MP machines.
 *	Original development of Linux SMP code supported by Caldera.
 *
 *	Fixes
 *		Felix Koop	:	NR_CPUS used properly
 *		Jose Renau	:	Handle single CPU case.
 *		Alan Cox	:	By repeated request 8) - Total BogoMIPS report.
 *		Greg Wright	:	Fix for kernel stacks panic.
 *		Erich Boleyn	:	MP v1.4 and additional changes.
 *	Matthias Sattler	:	Changes for 2.1 kernel map.
 *	Michel Lespinasse	:	Changes for 2.1 kernel map.
 *	Michael Chastain	:	Change trampoline.S to gnu as.
 *		Alan Cox	:	Dumb bug: 'B' step PPro's are fine
 *		Ingo Molnar	:	Added APIC timers, based on code
 *					from Jose Renau
 *		Ingo Molnar	:	various cleanups and rewrites
 *		Tigran Aivazian	:	fixed "0.00 in /proc/uptime on SMP" bug.
 *	Maciej W. Rozycki	:	Bits for genuine 82489DX APICs
 *	Andi Kleen		:	Changed for SMP boot into long mode.
 *		Martin J. Bligh	: 	Added support for multi-quad systems
 *		Dave Jones	:	Report invalid combinations of Athlon CPUs.
 *		Rusty Russell	:	Hacked into shape for new "hotplug" boot process.
 *      Andi Kleen              :       Converted to new state machine.
 *	Ashok Raj		: 	CPU hotplug support
 *	Glauber Costa		:	i386 and x86_64 integration
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/init.h>
#include <linux/smp.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/topology.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/task_stack.h>
#include <linux/percpu.h>
#include <linux/memblock.h>
#include <linux/err.h>
#include <linux/nmi.h>
#include <linux/tboot.h>
#include <linux/gfp.h>
#include <linux/cpuidle.h>
#include <linux/numa.h>
#include <linux/pgtable.h>
#include <linux/overflow.h>
#include <linux/syscore_ops.h>

#include <asm/acpi.h>
#include <asm/desc.h>
#include <asm/nmi.h>
#include <asm/irq.h>
#include <asm/realmode.h>
#include <asm/cpu.h>
#include <asm/numa.h>
#include <asm/tlbflush.h>
#include <asm/mtrr.h>
#include <asm/mwait.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
#include <asm/fpu/api.h>
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
#include <asm/i8259.h>
#include <asm/misc.h>
#include <asm/qspinlock.h>
#include <asm/intel-family.h>
#include <asm/cpu_device_id.h>
#include <asm/spec-ctrl.h>
#include <asm/hw_irq.h>
#include <asm/stackprotector.h>

#ifdef CONFIG_ACPI_CPPC_LIB
#include <acpi/cppc_acpi.h>
#endif

/* representing HT siblings of each logical CPU */
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);

/* representing HT and core siblings of each logical CPU */
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);

/* representing HT, core, and die siblings of each logical CPU */
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
EXPORT_PER_CPU_SYMBOL(cpu_die_map);

DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);

DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map);

/* Per CPU bogomips and other parameters */
DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);

/* Logical package management. We might want to allocate that dynamically */
unsigned int __max_logical_packages __read_mostly;
EXPORT_SYMBOL(__max_logical_packages);
static unsigned int logical_packages __read_mostly;
static unsigned int logical_die __read_mostly;

/* Maximum number of SMT threads on any online core */
int __read_mostly __max_smt_threads = 1;

/* Flag to indicate if a complete sched domain rebuild is required */
bool x86_topology_update;

int arch_update_cpu_topology(void)
{
	int retval = x86_topology_update;

	x86_topology_update = false;
	return retval;
}

static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
{
	unsigned long flags;

	spin_lock_irqsave(&rtc_lock, flags);
	CMOS_WRITE(0xa, 0xf);
	spin_unlock_irqrestore(&rtc_lock, flags);
	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
							start_eip >> 4;
	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
							start_eip & 0xf;
}

static inline void smpboot_restore_warm_reset_vector(void)
{
	unsigned long flags;

	/*
	 * Paranoid:  Set warm reset code and vector here back
	 * to default values.
	 */
	spin_lock_irqsave(&rtc_lock, flags);
	CMOS_WRITE(0, 0xf);
	spin_unlock_irqrestore(&rtc_lock, flags);

	*((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
}

static void init_freq_invariance(bool secondary, bool cppc_ready);

/*
 * Report back to the Boot Processor during boot time or to the caller processor
 * during CPU online.
 */
static void smp_callin(void)
{
	int cpuid;

	/*
	 * If waken up by an INIT in an 82489DX configuration
	 * cpu_callout_mask guarantees we don't get here before
	 * an INIT_deassert IPI reaches our local APIC, so it is
	 * now safe to touch our local APIC.
	 */
	cpuid = smp_processor_id();

	/*
	 * the boot CPU has finished the init stage and is spinning
	 * on callin_map until we finish. We are free to set up this
	 * CPU, first the APIC. (this is probably redundant on most
	 * boards)
	 */
	apic_ap_setup();

	/*
	 * Save our processor parameters. Note: this information
	 * is needed for clock calibration.
	 */
	smp_store_cpu_info(cpuid);

	/*
	 * The topology information must be up to date before
	 * calibrate_delay() and notify_cpu_starting().
	 */
	set_cpu_sibling_map(raw_smp_processor_id());

	init_freq_invariance(true, false);

	/*
	 * Get our bogomips.
	 * Update loops_per_jiffy in cpu_data. Previous call to
	 * smp_store_cpu_info() stored a value that is close but not as
	 * accurate as the value just calculated.
	 */
	calibrate_delay();
	cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
	pr_debug("Stack at about %p\n", &cpuid);

	wmb();

	notify_cpu_starting(cpuid);

	/*
	 * Allow the master to continue.
	 */
	cpumask_set_cpu(cpuid, cpu_callin_mask);
}

static int cpu0_logical_apicid;
static int enable_start_cpu0;
/*
 * Activate a secondary processor.
 */
static void notrace start_secondary(void *unused)
{
	/*
	 * Don't put *anything* except direct CPU state initialization
	 * before cpu_init(), SMP booting is too fragile that we want to
	 * limit the things done here to the most necessary things.
	 */
	cr4_init();

#ifdef CONFIG_X86_32
	/* switch away from the initial page table */
	load_cr3(swapper_pg_dir);
	__flush_tlb_all();
#endif
	cpu_init_secondary();
	rcu_cpu_starting(raw_smp_processor_id());
	x86_cpuinit.early_percpu_clock_init();
	smp_callin();

	enable_start_cpu0 = 0;

	/* otherwise gcc will move up smp_processor_id before the cpu_init */
	barrier();
	/*
	 * Check TSC synchronization with the boot CPU:
	 */
	check_tsc_sync_target();

	speculative_store_bypass_ht_init();

	/*
	 * Lock vector_lock, set CPU online and bring the vector
	 * allocator online. Online must be set with vector_lock held
	 * to prevent a concurrent irq setup/teardown from seeing a
	 * half valid vector space.
	 */
	lock_vector_lock();
	set_cpu_online(smp_processor_id(), true);
	lapic_online();
	unlock_vector_lock();
	cpu_set_state_online(smp_processor_id());
	x86_platform.nmi_init();

