summaryrefslogtreecommitdiffstats
path: root/kernel/cpu.c
blob: 34c09c3d37bc6420bdbf1687dcfbcfeaf0e0d960 (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
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
/* CPU control.
 * (C) 2001, 2002, 2003, 2004 Rusty Russell
 *
 * This code is licenced under the GPL.
 */
#include <linux/sched/mm.h>
#include <linux/proc_fs.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/sched/signal.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/task.h>
#include <linux/sched/smt.h>
#include <linux/unistd.h>
#include <linux/cpu.h>
#include <linux/oom.h>
#include <linux/rcupdate.h>
#include <linux/export.h>
#include <linux/bug.h>
#include <linux/kthread.h>
#include <linux/stop_machine.h>
#include <linux/mutex.h>
#include <linux/gfp.h>
#include <linux/suspend.h>
#include <linux/lockdep.h>
#include <linux/tick.h>
#include <linux/irq.h>
#include <linux/nmi.h>
#include <linux/smpboot.h>
#include <linux/relay.h>
#include <linux/slab.h>
#include <linux/percpu-rwsem.h>
#include <linux/cpuset.h>
#include <linux/random.h>

#include <trace/events/power.h>
#define CREATE_TRACE_POINTS
#include <trace/events/cpuhp.h>

#include "smpboot.h"

/**
 * cpuhp_cpu_state - Per cpu hotplug state storage
 * @state:	The current cpu state
 * @target:	The target state
 * @thread:	Pointer to the hotplug thread
 * @should_run:	Thread should execute
 * @rollback:	Perform a rollback
 * @single:	Single callback invocation
 * @bringup:	Single callback bringup or teardown selector
 * @cb_state:	The state for a single callback (install/uninstall)
 * @result:	Result of the operation
 * @done_up:	Signal completion to the issuer of the task for cpu-up
 * @done_down:	Signal completion to the issuer of the task for cpu-down
 */
struct cpuhp_cpu_state {
	enum cpuhp_state	state;
	enum cpuhp_state	target;
	enum cpuhp_state	fail;
#ifdef CONFIG_SMP
	struct task_struct	*thread;
	bool			should_run;
	bool			rollback;
	bool			single;
	bool			bringup;
	bool			booted_once;
	struct hlist_node	*node;
	struct hlist_node	*last;
	enum cpuhp_state	cb_state;
	int			result;
	struct completion	done_up;
	struct completion	done_down;
#endif
};

static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = {
	.fail = CPUHP_INVALID,
};

#if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
static struct lockdep_map cpuhp_state_up_map =
	STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map);
static struct lockdep_map cpuhp_state_down_map =
	STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map);


static inline void cpuhp_lock_acquire(bool bringup)
{
	lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
}

static inline void cpuhp_lock_release(bool bringup)
{
	lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
}
#else

static inline void cpuhp_lock_acquire(bool bringup) { }
static inline void cpuhp_lock_release(bool bringup) { }

#endif

/**
 * cpuhp_step - Hotplug state machine step
 * @name:	Name of the step
 * @startup:	Startup function of the step
 * @teardown:	Teardown function of the step
 * @cant_stop:	Bringup/teardown can't be stopped at this step
 */
struct cpuhp_step {
	const char		*name;
	union {
		int		(*single)(unsigned int cpu);
		int		(*multi)(unsigned int cpu,
					 struct hlist_node *node);
	} startup;
	union {
		int		(*single)(unsigned int cpu);
		int		(*multi)(unsigned int cpu,
					 struct hlist_node *node);
	} teardown;
	struct hlist_head	list;
	bool			cant_stop;
	bool			multi_instance;
};

static DEFINE_MUTEX(cpuhp_state_mutex);
static struct cpuhp_step cpuhp_hp_states[];

static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
{
	return cpuhp_hp_states + state;
}

/**
 * cpuhp_invoke_callback _ Invoke the callbacks for a given state
 * @cpu:	The cpu for which the callback should be invoked
 * @state:	The state to do callbacks for
 * @bringup:	True if the bringup callback should be invoked
 * @node:	For multi-instance, do a single entry callback for install/remove
 * @lastp:	For multi-instance rollback, remember how far we got
 *
 * Called from cpu hotplug and from the state register machinery.
 */
static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
				 bool bringup, struct hlist_node *node,
				 struct hlist_node **lastp)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	struct cpuhp_step *step = cpuhp_get_step(state);
	int (*cbm)(unsigned int cpu, struct hlist_node *node);
	int (*cb)(unsigned int cpu);
	int ret, cnt;

	if (st->fail == state) {
		st->fail = CPUHP_INVALID;

		if (!(bringup ? step->startup.single : step->teardown.single))
			return 0;

		return -EAGAIN;
	}

	if (!step->multi_instance) {
		WARN_ON_ONCE(lastp && *lastp);
		cb = bringup ? step->startup.single : step->teardown.single;
		if (!cb)
			return 0;
		trace_cpuhp_enter(cpu, st->target, state, cb);
		ret = cb(cpu);
		trace_cpuhp_exit(cpu, st->state, state, ret);
		return ret;
	}
	cbm = bringup ? step->startup.multi : step->teardown.multi;
	if (!cbm)
		return 0;

	/* Single invocation for instance add/remove */
	if (node) {
		WARN_ON_ONCE(lastp && *lastp);
		trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
		ret = cbm(cpu, node);
		trace_cpuhp_exit(cpu, st->state, state, ret);
		return ret;
	}

	/* State transition. Invoke on all instances */
	cnt = 0;
	hlist_for_each(node, &step->list) {
		if (lastp && node == *lastp)
			break;

		trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
		ret = cbm(cpu, node);
		trace_cpuhp_exit(cpu, st->state, state, ret);
		if (ret) {
			if (!lastp)
				goto err;

			*lastp = node;
			return ret;
		}
		cnt++;
	}
	if (lastp)
		*lastp = NULL;
	return 0;
err:
	/* Rollback the instances if one failed */
	cbm = !bringup ? step->startup.multi : step->teardown.multi;
	if (!cbm)
		return ret;

	hlist_for_each(node, &step->list) {
		if (!cnt--)
			break;

		trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
		ret = cbm(cpu, node);
		trace_cpuhp_exit(cpu, st->state, state, ret);
		/*
		 * Rollback must not fail,
		 */
		WARN_ON_ONCE(ret);
	}
	return ret;
}

#ifdef CONFIG_SMP
static bool cpuhp_is_ap_state(enum cpuhp_state state)
{
	/*
	 * The extra check for CPUHP_TEARDOWN_CPU is only for documentation
	 * purposes as that state is handled explicitly in cpu_down.
	 */
	return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
}

static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
{
	struct completion *done = bringup ? &st->done_up : &st->done_down;
	wait_for_completion(done);
}

static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
{
	struct completion *done = bringup ? &st->done_up : &st->done_down;
	complete(done);
}

/*
 * The former STARTING/DYING states, ran with IRQs disabled and must not fail.
 */
static bool cpuhp_is_atomic_state(enum cpuhp_state state)
{
	return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE;
}

/* Serializes the updates to cpu_online_mask, cpu_present_mask */
static DEFINE_MUTEX(cpu_add_remove_lock);
bool cpuhp_tasks_frozen;
EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);

/*
 * The following two APIs (cpu_maps_update_begin/done) must be used when
 * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
 */
void cpu_maps_update_begin(void)
{
	mutex_lock(&cpu_add_remove_lock);
}

void cpu_maps_update_done(void)
{
	mutex_unlock(&cpu_add_remove_lock);
}

/*
 * If set, cpu_up and cpu_down will return -EBUSY and do nothing.
 * Should always be manipulated under cpu_add_remove_lock
 */
static int cpu_hotplug_disabled;

