Home Home > GIT Browse > stable-xen
summaryrefslogtreecommitdiff
blob: 9bf97a366029f22b959a50d819d362b0f51bf5a4 (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
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
/*
 *  linux/drivers/cpufreq/cpufreq.c
 *
 *  Copyright (C) 2001 Russell King
 *            (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
 *            (C) 2013 Viresh Kumar <viresh.kumar@linaro.org>
 *
 *  Oct 2005 - Ashok Raj <ashok.raj@intel.com>
 *	Added handling for CPU hotplug
 *  Feb 2006 - Jacob Shin <jacob.shin@amd.com>
 *	Fix handling for CPU hotplug -- affected CPUs
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/cpu.h>
#include <linux/cpufreq.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/init.h>
#include <linux/kernel_stat.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
#include <linux/tick.h>
#include <trace/events/power.h>

static LIST_HEAD(cpufreq_policy_list);

static inline bool policy_is_inactive(struct cpufreq_policy *policy)
{
	return cpumask_empty(policy->cpus);
}

/* Macros to iterate over CPU policies */
#define for_each_suitable_policy(__policy, __active)			 \
	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list) \
		if ((__active) == !policy_is_inactive(__policy))

#define for_each_active_policy(__policy)		\
	for_each_suitable_policy(__policy, true)
#define for_each_inactive_policy(__policy)		\
	for_each_suitable_policy(__policy, false)

#define for_each_policy(__policy)			\
	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list)

/* Iterate over governors */
static LIST_HEAD(cpufreq_governor_list);
#define for_each_governor(__governor)				\
	list_for_each_entry(__governor, &cpufreq_governor_list, governor_list)

/**
 * The "cpufreq driver" - the arch- or hardware-dependent low
 * level driver of CPUFreq support, and its spinlock. This lock
 * also protects the cpufreq_cpu_data array.
 */
static struct cpufreq_driver *cpufreq_driver;
static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
static DEFINE_RWLOCK(cpufreq_driver_lock);

/* Flag to suspend/resume CPUFreq governors */
static bool cpufreq_suspended;

static inline bool has_target(void)
{
	return cpufreq_driver->target_index || cpufreq_driver->target;
}

/* internal prototypes */
static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
static int cpufreq_init_governor(struct cpufreq_policy *policy);
static void cpufreq_exit_governor(struct cpufreq_policy *policy);
static int cpufreq_start_governor(struct cpufreq_policy *policy);
static void cpufreq_stop_governor(struct cpufreq_policy *policy);
static void cpufreq_governor_limits(struct cpufreq_policy *policy);

/**
 * Two notifier lists: the "policy" list is involved in the
 * validation process for a new CPU frequency policy; the
 * "transition" list for kernel code that needs to handle
 * changes to devices when the CPU clock speed changes.
 * The mutex locks both lists.
 */
static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
static struct srcu_notifier_head cpufreq_transition_notifier_list;

static bool init_cpufreq_transition_notifier_list_called;
static int __init init_cpufreq_transition_notifier_list(void)
{
	srcu_init_notifier_head(&cpufreq_transition_notifier_list);
	init_cpufreq_transition_notifier_list_called = true;
	return 0;
}
pure_initcall(init_cpufreq_transition_notifier_list);

static int off __read_mostly;
static int cpufreq_disabled(void)
{
	return off;
}
void disable_cpufreq(void)
{
	off = 1;
}
static DEFINE_MUTEX(cpufreq_governor_mutex);

bool have_governor_per_policy(void)
{
	return !!(cpufreq_driver->flags & CPUFREQ_HAVE_GOVERNOR_PER_POLICY);
}
EXPORT_SYMBOL_GPL(have_governor_per_policy);

struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
{
	if (have_governor_per_policy())
		return &policy->kobj;
	else
		return cpufreq_global_kobject;
}
EXPORT_SYMBOL_GPL(get_governor_parent_kobj);

static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
{
	u64 idle_time;
	u64 cur_wall_time;
	u64 busy_time;

	cur_wall_time = jiffies64_to_nsecs(get_jiffies_64());

	busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];

	idle_time = cur_wall_time - busy_time;
	if (wall)
		*wall = div_u64(cur_wall_time, NSEC_PER_USEC);

	return div_u64(idle_time, NSEC_PER_USEC);
}

u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
{
	u64 idle_time = get_cpu_idle_time_us(cpu, io_busy ? wall : NULL);

	if (idle_time == -1ULL)
		return get_cpu_idle_time_jiffy(cpu, wall);
	else if (!io_busy)
		idle_time += get_cpu_iowait_time_us(cpu, wall);

	return idle_time;
}
EXPORT_SYMBOL_GPL(get_cpu_idle_time);

/*
 * This is a generic cpufreq init() routine which can be used by cpufreq
 * drivers of SMP systems. It will do following:
 * - validate & show freq table passed
 * - set policies transition latency
 * - policy->cpus with all possible CPUs
 */
int cpufreq_generic_init(struct cpufreq_policy *policy,
		struct cpufreq_frequency_table *table,
		unsigned int transition_latency)
{
	int ret;

	ret = cpufreq_table_validate_and_show(policy, table);
	if (ret) {
		pr_err("%s: invalid frequency table: %d\n", __func__, ret);
		return ret;
	}

	policy->cpuinfo.transition_latency = transition_latency;

	/*
	 * The driver only supports the SMP configuration where all processors
	 * share the clock and voltage and clock.
	 */
	cpumask_setall(policy->cpus);

	return 0;
}
EXPORT_SYMBOL_GPL(cpufreq_generic_init);

struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
{
	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);

	return policy && cpumask_test_cpu(cpu, policy->cpus) ? policy : NULL;
}
EXPORT_SYMBOL_GPL(cpufreq_cpu_get_raw);

unsigned int cpufreq_generic_get(unsigned int cpu)
{
	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);

	if (!policy || IS_ERR(policy->clk)) {
		pr_err("%s: No %s associated to cpu: %d\n",
		       __func__, policy ? "clk" : "policy", cpu);
		return 0;
	}

	return clk_get_rate(policy->clk) / 1000;
}
EXPORT_SYMBOL_GPL(cpufreq_generic_get);

/**
 * cpufreq_cpu_get: returns policy for a cpu and marks it busy.
 *
 * @cpu: cpu to find policy for.
 *
 * This returns policy for 'cpu', returns NULL if it doesn't exist.
 * It also increments the kobject reference count to mark it busy and so would
 * require a corresponding call to cpufreq_cpu_put() to decrement it back.
 * If corresponding call cpufreq_cpu_put() isn't made, the policy wouldn't be
 * freed as that depends on the kobj count.
 *
 * Return: A valid policy on success, otherwise NULL on failure.
 */
struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
{
	struct cpufreq_policy *policy = NULL;
	unsigned long flags;

	if (WARN_ON(cpu >= nr_cpu_ids))
		return NULL;

	/* get the cpufreq driver */
	read_lock_irqsave(&cpufreq_driver_lock, flags);

	if (cpufreq_driver) {
		/* get the CPU */
		policy = cpufreq_cpu_get_raw(cpu);
		if (policy)
			kobject_get(&policy->kobj);
	}

	read_unlock_irqrestore(&cpufreq_driver_lock, flags);

	return policy;
}
EXPORT_SYMBOL_GPL(cpufreq_cpu_get);

/**
 * cpufreq_cpu_put: Decrements the usage count of a policy
 *
 * @policy: policy earlier returned by cpufreq_cpu_get().
 *
 * This decrements the kobject reference count incremented earlier by calling
 * cpufreq_cpu_get().
 */
void cpufreq_cpu_put(struct cpufreq_policy *policy)
{
	kobject_put(&policy->kobj);
}
EXPORT_SYMBOL_GPL(cpufreq_cpu_put);

/*********************************************************************
 *            EXTERNALLY AFFECTING FREQUENCY CHANGES                 *
 *********************************************************************/

