summaryrefslogtreecommitdiff
path: root/drivers/cpufreq/intel_pstate.c
blob: a534a1f7f1ee73d8fe319df76e4511825b1daf6d (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
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
// SPDX-License-Identifier: GPL-2.0-only
/*
 * intel_pstate.c: Native P state management for Intel processors
 *
 * (C) Copyright 2012 Intel Corporation
 * Author: Dirk Brandewie <dirk.j.brandewie@intel.com>
 */

#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/cpufreq.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/acpi.h>
#include <linux/vmalloc.h>
#include <linux/pm_qos.h>
#include <trace/events/power.h>

#include <asm/cpu.h>
#include <asm/div64.h>
#include <asm/msr.h>
#include <asm/cpu_device_id.h>
#include <asm/cpufeature.h>
#include <asm/intel-family.h>
#include "../drivers/thermal/intel/thermal_interrupt.h"

#define INTEL_PSTATE_SAMPLING_INTERVAL	(10 * NSEC_PER_MSEC)

#define INTEL_CPUFREQ_TRANSITION_LATENCY	20000
#define INTEL_CPUFREQ_TRANSITION_DELAY_HWP	5000
#define INTEL_CPUFREQ_TRANSITION_DELAY		500

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

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

#define ONE_EIGHTH_FP ((int64_t)1 << (FRAC_BITS - 3))

#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
 * @perf_ctl_scaling:	PERF_CTL P-state to frequency scaling factor
 * @scaling:		Scaling factor between performance and frequency
 * @turbo_pstate:	Max Turbo P state possible for this platform
 * @min_freq:		@min_pstate frequency in cpufreq units
 * @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	perf_ctl_scaling;
	int	scaling;
	int	turbo_pstate;
	unsigned int min_freq;
	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 global_params - Global parameters, mostly tunable via sysfs.
 * @no_turbo:		Whether or not to use turbo P-states.
 * @turbo_disabled:	Whether or not turbo P-states are available at all,
 *			based on the MSR_IA32_MISC_ENABLE value and whether or
 *			not the maximum reported turbo P-state is different from
 *			the maximum reported non-turbo one.
 * @turbo_disabled_mf:	The @turbo_disabled value reflected by cpuinfo.max_freq.
 * @min_perf_pct:	Minimum capacity limit in percent of the maximum turbo
 *			P-state capacity.
 * @max_perf_pct:	Maximum capacity limit in percent of the maximum turbo
 *			P-state capacity.
 */
struct global_params {
	bool no_turbo;
	bool turbo_disabled;
	bool turbo_disabled_mf;
	int max_perf_pct;
	int min_perf_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
 * @last_sample_time:	Last Sample time
 * @aperf_mperf_shift:	APERF vs MPERF counting frequency difference
 * @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
 * @min_perf_ratio:	Minimum capacity in terms of PERF or HWP ratios
 * @max_perf_ratio:	Maximum capacity in terms of PERF or HWP ratios
 * @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_cached		Cached HWP energy-performance preference value
 * @hwp_req_cached:	Cached value of the last HWP Request MSR
 * @hwp_cap_cached:	Cached value of the last HWP Capabilities MSR
 * @last_io_update:	Last time when IO wake flag was set
 * @sched_flags:	Store scheduler flags for possible cross CPU update
 * @hwp_boost_min:	Last HWP boosted min performance
 * @suspended:		Whether or not the driver has been suspended.
 * @hwp_notify_work:	workqueue for HWP notifications.
 *
 * 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;

	u64	last_update;
	u64	last_sample_time;
	u64	aperf_mperf_shift;
	u64	prev_aperf;
	u64	prev_mperf;
	u64	prev_tsc;
	u64	prev_cummulative_iowait;
	struct sample sample;
	int32_t	min_perf_ratio;
	int32_t	max_perf_ratio;
#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_cached;
	u64 hwp_req_cached;
	u64 hwp_cap_cached;
	u64 last_io_update;
	unsigned int sched_flags;
	u32 hwp_boost_min;
	bool suspended;
	struct delayed_work hwp_notify_work;
};

static struct cpudata **all_cpu_data;

/**
 * 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_cpu_scaling:	Get frequency scaling factor for a given cpu
 * @get_aperf_mperf_shift: Callback to get the APERF vs MPERF frequency difference
 * @get_val:		Callback to convert P state to actual MSR write value
 * @get_vid:		Callback to get VID data for Atom platforms
 *
 * 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)(int cpu);
	int (*get_max_physical)(int cpu);
	int (*get_min)(int cpu);
	int (*get_turbo)(int cpu);
	int (*get_scaling)(void);
	int (*get_cpu_scaling)(int cpu);
	int (*get_aperf_mperf_shift)(void);
	u64 (*get_val)(struct cpudata*, int pstate);
	void (*get_vid)(struct cpudata *);
};

static struct pstate_funcs pstate_funcs __read_mostly;

static int hwp_active __read_mostly;
static int hwp_mode_bdw __read_mostly;
static bool per_cpu_limits __read_mostly;
static bool hwp_boost __read_mostly;
static bool hwp_forced __read_mostly;

static struct cpufreq_driver *intel_pstate_driver __read_mostly;

#define HYBRID_SCALING_FACTOR	78741

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

#ifdef CONFIG_ACPI
static bool acpi_ppc;
#endif

static struct global_params global;

static DEFINE_MUTEX(intel_pstate_driver_lock);
static DEFINE_MUTEX(intel_pstate_limits_lock);

#ifdef CONFIG_ACPI

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

	return false;
}

static bool intel_pstate_get_ppc_enable_status(void)
{
	if (intel_pstate_acpi_pm_profile_server())
		return true;

	return acpi_ppc;
}

#ifdef CONFIG_ACPI_CPPC_LIB

/* The work item is needed to avoid CPU hotplug locking issues */
static void intel_pstste_sched_itmt_work_fn(struct work_struct *work)
{
	sched_set_itmt_support();
}

static DECLARE_WORK(sched_itmt_work, intel_pstste_sched_itmt_work_fn);

#define CPPC_MAX_PERF	U8_MAX

static void intel_pstate_set_itmt_prio(int cpu)
{
	struct cppc_perf_caps cppc_perf;
	static u32 max_highest_perf = 0, min_highest_perf = U32_MAX;
	int ret;

	ret = cppc_get_perf_caps(cpu, &cppc_perf);
	if (ret)
		return;

	/*
	 * On some systems with overclocking enabled, CPPC.highest_perf is hardcoded to 0xff.
	 * In this case we can't use CPPC.highest_perf to enable ITMT.
	 * In this case we can look at MSR_HWP_CAPABILITIES bits [8:0] to decide.
	 */
	if (cppc_perf.highest_perf == CPPC_MAX_PERF)
		cppc_perf.highest_perf = HWP_HIGHEST_PERF(READ_ONCE(all_cpu_data[cpu]->hwp_cap_cached));

	/*
	 * The priorities can be set regardless of whether or not
	 * sched_set_itmt_support(true) has been called and it is valid to
	 * update them at any time after it has been called.
	 */
	sched_set_itmt_core_prio(cppc_perf.highest_perf, cpu);

	if (max_highest_perf <= min_highest_perf) {
		if (cppc_perf.highest_perf > max_highest_perf)
			max_highest_perf = cppc_perf.highest_perf;

		if (cppc_perf.highest_perf < min_highest_perf)
			min_highest_perf = cppc_perf.highest_perf;

		if (max_highest_perf > min_highest_perf) {
			/*
			 * This code can be run during CPU online under the
			 * CPU hotplug locks, so sched_set_itmt_support()
			 * cannot be called from here.  Queue up a work item
			 * to invoke it.
			 */
			schedule_work(&sched_itmt_work);
		}
	}
}

static int intel_pstate_get_cppc_guaranteed(int cpu)
{
	struct cppc_perf_caps cppc_perf;
	int ret;

	ret = cppc_get_perf_caps(cpu, &cppc_perf);
	if (ret)
		return ret;

	if (cppc_perf.guaranteed_perf)
		return cppc_perf.guaranteed_perf;

	return cppc_perf.nominal_perf;
}

static int intel_pstate_cppc_get_scaling(int cpu)
{
	struct cppc_perf_caps cppc_perf;
	int ret;

	ret = cppc_get_perf_caps(cpu, &cppc_perf);

	/*
	 * If the nominal frequency and the nominal performance are not
	 * zero and the ratio between them is not 100, return the hybrid
	 * scaling factor.
	 */
	if (!ret && cppc_perf.nominal_perf && cppc_perf.nominal_freq &&
	    cppc_perf.nominal_perf * 100 != cppc_perf.nominal_freq)
		return HYBRID_SCALING_FACTOR;

	return core_get_scaling();
}

#else /* CONFIG_ACPI_CPPC_LIB */
static inline void intel_pstate_set_itmt_prio(int cpu)
{
}
#endif /* CONFIG_ACPI_CPPC_LIB */

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

	if (hwp_active) {
		intel_pstate_set_itmt_prio(policy->cpu);
		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);
	}

	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 /* CONFIG_ACPI */
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)
{
}

static inline bool intel_pstate_acpi_pm_profile_server(void)
{
	return false;
}
#endif /* CONFIG_ACPI */

#ifndef CONFIG_ACPI_CPPC_LIB
static inline int intel_pstate_get_cppc_guaranteed(int cpu)
{
	return -ENOTSUPP;
}

static int intel_pstate_cppc_get_scaling(int cpu)
{
	return core_get_scaling();
}
#endif /* CONFIG_ACPI_CPPC_LIB */