	/* enable local interrupts */
	local_irq_enable();

	x86_cpuinit.setup_percpu_clockev();

	wmb();
	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}

/**
 * topology_is_primary_thread - Check whether CPU is the primary SMT thread
 * @cpu:	CPU to check
 */
bool topology_is_primary_thread(unsigned int cpu)
{
	return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu));
}

/**
 * topology_smt_supported - Check whether SMT is supported by the CPUs
 */
bool topology_smt_supported(void)
{
	return smp_num_siblings > 1;
}

/**
 * topology_phys_to_logical_pkg - Map a physical package id to a logical
 *
 * Returns logical package id or -1 if not found
 */
int topology_phys_to_logical_pkg(unsigned int phys_pkg)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		struct cpuinfo_x86 *c = &cpu_data(cpu);

		if (c->initialized && c->phys_proc_id == phys_pkg)
			return c->logical_proc_id;
	}
	return -1;
}
EXPORT_SYMBOL(topology_phys_to_logical_pkg);
/**
 * topology_phys_to_logical_die - Map a physical die id to logical
 *
 * Returns logical die id or -1 if not found
 */
int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
{
	int cpu;
	int proc_id = cpu_data(cur_cpu).phys_proc_id;

	for_each_possible_cpu(cpu) {
		struct cpuinfo_x86 *c = &cpu_data(cpu);

		if (c->initialized && c->cpu_die_id == die_id &&
		    c->phys_proc_id == proc_id)
			return c->logical_die_id;
	}
	return -1;
}
EXPORT_SYMBOL(topology_phys_to_logical_die);

/**
 * topology_update_package_map - Update the physical to logical package map
 * @pkg:	The physical package id as retrieved via CPUID
 * @cpu:	The cpu for which this is updated
 */
int topology_update_package_map(unsigned int pkg, unsigned int cpu)
{
	int new;

	/* Already available somewhere? */
	new = topology_phys_to_logical_pkg(pkg);
	if (new >= 0)
		goto found;

	new = logical_packages++;
	if (new != pkg) {
		pr_info("CPU %u Converting physical %u to logical package %u\n",
			cpu, pkg, new);
	}
found:
	cpu_data(cpu).logical_proc_id = new;
	return 0;
}
/**
 * topology_update_die_map - Update the physical to logical die map
 * @die:	The die id as retrieved via CPUID
 * @cpu:	The cpu for which this is updated
 */
int topology_update_die_map(unsigned int die, unsigned int cpu)
{
	int new;

	/* Already available somewhere? */
	new = topology_phys_to_logical_die(die, cpu);
	if (new >= 0)
		goto found;

	new = logical_die++;
	if (new != die) {
		pr_info("CPU %u Converting physical %u to logical die %u\n",
			cpu, die, new);
	}
found:
	cpu_data(cpu).logical_die_id = new;
	return 0;
}

void __init smp_store_boot_cpu_info(void)
{
	int id = 0; /* CPU 0 */
	struct cpuinfo_x86 *c = &cpu_data(id);

	*c = boot_cpu_data;
	c->cpu_index = id;
	topology_update_package_map(c->phys_proc_id, id);
	topology_update_die_map(c->cpu_die_id, id);
	c->initialized = true;
}

/*
 * The bootstrap kernel entry code has set these up. Save them for
 * a given CPU
 */
void smp_store_cpu_info(int id)
{
	struct cpuinfo_x86 *c = &cpu_data(id);

	/* Copy boot_cpu_data only on the first bringup */
	if (!c->initialized)
		*c = boot_cpu_data;
	c->cpu_index = id;
	/*
	 * During boot time, CPU0 has this setup already. Save the info when
	 * bringing up AP or offlined CPU0.
	 */
	identify_secondary_cpu(c);
	c->initialized = true;
}

static bool
topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;

	return (cpu_to_node(cpu1) == cpu_to_node(cpu2));
}

static bool
topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name)
{
	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;

	return !WARN_ONCE(!topology_same_node(c, o),
		"sched: CPU #%d's %s-sibling CPU #%d is not on the same node! "
		"[node: %d != %d]. Ignoring dependency.\n",
		cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2));
}

#define link_mask(mfunc, c1, c2)					\
do {									\
	cpumask_set_cpu((c1), mfunc(c2));				\
	cpumask_set_cpu((c2), mfunc(c1));				\
} while (0)

static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;

		if (c->phys_proc_id == o->phys_proc_id &&
		    c->cpu_die_id == o->cpu_die_id &&
		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
			if (c->cpu_core_id == o->cpu_core_id)
				return topology_sane(c, o, "smt");

			if ((c->cu_id != 0xff) &&
			    (o->cu_id != 0xff) &&
			    (c->cu_id == o->cu_id))
				return topology_sane(c, o, "smt");
		}

	} else if (c->phys_proc_id == o->phys_proc_id &&
		   c->cpu_die_id == o->cpu_die_id &&
		   c->cpu_core_id == o->cpu_core_id) {
		return topology_sane(c, o, "smt");
	}

	return false;
}

static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
	if (c->phys_proc_id == o->phys_proc_id &&
	    c->cpu_die_id == o->cpu_die_id)
		return true;
	return false;
}

static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;

	/* If the arch didn't set up l2c_id, fall back to SMT */
	if (per_cpu(cpu_l2c_id, cpu1) == BAD_APICID)
		return match_smt(c, o);

	/* Do not match if L2 cache id does not match: */
	if (per_cpu(cpu_l2c_id, cpu1) != per_cpu(cpu_l2c_id, cpu2))
		return false;

	return topology_sane(c, o, "l2c");
}

/*
 * Unlike the other levels, we do not enforce keeping a
 * multicore group inside a NUMA node.  If this happens, we will
 * discard the MC level of the topology later.
 */
static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
	if (c->phys_proc_id == o->phys_proc_id)
		return true;
	return false;
}

/*
 * Define intel_cod_cpu[] for Intel COD (Cluster-on-Die) CPUs.
 *
 * Any Intel CPU that has multiple nodes per package and does not
 * match intel_cod_cpu[] has the SNC (Sub-NUMA Cluster) topology.
 *
 * When in SNC mode, these CPUs enumerate an LLC that is shared
 * by multiple NUMA nodes. The LLC is shared for off-package data
 * access but private to the NUMA node (half of the package) for
 * on-package access. CPUID (the source of the information about
 * the LLC) can only enumerate the cache as shared or unshared,
 * but not this particular configuration.
 */

static const struct x86_cpu_id intel_cod_cpu[] = {
	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, 0),	/* COD */
	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, 0),	/* COD */
	X86_MATCH_INTEL_FAM6_MODEL(ANY, 1),		/* SNC */
	{}
};

static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
	const struct x86_cpu_id *id = x86_match_cpu(intel_cod_cpu);
	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
	bool intel_snc = id && id->driver_data;

	/* Do not match if we do not have a valid APICID for cpu: */
	if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID)
		return false;

	/* Do not match if LLC id does not match: */
	if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2))
		return false;

	/*
	 * Allow the SNC topology without warning. Return of false
	 * means 'c' does not share the LLC of 'o'. This will be
	 * reflected to userspace.
	 */
	if (match_pkg(c, o) && !topology_same_node(c, o) && intel_snc)
		return false;

	return topology_sane(c, o, "llc");
}


#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_CLUSTER) || defined(CONFIG_SCHED_MC)
static inline int x86_sched_itmt_flags(void)
{
	return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;
}

