summaryrefslogtreecommitdiff
path: root/drivers/cpufreq/intel_pstate.c
blob: f8e514d7fbc44a97bfe43b6456777b104682f53a (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
/*
 * intel_pstate.c: Native P state management for Intel processors
 *
 * (C) Copyright 2012 Intel Corporation
 * Author: Dirk Brandewie <dirk.j.brandewie@intel.com>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; version 2
 * of the License.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/kernel_stat.h>
#include <linux/module.h>
#include <linux/ktime.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/list.h>
#include <linux/cpu.h>
#include <linux/cpufreq.h>
#include <linux/sysfs.h>
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/debugfs.h>
#include <linux/acpi.h>
#include <linux/vmalloc.h>
#include <trace/events/power.h>

#include <asm/div64.h>
#include <asm/msr.h>
#include <asm/cpu_device_id.h>
#include <asm/cpufeature.h>
#include <asm/intel-family.h>

#define INTEL_CPUFREQ_TRANSITION_LATENCY	20000

#define ATOM_RATIOS		0x66a
#define ATOM_VIDS		0x66b
#define ATOM_TURBO_RATIOS	0x66c
#define ATOM_TURBO_VIDS		0x66d

#ifdef CONFIG_ACPI
#include <acpi/processor.h>
#endif

#define FRAC_BITS 8
#define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
#define fp_toint(X) ((X) >> FRAC_BITS)

#define EXT_BITS 6
#define EXT_FRAC_BITS (EXT_BITS + FRAC_BITS)
#define fp_ext_toint(X) ((X) >> EXT_FRAC_BITS)
#define int_ext_tofp(X) ((int64_t)(X) << EXT_FRAC_BITS)

static inline int32_t mul_fp(int32_t x, int32_t y)
{
	return ((int64_t)x * (int64_t)y) >> FRAC_BITS;
}

static inline int32_t div_fp(s64 x, s64 y)
{
	return div64_s64((int64_t)x << FRAC_BITS, y);
}

static inline int ceiling_fp(int32_t x)
{
	int mask, ret;

	ret = fp_toint(x);
	mask = (1 << FRAC_BITS) - 1;
	if (x & mask)
		ret += 1;
	return ret;
}

static inline u64 mul_ext_fp(u64 x, u64 y)
{
	return (x * y) >> EXT_FRAC_BITS;
}

static inline u64 div_ext_fp(u64 x, u64 y)
{
	return div64_u64(x << EXT_FRAC_BITS, y);
}

/**
 * struct sample -	Store performance sample
 * @core_avg_perf:	Ratio of APERF/MPERF which is the actual average
 *			performance during last sample period
 * @busy_scaled:	Scaled busy value which is used to calculate next
 *			P state. This can be different than core_avg_perf
 *			to account for cpu idle period
 * @aperf:		Difference of actual performance frequency clock count
 *			read from APERF MSR between last and current sample
 * @mperf:		Difference of maximum performance frequency clock count
 *			read from MPERF MSR between last and current sample
 * @tsc:		Difference of time stamp counter between last and
 *			current sample
 * @time:		Current time from scheduler
 *
 * This structure is used in the cpudata structure to store performance sample
 * data for choosing next P State.
 */
struct sample {
	int32_t core_avg_perf;
	int32_t busy_scaled;
	u64 aperf;
	u64 mperf;
	u64 tsc;
	u64 time;
};

/**
 * struct pstate_data - Store P state data
 * @current_pstate:	Current requested P state
 * @min_pstate:		Min P state possible for this platform
 * @max_pstate:		Max P state possible for this platform
 * @max_pstate_physical:This is physical Max P state for a processor
 *			This can be higher than the max_pstate which can
 *			be limited by platform thermal design power limits
 * @scaling:		Scaling factor to  convert frequency to cpufreq
 *			frequency units
 * @turbo_pstate:	Max Turbo P state possible for this platform
 * @max_freq:		@max_pstate frequency in cpufreq units
 * @turbo_freq:		@turbo_pstate frequency in cpufreq units
 *
 * Stores the per cpu model P state limits and current P state.
 */
struct pstate_data {
	int	current_pstate;
	int	min_pstate;
	int	max_pstate;
	int	max_pstate_physical;
	int	scaling;
	int	turbo_pstate;
	unsigned int max_freq;
	unsigned int turbo_freq;
};

/**
 * struct vid_data -	Stores voltage information data
 * @min:		VID data for this platform corresponding to
 *			the lowest P state
 * @max:		VID data corresponding to the highest P State.
 * @turbo:		VID data for turbo P state
 * @ratio:		Ratio of (vid max - vid min) /
 *			(max P state - Min P State)
 *
 * Stores the voltage data for DVFS (Dynamic Voltage and Frequency Scaling)
 * This data is used in Atom platforms, where in addition to target P state,
 * the voltage data needs to be specified to select next P State.
 */
struct vid_data {
	int min;
	int max;
	int turbo;
	int32_t ratio;
};

/**
 * struct _pid -	Stores PID data
 * @setpoint:		Target set point for busyness or performance
 * @integral:		Storage for accumulated error values
 * @p_gain:		PID proportional gain
 * @i_gain:		PID integral gain
 * @d_gain:		PID derivative gain
 * @deadband:		PID deadband
 * @last_err:		Last error storage for integral part of PID calculation
 *
 * Stores PID coefficients and last error for PID controller.
 */
struct _pid {
	int setpoint;
	int32_t integral;
	int32_t p_gain;
	int32_t i_gain;
	int32_t d_gain;
	int deadband;
	int32_t last_err;
};

/**
 * struct perf_limits - Store user and policy limits
 * @no_turbo:		User requested turbo state from intel_pstate sysfs
 * @turbo_disabled:	Platform turbo status either from msr
 *			MSR_IA32_MISC_ENABLE or when maximum available pstate
 *			matches the maximum turbo pstate
 * @max_perf_pct:	Effective maximum performance limit in percentage, this
 *			is minimum of either limits enforced by cpufreq policy
 *			or limits from user set limits via intel_pstate sysfs
 * @min_perf_pct:	Effective minimum performance limit in percentage, this
 *			is maximum of either limits enforced by cpufreq policy
 *			or limits from user set limits via intel_pstate sysfs
 * @max_perf:		This is a scaled value between 0 to 255 for max_perf_pct
 *			This value is used to limit max pstate
 * @min_perf:		This is a scaled value between 0 to 255 for min_perf_pct
 *			This value is used to limit min pstate
 * @max_policy_pct:	The maximum performance in percentage enforced by
 *			cpufreq setpolicy interface
 * @max_sysfs_pct:	The maximum performance in percentage enforced by
 *			intel pstate sysfs interface, unused when per cpu
 *			controls are enforced
 * @min_policy_pct:	The minimum performance in percentage enforced by
 *			cpufreq setpolicy interface
 * @min_sysfs_pct:	The minimum performance in percentage enforced by
 *			intel pstate sysfs interface, unused when per cpu
 *			controls are enforced
 *
 * Storage for user and policy defined limits.
 */
struct perf_limits {
	int no_turbo;
	int turbo_disabled;
	int max_perf_pct;
	int min_perf_pct;
	int32_t max_perf;
	int32_t min_perf;
	int max_policy_pct;
	int max_sysfs_pct;
	int min_policy_pct;
	int min_sysfs_pct;
};

/**
 * struct cpudata -	Per CPU instance data storage
 * @cpu:		CPU number for this instance data
 * @policy:		CPUFreq policy value
 * @update_util:	CPUFreq utility callback information
 * @update_util_set:	CPUFreq utility callback is set
 * @iowait_boost:	iowait-related boost fraction
 * @last_update:	Time of the last update.
 * @pstate:		Stores P state limits for this CPU
 * @vid:		Stores VID limits for this CPU
 * @pid:		Stores PID parameters for this CPU
 * @last_sample_time:	Last Sample time
 * @prev_aperf:		Last APERF value read from APERF MSR
 * @prev_mperf:		Last MPERF value read from MPERF MSR
 * @prev_tsc:		Last timestamp counter (TSC) value
 * @prev_cummulative_iowait: IO Wait time difference from last and
 *			current sample
 * @sample:		Storage for storing last Sample data
 * @perf_limits:	Pointer to perf_limit unique to this CPU
 *			Not all field in the structure are applicable
 *			when per cpu controls are enforced
 * @acpi_perf_data:	Stores ACPI perf information read from _PSS
 * @valid_pss_table:	Set to true for valid ACPI _PSS entries found
 * @epp_powersave:	Last saved HWP energy performance preference
 *			(EPP) or energy performance bias (EPB),
 *			when policy switched to performance
 * @epp_policy:		Last saved policy used to set EPP/EPB
 * @epp_default:	Power on default HWP energy performance
 *			preference/bias
 * @epp_saved:		Saved EPP/EPB during system suspend or CPU offline
 *			operation
 *
 * This structure stores per CPU instance data for all CPUs.
 */
struct cpudata {
	int cpu;

	unsigned int policy;
	struct update_util_data update_util;
	bool   update_util_set;

	struct pstate_data pstate;
	struct vid_data vid;
	struct _pid pid;

	u64	last_update;
	u64	last_sample_time;
	u64	prev_aperf;
	u64	prev_mperf;
	u64	prev_tsc;
	u64	prev_cummulative_iowait;
	struct sample sample;
	struct perf_limits *perf_limits;
#ifdef CONFIG_ACPI
	struct acpi_processor_performance acpi_perf_data;
	bool valid_pss_table;
#endif
	unsigned int iowait_boost;
	s16 epp_powersave;
	s16 epp_policy;
	s16 epp_default;
	s16 epp_saved;
};

static struct cpudata **all_cpu_data;

