aboutsummaryrefslogtreecommitdiff
path: root/drivers/acpi/cppc_acpi.c
blob: a4d4eebba1da422b2ef0c0236f424da4fa0ad783 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * CPPC (Collaborative Processor Performance Control) methods used by CPUfreq drivers.
 *
 * (C) Copyright 2014, 2015 Linaro Ltd.
 * Author: Ashwin Chaugule <ashwin.chaugule@linaro.org>
 *
 * CPPC describes a few methods for controlling CPU performance using
 * information from a per CPU table called CPC. This table is described in
 * the ACPI v5.0+ specification. The table consists of a list of
 * registers which may be memory mapped or hardware registers and also may
 * include some static integer values.
 *
 * CPU performance is on an abstract continuous scale as against a discretized
 * P-state scale which is tied to CPU frequency only. In brief, the basic
 * operation involves:
 *
 * - OS makes a CPU performance request. (Can provide min and max bounds)
 *
 * - Platform (such as BMC) is free to optimize request within requested bounds
 *   depending on power/thermal budgets etc.
 *
 * - Platform conveys its decision back to OS
 *
 * The communication between OS and platform occurs through another medium
 * called (PCC) Platform Communication Channel. This is a generic mailbox like
 * mechanism which includes doorbell semantics to indicate register updates.
 * See drivers/mailbox/pcc.c for details on PCC.
 *
 * Finer details about the PCC and CPPC spec are available in the ACPI v5.1 and
 * above specifications.
 */

#define pr_fmt(fmt)	"ACPI CPPC: " fmt

#include <linux/delay.h>
#include <linux/iopoll.h>
#include <linux/ktime.h>
#include <linux/rwsem.h>
#include <linux/wait.h>
#include <linux/topology.h>

#include <acpi/cppc_acpi.h>

struct cppc_pcc_data {
	struct mbox_chan *pcc_channel;
	void __iomem *pcc_comm_addr;
	bool pcc_channel_acquired;
	unsigned int deadline_us;
	unsigned int pcc_mpar, pcc_mrtt, pcc_nominal;

	bool pending_pcc_write_cmd;	/* Any pending/batched PCC write cmds? */
	bool platform_owns_pcc;		/* Ownership of PCC subspace */
	unsigned int pcc_write_cnt;	/* Running count of PCC write commands */

	/*
	 * Lock to provide controlled access to the PCC channel.
	 *
	 * For performance critical usecases(currently cppc_set_perf)
	 *	We need to take read_lock and check if channel belongs to OSPM
	 * before reading or writing to PCC subspace
	 *	We need to take write_lock before transferring the channel
	 * ownership to the platform via a Doorbell
	 *	This allows us to batch a number of CPPC requests if they happen
	 * to originate in about the same time
	 *
	 * For non-performance critical usecases(init)
	 *	Take write_lock for all purposes which gives exclusive access
	 */
	struct rw_semaphore pcc_lock;

	/* Wait queue for CPUs whose requests were batched */
	wait_queue_head_t pcc_write_wait_q;
	ktime_t last_cmd_cmpl_time;
	ktime_t last_mpar_reset;
	int mpar_count;
	int refcount;
};

/* Array to represent the PCC channel per subspace ID */
static struct cppc_pcc_data *pcc_data[MAX_PCC_SUBSPACES];
/* The cpu_pcc_subspace_idx contains per CPU subspace ID */
static DEFINE_PER_CPU(int, cpu_pcc_subspace_idx);

/*
 * The cpc_desc structure contains the ACPI register details
 * as described in the per CPU _CPC tables. The details
 * include the type of register (e.g. PCC, System IO, FFH etc.)
 * and destination addresses which lets us READ/WRITE CPU performance
 * information using the appropriate I/O methods.
 */
static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr);

/* pcc mapped address + header size + offset within PCC subspace */
#define GET_PCC_VADDR(offs, pcc_ss_id) (pcc_data[pcc_ss_id]->pcc_comm_addr + \
						0x8 + (offs))

/* Check if a CPC register is in PCC */
#define CPC_IN_PCC(cpc) ((cpc)->type == ACPI_TYPE_BUFFER &&		\
				(cpc)->cpc_entry.reg.space_id ==	\
				ACPI_ADR_SPACE_PLATFORM_COMM)

/* Evaluates to True if reg is a NULL register descriptor */
#define IS_NULL_REG(reg) ((reg)->space_id ==  ACPI_ADR_SPACE_SYSTEM_MEMORY && \
				(reg)->address == 0 &&			\
				(reg)->bit_width == 0 &&		\
				(reg)->bit_offset == 0 &&		\
				(reg)->access_width == 0)