#ifdef CONFIG_SCHED_MC
static int x86_core_flags(void)
{
	return cpu_core_flags() | x86_sched_itmt_flags();
}
#endif
#ifdef CONFIG_SCHED_SMT
static int x86_smt_flags(void)
{
	return cpu_smt_flags() | x86_sched_itmt_flags();
}
#endif
#ifdef CONFIG_SCHED_CLUSTER
static int x86_cluster_flags(void)
{
	return cpu_cluster_flags() | x86_sched_itmt_flags();
}
#endif
#endif

static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
#ifdef CONFIG_SCHED_SMT
	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
#endif
#ifdef CONFIG_SCHED_CLUSTER
	{ cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) },
#endif
#ifdef CONFIG_SCHED_MC
	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
#endif
	{ NULL, },
};

static struct sched_domain_topology_level x86_topology[] = {
#ifdef CONFIG_SCHED_SMT
	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
#endif
#ifdef CONFIG_SCHED_CLUSTER
	{ cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) },
#endif
#ifdef CONFIG_SCHED_MC
	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
#endif
	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
	{ NULL, },
};

/*
 * Set if a package/die has multiple NUMA nodes inside.
 * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
 * Sub-NUMA Clustering have this.
 */
static bool x86_has_numa_in_package;

void set_cpu_sibling_map(int cpu)
{
	bool has_smt = smp_num_siblings > 1;
	bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
	struct cpuinfo_x86 *c = &cpu_data(cpu);
	struct cpuinfo_x86 *o;
	int i, threads;

	cpumask_set_cpu(cpu, cpu_sibling_setup_mask);

	if (!has_mp) {
		cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
		cpumask_set_cpu(cpu, cpu_l2c_shared_mask(cpu));
		cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
		cpumask_set_cpu(cpu, topology_die_cpumask(cpu));
		c->booted_cores = 1;
		return;
	}

	for_each_cpu(i, cpu_sibling_setup_mask) {
		o = &cpu_data(i);

		if (match_pkg(c, o) && !topology_same_node(c, o))
			x86_has_numa_in_package = true;

		if ((i == cpu) || (has_smt && match_smt(c, o)))
			link_mask(topology_sibling_cpumask, cpu, i);

		if ((i == cpu) || (has_mp && match_llc(c, o)))
			link_mask(cpu_llc_shared_mask, cpu, i);

		if ((i == cpu) || (has_mp && match_l2c(c, o)))
			link_mask(cpu_l2c_shared_mask, cpu, i);

		if ((i == cpu) || (has_mp && match_die(c, o)))
			link_mask(topology_die_cpumask, cpu, i);
	}

	threads = cpumask_weight(topology_sibling_cpumask(cpu));
	if (threads > __max_smt_threads)
		__max_smt_threads = threads;

	for_each_cpu(i, topology_sibling_cpumask(cpu))
		cpu_data(i).smt_active = threads > 1;

	/*
	 * This needs a separate iteration over the cpus because we rely on all
	 * topology_sibling_cpumask links to be set-up.
	 */
	for_each_cpu(i, cpu_sibling_setup_mask) {
		o = &cpu_data(i);

		if ((i == cpu) || (has_mp && match_pkg(c, o))) {
			link_mask(topology_core_cpumask, cpu, i);

			/*
			 *  Does this new cpu bringup a new core?
			 */
			if (threads == 1) {
				/*
				 * for each core in package, increment
				 * the booted_cores for this new cpu
				 */
				if (cpumask_first(
				    topology_sibling_cpumask(i)) == i)
					c->booted_cores++;
				/*
				 * increment the core count for all
				 * the other cpus in this package
				 */
				if (i != cpu)
					cpu_data(i).booted_cores++;
			} else if (i != cpu && !c->booted_cores)
				c->booted_cores = cpu_data(i).booted_cores;
		}
	}
}

/* maps the cpu to the sched domain representing multi-core */
const struct cpumask *cpu_coregroup_mask(int cpu)
{
	return cpu_llc_shared_mask(cpu);
}

const struct cpumask *cpu_clustergroup_mask(int cpu)
{
	return cpu_l2c_shared_mask(cpu);
}

static void impress_friends(void)
{
	int cpu;
	unsigned long bogosum = 0;
	/*
	 * Allow the user to impress friends.
	 */
	pr_debug("Before bogomips\n");
	for_each_possible_cpu(cpu)
		if (cpumask_test_cpu(cpu, cpu_callout_mask))
			bogosum += cpu_data(cpu).loops_per_jiffy;
	pr_info("Total of %d processors activated (%lu.%02lu BogoMIPS)\n",
		num_online_cpus(),
		bogosum/(500000/HZ),
		(bogosum/(5000/HZ))%100);

	pr_debug("Before bogocount - setting activated=1\n");
}

void __inquire_remote_apic(int apicid)
{
	unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 };
	const char * const names[] = { "ID", "VERSION", "SPIV" };
	int timeout;
	u32 status;

	pr_info("Inquiring remote APIC 0x%x...\n", apicid);

	for (i = 0; i < ARRAY_SIZE(regs); i++) {
		pr_info("... APIC 0x%x %s: ", apicid, names[i]);

		/*
		 * Wait for idle.
		 */
		status = safe_apic_wait_icr_idle();
		if (status)
			pr_cont("a previous APIC delivery may have failed\n");

		apic_icr_write(APIC_DM_REMRD | regs[i], apicid);

		timeout = 0;
		do {
			udelay(100);
			status = apic_read(APIC_ICR) & APIC_ICR_RR_MASK;
		} while (status == APIC_ICR_RR_INPROG && timeout++ < 1000);

		switch (status) {
		case APIC_ICR_RR_VALID:
			status = apic_read(APIC_RRR);
			pr_cont("%08x\n", status);
			break;
		default:
			pr_cont("failed\n");
		}
	}
}

/*
 * The Multiprocessor Specification 1.4 (1997) example code suggests
 * that there should be a 10ms delay between the BSP asserting INIT
 * and de-asserting INIT, when starting a remote processor.
 * But that slows boot and resume on modern processors, which include
 * many cores and don't require that delay.
 *
 * Cmdline "init_cpu_udelay=" is available to over-ride this delay.
 * Modern processor families are quirked to remove the delay entirely.
 */
#define UDELAY_10MS_DEFAULT 10000

static unsigned int init_udelay = UINT_MAX;

static int __init cpu_init_udelay(char *str)
{
	get_option(&str, &init_udelay);

	return 0;
}
early_param("cpu_init_udelay", cpu_init_udelay);

static void __init smp_quirk_init_udelay(void)
{
	/* if cmdline changed it from default, leave it alone */
	if (init_udelay != UINT_MAX)
		return;

	/* if modern processor, use no delay */
	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
	    ((boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) && (boot_cpu_data.x86 >= 0x18)) ||
	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
		init_udelay = 0;
		return;
	}
	/* else, use legacy delay */
	init_udelay = UDELAY_10MS_DEFAULT;
}

/*
 * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
 * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
 * won't ... remember to clear down the APIC, etc later.
 */
int
wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
{
	u32 dm = apic->dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
	unsigned long send_status, accept_status = 0;
	int maxlvt;

	/* Target chip */
	/* Boot on the stack */
	/* Kick the second */
	apic_icr_write(APIC_DM_NMI | dm, apicid);

	pr_debug("Waiting for send to finish...\n");
	send_status = safe_apic_wait_icr_idle();