/**
 * adjust_jiffies - adjust the system "loops_per_jiffy"
 *
 * This function alters the system "loops_per_jiffy" for the clock
 * speed change. Note that loops_per_jiffy cannot be updated on SMP
 * systems as each CPU might be scaled differently. So, use the arch
 * per-CPU loops_per_jiffy value wherever possible.
 */
static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
{
#ifndef CONFIG_SMP
	static unsigned long l_p_j_ref;
	static unsigned int l_p_j_ref_freq;

	if (ci->flags & CPUFREQ_CONST_LOOPS)
		return;

	if (!l_p_j_ref_freq) {
		l_p_j_ref = loops_per_jiffy;
		l_p_j_ref_freq = ci->old;
		pr_debug("saving %lu as reference value for loops_per_jiffy; freq is %u kHz\n",
			 l_p_j_ref, l_p_j_ref_freq);
	}
	if (val == CPUFREQ_POSTCHANGE && ci->old != ci->new) {
		loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq,
								ci->new);
		pr_debug("scaling loops_per_jiffy to %lu for frequency %u kHz\n",
			 loops_per_jiffy, ci->new);
	}
#endif
}

static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
		struct cpufreq_freqs *freqs, unsigned int state)
{
	BUG_ON(irqs_disabled());

	if (cpufreq_disabled())
		return;

	freqs->flags = cpufreq_driver->flags;
	pr_debug("notification %u of frequency transition to %u kHz\n",
		 state, freqs->new);

	switch (state) {

	case CPUFREQ_PRECHANGE:
		/* detect if the driver reported a value as "old frequency"
		 * which is not equal to what the cpufreq core thinks is
		 * "old frequency".
		 */
		if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
			if ((policy) && (policy->cpu == freqs->cpu) &&
			    (policy->cur) && (policy->cur != freqs->old)) {
				pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
					 freqs->old, policy->cur);
				freqs->old = policy->cur;
			}
		}
		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
				CPUFREQ_PRECHANGE, freqs);
		adjust_jiffies(CPUFREQ_PRECHANGE, freqs);
		break;

	case CPUFREQ_POSTCHANGE:
		adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
		pr_debug("FREQ: %lu - CPU: %lu\n",
			 (unsigned long)freqs->new, (unsigned long)freqs->cpu);
		trace_cpu_frequency(freqs->new, freqs->cpu);
		cpufreq_stats_record_transition(policy, freqs->new);
		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
				CPUFREQ_POSTCHANGE, freqs);
		if (likely(policy) && likely(policy->cpu == freqs->cpu))
			policy->cur = freqs->new;
		break;
	}
}

/**
 * cpufreq_notify_transition - call notifier chain and adjust_jiffies
 * on frequency transition.
 *
 * This function calls the transition notifiers and the "adjust_jiffies"
 * function. It is called twice on all CPU frequency changes that have
 * external effects.
 */
static void cpufreq_notify_transition(struct cpufreq_policy *policy,
		struct cpufreq_freqs *freqs, unsigned int state)
{
	for_each_cpu(freqs->cpu, policy->cpus)
		__cpufreq_notify_transition(policy, freqs, state);
}

/* Do post notifications when there are chances that transition has failed */
static void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
		struct cpufreq_freqs *freqs, int transition_failed)
{
	cpufreq_notify_transition(policy, freqs, CPUFREQ_POSTCHANGE);
	if (!transition_failed)
		return;

	swap(freqs->old, freqs->new);
	cpufreq_notify_transition(policy, freqs, CPUFREQ_PRECHANGE);
	cpufreq_notify_transition(policy, freqs, CPUFREQ_POSTCHANGE);
}

void cpufreq_freq_transition_begin(struct cpufreq_policy *policy,
		struct cpufreq_freqs *freqs)
{

	/*
	 * Catch double invocations of _begin() which lead to self-deadlock.
	 * ASYNC_NOTIFICATION drivers are left out because the cpufreq core
	 * doesn't invoke _begin() on their behalf, and hence the chances of
	 * double invocations are very low. Moreover, there are scenarios
	 * where these checks can emit false-positive warnings in these
	 * drivers; so we avoid that by skipping them altogether.
	 */
	WARN_ON(!(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION)
				&& current == policy->transition_task);

wait:
	wait_event(policy->transition_wait, !policy->transition_ongoing);

	spin_lock(&policy->transition_lock);

	if (unlikely(policy->transition_ongoing)) {
		spin_unlock(&policy->transition_lock);
		goto wait;
	}

	policy->transition_ongoing = true;
	policy->transition_task = current;

	spin_unlock(&policy->transition_lock);

	cpufreq_notify_transition(policy, freqs, CPUFREQ_PRECHANGE);
}
EXPORT_SYMBOL_GPL(cpufreq_freq_transition_begin);

void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
		struct cpufreq_freqs *freqs, int transition_failed)
{
	if (unlikely(WARN_ON(!policy->transition_ongoing)))
		return;

	cpufreq_notify_post_transition(policy, freqs, transition_failed);

	policy->transition_ongoing = false;
	policy->transition_task = NULL;

	wake_up(&policy->transition_wait);
}
EXPORT_SYMBOL_GPL(cpufreq_freq_transition_end);

/*
 * Fast frequency switching status count.  Positive means "enabled", negative
 * means "disabled" and 0 means "not decided yet".
 */
static int cpufreq_fast_switch_count;
static DEFINE_MUTEX(cpufreq_fast_switch_lock);

static void cpufreq_list_transition_notifiers(void)
{
	struct notifier_block *nb;

	pr_info("Registered transition notifiers:\n");

	mutex_lock(&cpufreq_transition_notifier_list.mutex);

	for (nb = cpufreq_transition_notifier_list.head; nb; nb = nb->next)
		pr_info("%pF\n", nb->notifier_call);

	mutex_unlock(&cpufreq_transition_notifier_list.mutex);
}

/**
 * cpufreq_enable_fast_switch - Enable fast frequency switching for policy.
 * @policy: cpufreq policy to enable fast frequency switching for.
 *
 * Try to enable fast frequency switching for @policy.
 *
 * The attempt will fail if there is at least one transition notifier registered
 * at this point, as fast frequency switching is quite fundamentally at odds
 * with transition notifiers.  Thus if successful, it will make registration of
 * transition notifiers fail going forward.
 */
void cpufreq_enable_fast_switch(struct cpufreq_policy *policy)
{
	lockdep_assert_held(&policy->rwsem);

	if (!policy->fast_switch_possible)
		return;

	mutex_lock(&cpufreq_fast_switch_lock);
	if (cpufreq_fast_switch_count >= 0) {
		cpufreq_fast_switch_count++;
		policy->fast_switch_enabled = true;
	} else {
		pr_warn("CPU%u: Fast frequency switching not enabled\n",
			policy->cpu);
		cpufreq_list_transition_notifiers();
	}
	mutex_unlock(&cpufreq_fast_switch_lock);
}
EXPORT_SYMBOL_GPL(cpufreq_enable_fast_switch);

/**
 * cpufreq_disable_fast_switch - Disable fast frequency switching for policy.
 * @policy: cpufreq policy to disable fast frequency switching for.
 */
void cpufreq_disable_fast_switch(struct cpufreq_policy *policy)
{
	mutex_lock(&cpufreq_fast_switch_lock);
	if (policy->fast_switch_enabled) {
		policy->fast_switch_enabled = false;
		if (!WARN_ON(cpufreq_fast_switch_count <= 0))
			cpufreq_fast_switch_count--;
	}
	mutex_unlock(&cpufreq_fast_switch_lock);
}
EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch);

/**
 * cpufreq_driver_resolve_freq - Map a target frequency to a driver-supported
 * one.
 * @target_freq: target frequency to resolve.
 *
 * The target to driver frequency mapping is cached in the policy.
 *
 * Return: Lowest driver-supported frequency greater than or equal to the
 * given target_freq, subject to policy (min/max) and driver limitations.
 */
unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
					 unsigned int target_freq)
{
	target_freq = clamp_val(target_freq, policy->min, policy->max);
	policy->cached_target_freq = target_freq;

	if (cpufreq_driver->target_index) {
		int idx;

		idx = cpufreq_frequency_table_target(policy, target_freq,
						     CPUFREQ_RELATION_L);
		policy->cached_resolved_idx = idx;
		return policy->freq_table[idx].frequency;
	}

	if (cpufreq_driver->resolve_freq)
		return cpufreq_driver->resolve_freq(policy, target_freq);

	return target_freq;
}
EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq);

/*********************************************************************
 *                          SYSFS INTERFACE                          *
 *********************************************************************/
static ssize_t show_boost(struct kobject *kobj,
				 struct attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled);
}

static ssize_t store_boost(struct kobject *kobj, struct attribute *attr,
				  const char *buf, size_t count)
{
	int ret, enable;

	ret = sscanf(buf, "%d", &enable);
	if (ret != 1 || enable < 0 || enable > 1)
		return -EINVAL;

	if (cpufreq_boost_trigger_state(enable)) {
		pr_err("%s: Cannot %s BOOST!\n",
		       __func__, enable ? "enable" : "disable");
		return -EINVAL;
	}

	pr_debug("%s: cpufreq BOOST %s\n",
		 __func__, enable ? "enabled" : "disabled");

	return count;
}
define_one_global_rw(boost);

static struct cpufreq_governor *find_governor(const char *str_governor)
{
	struct cpufreq_governor *t;

	for_each_governor(t)
		if (!strncasecmp(str_governor, t->name, CPUFREQ_NAME_LEN))
			return t;

	return NULL;
}

/**
 * cpufreq_parse_governor - parse a governor string
 */
static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
				struct cpufreq_governor **governor)
{
	int err = -EINVAL;

	if (cpufreq_driver->setpolicy) {
		if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
			*policy = CPUFREQ_POLICY_PERFORMANCE;
			err = 0;
		} else if (!strncasecmp(str_governor, "powersave",
						CPUFREQ_NAME_LEN)) {
			*policy = CPUFREQ_POLICY_POWERSAVE;
			err = 0;
		}
	} else {
		struct cpufreq_governor *t;

		mutex_lock(&cpufreq_governor_mutex);

		t = find_governor(str_governor);

		if (t == NULL) {
			int ret;

			mutex_unlock(&cpufreq_governor_mutex);
			ret = request_module("cpufreq_%s", str_governor);
			mutex_lock(&cpufreq_governor_mutex);

			if (ret == 0)
				t = find_governor(str_governor);
		}

		if (t != NULL) {
			*governor = t;
			err = 0;
		}

		mutex_unlock(&cpufreq_governor_mutex);
	}
	return err;
}

/**
 * cpufreq_per_cpu_attr_read() / show_##file_name() -
 * print out cpufreq information
 *
 * Write out information from cpufreq_driver->policy[cpu]; object must be
 * "unsigned int".
 */