/* Evaluates to True if an optional cpc field is supported */
#define CPC_SUPPORTED(cpc) ((cpc)->type == ACPI_TYPE_INTEGER ?		\
				!!(cpc)->cpc_entry.int_value :		\
				!IS_NULL_REG(&(cpc)->cpc_entry.reg))
/*
 * Arbitrary Retries in case the remote processor is slow to respond
 * to PCC commands. Keeping it high enough to cover emulators where
 * the processors run painfully slow.
 */
#define NUM_RETRIES 500ULL

#define define_one_cppc_ro(_name)		\
static struct kobj_attribute _name =		\
__ATTR(_name, 0444, show_##_name, NULL)

#define to_cpc_desc(a) container_of(a, struct cpc_desc, kobj)

#define show_cppc_data(access_fn, struct_name, member_name)		\
	static ssize_t show_##member_name(struct kobject *kobj,		\
				struct kobj_attribute *attr, char *buf)	\
	{								\
		struct cpc_desc *cpc_ptr = to_cpc_desc(kobj);		\
		struct struct_name st_name = {0};			\
		int ret;						\
									\
		ret = access_fn(cpc_ptr->cpu_id, &st_name);		\
		if (ret)						\
			return ret;					\
									\
		return scnprintf(buf, PAGE_SIZE, "%llu\n",		\
				(u64)st_name.member_name);		\
	}								\
	define_one_cppc_ro(member_name)

show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, highest_perf);
show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_perf);
show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_perf);
show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_nonlinear_perf);
show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_freq);
show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_freq);

show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, reference_perf);
show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time);

static ssize_t show_feedback_ctrs(struct kobject *kobj,
		struct kobj_attribute *attr, char *buf)
{
	struct cpc_desc *cpc_ptr = to_cpc_desc(kobj);
	struct cppc_perf_fb_ctrs fb_ctrs = {0};
	int ret;

	ret = cppc_get_perf_ctrs(cpc_ptr->cpu_id, &fb_ctrs);
	if (ret)
		return ret;

	return scnprintf(buf, PAGE_SIZE, "ref:%llu del:%llu\n",
			fb_ctrs.reference, fb_ctrs.delivered);
}
define_one_cppc_ro(feedback_ctrs);

static struct attribute *cppc_attrs[] = {
	&feedback_ctrs.attr,
	&reference_perf.attr,
	&wraparound_time.attr,
	&highest_perf.attr,
	&lowest_perf.attr,
	&lowest_nonlinear_perf.attr,
	&nominal_perf.attr,
	&nominal_freq.attr,
	&lowest_freq.attr,
	NULL
};

static struct kobj_type cppc_ktype = {
	.sysfs_ops = &kobj_sysfs_ops,
	.default_attrs = cppc_attrs,
};

static int check_pcc_chan(int pcc_ss_id, bool chk_err_bit)
{
	int ret, status;
	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
	struct acpi_pcct_shared_memory __iomem *generic_comm_base =
		pcc_ss_data->pcc_comm_addr;

	if (!pcc_ss_data->platform_owns_pcc)
		return 0;

	/*
	 * Poll PCC status register every 3us(delay_us) for maximum of
	 * deadline_us(timeout_us) until PCC command complete bit is set(cond)
	 */
	ret = readw_relaxed_poll_timeout(&generic_comm_base->status, status,
					status & PCC_CMD_COMPLETE_MASK, 3,
					pcc_ss_data->deadline_us);

	if (likely(!ret)) {
		pcc_ss_data->platform_owns_pcc = false;
		if (chk_err_bit && (status & PCC_ERROR_MASK))
			ret = -EIO;
	}

	if (unlikely(ret))
		pr_err("PCC check channel failed for ss: %d. ret=%d\n",
		       pcc_ss_id, ret);

	return ret;
}

/*
 * This function transfers the ownership of the PCC to the platform
 * So it must be called while holding write_lock(pcc_lock)
 */
static int send_pcc_cmd(int pcc_ss_id, u16 cmd)
{
	int ret = -EIO, i;
	struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id];
	struct acpi_pcct_shared_memory __iomem *generic_comm_base =
		pcc_ss_data->pcc_comm_addr;
	unsigned int time_delta;

