summaryrefslogtreecommitdiff
path: root/drivers/cpufreq/amd-pstate.c
blob: ddd346a239e0b55acfaef158cb12ea1a8612f948 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * amd-pstate.c - AMD Processor P-state Frequency Driver
 *
 * Copyright (C) 2021 Advanced Micro Devices, Inc. All Rights Reserved.
 *
 * Author: Huang Rui <ray.huang@amd.com>
 *
 * AMD P-State introduces a new CPU performance scaling design for AMD
 * processors using the ACPI Collaborative Performance and Power Control (CPPC)
 * feature which works with the AMD SMU firmware providing a finer grained
 * frequency control range. It is to replace the legacy ACPI P-States control,
 * allows a flexible, low-latency interface for the Linux kernel to directly
 * communicate the performance hints to hardware.
 *
 * AMD P-State is supported on recent AMD Zen base CPU series include some of
 * Zen2 and Zen3 processors. _CPC needs to be present in the ACPI tables of AMD
 * P-State supported system. And there are two types of hardware implementations
 * for AMD P-State: 1) Full MSR Solution and 2) Shared Memory Solution.
 * X86_FEATURE_CPPC CPU feature flag is used to distinguish the different types.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/sched.h>
#include <linux/cpufreq.h>
#include <linux/compiler.h>
#include <linux/dmi.h>
#include <linux/slab.h>
#include <linux/acpi.h>
#include <linux/io.h>
#include <linux/delay.h>
#include <linux/uaccess.h>
#include <linux/static_call.h>
#include <linux/amd-pstate.h>

#include <acpi/processor.h>
#include <acpi/cppc_acpi.h>

#include <asm/msr.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>
#include <asm/cpu_device_id.h>
#include "amd-pstate-trace.h"

#define AMD_PSTATE_TRANSITION_LATENCY	20000
#define AMD_PSTATE_TRANSITION_DELAY	1000

/*
 * TODO: We need more time to fine tune processors with shared memory solution
 * with community together.
 *
 * There are some performance drops on the CPU benchmarks which reports from
 * Suse. We are co-working with them to fine tune the shared memory solution. So
 * we disable it by default to go acpi-cpufreq on these processors and add a
 * module parameter to be able to enable it manually for debugging.
 */
static struct cpufreq_driver *current_pstate_driver;
static struct cpufreq_driver amd_pstate_driver;
static struct cpufreq_driver amd_pstate_epp_driver;
static int cppc_state = AMD_PSTATE_DISABLE;

/*
 * AMD Energy Preference Performance (EPP)
 * The EPP is used in the CCLK DPM controller to drive
 * the frequency that a core is going to operate during
 * short periods of activity. EPP values will be utilized for
 * different OS profiles (balanced, performance, power savings)
 * 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,
	[EPP_INDEX_PERFORMANCE] = AMD_CPPC_EPP_PERFORMANCE,
	[EPP_INDEX_BALANCE_PERFORMANCE] = AMD_CPPC_EPP_BALANCE_PERFORMANCE,
	[EPP_INDEX_BALANCE_POWERSAVE] = AMD_CPPC_EPP_BALANCE_POWERSAVE,
	[EPP_INDEX_POWERSAVE] = AMD_CPPC_EPP_POWERSAVE,
 };

typedef int (*cppc_mode_transition_fn)(int);

static inline int get_mode_idx_from_str(const char *str, size_t size)
{
	int i;

	for (i=0; i < AMD_PSTATE_MAX; i++) {
		if (!strncmp(str, amd_pstate_mode_string[i], size))
			return i;
	}
	return -EINVAL;
}

static DEFINE_MUTEX(amd_pstate_limits_lock);
static DEFINE_MUTEX(amd_pstate_driver_lock);

static s16 amd_pstate_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached)
{
	u64 epp;
	int ret;

	if (boot_cpu_has(X86_FEATURE_CPPC)) {
		if (!cppc_req_cached) {
			epp = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
					&cppc_req_cached);
			if (epp)
				return epp;
		}
		epp = (cppc_req_cached >> 24) & 0xFF;
	} else {
		ret = cppc_get_epp_perf(cpudata->cpu, &epp);
		if (ret < 0) {
			pr_debug("Could not retrieve energy perf value (%d)\n", ret);
			return -EIO;
		}
	}

	return (s16)(epp & 0xff);
}

static int amd_pstate_get_energy_pref_index(struct amd_cpudata *cpudata)
{
	s16 epp;
	int index = -EINVAL;

	epp = amd_pstate_get_epp(cpudata, 0);
	if (epp < 0)
		return epp;

	switch (epp) {
	case AMD_CPPC_EPP_PERFORMANCE:
		index = EPP_INDEX_PERFORMANCE;
		break;
	case AMD_CPPC_EPP_BALANCE_PERFORMANCE:
		index = EPP_INDEX_BALANCE_PERFORMANCE;
		break;
	case AMD_CPPC_EPP_BALANCE_POWERSAVE:
		index = EPP_INDEX_BALANCE_POWERSAVE;
		break;
	case AMD_CPPC_EPP_POWERSAVE:
		index = EPP_INDEX_POWERSAVE;
		break;
	default:
		break;
	}

	return index;
}

static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp)
{
	int ret;
	struct cppc_perf_ctrls perf_ctrls;

	if (boot_cpu_has(X86_FEATURE_CPPC)) {
		u64 value = READ_ONCE(cpudata->cppc_req_cached);

		value &= ~GENMASK_ULL(31, 24);
		value |= (u64)epp << 24;
		WRITE_ONCE(cpudata->cppc_req_cached, value);

		ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
		if (!ret)
			cpudata->epp_cached = epp;
	} else {
		perf_ctrls.energy_perf = epp;
		ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1);
		if (ret) {
			pr_debug("failed to set energy perf value (%d)\n", ret);
			return ret;
		}
		cpudata->epp_cached = epp;
	}

	return ret;
}

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

	if (!pref_index) {
		pr_debug("EPP pref_index is invalid\n");
		return -EINVAL;
	}

	if (epp == -EINVAL)
		epp = epp_values[pref_index];

	if (epp > 0 && cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
		pr_debug("EPP cannot be set under performance policy\n");
		return -EBUSY;
	}

	ret = amd_pstate_set_epp(cpudata, epp);

	return ret;
}

static inline int pstate_enable(bool enable)
{
	return wrmsrl_safe(MSR_AMD_CPPC_ENABLE, enable);
}

static int cppc_enable(bool enable)
{
	int cpu, ret = 0;
	struct cppc_perf_ctrls perf_ctrls;

	for_each_present_cpu(cpu) {
		ret = cppc_set_enable(cpu, enable);
		if (ret)
			return ret;

		/* Enable autonomous mode for EPP */
		if (cppc_state == AMD_PSTATE_ACTIVE) {
			/* Set desired perf as zero to allow EPP firmware control */
			perf_ctrls.desired_perf = 0;
			ret = cppc_set_perf(cpu, &perf_ctrls);
			if (ret)
				return ret;
		}
	}

	return ret;
}

DEFINE_STATIC_CALL(amd_pstate_enable, pstate_enable);

static inline int amd_pstate_enable(bool enable)
{
	return static_call(amd_pstate_enable)(enable);
}

static int pstate_init_perf(struct amd_cpudata *cpudata)
{
	u64 cap1;
	u32 highest_perf;

	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
				     &cap1);
	if (ret)
		return ret;

	/*
	 * TODO: Introduce AMD specific power feature.
	 *
	 * CPPC entry doesn't indicate the highest performance in some ASICs.
	 */
	highest_perf = amd_get_highest_perf();
	if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1))
		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);

	WRITE_ONCE(cpudata->highest_perf, highest_perf);

	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
	WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1));

	return 0;
}

static int cppc_init_perf(struct amd_cpudata *cpudata)
{
	struct cppc_perf_caps cppc_perf;
	u32 highest_perf;

	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
	if (ret)
		return ret;

	highest_perf = amd_get_highest_perf();
	if (highest_perf > cppc_perf.highest_perf)
		highest_perf = cppc_perf.highest_perf;

	WRITE_ONCE(cpudata->highest_perf, highest_perf);

	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
		   cppc_perf.lowest_nonlinear_perf);
	WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf);

	if (cppc_state == AMD_PSTATE_ACTIVE)
		return 0;

	ret = cppc_get_auto_sel_caps(cpudata->cpu, &cppc_perf);
	if (ret) {
		pr_warn("failed to get auto_sel, ret: %d\n", ret);
		return 0;
	}

	ret = cppc_set_auto_sel(cpudata->cpu,
			(cppc_state == AMD_PSTATE_PASSIVE) ? 0 : 1);

	if (ret)
		pr_warn("failed to set auto_sel, ret: %d\n", ret);

	return ret;
}

DEFINE_STATIC_CALL(amd_pstate_init_perf, pstate_init_perf);

static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata)
{
	return static_call(amd_pstate_init_perf)(cpudata);
}

static void pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
			       u32 des_perf, u32 max_perf, bool fast_switch)
{
	if (fast_switch)
		wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached));
	else
		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
			      READ_ONCE(cpudata->cppc_req_cached));
}

static void cppc_update_perf(struct amd_cpudata *cpudata,
			     u32 min_perf, u32 des_perf,
			     u32 max_perf, bool fast_switch)
{
	struct cppc_perf_ctrls perf_ctrls;

	perf_ctrls.max_perf = max_perf;
	perf_ctrls.min_perf = min_perf;
	perf_ctrls.desired_perf = des_perf;

	cppc_set_perf(cpudata->cpu, &perf_ctrls);
}

DEFINE_STATIC_CALL(amd_pstate_update_perf, pstate_update_perf);

static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata,
					  u32 min_perf, u32 des_perf,
					  u32 max_perf, bool fast_switch)
{
	static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf,
					    max_perf, fast_switch);
}

static inline bool amd_pstate_sample(struct amd_cpudata *cpudata)
{
	u64 aperf, mperf, tsc;
	unsigned long flags;

	local_irq_save(flags);
	rdmsrl(MSR_IA32_APERF, aperf);
	rdmsrl(MSR_IA32_MPERF, mperf);
	tsc = rdtsc();