/**
 * struct pstate_adjust_policy - Stores static PID configuration data
 * @sample_rate_ms:	PID calculation sample rate in ms
 * @sample_rate_ns:	Sample rate calculation in ns
 * @deadband:		PID deadband
 * @setpoint:		PID Setpoint
 * @p_gain_pct:		PID proportional gain
 * @i_gain_pct:		PID integral gain
 * @d_gain_pct:		PID derivative gain
 *
 * Stores per CPU model static PID configuration data.
 */
struct pstate_adjust_policy {
	int sample_rate_ms;
	s64 sample_rate_ns;
	int deadband;
	int setpoint;
	int p_gain_pct;
	int d_gain_pct;
	int i_gain_pct;
};

/**
 * struct pstate_funcs - Per CPU model specific callbacks
 * @get_max:		Callback to get maximum non turbo effective P state
 * @get_max_physical:	Callback to get maximum non turbo physical P state
 * @get_min:		Callback to get minimum P state
 * @get_turbo:		Callback to get turbo P state
 * @get_scaling:	Callback to get frequency scaling factor
 * @get_val:		Callback to convert P state to actual MSR write value
 * @get_vid:		Callback to get VID data for Atom platforms
 * @get_target_pstate:	Callback to a function to calculate next P state to use
 *
 * Core and Atom CPU models have different way to get P State limits. This
 * structure is used to store those callbacks.
 */
struct pstate_funcs {
	int (*get_max)(void);
	int (*get_max_physical)(void);
	int (*get_min)(void);
	int (*get_turbo)(void);
	int (*get_scaling)(void);
	u64 (*get_val)(struct cpudata*, int pstate);
	void (*get_vid)(struct cpudata *);
	int32_t (*get_target_pstate)(struct cpudata *);
};

/**
 * struct cpu_defaults- Per CPU model default config data
 * @pid_policy:	PID config data
 * @funcs:		Callback function data
 */
struct cpu_defaults {
	struct pstate_adjust_policy pid_policy;
	struct pstate_funcs funcs;
};

static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu);
static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu);

static struct pstate_adjust_policy pid_params __read_mostly;
static struct pstate_funcs pstate_funcs __read_mostly;
static int hwp_active __read_mostly;
static bool per_cpu_limits __read_mostly;

#ifdef CONFIG_ACPI
static bool acpi_ppc;
#endif

static struct perf_limits performance_limits = {
	.no_turbo = 0,
	.turbo_disabled = 0,
	.max_perf_pct = 100,
	.max_perf = int_ext_tofp(1),
	.min_perf_pct = 100,
	.min_perf = int_ext_tofp(1),
	.max_policy_pct = 100,
	.max_sysfs_pct = 100,
	.min_policy_pct = 0,
	.min_sysfs_pct = 0,
};

static struct perf_limits powersave_limits = {
	.no_turbo = 0,
	.turbo_disabled = 0,
	.max_perf_pct = 100,
	.max_perf = int_ext_tofp(1),
	.min_perf_pct = 0,
	.min_perf = 0,
	.max_policy_pct = 100,
	.max_sysfs_pct = 100,
	.min_policy_pct = 0,
	.min_sysfs_pct = 0,
};

#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
static struct perf_limits *limits = &performance_limits;
#else
static struct perf_limits *limits = &powersave_limits;
#endif

static DEFINE_MUTEX(intel_pstate_limits_lock);

#ifdef CONFIG_ACPI

static bool intel_pstate_get_ppc_enable_status(void)
{
	if (acpi_gbl_FADT.preferred_profile == PM_ENTERPRISE_SERVER ||
	    acpi_gbl_FADT.preferred_profile == PM_PERFORMANCE_SERVER)
		return true;

	return acpi_ppc;
}

static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
{
	struct cpudata *cpu;
	int ret;
	int i;

	if (hwp_active)
		return;

	if (!intel_pstate_get_ppc_enable_status())
		return;

	cpu = all_cpu_data[policy->cpu];

	ret = acpi_processor_register_performance(&cpu->acpi_perf_data,
						  policy->cpu);
	if (ret)
		return;

	/*
	 * Check if the control value in _PSS is for PERF_CTL MSR, which should
	 * guarantee that the states returned by it map to the states in our
	 * list directly.
	 */
	if (cpu->acpi_perf_data.control_register.space_id !=
						ACPI_ADR_SPACE_FIXED_HARDWARE)
		goto err;

	/*
	 * If there is only one entry _PSS, simply ignore _PSS and continue as
	 * usual without taking _PSS into account
	 */
	if (cpu->acpi_perf_data.state_count < 2)
		goto err;

	pr_debug("CPU%u - ACPI _PSS perf data\n", policy->cpu);
	for (i = 0; i < cpu->acpi_perf_data.state_count; i++) {
		pr_debug("     %cP%d: %u MHz, %u mW, 0x%x\n",
			 (i == cpu->acpi_perf_data.state ? '*' : ' '), i,
			 (u32) cpu->acpi_perf_data.states[i].core_frequency,
			 (u32) cpu->acpi_perf_data.states[i].power,
			 (u32) cpu->acpi_perf_data.states[i].control);
	}

	/*
	 * The _PSS table doesn't contain whole turbo frequency range.
	 * This just contains +1 MHZ above the max non turbo frequency,
	 * with control value corresponding to max turbo ratio. But
	 * when cpufreq set policy is called, it will call with this
	 * max frequency, which will cause a reduced performance as
	 * this driver uses real max turbo frequency as the max
	 * frequency. So correct this frequency in _PSS table to
	 * correct max turbo frequency based on the turbo state.
	 * Also need to convert to MHz as _PSS freq is in MHz.
	 */
	if (!limits->turbo_disabled)
		cpu->acpi_perf_data.states[0].core_frequency =
					policy->cpuinfo.max_freq / 1000;
	cpu->valid_pss_table = true;
	pr_debug("_PPC limits will be enforced\n");

	return;

 err:
	cpu->valid_pss_table = false;
	acpi_processor_unregister_performance(policy->cpu);
}

static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
{
	struct cpudata *cpu;

	cpu = all_cpu_data[policy->cpu];
	if (!cpu->valid_pss_table)
		return;

	acpi_processor_unregister_performance(policy->cpu);
}

#else
static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
{
}

static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
{
}
#endif

static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
			     int deadband, int integral) {
	pid->setpoint = int_tofp(setpoint);
	pid->deadband  = int_tofp(deadband);
	pid->integral  = int_tofp(integral);
	pid->last_err  = int_tofp(setpoint) - int_tofp(busy);
}

static inline void pid_p_gain_set(struct _pid *pid, int percent)
{
	pid->p_gain = div_fp(percent, 100);
}

static inline void pid_i_gain_set(struct _pid *pid, int percent)
{
	pid->i_gain = div_fp(percent, 100);
}

static inline void pid_d_gain_set(struct _pid *pid, int percent)
{
	pid->d_gain = div_fp(percent, 100);
}

static signed int pid_calc(struct _pid *pid, int32_t busy)
{
	signed int result;
	int32_t pterm, dterm, fp_error;
	int32_t integral_limit;

	fp_error = pid->setpoint - busy;

	if (abs(fp_error) <= pid->deadband)
		return 0;

	pterm = mul_fp(pid->p_gain, fp_error);

	pid->integral += fp_error;

	/*
	 * We limit the integral here so that it will never
	 * get higher than 30.  This prevents it from becoming
	 * too large an input over long periods of time and allows
	 * it to get factored out sooner.
	 *
	 * The value of 30 was chosen through experimentation.
	 */
	integral_limit = int_tofp(30);
	if (pid->integral > integral_limit)
		pid->integral = integral_limit;
	if (pid->integral < -integral_limit)
		pid->integral = -integral_limit;

	dterm = mul_fp(pid->d_gain, fp_error - pid->last_err);
	pid->last_err = fp_error;

	result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm;
	result = result + (1 << (FRAC_BITS-1));
	return (signed int)fp_toint(result);
}

static inline void intel_pstate_busy_pid_reset(struct cpudata *cpu)
{
	pid_p_gain_set(&cpu->pid, pid_params.p_gain_pct);
	pid_d_gain_set(&cpu->pid, pid_params.d_gain_pct);
	pid_i_gain_set(&cpu->pid, pid_params.i_gain_pct);

	pid_reset(&cpu->pid, pid_params.setpoint, 100, pid_params.deadband, 0);
}

static inline void intel_pstate_reset_all_pid(void)
{
	unsigned int cpu;

	for_each_online_cpu(cpu) {
		if (all_cpu_data[cpu])
			intel_pstate_busy_pid_reset(all_cpu_data[cpu]);
	}
}

static inline void update_turbo_state(void)
{
	u64 misc_en;
	struct cpudata *cpu;

	cpu = all_cpu_data[0];
	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
	limits->turbo_disabled =
		(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
		 cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
}

static s16 intel_pstate_get_epb(struct cpudata *cpu_data)
{
	u64 epb;
	int ret;

	if (!static_cpu_has(X86_FEATURE_EPB))
		return -ENXIO;

	ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
	if (ret)
		return (s16)ret;

	return (s16)(epb & 0x0f);
}

static s16 intel_pstate_get_epp(struct cpudata *cpu_data, u64 hwp_req_data)
{
	s16 epp;

	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
		/*
		 * When hwp_req_data is 0, means that caller didn't read
		 * MSR_HWP_REQUEST, so need to read and get EPP.
		 */
		if (!hwp_req_data) {
			epp = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST,
					    &hwp_req_data);
			if (epp)
				return epp;
		}
		epp = (hwp_req_data >> 24) & 0xff;
	} else {
		/* When there is no EPP present, HWP uses EPB settings */
		epp = intel_pstate_get_epb(cpu_data);
	}

	return epp;
}

static int intel_pstate_set_epb(int cpu, s16 pref)
{
	u64 epb;
	int ret;

	if (!static_cpu_has(X86_FEATURE_EPB))
		return -ENXIO;

	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
	if (ret)
		return ret;

	epb = (epb & ~0x0f) | pref;
	wrmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, epb);

	return 0;
}

/*
 * EPP/EPB display strings corresponding to EPP index in the
 * energy_perf_strings[]
 *	index		String
 *-------------------------------------
 *	0		default
 *	1		performance
 *	2		balance_performance
 *	3		balance_power
 *	4		power
 */
static const char * const energy_perf_strings[] = {
	"default",
	"performance",
	"balance_performance",
	"balance_power",
	"power",
	NULL
};

static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data)
{
	s16 epp;
	int index = -EINVAL;

	epp = intel_pstate_get_epp(cpu_data, 0);
	if (epp < 0)
		return epp;

	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
		/*
		 * Range:
		 *	0x00-0x3F	:	Performance
		 *	0x40-0x7F	:	Balance performance
		 *	0x80-0xBF	:	Balance power
		 *	0xC0-0xFF	:	Power
		 * The EPP is a 8 bit value, but our ranges restrict the
		 * value which can be set. Here only using top two bits
		 * effectively.
		 */
		index = (epp >> 6) + 1;
	} else if (static_cpu_has(X86_FEATURE_EPB)) {
		/*
		 * Range:
		 *	0x00-0x03	:	Performance
		 *	0x04-0x07	:	Balance performance
		 *	0x08-0x0B	:	Balance power
		 *	0x0C-0x0F	:	Power
		 * The EPB is a 4 bit value, but our ranges restrict the
		 * value which can be set. Here only using top two bits
		 * effectively.
		 */
		index = (epp >> 2) + 1;
	}

	return index;
}

static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
					      int pref_index)
{
	int epp = -EINVAL;
	int ret;

	if (!pref_index)
		epp = cpu_data->epp_default;

	mutex_lock(&intel_pstate_limits_lock);

	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
		u64 value;

		ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, &value);
		if (ret)
			goto return_pref;

		value &= ~GENMASK_ULL(31, 24);

		/*
		 * If epp is not default, convert from index into
		 * energy_perf_strings to epp value, by shifting 6
		 * bits left to use only top two bits in epp.
		 * The resultant epp need to shifted by 24 bits to
		 * epp position in MSR_HWP_REQUEST.
		 */
		if (epp == -EINVAL)
			epp = (pref_index - 1) << 6;

		value |= (u64)epp << 24;
		ret = wrmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, value);
	} else {
		if (epp == -EINVAL)
			epp = (pref_index - 1) << 2;
		ret = intel_pstate_set_epb(cpu_data->cpu, epp);
	}
return_pref:
	mutex_unlock(&intel_pstate_limits_lock);

	return ret;
}

static ssize_t show_energy_performance_available_preferences(
				struct cpufreq_policy *policy, char *buf)
{
	int i = 0;
	int ret = 0;

	while (energy_perf_strings[i] != NULL)
		ret += sprintf(&buf[ret], "%s ", energy_perf_strings[i++]);

	ret += sprintf(&buf[ret], "\n");

	return ret;
}

cpufreq_freq_attr_ro(energy_performance_available_preferences);

static ssize_t store_energy_performance_preference(
		struct cpufreq_policy *policy, const char *buf, size_t count)
{
	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
	char str_preference[21];
	int ret, i = 0;

	ret = sscanf(buf, "%20s", str_preference);
	if (ret != 1)
		return -EINVAL;

	while (energy_perf_strings[i] != NULL) {
		if (!strcmp(str_preference, energy_perf_strings[i])) {
			intel_pstate_set_energy_pref_index(cpu_data, i);
			return count;
		}
		++i;
	}

	return -EINVAL;
}

static ssize_t show_energy_performance_preference(
				struct cpufreq_policy *policy, char *buf)
{
	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
	int preference;

	preference = intel_pstate_get_energy_pref_index(cpu_data);
	if (preference < 0)
		return preference;

	return  sprintf(buf, "%s\n", energy_perf_strings[preference]);
}

cpufreq_freq_attr_rw(energy_performance_preference);

static struct freq_attr *hwp_cpufreq_attrs[] = {
	&energy_performance_preference,
	&energy_performance_available_preferences,
	NULL,
};

static void intel_pstate_hwp_set(const struct cpumask *cpumask)
{
	int min, hw_min, max, hw_max, cpu, range, adj_range;
	struct perf_limits *perf_limits = limits;
	u64 value, cap;

	for_each_cpu(cpu, cpumask) {
		int max_perf_pct, min_perf_pct;
		struct cpudata *cpu_data = all_cpu_data[cpu];
		s16 epp;

		if (per_cpu_limits)
			perf_limits = all_cpu_data[cpu]->perf_limits;

		rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
		hw_min = HWP_LOWEST_PERF(cap);
		hw_max = HWP_HIGHEST_PERF(cap);
		range = hw_max - hw_min;

		max_perf_pct = perf_limits->max_perf_pct;
		min_perf_pct = perf_limits->min_perf_pct;

		rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
		adj_range = min_perf_pct * range / 100;
		min = hw_min + adj_range;
		value &= ~HWP_MIN_PERF(~0L);
		value |= HWP_MIN_PERF(min);

		adj_range = max_perf_pct * range / 100;
		max = hw_min + adj_range;
		if (limits->no_turbo) {
			hw_max = HWP_GUARANTEED_PERF(cap);
			if (hw_max < max)
				max = hw_max;
		}

		value &= ~HWP_MAX_PERF(~0L);
		value |= HWP_MAX_PERF(max);

		if (cpu_data->epp_policy == cpu_data->policy)
			goto skip_epp;

		cpu_data->epp_policy = cpu_data->policy;

		if (cpu_data->epp_saved >= 0) {
			epp = cpu_data->epp_saved;
			cpu_data->epp_saved = -EINVAL;
			goto update_epp;
		}

		if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) {
			epp = intel_pstate_get_epp(cpu_data, value);
			cpu_data->epp_powersave = epp;
			/* If EPP read was failed, then don't try to write */
			if (epp < 0)
				goto skip_epp;


			epp = 0;
		} else {
			/* skip setting EPP, when saved value is invalid */
			if (cpu_data->epp_powersave < 0)
				goto skip_epp;

			/*
			 * No need to restore EPP when it is not zero. This
			 * means:
			 *  - Policy is not changed
			 *  - user has manually changed
			 *  - Error reading EPB
			 */
			epp = intel_pstate_get_epp(cpu_data, value);
			if (epp)
				goto skip_epp;

			epp = cpu_data->epp_powersave;
		}
update_epp:
		if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
			value &= ~GENMASK_ULL(31, 24);
			value |= (u64)epp << 24;
		} else {
			intel_pstate_set_epb(cpu, epp);
		}
skip_epp:
		wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
	}
}

static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy)
{
	if (hwp_active)
		intel_pstate_hwp_set(policy->cpus);

	return 0;
}

static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy)
{
	struct cpudata *cpu_data = all_cpu_data[policy->cpu];

	if (!hwp_active)
		return 0;

	cpu_data->epp_saved = intel_pstate_get_epp(cpu_data, 0);

	return 0;
}

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

	if (!hwp_active)
		return 0;

	mutex_lock(&intel_pstate_limits_lock);

	all_cpu_data[policy->cpu]->epp_policy = 0;

	ret = intel_pstate_hwp_set_policy(policy);

	mutex_unlock(&intel_pstate_limits_lock);

	return ret;
}

static void intel_pstate_hwp_set_online_cpus(void)
{
	get_online_cpus();
	intel_pstate_hwp_set(cpu_online_mask);
	put_online_cpus();
}