/**
 * intel_pstate_hybrid_hwp_adjust - Calibrate HWP performance levels.
 * @cpu: Target CPU.
 *
 * On hybrid processors, HWP may expose more performance levels than there are
 * P-states accessible through the PERF_CTL interface.  If that happens, the
 * scaling factor between HWP performance levels and CPU frequency will be less
 * than the scaling factor between P-state values and CPU frequency.
 *
 * In that case, adjust the CPU parameters used in computations accordingly.
 */
static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
{
	int perf_ctl_max_phys = cpu->pstate.max_pstate_physical;
	int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
	int perf_ctl_turbo = pstate_funcs.get_turbo(cpu->cpu);
	int scaling = cpu->pstate.scaling;

	pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys);
	pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo);
	pr_debug("CPU%d: perf_ctl_scaling = %d\n", cpu->cpu, perf_ctl_scaling);
	pr_debug("CPU%d: HWP_CAP guaranteed = %d\n", cpu->cpu, cpu->pstate.max_pstate);
	pr_debug("CPU%d: HWP_CAP highest = %d\n", cpu->cpu, cpu->pstate.turbo_pstate);
	pr_debug("CPU%d: HWP-to-frequency scaling factor: %d\n", cpu->cpu, scaling);

	cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_pstate * scaling,
					   perf_ctl_scaling);
	cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling,
					 perf_ctl_scaling);

	cpu->pstate.max_pstate_physical =
			DIV_ROUND_UP(perf_ctl_max_phys * perf_ctl_scaling,
				     scaling);

	cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling;
	/*
	 * Cast the min P-state value retrieved via pstate_funcs.get_min() to
	 * the effective range of HWP performance levels.
	 */
	cpu->pstate.min_pstate = DIV_ROUND_UP(cpu->pstate.min_freq, scaling);
}

static inline void update_turbo_state(void)
{
	u64 misc_en;

	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
	global.turbo_disabled = misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE;
}

static int min_perf_pct_min(void)
{
	struct cpudata *cpu = all_cpu_data[0];
	int turbo_pstate = cpu->pstate.turbo_pstate;

	return turbo_pstate ?
		(cpu->pstate.min_pstate * 100 / turbo_pstate) : 0;
}

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

	if (!boot_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 (boot_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 (!boot_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
 */

enum energy_perf_value_index {
	EPP_INDEX_DEFAULT = 0,
	EPP_INDEX_PERFORMANCE,
	EPP_INDEX_BALANCE_PERFORMANCE,
	EPP_INDEX_BALANCE_POWERSAVE,
	EPP_INDEX_POWERSAVE,
};

static const char * const energy_perf_strings[] = {
	[EPP_INDEX_DEFAULT] = "default",
	[EPP_INDEX_PERFORMANCE] = "performance",
	[EPP_INDEX_BALANCE_PERFORMANCE] = "balance_performance",
	[EPP_INDEX_BALANCE_POWERSAVE] = "balance_power",
	[EPP_INDEX_POWERSAVE] = "power",
	NULL
};
static unsigned int epp_values[] = {
	[EPP_INDEX_DEFAULT] = 0, /* Unused index */
	[EPP_INDEX_PERFORMANCE] = HWP_EPP_PERFORMANCE,
	[EPP_INDEX_BALANCE_PERFORMANCE] = HWP_EPP_BALANCE_PERFORMANCE,
	[EPP_INDEX_BALANCE_POWERSAVE] = HWP_EPP_BALANCE_POWERSAVE,
	[EPP_INDEX_POWERSAVE] = HWP_EPP_POWERSAVE,
};

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

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

	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
		if (epp == epp_values[EPP_INDEX_PERFORMANCE])
			return EPP_INDEX_PERFORMANCE;
		if (epp == epp_values[EPP_INDEX_BALANCE_PERFORMANCE])
			return EPP_INDEX_BALANCE_PERFORMANCE;
		if (epp == epp_values[EPP_INDEX_BALANCE_POWERSAVE])
			return EPP_INDEX_BALANCE_POWERSAVE;
		if (epp == epp_values[EPP_INDEX_POWERSAVE])
			return EPP_INDEX_POWERSAVE;
		*raw_epp = epp;
		return 0;
	} else if (boot_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_epp(struct cpudata *cpu, u32 epp)
{
	int ret;

	/*
	 * Use the cached HWP Request MSR value, because in the active mode the
	 * register itself may be updated by intel_pstate_hwp_boost_up() or
	 * intel_pstate_hwp_boost_down() at any time.
	 */
	u64 value = READ_ONCE(cpu->hwp_req_cached);

	value &= ~GENMASK_ULL(31, 24);
	value |= (u64)epp << 24;
	/*
	 * The only other updater of hwp_req_cached in the active mode,
	 * intel_pstate_hwp_set(), is called under the same lock as this
	 * function, so it cannot run in parallel with the update below.
	 */
	WRITE_ONCE(cpu->hwp_req_cached, value);
	ret = wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
	if (!ret)
		cpu->epp_cached = epp;

	return ret;
}

static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
					      int pref_index, bool use_raw,
					      u32 raw_epp)
{
	int epp = -EINVAL;
	int ret;

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

	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
		if (use_raw)
			epp = raw_epp;
		else if (epp == -EINVAL)
			epp = epp_values[pref_index];

		/*
		 * To avoid confusion, refuse to set EPP to any values different
		 * from 0 (performance) if the current policy is "performance",
		 * because those values would be overridden.
		 */
		if (epp > 0 && cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
			return -EBUSY;

		ret = intel_pstate_set_epp(cpu_data, epp);
	} else {
		if (epp == -EINVAL)
			epp = (pref_index - 1) << 2;
		ret = intel_pstate_set_epb(cpu_data->cpu, epp);
	}

	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 struct cpufreq_driver intel_pstate;

static ssize_t store_energy_performance_preference(
		struct cpufreq_policy *policy, const char *buf, size_t count)
{
	struct cpudata *cpu = all_cpu_data[policy->cpu];
	char str_preference[21];
	bool raw = false;
	ssize_t ret;
	u32 epp = 0;

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

	ret = match_string(energy_perf_strings, -1, str_preference);
	if (ret < 0) {
		if (!boot_cpu_has(X86_FEATURE_HWP_EPP))
			return ret;

		ret = kstrtouint(buf, 10, &epp);
		if (ret)
			return ret;

		if (epp > 255)
			return -EINVAL;

		raw = true;
	}

	/*
	 * This function runs with the policy R/W semaphore held, which
	 * guarantees that the driver pointer will not change while it is
	 * running.
	 */
	if (!intel_pstate_driver)
		return -EAGAIN;

	mutex_lock(&intel_pstate_limits_lock);

	if (intel_pstate_driver == &intel_pstate) {
		ret = intel_pstate_set_energy_pref_index(cpu, ret, raw, epp);
	} else {
		/*
		 * In the passive mode the governor needs to be stopped on the
		 * target CPU before the EPP update and restarted after it,
		 * which is super-heavy-weight, so make sure it is worth doing
		 * upfront.
		 */
		if (!raw)
			epp = ret ? epp_values[ret] : cpu->epp_default;

		if (cpu->epp_cached != epp) {
			int err;

			cpufreq_stop_governor(policy);
			ret = intel_pstate_set_epp(cpu, epp);
			err = cpufreq_start_governor(policy);
			if (!ret)
				ret = err;
		} else {
			ret = 0;
		}
	}

	mutex_unlock(&intel_pstate_limits_lock);

	return ret ?: count;
}

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

	preference = intel_pstate_get_energy_pref_index(cpu_data, &raw_epp);
	if (preference < 0)
		return preference;

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

cpufreq_freq_attr_rw(energy_performance_preference);

static ssize_t show_base_frequency(struct cpufreq_policy *policy, char *buf)
{
	struct cpudata *cpu = all_cpu_data[policy->cpu];
	int ratio, freq;

	ratio = intel_pstate_get_cppc_guaranteed(policy->cpu);
	if (ratio <= 0) {
		u64 cap;

		rdmsrl_on_cpu(policy->cpu, MSR_HWP_CAPABILITIES, &cap);
		ratio = HWP_GUARANTEED_PERF(cap);
	}

	freq = ratio * cpu->pstate.scaling;
	if (cpu->pstate.scaling != cpu->pstate.perf_ctl_scaling)
		freq = rounddown(freq, cpu->pstate.perf_ctl_scaling);

	return sprintf(buf, "%d\n", freq);
}

cpufreq_freq_attr_ro(base_frequency);

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

static void __intel_pstate_get_hwp_cap(struct cpudata *cpu)
{
	u64 cap;

	rdmsrl_on_cpu(cpu->cpu, MSR_HWP_CAPABILITIES, &cap);
	WRITE_ONCE(cpu->hwp_cap_cached, cap);
	cpu->pstate.max_pstate = HWP_GUARANTEED_PERF(cap);
	cpu->pstate.turbo_pstate = HWP_HIGHEST_PERF(cap);
}

static void intel_pstate_get_hwp_cap(struct cpudata *cpu)
{
	int scaling = cpu->pstate.scaling;

	__intel_pstate_get_hwp_cap(cpu);

	cpu->pstate.max_freq = cpu->pstate.max_pstate * scaling;
	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * scaling;
	if (scaling != cpu->pstate.perf_ctl_scaling) {
		int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;

		cpu->pstate.max_freq = rounddown(cpu->pstate.max_freq,
						 perf_ctl_scaling);
		cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_freq,
						   perf_ctl_scaling);
	}
}

static void intel_pstate_hwp_set(unsigned int cpu)
{
	struct cpudata *cpu_data = all_cpu_data[cpu];
	int max, min;
	u64 value;
	s16 epp;

	max = cpu_data->max_perf_ratio;
	min = cpu_data->min_perf_ratio;

	if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
		min = max;

	rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);

	value &= ~HWP_MIN_PERF(~0L);
	value |= HWP_MIN_PERF(min);