	/*
	 * Give the other CPU some time to accept the IPI.
	 */
	udelay(200);
	if (APIC_INTEGRATED(boot_cpu_apic_version)) {
		maxlvt = lapic_get_maxlvt();
		if (maxlvt > 3)			/* Due to the Pentium erratum 3AP.  */
			apic_write(APIC_ESR, 0);
		accept_status = (apic_read(APIC_ESR) & 0xEF);
	}
	pr_debug("NMI sent\n");

	if (send_status)
		pr_err("APIC never delivered???\n");
	if (accept_status)
		pr_err("APIC delivery error (%lx)\n", accept_status);

	return (send_status | accept_status);
}

static int
wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
{
	unsigned long send_status = 0, accept_status = 0;
	int maxlvt, num_starts, j;

	maxlvt = lapic_get_maxlvt();

	/*
	 * Be paranoid about clearing APIC errors.
	 */
	if (APIC_INTEGRATED(boot_cpu_apic_version)) {
		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
			apic_write(APIC_ESR, 0);
		apic_read(APIC_ESR);
	}

	pr_debug("Asserting INIT\n");

	/*
	 * Turn INIT on target chip
	 */
	/*
	 * Send IPI
	 */
	apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT,
		       phys_apicid);

	pr_debug("Waiting for send to finish...\n");
	send_status = safe_apic_wait_icr_idle();

	udelay(init_udelay);

	pr_debug("Deasserting INIT\n");

	/* Target chip */
	/* Send IPI */
	apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);

	pr_debug("Waiting for send to finish...\n");
	send_status = safe_apic_wait_icr_idle();

	mb();

	/*
	 * Should we send STARTUP IPIs ?
	 *
	 * Determine this based on the APIC version.
	 * If we don't have an integrated APIC, don't send the STARTUP IPIs.
	 */
	if (APIC_INTEGRATED(boot_cpu_apic_version))
		num_starts = 2;
	else
		num_starts = 0;

	/*
	 * Run STARTUP IPI loop.
	 */
	pr_debug("#startup loops: %d\n", num_starts);

	for (j = 1; j <= num_starts; j++) {
		pr_debug("Sending STARTUP #%d\n", j);
		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
			apic_write(APIC_ESR, 0);
		apic_read(APIC_ESR);
		pr_debug("After apic_write\n");

		/*
		 * STARTUP IPI
		 */

		/* Target chip */
		/* Boot on the stack */
		/* Kick the second */
		apic_icr_write(APIC_DM_STARTUP | (start_eip >> 12),
			       phys_apicid);

		/*
		 * Give the other CPU some time to accept the IPI.
		 */
		if (init_udelay == 0)
			udelay(10);
		else
			udelay(300);

		pr_debug("Startup point 1\n");

		pr_debug("Waiting for send to finish...\n");
		send_status = safe_apic_wait_icr_idle();

		/*
		 * Give the other CPU some time to accept the IPI.
		 */
		if (init_udelay == 0)
			udelay(10);
		else
			udelay(200);

		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
			apic_write(APIC_ESR, 0);
		accept_status = (apic_read(APIC_ESR) & 0xEF);
		if (send_status || accept_status)
			break;
	}
	pr_debug("After Startup\n");

	if (send_status)
		pr_err("APIC never delivered???\n");
	if (accept_status)
		pr_err("APIC delivery error (%lx)\n", accept_status);

	return (send_status | accept_status);
}

/* reduce the number of lines printed when booting a large cpu count system */
static void announce_cpu(int cpu, int apicid)
{
	static int current_node = NUMA_NO_NODE;
	int node = early_cpu_to_node(cpu);
	static int width, node_width;

	if (!width)
		width = num_digits(num_possible_cpus()) + 1; /* + '#' sign */

	if (!node_width)
		node_width = num_digits(num_possible_nodes()) + 1; /* + '#' */

	if (cpu == 1)
		printk(KERN_INFO "x86: Booting SMP configuration:\n");

	if (system_state < SYSTEM_RUNNING) {
		if (node != current_node) {
			if (current_node > (-1))
				pr_cont("\n");
			current_node = node;

			printk(KERN_INFO ".... node %*s#%d, CPUs:  ",
			       node_width - num_digits(node), " ", node);
		}

		/* Add padding for the BSP */
		if (cpu == 1)
			pr_cont("%*s", width + 1, " ");

		pr_cont("%*s#%d", width - num_digits(cpu), " ", cpu);

	} else
		pr_info("Booting Node %d Processor %d APIC 0x%x\n",
			node, cpu, apicid);
}

static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs)
{
	int cpu;

	cpu = smp_processor_id();
	if (cpu == 0 && !cpu_online(cpu) && enable_start_cpu0)
		return NMI_HANDLED;

	return NMI_DONE;
}

/*
 * Wake up AP by INIT, INIT, STARTUP sequence.
 *
 * Instead of waiting for STARTUP after INITs, BSP will execute the BIOS
 * boot-strap code which is not a desired behavior for waking up BSP. To
 * void the boot-strap code, wake up CPU0 by NMI instead.
 *
 * This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined
 * (i.e. physically hot removed and then hot added), NMI won't wake it up.
 * We'll change this code in the future to wake up hard offlined CPU0 if
 * real platform and request are available.
 */
static int
wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid,
	       int *cpu0_nmi_registered)
{
	int id;
	int boot_error;

	preempt_disable();

	/*
	 * Wake up AP by INIT, INIT, STARTUP sequence.
	 */
	if (cpu) {
		boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip);
		goto out;
	}

	/*
	 * Wake up BSP by nmi.
	 *
	 * Register a NMI handler to help wake up CPU0.
	 */
	boot_error = register_nmi_handler(NMI_LOCAL,
					  wakeup_cpu0_nmi, 0, "wake_cpu0");

	if (!boot_error) {
		enable_start_cpu0 = 1;
		*cpu0_nmi_registered = 1;
		id = apic->dest_mode_logical ? cpu0_logical_apicid : apicid;
		boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip);
	}

out:
	preempt_enable();

	return boot_error;
}

int common_cpu_up(unsigned int cpu, struct task_struct *idle)
{
	int ret;

	/* Just in case we booted with a single CPU. */
	alternatives_enable_smp();

	per_cpu(current_task, cpu) = idle;
	cpu_init_stack_canary(cpu, idle);

	/* Initialize the interrupt stack(s) */
	ret = irq_init_percpu_irqstack(cpu);
	if (ret)
		return ret;

#ifdef CONFIG_X86_32
	/* Stack for startup_32 can be just as for start_secondary onwards */
	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
#else
	initial_gs = per_cpu_offset(cpu);
#endif
	return 0;
}

/*
 * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
 * (ie clustered apic addressing mode), this is a LOGICAL apic ID.
 * Returns zero if CPU booted OK, else error code from
 * ->wakeup_secondary_cpu.
 */
static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
		       int *cpu0_nmi_registered)
{
	/* start_ip had better be page-aligned! */
	unsigned long start_ip = real_mode_header->trampoline_start;

	unsigned long boot_error = 0;
	unsigned long timeout;

	idle->thread.sp = (unsigned long)task_pt_regs(idle);
	early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu);
	initial_code = (unsigned long)start_secondary;
	initial_stack  = idle->thread.sp;

	/* Enable the espfix hack for this CPU */
	init_espfix_ap(cpu);

	/* So we see what's up */
	announce_cpu(cpu, apicid);