#ifdef CONFIG_HOTPLUG_CPU

DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock);

void cpus_read_lock(void)
{
	percpu_down_read(&cpu_hotplug_lock);
}
EXPORT_SYMBOL_GPL(cpus_read_lock);

int cpus_read_trylock(void)
{
	return percpu_down_read_trylock(&cpu_hotplug_lock);
}
EXPORT_SYMBOL_GPL(cpus_read_trylock);

void cpus_read_unlock(void)
{
	percpu_up_read(&cpu_hotplug_lock);
}
EXPORT_SYMBOL_GPL(cpus_read_unlock);

void cpus_write_lock(void)
{
	percpu_down_write(&cpu_hotplug_lock);
}

void cpus_write_unlock(void)
{
	percpu_up_write(&cpu_hotplug_lock);
}

void lockdep_assert_cpus_held(void)
{
	/*
	 * We can't have hotplug operations before userspace starts running,
	 * and some init codepaths will knowingly not take the hotplug lock.
	 * This is all valid, so mute lockdep until it makes sense to report
	 * unheld locks.
	 */
	if (system_state < SYSTEM_RUNNING)
		return;

	percpu_rwsem_assert_held(&cpu_hotplug_lock);
}

/*
 * Wait for currently running CPU hotplug operations to complete (if any) and
 * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects
 * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the
 * hotplug path before performing hotplug operations. So acquiring that lock
 * guarantees mutual exclusion from any currently running hotplug operations.
 */
void cpu_hotplug_disable(void)
{
	cpu_maps_update_begin();
	cpu_hotplug_disabled++;
	cpu_maps_update_done();
}
EXPORT_SYMBOL_GPL(cpu_hotplug_disable);

static void __cpu_hotplug_enable(void)
{
	if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n"))
		return;
	cpu_hotplug_disabled--;
}

void cpu_hotplug_enable(void)
{
	cpu_maps_update_begin();
	__cpu_hotplug_enable();
	cpu_maps_update_done();
}
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
#endif	/* CONFIG_HOTPLUG_CPU */

/*
 * Architectures that need SMT-specific errata handling during SMT hotplug
 * should override this.
 */
void __weak arch_smt_update(void) { }

#ifdef CONFIG_HOTPLUG_SMT
enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;

void __init cpu_smt_disable(bool force)
{
	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
		cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
		return;

	if (force) {
		pr_info("SMT: Force disabled\n");
		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
	} else {
		pr_info("SMT: disabled\n");
		cpu_smt_control = CPU_SMT_DISABLED;
	}
}

/*
 * The decision whether SMT is supported can only be done after the full
 * CPU identification. Called from architecture code.
 */
void __init cpu_smt_check_topology(void)
{
	if (!topology_smt_supported())
		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
}

static int __init smt_cmdline_disable(char *str)
{
	cpu_smt_disable(str && !strcmp(str, "force"));
	return 0;
}
early_param("nosmt", smt_cmdline_disable);

static inline bool cpu_smt_allowed(unsigned int cpu)
{
	if (cpu_smt_control == CPU_SMT_ENABLED)
		return true;

	if (topology_is_primary_thread(cpu))
		return true;

	/*
	 * On x86 it's required to boot all logical CPUs at least once so
	 * that the init code can get a chance to set CR4.MCE on each
	 * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
	 * core will shutdown the machine.
	 */
	return !per_cpu(cpuhp_state, cpu).booted_once;
}
#else
static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
#endif

static inline enum cpuhp_state
cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
{
	enum cpuhp_state prev_state = st->state;

	st->rollback = false;
	st->last = NULL;

	st->target = target;
	st->single = false;
	st->bringup = st->state < target;

	return prev_state;
}

static inline void
cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state)
{
	st->rollback = true;

	/*
	 * If we have st->last we need to undo partial multi_instance of this
	 * state first. Otherwise start undo at the previous state.
	 */
	if (!st->last) {
		if (st->bringup)
			st->state--;
		else
			st->state++;
	}

	st->target = prev_state;
	st->bringup = !st->bringup;
}

/* Regular hotplug invocation of the AP hotplug thread */
static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st)
{
	if (!st->single && st->state == st->target)
		return;

	st->result = 0;
	/*
	 * Make sure the above stores are visible before should_run becomes
	 * true. Paired with the mb() above in cpuhp_thread_fun()
	 */
	smp_mb();
	st->should_run = true;
	wake_up_process(st->thread);
	wait_for_ap_thread(st, st->bringup);
}

static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target)
{
	enum cpuhp_state prev_state;
	int ret;

	prev_state = cpuhp_set_state(st, target);
	__cpuhp_kick_ap(st);
	if ((ret = st->result)) {
		cpuhp_reset_state(st, prev_state);
		__cpuhp_kick_ap(st);
	}

	return ret;
}

static int bringup_wait_for_ap(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);

	/* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */
	wait_for_ap_thread(st, true);
	if (WARN_ON_ONCE((!cpu_online(cpu))))
		return -ECANCELED;

	/* Unpark the hotplug thread of the target cpu */
	kthread_unpark(st->thread);

	/*
	 * SMT soft disabling on X86 requires to bring the CPU out of the
	 * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit.  The
	 * CPU marked itself as booted_once in cpu_notify_starting() so the
	 * cpu_smt_allowed() check will now return false if this is not the
	 * primary sibling.
	 */
	if (!cpu_smt_allowed(cpu))
		return -ECANCELED;

	if (st->target <= CPUHP_AP_ONLINE_IDLE)
		return 0;

	return cpuhp_kick_ap(st, st->target);
}

static int bringup_cpu(unsigned int cpu)
{
	struct task_struct *idle = idle_thread_get(cpu);
	int ret;

	/*
	 * Some architectures have to walk the irq descriptors to
	 * setup the vector space for the cpu which comes online.
	 * Prevent irq alloc/free across the bringup.
	 */
	irq_lock_sparse();

	/* Arch-specific enabling code. */
	ret = __cpu_up(cpu, idle);
	irq_unlock_sparse();
	if (ret)
		return ret;
	return bringup_wait_for_ap(cpu);
}

static int finish_cpu(unsigned int cpu)
{
	struct task_struct *idle = idle_thread_get(cpu);
	struct mm_struct *mm = idle->active_mm;

	/*
	 * idle_task_exit() will have switched to &init_mm, now
	 * clean up any remaining active_mm state.
	 */
	if (mm != &init_mm)
		idle->active_mm = &init_mm;
	mmdrop(mm);
	return 0;
}

/*
 * Hotplug state machine related functions
 */

static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st)
{
	for (st->state--; st->state > st->target; st->state--)
		cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
}

static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st)
{
	if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
		return true;
	/*
	 * When CPU hotplug is disabled, then taking the CPU down is not
	 * possible because takedown_cpu() and the architecture and
	 * subsystem specific mechanisms are not available. So the CPU
	 * which would be completely unplugged again needs to stay around
	 * in the current state.
	 */
	return st->state <= CPUHP_BRINGUP_CPU;
}

static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
			      enum cpuhp_state target)
{
	enum cpuhp_state prev_state = st->state;
	int ret = 0;

	while (st->state < target) {
		st->state++;
		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
		if (ret) {
			if (can_rollback_cpu(st)) {
				st->target = prev_state;
				undo_cpu_up(cpu, st);
			}
			break;
		}
	}
	return ret;
}

/*
 * The cpu hotplug threads manage the bringup and teardown of the cpus
 */
static void cpuhp_create(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);

	init_completion(&st->done_up);
	init_completion(&st->done_down);
}

static int cpuhp_should_run(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);

	return st->should_run;
}

/*
 * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke
 * callbacks when a state gets [un]installed at runtime.
 *
 * Each invocation of this function by the smpboot thread does a single AP
 * state callback.
 *
 * It has 3 modes of operation:
 *  - single: runs st->cb_state
 *  - up:     runs ++st->state, while st->state < st->target
 *  - down:   runs st->state--, while st->state > st->target
 *
 * When complete or on error, should_run is cleared and the completion is fired.
 */
static void cpuhp_thread_fun(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
	bool bringup = st->bringup;
	enum cpuhp_state state;

	if (WARN_ON_ONCE(!st->should_run))
		return;

