summaryrefslogtreecommitdiffstats
path: root/drivers/cpufreq/intel_pstate.c
blob: f502d5b90c2537b88a86b5224f21d175556be744 (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
/*
 * intel_pstate.c: Native P state management for Intel processors
 *
 * (C) Copyright 2012 Intel Corporation
 * Author: Dirk Brandewie <dirk.j.brandewie@intel.com>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; version 2
 * of the License.
 */

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

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

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

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

/**
 * struct sample -	Store performance sample
 * @core_pct_busy:	Ratio of APERF/MPERF in percent, which is actual
 *			performance during last sample period
 * @busy_scaled:	Scaled busy value which is used to calculate next
 *			P state. This can be different than core_pct_busy
 *			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
 * @freq:		Effective frequency calculated from APERF/MPERF
 * @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_pct_busy;
	int32_t busy_scaled;
	u64 aperf;
	u64 mperf;
	u64 tsc;
	int freq;
	u64 time;
};

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

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

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

/**
 * struct cpudata -	Per CPU instance data storage
 * @cpu:		CPU number for this instance data
 * @update_util:	CPUFreq utility callback information
 * @pstate:		Stores P state limits for this CPU
 * @vid:		Stores VID limits for this CPU
 * @pid:		Stores PID parameters for this CPU
 * @last_sample_time:	Last Sample time
 * @prev_aperf:		Last APERF value read from APERF MSR
 * @prev_mperf:		Last MPERF value read from MPERF MSR
 * @prev_tsc:		Last timestamp counter (TSC) value
 * @prev_cummulative_iowait: IO Wait time difference from last and
 *			current sample
 * @sample:		Storage for storing last Sample data
 *
 * This structure stores per CPU instance data for all CPUs.
 */
struct cpudata {
	int cpu;

	struct update_util_data update_util;

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

	u64	last_sample_time;
	u64	prev_aperf;
	u64	prev_mperf;
	u64	prev_tsc;
	u64	prev_cummulative_iowait;
	struct sample sample;
};

static struct cpudata **all_cpu_data;

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

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

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

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

static struct pstate_adjust_policy pid_params;
static struct pstate_funcs pstate_funcs;
static int hwp_active;


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

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

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

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

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

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

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

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

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

	fp_error = pid->setpoint - busy;

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

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

	pid->integral += fp_error;

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

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

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

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

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

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

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

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

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

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

	rdmsrl(MSR_HWP_CAPABILITIES, cap);
	hw_min = HWP_LOWEST_PERF(cap);
	hw_max = HWP_HIGHEST_PERF(cap);
	range = hw_max - hw_min;

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

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

		value &= ~HWP_MAX_PERF(~0L);
		value |= HWP_MAX_PERF(max);
		wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
	}
}

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

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

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

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

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

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

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

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

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

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

	cpu = all_cpu_data[0];

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

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

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

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

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

	return ret;
}

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

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

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

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

	if (hwp_active)
		intel_pstate_hwp_set_online_cpus();

	return count;
}

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

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

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

	if (hwp_active)
		intel_pstate_hwp_set_online_cpus();
	return count;
}

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

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

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

	if (hwp_active)
		intel_pstate_hwp_set_online_cpus();
	return count;
}

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

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

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

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

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

	intel_pstate_kobject = kobject_create_and_add("intel_pstate",
						&cpu_subsys.dev_root->kobj);
	BUG_ON(!intel_pstate_kobject);
	rc = sysfs_create_group(intel_pstate_kobject, &intel_pstate_attr_group);
	BUG_ON(rc);
}
/************************** sysfs end ************************/

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

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

static int atom_get_min_pstate(void)
{
	u64 value;

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

static int atom_get_max_pstate(void)
{
	u64 value;

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

static int atom_get_turbo_pstate(void)
{
	u64 value;

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

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

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

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

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

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

	return val | vid;
}

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

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

	return silvermont_freq_table[i];
}

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

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

	return airmont_freq_table[i];
}

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

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

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

static int core_get_min_pstate(void)
{
	u64 value;

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

static int core_get_max_pstate_physical(void)
{
	u64 value;

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

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

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

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

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

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

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

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

skip_tar:
	return max_pstate;
}

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

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

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

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

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

	return val;
}

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

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

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

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

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

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

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

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

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

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

static inline void intel_pstate_record_pstate(struct cpudata *cpu, int pstate)
{
	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
	cpu->pstate.current_pstate = pstate;
}