	if (cpudata->prev.mperf == mperf || cpudata->prev.tsc == tsc) {
		local_irq_restore(flags);
		return false;
	}

	local_irq_restore(flags);

	cpudata->cur.aperf = aperf;
	cpudata->cur.mperf = mperf;
	cpudata->cur.tsc =  tsc;
	cpudata->cur.aperf -= cpudata->prev.aperf;
	cpudata->cur.mperf -= cpudata->prev.mperf;
	cpudata->cur.tsc -= cpudata->prev.tsc;

	cpudata->prev.aperf = aperf;
	cpudata->prev.mperf = mperf;
	cpudata->prev.tsc = tsc;

	cpudata->freq = div64_u64((cpudata->cur.aperf * cpu_khz), cpudata->cur.mperf);

	return true;
}

static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
			      u32 des_perf, u32 max_perf, bool fast_switch, int gov_flags)
{
	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
	u64 value = prev;

	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);

	if ((cppc_state == AMD_PSTATE_GUIDED) && (gov_flags & CPUFREQ_GOV_DYNAMIC_SWITCHING)) {
		min_perf = des_perf;
		des_perf = 0;
	}

	value &= ~AMD_CPPC_MIN_PERF(~0L);
	value |= AMD_CPPC_MIN_PERF(min_perf);

	value &= ~AMD_CPPC_DES_PERF(~0L);
	value |= AMD_CPPC_DES_PERF(des_perf);

	value &= ~AMD_CPPC_MAX_PERF(~0L);
	value |= AMD_CPPC_MAX_PERF(max_perf);

	if (trace_amd_pstate_perf_enabled() && amd_pstate_sample(cpudata)) {
		trace_amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq,
			cpudata->cur.mperf, cpudata->cur.aperf, cpudata->cur.tsc,
				cpudata->cpu, (value != prev), fast_switch);
	}

	if (value == prev)
		return;

	WRITE_ONCE(cpudata->cppc_req_cached, value);

	amd_pstate_update_perf(cpudata, min_perf, des_perf,
			       max_perf, fast_switch);
}

static int amd_pstate_verify(struct cpufreq_policy_data *policy)
{
	cpufreq_verify_within_cpu_limits(policy);

	return 0;
}

static int amd_pstate_update_freq(struct cpufreq_policy *policy,
				  unsigned int target_freq, bool fast_switch)
{
	struct cpufreq_freqs freqs;
	struct amd_cpudata *cpudata = policy->driver_data;
	unsigned long max_perf, min_perf, des_perf, cap_perf;

	if (!cpudata->max_freq)
		return -ENODEV;

	cap_perf = READ_ONCE(cpudata->highest_perf);
	min_perf = READ_ONCE(cpudata->lowest_perf);
	max_perf = cap_perf;

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

	des_perf = DIV_ROUND_CLOSEST(target_freq * cap_perf,
				     cpudata->max_freq);

	WARN_ON(fast_switch && !policy->fast_switch_enabled);
	/*
	 * If fast_switch is desired, then there aren't any registered
	 * transition notifiers. See comment for
	 * cpufreq_enable_fast_switch().
	 */
	if (!fast_switch)
		cpufreq_freq_transition_begin(policy, &freqs);

	amd_pstate_update(cpudata, min_perf, des_perf,
			max_perf, fast_switch, policy->governor->flags);

	if (!fast_switch)
		cpufreq_freq_transition_end(policy, &freqs, false);

	return 0;
}

static int amd_pstate_target(struct cpufreq_policy *policy,
			     unsigned int target_freq,
			     unsigned int relation)
{
	return amd_pstate_update_freq(policy, target_freq, false);
}

static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy,
				  unsigned int target_freq)
{
	return amd_pstate_update_freq(policy, target_freq, true);
}

static void amd_pstate_adjust_perf(unsigned int cpu,
				   unsigned long _min_perf,
				   unsigned long target_perf,
				   unsigned long capacity)
{
	unsigned long max_perf, min_perf, des_perf,
		      cap_perf, lowest_nonlinear_perf, max_freq;
	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
	struct amd_cpudata *cpudata = policy->driver_data;
	unsigned int target_freq;

	cap_perf = READ_ONCE(cpudata->highest_perf);
	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
	max_freq = READ_ONCE(cpudata->max_freq);

	des_perf = cap_perf;
	if (target_perf < capacity)
		des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity);

	min_perf = READ_ONCE(cpudata->highest_perf);
	if (_min_perf < capacity)
		min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity);

	if (min_perf < lowest_nonlinear_perf)
		min_perf = lowest_nonlinear_perf;

	max_perf = cap_perf;
	if (max_perf < min_perf)
		max_perf = min_perf;

	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
	target_freq = div_u64(des_perf * max_freq, max_perf);
	policy->cur = target_freq;

	amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true,
			policy->governor->flags);
	cpufreq_cpu_put(policy);
}

static int amd_get_min_freq(struct amd_cpudata *cpudata)
{
	struct cppc_perf_caps cppc_perf;

	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
	if (ret)
		return ret;