	/*
	 * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures
	 * that if we see ->should_run we also see the rest of the state.
	 */
	smp_mb();

	cpuhp_lock_acquire(bringup);

	if (st->single) {
		state = st->cb_state;
		st->should_run = false;
	} else {
		if (bringup) {
			st->state++;
			state = st->state;
			st->should_run = (st->state < st->target);
			WARN_ON_ONCE(st->state > st->target);
		} else {
			state = st->state;
			st->state--;
			st->should_run = (st->state > st->target);
			WARN_ON_ONCE(st->state < st->target);
		}
	}

	WARN_ON_ONCE(!cpuhp_is_ap_state(state));

	if (cpuhp_is_atomic_state(state)) {
		local_irq_disable();
		st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
		local_irq_enable();

		/*
		 * STARTING/DYING must not fail!
		 */
		WARN_ON_ONCE(st->result);
	} else {
		st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
	}

	if (st->result) {
		/*
		 * If we fail on a rollback, we're up a creek without no
		 * paddle, no way forward, no way back. We loose, thanks for
		 * playing.
		 */
		WARN_ON_ONCE(st->rollback);
		st->should_run = false;
	}

	cpuhp_lock_release(bringup);

	if (!st->should_run)
		complete_ap_thread(st, bringup);
}

/* Invoke a single callback on a remote cpu */
static int
cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
			 struct hlist_node *node)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	int ret;

	if (!cpu_online(cpu))
		return 0;

	cpuhp_lock_acquire(false);
	cpuhp_lock_release(false);

	cpuhp_lock_acquire(true);
	cpuhp_lock_release(true);

	/*
	 * If we are up and running, use the hotplug thread. For early calls
	 * we invoke the thread function directly.
	 */
	if (!st->thread)
		return cpuhp_invoke_callback(cpu, state, bringup, node, NULL);

	st->rollback = false;
	st->last = NULL;

	st->node = node;
	st->bringup = bringup;
	st->cb_state = state;
	st->single = true;

	__cpuhp_kick_ap(st);

	/*
	 * If we failed and did a partial, do a rollback.
	 */
	if ((ret = st->result) && st->last) {
		st->rollback = true;
		st->bringup = !bringup;

		__cpuhp_kick_ap(st);
	}

	/*
	 * Clean up the leftovers so the next hotplug operation wont use stale
	 * data.
	 */
	st->node = st->last = NULL;
	return ret;
}

static int cpuhp_kick_ap_work(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	enum cpuhp_state prev_state = st->state;
	int ret;

	cpuhp_lock_acquire(false);
	cpuhp_lock_release(false);

	cpuhp_lock_acquire(true);
	cpuhp_lock_release(true);

	trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work);
	ret = cpuhp_kick_ap(st, st->target);
	trace_cpuhp_exit(cpu, st->state, prev_state, ret);

	return ret;
}

static struct smp_hotplug_thread cpuhp_threads = {
	.store			= &cpuhp_state.thread,
	.create			= &cpuhp_create,
	.thread_should_run	= cpuhp_should_run,
	.thread_fn		= cpuhp_thread_fun,
	.thread_comm		= "cpuhp/%u",
	.selfparking		= true,
};

void __init cpuhp_threads_init(void)
{
	BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads));
	kthread_unpark(this_cpu_read(cpuhp_state.thread));
}

/*
 *
 * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock
 * protected region.
 *
 * The operation is still serialized against concurrent CPU hotplug via
 * cpu_add_remove_lock, i.e. CPU map protection.  But it is _not_
 * serialized against other hotplug related activity like adding or
 * removing of state callbacks and state instances, which invoke either the
 * startup or the teardown callback of the affected state.
 *
 * This is required for subsystems which are unfixable vs. CPU hotplug and
 * evade lock inversion problems by scheduling work which has to be
 * completed _before_ cpu_up()/_cpu_down() returns.
 *
 * Don't even think about adding anything to this for any new code or even
 * drivers. It's only purpose is to keep existing lock order trainwrecks
 * working.
 *
 * For cpu_down() there might be valid reasons to finish cleanups which are
 * not required to be done under cpu_hotplug_lock, but that's a different
 * story and would be not invoked via this.
 */
static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen)
{
	/*
	 * cpusets delegate hotplug operations to a worker to "solve" the
	 * lock order problems. Wait for the worker, but only if tasks are
	 * _not_ frozen (suspend, hibernate) as that would wait forever.
	 *
	 * The wait is required because otherwise the hotplug operation
	 * returns with inconsistent state, which could even be observed in
	 * user space when a new CPU is brought up. The CPU plug uevent
	 * would be delivered and user space reacting on it would fail to
	 * move tasks to the newly plugged CPU up to the point where the
	 * work has finished because up to that point the newly plugged CPU
	 * is not assignable in cpusets/cgroups. On unplug that's not
	 * necessarily a visible issue, but it is still inconsistent state,
	 * which is the real problem which needs to be "fixed". This can't
	 * prevent the transient state between scheduling the work and
	 * returning from waiting for it.
	 */
	if (!tasks_frozen)
		cpuset_wait_for_hotplug();
}

#ifdef CONFIG_HOTPLUG_CPU
#ifndef arch_clear_mm_cpumask_cpu
#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm))
#endif

/**
 * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
 * @cpu: a CPU id
 *
 * This function walks all processes, finds a valid mm struct for each one and
 * then clears a corresponding bit in mm's cpumask.  While this all sounds
 * trivial, there are various non-obvious corner cases, which this function
 * tries to solve in a safe manner.
 *
 * Also note that the function uses a somewhat relaxed locking scheme, so it may
 * be called only for an already offlined CPU.
 */
void clear_tasks_mm_cpumask(int cpu)
{
	struct task_struct *p;

	/*
	 * This function is called after the cpu is taken down and marked
	 * offline, so its not like new tasks will ever get this cpu set in
	 * their mm mask. -- Peter Zijlstra
	 * Thus, we may use rcu_read_lock() here, instead of grabbing
	 * full-fledged tasklist_lock.
	 */
	WARN_ON(cpu_online(cpu));
	rcu_read_lock();
	for_each_process(p) {
		struct task_struct *t;

		/*
		 * Main thread might exit, but other threads may still have
		 * a valid mm. Find one.
		 */
		t = find_lock_task_mm(p);
		if (!t)
			continue;
		arch_clear_mm_cpumask_cpu(cpu, t->mm);
		task_unlock(t);
	}
	rcu_read_unlock();
}

/* Take this CPU down. */
static int take_cpu_down(void *_param)
{
	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
	enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
	int err, cpu = smp_processor_id();
	int ret;

	/* Ensure this CPU doesn't handle any more interrupts. */
	err = __cpu_disable();
	if (err < 0)
		return err;

	/*
	 * We get here while we are in CPUHP_TEARDOWN_CPU state and we must not
	 * do this step again.
	 */
	WARN_ON(st->state != CPUHP_TEARDOWN_CPU);
	st->state--;
	/* Invoke the former CPU_DYING callbacks */
	for (; st->state > target; st->state--) {
		ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
		/*
		 * DYING must not fail!
		 */
		WARN_ON_ONCE(ret);
	}

	/* Give up timekeeping duties */
	tick_handover_do_timer();
	/* Park the stopper thread */
	stop_machine_park(cpu);
	return 0;
}

static int takedown_cpu(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	int err;

	/* Park the smpboot threads */
	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);

	/*
	 * Prevent irq alloc/free while the dying cpu reorganizes the
	 * interrupt affinities.
	 */
	irq_lock_sparse();

	/*
	 * So now all preempt/rcu users must observe !cpu_active().
	 */
	err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu));
	if (err) {
		/* CPU refused to die */
		irq_unlock_sparse();
		/* Unpark the hotplug thread so we can rollback there */
		kthread_unpark(per_cpu_ptr(&cpuhp_state, cpu)->thread);
		return err;
	}
	BUG_ON(cpu_online(cpu));