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

	intel_pstate_record_pstate(cpu, 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_get_cpu_pstates(struct cpudata *cpu)
{
	cpu->pstate.min_pstate = pstate_funcs.get_min();
	cpu->pstate.max_pstate = pstate_funcs.get_max();
	cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical();
	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
	cpu->pstate.scaling = pstate_funcs.get_scaling();

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

	intel_pstate_set_min_pstate(cpu);
}

static inline void intel_pstate_calc_busy(struct cpudata *cpu)
{
	struct sample *sample = &cpu->sample;
	int64_t core_pct;

	core_pct = int_tofp(sample->aperf) * int_tofp(100);
	core_pct = div64_u64(core_pct, int_tofp(sample->mperf));

	sample->core_pct_busy = (int32_t)core_pct;
}

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

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

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

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

static inline int32_t get_avg_frequency(struct cpudata *cpu)
{
	return div64_u64(cpu->pstate.max_pstate_physical * cpu->sample.aperf *
		cpu->pstate.scaling, cpu->sample.mperf);
}

static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
{
	struct sample *sample = &cpu->sample;
	u64 cummulative_iowait, delta_iowait_us;
	u64 delta_iowait_mperf;
	u64 mperf, now;
	int32_t cpu_load;

	cummulative_iowait = get_cpu_iowait_time_us(cpu->cpu, &now);

	/*
	 * Convert iowait time into number of IO cycles spent at max_freq.
	 * IO is considered as busy only for the cpu_load algorithm. For
	 * performance this is not needed since we always try to reach the
	 * maximum P-State, so we are already boosting the IOs.
	 */
	delta_iowait_us = cummulative_iowait - cpu->prev_cummulative_iowait;
	delta_iowait_mperf = div64_u64(delta_iowait_us * cpu->pstate.scaling *
		cpu->pstate.max_pstate, MSEC_PER_SEC);

	mperf = cpu->sample.mperf + delta_iowait_mperf;
	cpu->prev_cummulative_iowait = cummulative_iowait;

	/*
	 * The load can be estimated as the ratio of the mperf counter
	 * running at a constant frequency during active periods
	 * (C0) and the time stamp counter running at the same frequency
	 * also during C-states.
	 */
	cpu_load = div64_u64(int_tofp(100) * mperf, sample->tsc);
	cpu->sample.busy_scaled = cpu_load;

	return cpu->pstate.current_pstate - pid_calc(&cpu->pid, cpu_load);
}

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

	intel_pstate_calc_busy(cpu);

	/*
	 * core_busy is the ratio of actual performance to max
	 * max_pstate is the max non turbo pstate available
	 * current_pstate was the pstate that was requested during
	 * 	the last sample period.
	 *
	 * We normalize core_busy, which was our actual percent
	 * performance to what we requested during the last sample
	 * period. The result will be a percentage of busy at a
	 * specified pstate.
	 */
	core_busy = cpu->sample.core_pct_busy;
	max_pstate = int_tofp(cpu->pstate.max_pstate_physical);
	current_pstate = int_tofp(cpu->pstate.current_pstate);
	core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));

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

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

static inline void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
{
	int max_perf, min_perf;

	update_turbo_state();

	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
	pstate = clamp_t(int, pstate, min_perf, max_perf);
	if (pstate == cpu->pstate.current_pstate)
		return;

	intel_pstate_record_pstate(cpu, pstate);
	wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate));
}

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

	from = cpu->pstate.current_pstate;

	target_pstate = pstate_funcs.get_target_pstate(cpu);

	intel_pstate_update_pstate(cpu, target_pstate);

	sample = &cpu->sample;
	trace_pstate_sample(fp_toint(sample->core_pct_busy),
		fp_toint(sample->busy_scaled),
		from,
		cpu->pstate.current_pstate,
		sample->mperf,
		sample->aperf,
		sample->tsc,
		get_avg_frequency(cpu));
}

static void intel_pstate_update_util(struct update_util_data *data, u64 time,
				     unsigned long util, unsigned long max)
{
	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
	u64 delta_ns = time - cpu->sample.time;