	/* Switch to khz */
	return cppc_perf.lowest_freq * 1000;
}

static int amd_get_max_freq(struct amd_cpudata *cpudata)
{
	struct cppc_perf_caps cppc_perf;
	u32 max_perf, max_freq, nominal_freq, nominal_perf;
	u64 boost_ratio;

	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
	if (ret)
		return ret;

	nominal_freq = cppc_perf.nominal_freq;
	nominal_perf = READ_ONCE(cpudata->nominal_perf);
	max_perf = READ_ONCE(cpudata->highest_perf);

	boost_ratio = div_u64(max_perf << SCHED_CAPACITY_SHIFT,
			      nominal_perf);

	max_freq = nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT;

	/* Switch to khz */
	return max_freq * 1000;
}

static int amd_get_nominal_freq(struct amd_cpudata *cpudata)
{
	struct cppc_perf_caps cppc_perf;

	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
	if (ret)
		return ret;

	/* Switch to khz */
	return cppc_perf.nominal_freq * 1000;
}

static int amd_get_lowest_nonlinear_freq(struct amd_cpudata *cpudata)
{
	struct cppc_perf_caps cppc_perf;
	u32 lowest_nonlinear_freq, lowest_nonlinear_perf,
	    nominal_freq, nominal_perf;
	u64 lowest_nonlinear_ratio;

	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
	if (ret)
		return ret;

	nominal_freq = cppc_perf.nominal_freq;
	nominal_perf = READ_ONCE(cpudata->nominal_perf);

	lowest_nonlinear_perf = cppc_perf.lowest_nonlinear_perf;

	lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT,
					 nominal_perf);

	lowest_nonlinear_freq = nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT;

	/* Switch to khz */
	return lowest_nonlinear_freq * 1000;
}

static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
{
	struct amd_cpudata *cpudata = policy->driver_data;
	int ret;

	if (!cpudata->boost_supported) {
		pr_err("Boost mode is not supported by this processor or SBIOS\n");
		return -EINVAL;
	}

	if (state)
		policy->cpuinfo.max_freq = cpudata->max_freq;
	else
		policy->cpuinfo.max_freq = cpudata->nominal_freq;

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

	ret = freq_qos_update_request(&cpudata->req[1],
				      policy->cpuinfo.max_freq);
	if (ret < 0)
		return ret;

	return 0;
}

static void amd_pstate_boost_init(struct amd_cpudata *cpudata)
{
	u32 highest_perf, nominal_perf;

	highest_perf = READ_ONCE(cpudata->highest_perf);
	nominal_perf = READ_ONCE(cpudata->nominal_perf);

	if (highest_perf <= nominal_perf)
		return;

	cpudata->boost_supported = true;
	current_pstate_driver->boost_enabled = true;
}

static void amd_perf_ctl_reset(unsigned int cpu)
{
	wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
}

static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
{
	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
	struct device *dev;
	struct amd_cpudata *cpudata;

	/*
	 * Resetting PERF_CTL_MSR will put the CPU in P0 frequency,
	 * which is ideal for initialization process.
	 */
	amd_perf_ctl_reset(policy->cpu);
	dev = get_cpu_device(policy->cpu);
	if (!dev)
		return -ENODEV;

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

	cpudata->cpu = policy->cpu;

	ret = amd_pstate_init_perf(cpudata);
	if (ret)
		goto free_cpudata1;

	min_freq = amd_get_min_freq(cpudata);
	max_freq = amd_get_max_freq(cpudata);
	nominal_freq = amd_get_nominal_freq(cpudata);
	lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata);

	if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) {
		dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n",
			min_freq, max_freq);
		ret = -EINVAL;
		goto free_cpudata1;
	}

	policy->cpuinfo.transition_latency = AMD_PSTATE_TRANSITION_LATENCY;
	policy->transition_delay_us = AMD_PSTATE_TRANSITION_DELAY;

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

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

	/* It will be updated by governor */
	policy->cur = policy->cpuinfo.min_freq;

	if (boot_cpu_has(X86_FEATURE_CPPC))
		policy->fast_switch_possible = true;

	ret = freq_qos_add_request(&policy->constraints, &cpudata->req[0],
				   FREQ_QOS_MIN, policy->cpuinfo.min_freq);
	if (ret < 0) {
		dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret);
		goto free_cpudata1;
	}

	ret = freq_qos_add_request(&policy->constraints, &cpudata->req[1],
				   FREQ_QOS_MAX, policy->cpuinfo.max_freq);
	if (ret < 0) {
		dev_err(dev, "Failed to add max-freq constraint (%d)\n", ret);
		goto free_cpudata2;
	}