	/*
	 * This grunge runs the startup process for
	 * the targeted processor.
	 */

	if (x86_platform.legacy.warm_reset) {

		pr_debug("Setting warm reset code and vector.\n");

		smpboot_setup_warm_reset_vector(start_ip);
		/*
		 * Be paranoid about clearing APIC errors.
		*/
		if (APIC_INTEGRATED(boot_cpu_apic_version)) {
			apic_write(APIC_ESR, 0);
			apic_read(APIC_ESR);
		}
	}

	/*
	 * AP might wait on cpu_callout_mask in cpu_init() with
	 * cpu_initialized_mask set if previous attempt to online
	 * it timed-out. Clear cpu_initialized_mask so that after
	 * INIT/SIPI it could start with a clean state.
	 */
	cpumask_clear_cpu(cpu, cpu_initialized_mask);
	smp_mb();

	/*
	 * Wake up a CPU in difference cases:
	 * - Use the method in the APIC driver if it's defined
	 * Otherwise,
	 * - Use an INIT boot APIC message for APs or NMI for BSP.
	 */
	if (apic->wakeup_secondary_cpu)
		boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
	else
		boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
						     cpu0_nmi_registered);

	if (!boot_error) {
		/*
		 * Wait 10s total for first sign of life from AP
		 */
		boot_error = -1;
		timeout = jiffies + 10*HZ;
		while (time_before(jiffies, timeout)) {
			if (cpumask_test_cpu(cpu, cpu_initialized_mask)) {
				/*
				 * Tell AP to proceed with initialization
				 */
				cpumask_set_cpu(cpu, cpu_callout_mask);
				boot_error = 0;
				break;
			}
			schedule();
		}
	}

	if (!boot_error) {
		/*
		 * Wait till AP completes initial initialization
		 */
		while (!cpumask_test_cpu(cpu, cpu_callin_mask)) {
			/*
			 * Allow other tasks to run while we wait for the
			 * AP to come online. This also gives a chance
			 * for the MTRR work(triggered by the AP coming online)
			 * to be completed in the stop machine context.
			 */
			schedule();
		}
	}

	if (x86_platform.legacy.warm_reset) {
		/*
		 * Cleanup possible dangling ends...
		 */
		smpboot_restore_warm_reset_vector();
	}

	return boot_error;
}

int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
{
	int apicid = apic->cpu_present_to_apicid(cpu);
	int cpu0_nmi_registered = 0;
	unsigned long flags;
	int err, ret = 0;

	lockdep_assert_irqs_enabled();

	pr_debug("++++++++++++++++++++=_---CPU UP  %u\n", cpu);

	if (apicid == BAD_APICID ||
	    !physid_isset(apicid, phys_cpu_present_map) ||
	    !apic->apic_id_valid(apicid)) {
		pr_err("%s: bad cpu %d\n", __func__, cpu);
		return -EINVAL;
	}

	/*
	 * Already booted CPU?
	 */
	if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
		pr_debug("do_boot_cpu %d Already started\n", cpu);
		return -ENOSYS;
	}

	/*
	 * Save current MTRR state in case it was changed since early boot
	 * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync:
	 */
	mtrr_save_state();

	/* x86 CPUs take themselves offline, so delayed offline is OK. */
	err = cpu_check_up_prepare(cpu);
	if (err && err != -EBUSY)
		return err;

	/* the FPU context is blank, nobody can own it */
	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;

	err = common_cpu_up(cpu, tidle);
	if (err)
		return err;

	err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered);
	if (err) {
		pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
		ret = -EIO;
		goto unreg_nmi;
	}

	/*
	 * Check TSC synchronization with the AP (keep irqs disabled
	 * while doing so):
	 */
	local_irq_save(flags);
	check_tsc_sync_source(cpu);
	local_irq_restore(flags);

	while (!cpu_online(cpu)) {
		cpu_relax();
		touch_nmi_watchdog();
	}

unreg_nmi:
	/*
	 * Clean up the nmi handler. Do this after the callin and callout sync
	 * to avoid impact of possible long unregister time.
	 */
	if (cpu0_nmi_registered)
		unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");

	return ret;
}

/**
 * arch_disable_smp_support() - disables SMP support for x86 at runtime
 */
void arch_disable_smp_support(void)
{
	disable_ioapic_support();
}

/*
 * Fall back to non SMP mode after errors.
 *
 * RED-PEN audit/test this more. I bet there is more state messed up here.
 */
static __init void disable_smp(void)
{
	pr_info("SMP disabled\n");

	disable_ioapic_support();

	init_cpu_present(cpumask_of(0));
	init_cpu_possible(cpumask_of(0));

	if (smp_found_config)
		physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
	else
		physid_set_mask_of_physid(0, &phys_cpu_present_map);
	cpumask_set_cpu(0, topology_sibling_cpumask(0));
	cpumask_set_cpu(0, topology_core_cpumask(0));
	cpumask_set_cpu(0, topology_die_cpumask(0));
}

/*
 * Various sanity checks.
 */
static void __init smp_sanity_check(void)
{
	preempt_disable();

#if !defined(CONFIG_X86_BIGSMP) && defined(CONFIG_X86_32)
	if (def_to_bigsmp && nr_cpu_ids > 8) {
		unsigned int cpu;
		unsigned nr;

		pr_warn("More than 8 CPUs detected - skipping them\n"
			"Use CONFIG_X86_BIGSMP\n");

		nr = 0;
		for_each_present_cpu(cpu) {
			if (nr >= 8)
				set_cpu_present(cpu, false);
			nr++;
		}

		nr = 0;
		for_each_possible_cpu(cpu) {
			if (nr >= 8)
				set_cpu_possible(cpu, false);
			nr++;
		}

		nr_cpu_ids = 8;
	}
#endif

	if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) {
		pr_warn("weird, boot CPU (#%d) not listed by the BIOS\n",
			hard_smp_processor_id());

		physid_set(hard_smp_processor_id(), phys_cpu_present_map);
	}

	/*
	 * Should not be necessary because the MP table should list the boot
	 * CPU too, but we do it for the sake of robustness anyway.
	 */
	if (!apic->check_phys_apicid_present(boot_cpu_physical_apicid)) {
		pr_notice("weird, boot CPU (#%d) not listed by the BIOS\n",
			  boot_cpu_physical_apicid);
		physid_set(hard_smp_processor_id(), phys_cpu_present_map);
	}
	preempt_enable();
}

static void __init smp_cpu_index_default(void)
{
	int i;
	struct cpuinfo_x86 *c;

	for_each_possible_cpu(i) {
		c = &cpu_data(i);
		/* mark all to hotplug */
		c->cpu_index = nr_cpu_ids;
	}
}

static void __init smp_get_logical_apicid(void)
{
	if (x2apic_mode)
		cpu0_logical_apicid = apic_read(APIC_LDR);
	else
		cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
}

void __init smp_prepare_cpus_common(void)
{
	unsigned int i;

	smp_cpu_index_default();

	/*
	 * Setup boot CPU information
	 */
	smp_store_boot_cpu_info(); /* Final full version of the data */
	cpumask_copy(cpu_callin_mask, cpumask_of(0));
	mb();

	for_each_possible_cpu(i) {
		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
		zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
		zalloc_cpumask_var(&per_cpu(cpu_l2c_shared_map, i), GFP_KERNEL);
	}