/************************** debugfs begin ************************/
static int pid_param_set(void *data, u64 val)
{
	*(u32 *)data = val;
	intel_pstate_reset_all_pid();
	return 0;
}

static int pid_param_get(void *data, u64 *val)
{
	*val = *(u32 *)data;
	return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(fops_pid_param, pid_param_get, pid_param_set, "%llu\n");

struct pid_param {
	char *name;
	void *value;
};

static struct pid_param pid_files[] = {
	{"sample_rate_ms", &pid_params.sample_rate_ms},
	{"d_gain_pct", &pid_params.d_gain_pct},
	{"i_gain_pct", &pid_params.i_gain_pct},
	{"deadband", &pid_params.deadband},
	{"setpoint", &pid_params.setpoint},
	{"p_gain_pct", &pid_params.p_gain_pct},
	{NULL, NULL}
};

static void __init intel_pstate_debug_expose_params(void)
{
	struct dentry *debugfs_parent;
	int i = 0;

	debugfs_parent = debugfs_create_dir("pstate_snb", NULL);
	if (IS_ERR_OR_NULL(debugfs_parent))
		return;
	while (pid_files[i].name) {
		debugfs_create_file(pid_files[i].name, 0660,
				    debugfs_parent, pid_files[i].value,
				    &fops_pid_param);
		i++;
	}
}

/************************** debugfs end ************************/

/************************** sysfs begin ************************/
#define show_one(file_name, object)					\
	static ssize_t show_##file_name					\
	(struct kobject *kobj, struct attribute *attr, char *buf)	\
	{								\
		return sprintf(buf, "%u\n", limits->object);		\
	}

static ssize_t show_turbo_pct(struct kobject *kobj,
				struct attribute *attr, char *buf)
{
	struct cpudata *cpu;
	int total, no_turbo, turbo_pct;
	uint32_t turbo_fp;

	cpu = all_cpu_data[0];

	total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1;
	no_turbo = cpu->pstate.max_pstate - cpu->pstate.min_pstate + 1;
	turbo_fp = div_fp(no_turbo, total);
	turbo_pct = 100 - fp_toint(mul_fp(turbo_fp, int_tofp(100)));
	return sprintf(buf, "%u\n", turbo_pct);
}

static ssize_t show_num_pstates(struct kobject *kobj,
				struct attribute *attr, char *buf)
{
	struct cpudata *cpu;
	int total;

	cpu = all_cpu_data[0];
	total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1;
	return sprintf(buf, "%u\n", total);
}

static ssize_t show_no_turbo(struct kobject *kobj,
			     struct attribute *attr, char *buf)
{
	ssize_t ret;

	update_turbo_state();
	if (limits->turbo_disabled)
		ret = sprintf(buf, "%u\n", limits->turbo_disabled);
	else
		ret = sprintf(buf, "%u\n", limits->no_turbo);

	return ret;
}

static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
			      const char *buf, size_t count)
{
	unsigned int input;
	int ret;

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

	mutex_lock(&intel_pstate_limits_lock);

	update_turbo_state();
	if (limits->turbo_disabled) {
		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
		mutex_unlock(&intel_pstate_limits_lock);
		return -EPERM;
	}

	limits->no_turbo = clamp_t(int, input, 0, 1);

	if (hwp_active)
		intel_pstate_hwp_set_online_cpus();

	mutex_unlock(&intel_pstate_limits_lock);

	return count;
}

static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
				  const char *buf, size_t count)
{
	unsigned int input;
	int ret;

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

	mutex_lock(&intel_pstate_limits_lock);

	limits->max_sysfs_pct = clamp_t(int, input, 0 , 100);
	limits->max_perf_pct = min(limits->max_policy_pct,
				   limits->max_sysfs_pct);
	limits->max_perf_pct = max(limits->min_policy_pct,
				   limits->max_perf_pct);
	limits->max_perf_pct = max(limits->min_perf_pct,
				   limits->max_perf_pct);
	limits->max_perf = div_ext_fp(limits->max_perf_pct, 100);

	if (hwp_active)
		intel_pstate_hwp_set_online_cpus();

	mutex_unlock(&intel_pstate_limits_lock);

	return count;
}

static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
				  const char *buf, size_t count)
{
	unsigned int input;
	int ret;

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

	mutex_lock(&intel_pstate_limits_lock);

	limits->min_sysfs_pct = clamp_t(int, input, 0 , 100);
	limits->min_perf_pct = max(limits->min_policy_pct,
				   limits->min_sysfs_pct);
	limits->min_perf_pct = min(limits->max_policy_pct,
				   limits->min_perf_pct);
	limits->min_perf_pct = min(limits->max_perf_pct,
				   limits->min_perf_pct);
	limits->min_perf = div_ext_fp(limits->min_perf_pct, 100);

	if (hwp_active)
		intel_pstate_hwp_set_online_cpus();

	mutex_unlock(&intel_pstate_limits_lock);

	return count;
}

show_one(max_perf_pct, max_perf_pct);
show_one(min_perf_pct, min_perf_pct);

define_one_global_rw(no_turbo);
define_one_global_rw(max_perf_pct);
define_one_global_rw(min_perf_pct);
define_one_global_ro(turbo_pct);
define_one_global_ro(num_pstates);

static struct attribute *intel_pstate_attributes[] = {
	&no_turbo.attr,
	&turbo_pct.attr,
	&num_pstates.attr,
	NULL
};

static struct attribute_group intel_pstate_attr_group = {
	.attrs = intel_pstate_attributes,
};

static void __init intel_pstate_sysfs_expose_params(void)
{
	struct kobject *intel_pstate_kobject;
	int rc;

	intel_pstate_kobject = kobject_create_and_add("intel_pstate",
						&cpu_subsys.dev_root->kobj);
	if (WARN_ON(!intel_pstate_kobject))
		return;

	rc = sysfs_create_group(intel_pstate_kobject, &intel_pstate_attr_group);
	if (WARN_ON(rc))
		return;

	/*
	 * If per cpu limits are enforced there are no global limits, so
	 * return without creating max/min_perf_pct attributes
	 */
	if (per_cpu_limits)
		return;

	rc = sysfs_create_file(intel_pstate_kobject, &max_perf_pct.attr);
	WARN_ON(rc);

	rc = sysfs_create_file(intel_pstate_kobject, &min_perf_pct.attr);
	WARN_ON(rc);

}
/************************** sysfs end ************************/

static void intel_pstate_hwp_enable(struct cpudata *cpudata)
{
	/* First disable HWP notification interrupt as we don't process them */
	if (static_cpu_has(X86_FEATURE_HWP_NOTIFY))
		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);

	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
	cpudata->epp_policy = 0;
	if (cpudata->epp_default == -EINVAL)
		cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
}

static int atom_get_min_pstate(void)
{
	u64 value;

	rdmsrl(ATOM_RATIOS, value);
	return (value >> 8) & 0x7F;
}

static int atom_get_max_pstate(void)
{
	u64 value;

	rdmsrl(ATOM_RATIOS, value);
	return (value >> 16) & 0x7F;
}

static int atom_get_turbo_pstate(void)
{
	u64 value;

	rdmsrl(ATOM_TURBO_RATIOS, value);
	return value & 0x7F;
}

static u64 atom_get_val(struct cpudata *cpudata, int pstate)
{
	u64 val;
	int32_t vid_fp;
	u32 vid;

	val = (u64)pstate << 8;
	if (limits->no_turbo && !limits->turbo_disabled)
		val |= (u64)1 << 32;

	vid_fp = cpudata->vid.min + mul_fp(
		int_tofp(pstate - cpudata->pstate.min_pstate),
		cpudata->vid.ratio);

	vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max);
	vid = ceiling_fp(vid_fp);

	if (pstate > cpudata->pstate.max_pstate)
		vid = cpudata->vid.turbo;

	return val | vid;
}

static int silvermont_get_scaling(void)
{
	u64 value;
	int i;
	/* Defined in Table 35-6 from SDM (Sept 2015) */
	static int silvermont_freq_table[] = {
		83300, 100000, 133300, 116700, 80000};

	rdmsrl(MSR_FSB_FREQ, value);
	i = value & 0x7;
	WARN_ON(i > 4);

	return silvermont_freq_table[i];
}

static int airmont_get_scaling(void)
{
	u64 value;
	int i;
	/* Defined in Table 35-10 from SDM (Sept 2015) */
	static int airmont_freq_table[] = {
		83300, 100000, 133300, 116700, 80000,
		93300, 90000, 88900, 87500};

	rdmsrl(MSR_FSB_FREQ, value);
	i = value & 0xF;
	WARN_ON(i > 8);

	return airmont_freq_table[i];
}

static void atom_get_vid(struct cpudata *cpudata)
{
	u64 value;

	rdmsrl(ATOM_VIDS, value);
	cpudata->vid.min = int_tofp((value >> 8) & 0x7f);
	cpudata->vid.max = int_tofp((value >> 16) & 0x7f);
	cpudata->vid.ratio = div_fp(
		cpudata->vid.max - cpudata->vid.min,
		int_tofp(cpudata->pstate.max_pstate -
			cpudata->pstate.min_pstate));

	rdmsrl(ATOM_TURBO_VIDS, value);
	cpudata->vid.turbo = value & 0x7f;
}

static int core_get_min_pstate(void)
{
	u64 value;

	rdmsrl(MSR_PLATFORM_INFO, value);
	return (value >> 40) & 0xFF;
}

static int core_get_max_pstate_physical(void)
{
	u64 value;

	rdmsrl(MSR_PLATFORM_INFO, value);
	return (value >> 8) & 0xFF;
}

static int core_get_max_pstate(void)
{
	u64 tar;
	u64 plat_info;
	int max_pstate;
	int err;

	rdmsrl(MSR_PLATFORM_INFO, plat_info);
	max_pstate = (plat_info >> 8) & 0xFF;

	err = rdmsrl_safe(MSR_TURBO_ACTIVATION_RATIO, &tar);
	if (!err) {
		/* Do some sanity checking for safety */
		if (plat_info & 0x600000000) {
			u64 tdp_ctrl;
			u64 tdp_ratio;
			int tdp_msr;

			err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
			if (err)
				goto skip_tar;

			tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x3);
			err = rdmsrl_safe(tdp_msr, &tdp_ratio);
			if (err)
				goto skip_tar;