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

static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata);

static void intel_pstate_hwp_offline(struct cpudata *cpu)
{
	u64 value = READ_ONCE(cpu->hwp_req_cached);
	int min_perf;

	intel_pstate_disable_hwp_interrupt(cpu);

	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
		/*
		 * In case the EPP has been set to "performance" by the
		 * active mode "performance" scaling algorithm, replace that
		 * temporary value with the cached EPP one.
		 */
		value &= ~GENMASK_ULL(31, 24);
		value |= HWP_ENERGY_PERF_PREFERENCE(cpu->epp_cached);
		/*
		 * However, make sure that EPP will be set to "performance" when
		 * the CPU is brought back online again and the "performance"
		 * scaling algorithm is still in effect.
		 */
		cpu->epp_policy = CPUFREQ_POLICY_UNKNOWN;
	}

	/*
	 * Clear the desired perf field in the cached HWP request value to
	 * prevent nonzero desired values from being leaked into the active
	 * mode.
	 */
	value &= ~HWP_DESIRED_PERF(~0L);
	WRITE_ONCE(cpu->hwp_req_cached, value);

	value &= ~GENMASK_ULL(31, 0);
	min_perf = HWP_LOWEST_PERF(READ_ONCE(cpu->hwp_cap_cached));

	/* Set hwp_max = hwp_min */
	value |= HWP_MAX_PERF(min_perf);
	value |= HWP_MIN_PERF(min_perf);

	/* Set EPP to min */
	if (boot_cpu_has(X86_FEATURE_HWP_EPP))
		value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE);

	wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
}

#define POWER_CTL_EE_ENABLE	1
#define POWER_CTL_EE_DISABLE	2

static int power_ctl_ee_state;

static void set_power_ctl_ee_state(bool input)
{
	u64 power_ctl;

	mutex_lock(&intel_pstate_driver_lock);
	rdmsrl(MSR_IA32_POWER_CTL, power_ctl);
	if (input) {
		power_ctl &= ~BIT(MSR_IA32_POWER_CTL_BIT_EE);
		power_ctl_ee_state = POWER_CTL_EE_ENABLE;
	} else {
		power_ctl |= BIT(MSR_IA32_POWER_CTL_BIT_EE);
		power_ctl_ee_state = POWER_CTL_EE_DISABLE;
	}
	wrmsrl(MSR_IA32_POWER_CTL, power_ctl);
	mutex_unlock(&intel_pstate_driver_lock);
}

static void intel_pstate_hwp_enable(struct cpudata *cpudata);

static void intel_pstate_hwp_reenable(struct cpudata *cpu)
{
	intel_pstate_hwp_enable(cpu);
	wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, READ_ONCE(cpu->hwp_req_cached));
}

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

	pr_debug("CPU %d suspending\n", cpu->cpu);

	cpu->suspended = true;

	/* disable HWP interrupt and cancel any pending work */
	intel_pstate_disable_hwp_interrupt(cpu);

	return 0;
}

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

	pr_debug("CPU %d resuming\n", cpu->cpu);

	/* Only restore if the system default is changed */
	if (power_ctl_ee_state == POWER_CTL_EE_ENABLE)
		set_power_ctl_ee_state(true);
	else if (power_ctl_ee_state == POWER_CTL_EE_DISABLE)
		set_power_ctl_ee_state(false);

	if (cpu->suspended && hwp_active) {
		mutex_lock(&intel_pstate_limits_lock);

		/* Re-enable HWP, because "online" has not done that. */
		intel_pstate_hwp_reenable(cpu);

		mutex_unlock(&intel_pstate_limits_lock);
	}

	cpu->suspended = false;

	return 0;
}

static void intel_pstate_update_policies(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		cpufreq_update_policy(cpu);
}

static void __intel_pstate_update_max_freq(struct cpudata *cpudata,
					   struct cpufreq_policy *policy)
{
	policy->cpuinfo.max_freq = global.turbo_disabled_mf ?
			cpudata->pstate.max_freq : cpudata->pstate.turbo_freq;
	refresh_frequency_limits(policy);
}

static void intel_pstate_update_max_freq(unsigned int cpu)
{
	struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu);

	if (!policy)
		return;

	__intel_pstate_update_max_freq(all_cpu_data[cpu], policy);

	cpufreq_cpu_release(policy);
}

static void intel_pstate_update_limits(unsigned int cpu)
{
	mutex_lock(&intel_pstate_driver_lock);

	update_turbo_state();
	/*
	 * If turbo has been turned on or off globally, policy limits for
	 * all CPUs need to be updated to reflect that.
	 */
	if (global.turbo_disabled_mf != global.turbo_disabled) {
		global.turbo_disabled_mf = global.turbo_disabled;
		arch_set_max_freq_ratio(global.turbo_disabled);
		for_each_possible_cpu(cpu)
			intel_pstate_update_max_freq(cpu);
	} else {
		cpufreq_update_policy(cpu);
	}

	mutex_unlock(&intel_pstate_driver_lock);
}

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

static ssize_t intel_pstate_show_status(char *buf);
static int intel_pstate_update_status(const char *buf, size_t size);

static ssize_t show_status(struct kobject *kobj,
			   struct kobj_attribute *attr, char *buf)
{
	ssize_t ret;

	mutex_lock(&intel_pstate_driver_lock);
	ret = intel_pstate_show_status(buf);
	mutex_unlock(&intel_pstate_driver_lock);

	return ret;
}

static ssize_t store_status(struct kobject *a, struct kobj_attribute *b,
			    const char *buf, size_t count)
{
	char *p = memchr(buf, '\n', count);
	int ret;

	mutex_lock(&intel_pstate_driver_lock);
	ret = intel_pstate_update_status(buf, p ? p - buf : count);
	mutex_unlock(&intel_pstate_driver_lock);

	return ret < 0 ? ret : count;
}

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

	mutex_lock(&intel_pstate_driver_lock);

	if (!intel_pstate_driver) {
		mutex_unlock(&intel_pstate_driver_lock);
		return -EAGAIN;
	}

	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)));

	mutex_unlock(&intel_pstate_driver_lock);

	return sprintf(buf, "%u\n", turbo_pct);
}

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

	mutex_lock(&intel_pstate_driver_lock);

	if (!intel_pstate_driver) {
		mutex_unlock(&intel_pstate_driver_lock);
		return -EAGAIN;
	}

	cpu = all_cpu_data[0];
	total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1;

	mutex_unlock(&intel_pstate_driver_lock);

	return sprintf(buf, "%u\n", total);
}

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

	mutex_lock(&intel_pstate_driver_lock);

	if (!intel_pstate_driver) {
		mutex_unlock(&intel_pstate_driver_lock);
		return -EAGAIN;
	}

	update_turbo_state();
	if (global.turbo_disabled)
		ret = sprintf(buf, "%u\n", global.turbo_disabled);
	else
		ret = sprintf(buf, "%u\n", global.no_turbo);

	mutex_unlock(&intel_pstate_driver_lock);

	return ret;
}

static ssize_t store_no_turbo(struct kobject *a, struct kobj_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_driver_lock);

	if (!intel_pstate_driver) {
		mutex_unlock(&intel_pstate_driver_lock);
		return -EAGAIN;
	}

	mutex_lock(&intel_pstate_limits_lock);

	update_turbo_state();
	if (global.turbo_disabled) {
		pr_notice_once("Turbo disabled by BIOS or unavailable on processor\n");
		mutex_unlock(&intel_pstate_limits_lock);
		mutex_unlock(&intel_pstate_driver_lock);
		return -EPERM;
	}

	global.no_turbo = clamp_t(int, input, 0, 1);

	if (global.no_turbo) {
		struct cpudata *cpu = all_cpu_data[0];
		int pct = cpu->pstate.max_pstate * 100 / cpu->pstate.turbo_pstate;

		/* Squash the global minimum into the permitted range. */
		if (global.min_perf_pct > pct)
			global.min_perf_pct = pct;
	}

	mutex_unlock(&intel_pstate_limits_lock);

	intel_pstate_update_policies();
	arch_set_max_freq_ratio(global.no_turbo);

	mutex_unlock(&intel_pstate_driver_lock);

	return count;
}

static void update_qos_request(enum freq_qos_req_type type)
{
	struct freq_qos_request *req;
	struct cpufreq_policy *policy;
	int i;

	for_each_possible_cpu(i) {
		struct cpudata *cpu = all_cpu_data[i];
		unsigned int freq, perf_pct;

		policy = cpufreq_cpu_get(i);
		if (!policy)
			continue;

		req = policy->driver_data;
		cpufreq_cpu_put(policy);

		if (!req)
			continue;

		if (hwp_active)
			intel_pstate_get_hwp_cap(cpu);

		if (type == FREQ_QOS_MIN) {
			perf_pct = global.min_perf_pct;
		} else {
			req++;
			perf_pct = global.max_perf_pct;
		}

		freq = DIV_ROUND_UP(cpu->pstate.turbo_freq * perf_pct, 100);

		if (freq_qos_update_request(req, freq) < 0)
			pr_warn("Failed to update freq constraint: CPU%d\n", i);
	}
}

static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_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_driver_lock);

	if (!intel_pstate_driver) {
		mutex_unlock(&intel_pstate_driver_lock);
		return -EAGAIN;
	}

	mutex_lock(&intel_pstate_limits_lock);

	global.max_perf_pct = clamp_t(int, input, global.min_perf_pct, 100);

	mutex_unlock(&intel_pstate_limits_lock);

	if (intel_pstate_driver == &intel_pstate)
		intel_pstate_update_policies();
	else
		update_qos_request(FREQ_QOS_MAX);

	mutex_unlock(&intel_pstate_driver_lock);

	return count;
}

static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_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_driver_lock);

	if (!intel_pstate_driver) {
		mutex_unlock(&intel_pstate_driver_lock);
		return -EAGAIN;
	}

	mutex_lock(&intel_pstate_limits_lock);

	global.min_perf_pct = clamp_t(int, input,
				      min_perf_pct_min(), global.max_perf_pct);

	mutex_unlock(&intel_pstate_limits_lock);

	if (intel_pstate_driver == &intel_pstate)
		intel_pstate_update_policies();
	else
		update_qos_request(FREQ_QOS_MIN);

	mutex_unlock(&intel_pstate_driver_lock);

	return count;
}

static ssize_t show_hwp_dynamic_boost(struct kobject *kobj,
				struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%u\n", hwp_boost);
}