	/*
	 * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed
	 * all runnable tasks from the CPU, there's only the idle task left now
	 * that the migration thread is done doing the stop_machine thing.
	 *
	 * Wait for the stop thread to go away.
	 */
	wait_for_ap_thread(st, false);
	BUG_ON(st->state != CPUHP_AP_IDLE_DEAD);

	/* Interrupts are moved away from the dying cpu, reenable alloc/free */
	irq_unlock_sparse();

	hotplug_cpu__broadcast_tick_pull(cpu);
	/* This actually kills the CPU. */
	__cpu_die(cpu);

	tick_cleanup_dead_cpu(cpu);
	rcutree_migrate_callbacks(cpu);
	return 0;
}

static void cpuhp_complete_idle_dead(void *arg)
{
	struct cpuhp_cpu_state *st = arg;

	complete_ap_thread(st, false);
}

void cpuhp_report_idle_dead(void)
{
	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);

	BUG_ON(st->state != CPUHP_AP_OFFLINE);
	rcu_report_dead(smp_processor_id());
	st->state = CPUHP_AP_IDLE_DEAD;
	/*
	 * We cannot call complete after rcu_report_dead() so we delegate it
	 * to an online cpu.
	 */
	smp_call_function_single(cpumask_first(cpu_online_mask),
				 cpuhp_complete_idle_dead, st, 0);
}

static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
{
	for (st->state++; st->state < st->target; st->state++)
		cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
}

static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
				enum cpuhp_state target)
{
	enum cpuhp_state prev_state = st->state;
	int ret = 0;

	for (; st->state > target; st->state--) {
		ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
		if (ret) {
			st->target = prev_state;
			if (st->state < prev_state)
				undo_cpu_down(cpu, st);
			break;
		}
	}
	return ret;
}

/* Requires cpu_add_remove_lock to be held */
static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
			   enum cpuhp_state target)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	int prev_state, ret = 0;

	if (num_online_cpus() == 1)
		return -EBUSY;

	if (!cpu_present(cpu))
		return -EINVAL;

	cpus_write_lock();

	cpuhp_tasks_frozen = tasks_frozen;

	prev_state = cpuhp_set_state(st, target);
	/*
	 * If the current CPU state is in the range of the AP hotplug thread,
	 * then we need to kick the thread.
	 */
	if (st->state > CPUHP_TEARDOWN_CPU) {
		st->target = max((int)target, CPUHP_TEARDOWN_CPU);
		ret = cpuhp_kick_ap_work(cpu);
		/*
		 * The AP side has done the error rollback already. Just
		 * return the error code..
		 */
		if (ret)
			goto out;

		/*
		 * We might have stopped still in the range of the AP hotplug
		 * thread. Nothing to do anymore.
		 */
		if (st->state > CPUHP_TEARDOWN_CPU)
			goto out;

		st->target = target;
	}
	/*
	 * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need
	 * to do the further cleanups.
	 */
	ret = cpuhp_down_callbacks(cpu, st, target);
	if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) {
		cpuhp_reset_state(st, prev_state);
		__cpuhp_kick_ap(st);
	}

out:
	cpus_write_unlock();
	/*
	 * Do post unplug cleanup. This is still protected against
	 * concurrent CPU hotplug via cpu_add_remove_lock.
	 */
	lockup_detector_cleanup();
	arch_smt_update();
	cpu_up_down_serialize_trainwrecks(tasks_frozen);
	return ret;
}

static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
{
	if (cpu_hotplug_disabled)
		return -EBUSY;
	return _cpu_down(cpu, 0, target);
}

static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
{
	int err;

	cpu_maps_update_begin();
	err = cpu_down_maps_locked(cpu, target);
	cpu_maps_update_done();
	return err;
}

int cpu_down(unsigned int cpu)
{
	return do_cpu_down(cpu, CPUHP_OFFLINE);
}
EXPORT_SYMBOL(cpu_down);

#else
#define takedown_cpu		NULL
#endif /*CONFIG_HOTPLUG_CPU*/

/**
 * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
 * @cpu: cpu that just started
 *
 * It must be called by the arch code on the new cpu, before the new cpu
 * enables interrupts and before the "boot" cpu returns from __cpu_up().
 */
void notify_cpu_starting(unsigned int cpu)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
	int ret;

	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
	st->booted_once = true;
	while (st->state < target) {
		st->state++;
		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
		/*
		 * STARTING must not fail!
		 */
		WARN_ON_ONCE(ret);
	}
}

/*
 * Called from the idle task. Wake up the controlling task which brings the
 * hotplug thread of the upcoming CPU up and then delegates the rest of the
 * online bringup to the hotplug thread.
 */
void cpuhp_online_idle(enum cpuhp_state state)
{
	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);

	/* Happens for the boot cpu */
	if (state != CPUHP_AP_ONLINE_IDLE)
		return;

	/*
	 * Unpart the stopper thread before we start the idle loop (and start
	 * scheduling); this ensures the stopper task is always available.
	 */
	stop_machine_unpark(smp_processor_id());

	st->state = CPUHP_AP_ONLINE_IDLE;
	complete_ap_thread(st, true);
}

/* Requires cpu_add_remove_lock to be held */
static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
	struct task_struct *idle;
	int ret = 0;

	cpus_write_lock();

	if (!cpu_present(cpu)) {
		ret = -EINVAL;
		goto out;
	}

	/*
	 * The caller of do_cpu_up might have raced with another
	 * caller. Ignore it for now.
	 */
	if (st->state >= target)
		goto out;

	if (st->state == CPUHP_OFFLINE) {
		/* Let it fail before we try to bring the cpu up */
		idle = idle_thread_get(cpu);
		if (IS_ERR(idle)) {
			ret = PTR_ERR(idle);
			goto out;
		}
	}

	cpuhp_tasks_frozen = tasks_frozen;

	cpuhp_set_state(st, target);
	/*
	 * If the current CPU state is in the range of the AP hotplug thread,
	 * then we need to kick the thread once more.
	 */
	if (st->state > CPUHP_BRINGUP_CPU) {
		ret = cpuhp_kick_ap_work(cpu);
		/*
		 * The AP side has done the error rollback already. Just
		 * return the error code..
		 */
		if (ret)
			goto out;
	}

	/*
	 * Try to reach the target state. We max out on the BP at
	 * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is
	 * responsible for bringing it up to the target state.
	 */
	target = min((int)target, CPUHP_BRINGUP_CPU);
	ret = cpuhp_up_callbacks(cpu, st, target);
out:
	cpus_write_unlock();
	arch_smt_update();
	cpu_up_down_serialize_trainwrecks(tasks_frozen);
	return ret;
}

static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
{
	int err = 0;

	if (!cpu_possible(cpu)) {
		pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n",
		       cpu);
#if defined(CONFIG_IA64)
		pr_err("please check additional_cpus= boot parameter\n");
#endif
		return -EINVAL;
	}

	err = try_online_node(cpu_to_node(cpu));
	if (err)
		return err;

	cpu_maps_update_begin();

	if (cpu_hotplug_disabled) {
		err = -EBUSY;
		goto out;
	}
	if (!cpu_smt_allowed(cpu)) {
		err = -EPERM;
		goto out;
	}

	err = _cpu_up(cpu, 0, target);
out:
	cpu_maps_update_done();
	return err;
}

int cpu_up(unsigned int cpu)
{
	return do_cpu_up(cpu, CPUHP_ONLINE);
}
EXPORT_SYMBOL_GPL(cpu_up);