#define show_one(file_name, object)			\
static ssize_t show_##file_name				\
(struct cpufreq_policy *policy, char *buf)		\
{							\
	return sprintf(buf, "%u\n", policy->object);	\
}

show_one(cpuinfo_min_freq, cpuinfo.min_freq);
show_one(cpuinfo_max_freq, cpuinfo.max_freq);
show_one(cpuinfo_transition_latency, cpuinfo.transition_latency);
show_one(scaling_min_freq, min);
show_one(scaling_max_freq, max);

__weak unsigned int arch_freq_get_on_cpu(int cpu)
{
	return 0;
}

static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf)
{
	ssize_t ret;
	unsigned int freq;

	freq = arch_freq_get_on_cpu(policy->cpu);
	if (freq)
		ret = sprintf(buf, "%u\n", freq);
	else if (cpufreq_driver && cpufreq_driver->setpolicy &&
			cpufreq_driver->get)
		ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu));
	else
		ret = sprintf(buf, "%u\n", policy->cur);
	return ret;
}

static int cpufreq_set_policy(struct cpufreq_policy *policy,
				struct cpufreq_policy *new_policy);

/**
 * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access
 */
#define store_one(file_name, object)			\
static ssize_t store_##file_name					\
(struct cpufreq_policy *policy, const char *buf, size_t count)		\
{									\
	int ret, temp;							\
	struct cpufreq_policy new_policy;				\
									\
	memcpy(&new_policy, policy, sizeof(*policy));			\
									\
	ret = sscanf(buf, "%u", &new_policy.object);			\
	if (ret != 1)							\
		return -EINVAL;						\
									\
	temp = new_policy.object;					\
	ret = cpufreq_set_policy(policy, &new_policy);		\
	if (!ret)							\
		policy->user_policy.object = temp;			\
									\
	return ret ? ret : count;					\
}

store_one(scaling_min_freq, min);
store_one(scaling_max_freq, max);

/**
 * show_cpuinfo_cur_freq - current CPU frequency as detected by hardware
 */
static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
					char *buf)
{
	unsigned int cur_freq = __cpufreq_get(policy);

	if (cur_freq)
		return sprintf(buf, "%u\n", cur_freq);

	return sprintf(buf, "<unknown>\n");
}

/**
 * show_scaling_governor - show the current policy for the specified CPU
 */
static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
{
	if (policy->policy == CPUFREQ_POLICY_POWERSAVE)
		return sprintf(buf, "powersave\n");
	else if (policy->policy == CPUFREQ_POLICY_PERFORMANCE)
		return sprintf(buf, "performance\n");
	else if (policy->governor)
		return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n",
				policy->governor->name);
	return -EINVAL;
}

/**
 * store_scaling_governor - store policy for the specified CPU
 */
static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
					const char *buf, size_t count)
{
	int ret;
	char	str_governor[16];
	struct cpufreq_policy new_policy;

	memcpy(&new_policy, policy, sizeof(*policy));

	ret = sscanf(buf, "%15s", str_governor);
	if (ret != 1)
		return -EINVAL;

	if (cpufreq_parse_governor(str_governor, &new_policy.policy,
						&new_policy.governor))
		return -EINVAL;

	ret = cpufreq_set_policy(policy, &new_policy);
	return ret ? ret : count;
}

/**
 * show_scaling_driver - show the cpufreq driver currently loaded
 */
static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf)
{
	return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", cpufreq_driver->name);
}

/**
 * show_scaling_available_governors - show the available CPUfreq governors
 */
static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
						char *buf)
{
	ssize_t i = 0;
	struct cpufreq_governor *t;

	if (!has_target()) {
		i += sprintf(buf, "performance powersave");
		goto out;
	}

	for_each_governor(t) {
		if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char))
		    - (CPUFREQ_NAME_LEN + 2)))
			goto out;
		i += scnprintf(&buf[i], CPUFREQ_NAME_PLEN, "%s ", t->name);
	}
out:
	i += sprintf(&buf[i], "\n");
	return i;
}

ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf)
{
	ssize_t i = 0;
	unsigned int cpu;

	for_each_cpu(cpu, mask) {
		if (i)
			i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), " ");
		i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), "%u", cpu);
		if (i >= (PAGE_SIZE - 5))
			break;
	}
	i += sprintf(&buf[i], "\n");
	return i;
}
EXPORT_SYMBOL_GPL(cpufreq_show_cpus);

/**
 * show_related_cpus - show the CPUs affected by each transition even if
 * hw coordination is in use
 */
static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf)
{
	return cpufreq_show_cpus(policy->related_cpus, buf);
}

/**
 * show_affected_cpus - show the CPUs affected by each transition
 */
static ssize_t show_affected_cpus(struct cpufreq_policy *policy, char *buf)
{
	return cpufreq_show_cpus(policy->cpus, buf);
}

static ssize_t store_scaling_setspeed(struct cpufreq_policy *policy,
					const char *buf, size_t count)
{
	unsigned int freq = 0;
	unsigned int ret;

	if (!policy->governor || !policy->governor->store_setspeed)
		return -EINVAL;

	ret = sscanf(buf, "%u", &freq);
	if (ret != 1)
		return -EINVAL;

	policy->governor->store_setspeed(policy, freq);

	return count;
}

static ssize_t show_scaling_setspeed(struct cpufreq_policy *policy, char *buf)
{
	if (!policy->governor || !policy->governor->show_setspeed)
		return sprintf(buf, "<unsupported>\n");

	return policy->governor->show_setspeed(policy, buf);
}

/**
 * show_bios_limit - show the current cpufreq HW/BIOS limitation
 */
static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
{
	unsigned int limit;
	int ret;
	if (cpufreq_driver->bios_limit) {
		ret = cpufreq_driver->bios_limit(policy->cpu, &limit);
		if (!ret)
			return sprintf(buf, "%u\n", limit);
	}
	return sprintf(buf, "%u\n", policy->cpuinfo.max_freq);
}

cpufreq_freq_attr_ro_perm(cpuinfo_cur_freq, 0400);
cpufreq_freq_attr_ro(cpuinfo_min_freq);
cpufreq_freq_attr_ro(cpuinfo_max_freq);
cpufreq_freq_attr_ro(cpuinfo_transition_latency);
cpufreq_freq_attr_ro(scaling_available_governors);
cpufreq_freq_attr_ro(scaling_driver);
cpufreq_freq_attr_ro(scaling_cur_freq);
cpufreq_freq_attr_ro(bios_limit);
cpufreq_freq_attr_ro(related_cpus);
cpufreq_freq_attr_ro(affected_cpus);
cpufreq_freq_attr_rw(scaling_min_freq);
cpufreq_freq_attr_rw(scaling_max_freq);
cpufreq_freq_attr_rw(scaling_governor);
cpufreq_freq_attr_rw(scaling_setspeed);

static struct attribute *default_attrs[] = {
	&cpuinfo_min_freq.attr,
	&cpuinfo_max_freq.attr,
	&cpuinfo_transition_latency.attr,
	&scaling_min_freq.attr,
	&scaling_max_freq.attr,
	&affected_cpus.attr,
	&related_cpus.attr,
	&scaling_governor.attr,
	&scaling_driver.attr,
	&scaling_available_governors.attr,
	&scaling_setspeed.attr,
	NULL
};

#define to_policy(k) container_of(k, struct cpufreq_policy, kobj)
#define to_attr(a) container_of(a, struct freq_attr, attr)

static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
{
	struct cpufreq_policy *policy = to_policy(kobj);
	struct freq_attr *fattr = to_attr(attr);
	ssize_t ret;

	down_read(&policy->rwsem);
	ret = fattr->show(policy, buf);
	up_read(&policy->rwsem);

	return ret;
}

static ssize_t store(struct kobject *kobj, struct attribute *attr,
		     const char *buf, size_t count)
{
	struct cpufreq_policy *policy = to_policy(kobj);
	struct freq_attr *fattr = to_attr(attr);
	ssize_t ret = -EINVAL;

	cpus_read_lock();

	if (cpu_online(policy->cpu)) {
		down_write(&policy->rwsem);
		ret = fattr->store(policy, buf, count);
		up_write(&policy->rwsem);
	}

	cpus_read_unlock();

	return ret;
}

static void cpufreq_sysfs_release(struct kobject *kobj)
{
	struct cpufreq_policy *policy = to_policy(kobj);
	pr_debug("last reference is dropped\n");
	complete(&policy->kobj_unregister);
}

static const struct sysfs_ops sysfs_ops = {
	.show	= show,
	.store	= store,
};

static struct kobj_type ktype_cpufreq = {
	.sysfs_ops	= &sysfs_ops,
	.default_attrs	= default_attrs,
	.release	= cpufreq_sysfs_release,
};

static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu)
{
	struct device *dev = get_cpu_device(cpu);

	if (!dev)
		return;

	if (cpumask_test_and_set_cpu(cpu, policy->real_cpus))
		return;

	dev_dbg(dev, "%s: Adding symlink\n", __func__);
	if (sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq"))
		dev_err(dev, "cpufreq symlink creation failed\n");
}

static void remove_cpu_dev_symlink(struct cpufreq_policy *policy,
				   struct device *dev)
{
	dev_dbg(dev, "%s: Removing symlink\n", __func__);
	sysfs_remove_link(&dev->kobj, "cpufreq");
}

static int cpufreq_add_dev_interface(struct cpufreq_policy *policy)
{
	struct freq_attr **drv_attr;
	int ret = 0;

	/* set up files for this cpu device */
	drv_attr = cpufreq_driver->attr;
	while (drv_attr && *drv_attr) {
		ret = sysfs_create_file(&policy->kobj, &((*drv_attr)->attr));
		if (ret)
			return ret;
		drv_attr++;
	}
	if (cpufreq_driver->get) {
		ret = sysfs_create_file(&policy->kobj, &cpuinfo_cur_freq.attr);
		if (ret)
			return ret;
	}

	ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
	if (ret)
		return ret;

	if (cpufreq_driver->bios_limit) {
		ret = sysfs_create_file(&policy->kobj, &bios_limit.attr);
		if (ret)
			return ret;
	}

	return 0;
}

__weak struct cpufreq_governor *cpufreq_default_governor(void)
{
	return NULL;
}

static int cpufreq_init_policy(struct cpufreq_policy *policy)
{
	struct cpufreq_governor *gov = NULL;
	struct cpufreq_policy new_policy;

	memcpy(&new_policy, policy, sizeof(*policy));

	/* Update governor of new_policy to the governor used before hotplug */
	gov = find_governor(policy->last_governor);
	if (gov) {
		pr_debug("Restoring governor %s for cpu %d\n",
				policy->governor->name, policy->cpu);
	} else {
		gov = cpufreq_default_governor();
		if (!gov)
			return -ENODATA;
	}

	new_policy.governor = gov;

	/* Use the default policy if there is no last_policy. */
	if (cpufreq_driver->setpolicy) {
		if (policy->last_policy)
			new_policy.policy = policy->last_policy;
		else
			cpufreq_parse_governor(gov->name, &new_policy.policy,
					       NULL);
	}
	/* set default policy */
	return cpufreq_set_policy(policy, &new_policy);
}

static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
{
	int ret = 0;

	/* Has this CPU been taken care of already? */
	if (cpumask_test_cpu(cpu, policy->cpus))
		return 0;

	down_write(&policy->rwsem);
	if (has_target())
		cpufreq_stop_governor(policy);

	cpumask_set_cpu(cpu, policy->cpus);

	if (has_target()) {
		ret = cpufreq_start_governor(policy);
		if (ret)
			pr_err("%s: Failed to start governor\n", __func__);
	}
	up_write(&policy->rwsem);
	return ret;
}

static void handle_update(struct work_struct *work)
{
	struct cpufreq_policy *policy =
		container_of(work, struct cpufreq_policy, update);
	unsigned int cpu = policy->cpu;
	pr_debug("handle_update for cpu %u called\n", cpu);
	cpufreq_update_policy(cpu);
}

static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
{
	struct cpufreq_policy *policy;
	int ret;

	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
	if (!policy)
		return NULL;

	if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL))
		goto err_free_policy;

	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
		goto err_free_cpumask;

	if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL))
		goto err_free_rcpumask;

	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
				   cpufreq_global_kobject, "policy%u", cpu);
	if (ret) {
		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
		goto err_free_real_cpus;
	}

	INIT_LIST_HEAD(&policy->policy_list);
	init_rwsem(&policy->rwsem);
	spin_lock_init(&policy->transition_lock);
	init_waitqueue_head(&policy->transition_wait);
	init_completion(&policy->kobj_unregister);
	INIT_WORK(&policy->update, handle_update);

	policy->cpu = cpu;
	return policy;

err_free_real_cpus:
	free_cpumask_var(policy->real_cpus);
err_free_rcpumask:
	free_cpumask_var(policy->related_cpus);
err_free_cpumask:
	free_cpumask_var(policy->cpus);
err_free_policy:
	kfree(policy);

	return NULL;
}

static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
{
	struct kobject *kobj;
	struct completion *cmp;

	down_write(&policy->rwsem);
	cpufreq_stats_free_table(policy);
	kobj = &policy->kobj;
	cmp = &policy->kobj_unregister;
	up_write(&policy->rwsem);
	kobject_put(kobj);

	/*
	 * We need to make sure that the underlying kobj is
	 * actually not referenced anymore by anybody before we
	 * proceed with unloading.
	 */
	pr_debug("waiting for dropping of refcount\n");
	wait_for_completion(cmp);
	pr_debug("wait complete\n");
}

static void cpufreq_policy_free(struct cpufreq_policy *policy)
{
	unsigned long flags;
	int cpu;

	/* Remove policy from list */
	write_lock_irqsave(&cpufreq_driver_lock, flags);
	list_del(&policy->policy_list);

	for_each_cpu(cpu, policy->related_cpus)
		per_cpu(cpufreq_cpu_data, cpu) = NULL;
	write_unlock_irqrestore(&cpufreq_driver_lock, flags);

	cpufreq_policy_put_kobj(policy);
	free_cpumask_var(policy->real_cpus);
	free_cpumask_var(policy->related_cpus);
	free_cpumask_var(policy->cpus);
	kfree(policy);
}

static int cpufreq_online(unsigned int cpu)
{
	struct cpufreq_policy *policy;
	bool new_policy;
	unsigned long flags;
	unsigned int j;
	int ret;

	pr_debug("%s: bringing CPU%u online\n", __func__, cpu);

	/* Check if this CPU already has a policy to manage it */
	policy = per_cpu(cpufreq_cpu_data, cpu);
	if (policy) {
		WARN_ON(!cpumask_test_cpu(cpu, policy->related_cpus));
		if (!policy_is_inactive(policy))
			return cpufreq_add_policy_cpu(policy, cpu);

		/* This is the only online CPU for the policy.  Start over. */
		new_policy = false;
		down_write(&policy->rwsem);
		policy->cpu = cpu;
		policy->governor = NULL;
		up_write(&policy->rwsem);
	} else {
		new_policy = true;
		policy = cpufreq_policy_alloc(cpu);
		if (!policy)
			return -ENOMEM;
	}

	cpumask_copy(policy->cpus, cpumask_of(cpu));

	/* call driver. From then on the cpufreq must be able
	 * to accept all calls to ->verify and ->setpolicy for this CPU
	 */
	ret = cpufreq_driver->init(policy);
	if (ret) {
		pr_debug("initialization failed\n");
		goto out_free_policy;
	}

	down_write(&policy->rwsem);

	if (new_policy) {
		/* related_cpus should at least include policy->cpus. */
		cpumask_copy(policy->related_cpus, policy->cpus);
	}

	/*
	 * affected cpus must always be the one, which are online. We aren't
	 * managing offline cpus here.
	 */
	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);

	if (new_policy) {
		policy->user_policy.min = policy->min;
		policy->user_policy.max = policy->max;

		for_each_cpu(j, policy->related_cpus) {
			per_cpu(cpufreq_cpu_data, j) = policy;
			add_cpu_dev_symlink(policy, j);
		}
	} else {
		policy->min = policy->user_policy.min;
		policy->max = policy->user_policy.max;
	}

	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
		policy->cur = cpufreq_driver->get(policy->cpu);
		if (!policy->cur) {
			pr_err("%s: ->get() failed\n", __func__);
			goto out_exit_policy;
		}
	}

	/*
	 * Sometimes boot loaders set CPU frequency to a value outside of
	 * frequency table present with cpufreq core. In such cases CPU might be
	 * unstable if it has to run on that frequency for long duration of time
	 * and so its better to set it to a frequency which is specified in
	 * freq-table. This also makes cpufreq stats inconsistent as
	 * cpufreq-stats would fail to register because current frequency of CPU
	 * isn't found in freq-table.
	 *
	 * Because we don't want this change to effect boot process badly, we go
	 * for the next freq which is >= policy->cur ('cur' must be set by now,
	 * otherwise we will end up setting freq to lowest of the table as 'cur'
	 * is initialized to zero).
	 *
	 * We are passing target-freq as "policy->cur - 1" otherwise
	 * __cpufreq_driver_target() would simply fail, as policy->cur will be
	 * equal to target-freq.
	 */
	if ((cpufreq_driver->flags & CPUFREQ_NEED_INITIAL_FREQ_CHECK)
	    && has_target()) {
		/* Are we running at unknown frequency ? */
		ret = cpufreq_frequency_table_get_index(policy, policy->cur);
		if (ret == -EINVAL) {
			/* Warn user and fix it */
			pr_warn("%s: CPU%d: Running at unlisted freq: %u KHz\n",
				__func__, policy->cpu, policy->cur);
			ret = __cpufreq_driver_target(policy, policy->cur - 1,
				CPUFREQ_RELATION_L);

			/*
			 * Reaching here after boot in a few seconds may not
			 * mean that system will remain stable at "unknown"
			 * frequency for longer duration. Hence, a BUG_ON().
			 */
			BUG_ON(ret);
			pr_warn("%s: CPU%d: Unlisted initial frequency changed to: %u KHz\n",
				__func__, policy->cpu, policy->cur);
		}
	}

	if (new_policy) {
		ret = cpufreq_add_dev_interface(policy);
		if (ret)
			goto out_exit_policy;

		cpufreq_stats_create_table(policy);

		write_lock_irqsave(&cpufreq_driver_lock, flags);
		list_add(&policy->policy_list, &cpufreq_policy_list);
		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
	}

	ret = cpufreq_init_policy(policy);
	if (ret) {
		pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n",
		       __func__, cpu, ret);
		/* cpufreq_policy_free() will notify based on this */
		new_policy = false;
		goto out_exit_policy;
	}

	up_write(&policy->rwsem);

	kobject_uevent(&policy->kobj, KOBJ_ADD);

	/* Callback for handling stuff after policy is ready */
	if (cpufreq_driver->ready)
		cpufreq_driver->ready(policy);

	pr_debug("initialization complete\n");

	return 0;

out_exit_policy:
	up_write(&policy->rwsem);

	if (cpufreq_driver->exit)
		cpufreq_driver->exit(policy);

	for_each_cpu(j, policy->real_cpus)
		remove_cpu_dev_symlink(policy, get_cpu_device(j));

out_free_policy:
	cpufreq_policy_free(policy);
	return ret;
}

/**
 * cpufreq_add_dev - the cpufreq interface for a CPU device.
 * @dev: CPU device.
 * @sif: Subsystem interface structure pointer (not used)
 */
static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
{
	struct cpufreq_policy *policy;
	unsigned cpu = dev->id;
	int ret;

	dev_dbg(dev, "%s: adding CPU%u\n", __func__, cpu);

	if (cpu_online(cpu)) {
		ret = cpufreq_online(cpu);
		if (ret)
			return ret;
	}

	/* Create sysfs link on CPU registration */
	policy = per_cpu(cpufreq_cpu_data, cpu);
	if (policy)
		add_cpu_dev_symlink(policy, cpu);

	return 0;
}

static int cpufreq_offline(unsigned int cpu)
{
	struct cpufreq_policy *policy;
	int ret;

	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);

	policy = cpufreq_cpu_get_raw(cpu);
	if (!policy) {
		pr_debug("%s: No cpu_data found\n", __func__);
		return 0;
	}

	down_write(&policy->rwsem);
	if (has_target())
		cpufreq_stop_governor(policy);

	cpumask_clear_cpu(cpu, policy->cpus);

	if (policy_is_inactive(policy)) {
		if (has_target())
			strncpy(policy->last_governor, policy->governor->name,
				CPUFREQ_NAME_LEN);
		else
			policy->last_policy = policy->policy;
	} else if (cpu == policy->cpu) {
		/* Nominate new CPU */
		policy->cpu = cpumask_any(policy->cpus);
	}

	/* Start governor again for active policy */
	if (!policy_is_inactive(policy)) {
		if (has_target()) {
			ret = cpufreq_start_governor(policy);
			if (ret)
				pr_err("%s: Failed to start governor\n", __func__);
		}

		goto unlock;
	}

	if (cpufreq_driver->stop_cpu)
		cpufreq_driver->stop_cpu(policy);

	if (has_target())
		cpufreq_exit_governor(policy);

	/*
	 * Perform the ->exit() even during light-weight tear-down,
	 * since this is a core component, and is essential for the
	 * subsequent light-weight ->init() to succeed.
	 */
	if (cpufreq_driver->exit) {
		cpufreq_driver->exit(policy);
		policy->freq_table = NULL;
	}

unlock:
	up_write(&policy->rwsem);
	return 0;
}

/**
 * cpufreq_remove_dev - remove a CPU device
 *
 * Removes the cpufreq interface for a CPU device.
 */
static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
{
	unsigned int cpu = dev->id;
	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);

	if (!policy)
		return;

	if (cpu_online(cpu))
		cpufreq_offline(cpu);

	cpumask_clear_cpu(cpu, policy->real_cpus);
	remove_cpu_dev_symlink(policy, dev);

	if (cpumask_empty(policy->real_cpus))
		cpufreq_policy_free(policy);
}

/**
 *	cpufreq_out_of_sync - If actual and saved CPU frequency differs, we're
 *	in deep trouble.
 *	@policy: policy managing CPUs
 *	@new_freq: CPU frequency the CPU actually runs at
 *
 *	We adjust to current frequency first, and need to clean up later.
 *	So either call to cpufreq_update_policy() or schedule handle_update()).
 */
static void cpufreq_out_of_sync(struct cpufreq_policy *policy,
				unsigned int new_freq)
{
	struct cpufreq_freqs freqs;

	pr_debug("Warning: CPU frequency out of sync: cpufreq and timing core thinks of %u, is %u kHz\n",
		 policy->cur, new_freq);

	freqs.old = policy->cur;
	freqs.new = new_freq;

	cpufreq_freq_transition_begin(policy, &freqs);
	cpufreq_freq_transition_end(policy, &freqs, 0);
}

/**
 * cpufreq_quick_get - get the CPU frequency (in kHz) from policy->cur
 * @cpu: CPU number
 *
 * This is the last known freq, without actually getting it from the driver.
 * Return value will be same as what is shown in scaling_cur_freq in sysfs.
 */
unsigned int cpufreq_quick_get(unsigned int cpu)
{
	struct cpufreq_policy *policy;
	unsigned int ret_freq = 0;
	unsigned long flags;

	read_lock_irqsave(&cpufreq_driver_lock, flags);

	if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get) {
		ret_freq = cpufreq_driver->get(cpu);
		read_unlock_irqrestore(&cpufreq_driver_lock, flags);
		return ret_freq;
	}

	read_unlock_irqrestore(&cpufreq_driver_lock, flags);

	policy = cpufreq_cpu_get(cpu);
	if (policy) {
		ret_freq = policy->cur;
		cpufreq_cpu_put(policy);
	}

	return ret_freq;
}
EXPORT_SYMBOL(cpufreq_quick_get);

/**
 * cpufreq_quick_get_max - get the max reported CPU frequency for this CPU
 * @cpu: CPU number
 *
 * Just return the max possible frequency for a given CPU.
 */
unsigned int cpufreq_quick_get_max(unsigned int cpu)
{
	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
	unsigned int ret_freq = 0;

	if (policy) {
		ret_freq = policy->max;
		cpufreq_cpu_put(policy);
	}

	return ret_freq;
}
EXPORT_SYMBOL(cpufreq_quick_get_max);

static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
{
	unsigned int ret_freq = 0;

	if (!cpufreq_driver->get)
		return ret_freq;

	ret_freq = cpufreq_driver->get(policy->cpu);

	/*
	 * Updating inactive policies is invalid, so avoid doing that.  Also
	 * if fast frequency switching is used with the given policy, the check
	 * against policy->cur is pointless, so skip it in that case too.
	 */
	if (unlikely(policy_is_inactive(policy)) || policy->fast_switch_enabled)
		return ret_freq;

	if (ret_freq && policy->cur &&
		!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
		/* verify no discrepancy between actual and
					saved value exists */
		if (unlikely(ret_freq != policy->cur)) {
			cpufreq_out_of_sync(policy, ret_freq);
			schedule_work(&policy->update);
		}
	}

	return ret_freq;
}

/**
 * cpufreq_get - get the current CPU frequency (in kHz)
 * @cpu: CPU number
 *
 * Get the CPU current (static) CPU frequency
 */
unsigned int cpufreq_get(unsigned int cpu)
{
	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
	unsigned int ret_freq = 0;

	if (policy) {
		down_read(&policy->rwsem);

		if (!policy_is_inactive(policy))
			ret_freq = __cpufreq_get(policy);

		up_read(&policy->rwsem);

		cpufreq_cpu_put(policy);
	}

	return ret_freq;
}
EXPORT_SYMBOL(cpufreq_get);

static unsigned int cpufreq_update_current_freq(struct cpufreq_policy *policy)
{
	unsigned int new_freq;

	new_freq = cpufreq_driver->get(policy->cpu);
	if (!new_freq)
		return 0;

	if (!policy->cur) {
		pr_debug("cpufreq: Driver did not initialize current freq\n");
		policy->cur = new_freq;
	} else if (policy->cur != new_freq && has_target()) {
		cpufreq_out_of_sync(policy, new_freq);
	}

	return new_freq;
}

static struct subsys_interface cpufreq_interface = {
	.name		= "cpufreq",
	.subsys		= &cpu_subsys,
	.add_dev	= cpufreq_add_dev,
	.remove_dev	= cpufreq_remove_dev,
};

/*
 * In case platform wants some specific frequency to be configured
 * during suspend..
 */
int cpufreq_generic_suspend(struct cpufreq_policy *policy)
{
	int ret;

	if (!policy->suspend_freq) {
		pr_debug("%s: suspend_freq not defined\n", __func__);
		return 0;
	}

	pr_debug("%s: Setting suspend-freq: %u\n", __func__,
			policy->suspend_freq);

	ret = __cpufreq_driver_target(policy, policy->suspend_freq,
			CPUFREQ_RELATION_H);
	if (ret)
		pr_err("%s: unable to set suspend-freq: %u. err: %d\n",
				__func__, policy->suspend_freq, ret);

	return ret;
}
EXPORT_SYMBOL(cpufreq_generic_suspend);

/**
 * cpufreq_suspend() - Suspend CPUFreq governors
 *
 * Called during system wide Suspend/Hibernate cycles for suspending governors
 * as some platforms can't change frequency after this point in suspend cycle.
 * Because some of the devices (like: i2c, regulators, etc) they use for
 * changing frequency are suspended quickly after this point.
 */
void cpufreq_suspend(void)
{
	struct cpufreq_policy *policy;

	if (!cpufreq_driver)
		return;

	if (!has_target() && !cpufreq_driver->suspend)
		goto suspend;

	pr_debug("%s: Suspending Governors\n", __func__);

	for_each_active_policy(policy) {
		if (has_target()) {
			down_write(&policy->rwsem);
			cpufreq_stop_governor(policy);
			up_write(&policy->rwsem);
		}

		if (cpufreq_driver->suspend && cpufreq_driver->suspend(policy))
			pr_err("%s: Failed to suspend driver: %p\n", __func__,
				policy);
	}

suspend:
	cpufreq_suspended = true;
}

/**
 * cpufreq_resume() - Resume CPUFreq governors
 *
 * Called during system wide Suspend/Hibernate cycle for resuming governors that
 * are suspended with cpufreq_suspend().
 */
void cpufreq_resume(void)
{
	struct cpufreq_policy *policy;
	int ret;

	if (!cpufreq_driver)
		return;

	cpufreq_suspended = false;

	if (!has_target() && !cpufreq_driver->resume)
		return;

	pr_debug("%s: Resuming Governors\n", __func__);

	for_each_active_policy(policy) {
		if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) {
			pr_err("%s: Failed to resume driver: %p\n", __func__,
				policy);
		} else if (has_target()) {
			down_write(&policy->rwsem);
			ret = cpufreq_start_governor(policy);
			up_write(&policy->rwsem);

			if (ret)
				pr_err("%s: Failed to start governor for policy: %p\n",
				       __func__, policy);
		}
	}
}

/**
 *	cpufreq_get_current_driver - return current driver's name
 *
 *	Return the name string of the currently loaded cpufreq driver
 *	or NULL, if none.
 */
const char *cpufreq_get_current_driver(void)
{
	if (cpufreq_driver)
		return cpufreq_driver->name;

	return NULL;
}
EXPORT_SYMBOL_GPL(cpufreq_get_current_driver);

/**
 *	cpufreq_get_driver_data - return current driver data
 *
 *	Return the private data of the currently loaded cpufreq
 *	driver, or NULL if no cpufreq driver is loaded.
 */
void *cpufreq_get_driver_data(void)
{
	if (cpufreq_driver)
		return cpufreq_driver->driver_data;

	return NULL;
}
EXPORT_SYMBOL_GPL(cpufreq_get_driver_data);

/*********************************************************************
 *                     NOTIFIER LISTS INTERFACE                      *
 *********************************************************************/

/**
 *	cpufreq_register_notifier - register a driver with cpufreq
 *	@nb: notifier function to register
 *      @list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER
 *
 *	Add a driver to one of two lists: either a list of drivers that
 *      are notified about clock rate changes (once before and once after
 *      the transition), or a list of drivers that are notified about
 *      changes in cpufreq policy.
 *
 *	This function may sleep, and has the same return conditions as
 *	blocking_notifier_chain_register.
 */
int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
{
	int ret;

	if (cpufreq_disabled())
		return -EINVAL;

	WARN_ON(!init_cpufreq_transition_notifier_list_called);

	switch (list) {
	case CPUFREQ_TRANSITION_NOTIFIER:
		mutex_lock(&cpufreq_fast_switch_lock);

		if (cpufreq_fast_switch_count > 0) {
			mutex_unlock(&cpufreq_fast_switch_lock);
			return -EBUSY;
		}
		ret = srcu_notifier_chain_register(
				&cpufreq_transition_notifier_list, nb);
		if (!ret)
			cpufreq_fast_switch_count--;

		mutex_unlock(&cpufreq_fast_switch_lock);
		break;
	case CPUFREQ_POLICY_NOTIFIER:
		ret = blocking_notifier_chain_register(
				&cpufreq_policy_notifier_list, nb);
		break;
	default:
		ret = -EINVAL;
	}

	return ret;
}
EXPORT_SYMBOL(cpufreq_register_notifier);

/**
 *	cpufreq_unregister_notifier - unregister a driver with cpufreq
 *	@nb: notifier block to be unregistered
 *	@list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER
 *
 *	Remove a driver from the CPU frequency notifier list.
 *
 *	This function may sleep, and has the same return conditions as
 *	blocking_notifier_chain_unregister.
 */
int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list)
{
	int ret;

	if (cpufreq_disabled())
		return -EINVAL;

	switch (list) {
	case CPUFREQ_TRANSITION_NOTIFIER:
		mutex_lock(&cpufreq_fast_switch_lock);

		ret = srcu_notifier_chain_unregister(
				&cpufreq_transition_notifier_list, nb);
		if (!ret && !WARN_ON(cpufreq_fast_switch_count >= 0))
			cpufreq_fast_switch_count++;

		mutex_unlock(&cpufreq_fast_switch_lock);
		break;
	case CPUFREQ_POLICY_NOTIFIER:
		ret = blocking_notifier_chain_unregister(
				&cpufreq_policy_notifier_list, nb);
		break;
	default:
		ret = -EINVAL;
	}

	return ret;
}
EXPORT_SYMBOL(cpufreq_unregister_notifier);


/*********************************************************************
 *                              GOVERNORS                            *
 *********************************************************************/

/**
 * cpufreq_driver_fast_switch - Carry out a fast CPU frequency switch.
 * @policy: cpufreq policy to switch the frequency for.
 * @target_freq: New frequency to set (may be approximate).
 *
 * Carry out a fast frequency switch without sleeping.
 *
 * The driver's ->fast_switch() callback invoked by this function must be
 * suitable for being called from within RCU-sched read-side critical sections
 * and it is expected to select the minimum available frequency greater than or
 * equal to @target_freq (CPUFREQ_RELATION_L).
 *
 * This function must not be called if policy->fast_switch_enabled is unset.
 *
 * Governors calling this function must guarantee that it will never be invoked
 * twice in parallel for the same policy and that it will never be called in
 * parallel with either ->target() or ->target_index() for the same policy.
 *
 * If CPUFREQ_ENTRY_INVALID is returned by the driver's ->fast_switch()
 * callback to indicate an error condition, the hardware configuration must be
 * preserved.
 */
unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
					unsigned int target_freq)
{
	target_freq = clamp_val(target_freq, policy->min, policy->max);

	return cpufreq_driver->fast_switch(policy, target_freq);
}
EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);

/* Must set freqs->new to intermediate frequency */
static int __target_intermediate(struct cpufreq_policy *policy,
				 struct cpufreq_freqs *freqs, int index)
{
	int ret;

	freqs->new = cpufreq_driver->get_intermediate(policy, index);

	/* We don't need to switch to intermediate freq */
	if (!freqs->new)
		return 0;

	pr_debug("%s: cpu: %d, switching to intermediate freq: oldfreq: %u, intermediate freq: %u\n",
		 __func__, policy->cpu, freqs->old, freqs->new);

	cpufreq_freq_transition_begin(policy, freqs);
	ret = cpufreq_driver->target_intermediate(policy, index);
	cpufreq_freq_transition_end(policy, freqs, ret);

	if (ret)
		pr_err("%s: Failed to change to intermediate frequency: %d\n",
		       __func__, ret);

	return ret;
}

static int __target_index(struct cpufreq_policy *policy, int index)
{
	struct cpufreq_freqs freqs = {.old = policy->cur, .flags = 0};
	unsigned int intermediate_freq = 0;
	unsigned int newfreq = policy->freq_table[index].frequency;
	int retval = -EINVAL;
	bool notify;

	if (newfreq == policy->cur)
		return 0;

	notify = !(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION);
	if (notify) {
		/* Handle switching to intermediate frequency */
		if (cpufreq_driver->get_intermediate) {
			retval = __target_intermediate(policy, &freqs, index);
			if (retval)
				return retval;

			intermediate_freq = freqs.new;
			/* Set old freq to intermediate */
			if (intermediate_freq)
				freqs.old = freqs.new;
		}

		freqs.new = newfreq;
		pr_debug("%s: cpu: %d, oldfreq: %u, new freq: %u\n",
			 __func__, policy->cpu, freqs.old, freqs.new);

		cpufreq_freq_transition_begin(policy, &freqs);
	}

	retval = cpufreq_driver->target_index(policy, index);
	if (retval)
		pr_err("%s: Failed to change cpu frequency: %d\n", __func__,
		       retval);

	if (notify) {
		cpufreq_freq_transition_end(policy, &freqs, retval);

		/*
		 * Failed after setting to intermediate freq? Driver should have
		 * reverted back to initial frequency and so should we. Check
		 * here for intermediate_freq instead of get_intermediate, in
		 * case we haven't switched to intermediate freq at all.
		 */
		if (unlikely(retval && intermediate_freq)) {
			freqs.old = intermediate_freq;
			freqs.new = policy->restore_freq;
			cpufreq_freq_transition_begin(policy, &freqs);
			cpufreq_freq_transition_end(policy, &freqs, 0);
		}
	}

	return retval;
}

int __cpufreq_driver_target(struct cpufreq_policy *policy,
			    unsigned int target_freq,
			    unsigned int relation)
{
	unsigned int old_target_freq = target_freq;
	int index;

	if (cpufreq_disabled())
		return -ENODEV;

	/* Make sure that target_freq is within supported range */
	target_freq = clamp_val(target_freq, policy->min, policy->max);

	pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
		 policy->cpu, target_freq, relation, old_target_freq);

	/*
	 * This might look like a redundant call as we are checking it again
	 * after finding index. But it is left intentionally for cases where
	 * exactly same freq is called again and so we can save on few function
	 * calls.
	 */
	if (target_freq == policy->cur)
		return 0;

	/* Save last value to restore later on errors */
	policy->restore_freq = policy->cur;

	if (cpufreq_driver->target)
		return cpufreq_driver->target(policy, target_freq, relation);

	if (!cpufreq_driver->target_index)
		return -EINVAL;

	index = cpufreq_frequency_table_target(policy, target_freq, relation);

	return __target_index(policy, index);
}
EXPORT_SYMBOL_GPL(__cpufreq_driver_target);

int cpufreq_driver_target(struct cpufreq_policy *policy,
			  unsigned int target_freq,
			  unsigned int relation)
{
	int ret = -EINVAL;

	down_write(&policy->rwsem);

	ret = __cpufreq_driver_target(policy, target_freq, relation);

	up_write(&policy->rwsem);

	return ret;
}
EXPORT_SYMBOL_GPL(cpufreq_driver_target);

__weak struct cpufreq_governor *cpufreq_fallback_governor(void)
{
	return NULL;
}

static int cpufreq_init_governor(struct cpufreq_policy *policy)
{
	int ret;

	/* Don't start any governor operations if we are entering suspend */
	if (cpufreq_suspended)
		return 0;
	/*
	 * Governor might not be initiated here if ACPI _PPC changed
	 * notification happened, so check it.
	 */
	if (!policy->governor)
		return -EINVAL;

	if (policy->governor->max_transition_latency &&
	    policy->cpuinfo.transition_latency >
	    policy->governor->max_transition_latency) {
		struct cpufreq_governor *gov = cpufreq_fallback_governor();

		if (gov) {
			pr_warn("%s governor failed, too long transition latency of HW, fallback to %s governor\n",
				policy->governor->name, gov->name);
			policy->governor = gov;
		} else {
			return -EINVAL;
		}
	}

	if (!try_module_get(policy->governor->owner))
		return -EINVAL;

	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);

	if (policy->governor->init) {
		ret = policy->governor->init(policy);
		if (ret) {
			module_put(policy->governor->owner);
			return ret;
		}
	}

	return 0;
}

static void cpufreq_exit_governor(struct cpufreq_policy *policy)
{
	if (cpufreq_suspended || !policy->governor)
		return;

	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);

	if (policy->governor->exit)
		policy->governor->exit(policy);

	module_put(policy->governor->owner);
}

static int cpufreq_start_governor(struct cpufreq_policy *policy)
{
	int ret;

	if (cpufreq_suspended)
		return 0;

	if (!policy->governor)
		return -EINVAL;

	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);

	if (cpufreq_driver->get && !cpufreq_driver->setpolicy)
		cpufreq_update_current_freq(policy);

	if (policy->governor->start) {
		ret = policy->governor->start(policy);
		if (ret)
			return ret;
	}

	if (policy->governor->limits)
		policy->governor->limits(policy);

	return 0;
}

static void cpufreq_stop_governor(struct cpufreq_policy *policy)
{
	if (cpufreq_suspended || !policy->governor)
		return;

	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);

	if (policy->governor->stop)
		policy->governor->stop(policy);
}

static void cpufreq_governor_limits(struct cpufreq_policy *policy)
{
	if (cpufreq_suspended || !policy->governor)
		return;

	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);

	if (policy->governor->limits)
		policy->governor->limits(policy);
}

int cpufreq_register_governor(struct cpufreq_governor *governor)
{
	int err;

	if (!governor)
		return -EINVAL;

	if (cpufreq_disabled())
		return -ENODEV;

	mutex_lock(&cpufreq_governor_mutex);

	err = -EBUSY;
	if (!find_governor(governor->name)) {
		err = 0;
		list_add(&governor->governor_list, &cpufreq_governor_list);
	}

	mutex_unlock(&cpufreq_governor_mutex);
	return err;
}
EXPORT_SYMBOL_GPL(cpufreq_register_governor);

void cpufreq_unregister_governor(struct cpufreq_governor *governor)
{
	struct cpufreq_policy *policy;
	unsigned long flags;

	if (!governor)
		return;

	if (cpufreq_disabled())
		return;

	/* clear last_governor for all inactive policies */
	read_lock_irqsave(&cpufreq_driver_lock, flags);
	for_each_inactive_policy(policy) {
		if (!strcmp(policy->last_governor, governor->name)) {
			policy->governor = NULL;
			strcpy(policy->last_governor, "\0");
		}
	}
	read_unlock_irqrestore(&cpufreq_driver_lock, flags);

	mutex_lock(&cpufreq_governor_mutex);
	list_del(&governor->governor_list);
	mutex_unlock(&cpufreq_governor_mutex);
	return;
}
EXPORT_SYMBOL_GPL(cpufreq_unregister_governor);


/*********************************************************************
 *                          POLICY INTERFACE                         *
 *********************************************************************/

/**
 * cpufreq_get_policy - get the current cpufreq_policy
 * @policy: struct cpufreq_policy into which the current cpufreq_policy
 *	is written
 *
 * Reads the current cpufreq policy.
 */
int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu)
{
	struct cpufreq_policy *cpu_policy;
	if (!policy)
		return -EINVAL;

	cpu_policy = cpufreq_cpu_get(cpu);
	if (!cpu_policy)
		return -EINVAL;

	memcpy(policy, cpu_policy, sizeof(*policy));

	cpufreq_cpu_put(cpu_policy);
	return 0;
}
EXPORT_SYMBOL(cpufreq_get_policy);

/*
 * policy : current policy.
 * new_policy: policy to be set.
 */
static int cpufreq_set_policy(struct cpufreq_policy *policy,
				struct cpufreq_policy *new_policy)
{
	struct cpufreq_governor *old_gov;
	int ret;

	pr_debug("setting new policy for CPU %u: %u - %u kHz\n",
		 new_policy->cpu, new_policy->min, new_policy->max);

	memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo));

	/*
	* This check works well when we store new min/max freq attributes,
	* because new_policy is a copy of policy with one field updated.
	*/
	if (new_policy->min > new_policy->max)
		return -EINVAL;

	/* verify the cpu speed can be set within this limit */
	ret = cpufreq_driver->verify(new_policy);
	if (ret)
		return ret;

	/* adjust if necessary - all reasons */
	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
			CPUFREQ_ADJUST, new_policy);

	/*
	 * verify the cpu speed can be set within this limit, which might be
	 * different to the first one
	 */
	ret = cpufreq_driver->verify(new_policy);
	if (ret)
		return ret;

	/* notification of the new policy */
	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
			CPUFREQ_NOTIFY, new_policy);

	policy->min = new_policy->min;
	policy->max = new_policy->max;

	policy->cached_target_freq = UINT_MAX;

	pr_debug("new min and max freqs are %u - %u kHz\n",
		 policy->min, policy->max);

	if (cpufreq_driver->setpolicy) {
		policy->policy = new_policy->policy;
		pr_debug("setting range\n");
		return cpufreq_driver->setpolicy(new_policy);
	}

	if (new_policy->governor == policy->governor) {
		pr_debug("cpufreq: governor limits update\n");
		cpufreq_governor_limits(policy);
		return 0;
	}

	pr_debug("governor switch\n");

	/* save old, working values */
	old_gov = policy->governor;
	/* end old governor */
	if (old_gov) {
		cpufreq_stop_governor(policy);
		cpufreq_exit_governor(policy);
	}

	/* start new governor */
	policy->governor = new_policy->governor;
	ret = cpufreq_init_governor(policy);
	if (!ret) {
		ret = cpufreq_start_governor(policy);
		if (!ret) {
			pr_debug("cpufreq: governor change\n");
			return 0;
		}
		cpufreq_exit_governor(policy);
	}

	/* new governor failed, so re-start old one */
	pr_debug("starting governor %s failed\n", policy->governor->name);
	if (old_gov) {
		policy->governor = old_gov;
		if (cpufreq_init_governor(policy))
			policy->governor = NULL;
		else
			cpufreq_start_governor(policy);
	}

	return ret;
}

/**
 *	cpufreq_update_policy - re-evaluate an existing cpufreq policy
 *	@cpu: CPU which shall be re-evaluated
 *
 *	Useful for policy notifiers which have different necessities
 *	at different times.
 */
void cpufreq_update_policy(unsigned int cpu)
{
	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
	struct cpufreq_policy new_policy;

	if (!policy)
		return;

	down_write(&policy->rwsem);

	if (policy_is_inactive(policy))
		goto unlock;

	pr_debug("updating policy for CPU %u\n", cpu);
	memcpy(&new_policy, policy, sizeof(*policy));
	new_policy.min = policy->user_policy.min;
	new_policy.max = policy->user_policy.max;

	/*
	 * BIOS might change freq behind our back
	 * -> ask driver for current freq and notify governors about a change
	 */
	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
		if (cpufreq_suspended)
			goto unlock;

		new_policy.cur = cpufreq_update_current_freq(policy);
		if (WARN_ON(!new_policy.cur))
			goto unlock;
	}

	cpufreq_set_policy(policy, &new_policy);

unlock:
	up_write(&policy->rwsem);

	cpufreq_cpu_put(policy);
}
EXPORT_SYMBOL(cpufreq_update_policy);

/*********************************************************************
 *               BOOST						     *
 *********************************************************************/
static int cpufreq_boost_set_sw(int state)
{
	struct cpufreq_policy *policy;
	int ret = -EINVAL;

	for_each_active_policy(policy) {
		if (!policy->freq_table)
			continue;

		ret = cpufreq_frequency_table_cpuinfo(policy,
						      policy->freq_table);
		if (ret) {
			pr_err("%s: Policy frequency update failed\n",
			       __func__);
			break;
		}

		down_write(&policy->rwsem);
		policy->user_policy.max = policy->max;
		cpufreq_governor_limits(policy);
		up_write(&policy->rwsem);
	}

	return ret;
}

int cpufreq_boost_trigger_state(int state)
{
	unsigned long flags;
	int ret = 0;

	if (cpufreq_driver->boost_enabled == state)
		return 0;

	write_lock_irqsave(&cpufreq_driver_lock, flags);
	cpufreq_driver->boost_enabled = state;
	write_unlock_irqrestore(&cpufreq_driver_lock, flags);

	ret = cpufreq_driver->set_boost(state);
	if (ret) {
		write_lock_irqsave(&cpufreq_driver_lock, flags);
		cpufreq_driver->boost_enabled = !state;
		write_unlock_irqrestore(&cpufreq_driver_lock, flags);

		pr_err("%s: Cannot %s BOOST\n",
		       __func__, state ? "enable" : "disable");
	}

	return ret;
}

static bool cpufreq_boost_supported(void)
{
	return likely(cpufreq_driver) && cpufreq_driver->set_boost;
}

static int create_boost_sysfs_file(void)
{
	int ret;

	ret = sysfs_create_file(cpufreq_global_kobject, &boost.attr);
	if (ret)
		pr_err("%s: cannot register global BOOST sysfs file\n",
		       __func__);

	return ret;
}

static void remove_boost_sysfs_file(void)
{
	if (cpufreq_boost_supported())
		sysfs_remove_file(cpufreq_global_kobject, &boost.attr);
}

int cpufreq_enable_boost_support(void)
{
	if (!cpufreq_driver)
		return -EINVAL;

	if (cpufreq_boost_supported())
		return 0;

	cpufreq_driver->set_boost = cpufreq_boost_set_sw;

	/* This will get removed on driver unregister */
	return create_boost_sysfs_file();
}
EXPORT_SYMBOL_GPL(cpufreq_enable_boost_support);

int cpufreq_boost_enabled(void)
{
	return cpufreq_driver->boost_enabled;
}
EXPORT_SYMBOL_GPL(cpufreq_boost_enabled);

/*********************************************************************
 *               REGISTER / UNREGISTER CPUFREQ DRIVER                *
 *********************************************************************/
static enum cpuhp_state hp_online;

static int cpuhp_cpufreq_online(unsigned int cpu)
{
	cpufreq_online(cpu);

	return 0;
}

static int cpuhp_cpufreq_offline(unsigned int cpu)
{
	cpufreq_offline(cpu);

	return 0;
}

/**
 * cpufreq_register_driver - register a CPU Frequency driver
 * @driver_data: A struct cpufreq_driver containing the values#
 * submitted by the CPU Frequency driver.
 *
 * Registers a CPU Frequency driver to this core code. This code
 * returns zero on success, -EEXIST when another driver got here first
 * (and isn't unregistered in the meantime).
 *
 */
int cpufreq_register_driver(struct cpufreq_driver *driver_data)
{
	unsigned long flags;
	int ret;

	if (cpufreq_disabled())
		return -ENODEV;

	if (!driver_data || !driver_data->verify || !driver_data->init ||
	    !(driver_data->setpolicy || driver_data->target_index ||
		    driver_data->target) ||
	     (driver_data->setpolicy && (driver_data->target_index ||
		    driver_data->target)) ||
	     (!!driver_data->get_intermediate != !!driver_data->target_intermediate))
		return -EINVAL;

	pr_debug("trying to register driver %s\n", driver_data->name);

	/* Protect against concurrent CPU online/offline. */
	cpus_read_lock();

	write_lock_irqsave(&cpufreq_driver_lock, flags);
	if (cpufreq_driver) {
		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
		ret = -EEXIST;
		goto out;
	}
	cpufreq_driver = driver_data;
	write_unlock_irqrestore(&cpufreq_driver_lock, flags);

	if (driver_data->setpolicy)
		driver_data->flags |= CPUFREQ_CONST_LOOPS;

	if (cpufreq_boost_supported()) {
		ret = create_boost_sysfs_file();
		if (ret)
			goto err_null_driver;
	}

	ret = subsys_interface_register(&cpufreq_interface);
	if (ret)
		goto err_boost_unreg;

	if (!(cpufreq_driver->flags & CPUFREQ_STICKY) &&
	    list_empty(&cpufreq_policy_list)) {
		/* if all ->init() calls failed, unregister */
		ret = -ENODEV;
		pr_debug("%s: No CPU initialized for driver %s\n", __func__,
			 driver_data->name);
		goto err_if_unreg;
	}

	ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN,
						   "cpufreq:online",
						   cpuhp_cpufreq_online,
						   cpuhp_cpufreq_offline);
	if (ret < 0)
		goto err_if_unreg;
	hp_online = ret;
	ret = 0;

	pr_debug("driver %s up and running\n", driver_data->name);
	goto out;

err_if_unreg:
	subsys_interface_unregister(&cpufreq_interface);
err_boost_unreg:
	remove_boost_sysfs_file();
err_null_driver:
	write_lock_irqsave(&cpufreq_driver_lock, flags);
	cpufreq_driver = NULL;
	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
out:
	cpus_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(cpufreq_register_driver);

/**
 * cpufreq_unregister_driver - unregister the current CPUFreq driver
 *
 * Unregister the current CPUFreq driver. Only call this if you have
 * the right to do so, i.e. if you have succeeded in initialising before!
 * Returns zero if successful, and -EINVAL if the cpufreq_driver is
 * currently not initialised.
 */
int cpufreq_unregister_driver(struct cpufreq_driver *driver)
{
	unsigned long flags;

	if (!cpufreq_driver || (driver != cpufreq_driver))
		return -EINVAL;

	pr_debug("unregistering driver %s\n", driver->name);

	/* Protect against concurrent cpu hotplug */
	cpus_read_lock();
	subsys_interface_unregister(&cpufreq_interface);
	remove_boost_sysfs_file();
	cpuhp_remove_state_nocalls_cpuslocked(hp_online);

	write_lock_irqsave(&cpufreq_driver_lock, flags);

	cpufreq_driver = NULL;

	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
	cpus_read_unlock();

	return 0;
}
EXPORT_SYMBOL_GPL(cpufreq_unregister_driver);

/*
 * Stop cpufreq at shutdown to make sure it isn't holding any locks
 * or mutexes when secondary CPUs are halted.
 */
static struct syscore_ops cpufreq_syscore_ops = {
	.shutdown = cpufreq_suspend,
};

struct kobject *cpufreq_global_kobject;
EXPORT_SYMBOL(cpufreq_global_kobject);

static int __init cpufreq_core_init(void)
{
	if (cpufreq_disabled())
		return -ENODEV;

	cpufreq_global_kobject = kobject_create_and_add("cpufreq", &cpu_subsys.dev_root->kobj);
	BUG_ON(!cpufreq_global_kobject);

	register_syscore_ops(&cpufreq_syscore_ops);

	return 0;
}
module_param(off, int, 0444);
core_initcall(cpufreq_core_init);