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

	ret = kstrtouint(buf, 10, &input);
	if (ret)
		return ret;

	mutex_lock(&intel_pstate_driver_lock);
	hwp_boost = !!input;
	intel_pstate_update_policies();
	mutex_unlock(&intel_pstate_driver_lock);

	return count;
}

static ssize_t show_energy_efficiency(struct kobject *kobj, struct kobj_attribute *attr,
				      char *buf)
{
	u64 power_ctl;
	int enable;

	rdmsrl(MSR_IA32_POWER_CTL, power_ctl);
	enable = !!(power_ctl & BIT(MSR_IA32_POWER_CTL_BIT_EE));
	return sprintf(buf, "%d\n", !enable);
}

static ssize_t store_energy_efficiency(struct kobject *a, struct kobj_attribute *b,
				       const char *buf, size_t count)
{
	bool input;
	int ret;

	ret = kstrtobool(buf, &input);
	if (ret)
		return ret;

	set_power_ctl_ee_state(input);

	return count;
}

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

define_one_global_rw(status);
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);
define_one_global_rw(hwp_dynamic_boost);
define_one_global_rw(energy_efficiency);

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

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

static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[];

static struct kobject *intel_pstate_kobject;

static void __init intel_pstate_sysfs_expose_params(void)
{
	struct device *dev_root = bus_get_dev_root(&cpu_subsys);
	int rc;

	if (dev_root) {
		intel_pstate_kobject = kobject_create_and_add("intel_pstate", &dev_root->kobj);
		put_device(dev_root);
	}
	if (WARN_ON(!intel_pstate_kobject))
		return;

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

	if (!boot_cpu_has(X86_FEATURE_HYBRID_CPU)) {
		rc = sysfs_create_file(intel_pstate_kobject, &turbo_pct.attr);
		WARN_ON(rc);

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

	/*
	 * 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);

	if (x86_match_cpu(intel_pstate_cpu_ee_disable_ids)) {
		rc = sysfs_create_file(intel_pstate_kobject, &energy_efficiency.attr);
		WARN_ON(rc);
	}
}

static void __init intel_pstate_sysfs_remove(void)
{
	if (!intel_pstate_kobject)
		return;

	sysfs_remove_group(intel_pstate_kobject, &intel_pstate_attr_group);

	if (!boot_cpu_has(X86_FEATURE_HYBRID_CPU)) {
		sysfs_remove_file(intel_pstate_kobject, &num_pstates.attr);
		sysfs_remove_file(intel_pstate_kobject, &turbo_pct.attr);
	}

	if (!per_cpu_limits) {
		sysfs_remove_file(intel_pstate_kobject, &max_perf_pct.attr);
		sysfs_remove_file(intel_pstate_kobject, &min_perf_pct.attr);

		if (x86_match_cpu(intel_pstate_cpu_ee_disable_ids))
			sysfs_remove_file(intel_pstate_kobject, &energy_efficiency.attr);
	}

	kobject_put(intel_pstate_kobject);
}

static void intel_pstate_sysfs_expose_hwp_dynamic_boost(void)
{
	int rc;

	if (!hwp_active)
		return;

	rc = sysfs_create_file(intel_pstate_kobject, &hwp_dynamic_boost.attr);
	WARN_ON_ONCE(rc);
}

static void intel_pstate_sysfs_hide_hwp_dynamic_boost(void)
{
	if (!hwp_active)
		return;

	sysfs_remove_file(intel_pstate_kobject, &hwp_dynamic_boost.attr);
}

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

static void intel_pstate_notify_work(struct work_struct *work)
{
	struct cpudata *cpudata =
		container_of(to_delayed_work(work), struct cpudata, hwp_notify_work);
	struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpudata->cpu);

	if (policy) {
		intel_pstate_get_hwp_cap(cpudata);
		__intel_pstate_update_max_freq(cpudata, policy);

		cpufreq_cpu_release(policy);
	}

	wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0);
}

static DEFINE_SPINLOCK(hwp_notify_lock);
static cpumask_t hwp_intr_enable_mask;

void notify_hwp_interrupt(void)
{
	unsigned int this_cpu = smp_processor_id();
	struct cpudata *cpudata;
	unsigned long flags;
	u64 value;

	if (!READ_ONCE(hwp_active) || !boot_cpu_has(X86_FEATURE_HWP_NOTIFY))
		return;

	rdmsrl_safe(MSR_HWP_STATUS, &value);
	if (!(value & 0x01))
		return;

	spin_lock_irqsave(&hwp_notify_lock, flags);

	if (!cpumask_test_cpu(this_cpu, &hwp_intr_enable_mask))
		goto ack_intr;

	/*
	 * Currently we never free all_cpu_data. And we can't reach here
	 * without this allocated. But for safety for future changes, added
	 * check.
	 */
	if (unlikely(!READ_ONCE(all_cpu_data)))
		goto ack_intr;

	/*
	 * The free is done during cleanup, when cpufreq registry is failed.
	 * We wouldn't be here if it fails on init or switch status. But for
	 * future changes, added check.
	 */
	cpudata = READ_ONCE(all_cpu_data[this_cpu]);
	if (unlikely(!cpudata))
		goto ack_intr;

	schedule_delayed_work(&cpudata->hwp_notify_work, msecs_to_jiffies(10));

	spin_unlock_irqrestore(&hwp_notify_lock, flags);

	return;

ack_intr:
	wrmsrl_safe(MSR_HWP_STATUS, 0);
	spin_unlock_irqrestore(&hwp_notify_lock, flags);
}

static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata)
{
	unsigned long flags;

	if (!boot_cpu_has(X86_FEATURE_HWP_NOTIFY))
		return;

	/* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */
	wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);

	spin_lock_irqsave(&hwp_notify_lock, flags);
	if (cpumask_test_and_clear_cpu(cpudata->cpu, &hwp_intr_enable_mask))
		cancel_delayed_work(&cpudata->hwp_notify_work);
	spin_unlock_irqrestore(&hwp_notify_lock, flags);
}

static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata)
{
	/* Enable HWP notification interrupt for guaranteed performance change */
	if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) {
		unsigned long flags;

		spin_lock_irqsave(&hwp_notify_lock, flags);
		INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work);
		cpumask_set_cpu(cpudata->cpu, &hwp_intr_enable_mask);
		spin_unlock_irqrestore(&hwp_notify_lock, flags);

		/* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */
		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01);
		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0);
	}
}

static void intel_pstate_update_epp_defaults(struct cpudata *cpudata)
{
	cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);

	/*
	 * If this CPU gen doesn't call for change in balance_perf
	 * EPP return.
	 */
	if (epp_values[EPP_INDEX_BALANCE_PERFORMANCE] == HWP_EPP_BALANCE_PERFORMANCE)
		return;

	/*
	 * If the EPP is set by firmware, which means that firmware enabled HWP
	 * - Is equal or less than 0x80 (default balance_perf EPP)
	 * - But less performance oriented than performance EPP
	 *   then use this as new balance_perf EPP.
	 */
	if (hwp_forced && cpudata->epp_default <= HWP_EPP_BALANCE_PERFORMANCE &&
	    cpudata->epp_default > HWP_EPP_PERFORMANCE) {
		epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = cpudata->epp_default;
		return;
	}

	/*
	 * Use hard coded value per gen to update the balance_perf
	 * and default EPP.
	 */
	cpudata->epp_default = epp_values[EPP_INDEX_BALANCE_PERFORMANCE];
	intel_pstate_set_epp(cpudata, cpudata->epp_default);
}

static void intel_pstate_hwp_enable(struct cpudata *cpudata)
{
	/* First disable HWP notification interrupt till we activate again */
	if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY))
		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);

	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);

	intel_pstate_enable_hwp_interrupt(cpudata);

	if (cpudata->epp_default >= 0)
		return;

	intel_pstate_update_epp_defaults(cpudata);
}

static int atom_get_min_pstate(int not_used)
{
	u64 value;

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

static int atom_get_max_pstate(int not_used)
{
	u64 value;

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

static int atom_get_turbo_pstate(int not_used)
{
	u64 value;

	rdmsrl(MSR_ATOM_CORE_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 (global.no_turbo && !global.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(MSR_ATOM_CORE_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(MSR_ATOM_CORE_TURBO_VIDS, value);
	cpudata->vid.turbo = value & 0x7f;
}

static int core_get_min_pstate(int cpu)
{
	u64 value;

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

static int core_get_max_pstate_physical(int cpu)
{
	u64 value;

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

static int core_get_tdp_ratio(int cpu, u64 plat_info)
{
	/* Check how many TDP levels present */
	if (plat_info & 0x600000000) {
		u64 tdp_ctrl;
		u64 tdp_ratio;
		int tdp_msr;
		int err;