			/* For level 1 and 2, bits[23:16] contain the ratio */
			if (tdp_ctrl)
				tdp_ratio >>= 16;

			tdp_ratio &= 0xff; /* ratios are only 8 bits long */
			if (tdp_ratio - 1 == tar) {
				max_pstate = tar;
				pr_debug("max_pstate=TAC %x\n", max_pstate);
			} else {
				goto skip_tar;
			}
		}
	}

skip_tar:
	return max_pstate;
}

static int core_get_turbo_pstate(void)
{
	u64 value;
	int nont, ret;

	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
	nont = core_get_max_pstate();
	ret = (value) & 255;
	if (ret <= nont)
		ret = nont;
	return ret;
}

static inline int core_get_scaling(void)
{
	return 100000;
}

static u64 core_get_val(struct cpudata *cpudata, int pstate)
{
	u64 val;

	val = (u64)pstate << 8;
	if (limits->no_turbo && !limits->turbo_disabled)
		val |= (u64)1 << 32;

	return val;
}

static int knl_get_turbo_pstate(void)
{
	u64 value;
	int nont, ret;

	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
	nont = core_get_max_pstate();
	ret = (((value) >> 8) & 0xFF);
	if (ret <= nont)
		ret = nont;
	return ret;
}

static struct cpu_defaults core_params = {
	.pid_policy = {
		.sample_rate_ms = 10,
		.deadband = 0,
		.setpoint = 97,
		.p_gain_pct = 20,
		.d_gain_pct = 0,
		.i_gain_pct = 0,
	},
	.funcs = {
		.get_max = core_get_max_pstate,
		.get_max_physical = core_get_max_pstate_physical,
		.get_min = core_get_min_pstate,
		.get_turbo = core_get_turbo_pstate,
		.get_scaling = core_get_scaling,
		.get_val = core_get_val,
		.get_target_pstate = get_target_pstate_use_performance,
	},
};

static const struct cpu_defaults silvermont_params = {
	.pid_policy = {
		.sample_rate_ms = 10,
		.deadband = 0,
		.setpoint = 60,
		.p_gain_pct = 14,
		.d_gain_pct = 0,
		.i_gain_pct = 4,
	},
	.funcs = {
		.get_max = atom_get_max_pstate,
		.get_max_physical = atom_get_max_pstate,
		.get_min = atom_get_min_pstate,
		.get_turbo = atom_get_turbo_pstate,
		.get_val = atom_get_val,
		.get_scaling = silvermont_get_scaling,
		.get_vid = atom_get_vid,
		.get_target_pstate = get_target_pstate_use_cpu_load,
	},
};

static const struct cpu_defaults airmont_params = {
	.pid_policy = {
		.sample_rate_ms = 10,
		.deadband = 0,
		.setpoint = 60,
		.p_gain_pct = 14,
		.d_gain_pct = 0,
		.i_gain_pct = 4,
	},
	.funcs = {
		.get_max = atom_get_max_pstate,
		.get_max_physical = atom_get_max_pstate,
		.get_min = atom_get_min_pstate,
		.get_turbo = atom_get_turbo_pstate,
		.get_val = atom_get_val,
		.get_scaling = airmont_get_scaling,
		.get_vid = atom_get_vid,
		.get_target_pstate = get_target_pstate_use_cpu_load,
	},
};

static const struct cpu_defaults knl_params = {
	.pid_policy = {
		.sample_rate_ms = 10,
		.deadband = 0,
		.setpoint = 97,
		.p_gain_pct = 20,
		.d_gain_pct = 0,
		.i_gain_pct = 0,
	},
	.funcs = {
		.get_max = core_get_max_pstate,
		.get_max_physical = core_get_max_pstate_physical,
		.get_min = core_get_min_pstate,
		.get_turbo = knl_get_turbo_pstate,
		.get_scaling = core_get_scaling,
		.get_val = core_get_val,
		.get_target_pstate = get_target_pstate_use_performance,
	},
};

static const struct cpu_defaults bxt_params = {
	.pid_policy = {
		.sample_rate_ms = 10,
		.deadband = 0,
		.setpoint = 60,
		.p_gain_pct = 14,
		.d_gain_pct = 0,
		.i_gain_pct = 4,
	},
	.funcs = {
		.get_max = core_get_max_pstate,
		.get_max_physical = core_get_max_pstate_physical,
		.get_min = core_get_min_pstate,
		.get_turbo = core_get_turbo_pstate,
		.get_scaling = core_get_scaling,
		.get_val = core_get_val,
		.get_target_pstate = get_target_pstate_use_cpu_load,
	},
};

static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
{
	int max_perf = cpu->pstate.turbo_pstate;
	int max_perf_adj;
	int min_perf;
	struct perf_limits *perf_limits = limits;

	if (limits->no_turbo || limits->turbo_disabled)
		max_perf = cpu->pstate.max_pstate;

	if (per_cpu_limits)
		perf_limits = cpu->perf_limits;

	/*
	 * performance can be limited by user through sysfs, by cpufreq
	 * policy, or by cpu specific default values determined through
	 * experimentation.
	 */
	max_perf_adj = fp_ext_toint(max_perf * perf_limits->max_perf);
	*max = clamp_t(int, max_perf_adj,
			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);

	min_perf = fp_ext_toint(max_perf * perf_limits->min_perf);
	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
}

static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
{
	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
	cpu->pstate.current_pstate = pstate;
	/*
	 * Generally, there is no guarantee that this code will always run on
	 * the CPU being updated, so force the register update to run on the
	 * right CPU.
	 */
	wrmsrl_on_cpu(cpu->cpu, MSR_IA32_PERF_CTL,
		      pstate_funcs.get_val(cpu, pstate));
}

static void intel_pstate_set_min_pstate(struct cpudata *cpu)
{
	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
}

static void intel_pstate_max_within_limits(struct cpudata *cpu)
{
	int min_pstate, max_pstate;

	update_turbo_state();
	intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
	intel_pstate_set_pstate(cpu, max_pstate);
}

static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
{
	cpu->pstate.min_pstate = pstate_funcs.get_min();
	cpu->pstate.max_pstate = pstate_funcs.get_max();
	cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical();
	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
	cpu->pstate.scaling = pstate_funcs.get_scaling();
	cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling;
	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;

	if (pstate_funcs.get_vid)
		pstate_funcs.get_vid(cpu);

	intel_pstate_set_min_pstate(cpu);
}

static inline void intel_pstate_calc_avg_perf(struct cpudata *cpu)
{
	struct sample *sample = &cpu->sample;

	sample->core_avg_perf = div_ext_fp(sample->aperf, sample->mperf);
}

static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
{
	u64 aperf, mperf;
	unsigned long flags;
	u64 tsc;

	local_irq_save(flags);
	rdmsrl(MSR_IA32_APERF, aperf);
	rdmsrl(MSR_IA32_MPERF, mperf);
	tsc = rdtsc();
	if (cpu->prev_mperf == mperf || cpu->prev_tsc == tsc) {
		local_irq_restore(flags);
		return false;
	}
	local_irq_restore(flags);

	cpu->last_sample_time = cpu->sample.time;
	cpu->sample.time = time;
	cpu->sample.aperf = aperf;
	cpu->sample.mperf = mperf;
	cpu->sample.tsc =  tsc;
	cpu->sample.aperf -= cpu->prev_aperf;
	cpu->sample.mperf -= cpu->prev_mperf;
	cpu->sample.tsc -= cpu->prev_tsc;

	cpu->prev_aperf = aperf;
	cpu->prev_mperf = mperf;
	cpu->prev_tsc = tsc;
	/*
	 * First time this function is invoked in a given cycle, all of the
	 * previous sample data fields are equal to zero or stale and they must
	 * be populated with meaningful numbers for things to work, so assume
	 * that sample.time will always be reset before setting the utilization
	 * update hook and make the caller skip the sample then.
	 */
	return !!cpu->last_sample_time;
}

static inline int32_t get_avg_frequency(struct cpudata *cpu)
{
	return mul_ext_fp(cpu->sample.core_avg_perf,
			  cpu->pstate.max_pstate_physical * cpu->pstate.scaling);
}

static inline int32_t get_avg_pstate(struct cpudata *cpu)
{
	return mul_ext_fp(cpu->pstate.max_pstate_physical,
			  cpu->sample.core_avg_perf);
}

static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
{
	struct sample *sample = &cpu->sample;
	int32_t busy_frac, boost;
	int target, avg_pstate;

	busy_frac = div_fp(sample->mperf, sample->tsc);

	boost = cpu->iowait_boost;
	cpu->iowait_boost >>= 1;

	if (busy_frac < boost)
		busy_frac = boost;

	sample->busy_scaled = busy_frac * 100;

	target = limits->no_turbo || limits->turbo_disabled ?
			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
	target += target >> 2;
	target = mul_fp(target, busy_frac);
	if (target < cpu->pstate.min_pstate)
		target = cpu->pstate.min_pstate;