	/*
	 * For CMD_WRITE we know for a fact the caller should have checked
	 * the channel before writing to PCC space
	 */
	if (cmd == CMD_READ) {
		/*
		 * If there are pending cpc_writes, then we stole the channel
		 * before write completion, so first send a WRITE command to
		 * platform
		 */
		if (pcc_ss_data->pending_pcc_write_cmd)
			send_pcc_cmd(pcc_ss_id, CMD_WRITE);

		ret = check_pcc_chan(pcc_ss_id, false);
		if (ret)
			goto end;
	} else /* CMD_WRITE */
		pcc_ss_data->pending_pcc_write_cmd = FALSE;

	/*
	 * Handle the Minimum Request Turnaround Time(MRTT)
	 * "The minimum amount of time that OSPM must wait after the completion
	 * of a command before issuing the next command, in microseconds"
	 */
	if (pcc_ss_data->pcc_mrtt) {
		time_delta = ktime_us_delta(ktime_get(),
					    pcc_ss_data->last_cmd_cmpl_time);
		if (pcc_ss_data->pcc_mrtt > time_delta)
			udelay(pcc_ss_data->pcc_mrtt - time_delta);
	}

	/*
	 * Handle the non-zero Maximum Periodic Access Rate(MPAR)
	 * "The maximum number of periodic requests that the subspace channel can
	 * support, reported in commands per minute. 0 indicates no limitation."
	 *
	 * This parameter should be ideally zero or large enough so that it can
	 * handle maximum number of requests that all the cores in the system can
	 * collectively generate. If it is not, we will follow the spec and just
	 * not send the request to the platform after hitting the MPAR limit in
	 * any 60s window
	 */
	if (pcc_ss_data->pcc_mpar) {
		if (pcc_ss_data->mpar_count == 0) {
			time_delta = ktime_ms_delta(ktime_get(),
						    pcc_ss_data->last_mpar_reset);
			if ((time_delta < 60 * MSEC_PER_SEC) && pcc_ss_data->last_mpar_reset) {
				pr_debug("PCC cmd for subspace %d not sent due to MPAR limit",
					 pcc_ss_id);
				ret = -EIO;
				goto end;
			}
			pcc_ss_data->last_mpar_reset = ktime_get();
			pcc_ss_data->mpar_count = pcc_ss_data->pcc_mpar;
		}
		pcc_ss_data->mpar_count--;
	}

	/* Write to the shared comm region. */
	writew_relaxed(cmd, &generic_comm_base->command);

	/* Flip CMD COMPLETE bit */
	writew_relaxed(0, &generic_comm_base->status);

	pcc_ss_data->platform_owns_pcc = true;

	/* Ring doorbell */
	ret = mbox_send_message(pcc_ss_data->pcc_channel, &cmd);
	if (ret < 0) {
		pr_err("Err sending PCC mbox message. ss: %d cmd:%d, ret:%d\n",
		       pcc_ss_id, cmd, ret);
		goto end;
	}

	/* wait for completion and check for PCC errro bit */
	ret = check_pcc_chan(pcc_ss_id, true);

	if (pcc_ss_data->pcc_mrtt)
		pcc_ss_data->last_cmd_cmpl_time = ktime_get();

	if (pcc_ss_data->pcc_channel->mbox->txdone_irq)
		mbox_chan_txdone(pcc_ss_data->pcc_channel, ret);
	else
		mbox_client_txdone(pcc_ss_data->pcc_channel, ret);

end:
	if (cmd == CMD_WRITE) {
		if (unlikely(ret)) {
			for_each_possible_cpu(i) {
				struct cpc_desc *desc = per_cpu(cpc_desc_ptr, i);

				if (!desc)
					continue;

				if (desc->write_cmd_id == pcc_ss_data->pcc_write_cnt)
					desc->write_cmd_status = ret;
			}
		}
		pcc_ss_data->pcc_write_cnt++;
		wake_up_all(&pcc_ss_data->pcc_write_wait_q);
	}

	return ret;
}

static void cppc_chan_tx_done(struct mbox_client *cl, void *msg, int ret)
{
	if (ret < 0)
		pr_debug("TX did not complete: CMD sent:%x, ret:%d\n",
				*(u16 *)msg, ret);
	else
		pr_debug("TX completed. CMD sent:%x, ret:%d\n",
				*(u16 *)msg, ret);
}

static struct mbox_client cppc_mbox_cl = {
	.tx_done = cppc_chan_tx_done,
	.knows_txdone = true,
};

static int acpi_get_psd(struct cpc_desc *cpc_ptr, acpi_handle handle)
{
	int result = -EFAULT;
	acpi_status status = AE_OK;
	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
	struct acpi_buffer format = {sizeof("NNNNN"), "NNNNN"};
	struct acpi_buffer state = {0, NULL};
	union acpi_object  *psd = NULL;
	struct acpi_psd_package *pdomain;