#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_var_t frozen_cpus;

int freeze_secondary_cpus(int primary)
{
	int cpu, error = 0;

	cpu_maps_update_begin();
	if (!cpu_online(primary))
		primary = cpumask_first(cpu_online_mask);
	/*
	 * We take down all of the non-boot CPUs in one shot to avoid races
	 * with the userspace trying to use the CPU hotplug at the same time
	 */
	cpumask_clear(frozen_cpus);

	pr_info("Disabling non-boot CPUs ...\n");
	for_each_online_cpu(cpu) {
		if (cpu == primary)
			continue;
		trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
		error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
		trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
		if (!error)
			cpumask_set_cpu(cpu, frozen_cpus);
		else {
			pr_err("Error taking CPU%d down: %d\n", cpu, error);
			break;
		}
	}

	if (!error)
		BUG_ON(num_online_cpus() > 1);
	else
		pr_err("Non-boot CPUs are not disabled\n");

	/*
	 * Make sure the CPUs won't be enabled by someone else. We need to do
	 * this even in case of failure as all disable_nonboot_cpus() users are
	 * supposed to do enable_nonboot_cpus() on the failure path.
	 */
	cpu_hotplug_disabled++;

	cpu_maps_update_done();
	return error;
}

void __weak arch_enable_nonboot_cpus_begin(void)
{
}

void __weak arch_enable_nonboot_cpus_end(void)
{
}

void enable_nonboot_cpus(void)
{
	int cpu, error;

	/* Allow everyone to use the CPU hotplug again */
	cpu_maps_update_begin();
	__cpu_hotplug_enable();
	if (cpumask_empty(frozen_cpus))
		goto out;

	pr_info("Enabling non-boot CPUs ...\n");

	arch_enable_nonboot_cpus_begin();

	for_each_cpu(cpu, frozen_cpus) {
		trace_suspend_resume(TPS("CPU_ON"), cpu, true);
		error = _cpu_up(cpu, 1, CPUHP_ONLINE);
		trace_suspend_resume(TPS("CPU_ON"), cpu, false);
		if (!error) {
			pr_info("CPU%d is up\n", cpu);
			continue;
		}
		pr_warn("Error taking CPU%d up: %d\n", cpu, error);
	}

	arch_enable_nonboot_cpus_end();

	cpumask_clear(frozen_cpus);
out:
	cpu_maps_update_done();
}

static int __init alloc_frozen_cpus(void)
{
	if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))
		return -ENOMEM;
	return 0;
}
core_initcall(alloc_frozen_cpus);

/*
 * When callbacks for CPU hotplug notifications are being executed, we must
 * ensure that the state of the system with respect to the tasks being frozen
 * or not, as reported by the notification, remains unchanged *throughout the
 * duration* of the execution of the callbacks.
 * Hence we need to prevent the freezer from racing with regular CPU hotplug.
 *
 * This synchronization is implemented by mutually excluding regular CPU
 * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/
 * Hibernate notifications.
 */
static int
cpu_hotplug_pm_callback(struct notifier_block *nb,
			unsigned long action, void *ptr)
{
	switch (action) {

	case PM_SUSPEND_PREPARE:
	case PM_HIBERNATION_PREPARE:
		cpu_hotplug_disable();
		break;

	case PM_POST_SUSPEND:
	case PM_POST_HIBERNATION:
		cpu_hotplug_enable();
		break;

	default:
		return NOTIFY_DONE;
	}

	return NOTIFY_OK;
}


static int __init cpu_hotplug_pm_sync_init(void)
{
	/*
	 * cpu_hotplug_pm_callback has higher priority than x86
	 * bsp_pm_callback which depends on cpu_hotplug_pm_callback
	 * to disable cpu hotplug to avoid cpu hotplug race.
	 */
	pm_notifier(cpu_hotplug_pm_callback, 0);
	return 0;
}
core_initcall(cpu_hotplug_pm_sync_init);

#endif /* CONFIG_PM_SLEEP_SMP */

int __boot_cpu_id;

#endif /* CONFIG_SMP */

/* Boot processor state steps */
static struct cpuhp_step cpuhp_hp_states[] = {
	[CPUHP_OFFLINE] = {
		.name			= "offline",
		.startup.single		= NULL,
		.teardown.single	= NULL,
	},
#ifdef CONFIG_SMP
	[CPUHP_CREATE_THREADS]= {
		.name			= "threads:prepare",
		.startup.single		= smpboot_create_threads,
		.teardown.single	= NULL,
		.cant_stop		= true,
	},
	[CPUHP_PERF_PREPARE] = {
		.name			= "perf:prepare",
		.startup.single		= perf_event_init_cpu,
		.teardown.single	= perf_event_exit_cpu,
	},
	[CPUHP_RANDOM_PREPARE] = {
		.name			= "random:prepare",
		.startup.single		= random_prepare_cpu,
		.teardown.single	= NULL,
	},
	[CPUHP_WORKQUEUE_PREP] = {
		.name			= "workqueue:prepare",
		.startup.single		= workqueue_prepare_cpu,
		.teardown.single	= NULL,
	},
	[CPUHP_HRTIMERS_PREPARE] = {
		.name			= "hrtimers:prepare",
		.startup.single		= hrtimers_prepare_cpu,
		.teardown.single	= NULL,
	},
	[CPUHP_SMPCFD_PREPARE] = {
		.name			= "smpcfd:prepare",
		.startup.single		= smpcfd_prepare_cpu,
		.teardown.single	= smpcfd_dead_cpu,
	},
	[CPUHP_RELAY_PREPARE] = {
		.name			= "relay:prepare",
		.startup.single		= relay_prepare_cpu,
		.teardown.single	= NULL,
	},
	[CPUHP_SLAB_PREPARE] = {
		.name			= "slab:prepare",
		.startup.single		= slab_prepare_cpu,
		.teardown.single	= slab_dead_cpu,
	},
	[CPUHP_RCUTREE_PREP] = {
		.name			= "RCU/tree:prepare",
		.startup.single		= rcutree_prepare_cpu,
		.teardown.single	= rcutree_dead_cpu,
	},
	/*
	 * On the tear-down path, timers_dead_cpu() must be invoked
	 * before blk_mq_queue_reinit_notify() from notify_dead(),
	 * otherwise a RCU stall occurs.
	 */
	[CPUHP_TIMERS_PREPARE] = {
		.name			= "timers:prepare",
		.startup.single		= timers_prepare_cpu,
		.teardown.single	= timers_dead_cpu,
	},
	/* Kicks the plugged cpu into life */
	[CPUHP_BRINGUP_CPU] = {
		.name			= "cpu:bringup",
		.startup.single		= bringup_cpu,
		.teardown.single	= finish_cpu,
		.cant_stop		= true,
	},
	/* Final state before CPU kills itself */
	[CPUHP_AP_IDLE_DEAD] = {
		.name			= "idle:dead",
	},
	/*
	 * Last state before CPU enters the idle loop to die. Transient state
	 * for synchronization.
	 */
	[CPUHP_AP_OFFLINE] = {
		.name			= "ap:offline",
		.cant_stop		= true,
	},
	/* First state is scheduler control. Interrupts are disabled */
	[CPUHP_AP_SCHED_STARTING] = {
		.name			= "sched:starting",
		.startup.single		= sched_cpu_starting,
		.teardown.single	= sched_cpu_dying,
	},
	[CPUHP_AP_RCUTREE_DYING] = {
		.name			= "RCU/tree:dying",
		.startup.single		= NULL,
		.teardown.single	= rcutree_dying_cpu,
	},
	[CPUHP_AP_SMPCFD_DYING] = {
		.name			= "smpcfd:dying",
		.startup.single		= NULL,
		.teardown.single	= smpcfd_dying_cpu,
	},
	[CPUHP_AP_HRTIMERS_DYING] = {
		.name			= "hrtimers:dying",
		.startup.single		= NULL,
		.teardown.single	= hrtimers_cpu_dying,
	},