	/*
	 * If the average P-state during the previous cycle was higher than the
	 * current target, add 50% of the difference to the target to reduce
	 * possible performance oscillations and offset possible performance
	 * loss related to moving the workload from one CPU to another within
	 * a package/module.
	 */
	avg_pstate = get_avg_pstate(cpu);
	if (avg_pstate > target)
		target += (avg_pstate - target) >> 1;

	return target;
}

static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
{
	int32_t perf_scaled, max_pstate, current_pstate, sample_ratio;
	u64 duration_ns;

	/*
	 * perf_scaled is the ratio of the average P-state during the last
	 * sampling period to the P-state requested last time (in percent).
	 *
	 * That measures the system's response to the previous P-state
	 * selection.
	 */
	max_pstate = cpu->pstate.max_pstate_physical;
	current_pstate = cpu->pstate.current_pstate;
	perf_scaled = mul_ext_fp(cpu->sample.core_avg_perf,
			       div_fp(100 * max_pstate, current_pstate));

	/*
	 * Since our utilization update callback will not run unless we are
	 * in C0, check if the actual elapsed time is significantly greater (3x)
	 * than our sample interval.  If it is, then we were idle for a long
	 * enough period of time to adjust our performance metric.
	 */
	duration_ns = cpu->sample.time - cpu->last_sample_time;
	if ((s64)duration_ns > pid_params.sample_rate_ns * 3) {
		sample_ratio = div_fp(pid_params.sample_rate_ns, duration_ns);
		perf_scaled = mul_fp(perf_scaled, sample_ratio);
	} else {
		sample_ratio = div_fp(100 * cpu->sample.mperf, cpu->sample.tsc);
		if (sample_ratio < int_tofp(1))
			perf_scaled = 0;
	}

	cpu->sample.busy_scaled = perf_scaled;
	return cpu->pstate.current_pstate - pid_calc(&cpu->pid, perf_scaled);
}

static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate)
{
	int max_perf, min_perf;

	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
	pstate = clamp_t(int, pstate, min_perf, max_perf);
	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
	return pstate;
}

static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
{
	pstate = intel_pstate_prepare_request(cpu, pstate);
	if (pstate == cpu->pstate.current_pstate)
		return;

	cpu->pstate.current_pstate = pstate;
	wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate));
}

static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
{
	int from, target_pstate;
	struct sample *sample;

	from = cpu->pstate.current_pstate;

	target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ?
		cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu);

	update_turbo_state();

	intel_pstate_update_pstate(cpu, target_pstate);

	sample = &cpu->sample;
	trace_pstate_sample(mul_ext_fp(100, sample->core_avg_perf),
		fp_toint(sample->busy_scaled),
		from,
		cpu->pstate.current_pstate,
		sample->mperf,
		sample->aperf,
		sample->tsc,
		get_avg_frequency(cpu),
		fp_toint(cpu->iowait_boost * 100));
}

static void intel_pstate_update_util(struct update_util_data *data, u64 time,
				     unsigned int flags)
{
	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
	u64 delta_ns;

	if (pstate_funcs.get_target_pstate == get_target_pstate_use_cpu_load) {
		if (flags & SCHED_CPUFREQ_IOWAIT) {
			cpu->iowait_boost = int_tofp(1);
		} else if (cpu->iowait_boost) {
			/* Clear iowait_boost if the CPU may have been idle. */
			delta_ns = time - cpu->last_update;
			if (delta_ns > TICK_NSEC)
				cpu->iowait_boost = 0;
		}
		cpu->last_update = time;
	}

	delta_ns = time - cpu->sample.time;
	if ((s64)delta_ns >= pid_params.sample_rate_ns) {
		bool sample_taken = intel_pstate_sample(cpu, time);

		if (sample_taken) {
			intel_pstate_calc_avg_perf(cpu);
			if (!hwp_active)
				intel_pstate_adjust_busy_pstate(cpu);
		}
	}
}

#define ICPU(model, policy) \
	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
			(unsigned long)&policy }

static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
	ICPU(INTEL_FAM6_SANDYBRIDGE, 		core_params),
	ICPU(INTEL_FAM6_SANDYBRIDGE_X,		core_params),
	ICPU(INTEL_FAM6_ATOM_SILVERMONT1,	silvermont_params),
	ICPU(INTEL_FAM6_IVYBRIDGE,		core_params),
	ICPU(INTEL_FAM6_HASWELL_CORE,		core_params),
	ICPU(INTEL_FAM6_BROADWELL_CORE,		core_params),
	ICPU(INTEL_FAM6_IVYBRIDGE_X,		core_params),
	ICPU(INTEL_FAM6_HASWELL_X,		core_params),
	ICPU(INTEL_FAM6_HASWELL_ULT,		core_params),
	ICPU(INTEL_FAM6_HASWELL_GT3E,		core_params),
	ICPU(INTEL_FAM6_BROADWELL_GT3E,		core_params),
	ICPU(INTEL_FAM6_ATOM_AIRMONT,		airmont_params),
	ICPU(INTEL_FAM6_SKYLAKE_MOBILE,		core_params),
	ICPU(INTEL_FAM6_BROADWELL_X,		core_params),
	ICPU(INTEL_FAM6_SKYLAKE_DESKTOP,	core_params),
	ICPU(INTEL_FAM6_BROADWELL_XEON_D,	core_params),
	ICPU(INTEL_FAM6_XEON_PHI_KNL,		knl_params),
	ICPU(INTEL_FAM6_XEON_PHI_KNM,		knl_params),
	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		bxt_params),
	{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);

static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
	ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params),
	ICPU(INTEL_FAM6_BROADWELL_X, core_params),
	ICPU(INTEL_FAM6_SKYLAKE_X, core_params),
	{}
};

static int intel_pstate_init_cpu(unsigned int cpunum)
{
	struct cpudata *cpu;

	cpu = all_cpu_data[cpunum];

	if (!cpu) {
		unsigned int size = sizeof(struct cpudata);

		if (per_cpu_limits)
			size += sizeof(struct perf_limits);

		cpu = kzalloc(size, GFP_KERNEL);
		if (!cpu)
			return -ENOMEM;

		all_cpu_data[cpunum] = cpu;
		if (per_cpu_limits)
			cpu->perf_limits = (struct perf_limits *)(cpu + 1);

		cpu->epp_default = -EINVAL;
		cpu->epp_powersave = -EINVAL;
		cpu->epp_saved = -EINVAL;
	}

	cpu = all_cpu_data[cpunum];

	cpu->cpu = cpunum;

	if (hwp_active) {
		intel_pstate_hwp_enable(cpu);
		pid_params.sample_rate_ms = 50;
		pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC;
	}

	intel_pstate_get_cpu_pstates(cpu);

	intel_pstate_busy_pid_reset(cpu);

	pr_debug("controlling: cpu %d\n", cpunum);

	return 0;
}

static unsigned int intel_pstate_get(unsigned int cpu_num)
{
	struct cpudata *cpu = all_cpu_data[cpu_num];

	return cpu ? get_avg_frequency(cpu) : 0;
}

static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
{
	struct cpudata *cpu = all_cpu_data[cpu_num];

	if (cpu->update_util_set)
		return;

	/* Prevent intel_pstate_update_util() from using stale data. */
	cpu->sample.time = 0;
	cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
				     intel_pstate_update_util);
	cpu->update_util_set = true;
}

static void intel_pstate_clear_update_util_hook(unsigned int cpu)
{
	struct cpudata *cpu_data = all_cpu_data[cpu];

	if (!cpu_data->update_util_set)
		return;

	cpufreq_remove_update_util_hook(cpu);
	cpu_data->update_util_set = false;
	synchronize_sched();
}

static void intel_pstate_set_performance_limits(struct perf_limits *limits)
{
	limits->no_turbo = 0;
	limits->turbo_disabled = 0;
	limits->max_perf_pct = 100;
	limits->max_perf = int_ext_tofp(1);
	limits->min_perf_pct = 100;
	limits->min_perf = int_ext_tofp(1);
	limits->max_policy_pct = 100;
	limits->max_sysfs_pct = 100;
	limits->min_policy_pct = 0;
	limits->min_sysfs_pct = 0;
}

static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
					    struct perf_limits *limits)
{

	limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
					      policy->cpuinfo.max_freq);
	limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0, 100);
	if (policy->max == policy->min) {
		limits->min_policy_pct = limits->max_policy_pct;
	} else {
		limits->min_policy_pct = DIV_ROUND_UP(policy->min * 100,
						      policy->cpuinfo.max_freq);
		limits->min_policy_pct = clamp_t(int, limits->min_policy_pct,
						 0, 100);
	}