	status = acpi_evaluate_object_typed(handle, "_PSD", NULL,
					    &buffer, ACPI_TYPE_PACKAGE);
	if (status == AE_NOT_FOUND)	/* _PSD is optional */
		return 0;
	if (ACPI_FAILURE(status))
		return -ENODEV;

	psd = buffer.pointer;
	if (!psd || psd->package.count != 1) {
		pr_debug("Invalid _PSD data\n");
		goto end;
	}

	pdomain = &(cpc_ptr->domain_info);

	state.length = sizeof(struct acpi_psd_package);
	state.pointer = pdomain;

	status = acpi_extract_package(&(psd->package.elements[0]),
		&format, &state);
	if (ACPI_FAILURE(status)) {
		pr_debug("Invalid _PSD data for CPU:%d\n", cpc_ptr->cpu_id);
		goto end;
	}

	if (pdomain->num_entries != ACPI_PSD_REV0_ENTRIES) {
		pr_debug("Unknown _PSD:num_entries for CPU:%d\n", cpc_ptr->cpu_id);
		goto end;
	}

	if (pdomain->revision != ACPI_PSD_REV0_REVISION) {
		pr_debug("Unknown _PSD:revision for CPU: %d\n", cpc_ptr->cpu_id);
		goto end;
	}

	if (pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ALL &&
	    pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ANY &&
	    pdomain->coord_type != DOMAIN_COORD_TYPE_HW_ALL) {
		pr_debug("Invalid _PSD:coord_type for CPU:%d\n", cpc_ptr->cpu_id);
		goto end;
	}

	result = 0;
end:
	kfree(buffer.pointer);
	return result;
}

bool acpi_cpc_valid(void)
{
	struct cpc_desc *cpc_ptr;
	int cpu;

	for_each_possible_cpu(cpu) {
		cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
		if (!cpc_ptr)
			return false;
	}

	return true;
}
EXPORT_SYMBOL_GPL(acpi_cpc_valid);

/**
 * acpi_get_psd_map - Map the CPUs in the freq domain of a given cpu
 * @cpu: Find all CPUs that share a domain with cpu.
 * @cpu_data: Pointer to CPU specific CPPC data including PSD info.
 *
 *	Return: 0 for success or negative value for err.
 */
int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data)
{
	struct cpc_desc *cpc_ptr, *match_cpc_ptr;
	struct acpi_psd_package *match_pdomain;
	struct acpi_psd_package *pdomain;
	int count_target, i;

	/*
	 * Now that we have _PSD data from all CPUs, let's setup P-state
	 * domain info.
	 */
	cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
	if (!cpc_ptr)
		return -EFAULT;

	pdomain = &(cpc_ptr->domain_info);
	cpumask_set_cpu(cpu, cpu_data->shared_cpu_map);
	if (pdomain->num_processors <= 1)
		return 0;

	/* Validate the Domain info */
	count_target = pdomain->num_processors;
	if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
		cpu_data->shared_type = CPUFREQ_SHARED_TYPE_ALL;
	else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
		cpu_data->shared_type = CPUFREQ_SHARED_TYPE_HW;
	else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
		cpu_data->shared_type = CPUFREQ_SHARED_TYPE_ANY;

	for_each_possible_cpu(i) {
		if (i == cpu)
			continue;

		match_cpc_ptr = per_cpu(cpc_desc_ptr, i);
		if (!match_cpc_ptr)
			goto err_fault;

		match_pdomain = &(match_cpc_ptr->domain_info);
		if (match_pdomain->domain != pdomain->domain)
			continue;

		/* Here i and cpu are in the same domain */
		if (match_pdomain->num_processors != count_target)
			goto err_fault;

		if (pdomain->coord_type != match_pdomain->coord_type)
			goto err_fault;

		cpumask_set_cpu(i, cpu_data->shared_cpu_map);
	}

	return 0;

err_fault:
	/* Assume no coordination on any error parsing domain info */
	cpumask_clear(cpu_data->shared_cpu_map);
	cpumask_set_cpu(cpu, cpu_data->shared_cpu_map);
	cpu_data->shared_type = CPUFREQ_SHARED_TYPE_NONE;

	return -EFAULT;
}
EXPORT_SYMBOL_GPL(acpi_get_psd_map);

static int register_pcc_channel(int pcc_ss_idx)
{
	struct acpi_pcct_hw_reduced *cppc_ss;
	u64 usecs_lat;

	if (pcc_ss_idx >= 0) {
		pcc_data[pcc_ss_idx]->pcc_channel =
			pcc_mbox_request_channel(&cppc_mbox_cl,	pcc_ss_idx);

		if (IS_ERR(pcc_data[pcc_ss_idx]->pcc_channel)) {
			pr_err("Failed to find PCC channel for subspace %d\n",
			       pcc_ss_idx);
			return -ENODEV;
		}