	/* Entry state on starting. Interrupts enabled from here on. Transient
	 * state for synchronsization */
	[CPUHP_AP_ONLINE] = {
		.name			= "ap:online",
	},
	/*
	 * Handled on controll processor until the plugged processor manages
	 * this itself.
	 */
	[CPUHP_TEARDOWN_CPU] = {
		.name			= "cpu:teardown",
		.startup.single		= NULL,
		.teardown.single	= takedown_cpu,
		.cant_stop		= true,
	},
	/* Handle smpboot threads park/unpark */
	[CPUHP_AP_SMPBOOT_THREADS] = {
		.name			= "smpboot/threads:online",
		.startup.single		= smpboot_unpark_threads,
		.teardown.single	= smpboot_park_threads,
	},
	[CPUHP_AP_IRQ_AFFINITY_ONLINE] = {
		.name			= "irq/affinity:online",
		.startup.single		= irq_affinity_online_cpu,
		.teardown.single	= NULL,
	},
	[CPUHP_AP_PERF_ONLINE] = {
		.name			= "perf:online",
		.startup.single		= perf_event_init_cpu,
		.teardown.single	= perf_event_exit_cpu,
	},
	[CPUHP_AP_WATCHDOG_ONLINE] = {
		.name			= "lockup_detector:online",
		.startup.single		= lockup_detector_online_cpu,
		.teardown.single	= lockup_detector_offline_cpu,
	},
	[CPUHP_AP_WORKQUEUE_ONLINE] = {
		.name			= "workqueue:online",
		.startup.single		= workqueue_online_cpu,
		.teardown.single	= workqueue_offline_cpu,
	},
	[CPUHP_AP_RANDOM_ONLINE] = {
		.name			= "random:online",
		.startup.single		= random_online_cpu,
		.teardown.single	= NULL,
	},
	[CPUHP_AP_RCUTREE_ONLINE] = {
		.name			= "RCU/tree:online",
		.startup.single		= rcutree_online_cpu,
		.teardown.single	= rcutree_offline_cpu,
	},
#endif
	/*
	 * The dynamically registered state space is here
	 */

#ifdef CONFIG_SMP
	/* Last state is scheduler control setting the cpu active */
	[CPUHP_AP_ACTIVE] = {
		.name			= "sched:active",
		.startup.single		= sched_cpu_activate,
		.teardown.single	= sched_cpu_deactivate,
	},
#endif

	/* CPU is fully up and running. */
	[CPUHP_ONLINE] = {
		.name			= "online",
		.startup.single		= NULL,
		.teardown.single	= NULL,
	},
};

/* Sanity check for callbacks */
static int cpuhp_cb_check(enum cpuhp_state state)
{
	if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE)
		return -EINVAL;
	return 0;
}

/*
 * Returns a free for dynamic slot assignment of the Online state. The states
 * are protected by the cpuhp_slot_states mutex and an empty slot is identified
 * by having no name assigned.
 */
static int cpuhp_reserve_state(enum cpuhp_state state)
{
	enum cpuhp_state i, end;
	struct cpuhp_step *step;

	switch (state) {
	case CPUHP_AP_ONLINE_DYN:
		step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN;
		end = CPUHP_AP_ONLINE_DYN_END;
		break;
	case CPUHP_BP_PREPARE_DYN:
		step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN;
		end = CPUHP_BP_PREPARE_DYN_END;
		break;
	default:
		return -EINVAL;
	}

	for (i = state; i <= end; i++, step++) {
		if (!step->name)
			return i;
	}
	WARN(1, "No more dynamic states available for CPU hotplug\n");
	return -ENOSPC;
}

static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
				 int (*startup)(unsigned int cpu),
				 int (*teardown)(unsigned int cpu),
				 bool multi_instance)
{
	/* (Un)Install the callbacks for further cpu hotplug operations */
	struct cpuhp_step *sp;
	int ret = 0;

	/*
	 * If name is NULL, then the state gets removed.
	 *
	 * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on
	 * the first allocation from these dynamic ranges, so the removal
	 * would trigger a new allocation and clear the wrong (already
	 * empty) state, leaving the callbacks of the to be cleared state
	 * dangling, which causes wreckage on the next hotplug operation.
	 */
	if (name && (state == CPUHP_AP_ONLINE_DYN ||
		     state == CPUHP_BP_PREPARE_DYN)) {
		ret = cpuhp_reserve_state(state);
		if (ret < 0)
			return ret;
		state = ret;
	}
	sp = cpuhp_get_step(state);
	if (name && sp->name)
		return -EBUSY;

	sp->startup.single = startup;
	sp->teardown.single = teardown;
	sp->name = name;
	sp->multi_instance = multi_instance;
	INIT_HLIST_HEAD(&sp->list);
	return ret;
}

static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
{
	return cpuhp_get_step(state)->teardown.single;
}

/*
 * Call the startup/teardown function for a step either on the AP or
 * on the current CPU.
 */
static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup,
			    struct hlist_node *node)
{
	struct cpuhp_step *sp = cpuhp_get_step(state);
	int ret;

	/*
	 * If there's nothing to do, we done.
	 * Relies on the union for multi_instance.
	 */
	if ((bringup && !sp->startup.single) ||
	    (!bringup && !sp->teardown.single))
		return 0;
	/*
	 * The non AP bound callbacks can fail on bringup. On teardown
	 * e.g. module removal we crash for now.
	 */
#ifdef CONFIG_SMP
	if (cpuhp_is_ap_state(state))
		ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node);
	else
		ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
#else
	ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
#endif
	BUG_ON(ret && !bringup);
	return ret;
}

/*
 * Called from __cpuhp_setup_state on a recoverable failure.
 *
 * Note: The teardown callbacks for rollback are not allowed to fail!
 */
static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
				   struct hlist_node *node)
{
	int cpu;

	/* Roll back the already executed steps on the other cpus */
	for_each_present_cpu(cpu) {
		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
		int cpustate = st->state;

		if (cpu >= failedcpu)
			break;

		/* Did we invoke the startup call on that cpu ? */
		if (cpustate >= state)
			cpuhp_issue_call(cpu, state, false, node);
	}
}

int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state,
					  struct hlist_node *node,
					  bool invoke)
{
	struct cpuhp_step *sp;
	int cpu;
	int ret;

	lockdep_assert_cpus_held();

	sp = cpuhp_get_step(state);
	if (sp->multi_instance == false)
		return -EINVAL;

	mutex_lock(&cpuhp_state_mutex);

	if (!invoke || !sp->startup.multi)
		goto add_node;

	/*
	 * Try to call the startup callback for each present cpu
	 * depending on the hotplug state of the cpu.
	 */
	for_each_present_cpu(cpu) {
		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
		int cpustate = st->state;

		if (cpustate < state)
			continue;

		ret = cpuhp_issue_call(cpu, state, true, node);
		if (ret) {
			if (sp->teardown.multi)
				cpuhp_rollback_install(cpu, state, node);
			goto unlock;
		}
	}
add_node:
	ret = 0;
	hlist_add_head(node, &sp->list);
unlock:
	mutex_unlock(&cpuhp_state_mutex);
	return ret;
}

int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
			       bool invoke)
{
	int ret;

	cpus_read_lock();
	ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke);
	cpus_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);

/**
 * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state
 * @state:		The state to setup
 * @invoke:		If true, the startup function is invoked for cpus where
 *			cpu state >= @state
 * @startup:		startup callback function
 * @teardown:		teardown callback function
 * @multi_instance:	State is set up for multiple instances which get
 *			added afterwards.
 *
 * The caller needs to hold cpus read locked while calling this function.
 * Returns:
 *   On success:
 *      Positive state number if @state is CPUHP_AP_ONLINE_DYN
 *      0 for all other states
 *   On failure: proper (negative) error code
 */
int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
				   const char *name, bool invoke,
				   int (*startup)(unsigned int cpu),
				   int (*teardown)(unsigned int cpu),
				   bool multi_instance)
{
	int cpu, ret = 0;
	bool dynstate;

	lockdep_assert_cpus_held();

	if (cpuhp_cb_check(state) || !name)
		return -EINVAL;

	mutex_lock(&cpuhp_state_mutex);

	ret = cpuhp_store_callbacks(state, name, startup, teardown,
				    multi_instance);

	dynstate = state == CPUHP_AP_ONLINE_DYN;
	if (ret > 0 && dynstate) {
		state = ret;
		ret = 0;
	}

	if (ret || !invoke || !startup)
		goto out;

	/*
	 * Try to call the startup callback for each present cpu
	 * depending on the hotplug state of the cpu.
	 */
	for_each_present_cpu(cpu) {
		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
		int cpustate = st->state;

		if (cpustate < state)
			continue;

		ret = cpuhp_issue_call(cpu, state, true, NULL);
		if (ret) {
			if (teardown)
				cpuhp_rollback_install(cpu, state, NULL);
			cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
			goto out;
		}
	}
out:
	mutex_unlock(&cpuhp_state_mutex);
	/*
	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
	 * dynamically allocated state in case of success.
	 */
	if (!ret && dynstate)
		return state;
	return ret;
}
EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked);

int __cpuhp_setup_state(enum cpuhp_state state,
			const char *name, bool invoke,
			int (*startup)(unsigned int cpu),
			int (*teardown)(unsigned int cpu),
			bool multi_instance)
{
	int ret;

	cpus_read_lock();
	ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup,
					     teardown, multi_instance);
	cpus_read_unlock();
	return ret;
}
EXPORT_SYMBOL(__cpuhp_setup_state);

int __cpuhp_state_remove_instance(enum cpuhp_state state,
				  struct hlist_node *node, bool invoke)
{
	struct cpuhp_step *sp = cpuhp_get_step(state);
	int cpu;

	BUG_ON(cpuhp_cb_check(state));

	if (!sp->multi_instance)
		return -EINVAL;

	cpus_read_lock();
	mutex_lock(&cpuhp_state_mutex);

	if (!invoke || !cpuhp_get_teardown_cb(state))
		goto remove;
	/*
	 * Call the teardown callback for each present cpu depending
	 * on the hotplug state of the cpu. This function is not
	 * allowed to fail currently!
	 */
	for_each_present_cpu(cpu) {
		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
		int cpustate = st->state;

		if (cpustate >= state)
			cpuhp_issue_call(cpu, state, false, node);
	}

remove:
	hlist_del(node);
	mutex_unlock(&cpuhp_state_mutex);
	cpus_read_unlock();

	return 0;
}
EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);

/**
 * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state
 * @state:	The state to remove
 * @invoke:	If true, the teardown function is invoked for cpus where
 *		cpu state >= @state
 *
 * The caller needs to hold cpus read locked while calling this function.
 * The teardown callback is currently not allowed to fail. Think
 * about module removal!
 */
void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke)
{
	struct cpuhp_step *sp = cpuhp_get_step(state);
	int cpu;

	BUG_ON(cpuhp_cb_check(state));

	lockdep_assert_cpus_held();

	mutex_lock(&cpuhp_state_mutex);
	if (sp->multi_instance) {
		WARN(!hlist_empty(&sp->list),
		     "Error: Removing state %d which has instances left.\n",
		     state);
		goto remove;
	}

	if (!invoke || !cpuhp_get_teardown_cb(state))
		goto remove;

	/*
	 * Call the teardown callback for each present cpu depending
	 * on the hotplug state of the cpu. This function is not
	 * allowed to fail currently!
	 */
	for_each_present_cpu(cpu) {
		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
		int cpustate = st->state;

		if (cpustate >= state)
			cpuhp_issue_call(cpu, state, false, NULL);
	}
remove:
	cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
	mutex_unlock(&cpuhp_state_mutex);
}
EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked);

void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
{
	cpus_read_lock();
	__cpuhp_remove_state_cpuslocked(state, invoke);
	cpus_read_unlock();
}
EXPORT_SYMBOL(__cpuhp_remove_state);

#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
static ssize_t show_cpuhp_state(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);

	return sprintf(buf, "%d\n", st->state);
}
static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL);

static ssize_t write_cpuhp_target(struct device *dev,
				  struct device_attribute *attr,
				  const char *buf, size_t count)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
	struct cpuhp_step *sp;
	int target, ret;

	ret = kstrtoint(buf, 10, &target);
	if (ret)
		return ret;

#ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL
	if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE)
		return -EINVAL;
#else
	if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE)
		return -EINVAL;
#endif

	ret = lock_device_hotplug_sysfs();
	if (ret)
		return ret;

	mutex_lock(&cpuhp_state_mutex);
	sp = cpuhp_get_step(target);
	ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
	mutex_unlock(&cpuhp_state_mutex);
	if (ret)
		goto out;

	if (st->state < target)
		ret = do_cpu_up(dev->id, target);
	else
		ret = do_cpu_down(dev->id, target);
out:
	unlock_device_hotplug();
	return ret ? ret : count;
}

static ssize_t show_cpuhp_target(struct device *dev,
				 struct device_attribute *attr, char *buf)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);

	return sprintf(buf, "%d\n", st->target);
}
static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target);


static ssize_t write_cpuhp_fail(struct device *dev,
				struct device_attribute *attr,
				const char *buf, size_t count)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
	struct cpuhp_step *sp;
	int fail, ret;

	ret = kstrtoint(buf, 10, &fail);
	if (ret)
		return ret;

	if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE)
		return -EINVAL;

	/*
	 * Cannot fail STARTING/DYING callbacks.
	 */
	if (cpuhp_is_atomic_state(fail))
		return -EINVAL;

	/*
	 * Cannot fail anything that doesn't have callbacks.
	 */
	mutex_lock(&cpuhp_state_mutex);
	sp = cpuhp_get_step(fail);
	if (!sp->startup.single && !sp->teardown.single)
		ret = -EINVAL;
	mutex_unlock(&cpuhp_state_mutex);
	if (ret)
		return ret;

	st->fail = fail;

	return count;
}

static ssize_t show_cpuhp_fail(struct device *dev,
			       struct device_attribute *attr, char *buf)
{
	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);

	return sprintf(buf, "%d\n", st->fail);
}

static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail);

static struct attribute *cpuhp_cpu_attrs[] = {
	&dev_attr_state.attr,
	&dev_attr_target.attr,
	&dev_attr_fail.attr,
	NULL
};

static const struct attribute_group cpuhp_cpu_attr_group = {
	.attrs = cpuhp_cpu_attrs,
	.name = "hotplug",
	NULL
};

static ssize_t show_cpuhp_states(struct device *dev,
				 struct device_attribute *attr, char *buf)
{
	ssize_t cur, res = 0;
	int i;

	mutex_lock(&cpuhp_state_mutex);
	for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) {
		struct cpuhp_step *sp = cpuhp_get_step(i);

		if (sp->name) {
			cur = sprintf(buf, "%3d: %s\n", i, sp->name);
			buf += cur;
			res += cur;
		}
	}
	mutex_unlock(&cpuhp_state_mutex);
	return res;
}
static DEVICE_ATTR(states, 0444, show_cpuhp_states, NULL);

static struct attribute *cpuhp_cpu_root_attrs[] = {
	&dev_attr_states.attr,
	NULL
};

static const struct attribute_group cpuhp_cpu_root_attr_group = {
	.attrs = cpuhp_cpu_root_attrs,
	.name = "hotplug",
	NULL
};