	/*
	 * Set 'default' x86 topology, this matches default_topology() in that
	 * it has NUMA nodes as a topology level. See also
	 * native_smp_cpus_done().
	 *
	 * Must be done before set_cpus_sibling_map() is ran.
	 */
	set_sched_topology(x86_topology);

	set_cpu_sibling_map(0);
}

/*
 * Prepare for SMP bootup.
 * @max_cpus: configured maximum number of CPUs, It is a legacy parameter
 *            for common interface support.
 */
void __init native_smp_prepare_cpus(unsigned int max_cpus)
{
	smp_prepare_cpus_common();

	init_freq_invariance(false, false);
	smp_sanity_check();

	switch (apic_intr_mode) {
	case APIC_PIC:
	case APIC_VIRTUAL_WIRE_NO_CONFIG:
		disable_smp();
		return;
	case APIC_SYMMETRIC_IO_NO_ROUTING:
		disable_smp();
		/* Setup local timer */
		x86_init.timers.setup_percpu_clockev();
		return;
	case APIC_VIRTUAL_WIRE:
	case APIC_SYMMETRIC_IO:
		break;
	}

	/* Setup local timer */
	x86_init.timers.setup_percpu_clockev();

	smp_get_logical_apicid();

	pr_info("CPU0: ");
	print_cpu_info(&cpu_data(0));

	uv_system_init();

	set_mtrr_aps_delayed_init();

	smp_quirk_init_udelay();

	speculative_store_bypass_ht_init();
}

void arch_thaw_secondary_cpus_begin(void)
{
	set_mtrr_aps_delayed_init();
}

void arch_thaw_secondary_cpus_end(void)
{
	mtrr_aps_init();
}

/*
 * Early setup to make printk work.
 */
void __init native_smp_prepare_boot_cpu(void)
{
	int me = smp_processor_id();
	switch_to_new_gdt(me);
	/* already set me in cpu_online_mask in boot_cpu_init() */
	cpumask_set_cpu(me, cpu_callout_mask);
	cpu_set_state_online(me);
	native_pv_lock_init();
}

void __init calculate_max_logical_packages(void)
{
	int ncpus;

	/*
	 * Today neither Intel nor AMD support heterogeneous systems so
	 * extrapolate the boot cpu's data to all packages.
	 */
	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
	pr_info("Max logical packages: %u\n", __max_logical_packages);
}

void __init native_smp_cpus_done(unsigned int max_cpus)
{
	pr_debug("Boot done\n");

	calculate_max_logical_packages();

	if (x86_has_numa_in_package)
		set_sched_topology(x86_numa_in_package_topology);

	nmi_selftest();
	impress_friends();
	mtrr_aps_init();
}

static int __initdata setup_possible_cpus = -1;
static int __init _setup_possible_cpus(char *str)
{
	get_option(&str, &setup_possible_cpus);
	return 0;
}
early_param("possible_cpus", _setup_possible_cpus);


/*
 * cpu_possible_mask should be static, it cannot change as cpu's
 * are onlined, or offlined. The reason is per-cpu data-structures
 * are allocated by some modules at init time, and don't expect to
 * do this dynamically on cpu arrival/departure.
 * cpu_present_mask on the other hand can change dynamically.
 * In case when cpu_hotplug is not compiled, then we resort to current
 * behaviour, which is cpu_possible == cpu_present.
 * - Ashok Raj
 *
 * Three ways to find out the number of additional hotplug CPUs:
 * - If the BIOS specified disabled CPUs in ACPI/mptables use that.
 * - The user can overwrite it with possible_cpus=NUM
 * - Otherwise don't reserve additional CPUs.
 * We do this because additional CPUs waste a lot of memory.
 * -AK
 */
__init void prefill_possible_map(void)
{
	int i, possible;

	/* No boot processor was found in mptable or ACPI MADT */
	if (!num_processors) {
		if (boot_cpu_has(X86_FEATURE_APIC)) {
			int apicid = boot_cpu_physical_apicid;
			int cpu = hard_smp_processor_id();

			pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu);

			/* Make sure boot cpu is enumerated */
			if (apic->cpu_present_to_apicid(0) == BAD_APICID &&
			    apic->apic_id_valid(apicid))
				generic_processor_info(apicid, boot_cpu_apic_version);
		}

		if (!num_processors)
			num_processors = 1;
	}

	i = setup_max_cpus ?: 1;
	if (setup_possible_cpus == -1) {
		possible = num_processors;
#ifdef CONFIG_HOTPLUG_CPU
		if (setup_max_cpus)
			possible += disabled_cpus;
#else
		if (possible > i)
			possible = i;
#endif
	} else
		possible = setup_possible_cpus;

	total_cpus = max_t(int, possible, num_processors + disabled_cpus);

	/* nr_cpu_ids could be reduced via nr_cpus= */
	if (possible > nr_cpu_ids) {
		pr_warn("%d Processors exceeds NR_CPUS limit of %u\n",
			possible, nr_cpu_ids);
		possible = nr_cpu_ids;
	}

#ifdef CONFIG_HOTPLUG_CPU
	if (!setup_max_cpus)
#endif
	if (possible > i) {
		pr_warn("%d Processors exceeds max_cpus limit of %u\n",
			possible, setup_max_cpus);
		possible = i;
	}

	nr_cpu_ids = possible;

	pr_info("Allowing %d CPUs, %d hotplug CPUs\n",
		possible, max_t(int, possible - num_processors, 0));

	reset_cpu_possible_mask();

	for (i = 0; i < possible; i++)
		set_cpu_possible(i, true);
}

#ifdef CONFIG_HOTPLUG_CPU

/* Recompute SMT state for all CPUs on offline */
static void recompute_smt_state(void)
{
	int max_threads, cpu;

	max_threads = 0;
	for_each_online_cpu (cpu) {
		int threads = cpumask_weight(topology_sibling_cpumask(cpu));

		if (threads > max_threads)
			max_threads = threads;
	}
	__max_smt_threads = max_threads;
}

static void remove_siblinginfo(int cpu)
{
	int sibling;
	struct cpuinfo_x86 *c = &cpu_data(cpu);

	for_each_cpu(sibling, topology_core_cpumask(cpu)) {
		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
		/*/
		 * last thread sibling in this cpu core going down
		 */
		if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1)
			cpu_data(sibling).booted_cores--;
	}

	for_each_cpu(sibling, topology_die_cpumask(cpu))
		cpumask_clear_cpu(cpu, topology_die_cpumask(sibling));

	for_each_cpu(sibling, topology_sibling_cpumask(cpu)) {
		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
		if (cpumask_weight(topology_sibling_cpumask(sibling)) == 1)
			cpu_data(sibling).smt_active = false;
	}

	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
	for_each_cpu(sibling, cpu_l2c_shared_mask(cpu))
		cpumask_clear_cpu(cpu, cpu_l2c_shared_mask(sibling));
	cpumask_clear(cpu_llc_shared_mask(cpu));
	cpumask_clear(cpu_l2c_shared_mask(cpu));
	cpumask_clear(topology_sibling_cpumask(cpu));
	cpumask_clear(topology_core_cpumask(cpu));
	cpumask_clear(topology_die_cpumask(cpu));
	c->cpu_core_id = 0;
	c->booted_cores = 0;
	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
	recompute_smt_state();
}

static void remove_cpu_from_maps(int cpu)
{
	set_cpu_online(cpu, false);
	cpumask_clear_cpu(cpu, cpu_callout_mask);
	cpumask_clear_cpu(cpu, cpu_callin_mask);
	/* was set by cpu_init() */
	cpumask_clear_cpu(cpu, cpu_initialized_mask);
	numa_remove_cpu(cpu);
}

void cpu_disable_common(void)
{
	int cpu = smp_processor_id();

	remove_siblinginfo(cpu);