		/*
		 * The PCC mailbox controller driver should
		 * have parsed the PCCT (global table of all
		 * PCC channels) and stored pointers to the
		 * subspace communication region in con_priv.
		 */
		cppc_ss = (pcc_data[pcc_ss_idx]->pcc_channel)->con_priv;

		if (!cppc_ss) {
			pr_err("No PCC subspace found for %d CPPC\n",
			       pcc_ss_idx);
			return -ENODEV;
		}

		/*
		 * cppc_ss->latency is just a Nominal value. In reality
		 * the remote processor could be much slower to reply.
		 * So add an arbitrary amount of wait on top of Nominal.
		 */
		usecs_lat = NUM_RETRIES * cppc_ss->latency;
		pcc_data[pcc_ss_idx]->deadline_us = usecs_lat;
		pcc_data[pcc_ss_idx]->pcc_mrtt = cppc_ss->min_turnaround_time;
		pcc_data[pcc_ss_idx]->pcc_mpar = cppc_ss->max_access_rate;
		pcc_data[pcc_ss_idx]->pcc_nominal = cppc_ss->latency;

		pcc_data[pcc_ss_idx]->pcc_comm_addr =
			acpi_os_ioremap(cppc_ss->base_address, cppc_ss->length);
		if (!pcc_data[pcc_ss_idx]->pcc_comm_addr) {
			pr_err("Failed to ioremap PCC comm region mem for %d\n",
			       pcc_ss_idx);
			return -ENOMEM;
		}

		/* Set flag so that we don't come here for each CPU. */
		pcc_data[pcc_ss_idx]->pcc_channel_acquired = true;
	}

	return 0;
}

/**
 * cpc_ffh_supported() - check if FFH reading supported
 *
 * Check if the architecture has support for functional fixed hardware
 * read/write capability.
 *
 * Return: true for supported, false for not supported
 */
bool __weak cpc_ffh_supported(void)
{
	return false;
}

/**
 * pcc_data_alloc() - Allocate the pcc_data memory for pcc subspace
 *
 * Check and allocate the cppc_pcc_data memory.
 * In some processor configurations it is possible that same subspace
 * is shared between multiple CPUs. This is seen especially in CPUs
 * with hardware multi-threading support.
 *
 * Return: 0 for success, errno for failure
 */
static int pcc_data_alloc(int pcc_ss_id)
{
	if (pcc_ss_id < 0 || pcc_ss_id >= MAX_PCC_SUBSPACES)
		return -EINVAL;

	if (pcc_data[pcc_ss_id]) {
		pcc_data[pcc_ss_id]->refcount++;
	} else {
		pcc_data[pcc_ss_id] = kzalloc(sizeof(struct cppc_pcc_data),
					      GFP_KERNEL);
		if (!pcc_data[pcc_ss_id])
			return -ENOMEM;
		pcc_data[pcc_ss_id]->refcount++;
	}

	return 0;
}

/* Check if CPPC revision + num_ent combination is supported */
static bool is_cppc_supported(int revision, int num_ent)
{
	int expected_num_ent;

	switch (revision) {
	case CPPC_V2_REV:
		expected_num_ent = CPPC_V2_NUM_ENT;
		break;
	case CPPC_V3_REV:
		expected_num_ent = CPPC_V3_NUM_ENT;
		break;
	default:
		pr_debug("Firmware exports unsupported CPPC revision: %d\n",
			revision);
		return false;
	}

	if (expected_num_ent != num_ent) {
		pr_debug("Firmware exports %d entries. Expected: %d for CPPC rev:%d\n",
			num_ent, expected_num_ent, revision);
		return false;
	}