	/* Normalize user input to [min_policy_pct, max_policy_pct] */
	limits->min_perf_pct = max(limits->min_policy_pct,
				   limits->min_sysfs_pct);
	limits->min_perf_pct = min(limits->max_policy_pct,
				   limits->min_perf_pct);
	limits->max_perf_pct = min(limits->max_policy_pct,
				   limits->max_sysfs_pct);
	limits->max_perf_pct = max(limits->min_policy_pct,
				   limits->max_perf_pct);

	/* Make sure min_perf_pct <= max_perf_pct */
	limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);

	limits->min_perf = div_ext_fp(limits->min_perf_pct, 100);
	limits->max_perf = div_ext_fp(limits->max_perf_pct, 100);
	limits->max_perf = round_up(limits->max_perf, EXT_FRAC_BITS);
	limits->min_perf = round_up(limits->min_perf, EXT_FRAC_BITS);

	pr_debug("cpu:%d max_perf_pct:%d min_perf_pct:%d\n", policy->cpu,
		 limits->max_perf_pct, limits->min_perf_pct);
}

static int intel_pstate_set_policy(struct cpufreq_policy *policy)
{
	struct cpudata *cpu;
	struct perf_limits *perf_limits = NULL;

	if (!policy->cpuinfo.max_freq)
		return -ENODEV;

	pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
		 policy->cpuinfo.max_freq, policy->max);

	cpu = all_cpu_data[policy->cpu];
	cpu->policy = policy->policy;

	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
	    policy->max < policy->cpuinfo.max_freq &&
	    policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
		pr_debug("policy->max > max non turbo frequency\n");
		policy->max = policy->cpuinfo.max_freq;
	}

	if (per_cpu_limits)
		perf_limits = cpu->perf_limits;

	mutex_lock(&intel_pstate_limits_lock);

	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
		if (!perf_limits) {
			limits = &performance_limits;
			perf_limits = limits;
		}
		if (policy->max >= policy->cpuinfo.max_freq) {
			pr_debug("set performance\n");
			intel_pstate_set_performance_limits(perf_limits);
			goto out;
		}
	} else {
		pr_debug("set powersave\n");
		if (!perf_limits) {
			limits = &powersave_limits;
			perf_limits = limits;
		}

	}

	intel_pstate_update_perf_limits(policy, perf_limits);
 out:
	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
		/*
		 * NOHZ_FULL CPUs need this as the governor callback may not
		 * be invoked on them.
		 */
		intel_pstate_clear_update_util_hook(policy->cpu);
		intel_pstate_max_within_limits(cpu);
	}

	intel_pstate_set_update_util_hook(policy->cpu);

	intel_pstate_hwp_set_policy(policy);

	mutex_unlock(&intel_pstate_limits_lock);

	return 0;
}

static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
{
	cpufreq_verify_within_cpu_limits(policy);

	if (policy->policy != CPUFREQ_POLICY_POWERSAVE &&
	    policy->policy != CPUFREQ_POLICY_PERFORMANCE)
		return -EINVAL;

	return 0;
}

static void intel_cpufreq_stop_cpu(struct cpufreq_policy *policy)
{
	intel_pstate_set_min_pstate(all_cpu_data[policy->cpu]);
}

static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
{
	pr_debug("CPU %d exiting\n", policy->cpu);

	intel_pstate_clear_update_util_hook(policy->cpu);
	if (hwp_active)
		intel_pstate_hwp_save_state(policy);
	else
		intel_cpufreq_stop_cpu(policy);
}

static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
{
	intel_pstate_exit_perf_limits(policy);

	policy->fast_switch_possible = false;

	return 0;
}

static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
{
	struct cpudata *cpu;
	int rc;

	rc = intel_pstate_init_cpu(policy->cpu);
	if (rc)
		return rc;

	cpu = all_cpu_data[policy->cpu];

	/*
	 * We need sane value in the cpu->perf_limits, so inherit from global
	 * perf_limits limits, which are seeded with values based on the
	 * CONFIG_CPU_FREQ_DEFAULT_GOV_*, during boot up.
	 */
	if (per_cpu_limits)
		memcpy(cpu->perf_limits, limits, sizeof(struct perf_limits));

	policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
	policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;

	/* cpuinfo and default policy values */
	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
	update_turbo_state();
	policy->cpuinfo.max_freq = limits->turbo_disabled ?
			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
	policy->cpuinfo.max_freq *= cpu->pstate.scaling;

	intel_pstate_init_acpi_perf_limits(policy);
	cpumask_set_cpu(policy->cpu, policy->cpus);

	policy->fast_switch_possible = true;

	return 0;
}

static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
{
	int ret = __intel_pstate_cpu_init(policy);

	if (ret)
		return ret;

	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
	if (limits->min_perf_pct == 100 && limits->max_perf_pct == 100)
		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
	else
		policy->policy = CPUFREQ_POLICY_POWERSAVE;

	return 0;
}

static struct cpufreq_driver intel_pstate = {
	.flags		= CPUFREQ_CONST_LOOPS,
	.verify		= intel_pstate_verify_policy,
	.setpolicy	= intel_pstate_set_policy,
	.suspend	= intel_pstate_hwp_save_state,
	.resume		= intel_pstate_resume,
	.get		= intel_pstate_get,
	.init		= intel_pstate_cpu_init,
	.exit		= intel_pstate_cpu_exit,
	.stop_cpu	= intel_pstate_stop_cpu,
	.name		= "intel_pstate",
};

static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
{
	struct cpudata *cpu = all_cpu_data[policy->cpu];
	struct perf_limits *perf_limits = limits;

	update_turbo_state();
	policy->cpuinfo.max_freq = limits->turbo_disabled ?
			cpu->pstate.max_freq : cpu->pstate.turbo_freq;

	cpufreq_verify_within_cpu_limits(policy);

	if (per_cpu_limits)
		perf_limits = cpu->perf_limits;

	mutex_lock(&intel_pstate_limits_lock);

	intel_pstate_update_perf_limits(policy, perf_limits);

	mutex_unlock(&intel_pstate_limits_lock);

	return 0;
}

static unsigned int intel_cpufreq_turbo_update(struct cpudata *cpu,
					       struct cpufreq_policy *policy,
					       unsigned int target_freq)
{
	unsigned int max_freq;

	update_turbo_state();

	max_freq = limits->no_turbo || limits->turbo_disabled ?
			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
	policy->cpuinfo.max_freq = max_freq;
	if (policy->max > max_freq)
		policy->max = max_freq;

	if (target_freq > max_freq)
		target_freq = max_freq;

	return target_freq;
}

static int intel_cpufreq_target(struct cpufreq_policy *policy,
				unsigned int target_freq,
				unsigned int relation)
{
	struct cpudata *cpu = all_cpu_data[policy->cpu];
	struct cpufreq_freqs freqs;
	int target_pstate;

	freqs.old = policy->cur;
	freqs.new = intel_cpufreq_turbo_update(cpu, policy, target_freq);

	cpufreq_freq_transition_begin(policy, &freqs);
	switch (relation) {
	case CPUFREQ_RELATION_L:
		target_pstate = DIV_ROUND_UP(freqs.new, cpu->pstate.scaling);
		break;
	case CPUFREQ_RELATION_H:
		target_pstate = freqs.new / cpu->pstate.scaling;
		break;
	default:
		target_pstate = DIV_ROUND_CLOSEST(freqs.new, cpu->pstate.scaling);
		break;
	}
	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
	if (target_pstate != cpu->pstate.current_pstate) {
		cpu->pstate.current_pstate = target_pstate;
		wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL,
			      pstate_funcs.get_val(cpu, target_pstate));
	}
	cpufreq_freq_transition_end(policy, &freqs, false);

	return 0;
}

static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
					      unsigned int target_freq)
{
	struct cpudata *cpu = all_cpu_data[policy->cpu];
	int target_pstate;

	target_freq = intel_cpufreq_turbo_update(cpu, policy, target_freq);
	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
	intel_pstate_update_pstate(cpu, target_pstate);
	return target_freq;
}

static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
{
	int ret = __intel_pstate_cpu_init(policy);

	if (ret)
		return ret;

	policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY;
	/* This reflects the intel_pstate_get_cpu_pstates() setting. */
	policy->cur = policy->cpuinfo.min_freq;

	return 0;
}

static struct cpufreq_driver intel_cpufreq = {
	.flags		= CPUFREQ_CONST_LOOPS,
	.verify		= intel_cpufreq_verify_policy,
	.target		= intel_cpufreq_target,
	.fast_switch	= intel_cpufreq_fast_switch,
	.init		= intel_cpufreq_cpu_init,
	.exit		= intel_pstate_cpu_exit,
	.stop_cpu	= intel_cpufreq_stop_cpu,
	.name		= "intel_cpufreq",
};

static struct cpufreq_driver *intel_pstate_driver = &intel_pstate;

static int no_load __initdata;
static int no_hwp __initdata;
static int hwp_only __initdata;
static unsigned int force_load __initdata;

static int __init intel_pstate_msrs_not_valid(void)
{
	if (!pstate_funcs.get_max() ||
	    !pstate_funcs.get_min() ||
	    !pstate_funcs.get_turbo())
		return -ENODEV;

	return 0;
}

static void __init copy_pid_params(struct pstate_adjust_policy *policy)
{
	pid_params.sample_rate_ms = policy->sample_rate_ms;
	pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
	pid_params.p_gain_pct = policy->p_gain_pct;
	pid_params.i_gain_pct = policy->i_gain_pct;
	pid_params.d_gain_pct = policy->d_gain_pct;
	pid_params.deadband = policy->deadband;
	pid_params.setpoint = policy->setpoint;
}