		/* Get the TDP level (0, 1, 2) to get ratios */
		err = rdmsrl_safe_on_cpu(cpu, MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
		if (err)
			return err;

		/* TDP MSR are continuous starting at 0x648 */
		tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x03);
		err = rdmsrl_safe_on_cpu(cpu, tdp_msr, &tdp_ratio);
		if (err)
			return err;

		/* For level 1 and 2, bits[23:16] contain the ratio */
		if (tdp_ctrl & 0x03)
			tdp_ratio >>= 16;

		tdp_ratio &= 0xff; /* ratios are only 8 bits long */
		pr_debug("tdp_ratio %x\n", (int)tdp_ratio);

		return (int)tdp_ratio;
	}

	return -ENXIO;
}

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

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

	tdp_ratio = core_get_tdp_ratio(cpu, plat_info);
	if (tdp_ratio <= 0)
		return max_pstate;

	if (hwp_active) {
		/* Turbo activation ratio is not used on HWP platforms */
		return tdp_ratio;
	}

	err = rdmsrl_safe_on_cpu(cpu, MSR_TURBO_ACTIVATION_RATIO, &tar);
	if (!err) {
		int tar_levels;

		/* Do some sanity checking for safety */
		tar_levels = tar & 0xff;
		if (tdp_ratio - 1 == tar_levels) {
			max_pstate = tar_levels;
			pr_debug("max_pstate=TAC %x\n", max_pstate);
		}
	}

	return max_pstate;
}

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

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

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

	val = (u64)pstate << 8;
	if (global.no_turbo && !global.turbo_disabled)
		val |= (u64)1 << 32;

	return val;
}

static int knl_get_aperf_mperf_shift(void)
{
	return 10;
}

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

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

static void hybrid_get_type(void *data)
{
	u8 *cpu_type = data;

	*cpu_type = get_this_hybrid_cpu_type();
}

static int hwp_get_cpu_scaling(int cpu)
{
	u8 cpu_type = 0;

	smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1);
	/* P-cores have a smaller perf level-to-freqency scaling factor. */
	if (cpu_type == 0x40)
		return HYBRID_SCALING_FACTOR;

	/* Use default core scaling for E-cores */
	if (cpu_type == 0x20)
		return core_get_scaling();

	/*
	 * If reached here, this system is either non-hybrid (like Tiger
	 * Lake) or hybrid-capable (like Alder Lake or Raptor Lake) with
	 * no E cores (in which case CPUID for hybrid support is 0).
	 *
	 * The CPPC nominal_frequency field is 0 for non-hybrid systems,
	 * so the default core scaling will be used for them.
	 */
	return intel_pstate_cppc_get_scaling(cpu);
}

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 pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio);

	update_turbo_state();
	intel_pstate_set_pstate(cpu, pstate);
}

static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
{
	int perf_ctl_max_phys = pstate_funcs.get_max_physical(cpu->cpu);
	int perf_ctl_scaling = pstate_funcs.get_scaling();

	cpu->pstate.min_pstate = pstate_funcs.get_min(cpu->cpu);
	cpu->pstate.max_pstate_physical = perf_ctl_max_phys;
	cpu->pstate.perf_ctl_scaling = perf_ctl_scaling;

	if (hwp_active && !hwp_mode_bdw) {
		__intel_pstate_get_hwp_cap(cpu);

		if (pstate_funcs.get_cpu_scaling) {
			cpu->pstate.scaling = pstate_funcs.get_cpu_scaling(cpu->cpu);
			if (cpu->pstate.scaling != perf_ctl_scaling)
				intel_pstate_hybrid_hwp_adjust(cpu);
		} else {
			cpu->pstate.scaling = perf_ctl_scaling;
		}
	} else {
		cpu->pstate.scaling = perf_ctl_scaling;
		cpu->pstate.max_pstate = pstate_funcs.get_max(cpu->cpu);
		cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(cpu->cpu);
	}

	if (cpu->pstate.scaling == perf_ctl_scaling) {
		cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling;
		cpu->pstate.max_freq = cpu->pstate.max_pstate * perf_ctl_scaling;
		cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * perf_ctl_scaling;
	}

	if (pstate_funcs.get_aperf_mperf_shift)
		cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift();

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

	intel_pstate_set_min_pstate(cpu);
}

/*
 * Long hold time will keep high perf limits for long time,
 * which negatively impacts perf/watt for some workloads,
 * like specpower. 3ms is based on experiements on some
 * workoads.
 */
static int hwp_boost_hold_time_ns = 3 * NSEC_PER_MSEC;

static inline void intel_pstate_hwp_boost_up(struct cpudata *cpu)
{
	u64 hwp_req = READ_ONCE(cpu->hwp_req_cached);
	u64 hwp_cap = READ_ONCE(cpu->hwp_cap_cached);
	u32 max_limit = (hwp_req & 0xff00) >> 8;
	u32 min_limit = (hwp_req & 0xff);
	u32 boost_level1;

	/*
	 * Cases to consider (User changes via sysfs or boot time):
	 * If, P0 (Turbo max) = P1 (Guaranteed max) = min:
	 *	No boost, return.
	 * If, P0 (Turbo max) > P1 (Guaranteed max) = min:
	 *     Should result in one level boost only for P0.
	 * If, P0 (Turbo max) = P1 (Guaranteed max) > min:
	 *     Should result in two level boost:
	 *         (min + p1)/2 and P1.
	 * If, P0 (Turbo max) > P1 (Guaranteed max) > min:
	 *     Should result in three level boost:
	 *        (min + p1)/2, P1 and P0.
	 */

	/* If max and min are equal or already at max, nothing to boost */
	if (max_limit == min_limit || cpu->hwp_boost_min >= max_limit)
		return;

	if (!cpu->hwp_boost_min)
		cpu->hwp_boost_min = min_limit;

	/* level at half way mark between min and guranteed */
	boost_level1 = (HWP_GUARANTEED_PERF(hwp_cap) + min_limit) >> 1;

	if (cpu->hwp_boost_min < boost_level1)
		cpu->hwp_boost_min = boost_level1;
	else if (cpu->hwp_boost_min < HWP_GUARANTEED_PERF(hwp_cap))
		cpu->hwp_boost_min = HWP_GUARANTEED_PERF(hwp_cap);
	else if (cpu->hwp_boost_min == HWP_GUARANTEED_PERF(hwp_cap) &&
		 max_limit != HWP_GUARANTEED_PERF(hwp_cap))
		cpu->hwp_boost_min = max_limit;
	else
		return;

	hwp_req = (hwp_req & ~GENMASK_ULL(7, 0)) | cpu->hwp_boost_min;
	wrmsrl(MSR_HWP_REQUEST, hwp_req);
	cpu->last_update = cpu->sample.time;
}

static inline void intel_pstate_hwp_boost_down(struct cpudata *cpu)
{
	if (cpu->hwp_boost_min) {
		bool expired;

		/* Check if we are idle for hold time to boost down */
		expired = time_after64(cpu->sample.time, cpu->last_update +
				       hwp_boost_hold_time_ns);
		if (expired) {
			wrmsrl(MSR_HWP_REQUEST, cpu->hwp_req_cached);
			cpu->hwp_boost_min = 0;
		}
	}
	cpu->last_update = cpu->sample.time;
}

static inline void intel_pstate_update_util_hwp_local(struct cpudata *cpu,
						      u64 time)
{
	cpu->sample.time = time;

	if (cpu->sched_flags & SCHED_CPUFREQ_IOWAIT) {
		bool do_io = false;

		cpu->sched_flags = 0;
		/*
		 * Set iowait_boost flag and update time. Since IO WAIT flag
		 * is set all the time, we can't just conclude that there is
		 * some IO bound activity is scheduled on this CPU with just
		 * one occurrence. If we receive at least two in two
		 * consecutive ticks, then we treat as boost candidate.
		 */
		if (time_before64(time, cpu->last_io_update + 2 * TICK_NSEC))
			do_io = true;

		cpu->last_io_update = time;

		if (do_io)
			intel_pstate_hwp_boost_up(cpu);

	} else {
		intel_pstate_hwp_boost_down(cpu);
	}
}

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

	cpu->sched_flags |= flags;

	if (smp_processor_id() == cpu->cpu)
		intel_pstate_update_util_hwp_local(cpu, time);
}

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.
	 */
	if (cpu->last_sample_time) {
		intel_pstate_calc_avg_perf(cpu);
		return true;
	}
	return false;
}

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

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

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

	if (busy_frac < cpu->iowait_boost)
		busy_frac = cpu->iowait_boost;

	sample->busy_scaled = busy_frac * 100;

	target = global.no_turbo || global.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 int intel_pstate_prepare_request(struct cpudata *cpu, int pstate)
{
	int min_pstate = max(cpu->pstate.min_pstate, cpu->min_perf_ratio);
	int max_pstate = max(min_pstate, cpu->max_perf_ratio);

	return clamp_t(int, pstate, min_pstate, max_pstate);
}

static void intel_pstate_update_pstate(struct cpudata *cpu, int 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 void intel_pstate_adjust_pstate(struct cpudata *cpu)
{
	int from = cpu->pstate.current_pstate;
	struct sample *sample;
	int target_pstate;

	update_turbo_state();

	target_pstate = get_target_pstate(cpu);
	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
	trace_cpu_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu);
	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;

	/* Don't allow remote callbacks */
	if (smp_processor_id() != cpu->cpu)
		return;

	delta_ns = time - cpu->last_update;
	if (flags & SCHED_CPUFREQ_IOWAIT) {
		/* Start over if the CPU may have been idle. */
		if (delta_ns > TICK_NSEC) {
			cpu->iowait_boost = ONE_EIGHTH_FP;
		} else if (cpu->iowait_boost >= ONE_EIGHTH_FP) {
			cpu->iowait_boost <<= 1;
			if (cpu->iowait_boost > int_tofp(1))
				cpu->iowait_boost = int_tofp(1);
		} else {
			cpu->iowait_boost = ONE_EIGHTH_FP;
		}
	} else if (cpu->iowait_boost) {
		/* Clear iowait_boost if the CPU may have been idle. */
		if (delta_ns > TICK_NSEC)
			cpu->iowait_boost = 0;
		else
			cpu->iowait_boost >>= 1;
	}
	cpu->last_update = time;
	delta_ns = time - cpu->sample.time;
	if ((s64)delta_ns < INTEL_PSTATE_SAMPLING_INTERVAL)
		return;

	if (intel_pstate_sample(cpu, time))
		intel_pstate_adjust_pstate(cpu);
}

static struct pstate_funcs core_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,
};

static const struct pstate_funcs silvermont_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,
};

static const struct pstate_funcs airmont_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,
};

static const struct pstate_funcs knl_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_aperf_mperf_shift = knl_get_aperf_mperf_shift,
	.get_scaling = core_get_scaling,
	.get_val = core_get_val,
};

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

static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
	X86_MATCH(SANDYBRIDGE,		core_funcs),
	X86_MATCH(SANDYBRIDGE_X,	core_funcs),
	X86_MATCH(ATOM_SILVERMONT,	silvermont_funcs),
	X86_MATCH(IVYBRIDGE,		core_funcs),
	X86_MATCH(HASWELL,		core_funcs),
	X86_MATCH(BROADWELL,		core_funcs),
	X86_MATCH(IVYBRIDGE_X,		core_funcs),
	X86_MATCH(HASWELL_X,		core_funcs),
	X86_MATCH(HASWELL_L,		core_funcs),
	X86_MATCH(HASWELL_G,		core_funcs),
	X86_MATCH(BROADWELL_G,		core_funcs),
	X86_MATCH(ATOM_AIRMONT,		airmont_funcs),
	X86_MATCH(SKYLAKE_L,		core_funcs),
	X86_MATCH(BROADWELL_X,		core_funcs),
	X86_MATCH(SKYLAKE,		core_funcs),
	X86_MATCH(BROADWELL_D,		core_funcs),
	X86_MATCH(XEON_PHI_KNL,		knl_funcs),
	X86_MATCH(XEON_PHI_KNM,		knl_funcs),
	X86_MATCH(ATOM_GOLDMONT,	core_funcs),
	X86_MATCH(ATOM_GOLDMONT_PLUS,	core_funcs),
	X86_MATCH(SKYLAKE_X,		core_funcs),
	X86_MATCH(COMETLAKE,		core_funcs),
	X86_MATCH(ICELAKE_X,		core_funcs),
	X86_MATCH(TIGERLAKE,		core_funcs),
	X86_MATCH(SAPPHIRERAPIDS_X,	core_funcs),
	{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);

static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
	X86_MATCH(BROADWELL_D,		core_funcs),
	X86_MATCH(BROADWELL_X,		core_funcs),
	X86_MATCH(SKYLAKE_X,		core_funcs),
	X86_MATCH(ICELAKE_X,		core_funcs),
	X86_MATCH(SAPPHIRERAPIDS_X,	core_funcs),
	{}
};

static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
	X86_MATCH(KABYLAKE,		core_funcs),
	{}
};

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

	cpu = all_cpu_data[cpunum];

	if (!cpu) {
		cpu = kzalloc(sizeof(*cpu), GFP_KERNEL);
		if (!cpu)
			return -ENOMEM;

		WRITE_ONCE(all_cpu_data[cpunum], cpu);

		cpu->cpu = cpunum;

		cpu->epp_default = -EINVAL;

		if (hwp_active) {
			intel_pstate_hwp_enable(cpu);

			if (intel_pstate_acpi_pm_profile_server())
				hwp_boost = true;
		}
	} else if (hwp_active) {
		/*
		 * Re-enable HWP in case this happens after a resume from ACPI
		 * S3 if the CPU was offline during the whole system/resume
		 * cycle.
		 */
		intel_pstate_hwp_reenable(cpu);
	}

	cpu->epp_powersave = -EINVAL;
	cpu->epp_policy = 0;

	intel_pstate_get_cpu_pstates(cpu);

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

	return 0;
}

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

	if (hwp_active && !hwp_boost)
		return;

	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,
				     (hwp_active ?
				      intel_pstate_update_util_hwp :
				      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_rcu();
}

static int intel_pstate_get_max_freq(struct cpudata *cpu)
{
	return global.turbo_disabled || global.no_turbo ?
			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
}

static void intel_pstate_update_perf_limits(struct cpudata *cpu,
					    unsigned int policy_min,
					    unsigned int policy_max)
{
	int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
	int32_t max_policy_perf, min_policy_perf;

	max_policy_perf = policy_max / perf_ctl_scaling;
	if (policy_max == policy_min) {
		min_policy_perf = max_policy_perf;
	} else {
		min_policy_perf = policy_min / perf_ctl_scaling;
		min_policy_perf = clamp_t(int32_t, min_policy_perf,
					  0, max_policy_perf);
	}

	/*
	 * HWP needs some special consideration, because HWP_REQUEST uses
	 * abstract values to represent performance rather than pure ratios.
	 */
	if (hwp_active && cpu->pstate.scaling != perf_ctl_scaling) {
		int scaling = cpu->pstate.scaling;
		int freq;

		freq = max_policy_perf * perf_ctl_scaling;
		max_policy_perf = DIV_ROUND_UP(freq, scaling);
		freq = min_policy_perf * perf_ctl_scaling;
		min_policy_perf = DIV_ROUND_UP(freq, scaling);
	}

	pr_debug("cpu:%d min_policy_perf:%d max_policy_perf:%d\n",
		 cpu->cpu, min_policy_perf, max_policy_perf);

	/* Normalize user input to [min_perf, max_perf] */
	if (per_cpu_limits) {
		cpu->min_perf_ratio = min_policy_perf;
		cpu->max_perf_ratio = max_policy_perf;
	} else {
		int turbo_max = cpu->pstate.turbo_pstate;
		int32_t global_min, global_max;

		/* Global limits are in percent of the maximum turbo P-state. */
		global_max = DIV_ROUND_UP(turbo_max * global.max_perf_pct, 100);
		global_min = DIV_ROUND_UP(turbo_max * global.min_perf_pct, 100);
		global_min = clamp_t(int32_t, global_min, 0, global_max);

		pr_debug("cpu:%d global_min:%d global_max:%d\n", cpu->cpu,
			 global_min, global_max);

		cpu->min_perf_ratio = max(min_policy_perf, global_min);
		cpu->min_perf_ratio = min(cpu->min_perf_ratio, max_policy_perf);
		cpu->max_perf_ratio = min(max_policy_perf, global_max);
		cpu->max_perf_ratio = max(min_policy_perf, cpu->max_perf_ratio);

		/* Make sure min_perf <= max_perf */
		cpu->min_perf_ratio = min(cpu->min_perf_ratio,
					  cpu->max_perf_ratio);

	}
	pr_debug("cpu:%d max_perf_ratio:%d min_perf_ratio:%d\n", cpu->cpu,
		 cpu->max_perf_ratio,
		 cpu->min_perf_ratio);
}

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

	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;

	mutex_lock(&intel_pstate_limits_lock);

	intel_pstate_update_perf_limits(cpu, policy->min, policy->max);

	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);
	} else {
		intel_pstate_set_update_util_hook(policy->cpu);
	}

	if (hwp_active) {
		/*
		 * When hwp_boost was active before and dynamically it
		 * was turned off, in that case we need to clear the
		 * update util hook.
		 */
		if (!hwp_boost)
			intel_pstate_clear_update_util_hook(policy->cpu);
		intel_pstate_hwp_set(policy->cpu);
	}
	/*
	 * policy->cur is never updated with the intel_pstate driver, but it
	 * is used as a stale frequency value. So, keep it within limits.
	 */
	policy->cur = policy->min;

	mutex_unlock(&intel_pstate_limits_lock);

	return 0;
}

static void intel_pstate_adjust_policy_max(struct cpudata *cpu,
					   struct cpufreq_policy_data *policy)
{
	if (!hwp_active &&
	    cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
	    policy->max < policy->cpuinfo.max_freq &&
	    policy->max > cpu->pstate.max_freq) {
		pr_debug("policy->max > max non turbo frequency\n");
		policy->max = policy->cpuinfo.max_freq;
	}
}

static void intel_pstate_verify_cpu_policy(struct cpudata *cpu,
					   struct cpufreq_policy_data *policy)
{
	int max_freq;

	update_turbo_state();
	if (hwp_active) {
		intel_pstate_get_hwp_cap(cpu);
		max_freq = global.no_turbo || global.turbo_disabled ?
				cpu->pstate.max_freq : cpu->pstate.turbo_freq;
	} else {
		max_freq = intel_pstate_get_max_freq(cpu);
	}
	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, max_freq);

	intel_pstate_adjust_policy_max(cpu, policy);
}

static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy)
{
	intel_pstate_verify_cpu_policy(all_cpu_data[policy->cpu], policy);

	return 0;
}

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

	pr_debug("CPU %d going offline\n", cpu->cpu);

	if (cpu->suspended)
		return 0;

	/*
	 * If the CPU is an SMT thread and it goes offline with the performance
	 * settings different from the minimum, it will prevent its sibling
	 * from getting to lower performance levels, so force the minimum
	 * performance on CPU offline to prevent that from happening.
	 */
	if (hwp_active)
		intel_pstate_hwp_offline(cpu);
	else
		intel_pstate_set_min_pstate(cpu);

	intel_pstate_exit_perf_limits(policy);

	return 0;
}

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

	pr_debug("CPU %d going online\n", cpu->cpu);

	intel_pstate_init_acpi_perf_limits(policy);

	if (hwp_active) {
		/*
		 * Re-enable HWP and clear the "suspended" flag to let "resume"
		 * know that it need not do that.
		 */
		intel_pstate_hwp_reenable(cpu);
		cpu->suspended = false;
	}

	return 0;
}

static int intel_pstate_cpu_offline(struct cpufreq_policy *policy)
{
	intel_pstate_clear_update_util_hook(policy->cpu);

	return intel_cpufreq_cpu_offline(policy);
}

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

	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];

	cpu->max_perf_ratio = 0xFF;
	cpu->min_perf_ratio = 0;

	/* cpuinfo and default policy values */
	policy->cpuinfo.min_freq = cpu->pstate.min_freq;
	update_turbo_state();
	global.turbo_disabled_mf = global.turbo_disabled;
	policy->cpuinfo.max_freq = global.turbo_disabled ?
			cpu->pstate.max_freq : cpu->pstate.turbo_freq;

	policy->min = policy->cpuinfo.min_freq;
	policy->max = policy->cpuinfo.max_freq;

	intel_pstate_init_acpi_perf_limits(policy);

	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;

	/*
	 * Set the policy to powersave to provide a valid fallback value in case
	 * the default cpufreq governor is neither powersave nor performance.
	 */
	policy->policy = CPUFREQ_POLICY_POWERSAVE;

	if (hwp_active) {
		struct cpudata *cpu = all_cpu_data[policy->cpu];

		cpu->epp_cached = intel_pstate_get_epp(cpu, 0);
	}

	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_suspend,
	.resume		= intel_pstate_resume,
	.init		= intel_pstate_cpu_init,
	.exit		= intel_pstate_cpu_exit,
	.offline	= intel_pstate_cpu_offline,
	.online		= intel_pstate_cpu_online,
	.update_limits	= intel_pstate_update_limits,
	.name		= "intel_pstate",
};

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

	intel_pstate_verify_cpu_policy(cpu, policy);
	intel_pstate_update_perf_limits(cpu, policy->min, policy->max);

	return 0;
}

/* Use of trace in passive mode:
 *
 * In passive mode the trace core_busy field (also known as the
 * performance field, and lablelled as such on the graphs; also known as
 * core_avg_perf) is not needed and so is re-assigned to indicate if the
 * driver call was via the normal or fast switch path. Various graphs
 * output from the intel_pstate_tracer.py utility that include core_busy
 * (or performance or core_avg_perf) have a fixed y-axis from 0 to 100%,
 * so we use 10 to indicate the normal path through the driver, and
 * 90 to indicate the fast switch path through the driver.
 * The scaled_busy field is not used, and is set to 0.
 */

#define	INTEL_PSTATE_TRACE_TARGET 10
#define	INTEL_PSTATE_TRACE_FAST_SWITCH 90

static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, int old_pstate)
{
	struct sample *sample;

	if (!trace_pstate_sample_enabled())
		return;

	if (!intel_pstate_sample(cpu, ktime_get()))
		return;

	sample = &cpu->sample;
	trace_pstate_sample(trace_type,
		0,
		old_pstate,
		cpu->pstate.current_pstate,
		sample->mperf,
		sample->aperf,
		sample->tsc,
		get_avg_frequency(cpu),
		fp_toint(cpu->iowait_boost * 100));
}

static void intel_cpufreq_hwp_update(struct cpudata *cpu, u32 min, u32 max,
				     u32 desired, bool fast_switch)
{
	u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev;

	value &= ~HWP_MIN_PERF(~0L);
	value |= HWP_MIN_PERF(min);

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

	value &= ~HWP_DESIRED_PERF(~0L);
	value |= HWP_DESIRED_PERF(desired);

	if (value == prev)
		return;

	WRITE_ONCE(cpu->hwp_req_cached, value);
	if (fast_switch)
		wrmsrl(MSR_HWP_REQUEST, value);
	else
		wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
}

static void intel_cpufreq_perf_ctl_update(struct cpudata *cpu,
					  u32 target_pstate, bool fast_switch)
{
	if (fast_switch)
		wrmsrl(MSR_IA32_PERF_CTL,
		       pstate_funcs.get_val(cpu, target_pstate));
	else
		wrmsrl_on_cpu(cpu->cpu, MSR_IA32_PERF_CTL,
			      pstate_funcs.get_val(cpu, target_pstate));
}

static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy,
				       int target_pstate, bool fast_switch)
{
	struct cpudata *cpu = all_cpu_data[policy->cpu];
	int old_pstate = cpu->pstate.current_pstate;

	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
	if (hwp_active) {
		int max_pstate = policy->strict_target ?
					target_pstate : cpu->max_perf_ratio;

		intel_cpufreq_hwp_update(cpu, target_pstate, max_pstate, 0,
					 fast_switch);
	} else if (target_pstate != old_pstate) {
		intel_cpufreq_perf_ctl_update(cpu, target_pstate, fast_switch);
	}

	cpu->pstate.current_pstate = target_pstate;

	intel_cpufreq_trace(cpu, fast_switch ? INTEL_PSTATE_TRACE_FAST_SWITCH :
			    INTEL_PSTATE_TRACE_TARGET, old_pstate);

	return target_pstate;
}

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;

	update_turbo_state();

	freqs.old = policy->cur;
	freqs.new = 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_cpufreq_update_pstate(policy, target_pstate, false);

	freqs.new = target_pstate * cpu->pstate.scaling;

	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;

	update_turbo_state();

	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);

	target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true);

	return target_pstate * cpu->pstate.scaling;
}

static void intel_cpufreq_adjust_perf(unsigned int cpunum,
				      unsigned long min_perf,
				      unsigned long target_perf,
				      unsigned long capacity)
{
	struct cpudata *cpu = all_cpu_data[cpunum];
	u64 hwp_cap = READ_ONCE(cpu->hwp_cap_cached);
	int old_pstate = cpu->pstate.current_pstate;
	int cap_pstate, min_pstate, max_pstate, target_pstate;

	update_turbo_state();
	cap_pstate = global.turbo_disabled ? HWP_GUARANTEED_PERF(hwp_cap) :
					     HWP_HIGHEST_PERF(hwp_cap);

	/* Optimization: Avoid unnecessary divisions. */

	target_pstate = cap_pstate;
	if (target_perf < capacity)
		target_pstate = DIV_ROUND_UP(cap_pstate * target_perf, capacity);

	min_pstate = cap_pstate;
	if (min_perf < capacity)
		min_pstate = DIV_ROUND_UP(cap_pstate * min_perf, capacity);

	if (min_pstate < cpu->pstate.min_pstate)
		min_pstate = cpu->pstate.min_pstate;

	if (min_pstate < cpu->min_perf_ratio)
		min_pstate = cpu->min_perf_ratio;

	max_pstate = min(cap_pstate, cpu->max_perf_ratio);
	if (max_pstate < min_pstate)
		max_pstate = min_pstate;

	target_pstate = clamp_t(int, target_pstate, min_pstate, max_pstate);

	intel_cpufreq_hwp_update(cpu, min_pstate, max_pstate, target_pstate, true);

	cpu->pstate.current_pstate = target_pstate;
	intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_FAST_SWITCH, old_pstate);
}

static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
{
	struct freq_qos_request *req;
	struct cpudata *cpu;
	struct device *dev;
	int ret, freq;

	dev = get_cpu_device(policy->cpu);
	if (!dev)
		return -ENODEV;

	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;

	req = kcalloc(2, sizeof(*req), GFP_KERNEL);
	if (!req) {
		ret = -ENOMEM;
		goto pstate_exit;
	}

	cpu = all_cpu_data[policy->cpu];

	if (hwp_active) {
		u64 value;

		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY_HWP;

		intel_pstate_get_hwp_cap(cpu);

		rdmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, &value);
		WRITE_ONCE(cpu->hwp_req_cached, value);

		cpu->epp_cached = intel_pstate_get_epp(cpu, value);
	} else {
		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
	}

	freq = DIV_ROUND_UP(cpu->pstate.turbo_freq * global.min_perf_pct, 100);

	ret = freq_qos_add_request(&policy->constraints, req, FREQ_QOS_MIN,
				   freq);
	if (ret < 0) {
		dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret);
		goto free_req;
	}

	freq = DIV_ROUND_UP(cpu->pstate.turbo_freq * global.max_perf_pct, 100);

	ret = freq_qos_add_request(&policy->constraints, req + 1, FREQ_QOS_MAX,
				   freq);
	if (ret < 0) {
		dev_err(dev, "Failed to add max-freq constraint (%d)\n", ret);
		goto remove_min_req;
	}

	policy->driver_data = req;

	return 0;

remove_min_req:
	freq_qos_remove_request(req);
free_req:
	kfree(req);
pstate_exit:
	intel_pstate_exit_perf_limits(policy);

	return ret;
}

static int intel_cpufreq_cpu_exit(struct cpufreq_policy *policy)
{
	struct freq_qos_request *req;

	req = policy->driver_data;

	freq_qos_remove_request(req + 1);
	freq_qos_remove_request(req);
	kfree(req);

	return intel_pstate_cpu_exit(policy);
}

static int intel_cpufreq_suspend(struct cpufreq_policy *policy)
{
	intel_pstate_suspend(policy);

	if (hwp_active) {
		struct cpudata *cpu = all_cpu_data[policy->cpu];
		u64 value = READ_ONCE(cpu->hwp_req_cached);