	/* Initial processor data capability frequencies */
	cpudata->max_freq = max_freq;
	cpudata->min_freq = min_freq;
	cpudata->nominal_freq = nominal_freq;
	cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq;

	policy->driver_data = cpudata;

	amd_pstate_boost_init(cpudata);
	if (!current_pstate_driver->adjust_perf)
		current_pstate_driver->adjust_perf = amd_pstate_adjust_perf;

	return 0;

free_cpudata2:
	freq_qos_remove_request(&cpudata->req[0]);
free_cpudata1:
	kfree(cpudata);
	return ret;
}

static int amd_pstate_cpu_exit(struct cpufreq_policy *policy)
{
	struct amd_cpudata *cpudata = policy->driver_data;

	freq_qos_remove_request(&cpudata->req[1]);
	freq_qos_remove_request(&cpudata->req[0]);
	policy->fast_switch_possible = false;
	kfree(cpudata);

	return 0;
}

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

	ret = amd_pstate_enable(true);
	if (ret)
		pr_err("failed to enable amd-pstate during resume, return %d\n", ret);

	return ret;
}

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

	ret = amd_pstate_enable(false);
	if (ret)
		pr_err("failed to disable amd-pstate during suspend, return %d\n", ret);

	return ret;
}

/* Sysfs attributes */

/*
 * This frequency is to indicate the maximum hardware frequency.
 * If boost is not active but supported, the frequency will be larger than the
 * one in cpuinfo.
 */
static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy,
					char *buf)
{
	int max_freq;
	struct amd_cpudata *cpudata = policy->driver_data;

	max_freq = amd_get_max_freq(cpudata);
	if (max_freq < 0)
		return max_freq;

	return sysfs_emit(buf, "%u\n", max_freq);
}

static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *policy,
						     char *buf)
{
	int freq;
	struct amd_cpudata *cpudata = policy->driver_data;

	freq = amd_get_lowest_nonlinear_freq(cpudata);
	if (freq < 0)
		return freq;

	return sysfs_emit(buf, "%u\n", freq);
}

/*
 * In some of ASICs, the highest_perf is not the one in the _CPC table, so we
 * need to expose it to sysfs.
 */
static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy,
					    char *buf)
{
	u32 perf;
	struct amd_cpudata *cpudata = policy->driver_data;

	perf = READ_ONCE(cpudata->highest_perf);

	return sysfs_emit(buf, "%u\n", perf);
}

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

	while (energy_perf_strings[i] != NULL)
		offset += sysfs_emit_at(buf, offset, "%s ", energy_perf_strings[i++]);

	sysfs_emit_at(buf, offset, "\n");

	return offset;
}

static ssize_t store_energy_performance_preference(
		struct cpufreq_policy *policy, const char *buf, size_t count)
{
	struct amd_cpudata *cpudata = policy->driver_data;
	char str_preference[21];
	ssize_t ret;

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

	ret = match_string(energy_perf_strings, -1, str_preference);
	if (ret < 0)
		return -EINVAL;

	mutex_lock(&amd_pstate_limits_lock);
	ret = amd_pstate_set_energy_pref_index(cpudata, ret);
	mutex_unlock(&amd_pstate_limits_lock);

	return ret ?: count;
}

static ssize_t show_energy_performance_preference(
				struct cpufreq_policy *policy, char *buf)
{
	struct amd_cpudata *cpudata = policy->driver_data;
	int preference;

	preference = amd_pstate_get_energy_pref_index(cpudata);
	if (preference < 0)
		return preference;

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

static void amd_pstate_driver_cleanup(void)
{
	amd_pstate_enable(false);
	cppc_state = AMD_PSTATE_DISABLE;
	current_pstate_driver = NULL;
}

static int amd_pstate_register_driver(int mode)
{
	int ret;

	if (mode == AMD_PSTATE_PASSIVE || mode == AMD_PSTATE_GUIDED)
		current_pstate_driver = &amd_pstate_driver;
	else if (mode == AMD_PSTATE_ACTIVE)
		current_pstate_driver = &amd_pstate_epp_driver;
	else
		return -EINVAL;

	cppc_state = mode;
	ret = cpufreq_register_driver(current_pstate_driver);
	if (ret) {
		amd_pstate_driver_cleanup();
		return ret;
	}
	return 0;
}

static int amd_pstate_unregister_driver(int dummy)
{
	cpufreq_unregister_driver(current_pstate_driver);
	amd_pstate_driver_cleanup();
	return 0;
}

static int amd_pstate_change_mode_without_dvr_change(int mode)
{
	int cpu = 0;

	cppc_state = mode;

	if (boot_cpu_has(X86_FEATURE_CPPC) || cppc_state == AMD_PSTATE_ACTIVE)
		return 0;

	for_each_present_cpu(cpu) {
		cppc_set_auto_sel(cpu, (cppc_state == AMD_PSTATE_PASSIVE) ? 0 : 1);
	}

	return 0;
}

static int amd_pstate_change_driver_mode(int mode)
{
	int ret;

	ret = amd_pstate_unregister_driver(0);
	if (ret)
		return ret;

	ret = amd_pstate_register_driver(mode);
	if (ret)
		return ret;