	return true;
}

/*
 * An example CPC table looks like the following.
 *
 *	Name(_CPC, Package()
 *			{
 *			17,
 *			NumEntries
 *			1,
 *			// Revision
 *			ResourceTemplate(){Register(PCC, 32, 0, 0x120, 2)},
 *			// Highest Performance
 *			ResourceTemplate(){Register(PCC, 32, 0, 0x124, 2)},
 *			// Nominal Performance
 *			ResourceTemplate(){Register(PCC, 32, 0, 0x128, 2)},
 *			// Lowest Nonlinear Performance
 *			ResourceTemplate(){Register(PCC, 32, 0, 0x12C, 2)},
 *			// Lowest Performance
 *			ResourceTemplate(){Register(PCC, 32, 0, 0x130, 2)},
 *			// Guaranteed Performance Register
 *			ResourceTemplate(){Register(PCC, 32, 0, 0x110, 2)},
 *			// Desired Performance Register
 *			ResourceTemplate(){Register(SystemMemory, 0, 0, 0, 0)},
 *			..
 *			..
 *			..
 *
 *		}
 * Each Register() encodes how to access that specific register.
 * e.g. a sample PCC entry has the following encoding:
 *
 *	Register (
 *		PCC,
 *		AddressSpaceKeyword
 *		8,
 *		//RegisterBitWidth
 *		8,
 *		//RegisterBitOffset
 *		0x30,
 *		//RegisterAddress
 *		9
 *		//AccessSize (subspace ID)
 *		0
 *		)
 *	}
 */

#ifndef init_freq_invariance_cppc
static inline void init_freq_invariance_cppc(void) { }
#endif

/**
 * acpi_cppc_processor_probe - Search for per CPU _CPC objects.
 * @pr: Ptr to acpi_processor containing this CPU's logical ID.
 *
 *	Return: 0 for success or negative value for err.
 */
int acpi_cppc_processor_probe(struct acpi_processor *pr)
{
	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
	union acpi_object *out_obj, *cpc_obj;
	struct cpc_desc *cpc_ptr;
	struct cpc_reg *gas_t;
	struct device *cpu_dev;
	acpi_handle handle = pr->handle;
	unsigned int num_ent, i, cpc_rev;
	int pcc_subspace_id = -1;
	acpi_status status;
	int ret = -EFAULT;

	/* Parse the ACPI _CPC table for this CPU. */
	status = acpi_evaluate_object_typed(handle, "_CPC", NULL, &output,
			ACPI_TYPE_PACKAGE);
	if (ACPI_FAILURE(status)) {
		ret = -ENODEV;
		goto out_buf_free;
	}

	out_obj = (union acpi_object *) output.pointer;

	cpc_ptr = kzalloc(sizeof(struct cpc_desc), GFP_KERNEL);
	if (!cpc_ptr) {
		ret = -ENOMEM;
		goto out_buf_free;
	}

	/* First entry is NumEntries. */
	cpc_obj = &out_obj->package.elements[0];
	if (cpc_obj->type == ACPI_TYPE_INTEGER)	{
		num_ent = cpc_obj->integer.value;
	} else {
		pr_debug("Unexpected entry type(%d) for NumEntries\n",
				cpc_obj->type);
		goto out_free;
	}
	cpc_ptr->num_entries = num_ent;

	/* Second entry should be revision. */
	cpc_obj = &out_obj->package.elements[1];
	if (cpc_obj->type == ACPI_TYPE_INTEGER)	{
		cpc_rev = cpc_obj->integer.value;
	} else {
		pr_debug("Unexpected entry type(%d) for Revision\n",
				cpc_obj->type);
		goto out_free;
	}
	cpc_ptr->version = cpc_rev;

	if (!is_cppc_supported(cpc_rev, num_ent))
		goto out_free;

	/* Iterate through remaining entries in _CPC */
	for (i = 2; i < num_ent; i++) {
		cpc_obj = &out_obj->package.elements[i];

		if (cpc_obj->type == ACPI_TYPE_INTEGER)	{
			cpc_ptr->cpc_regs[i-2].type = ACPI_TYPE_INTEGER;
			cpc_ptr->cpc_regs[i-2].cpc_entry.int_value = cpc_obj->integer.value;
		} else if (cpc_obj->type == ACPI_TYPE_BUFFER) {
			gas_t = (struct cpc_reg *)
				cpc_obj->buffer.pointer;

