summaryrefslogtreecommitdiffstats
path: root/drivers/cpufreq/powernv-cpufreq.c
blob: 8977e4de591570a728958f4000acd0f43d51edc6 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * POWERNV cpufreq driver for the IBM POWER processors
 *
 * (C) Copyright IBM 2014
 *
 * Author: Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>
 */

#define pr_fmt(fmt)	"powernv-cpufreq: " fmt

#include <linux/kernel.h>
#include <linux/sysfs.h>
#include <linux/cpumask.h>
#include <linux/module.h>
#include <linux/cpufreq.h>
#include <linux/smp.h>
#include <linux/of.h>
#include <linux/reboot.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/hashtable.h>
#include <trace/events/power.h>

#include <asm/cputhreads.h>
#include <asm/firmware.h>
#include <asm/reg.h>
#include <asm/smp.h> /* Required for cpu_sibling_mask() in UP configs */
#include <asm/opal.h>
#include <linux/timer.h>

#define POWERNV_MAX_PSTATES_ORDER  8
#define POWERNV_MAX_PSTATES	(1UL << (POWERNV_MAX_PSTATES_ORDER))
#define PMSR_PSAFE_ENABLE	(1UL << 30)
#define PMSR_SPR_EM_DISABLE	(1UL << 31)
#define MAX_PSTATE_SHIFT	32
#define LPSTATE_SHIFT		48
#define GPSTATE_SHIFT		56
#define MAX_NR_CHIPS		32

#define MAX_RAMP_DOWN_TIME				5120
/*
 * On an idle system we want the global pstate to ramp-down from max value to
 * min over a span of ~5 secs. Also we want it to initially ramp-down slowly and
 * then ramp-down rapidly later on.
 *
 * This gives a percentage rampdown for time elapsed in milliseconds.
 * ramp_down_percentage = ((ms * ms) >> 18)
 *			~= 3.8 * (sec * sec)
 *
 * At 0 ms	ramp_down_percent = 0
 * At 5120 ms	ramp_down_percent = 100
 */
#define ramp_down_percent(time)		((time * time) >> 18)

/* Interval after which the timer is queued to bring down global pstate */
#define GPSTATE_TIMER_INTERVAL				2000

/**
 * struct global_pstate_info -	Per policy data structure to maintain history of
 *				global pstates
 * @highest_lpstate_idx:	The local pstate index from which we are
 *				ramping down
 * @elapsed_time:		Time in ms spent in ramping down from
 *				highest_lpstate_idx
 * @last_sampled_time:		Time from boot in ms when global pstates were
 *				last set
 * @last_lpstate_idx:		Last set value of local pstate and global
 * @last_gpstate_idx:		pstate in terms of cpufreq table index
 * @timer:			Is used for ramping down if cpu goes idle for
 *				a long time with global pstate held high
 * @gpstate_lock:		A spinlock to maintain synchronization between
 *				routines called by the timer handler and
 *				governer's target_index calls
 * @policy:			Associated CPUFreq policy
 */
struct global_pstate_info {
	int highest_lpstate_idx;
	unsigned int elapsed_time;
	unsigned int last_sampled_time;
	int last_lpstate_idx;
	int last_gpstate_idx;
	spinlock_t gpstate_lock;
	struct timer_list timer;
	struct cpufreq_policy *policy;
};

static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];

static DEFINE_HASHTABLE(pstate_revmap, POWERNV_MAX_PSTATES_ORDER);
/**
 * struct pstate_idx_revmap_data: Entry in the hashmap pstate_revmap
 *				  indexed by a function of pstate id.
 *
 * @pstate_id: pstate id for this entry.
 *
 * @cpufreq_table_idx: Index into the powernv_freqs
 *		       cpufreq_frequency_table for frequency
 *		       corresponding to pstate_id.
 *
 * @hentry: hlist_node that hooks this entry into the pstate_revmap
 *	    hashtable
 */
struct pstate_idx_revmap_data {
	u8 pstate_id;
	unsigned int cpufreq_table_idx;
	struct hlist_node hentry;
};

static bool rebooting, throttled, occ_reset;

static const char * const throttle_reason[] = {
	"No throttling",
	"Power Cap",
	"Processor Over Temperature",
	"Power Supply Failure",
	"Over Current",
	"OCC Reset"
};

enum throttle_reason_type {
	NO_THROTTLE = 0,
	POWERCAP,
	CPU_OVERTEMP,
	POWER_SUPPLY_FAILURE,
	OVERCURRENT,
	OCC_RESET_THROTTLE,
	OCC_MAX_REASON
};

static struct chip {
	unsigned int id;
	bool throttled;
	bool restore;
	u8 throttle_reason;
	cpumask_t mask;
	struct work_struct throttle;
	int throttle_turbo;
	int throttle_sub_turbo;
	int reason[OCC_MAX_REASON];
} *chips;

static int nr_chips;
static DEFINE_PER_CPU(struct chip *, chip_info);