	return 0;
}

static cppc_mode_transition_fn mode_state_machine[AMD_PSTATE_MAX][AMD_PSTATE_MAX] = {
	[AMD_PSTATE_DISABLE]         = {
		[AMD_PSTATE_DISABLE]     = NULL,
		[AMD_PSTATE_PASSIVE]     = amd_pstate_register_driver,
		[AMD_PSTATE_ACTIVE]      = amd_pstate_register_driver,
		[AMD_PSTATE_GUIDED]      = amd_pstate_register_driver,
	},
	[AMD_PSTATE_PASSIVE]         = {
		[AMD_PSTATE_DISABLE]     = amd_pstate_unregister_driver,
		[AMD_PSTATE_PASSIVE]     = NULL,
		[AMD_PSTATE_ACTIVE]      = amd_pstate_change_driver_mode,
		[AMD_PSTATE_GUIDED]      = amd_pstate_change_mode_without_dvr_change,
	},
	[AMD_PSTATE_ACTIVE]          = {
		[AMD_PSTATE_DISABLE]     = amd_pstate_unregister_driver,
		[AMD_PSTATE_PASSIVE]     = amd_pstate_change_driver_mode,
		[AMD_PSTATE_ACTIVE]      = NULL,
		[AMD_PSTATE_GUIDED]      = amd_pstate_change_driver_mode,
	},
	[AMD_PSTATE_GUIDED]          = {
		[AMD_PSTATE_DISABLE]     = amd_pstate_unregister_driver,
		[AMD_PSTATE_PASSIVE]     = amd_pstate_change_mode_without_dvr_change,
		[AMD_PSTATE_ACTIVE]      = amd_pstate_change_driver_mode,
		[AMD_PSTATE_GUIDED]      = NULL,
	},
};

static ssize_t amd_pstate_show_status(char *buf)
{
	if (!current_pstate_driver)
		return sysfs_emit(buf, "disable\n");

	return sysfs_emit(buf, "%s\n", amd_pstate_mode_string[cppc_state]);
}

static int amd_pstate_update_status(const char *buf, size_t size)
{
	int mode_idx;

	if (size > strlen("passive") || size < strlen("active"))
		return -EINVAL;

	mode_idx = get_mode_idx_from_str(buf, size);

	if (mode_idx < 0 || mode_idx >= AMD_PSTATE_MAX)
		return -EINVAL;

	if (mode_state_machine[cppc_state][mode_idx])
		return mode_state_machine[cppc_state][mode_idx](mode_idx);

	return 0;
}

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

	mutex_lock(&amd_pstate_driver_lock);
	ret = amd_pstate_show_status(buf);
	mutex_unlock(&amd_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(&amd_pstate_driver_lock);
	ret = amd_pstate_update_status(buf, p ? p - buf : count);
	mutex_unlock(&amd_pstate_driver_lock);

	return ret < 0 ? ret : count;
}

cpufreq_freq_attr_ro(amd_pstate_max_freq);
cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq);

cpufreq_freq_attr_ro(amd_pstate_highest_perf);
cpufreq_freq_attr_rw(energy_performance_preference);
cpufreq_freq_attr_ro(energy_performance_available_preferences);
define_one_global_rw(status);

static struct freq_attr *amd_pstate_attr[] = {
	&amd_pstate_max_freq,
	&amd_pstate_lowest_nonlinear_freq,
	&amd_pstate_highest_perf,
	NULL,
};

static struct freq_attr *amd_pstate_epp_attr[] = {
	&amd_pstate_max_freq,
	&amd_pstate_lowest_nonlinear_freq,
	&amd_pstate_highest_perf,
	&energy_performance_preference,
	&energy_performance_available_preferences,
	NULL,
};

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

static const struct attribute_group amd_pstate_global_attr_group = {
	.name = "amd_pstate",
	.attrs = pstate_global_attributes,
};

static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
{
	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
	struct amd_cpudata *cpudata;
	struct device *dev;
	u64 value;

	/*
	 * Resetting PERF_CTL_MSR will put the CPU in P0 frequency,
	 * which is ideal for initialization process.
	 */
	amd_perf_ctl_reset(policy->cpu);
	dev = get_cpu_device(policy->cpu);
	if (!dev)
		return -ENODEV;

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

	cpudata->cpu = policy->cpu;
	cpudata->epp_policy = 0;

	ret = amd_pstate_init_perf(cpudata);
	if (ret)
		goto free_cpudata1;

	min_freq = amd_get_min_freq(cpudata);
	max_freq = amd_get_max_freq(cpudata);
	nominal_freq = amd_get_nominal_freq(cpudata);
	lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata);
	if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) {
		dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n",
				min_freq, max_freq);
		ret = -EINVAL;
		goto free_cpudata1;
	}

	policy->cpuinfo.min_freq = min_freq;
	policy->cpuinfo.max_freq = max_freq;
	/* It will be updated by governor */
	policy->cur = policy->cpuinfo.min_freq;

	/* Initial processor data capability frequencies */
	cpudata->max_freq = max_freq;
	cpudata->min_freq = min_freq;
	cpudata->nominal_freq = nominal_freq;
	cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq;

	policy->driver_data = cpudata;

	cpudata->epp_cached = amd_pstate_get_epp(cpudata, 0);

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

	/*
	 * 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 (boot_cpu_has(X86_FEATURE_CPPC)) {
		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value);
		if (ret)
			return ret;
		WRITE_ONCE(cpudata->cppc_req_cached, value);