			/*
			 * The PCC Subspace index is encoded inside
			 * the CPC table entries. The same PCC index
			 * will be used for all the PCC entries,
			 * so extract it only once.
			 */
			if (gas_t->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) {
				if (pcc_subspace_id < 0) {
					pcc_subspace_id = gas_t->access_width;
					if (pcc_data_alloc(pcc_subspace_id))
						goto out_free;
				} else if (pcc_subspace_id != gas_t->access_width) {
					pr_debug("Mismatched PCC ids.\n");
					goto out_free;
				}
			} else if (gas_t->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
				if (gas_t->address) {
					void __iomem *addr;

					addr = ioremap(gas_t->address, gas_t->bit_width/8);
					if (!addr)
						goto out_free;
					cpc_ptr->cpc_regs[i-2].sys_mem_vaddr = addr;
				}
			} else {
				if (gas_t->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE || !cpc_ffh_supported()) {
					/* Support only PCC ,SYS MEM and FFH type regs */
					pr_debug("Unsupported register type: %d\n", gas_t->space_id);
					goto out_free;
				}
			}

			cpc_ptr->cpc_regs[i-2].type = ACPI_TYPE_BUFFER;
			memcpy(&cpc_ptr->cpc_regs[i-2].cpc_entry.reg, gas_t, sizeof(*gas_t));
		} else {
			pr_debug("Err in entry:%d in CPC table of CPU:%d\n", i, pr->id);
			goto out_free;
		}
	}
	per_cpu(cpu_pcc_subspace_idx, pr->id) = pcc_subspace_id;

	/*
	 * Initialize the remaining cpc_regs as unsupported.
	 * Example: In case FW exposes CPPC v2, the below loop will initialize
	 * LOWEST_FREQ and NOMINAL_FREQ regs as unsupported
	 */
	for (i = num_ent - 2; i < MAX_CPC_REG_ENT; i++) {
		cpc_ptr->cpc_regs[i].type = ACPI_TYPE_INTEGER;
		cpc_ptr->cpc_regs[i].cpc_entry.int_value = 0;
	}


	/* Store CPU Logical ID */
	cpc_ptr->cpu_id = pr->id;

	/* Parse PSD data for this CPU */
	ret = acpi_get_psd(cpc_ptr, handle);
	if (ret)
		goto out_free;

	/* Register PCC channel once for all PCC subspace ID. */
	if (pcc_subspace_id >= 0 && !pcc_data[pcc_subspace_id]->pcc_channel_acquired) {
		ret = register_pcc_channel(pcc_subspace_id);
		if (ret)
			goto out_free;

		init_rwsem(&pcc_data[pcc_subspace_id]->pcc_lock);
		init_waitqueue_head(&pcc_data[pcc_subspace_id]->pcc_write_wait_q);
	}

	/* Everything looks okay */
	pr_debug("Parsed CPC struct for CPU: %d\n", pr->id);

	/* Add per logical CPU nodes for reading its feedback counters. */
	cpu_dev = get_cpu_device(pr->id);
	if (!cpu_dev) {
		ret = -EINVAL;
		goto out_free;
	}

	/* Plug PSD data into this CPU's CPC descriptor. */
	per_cpu(cpc_desc_ptr, pr->id) = cpc_ptr;

	ret = kobject_init_and_add(&cpc_ptr->kobj, &cppc_ktype, &cpu_dev->kobj,
			"acpi_cppc");
	if (ret) {
		per_cpu(cpc_desc_ptr, pr->id) = NULL;
		kobject_put(&cpc_ptr->kobj);
		goto out_free;
	}

	init_freq_invariance_cppc();

	kfree(output.pointer);
	return 0;

out_free:
	/* Free all the mapped sys mem areas for this CPU */
	for (i = 2; i < cpc_ptr->num_entries; i++) {
		void __iomem *addr = cpc_ptr->cpc_regs[i-2].sys_mem_vaddr;

		if (addr)
			iounmap(addr);
	}
	kfree(cpc_ptr);

out_buf_free:
	kfree(output.pointer);
	return ret;
}
EXPORT_SYMBOL_GPL(acpi_cppc_processor_probe);

/**
 * acpi_cppc_processor_exit - Cleanup CPC structs.
 * @pr: Ptr to acpi_processor containing this CPU's logical ID.
 *
 * Return: Void
 */
void acpi_cppc_processor_exit(struct acpi_processor *pr)
{
	struct cpc_desc *cpc_ptr;
	unsigned int i;
	void __iomem *addr;
	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, pr->id);

	if (pcc_ss_id >= 0 && pcc_data[pcc_ss_id]) {
		if (pcc_data[pcc_ss_id]->pcc_channel_acquired) {
			pcc_data[pcc_ss_id]->refcount--;
			if (!pcc_data[pcc_ss_id]->refcount) {
				pcc_mbox_free_channel(pcc_data[pcc_ss_id]->pcc_channel);
				kfree(pcc_data[pcc_ss_id]);
				pcc_data[pcc_ss_id] = NULL;
			}
		}
	}

	cpc_ptr = per_cpu(cpc_desc_ptr, pr->id);
	if (!cpc_ptr)
		return;