/*
 * Note:
 * The set of pstates consists of contiguous integers.
 * powernv_pstate_info stores the index of the frequency table for
 * max, min and nominal frequencies. It also stores number of
 * available frequencies.
 *
 * powernv_pstate_info.nominal indicates the index to the highest
 * non-turbo frequency.
 */
static struct powernv_pstate_info {
	unsigned int min;
	unsigned int max;
	unsigned int nominal;
	unsigned int nr_pstates;
	bool wof_enabled;
} powernv_pstate_info;

static inline u8 extract_pstate(u64 pmsr_val, unsigned int shift)
{
	return ((pmsr_val >> shift) & 0xFF);
}

#define extract_local_pstate(x) extract_pstate(x, LPSTATE_SHIFT)
#define extract_global_pstate(x) extract_pstate(x, GPSTATE_SHIFT)
#define extract_max_pstate(x)  extract_pstate(x, MAX_PSTATE_SHIFT)

/* Use following functions for conversions between pstate_id and index */

/*
 * idx_to_pstate : Returns the pstate id corresponding to the
 *		   frequency in the cpufreq frequency table
 *		   powernv_freqs indexed by @i.
 *
 *		   If @i is out of bound, this will return the pstate
 *		   corresponding to the nominal frequency.
 */
static inline u8 idx_to_pstate(unsigned int i)
{
	if (unlikely(i >= powernv_pstate_info.nr_pstates)) {
		pr_warn_once("idx_to_pstate: index %u is out of bound\n", i);
		return powernv_freqs[powernv_pstate_info.nominal].driver_data;
	}

	return powernv_freqs[i].driver_data;
}

/*
 * pstate_to_idx : Returns the index in the cpufreq frequencytable
 *		   powernv_freqs for the frequency whose corresponding
 *		   pstate id is @pstate.
 *
 *		   If no frequency corresponding to @pstate is found,
 *		   this will return the index of the nominal
 *		   frequency.
 */
static unsigned int pstate_to_idx(u8 pstate)
{
	unsigned int key = pstate % POWERNV_MAX_PSTATES;
	struct pstate_idx_revmap_data *revmap_data;

	hash_for_each_possible(pstate_revmap, revmap_data, hentry, key) {
		if (revmap_data->pstate_id == pstate)
			return revmap_data->cpufreq_table_idx;
	}

	pr_warn_once("pstate_to_idx: pstate 0x%x not found\n", pstate);
	return powernv_pstate_info.nominal;
}

static inline void reset_gpstates(struct cpufreq_policy *policy)
{
	struct global_pstate_info *gpstates = policy->driver_data;

	gpstates->highest_lpstate_idx = 0;
	gpstates->elapsed_time = 0;
	gpstates->last_sampled_time = 0;
	gpstates->last_lpstate_idx = 0;
	gpstates->last_gpstate_idx = 0;
}

/*
 * Initialize the freq table based on data obtained
 * from the firmware passed via device-tree
 */
static int init_powernv_pstates(void)
{
	struct device_node *power_mgt;
	int i, nr_pstates = 0;
	const __be32 *pstate_ids, *pstate_freqs;
	u32 len_ids, len_freqs;
	u32 pstate_min, pstate_max, pstate_nominal;
	u32 pstate_turbo, pstate_ultra_turbo;
	int rc = -ENODEV;

	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
	if (!power_mgt) {
		pr_warn("power-mgt node not found\n");
		return -ENODEV;
	}

	if (of_property_read_u32(power_mgt, "ibm,pstate-min", &pstate_min)) {
		pr_warn("ibm,pstate-min node not found\n");
		goto out;
	}

	if (of_property_read_u32(power_mgt, "ibm,pstate-max", &pstate_max)) {
		pr_warn("ibm,pstate-max node not found\n");
		goto out;
	}

	if (of_property_read_u32(power_mgt, "ibm,pstate-nominal",
				 &pstate_nominal)) {
		pr_warn("ibm,pstate-nominal not found\n");
		goto out;
	}

	if (of_property_read_u32(power_mgt, "ibm,pstate-ultra-turbo",
				 &pstate_ultra_turbo)) {
		powernv_pstate_info.wof_enabled = false;
		goto next;
	}

	if (of_property_read_u32(power_mgt, "ibm,pstate-turbo",
				 &pstate_turbo)) {
		powernv_pstate_info.wof_enabled = false;
		goto next;
	}

	if (pstate_turbo == pstate_ultra_turbo)
		powernv_pstate_info.wof_enabled = false;
	else
		powernv_pstate_info.wof_enabled = true;

next:
	pr_info("cpufreq pstate min 0x%x nominal 0x%x max 0x%x\n", pstate_min,
		pstate_nominal, pstate_max);
	pr_info("Workload Optimized Frequency is %s in the platform\n",
		(powernv_pstate_info.wof_enabled) ? "enabled" : "disabled");

	pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids);
	if (!pstate_ids) {
		pr_warn("ibm,pstate-ids not found\n");
		goto out;
	}

	pstate_freqs = of_get_property(power_mgt, "ibm,pstate-frequencies-mhz",
				      &len_freqs);
	if (!pstate_freqs) {
		pr_warn("ibm,pstate-frequencies-mhz not found\n");
		goto out;
	}

	if (len_ids != len_freqs) {
		pr_warn("Entries in ibm,pstate-ids and "
			"ibm,pstate-frequencies-mhz does not match\n");
	}

	nr_pstates = min(len_ids, len_freqs) / sizeof(u32);
	if (!nr_pstates) {
		pr_warn("No PStates found\n");
		goto out;
	}

	powernv_pstate_info.nr_pstates = nr_pstates;
	pr_debug("NR PStates %d\n", nr_pstates);

	for (i = 0; i < nr_pstates; i++) {
		u32 id = be32_to_cpu(pstate_ids[i]);
		u32 freq = be32_to_cpu(pstate_freqs[i]);
		struct pstate_idx_revmap_data *revmap_data;
		unsigned int key;

		pr_debug("PState id %d freq %d MHz\n", id, freq);
		powernv_freqs[i].frequency = freq * 1000; /* kHz */
		powernv_freqs[i].driver_data = id & 0xFF;

		revmap_data = kmalloc(sizeof(*revmap_data), GFP_KERNEL);
		if (!revmap_data) {
			rc = -ENOMEM;
			goto out;
		}

		revmap_data->pstate_id = id & 0xFF;
		revmap_data->cpufreq_table_idx = i;
		key = (revmap_data->pstate_id) % POWERNV_MAX_PSTATES;
		hash_add(pstate_revmap, &revmap_data->hentry, key);

		if (id == pstate_max)
			powernv_pstate_info.max = i;
		if (id == pstate_nominal)
			powernv_pstate_info.nominal = i;
		if (id == pstate_min)
			powernv_pstate_info.min = i;

		if (powernv_pstate_info.wof_enabled && id == pstate_turbo) {
			int j;

			for (j = i - 1; j >= (int)powernv_pstate_info.max; j--)
				powernv_freqs[j].flags = CPUFREQ_BOOST_FREQ;
		}
	}

	/* End of list marker entry */
	powernv_freqs[i].frequency = CPUFREQ_TABLE_END;

	of_node_put(power_mgt);
	return 0;
out:
	of_node_put(power_mgt);
	return rc;
}

/* Returns the CPU frequency corresponding to the pstate_id. */
static unsigned int pstate_id_to_freq(u8 pstate_id)
{
	int i;

	i = pstate_to_idx(pstate_id);
	if (i >= powernv_pstate_info.nr_pstates || i < 0) {
		pr_warn("PState id 0x%x outside of PState table, reporting nominal id 0x%x instead\n",
			pstate_id, idx_to_pstate(powernv_pstate_info.nominal));
		i = powernv_pstate_info.nominal;
	}

	return powernv_freqs[i].frequency;
}

/*
 * cpuinfo_nominal_freq_show - Show the nominal CPU frequency as indicated by
 * the firmware
 */
static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy,
					char *buf)
{
	return sprintf(buf, "%u\n",
		powernv_freqs[powernv_pstate_info.nominal].frequency);
}

static struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq =
	__ATTR_RO(cpuinfo_nominal_freq);

#define SCALING_BOOST_FREQS_ATTR_INDEX		2

static struct freq_attr *powernv_cpu_freq_attr[] = {
	&cpufreq_freq_attr_scaling_available_freqs,
	&cpufreq_freq_attr_cpuinfo_nominal_freq,
	&cpufreq_freq_attr_scaling_boost_freqs,
	NULL,
};

#define throttle_attr(name, member)					\
static ssize_t name##_show(struct cpufreq_policy *policy, char *buf)	\
{									\
	struct chip *chip = per_cpu(chip_info, policy->cpu);		\
									\
	return sprintf(buf, "%u\n", chip->member);			\
}									\
									\
static struct freq_attr throttle_attr_##name = __ATTR_RO(name)		\

throttle_attr(unthrottle, reason[NO_THROTTLE]);
throttle_attr(powercap, reason[POWERCAP]);
throttle_attr(overtemp, reason[CPU_OVERTEMP]);
throttle_attr(supply_fault, reason[POWER_SUPPLY_FAILURE]);
throttle_attr(overcurrent, reason[OVERCURRENT]);
throttle_attr(occ_reset, reason[OCC_RESET_THROTTLE]);
throttle_attr(turbo_stat, throttle_turbo);
throttle_attr(sub_turbo_stat, throttle_sub_turbo);

static struct attribute *throttle_attrs[] = {
	&throttle_attr_unthrottle.attr,
	&throttle_attr_powercap.attr,
	&throttle_attr_overtemp.attr,
	&throttle_attr_supply_fault.attr,
	&throttle_attr_overcurrent.attr,
	&throttle_attr_occ_reset.attr,
	&throttle_attr_turbo_stat.attr,
	&throttle_attr_sub_turbo_stat.attr,
	NULL,
};

static const struct attribute_group throttle_attr_grp = {
	.name	= "throttle_stats",
	.attrs	= throttle_attrs,
};

/* Helper routines */

/* Access helpers to power mgt SPR */

static inline unsigned long get_pmspr(unsigned long sprn)
{
	switch (sprn) {
	case SPRN_PMCR:
		return mfspr(SPRN_PMCR);

	case SPRN_PMICR:
		return mfspr(SPRN_PMICR);

	case SPRN_PMSR:
		return mfspr(SPRN_PMSR);
	}
	BUG();
}

static inline void set_pmspr(unsigned long sprn, unsigned long val)
{
	switch (sprn) {
	case SPRN_PMCR:
		mtspr(SPRN_PMCR, val);
		return;

	case SPRN_PMICR:
		mtspr(SPRN_PMICR, val);
		return;
	}
	BUG();
}

/*
 * Use objects of this type to query/update
 * pstates on a remote CPU via smp_call_function.
 */
struct powernv_smp_call_data {
	unsigned int freq;
	u8 pstate_id;
	u8 gpstate_id;
};

/*
 * powernv_read_cpu_freq: Reads the current frequency on this CPU.
 *
 * Called via smp_call_function.
 *
 * Note: The caller of the smp_call_function should pass an argument of
 * the type 'struct powernv_smp_call_data *' along with this function.
 *
 * The current frequency on this CPU will be returned via
 * ((struct powernv_smp_call_data *)arg)->freq;
 */
static void powernv_read_cpu_freq(void *arg)
{
	unsigned long pmspr_val;
	struct powernv_smp_call_data *freq_data = arg;

	pmspr_val = get_pmspr(SPRN_PMSR);
	freq_data->pstate_id = extract_local_pstate(pmspr_val);
	freq_data->freq = pstate_id_to_freq(freq_data->pstate_id);

	pr_debug("cpu %d pmsr %016lX pstate_id 0x%x frequency %d kHz\n",
		 raw_smp_processor_id(), pmspr_val, freq_data->pstate_id,
		 freq_data->freq);
}

/*
 * powernv_cpufreq_get: Returns the CPU frequency as reported by the
 * firmware for CPU 'cpu'. This value is reported through the sysfs
 * file cpuinfo_cur_freq.
 */
static unsigned int powernv_cpufreq_get(unsigned int cpu)
{
	struct powernv_smp_call_data freq_data;

	smp_call_function_any(cpu_sibling_mask(cpu), powernv_read_cpu_freq,
			&freq_data, 1);

	return freq_data.freq;
}

/*
 * set_pstate: Sets the pstate on this CPU.
 *
 * This is called via an smp_call_function.
 *
 * The caller must ensure that freq_data is of the type
 * (struct powernv_smp_call_data *) and the pstate_id which needs to be set
 * on this CPU should be present in freq_data->pstate_id.
 */
static void set_pstate(void *data)
{
	unsigned long val;
	struct powernv_smp_call_data *freq_data = data;
	unsigned long pstate_ul = freq_data->pstate_id;
	unsigned long gpstate_ul = freq_data->gpstate_id;

	val = get_pmspr(SPRN_PMCR);
	val = val & 0x0000FFFFFFFFFFFFULL;

	pstate_ul = pstate_ul & 0xFF;
	gpstate_ul = gpstate_ul & 0xFF;

	/* Set both global(bits 56..63) and local(bits 48..55) PStates */
	val = val | (gpstate_ul << 56) | (pstate_ul << 48);

	pr_debug("Setting cpu %d pmcr to %016lX\n",
			raw_smp_processor_id(), val);
	set_pmspr(SPRN_PMCR, val);
}

/*
 * get_nominal_index: Returns the index corresponding to the nominal
 * pstate in the cpufreq table
 */
static inline unsigned int get_nominal_index(void)
{
	return powernv_pstate_info.nominal;
}

static void powernv_cpufreq_throttle_check(void *data)
{
	struct chip *chip;
	unsigned int cpu = smp_processor_id();
	unsigned long pmsr;
	u8 pmsr_pmax;
	unsigned int pmsr_pmax_idx;

	pmsr = get_pmspr(SPRN_PMSR);
	chip = this_cpu_read(chip_info);

	/* Check for Pmax Capping */
	pmsr_pmax = extract_max_pstate(pmsr);
	pmsr_pmax_idx = pstate_to_idx(pmsr_pmax);
	if (pmsr_pmax_idx != powernv_pstate_info.max) {
		if (chip->throttled)
			goto next;
		chip->throttled = true;
		if (pmsr_pmax_idx > powernv_pstate_info.nominal) {
			pr_warn_once("CPU %d on Chip %u has Pmax(0x%x) reduced below that of nominal frequency(0x%x)\n",
				     cpu, chip->id, pmsr_pmax,
				     idx_to_pstate(powernv_pstate_info.nominal));
			chip->throttle_sub_turbo++;
		} else {
			chip->throttle_turbo++;
		}
		trace_powernv_throttle(chip->id,
				      throttle_reason[chip->throttle_reason],
				      pmsr_pmax);
	} else if (chip->throttled) {
		chip->throttled = false;
		trace_powernv_throttle(chip->id,
				      throttle_reason[chip->throttle_reason],
				      pmsr_pmax);
	}

	/* Check if Psafe_mode_active is set in PMSR. */
next:
	if (pmsr & PMSR_PSAFE_ENABLE) {
		throttled = true;
		pr_info("Pstate set to safe frequency\n");
	}

	/* Check if SPR_EM_DISABLE is set in PMSR */
	if (pmsr & PMSR_SPR_EM_DISABLE) {
		throttled = true;
		pr_info("Frequency Control disabled from OS\n");
	}

	if (throttled) {
		pr_info("PMSR = %16lx\n", pmsr);
		pr_warn("CPU Frequency could be throttled\n");
	}
}

/**
 * calc_global_pstate - Calculate global pstate
 * @elapsed_time:		Elapsed time in milliseconds
 * @local_pstate_idx:		New local pstate
 * @highest_lpstate_idx:	pstate from which its ramping down
 *
 * Finds the appropriate global pstate based on the pstate from which its
 * ramping down and the time elapsed in ramping down. It follows a quadratic
 * equation which ensures that it reaches ramping down to pmin in 5sec.
 */
static inline int calc_global_pstate(unsigned int elapsed_time,
				     int highest_lpstate_idx,
				     int local_pstate_idx)
{
	int index_diff;

	/*
	 * Using ramp_down_percent we get the percentage of rampdown
	 * that we are expecting to be dropping. Difference between
	 * highest_lpstate_idx and powernv_pstate_info.min will give a absolute
	 * number of how many pstates we will drop eventually by the end of
	 * 5 seconds, then just scale it get the number pstates to be dropped.
	 */
	index_diff =  ((int)ramp_down_percent(elapsed_time) *
			(powernv_pstate_info.min - highest_lpstate_idx)) / 100;

	/* Ensure that global pstate is >= to local pstate */
	if (highest_lpstate_idx + index_diff >= local_pstate_idx)
		return local_pstate_idx;
	else
		return highest_lpstate_idx + index_diff;
}

static inline void  queue_gpstate_timer(struct global_pstate_info *gpstates)
{
	unsigned int timer_interval;

	/*
	 * Setting up timer to fire after GPSTATE_TIMER_INTERVAL ms, But
	 * if it exceeds MAX_RAMP_DOWN_TIME ms for ramp down time.
	 * Set timer such that it fires exactly at MAX_RAMP_DOWN_TIME
	 * seconds of ramp down time.
	 */
	if ((gpstates->elapsed_time + GPSTATE_TIMER_INTERVAL)
	     > MAX_RAMP_DOWN_TIME)
		timer_interval = MAX_RAMP_DOWN_TIME - gpstates->elapsed_time;
	else
		timer_interval = GPSTATE_TIMER_INTERVAL;

	mod_timer(&gpstates->timer, jiffies + msecs_to_jiffies(timer_interval));
}

/**
 * gpstate_timer_handler
 *
 * @t: Timer context used to fetch global pstate info struct
 *
 * This handler brings down the global pstate closer to the local pstate
 * according quadratic equation. Queues a new timer if it is still not equal
 * to local pstate
 */
static void gpstate_timer_handler(struct timer_list *t)
{
	struct global_pstate_info *gpstates = from_timer(gpstates, t, timer);
	struct cpufreq_policy *policy = gpstates->policy;
	int gpstate_idx, lpstate_idx;
	unsigned long val;
	unsigned int time_diff = jiffies_to_msecs(jiffies)
					- gpstates->last_sampled_time;
	struct powernv_smp_call_data freq_data;

	if (!spin_trylock(&gpstates->gpstate_lock))
		return;
	/*
	 * If the timer has migrated to the different cpu then bring
	 * it back to one of the policy->cpus
	 */
	if (!cpumask_test_cpu(raw_smp_processor_id(), policy->cpus)) {
		gpstates->timer.expires = jiffies + msecs_to_jiffies(1);
		add_timer_on(&gpstates->timer, cpumask_first(policy->cpus));
		spin_unlock(&gpstates->gpstate_lock);
		return;
	}

	/*
	 * If PMCR was last updated was using fast_swtich then
	 * We may have wrong in gpstate->last_lpstate_idx
	 * value. Hence, read from PMCR to get correct data.
	 */
	val = get_pmspr(SPRN_PMCR);
	freq_data.gpstate_id = extract_global_pstate(val);
	freq_data.pstate_id = extract_local_pstate(val);
	if (freq_data.gpstate_id  == freq_data.pstate_id) {
		reset_gpstates(policy);
		spin_unlock(&gpstates->gpstate_lock);
		return;
	}

	gpstates->last_sampled_time += time_diff;
	gpstates->elapsed_time += time_diff;

	if (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME) {
		gpstate_idx = pstate_to_idx(freq_data.pstate_id);
		lpstate_idx = gpstate_idx;
		reset_gpstates(policy);
		gpstates->highest_lpstate_idx = gpstate_idx;
	} else {
		lpstate_idx = pstate_to_idx(freq_data.pstate_id);
		gpstate_idx = calc_global_pstate(gpstates->elapsed_time,
						 gpstates->highest_lpstate_idx,
						 lpstate_idx);
	}
	freq_data.gpstate_id = idx_to_pstate(gpstate_idx);
	gpstates->last_gpstate_idx = gpstate_idx;
	gpstates->last_lpstate_idx = lpstate_idx;
	/*
	 * If local pstate is equal to global pstate, rampdown is over
	 * So timer is not required to be queued.
	 */
	if (gpstate_idx != gpstates->last_lpstate_idx)
		queue_gpstate_timer(gpstates);

	set_pstate(&freq_data);
	spin_unlock(&gpstates->gpstate_lock);
}

/*
 * powernv_cpufreq_target_index: Sets the frequency corresponding to
 * the cpufreq table entry indexed by new_index on the cpus in the
 * mask policy->cpus
 */
static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
					unsigned int new_index)
{
	struct powernv_smp_call_data freq_data;
	unsigned int cur_msec, gpstate_idx;
	struct global_pstate_info *gpstates = policy->driver_data;

	if (unlikely(rebooting) && new_index != get_nominal_index())
		return 0;

	if (!throttled) {
		/* we don't want to be preempted while
		 * checking if the CPU frequency has been throttled
		 */
		preempt_disable();
		powernv_cpufreq_throttle_check(NULL);
		preempt_enable();
	}

	cur_msec = jiffies_to_msecs(get_jiffies_64());

	freq_data.pstate_id = idx_to_pstate(new_index);
	if (!gpstates) {
		freq_data.gpstate_id = freq_data.pstate_id;
		goto no_gpstate;
	}

	spin_lock(&gpstates->gpstate_lock);

	if (!gpstates->last_sampled_time) {
		gpstate_idx = new_index;
		gpstates->highest_lpstate_idx = new_index;
		goto gpstates_done;
	}

	if (gpstates->last_gpstate_idx < new_index) {
		gpstates->elapsed_time += cur_msec -
						 gpstates->last_sampled_time;

		/*
		 * If its has been ramping down for more than MAX_RAMP_DOWN_TIME
		 * we should be resetting all global pstate related data. Set it
		 * equal to local pstate to start fresh.
		 */
		if (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME) {
			reset_gpstates(policy);
			gpstates->highest_lpstate_idx = new_index;
			gpstate_idx = new_index;
		} else {
		/* Elaspsed_time is less than 5 seconds, continue to rampdown */
			gpstate_idx = calc_global_pstate(gpstates->elapsed_time,
							 gpstates->highest_lpstate_idx,
							 new_index);
		}
	} else {
		reset_gpstates(policy);
		gpstates->highest_lpstate_idx = new_index;
		gpstate_idx = new_index;
	}

	/*
	 * If local pstate is equal to global pstate, rampdown is over
	 * So timer is not required to be queued.
	 */
	if (gpstate_idx != new_index)
		queue_gpstate_timer(gpstates);
	else
		del_timer_sync(&gpstates->timer);

gpstates_done:
	freq_data.gpstate_id = idx_to_pstate(gpstate_idx);
	gpstates->last_sampled_time = cur_msec;
	gpstates->last_gpstate_idx = gpstate_idx;
	gpstates->last_lpstate_idx = new_index;

	spin_unlock(&gpstates->gpstate_lock);

no_gpstate:
	/*
	 * Use smp_call_function to send IPI and execute the
	 * mtspr on target CPU.  We could do that without IPI
	 * if current CPU is within policy->cpus (core)
	 */
	smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1);
	return 0;
}

static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy)
{
	int base, i;
	struct kernfs_node *kn;
	struct global_pstate_info *gpstates;

	base = cpu_first_thread_sibling(policy->cpu);

	for (i = 0; i < threads_per_core; i++)
		cpumask_set_cpu(base + i, policy->cpus);

	kn = kernfs_find_and_get(policy->kobj.sd, throttle_attr_grp.name);
	if (!kn) {
		int ret;

		ret = sysfs_create_group(&policy->kobj, &throttle_attr_grp);
		if (ret) {
			pr_info("Failed to create throttle stats directory for cpu %d\n",
				policy->cpu);
			return ret;
		}
	} else {
		kernfs_put(kn);
	}

	policy->freq_table = powernv_freqs;
	policy->fast_switch_possible = true;

	if (pvr_version_is(PVR_POWER9))
		return 0;

	/* Initialise Gpstate ramp-down timer only on POWER8 */
	gpstates =  kzalloc(sizeof(*gpstates), GFP_KERNEL);
	if (!gpstates)
		return -ENOMEM;

	policy->driver_data = gpstates;

	/* initialize timer */
	gpstates->policy = policy;
	timer_setup(&gpstates->timer, gpstate_timer_handler,
		    TIMER_PINNED | TIMER_DEFERRABLE);
	gpstates->timer.expires = jiffies +
				msecs_to_jiffies(GPSTATE_TIMER_INTERVAL);
	spin_lock_init(&gpstates->gpstate_lock);

	return 0;
}

static int powernv_cpufreq_cpu_exit(struct cpufreq_policy *policy)
{
	/* timer is deleted in cpufreq_cpu_stop() */
	kfree(policy->driver_data);

	return 0;
}

static int powernv_cpufreq_reboot_notifier(struct notifier_block *nb,
				unsigned long action, void *unused)
{
	int cpu;
	struct cpufreq_policy *cpu_policy;

	rebooting = true;
	for_each_online_cpu(cpu) {
		cpu_policy = cpufreq_cpu_get(cpu);
		if (!cpu_policy)
			continue;
		powernv_cpufreq_target_index(cpu_policy, get_nominal_index());
		cpufreq_cpu_put(cpu_policy);
	}

	return NOTIFY_DONE;
}

static struct notifier_block powernv_cpufreq_reboot_nb = {
	.notifier_call = powernv_cpufreq_reboot_notifier,
};

static void powernv_cpufreq_work_fn(struct work_struct *work)
{
	struct chip *chip = container_of(work, struct chip, throttle);
	struct cpufreq_policy *policy;
	unsigned int cpu;
	cpumask_t mask;

	get_online_cpus();
	cpumask_and(&mask, &chip->mask, cpu_online_mask);
	smp_call_function_any(&mask,
			      powernv_cpufreq_throttle_check, NULL, 0);

	if (!chip->restore)
		goto out;

	chip->restore = false;
	for_each_cpu(cpu, &mask) {
		int index;

		policy = cpufreq_cpu_get(cpu);
		if (!policy)
			continue;
		index = cpufreq_table_find_index_c(policy, policy->cur);
		powernv_cpufreq_target_index(policy, index);
		cpumask_andnot(&mask, &mask, policy->cpus);
		cpufreq_cpu_put(policy);
	}
out:
	put_online_cpus();
}

static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
				   unsigned long msg_type, void *_msg)
{
	struct opal_msg *msg = _msg;
	struct opal_occ_msg omsg;
	int i;

	if (msg_type != OPAL_MSG_OCC)
		return 0;

	omsg.type = be64_to_cpu(msg->params[0]);

	switch (omsg.type) {
	case OCC_RESET:
		occ_reset = true;
		pr_info("OCC (On Chip Controller - enforces hard thermal/power limits) Resetting\n");
		/*
		 * powernv_cpufreq_throttle_check() is called in
		 * target() callback which can detect the throttle state
		 * for governors like ondemand.
		 * But static governors will not call target() often thus
		 * report throttling here.
		 */
		if (!throttled) {
			throttled = true;
			pr_warn("CPU frequency is throttled for duration\n");
		}

		break;
	case OCC_LOAD:
		pr_info("OCC Loading, CPU frequency is throttled until OCC is started\n");
		break;
	case OCC_THROTTLE:
		omsg.chip = be64_to_cpu(msg->params[1]);
		omsg.throttle_status = be64_to_cpu(msg->params[2]);

		if (occ_reset) {
			occ_reset = false;
			throttled = false;
			pr_info("OCC Active, CPU frequency is no longer throttled\n");

			for (i = 0; i < nr_chips; i++) {
				chips[i].restore = true;
				schedule_work(&chips[i].throttle);
			}

			return 0;
		}

		for (i = 0; i < nr_chips; i++)
			if (chips[i].id == omsg.chip)
				break;

		if (omsg.throttle_status >= 0 &&
		    omsg.throttle_status <= OCC_MAX_THROTTLE_STATUS) {
			chips[i].throttle_reason = omsg.throttle_status;
			chips[i].reason[omsg.throttle_status]++;
		}

		if (!omsg.throttle_status)
			chips[i].restore = true;

		schedule_work(&chips[i].throttle);
	}
	return 0;
}

static struct notifier_block powernv_cpufreq_opal_nb = {
	.notifier_call	= powernv_cpufreq_occ_msg,
	.next		= NULL,
	.priority	= 0,
};

static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy)
{
	struct powernv_smp_call_data freq_data;
	struct global_pstate_info *gpstates = policy->driver_data;

	freq_data.pstate_id = idx_to_pstate(powernv_pstate_info.min);
	freq_data.gpstate_id = idx_to_pstate(powernv_pstate_info.min);
	smp_call_function_single(policy->cpu, set_pstate, &freq_data, 1);
	if (gpstates)
		del_timer_sync(&gpstates->timer);
}

static unsigned int powernv_fast_switch(struct cpufreq_policy *policy,
					unsigned int target_freq)
{
	int index;
	struct powernv_smp_call_data freq_data;

	index = cpufreq_table_find_index_dl(policy, target_freq);
	freq_data.pstate_id = powernv_freqs[index].driver_data;
	freq_data.gpstate_id = powernv_freqs[index].driver_data;
	set_pstate(&freq_data);

	return powernv_freqs[index].frequency;
}

static struct cpufreq_driver powernv_cpufreq_driver = {
	.name		= "powernv-cpufreq",
	.flags		= CPUFREQ_CONST_LOOPS,
	.init		= powernv_cpufreq_cpu_init,
	.exit		= powernv_cpufreq_cpu_exit,
	.verify		= cpufreq_generic_frequency_table_verify,
	.target_index	= powernv_cpufreq_target_index,
	.fast_switch	= powernv_fast_switch,
	.get		= powernv_cpufreq_get,
	.stop_cpu	= powernv_cpufreq_stop_cpu,
	.attr		= powernv_cpu_freq_attr,
};

static int init_chip_info(void)
{
	unsigned int *chip;
	unsigned int cpu, i;
	unsigned int prev_chip_id = UINT_MAX;
	cpumask_t *chip_cpu_mask;
	int ret = 0;

	chip = kcalloc(num_possible_cpus(), sizeof(*chip), GFP_KERNEL);
	if (!chip)
		return -ENOMEM;

	/* Allocate a chip cpu mask large enough to fit mask for all chips */
	chip_cpu_mask = kcalloc(MAX_NR_CHIPS, sizeof(cpumask_t), GFP_KERNEL);
	if (!chip_cpu_mask) {
		ret = -ENOMEM;
		goto free_and_return;
	}

	for_each_possible_cpu(cpu) {
		unsigned int id = cpu_to_chip_id(cpu);

		if (prev_chip_id != id) {
			prev_chip_id = id;
			chip[nr_chips++] = id;
		}
		cpumask_set_cpu(cpu, &chip_cpu_mask[nr_chips-1]);
	}

	chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL);
	if (!chips) {
		ret = -ENOMEM;
		goto out_free_chip_cpu_mask;
	}

	for (i = 0; i < nr_chips; i++) {
		chips[i].id = chip[i];
		cpumask_copy(&chips[i].mask, &chip_cpu_mask[i]);
		INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn);
		for_each_cpu(cpu, &chips[i].mask)
			per_cpu(chip_info, cpu) =  &chips[i];
	}

out_free_chip_cpu_mask:
	kfree(chip_cpu_mask);
free_and_return:
	kfree(chip);
	return ret;
}

static inline void clean_chip_info(void)
{
	int i;

	/* flush any pending work items */
	if (chips)
		for (i = 0; i < nr_chips; i++)
			cancel_work_sync(&chips[i].throttle);
	kfree(chips);
}

static inline void unregister_all_notifiers(void)
{
	opal_message_notifier_unregister(OPAL_MSG_OCC,
					 &powernv_cpufreq_opal_nb);
	unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
}

static int __init powernv_cpufreq_init(void)
{
	int rc = 0;

	/* Don't probe on pseries (guest) platforms */
	if (!firmware_has_feature(FW_FEATURE_OPAL))
		return -ENODEV;

	/* Discover pstates from device tree and init */
	rc = init_powernv_pstates();
	if (rc)
		goto out;

	/* Populate chip info */
	rc = init_chip_info();
	if (rc)
		goto out;

	if (powernv_pstate_info.wof_enabled)
		powernv_cpufreq_driver.boost_enabled = true;
	else
		powernv_cpu_freq_attr[SCALING_BOOST_FREQS_ATTR_INDEX] = NULL;

	rc = cpufreq_register_driver(&powernv_cpufreq_driver);
	if (rc) {
		pr_info("Failed to register the cpufreq driver (%d)\n", rc);
		goto cleanup;
	}

	if (powernv_pstate_info.wof_enabled)
		cpufreq_enable_boost_support();

	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
	opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb);

	return 0;
cleanup:
	clean_chip_info();
out:
	pr_info("Platform driver disabled. System does not support PState control\n");
	return rc;
}
module_init(powernv_cpufreq_init);

static void __exit powernv_cpufreq_exit(void)
{
	cpufreq_unregister_driver(&powernv_cpufreq_driver);
	unregister_all_notifiers();
	clean_chip_info();
}
module_exit(powernv_cpufreq_exit);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>");