		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1, &value);
		if (ret)
			return ret;
		WRITE_ONCE(cpudata->cppc_cap1_cached, value);
	}
	amd_pstate_boost_init(cpudata);

	return 0;

free_cpudata1:
	kfree(cpudata);
	return ret;
}

static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
{
	pr_debug("CPU %d exiting\n", policy->cpu);
	return 0;
}

static void amd_pstate_epp_init(unsigned int cpu)
{
	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
	struct amd_cpudata *cpudata = policy->driver_data;
	u32 max_perf, min_perf;
	u64 value;
	s16 epp;

	max_perf = READ_ONCE(cpudata->highest_perf);
	min_perf = READ_ONCE(cpudata->lowest_perf);

	value = READ_ONCE(cpudata->cppc_req_cached);

	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
		min_perf = max_perf;

	/* Initial min/max values for CPPC Performance Controls Register */
	value &= ~AMD_CPPC_MIN_PERF(~0L);
	value |= AMD_CPPC_MIN_PERF(min_perf);

	value &= ~AMD_CPPC_MAX_PERF(~0L);
	value |= AMD_CPPC_MAX_PERF(max_perf);

	/* CPPC EPP feature require to set zero to the desire perf bit */
	value &= ~AMD_CPPC_DES_PERF(~0L);
	value |= AMD_CPPC_DES_PERF(0);

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

	cpudata->epp_policy = cpudata->policy;

	/* Get BIOS pre-defined epp value */
	epp = amd_pstate_get_epp(cpudata, value);
	if (epp < 0) {
		/**
		 * This return value can only be negative for shared_memory
		 * systems where EPP register read/write not supported.
		 */
		goto skip_epp;
	}

	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
		epp = 0;

	/* Set initial EPP value */
	if (boot_cpu_has(X86_FEATURE_CPPC)) {
		value &= ~GENMASK_ULL(31, 24);
		value |= (u64)epp << 24;
	}

	WRITE_ONCE(cpudata->cppc_req_cached, value);
	amd_pstate_set_epp(cpudata, epp);
skip_epp:
	cpufreq_cpu_put(policy);
}

static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
{
	struct amd_cpudata *cpudata = policy->driver_data;

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

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

	cpudata->policy = policy->policy;

	amd_pstate_epp_init(policy->cpu);

	return 0;
}

static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
{
	struct cppc_perf_ctrls perf_ctrls;
	u64 value, max_perf;
	int ret;

	ret = amd_pstate_enable(true);
	if (ret)
		pr_err("failed to enable amd pstate during resume, return %d\n", ret);

	value = READ_ONCE(cpudata->cppc_req_cached);
	max_perf = READ_ONCE(cpudata->highest_perf);

	if (boot_cpu_has(X86_FEATURE_CPPC)) {
		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
	} else {
		perf_ctrls.max_perf = max_perf;
		perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(cpudata->epp_cached);
		cppc_set_perf(cpudata->cpu, &perf_ctrls);
	}
}

static int amd_pstate_epp_cpu_online(struct cpufreq_policy *policy)
{
	struct amd_cpudata *cpudata = policy->driver_data;

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

	if (cppc_state == AMD_PSTATE_ACTIVE) {
		amd_pstate_epp_reenable(cpudata);
		cpudata->suspended = false;
	}

	return 0;
}

static void amd_pstate_epp_offline(struct cpufreq_policy *policy)
{
	struct amd_cpudata *cpudata = policy->driver_data;
	struct cppc_perf_ctrls perf_ctrls;
	int min_perf;
	u64 value;

	min_perf = READ_ONCE(cpudata->lowest_perf);
	value = READ_ONCE(cpudata->cppc_req_cached);

	mutex_lock(&amd_pstate_limits_lock);
	if (boot_cpu_has(X86_FEATURE_CPPC)) {
		cpudata->epp_policy = CPUFREQ_POLICY_UNKNOWN;

		/* Set max perf same as min perf */
		value &= ~AMD_CPPC_MAX_PERF(~0L);
		value |= AMD_CPPC_MAX_PERF(min_perf);
		value &= ~AMD_CPPC_MIN_PERF(~0L);
		value |= AMD_CPPC_MIN_PERF(min_perf);
		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
	} else {
		perf_ctrls.desired_perf = 0;
		perf_ctrls.max_perf = min_perf;
		perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(HWP_EPP_BALANCE_POWERSAVE);
		cppc_set_perf(cpudata->cpu, &perf_ctrls);
	}
	mutex_unlock(&amd_pstate_limits_lock);
}

static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
{
	struct amd_cpudata *cpudata = policy->driver_data;

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

	if (cpudata->suspended)
		return 0;

	if (cppc_state == AMD_PSTATE_ACTIVE)
		amd_pstate_epp_offline(policy);

	return 0;
}

static int amd_pstate_epp_verify_policy(struct cpufreq_policy_data *policy)
{
	cpufreq_verify_within_cpu_limits(policy);
	pr_debug("policy_max =%d, policy_min=%d\n", policy->max, policy->min);
	return 0;
}

static int amd_pstate_epp_suspend(struct cpufreq_policy *policy)
{
	struct amd_cpudata *cpudata = policy->driver_data;
	int ret;

	/* avoid suspending when EPP is not enabled */
	if (cppc_state != AMD_PSTATE_ACTIVE)
		return 0;