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

		if (sample_taken && !hwp_active)
			intel_pstate_adjust_busy_pstate(cpu);
	}
}

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

static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
	ICPU(0x2a, core_params),
	ICPU(0x2d, core_params),
	ICPU(0x37, silvermont_params),
	ICPU(0x3a, core_params),
	ICPU(0x3c, core_params),
	ICPU(0x3d, core_params),
	ICPU(0x3e, core_params),
	ICPU(0x3f, core_params),
	ICPU(0x45, core_params),
	ICPU(0x46, core_params),
	ICPU(0x47, core_params),
	ICPU(0x4c, airmont_params),
	ICPU(0x4e, core_params),
	ICPU(0x4f, core_params),
	ICPU(0x5e, core_params),
	ICPU(0x56, core_params),
	ICPU(0x57, knl_params),
	{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);

static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] = {
	ICPU(0x56, core_params),
	{}
};

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

	if (!all_cpu_data[cpunum])
		all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata),
					       GFP_KERNEL);
	if (!all_cpu_data[cpunum])
		return -ENOMEM;

	cpu = all_cpu_data[cpunum];

	cpu->cpu = cpunum;

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

	intel_pstate_get_cpu_pstates(cpu);

	intel_pstate_busy_pid_reset(cpu);

	cpu->update_util.func = intel_pstate_update_util;

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

	return 0;
}

static unsigned int intel_pstate_get(unsigned int cpu_num)
{
	struct sample *sample;
	struct cpudata *cpu;

	cpu = all_cpu_data[cpu_num];
	if (!cpu)
		return 0;
	sample = &cpu->sample;
	return get_avg_frequency(cpu);
}

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

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

static void intel_pstate_clear_update_util_hook(unsigned int cpu)
{
	cpufreq_set_update_util_data(cpu, NULL);
	synchronize_sched();
}

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

static int intel_pstate_set_policy(struct cpufreq_policy *policy)
{
	if (!policy->cpuinfo.max_freq)
		return -ENODEV;

	intel_pstate_clear_update_util_hook(policy->cpu);

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

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

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

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

	limits->min_perf = div_fp(int_tofp(limits->min_perf_pct),
				  int_tofp(100));
	limits->max_perf = div_fp(int_tofp(limits->max_perf_pct),
				  int_tofp(100));

 out:
	intel_pstate_set_update_util_hook(policy->cpu);

	if (hwp_active)
		intel_pstate_hwp_set(policy->cpus);

	return 0;
}

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

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

	return 0;
}

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

	pr_debug("intel_pstate: CPU %d exiting\n", cpu_num);

	intel_pstate_clear_update_util_hook(cpu_num);

	if (hwp_active)
		return;

	intel_pstate_set_min_pstate(cpu);
}

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];

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

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

	/* cpuinfo and default policy values */
	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
	policy->cpuinfo.max_freq =
		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
	cpumask_set_cpu(policy->cpu, policy->cpus);

	return 0;
}

static struct cpufreq_driver intel_pstate_driver = {
	.flags		= CPUFREQ_CONST_LOOPS,
	.verify		= intel_pstate_verify_policy,
	.setpolicy	= intel_pstate_set_policy,
	.get		= intel_pstate_get,
	.init		= intel_pstate_cpu_init,
	.stop_cpu	= intel_pstate_stop_cpu,
	.name		= "intel_pstate",
};

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

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

	return 0;
}

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

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

}

#if IS_ENABLED(CONFIG_ACPI)
#include <acpi/processor.h>

static bool intel_pstate_no_acpi_pss(void)
{
	int i;

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

		if (!pr)
			continue;

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

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

		kfree(pss);
	}

	return true;
}

static bool intel_pstate_has_acpi_ppc(void)
{
	int i;

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

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

enum {
	PSS,
	PPC,
};

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

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

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

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

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

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

	return false;
}
#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; }
#endif /* CONFIG_ACPI */

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

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

	if (no_load)
		return -ENODEV;

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

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

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

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

	if (intel_pstate_msrs_not_valid())
		return -ENODEV;

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

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

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

	if (!hwp_active && hwp_only)
		goto out;

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

	intel_pstate_debug_expose_params();
	intel_pstate_sysfs_expose_params();

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

	return rc;
out:
	get_online_cpus();
	for_each_online_cpu(cpu) {
		if (all_cpu_data[cpu]) {
			intel_pstate_clear_update_util_hook(cpu);
			kfree(all_cpu_data[cpu]);
		}
	}

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

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

	if (!strcmp(str, "disable"))
		no_load = 1;
	if (!strcmp(str, "no_hwp")) {
		pr_info("intel_pstate: HWP disabled\n");
		no_hwp = 1;
	}
	if (!strcmp(str, "force"))
		force_load = 1;
	if (!strcmp(str, "hwp_only"))
		hwp_only = 1;
	return 0;
}
early_param("intel_pstate", intel_pstate_setup);

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