#ifdef CONFIG_ACPI
static void intel_pstate_use_acpi_profile(void)
{
	if (acpi_gbl_FADT.preferred_profile == PM_MOBILE)
		pstate_funcs.get_target_pstate =
				get_target_pstate_use_cpu_load;
}
#else
static void intel_pstate_use_acpi_profile(void)
{
}
#endif

static void __init copy_cpu_funcs(struct pstate_funcs *funcs)
{
	pstate_funcs.get_max   = funcs->get_max;
	pstate_funcs.get_max_physical = funcs->get_max_physical;
	pstate_funcs.get_min   = funcs->get_min;
	pstate_funcs.get_turbo = funcs->get_turbo;
	pstate_funcs.get_scaling = funcs->get_scaling;
	pstate_funcs.get_val   = funcs->get_val;
	pstate_funcs.get_vid   = funcs->get_vid;
	pstate_funcs.get_target_pstate = funcs->get_target_pstate;

	intel_pstate_use_acpi_profile();
}

#ifdef CONFIG_ACPI

static bool __init intel_pstate_no_acpi_pss(void)
{
	int i;

	for_each_possible_cpu(i) {
		acpi_status status;
		union acpi_object *pss;
		struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
		struct acpi_processor *pr = per_cpu(processors, i);

		if (!pr)
			continue;

		status = acpi_evaluate_object(pr->handle, "_PSS", NULL, &buffer);
		if (ACPI_FAILURE(status))
			continue;

		pss = buffer.pointer;
		if (pss && pss->type == ACPI_TYPE_PACKAGE) {
			kfree(pss);
			return false;
		}

		kfree(pss);
	}

	return true;
}

static bool __init intel_pstate_has_acpi_ppc(void)
{
	int i;

	for_each_possible_cpu(i) {
		struct acpi_processor *pr = per_cpu(processors, i);

		if (!pr)
			continue;
		if (acpi_has_method(pr->handle, "_PPC"))
			return true;
	}
	return false;
}

enum {
	PSS,
	PPC,
};

struct hw_vendor_info {
	u16  valid;
	char oem_id[ACPI_OEM_ID_SIZE];
	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE];
	int  oem_pwr_table;
};

/* Hardware vendor-specific info that has its own power management modes */
static struct hw_vendor_info vendor_info[] __initdata = {
	{1, "HP    ", "ProLiant", PSS},
	{1, "ORACLE", "X4-2    ", PPC},
	{1, "ORACLE", "X4-2L   ", PPC},
	{1, "ORACLE", "X4-2B   ", PPC},
	{1, "ORACLE", "X3-2    ", PPC},
	{1, "ORACLE", "X3-2L   ", PPC},
	{1, "ORACLE", "X3-2B   ", PPC},
	{1, "ORACLE", "X4470M2 ", PPC},
	{1, "ORACLE", "X4270M3 ", PPC},
	{1, "ORACLE", "X4270M2 ", PPC},
	{1, "ORACLE", "X4170M2 ", PPC},
	{1, "ORACLE", "X4170 M3", PPC},
	{1, "ORACLE", "X4275 M3", PPC},
	{1, "ORACLE", "X6-2    ", PPC},
	{1, "ORACLE", "Sudbury ", PPC},
	{0, "", ""},
};

static bool __init intel_pstate_platform_pwr_mgmt_exists(void)
{
	struct acpi_table_header hdr;
	struct hw_vendor_info *v_info;
	const struct x86_cpu_id *id;
	u64 misc_pwr;

	id = x86_match_cpu(intel_pstate_cpu_oob_ids);
	if (id) {
		rdmsrl(MSR_MISC_PWR_MGMT, misc_pwr);
		if ( misc_pwr & (1 << 8))
			return true;
	}

	if (acpi_disabled ||
	    ACPI_FAILURE(acpi_get_table_header(ACPI_SIG_FADT, 0, &hdr)))
		return false;

	for (v_info = vendor_info; v_info->valid; v_info++) {
		if (!strncmp(hdr.oem_id, v_info->oem_id, ACPI_OEM_ID_SIZE) &&
			!strncmp(hdr.oem_table_id, v_info->oem_table_id,
						ACPI_OEM_TABLE_ID_SIZE))
			switch (v_info->oem_pwr_table) {
			case PSS:
				return intel_pstate_no_acpi_pss();
			case PPC:
				return intel_pstate_has_acpi_ppc() &&
					(!force_load);
			}
	}

	return false;
}

static void intel_pstate_request_control_from_smm(void)
{
	/*
	 * It may be unsafe to request P-states control from SMM if _PPC support
	 * has not been enabled.
	 */
	if (acpi_ppc)
		acpi_processor_pstate_control();
}
#else /* CONFIG_ACPI not enabled */
static inline bool intel_pstate_platform_pwr_mgmt_exists(void) { return false; }
static inline bool intel_pstate_has_acpi_ppc(void) { return false; }
static inline void intel_pstate_request_control_from_smm(void) {}
#endif /* CONFIG_ACPI */

static const struct x86_cpu_id hwp_support_ids[] __initconst = {
	{ X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_HWP },
	{}
};

static int __init intel_pstate_init(void)
{
	int cpu, rc = 0;
	const struct x86_cpu_id *id;
	struct cpu_defaults *cpu_def;

	if (no_load)
		return -ENODEV;

	if (x86_match_cpu(hwp_support_ids) && !no_hwp) {
		copy_cpu_funcs(&core_params.funcs);
		hwp_active++;
		intel_pstate.attr = hwp_cpufreq_attrs;
		goto hwp_cpu_matched;
	}

	id = x86_match_cpu(intel_pstate_cpu_ids);
	if (!id)
		return -ENODEV;

	cpu_def = (struct cpu_defaults *)id->driver_data;

	copy_pid_params(&cpu_def->pid_policy);
	copy_cpu_funcs(&cpu_def->funcs);

	if (intel_pstate_msrs_not_valid())
		return -ENODEV;

hwp_cpu_matched:
	/*
	 * The Intel pstate driver will be ignored if the platform
	 * firmware has its own power management modes.
	 */
	if (intel_pstate_platform_pwr_mgmt_exists())
		return -ENODEV;

	pr_info("Intel P-state driver initializing\n");

	all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
	if (!all_cpu_data)
		return -ENOMEM;

	if (!hwp_active && hwp_only)
		goto out;

	intel_pstate_request_control_from_smm();

	rc = cpufreq_register_driver(intel_pstate_driver);
	if (rc)
		goto out;

	if (intel_pstate_driver == &intel_pstate && !hwp_active &&
	    pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
		intel_pstate_debug_expose_params();

	intel_pstate_sysfs_expose_params();

	if (hwp_active)
		pr_info("HWP enabled\n");

	return rc;
out:
	get_online_cpus();
	for_each_online_cpu(cpu) {
		if (all_cpu_data[cpu]) {
			if (intel_pstate_driver == &intel_pstate)
				intel_pstate_clear_update_util_hook(cpu);

			kfree(all_cpu_data[cpu]);
		}
	}

	put_online_cpus();
	vfree(all_cpu_data);
	return -ENODEV;
}
device_initcall(intel_pstate_init);

static int __init intel_pstate_setup(char *str)
{
	if (!str)
		return -EINVAL;

	if (!strcmp(str, "disable")) {
		no_load = 1;
	} else if (!strcmp(str, "passive")) {
		pr_info("Passive mode enabled\n");
		intel_pstate_driver = &intel_cpufreq;
		no_hwp = 1;
	}
	if (!strcmp(str, "no_hwp")) {
		pr_info("HWP disabled\n");
		no_hwp = 1;
	}
	if (!strcmp(str, "force"))
		force_load = 1;
	if (!strcmp(str, "hwp_only"))
		hwp_only = 1;
	if (!strcmp(str, "per_cpu_perf_limits"))
		per_cpu_limits = true;

#ifdef CONFIG_ACPI
	if (!strcmp(str, "support_acpi_ppc"))
		acpi_ppc = true;
#endif

	return 0;
}
early_param("intel_pstate", intel_pstate_setup);

MODULE_AUTHOR("Dirk Brandewie <dirk.j.brandewie@intel.com>");
MODULE_DESCRIPTION("'intel_pstate' - P state driver Intel Core processors");
MODULE_LICENSE("GPL");