	/* It's now safe to remove this processor from the online map */
	lock_vector_lock();
	remove_cpu_from_maps(cpu);
	unlock_vector_lock();
	fixup_irqs();
	lapic_offline();
}

int native_cpu_disable(void)
{
	int ret;

	ret = lapic_can_unplug_cpu();
	if (ret)
		return ret;

	cpu_disable_common();

        /*
         * Disable the local APIC. Otherwise IPI broadcasts will reach
         * it. It still responds normally to INIT, NMI, SMI, and SIPI
         * messages.
         *
         * Disabling the APIC must happen after cpu_disable_common()
         * which invokes fixup_irqs().
         *
         * Disabling the APIC preserves already set bits in IRR, but
         * an interrupt arriving after disabling the local APIC does not
         * set the corresponding IRR bit.
         *
         * fixup_irqs() scans IRR for set bits so it can raise a not
         * yet handled interrupt on the new destination CPU via an IPI
         * but obviously it can't do so for IRR bits which are not set.
         * IOW, interrupts arriving after disabling the local APIC will
         * be lost.
         */
	apic_soft_disable();

	return 0;
}

int common_cpu_die(unsigned int cpu)
{
	int ret = 0;

	/* We don't do anything here: idle task is faking death itself. */

	/* They ack this in play_dead() by setting CPU_DEAD */
	if (cpu_wait_death(cpu, 5)) {
		if (system_state == SYSTEM_RUNNING)
			pr_info("CPU %u is now offline\n", cpu);
	} else {
		pr_err("CPU %u didn't die...\n", cpu);
		ret = -1;
	}

	return ret;
}

void native_cpu_die(unsigned int cpu)
{
	common_cpu_die(cpu);
}

void play_dead_common(void)
{
	idle_task_exit();

	/* Ack it */
	(void)cpu_report_death();

	/*
	 * With physical CPU hotplug, we should halt the cpu
	 */
	local_irq_disable();
}

/**
 * cond_wakeup_cpu0 - Wake up CPU0 if needed.
 *
 * If NMI wants to wake up CPU0, start CPU0.
 */
void cond_wakeup_cpu0(void)
{
	if (smp_processor_id() == 0 && enable_start_cpu0)
		start_cpu0();
}
EXPORT_SYMBOL_GPL(cond_wakeup_cpu0);

/*
 * We need to flush the caches before going to sleep, lest we have
 * dirty data in our caches when we come back up.
 */
static inline void mwait_play_dead(void)
{
	unsigned int eax, ebx, ecx, edx;
	unsigned int highest_cstate = 0;
	unsigned int highest_subcstate = 0;
	void *mwait_ptr;
	int i;

	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
		return;
	if (!this_cpu_has(X86_FEATURE_MWAIT))
		return;
	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
		return;
	if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
		return;

	eax = CPUID_MWAIT_LEAF;
	ecx = 0;
	native_cpuid(&eax, &ebx, &ecx, &edx);

	/*
	 * eax will be 0 if EDX enumeration is not valid.
	 * Initialized below to cstate, sub_cstate value when EDX is valid.
	 */
	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
		eax = 0;
	} else {
		edx >>= MWAIT_SUBSTATE_SIZE;
		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
			if (edx & MWAIT_SUBSTATE_MASK) {
				highest_cstate = i;
				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
			}
		}
		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
			(highest_subcstate - 1);
	}

	/*
	 * This should be a memory location in a cache line which is
	 * unlikely to be touched by other processors.  The actual
	 * content is immaterial as it is not actually modified in any way.
	 */
	mwait_ptr = &current_thread_info()->flags;

	wbinvd();

	while (1) {
		/*
		 * The CLFLUSH is a workaround for erratum AAI65 for
		 * the Xeon 7400 series.  It's not clear it is actually
		 * needed, but it should be harmless in either case.
		 * The WBINVD is insufficient due to the spurious-wakeup
		 * case where we return around the loop.
		 */
		mb();
		clflush(mwait_ptr);
		mb();
		__monitor(mwait_ptr, 0, 0);
		mb();
		__mwait(eax, 0);

		cond_wakeup_cpu0();
	}
}

void hlt_play_dead(void)
{
	if (__this_cpu_read(cpu_info.x86) >= 4)
		wbinvd();

	while (1) {
		native_halt();

		cond_wakeup_cpu0();
	}
}

void native_play_dead(void)
{
	play_dead_common();
	tboot_shutdown(TB_SHUTDOWN_WFS);

	mwait_play_dead();	/* Only returns on failure */
	if (cpuidle_play_dead())
		hlt_play_dead();
}

#else /* ... !CONFIG_HOTPLUG_CPU */
int native_cpu_disable(void)
{
	return -ENOSYS;
}

void native_cpu_die(unsigned int cpu)
{
	/* We said "no" in __cpu_disable */
	BUG();
}

void native_play_dead(void)
{
	BUG();
}

#endif

#ifdef CONFIG_X86_64
/*
 * APERF/MPERF frequency ratio computation.
 *
 * The scheduler wants to do frequency invariant accounting and needs a <1
 * ratio to account for the 'current' frequency, corresponding to
 * freq_curr / freq_max.
 *
 * Since the frequency freq_curr on x86 is controlled by micro-controller and
 * our P-state setting is little more than a request/hint, we need to observe
 * the effective frequency 'BusyMHz', i.e. the average frequency over a time
 * interval after discarding idle time. This is given by:
 *
 *   BusyMHz = delta_APERF / delta_MPERF * freq_base
 *
 * where freq_base is the max non-turbo P-state.
 *
 * The freq_max term has to be set to a somewhat arbitrary value, because we
 * can't know which turbo states will be available at a given point in time:
 * it all depends on the thermal headroom of the entire package. We set it to
 * the turbo level with 4 cores active.
 *
 * Benchmarks show that's a good compromise between the 1C turbo ratio
 * (freq_curr/freq_max would rarely reach 1) and something close to freq_base,
 * which would ignore the entire turbo range (a conspicuous part, making
 * freq_curr/freq_max always maxed out).
 *
 * An exception to the heuristic above is the Atom uarch, where we choose the
 * highest turbo level for freq_max since Atom's are generally oriented towards
 * power efficiency.
 *
 * Setting freq_max to anything less than the 1C turbo ratio makes the ratio
 * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1.
 */

DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key);

static DEFINE_PER_CPU(u64, arch_prev_aperf);
static DEFINE_PER_CPU(u64, arch_prev_mperf);
static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE;
static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE;

void arch_set_max_freq_ratio(bool turbo_disabled)
{
	arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE :
					arch_turbo_freq_ratio;
}
EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio);

static bool turbo_disabled(void)
{
	u64 misc_en;
	int err;

	err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en);
	if (err)
		return false;

	return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
}

static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
{
	int err;

	err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq);
	if (err)
		return false;

	err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
	if (err)
		return false;

	*base_freq = (*base_freq >> 16) & 0x3F;     /* max P state */
	*turbo_freq = *turbo_freq & 0x3F;           /* 1C turbo    */

	return true;
}

#define X86_MATCH(model)					\
	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6,		\
		INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL)

static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = {
	X86_MATCH(XEON_PHI_KNL),
	X86_MATCH(XEON_PHI_KNM),
	{}
};

static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = {
	X86_MATCH(SKYLAKE_X),
	{}
};

static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = {
	X86_MATCH(ATOM_GOLDMONT),
	X86_MATCH(ATOM_GOLDMONT_D),
	X86_MATCH(ATOM_GOLDMONT_PLUS),
	{}
};

static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
				int num_delta_fratio)
{
	int fratio, delta_fratio, found;
	int err, i;
	u64 msr;

	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
	if (err)
		return false;

	*base_freq = (*base_freq >> 8) & 0xFF;	    /* max P state */

	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
	if (err)
		return false;

	fratio = (msr >> 8) & 0xFF;
	i = 16;
	found = 0;
	do {
		if (found >= num_delta_fratio) {
			*turbo_freq = fratio;
			return true;
		}

		delta_fratio = (msr >> (i + 5)) & 0x7;

		if (delta_fratio) {
			found += 1;
			fratio -= delta_fratio;
		}

		i += 8;
	} while (i < 64);

	return true;
}

static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
{
	u64 ratios, counts;
	u32 group_size;
	int err, i;

	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
	if (err)
		return false;

	*base_freq = (*base_freq >> 8) & 0xFF;      /* max P state */

	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
	if (err)
		return false;

	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
	if (err)
		return false;

	for (i = 0; i < 64; i += 8) {
		group_size = (counts >> i) & 0xFF;
		if (group_size >= size) {
			*turbo_freq = (ratios >> i) & 0xFF;
			return true;
		}
	}

	return false;
}

static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
{
	u64 msr;
	int err;

	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
	if (err)
		return false;

	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
	if (err)
		return false;

	*base_freq = (*base_freq >> 8) & 0xFF;    /* max P state */
	*turbo_freq = (msr >> 24) & 0xFF;         /* 4C turbo    */

	/* The CPU may have less than 4 cores */
	if (!*turbo_freq)
		*turbo_freq = msr & 0xFF;         /* 1C turbo    */

	return true;
}

static bool intel_set_max_freq_ratio(void)
{
	u64 base_freq, turbo_freq;
	u64 turbo_ratio;

	if (slv_set_max_freq_ratio(&base_freq, &turbo_freq))
		goto out;

	if (x86_match_cpu(has_glm_turbo_ratio_limits) &&
	    skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
		goto out;

	if (x86_match_cpu(has_knl_turbo_ratio_limits) &&
	    knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
		goto out;

	if (x86_match_cpu(has_skx_turbo_ratio_limits) &&
	    skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4))
		goto out;

	if (core_set_max_freq_ratio(&base_freq, &turbo_freq))
		goto out;

	return false;

out:
	/*
	 * Some hypervisors advertise X86_FEATURE_APERFMPERF
	 * but then fill all MSR's with zeroes.
	 * Some CPUs have turbo boost but don't declare any turbo ratio
	 * in MSR_TURBO_RATIO_LIMIT.
	 */
	if (!base_freq || !turbo_freq) {
		pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n");
		return false;
	}

	turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq);
	if (!turbo_ratio) {
		pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n");
		return false;
	}

	arch_turbo_freq_ratio = turbo_ratio;
	arch_set_max_freq_ratio(turbo_disabled());

	return true;
}

#ifdef CONFIG_ACPI_CPPC_LIB
static bool amd_set_max_freq_ratio(void)
{
	struct cppc_perf_caps perf_caps;
	u64 highest_perf, nominal_perf;
	u64 perf_ratio;
	int rc;

	rc = cppc_get_perf_caps(0, &perf_caps);
	if (rc) {
		pr_debug("Could not retrieve perf counters (%d)\n", rc);
		return false;
	}

	highest_perf = amd_get_highest_perf();
	nominal_perf = perf_caps.nominal_perf;

	if (!highest_perf || !nominal_perf) {
		pr_debug("Could not retrieve highest or nominal performance\n");
		return false;
	}

	perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
	/* midpoint between max_boost and max_P */
	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
	if (!perf_ratio) {
		pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
		return false;
	}

	arch_turbo_freq_ratio = perf_ratio;
	arch_set_max_freq_ratio(false);

	return true;
}
#else
static bool amd_set_max_freq_ratio(void)
{
	return false;
}
#endif

static void init_counter_refs(void)
{
	u64 aperf, mperf;

	rdmsrl(MSR_IA32_APERF, aperf);
	rdmsrl(MSR_IA32_MPERF, mperf);

	this_cpu_write(arch_prev_aperf, aperf);
	this_cpu_write(arch_prev_mperf, mperf);
}

#ifdef CONFIG_PM_SLEEP
static struct syscore_ops freq_invariance_syscore_ops = {
	.resume = init_counter_refs,
};

static void register_freq_invariance_syscore_ops(void)
{
	/* Bail out if registered already. */
	if (freq_invariance_syscore_ops.node.prev)
		return;

	register_syscore_ops(&freq_invariance_syscore_ops);
}
#else
static inline void register_freq_invariance_syscore_ops(void) {}
#endif

static void init_freq_invariance(bool secondary, bool cppc_ready)
{
	bool ret = false;

	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
		return;

	if (secondary) {
		if (static_branch_likely(&arch_scale_freq_key)) {
			init_counter_refs();
		}
		return;
	}

	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
		ret = intel_set_max_freq_ratio();
	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
		if (!cppc_ready) {
			return;
		}
		ret = amd_set_max_freq_ratio();
	}

	if (ret) {
		init_counter_refs();
		static_branch_enable(&arch_scale_freq_key);
		register_freq_invariance_syscore_ops();
		pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
	} else {
		pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
	}
}

#ifdef CONFIG_ACPI_CPPC_LIB
static DEFINE_MUTEX(freq_invariance_lock);

void init_freq_invariance_cppc(void)
{
	static bool secondary;

	mutex_lock(&freq_invariance_lock);

	init_freq_invariance(secondary, true);
	secondary = true;

	mutex_unlock(&freq_invariance_lock);
}
#endif

static void disable_freq_invariance_workfn(struct work_struct *work)
{
	static_branch_disable(&arch_scale_freq_key);
}

static DECLARE_WORK(disable_freq_invariance_work,
		    disable_freq_invariance_workfn);

DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;

void arch_scale_freq_tick(void)
{
	u64 freq_scale;
	u64 aperf, mperf;
	u64 acnt, mcnt;

	if (!arch_scale_freq_invariant())
		return;

	rdmsrl(MSR_IA32_APERF, aperf);
	rdmsrl(MSR_IA32_MPERF, mperf);

	acnt = aperf - this_cpu_read(arch_prev_aperf);
	mcnt = mperf - this_cpu_read(arch_prev_mperf);

	this_cpu_write(arch_prev_aperf, aperf);
	this_cpu_write(arch_prev_mperf, mperf);

	if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt))
		goto error;

	if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt)
		goto error;

	freq_scale = div64_u64(acnt, mcnt);
	if (!freq_scale)
		goto error;

	if (freq_scale > SCHED_CAPACITY_SCALE)
		freq_scale = SCHED_CAPACITY_SCALE;

	this_cpu_write(arch_freq_scale, freq_scale);
	return;

error:
	pr_warn("Scheduler frequency invariance went wobbly, disabling!\n");
	schedule_work(&disable_freq_invariance_work);
}
#else
static inline void init_freq_invariance(bool secondary, bool cppc_ready)
{
}
#endif /* CONFIG_X86_64 */