		/*
		 * Clear the desired perf field in MSR_HWP_REQUEST in case
		 * intel_cpufreq_adjust_perf() is in use and the last value
		 * written by it may not be suitable.
		 */
		value &= ~HWP_DESIRED_PERF(~0L);
		wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
		WRITE_ONCE(cpu->hwp_req_cached, value);
	}

	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_cpufreq_cpu_exit,
	.offline	= intel_cpufreq_cpu_offline,
	.online		= intel_pstate_cpu_online,
	.suspend	= intel_cpufreq_suspend,
	.resume		= intel_pstate_resume,
	.update_limits	= intel_pstate_update_limits,
	.name		= "intel_cpufreq",
};

static struct cpufreq_driver *default_driver;

static void intel_pstate_driver_cleanup(void)
{
	unsigned int cpu;

	cpus_read_lock();
	for_each_online_cpu(cpu) {
		if (all_cpu_data[cpu]) {
			if (intel_pstate_driver == &intel_pstate)
				intel_pstate_clear_update_util_hook(cpu);

			spin_lock(&hwp_notify_lock);
			kfree(all_cpu_data[cpu]);
			WRITE_ONCE(all_cpu_data[cpu], NULL);
			spin_unlock(&hwp_notify_lock);
		}
	}
	cpus_read_unlock();

	intel_pstate_driver = NULL;
}

static int intel_pstate_register_driver(struct cpufreq_driver *driver)
{
	int ret;

	if (driver == &intel_pstate)
		intel_pstate_sysfs_expose_hwp_dynamic_boost();

	memset(&global, 0, sizeof(global));
	global.max_perf_pct = 100;

	intel_pstate_driver = driver;
	ret = cpufreq_register_driver(intel_pstate_driver);
	if (ret) {
		intel_pstate_driver_cleanup();
		return ret;
	}

	global.min_perf_pct = min_perf_pct_min();

	return 0;
}

static ssize_t intel_pstate_show_status(char *buf)
{
	if (!intel_pstate_driver)
		return sprintf(buf, "off\n");

	return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ?
					"active" : "passive");
}

static int intel_pstate_update_status(const char *buf, size_t size)
{
	if (size == 3 && !strncmp(buf, "off", size)) {
		if (!intel_pstate_driver)
			return -EINVAL;

		if (hwp_active)
			return -EBUSY;

		cpufreq_unregister_driver(intel_pstate_driver);
		intel_pstate_driver_cleanup();
		return 0;
	}

	if (size == 6 && !strncmp(buf, "active", size)) {
		if (intel_pstate_driver) {
			if (intel_pstate_driver == &intel_pstate)
				return 0;

			cpufreq_unregister_driver(intel_pstate_driver);
		}

		return intel_pstate_register_driver(&intel_pstate);
	}

	if (size == 7 && !strncmp(buf, "passive", size)) {
		if (intel_pstate_driver) {
			if (intel_pstate_driver == &intel_cpufreq)
				return 0;

			cpufreq_unregister_driver(intel_pstate_driver);
			intel_pstate_sysfs_hide_hwp_dynamic_boost();
		}

		return intel_pstate_register_driver(&intel_cpufreq);
	}

	return -EINVAL;
}

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(0) ||
	    !pstate_funcs.get_min(0) ||
	    !pstate_funcs.get_turbo(0))
		return -ENODEV;

	return 0;
}

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_aperf_mperf_shift = funcs->get_aperf_mperf_shift;
}

#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);
	}

	pr_debug("ACPI _PSS not found\n");
	return true;
}

static bool __init intel_pstate_no_acpi_pcch(void)
{
	acpi_status status;
	acpi_handle handle;

	status = acpi_get_handle(NULL, "\\_SB", &handle);
	if (ACPI_FAILURE(status))
		goto not_found;

	if (acpi_has_method(handle, "PCCH"))
		return false;

not_found:
	pr_debug("ACPI PCCH not found\n");
	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;
	}
	pr_debug("ACPI _PPC not found\n");
	return false;
}

enum {
	PSS,
	PPC,
};

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

#define BITMASK_OOB	(BIT(8) | BIT(18))

static bool __init intel_pstate_platform_pwr_mgmt_exists(void)
{
	const struct x86_cpu_id *id;
	u64 misc_pwr;
	int idx;

	id = x86_match_cpu(intel_pstate_cpu_oob_ids);
	if (id) {
		rdmsrl(MSR_MISC_PWR_MGMT, misc_pwr);
		if (misc_pwr & BITMASK_OOB) {
			pr_debug("Bit 8 or 18 in the MISC_PWR_MGMT MSR set\n");
			pr_debug("P states are controlled in Out of Band mode by the firmware/hardware\n");
			return true;
		}
	}

	idx = acpi_match_platform_list(plat_info);
	if (idx < 0)
		return false;

	switch (plat_info[idx].data) {
	case PSS:
		if (!intel_pstate_no_acpi_pss())
			return false;

		return intel_pstate_no_acpi_pcch();
	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 */

#define INTEL_PSTATE_HWP_BROADWELL	0x01

#define X86_MATCH_HWP(model, hwp_mode)					\
	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
					   X86_FEATURE_HWP, hwp_mode)

static const struct x86_cpu_id hwp_support_ids[] __initconst = {
	X86_MATCH_HWP(BROADWELL_X,	INTEL_PSTATE_HWP_BROADWELL),
	X86_MATCH_HWP(BROADWELL_D,	INTEL_PSTATE_HWP_BROADWELL),
	X86_MATCH_HWP(ANY,		0),
	{}
};

static bool intel_pstate_hwp_is_enabled(void)
{
	u64 value;

	rdmsrl(MSR_PM_ENABLE, value);
	return !!(value & 0x1);
}

static const struct x86_cpu_id intel_epp_balance_perf[] = {
	/*
	 * Set EPP value as 102, this is the max suggested EPP
	 * which can result in one core turbo frequency for
	 * AlderLake Mobile CPUs.
	 */
	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 102),
	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 32),
	{}
};

static int __init intel_pstate_init(void)
{
	static struct cpudata **_all_cpu_data;
	const struct x86_cpu_id *id;
	int rc;

	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
		return -ENODEV;

	id = x86_match_cpu(hwp_support_ids);
	if (id) {
		hwp_forced = intel_pstate_hwp_is_enabled();

		if (hwp_forced)
			pr_info("HWP enabled by BIOS\n");
		else if (no_load)
			return -ENODEV;

		copy_cpu_funcs(&core_funcs);
		/*
		 * Avoid enabling HWP for processors without EPP support,
		 * because that means incomplete HWP implementation which is a
		 * corner case and supporting it is generally problematic.
		 *
		 * If HWP is enabled already, though, there is no choice but to
		 * deal with it.
		 */
		if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) || hwp_forced) {
			WRITE_ONCE(hwp_active, 1);
			hwp_mode_bdw = id->driver_data;
			intel_pstate.attr = hwp_cpufreq_attrs;
			intel_cpufreq.attr = hwp_cpufreq_attrs;
			intel_cpufreq.flags |= CPUFREQ_NEED_UPDATE_LIMITS;
			intel_cpufreq.adjust_perf = intel_cpufreq_adjust_perf;
			if (!default_driver)
				default_driver = &intel_pstate;

			pstate_funcs.get_cpu_scaling = hwp_get_cpu_scaling;

			goto hwp_cpu_matched;
		}
		pr_info("HWP not enabled\n");
	} else {
		if (no_load)
			return -ENODEV;

		id = x86_match_cpu(intel_pstate_cpu_ids);
		if (!id) {
			pr_info("CPU model not supported\n");
			return -ENODEV;
		}

		copy_cpu_funcs((struct pstate_funcs *)id->driver_data);
	}

	if (intel_pstate_msrs_not_valid()) {
		pr_info("Invalid MSRs\n");
		return -ENODEV;
	}
	/* Without HWP start in the passive mode. */
	if (!default_driver)
		default_driver = &intel_cpufreq;

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()) {
		pr_info("P-states controlled by the platform\n");
		return -ENODEV;
	}

	if (!hwp_active && hwp_only)
		return -ENOTSUPP;

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

	_all_cpu_data = vzalloc(array_size(sizeof(void *), num_possible_cpus()));
	if (!_all_cpu_data)
		return -ENOMEM;

	WRITE_ONCE(all_cpu_data, _all_cpu_data);

	intel_pstate_request_control_from_smm();

	intel_pstate_sysfs_expose_params();

	if (hwp_active) {
		const struct x86_cpu_id *id = x86_match_cpu(intel_epp_balance_perf);

		if (id)
			epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = id->driver_data;
	}

	mutex_lock(&intel_pstate_driver_lock);
	rc = intel_pstate_register_driver(default_driver);
	mutex_unlock(&intel_pstate_driver_lock);
	if (rc) {
		intel_pstate_sysfs_remove();
		return rc;
	}

	if (hwp_active) {
		const struct x86_cpu_id *id;

		id = x86_match_cpu(intel_pstate_cpu_ee_disable_ids);
		if (id) {
			set_power_ctl_ee_state(false);
			pr_info("Disabling energy efficiency optimization\n");
		}

		pr_info("HWP enabled\n");
	} else if (boot_cpu_has(X86_FEATURE_HYBRID_CPU)) {
		pr_warn("Problematic setup: Hybrid processor with disabled HWP\n");
	}

	return 0;
}
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, "active"))
		default_driver = &intel_pstate;
	else if (!strcmp(str, "passive"))
		default_driver = &intel_cpufreq;

	if (!strcmp(str, "no_hwp"))
		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");