#ifdef CONFIG_HOTPLUG_SMT

static const char *smt_states[] = {
	[CPU_SMT_ENABLED]		= "on",
	[CPU_SMT_DISABLED]		= "off",
	[CPU_SMT_FORCE_DISABLED]	= "forceoff",
	[CPU_SMT_NOT_SUPPORTED]		= "notsupported",
};

static ssize_t
show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
{
	return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
}

static void cpuhp_offline_cpu_device(unsigned int cpu)
{
	struct device *dev = get_cpu_device(cpu);

	dev->offline = true;
	/* Tell user space about the state change */
	kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
}

static void cpuhp_online_cpu_device(unsigned int cpu)
{
	struct device *dev = get_cpu_device(cpu);

	dev->offline = false;
	/* Tell user space about the state change */
	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
}

int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
{
	int cpu, ret = 0;

	cpu_maps_update_begin();
	for_each_online_cpu(cpu) {
		if (topology_is_primary_thread(cpu))
			continue;
		ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
		if (ret)
			break;
		/*
		 * As this needs to hold the cpu maps lock it's impossible
		 * to call device_offline() because that ends up calling
		 * cpu_down() which takes cpu maps lock. cpu maps lock
		 * needs to be held as this might race against in kernel
		 * abusers of the hotplug machinery (thermal management).
		 *
		 * So nothing would update device:offline state. That would
		 * leave the sysfs entry stale and prevent onlining after
		 * smt control has been changed to 'off' again. This is
		 * called under the sysfs hotplug lock, so it is properly
		 * serialized against the regular offline usage.
		 */
		cpuhp_offline_cpu_device(cpu);
	}
	if (!ret)
		cpu_smt_control = ctrlval;
	cpu_maps_update_done();
	return ret;
}

int cpuhp_smt_enable(void)
{
	int cpu, ret = 0;

	cpu_maps_update_begin();
	cpu_smt_control = CPU_SMT_ENABLED;
	for_each_present_cpu(cpu) {
		/* Skip online CPUs and CPUs on offline nodes */
		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
			continue;
		ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
		if (ret)
			break;
		/* See comment in cpuhp_smt_disable() */
		cpuhp_online_cpu_device(cpu);
	}
	cpu_maps_update_done();
	return ret;
}

static ssize_t
store_smt_control(struct device *dev, struct device_attribute *attr,
		  const char *buf, size_t count)
{
	int ctrlval, ret;

	if (sysfs_streq(buf, "on"))
		ctrlval = CPU_SMT_ENABLED;
	else if (sysfs_streq(buf, "off"))
		ctrlval = CPU_SMT_DISABLED;
	else if (sysfs_streq(buf, "forceoff"))
		ctrlval = CPU_SMT_FORCE_DISABLED;
	else
		return -EINVAL;

	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
		return -EPERM;

	if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
		return -ENODEV;

	ret = lock_device_hotplug_sysfs();
	if (ret)
		return ret;

	if (ctrlval != cpu_smt_control) {
		switch (ctrlval) {
		case CPU_SMT_ENABLED:
			ret = cpuhp_smt_enable();
			break;
		case CPU_SMT_DISABLED:
		case CPU_SMT_FORCE_DISABLED:
			ret = cpuhp_smt_disable(ctrlval);
			break;
		}
	}

	unlock_device_hotplug();
	return ret ? ret : count;
}
static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);

static ssize_t
show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
{
	bool active = topology_max_smt_threads() > 1;

	return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
}
static DEVICE_ATTR(active, 0444, show_smt_active, NULL);

static struct attribute *cpuhp_smt_attrs[] = {
	&dev_attr_control.attr,
	&dev_attr_active.attr,
	NULL
};

static const struct attribute_group cpuhp_smt_attr_group = {
	.attrs = cpuhp_smt_attrs,
	.name = "smt",
	NULL
};

static int __init cpu_smt_state_init(void)
{
	return sysfs_create_group(&cpu_subsys.dev_root->kobj,
				  &cpuhp_smt_attr_group);
}

#else
static inline int cpu_smt_state_init(void) { return 0; }
#endif

static int __init cpuhp_sysfs_init(void)
{
	int cpu, ret;

	ret = cpu_smt_state_init();
	if (ret)
		return ret;

	ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
				 &cpuhp_cpu_root_attr_group);
	if (ret)
		return ret;

	for_each_possible_cpu(cpu) {
		struct device *dev = get_cpu_device(cpu);

		if (!dev)
			continue;
		ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group);
		if (ret)
			return ret;
	}
	return 0;
}
device_initcall(cpuhp_sysfs_init);
#endif

/*
 * cpu_bit_bitmap[] is a special, "compressed" data structure that
 * represents all NR_CPUS bits binary values of 1<<nr.
 *
 * It is used by cpumask_of() to get a constant address to a CPU
 * mask value that has a single bit set only.
 */

/* cpu_bit_bitmap[0] is empty - so we can back into it */
#define MASK_DECLARE_1(x)	[x+1][0] = (1UL << (x))
#define MASK_DECLARE_2(x)	MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
#define MASK_DECLARE_4(x)	MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
#define MASK_DECLARE_8(x)	MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)

const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {

	MASK_DECLARE_8(0),	MASK_DECLARE_8(8),
	MASK_DECLARE_8(16),	MASK_DECLARE_8(24),
#if BITS_PER_LONG > 32
	MASK_DECLARE_8(32),	MASK_DECLARE_8(40),
	MASK_DECLARE_8(48),	MASK_DECLARE_8(56),
#endif
};
EXPORT_SYMBOL_GPL(cpu_bit_bitmap);

const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
EXPORT_SYMBOL(cpu_all_bits);

#ifdef CONFIG_INIT_ALL_POSSIBLE
struct cpumask __cpu_possible_mask __read_mostly
	= {CPU_BITS_ALL};
#else
struct cpumask __cpu_possible_mask __read_mostly;
#endif
EXPORT_SYMBOL(__cpu_possible_mask);

struct cpumask __cpu_online_mask __read_mostly;
EXPORT_SYMBOL(__cpu_online_mask);

struct cpumask __cpu_present_mask __read_mostly;
EXPORT_SYMBOL(__cpu_present_mask);

struct cpumask __cpu_active_mask __read_mostly;
EXPORT_SYMBOL(__cpu_active_mask);

void init_cpu_present(const struct cpumask *src)
{
	cpumask_copy(&__cpu_present_mask, src);
}

void init_cpu_possible(const struct cpumask *src)
{
	cpumask_copy(&__cpu_possible_mask, src);
}

void init_cpu_online(const struct cpumask *src)
{
	cpumask_copy(&__cpu_online_mask, src);
}

/*
 * Activate the first processor.
 */
void __init boot_cpu_init(void)
{
	int cpu = smp_processor_id();

	/* Mark the boot cpu "present", "online" etc for SMP and UP case */
	set_cpu_online(cpu, true);
	set_cpu_active(cpu, true);
	set_cpu_present(cpu, true);
	set_cpu_possible(cpu, true);

#ifdef CONFIG_SMP
	__boot_cpu_id = cpu;
#endif
}

/*
 * Must be called _AFTER_ setting up the per_cpu areas
 */
void __init boot_cpu_hotplug_init(void)
{
#ifdef CONFIG_SMP
	this_cpu_write(cpuhp_state.booted_once, true);
#endif
	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
}

/*
 * These are used for a global "mitigations=" cmdline option for toggling
 * optional CPU mitigations.
 */
enum cpu_mitigations {
	CPU_MITIGATIONS_OFF,
	CPU_MITIGATIONS_AUTO,
	CPU_MITIGATIONS_AUTO_NOSMT,
};

static enum cpu_mitigations cpu_mitigations __ro_after_init =
	CPU_MITIGATIONS_AUTO;

static int __init mitigations_parse_cmdline(char *arg)
{
	if (!strcmp(arg, "off"))
		cpu_mitigations = CPU_MITIGATIONS_OFF;
	else if (!strcmp(arg, "auto"))
		cpu_mitigations = CPU_MITIGATIONS_AUTO;
	else if (!strcmp(arg, "auto,nosmt"))
		cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT;
	else
		pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n",
			arg);

	return 0;
}
early_param("mitigations", mitigations_parse_cmdline);

/* mitigations=off */
bool cpu_mitigations_off(void)
{
	return cpu_mitigations == CPU_MITIGATIONS_OFF;
}
EXPORT_SYMBOL_GPL(cpu_mitigations_off);

/* mitigations=auto,nosmt */
bool cpu_mitigations_auto_nosmt(void)
{
	return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
}
EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);