	/* set this flag to avoid setting core offline*/
	cpudata->suspended = true;

	/* disable CPPC in lowlevel firmware */
	ret = amd_pstate_enable(false);
	if (ret)
		pr_err("failed to suspend, return %d\n", ret);

	return 0;
}

static int amd_pstate_epp_resume(struct cpufreq_policy *policy)
{
	struct amd_cpudata *cpudata = policy->driver_data;

	if (cpudata->suspended) {
		mutex_lock(&amd_pstate_limits_lock);

		/* enable amd pstate from suspend state*/
		amd_pstate_epp_reenable(cpudata);

		mutex_unlock(&amd_pstate_limits_lock);

		cpudata->suspended = false;
	}

	return 0;
}

static struct cpufreq_driver amd_pstate_driver = {
	.flags		= CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS,
	.verify		= amd_pstate_verify,
	.target		= amd_pstate_target,
	.fast_switch    = amd_pstate_fast_switch,
	.init		= amd_pstate_cpu_init,
	.exit		= amd_pstate_cpu_exit,
	.suspend	= amd_pstate_cpu_suspend,
	.resume		= amd_pstate_cpu_resume,
	.set_boost	= amd_pstate_set_boost,
	.name		= "amd-pstate",
	.attr		= amd_pstate_attr,
};

static struct cpufreq_driver amd_pstate_epp_driver = {
	.flags		= CPUFREQ_CONST_LOOPS,
	.verify		= amd_pstate_epp_verify_policy,
	.setpolicy	= amd_pstate_epp_set_policy,
	.init		= amd_pstate_epp_cpu_init,
	.exit		= amd_pstate_epp_cpu_exit,
	.offline	= amd_pstate_epp_cpu_offline,
	.online		= amd_pstate_epp_cpu_online,
	.suspend	= amd_pstate_epp_suspend,
	.resume		= amd_pstate_epp_resume,
	.name		= "amd_pstate_epp",
	.attr		= amd_pstate_epp_attr,
};

static int __init amd_pstate_init(void)
{
	struct device *dev_root;
	int ret;

	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
		return -ENODEV;
	/*
	 * by default the pstate driver is disabled to load
	 * enable the amd_pstate passive mode driver explicitly
	 * with amd_pstate=passive or other modes in kernel command line
	 */
	if (cppc_state == AMD_PSTATE_DISABLE) {
		pr_info("driver load is disabled, boot with specific mode to enable this\n");
		return -ENODEV;
	}

	if (!acpi_cpc_valid()) {
		pr_warn_once("the _CPC object is not present in SBIOS or ACPI disabled\n");
		return -ENODEV;
	}

	/* don't keep reloading if cpufreq_driver exists */
	if (cpufreq_get_current_driver())
		return -EEXIST;

	/* capability check */
	if (boot_cpu_has(X86_FEATURE_CPPC)) {
		pr_debug("AMD CPPC MSR based functionality is supported\n");
		if (cppc_state != AMD_PSTATE_ACTIVE)
			current_pstate_driver->adjust_perf = amd_pstate_adjust_perf;
	} else {
		pr_debug("AMD CPPC shared memory based functionality is supported\n");
		static_call_update(amd_pstate_enable, cppc_enable);
		static_call_update(amd_pstate_init_perf, cppc_init_perf);
		static_call_update(amd_pstate_update_perf, cppc_update_perf);
	}

	/* enable amd pstate feature */
	ret = amd_pstate_enable(true);
	if (ret) {
		pr_err("failed to enable with return %d\n", ret);
		return ret;
	}

	ret = cpufreq_register_driver(current_pstate_driver);
	if (ret)
		pr_err("failed to register with return %d\n", ret);

	dev_root = bus_get_dev_root(&cpu_subsys);
	if (dev_root) {
		ret = sysfs_create_group(&dev_root->kobj, &amd_pstate_global_attr_group);
		put_device(dev_root);
		if (ret) {
			pr_err("sysfs attribute export failed with error %d.\n", ret);
			goto global_attr_free;
		}
	}

	return ret;

global_attr_free:
	cpufreq_unregister_driver(current_pstate_driver);
	return ret;
}
device_initcall(amd_pstate_init);

static int __init amd_pstate_param(char *str)
{
	size_t size;
	int mode_idx;

	if (!str)
		return -EINVAL;

	size = strlen(str);
	mode_idx = get_mode_idx_from_str(str, size);

	if (mode_idx >= AMD_PSTATE_DISABLE && mode_idx < AMD_PSTATE_MAX) {
		cppc_state = mode_idx;
		if (cppc_state == AMD_PSTATE_DISABLE)
			pr_info("driver is explicitly disabled\n");

		if (cppc_state == AMD_PSTATE_ACTIVE)
			current_pstate_driver = &amd_pstate_epp_driver;

		if (cppc_state == AMD_PSTATE_PASSIVE || cppc_state == AMD_PSTATE_GUIDED)
			current_pstate_driver = &amd_pstate_driver;

		return 0;
	}

	return -EINVAL;
}
early_param("amd_pstate", amd_pstate_param);

MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>");
MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver");