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
|
// 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/kexec.h>
#include <linux/numa.h>
#include <linux/pgtable.h>
#include <linux/overflow.h>
#include <linux/stackprotector.h>
#include <linux/cpuhotplug.h>
#include <linux/mc146818rtc.h>
#include <asm/acpi.h>
#include <asm/cacheinfo.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 <asm/microcode.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>
#include <asm/sev.h>
/* 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);
/* Per CPU bogomips and other parameters */
DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
/* CPUs which are the primary SMT threads */
struct cpumask __cpu_primary_thread_mask __read_mostly;
/* Representing CPUs for which sibling maps can be computed */
static cpumask_var_t cpu_sibling_setup_mask;
struct mwait_cpu_dead {
unsigned int control;
unsigned int status;
};
#define CPUDEAD_MWAIT_WAIT 0xDEADBEEF
#define CPUDEAD_MWAIT_KEXEC_HLT 0x4A17DEAD
/*
* Cache line aligned data for mwait_play_dead(). Separate on purpose so
* that it's unlikely to be touched by other CPUs.
*/
static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead);
/* 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 unsigned int smpboot_warm_reset_vector_count;
static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
{
unsigned long flags;
spin_lock_irqsave(&rtc_lock, flags);
if (!smpboot_warm_reset_vector_count++) {
CMOS_WRITE(0xa, 0xf);
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = start_eip >> 4;
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = start_eip & 0xf;
}
spin_unlock_irqrestore(&rtc_lock, flags);
}
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);
if (!--smpboot_warm_reset_vector_count) {
CMOS_WRITE(0, 0xf);
*((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
}
spin_unlock_irqrestore(&rtc_lock, flags);
}
/* Run the next set of setup steps for the upcoming CPU */
static void ap_starting(void)
{
int cpuid = smp_processor_id();
/* Mop up eventual mwait_play_dead() wreckage */
this_cpu_write(mwait_cpu_dead.status, 0);
this_cpu_write(mwait_cpu_dead.control, 0);
/*
* If woken up by an INIT in an 82489DX configuration the alive
* synchronization guarantees that the CPU does not reach this
* point before an INIT_deassert IPI reaches the local APIC, so it
* is now safe to touch the local APIC.
*
* Set up this CPU, first the APIC, which is probably redundant on
* most boards.
*/
apic_ap_setup();
/* Save the processor parameters. */
smp_store_cpu_info(cpuid);
/*
* The topology information must be up to date before
* notify_cpu_starting().
*/
set_cpu_sibling_map(cpuid);
ap_init_aperfmperf();
pr_debug("Stack at about %p\n", &cpuid);
wmb();
/*
* This runs the AP through all the cpuhp states to its target
* state CPUHP_ONLINE.
*/
notify_cpu_starting(cpuid);
}
static void ap_calibrate_delay(void)
{
/*
* Calibrate the delay loop and update loops_per_jiffy in cpu_data.
* smp_store_cpu_info() stored a value that is close but not as
* accurate as the value just calculated.
*
* As this is invoked after the TSC synchronization check,
* calibrate_delay_is_known() will skip the calibration routine
* when TSC is synchronized across sockets.
*/
calibrate_delay();
cpu_data(smp_processor_id()).loops_per_jiffy = loops_per_jiffy;
}
/*
* 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();
/*
* 32-bit specific. 64-bit reaches this code with the correct page
* table established. Yet another historical divergence.
*/
if (IS_ENABLED(CONFIG_X86_32)) {
/* switch away from the initial page table */
load_cr3(swapper_pg_dir);
__flush_tlb_all();
}
cpu_init_exception_handling();
/*
* 32-bit systems load the microcode from the ASM startup code for
* historical reasons.
*
* On 64-bit systems load it before reaching the AP alive
* synchronization point below so it is not part of the full per
* CPU serialized bringup part when "parallel" bringup is enabled.
*
* That's even safe when hyperthreading is enabled in the CPU as
* the core code starts the primary threads first and leaves the
* secondary threads waiting for SIPI. Loading microcode on
* physical cores concurrently is a safe operation.
*
* This covers both the Intel specific issue that concurrent
* microcode loading on SMT siblings must be prohibited and the
* vendor independent issue`that microcode loading which changes
* CPUID, MSRs etc. must be strictly serialized to maintain
* software state correctness.
*/
if (IS_ENABLED(CONFIG_X86_64))
load_ucode_ap();
/*
* Synchronization point with the hotplug core. Sets this CPUs
* synchronization state to ALIVE and spin-waits for the control CPU to
* release this CPU for further bringup.
*/
cpuhp_ap_sync_alive();
cpu_init();
fpu__init_cpu();
rcu_cpu_starting(raw_smp_processor_id());
x86_cpuinit.early_percpu_clock_init();
ap_starting();
/* Check TSC synchronization with the control CPU. */
check_tsc_sync_target();
/*
* Calibrate the delay loop after the TSC synchronization check.
* This allows to skip the calibration when TSC is synchronized
* across sockets.
*/
ap_calibrate_delay();
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();
x86_platform.nmi_init();
/* enable local interrupts */
local_irq_enable();
x86_cpuinit.setup_percpu_clockev();
wmb();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
/**
* topology_phys_to_logical_pkg - Map a physical package id to a logical
* @phys_pkg: The physical package id to map
*
* 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
* @die_id: The physical die id to map
* @cur_cpu: The CPU for which the mapping is done
*
* Returns logical die id or -1 if not found
*/
static int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
{
int cpu, 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;
}
/**
* 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;
}
static 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 an AP.
*/
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");
}
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();
}
#endif
#ifdef CONFIG_SCHED_CLUSTER
static int x86_cluster_flags(void)
{
return cpu_cluster_flags() | x86_sched_itmt_flags();
}
#endif
static int x86_die_flags(void)
{
if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
return x86_sched_itmt_flags();
return 0;
}
/*
* 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;
static struct sched_domain_topology_level x86_topology[6];
static void __init build_sched_topology(void)
{
int i = 0;
#ifdef CONFIG_SCHED_SMT
x86_topology[i++] = (struct sched_domain_topology_level){
cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT)
};
#endif
#ifdef CONFIG_SCHED_CLUSTER
x86_topology[i++] = (struct sched_domain_topology_level){
cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS)
};
#endif
#ifdef CONFIG_SCHED_MC
x86_topology[i++] = (struct sched_domain_topology_level){
cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC)
};
#endif
/*
* When there is NUMA topology inside the package skip the DIE domain
* since the NUMA domains will auto-magically create the right spanning
* domains based on the SLIT.
*/
if (!x86_has_numa_in_package) {
x86_topology[i++] = (struct sched_domain_topology_level){
cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(DIE)
};
}
/*
* There must be one trailing NULL entry left.
*/
BUG_ON(i >= ARRAY_SIZE(x86_topology)-1);
set_sched_topology(x86_topology);
}
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_online_cpu(cpu)
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");
}
/*
* 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;
}
/*
* Wake up AP by INIT, INIT, STARTUP sequence.
*/
static void send_init_sequence(int phys_apicid)
{
int maxlvt = lapic_get_maxlvt();
/* Be paranoid about clearing APIC errors. */
if (APIC_INTEGRATED(boot_cpu_apic_version)) {
/* Due to the Pentium erratum 3AP. */
if (maxlvt > 3)
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
}
/* Assert INIT on the target CPU */
apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT, phys_apicid);
safe_apic_wait_icr_idle();
udelay(init_udelay);
/* Deassert INIT on the target CPU */
apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);
safe_apic_wait_icr_idle();
}
/*
* Wake up AP by INIT, INIT, STARTUP sequence.
*/
static int wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
{
unsigned long send_status = 0, accept_status = 0;
int num_starts, j, maxlvt;
preempt_disable();
maxlvt = lapic_get_maxlvt();
send_init_sequence(phys_apicid);
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);
preempt_enable();
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 width, node_width, first = 1;
static int current_node = NUMA_NO_NODE;
int node = early_cpu_to_node(cpu);
if (!width)
width = num_digits(num_possible_cpus()) + 1; /* + '#' sign */
if (!node_width)
node_width = num_digits(num_possible_nodes()) + 1; /* + '#' */
if (system_state < SYSTEM_RUNNING) {
if (first)
pr_info("x86: Booting SMP configuration:\n");
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 (first)
pr_cont("%*s", width + 1, " ");
first = 0;
pr_cont("%*s#%d", width - num_digits(cpu), " ", cpu);
} else
pr_info("Booting Node %d Processor %d APIC 0x%x\n",
node, cpu, apicid);
}
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(pcpu_hot.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(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle);
#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 startup was successfully sent, else error code from
* ->wakeup_secondary_cpu.
*/
static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
{
unsigned long start_ip = real_mode_header->trampoline_start;
int ret;
#ifdef CONFIG_X86_64
/* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */
if (apic->wakeup_secondary_cpu_64)
start_ip = real_mode_header->trampoline_start64;
#endif
idle->thread.sp = (unsigned long)task_pt_regs(idle);
initial_code = (unsigned long)start_secondary;
if (IS_ENABLED(CONFIG_X86_32)) {
early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu);
initial_stack = idle->thread.sp;
} else if (!(smpboot_control & STARTUP_PARALLEL_MASK)) {
smpboot_control = cpu;
}
/* 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);
}
}
smp_mb();
/*
* Wake up a CPU in difference cases:
* - Use a method from the APIC driver if one defined, with wakeup
* straight to 64-bit mode preferred over wakeup to RM.
* Otherwise,
* - Use an INIT boot APIC message
*/
if (apic->wakeup_secondary_cpu_64)
ret = apic->wakeup_secondary_cpu_64(apicid, start_ip);
else if (apic->wakeup_secondary_cpu)
ret = apic->wakeup_secondary_cpu(apicid, start_ip);
else
ret = wakeup_secondary_cpu_via_init(apicid, start_ip);
/* If the wakeup mechanism failed, cleanup the warm reset vector */
if (ret)
arch_cpuhp_cleanup_kick_cpu(cpu);
return ret;
}
int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
{
int apicid = apic->cpu_present_to_apicid(cpu);
int err;
lockdep_assert_irqs_enabled();
pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu);
if (apicid == BAD_APICID || !physid_isset(apicid, phys_cpu_present_map) ||
!apic_id_valid(apicid)) {
pr_err("%s: bad cpu %d\n", __func__, cpu);
return -EINVAL;
}
/*
* 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();
/* 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);
if (err)
pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
return err;
}
int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle)
{
return smp_ops.kick_ap_alive(cpu, tidle);
}
void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu)
{
/* Cleanup possible dangling ends... */
if (smp_ops.kick_ap_alive == native_kick_ap && x86_platform.legacy.warm_reset)
smpboot_restore_warm_reset_vector();
}
void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
{
if (smp_ops.cleanup_dead_cpu)
smp_ops.cleanup_dead_cpu(cpu);
if (system_state == SYSTEM_RUNNING)
pr_info("CPU %u is now offline\n", cpu);
}
void arch_cpuhp_sync_state_poll(void)
{
if (smp_ops.poll_sync_state)
smp_ops.poll_sync_state();
}
/**
* arch_disable_smp_support() - Disables SMP support for x86 at boottime
*/
void __init 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));
}
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;
}
}
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 */
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_cpu_sibling_map(0);
}
#ifdef CONFIG_X86_64
/* Establish whether parallel bringup can be supported. */
bool __init arch_cpuhp_init_parallel_bringup(void)
{
if (!x86_cpuinit.parallel_bringup) {
pr_info("Parallel CPU startup disabled by the platform\n");
return false;
}
smpboot_control = STARTUP_READ_APICID;
pr_debug("Parallel CPU startup enabled: 0x%08x\n", smpboot_control);
return true;
}
#endif
/*
* 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();
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();
pr_info("CPU0: ");
print_cpu_info(&cpu_data(0));
uv_system_init();
smp_quirk_init_udelay();
speculative_store_bypass_ht_init();
snp_set_wakeup_secondary_cpu();
}
void arch_thaw_secondary_cpus_begin(void)
{
set_cache_aps_delayed_init(true);
}
void arch_thaw_secondary_cpus_end(void)
{
cache_aps_init();
}
/*
* Early setup to make printk work.
*/
void __init native_smp_prepare_boot_cpu(void)
{
int me = smp_processor_id();
/* SMP handles this from setup_per_cpu_areas() */
if (!IS_ENABLED(CONFIG_SMP))
switch_gdt_and_percpu_base(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();
build_sched_topology();
nmi_selftest();
impress_friends();
cache_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;
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;
}
set_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);
}
/* correctly size the local cpu masks */
void __init setup_cpu_local_masks(void)
{
alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
}
#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);
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;
}
void play_dead_common(void)
{
idle_task_exit();
cpuhp_ap_report_dead();
local_irq_disable();
}
/*
* 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)
{
struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
unsigned int eax, ebx, ecx, edx;
unsigned int highest_cstate = 0;
unsigned int highest_subcstate = 0;
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);
}
/* Set up state for the kexec() hack below */
md->status = CPUDEAD_MWAIT_WAIT;
md->control = CPUDEAD_MWAIT_WAIT;
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(md);
mb();
__monitor(md, 0, 0);
mb();
__mwait(eax, 0);
if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) {
/*
* Kexec is about to happen. Don't go back into mwait() as
* the kexec kernel might overwrite text and data including
* page tables and stack. So mwait() would resume when the
* monitor cache line is written to and then the CPU goes
* south due to overwritten text, page tables and stack.
*
* Note: This does _NOT_ protect against a stray MCE, NMI,
* SMI. They will resume execution at the instruction
* following the HLT instruction and run into the problem
* which this is trying to prevent.
*/
WRITE_ONCE(md->status, CPUDEAD_MWAIT_KEXEC_HLT);
while(1)
native_halt();
}
}
}
/*
* Kick all "offline" CPUs out of mwait on kexec(). See comment in
* mwait_play_dead().
*/
void smp_kick_mwait_play_dead(void)
{
u32 newstate = CPUDEAD_MWAIT_KEXEC_HLT;
struct mwait_cpu_dead *md;
unsigned int cpu, i;
for_each_cpu_andnot(cpu, cpu_present_mask, cpu_online_mask) {
md = per_cpu_ptr(&mwait_cpu_dead, cpu);
/* Does it sit in mwait_play_dead() ? */
if (READ_ONCE(md->status) != CPUDEAD_MWAIT_WAIT)
continue;
/* Wait up to 5ms */
for (i = 0; READ_ONCE(md->status) != newstate && i < 1000; i++) {
/* Bring it out of mwait */
WRITE_ONCE(md->control, newstate);
udelay(5);
}
if (READ_ONCE(md->status) != newstate)
pr_err_once("CPU%u is stuck in mwait_play_dead()\n", cpu);
}
}
void __noreturn hlt_play_dead(void)
{
if (__this_cpu_read(cpu_info.x86) >= 4)
wbinvd();
while (1)
native_halt();
}
void native_play_dead(void)
{
play_dead_common();
tboot_shutdown(TB_SHUTDOWN_WFS);
mwait_play_dead();
if (cpuidle_play_dead())
hlt_play_dead();
}
#else /* ... !CONFIG_HOTPLUG_CPU */
int native_cpu_disable(void)
{
return -ENOSYS;
}
void native_play_dead(void)
{
BUG();
}
#endif
|