	/* Free all the mapped sys mem areas for this CPU */
	for (i = 2; i < cpc_ptr->num_entries; i++) {
		addr = cpc_ptr->cpc_regs[i-2].sys_mem_vaddr;
		if (addr)
			iounmap(addr);
	}

	kobject_put(&cpc_ptr->kobj);
	kfree(cpc_ptr);
}
EXPORT_SYMBOL_GPL(acpi_cppc_processor_exit);

/**
 * cpc_read_ffh() - Read FFH register
 * @cpunum:	CPU number to read
 * @reg:	cppc register information
 * @val:	place holder for return value
 *
 * Read bit_width bits from a specified address and bit_offset
 *
 * Return: 0 for success and error code
 */
int __weak cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
{
	return -ENOTSUPP;
}

/**
 * cpc_write_ffh() - Write FFH register
 * @cpunum:	CPU number to write
 * @reg:	cppc register information
 * @val:	value to write
 *
 * Write value of bit_width bits to a specified address and bit_offset
 *
 * Return: 0 for success and error code
 */
int __weak cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
{
	return -ENOTSUPP;
}

/*
 * Since cpc_read and cpc_write are called while holding pcc_lock, it should be
 * as fast as possible. We have already mapped the PCC subspace during init, so
 * we can directly write to it.
 */

static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val)
{
	int ret_val = 0;
	void __iomem *vaddr = NULL;
	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
	struct cpc_reg *reg = &reg_res->cpc_entry.reg;

	if (reg_res->type == ACPI_TYPE_INTEGER) {
		*val = reg_res->cpc_entry.int_value;
		return ret_val;
	}

	*val = 0;
	if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0)
		vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id);
	else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
		vaddr = reg_res->sys_mem_vaddr;
	else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE)
		return cpc_read_ffh(cpu, reg, val);
	else
		return acpi_os_read_memory((acpi_physical_address)reg->address,
				val, reg->bit_width);

	switch (reg->bit_width) {
	case 8:
		*val = readb_relaxed(vaddr);
		break;
	case 16:
		*val = readw_relaxed(vaddr);
		break;
	case 32:
		*val = readl_relaxed(vaddr);
		break;
	case 64:
		*val = readq_relaxed(vaddr);
		break;
	default:
		pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n",
			 reg->bit_width, pcc_ss_id);
		ret_val = -EFAULT;
	}

	return ret_val;
}

static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
{
	int ret_val = 0;
	void __iomem *vaddr = NULL;
	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
	struct cpc_reg *reg = &reg_res->cpc_entry.reg;

	if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0)
		vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id);
	else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
		vaddr = reg_res->sys_mem_vaddr;
	else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE)
		return cpc_write_ffh(cpu, reg, val);
	else
		return acpi_os_write_memory((acpi_physical_address)reg->address,
				val, reg->bit_width);

	switch (reg->bit_width) {
	case 8:
		writeb_relaxed(val, vaddr);
		break;
	case 16:
		writew_relaxed(val, vaddr);
		break;
	case 32:
		writel_relaxed(val, vaddr);
		break;
	case 64:
		writeq_relaxed(val, vaddr);
		break;
	default:
		pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n",
			 reg->bit_width, pcc_ss_id);
		ret_val = -EFAULT;
		break;
	}

	return ret_val;
}

/**
 * cppc_get_desired_perf - Get the value of desired performance register.
 * @cpunum: CPU from which to get desired performance.
 * @desired_perf: address of a variable to store the returned desired performance
 *
 * Return: 0 for success, -EIO otherwise.
 */
int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
{
	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
	struct cpc_register_resource *desired_reg;
	struct cppc_pcc_data *pcc_ss_data = NULL;

	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];

	if (CPC_IN_PCC(desired_reg)) {
		int ret = 0;

		if (pcc_ss_id < 0)
			return -EIO;

		pcc_ss_data = pcc_data[pcc_ss_id];

		down_write(&pcc_ss_data->pcc_lock);

		if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0)
			cpc_read(cpunum, desired_reg, desired_perf);
		else
			ret = -EIO;

		up_write(&pcc_ss_data->pcc_lock);

		return ret;
	}

	cpc_read(cpunum, desired_reg, desired_perf);

	return 0;
}
EXPORT_SYMBOL_GPL(cppc_get_desired_perf);

/**
 * cppc_get_perf_caps - Get a CPU's performance capabilities.
 * @cpunum: CPU from which to get capabilities info.
 * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h
 *
 * Return: 0 for success with perf_caps populated else -ERRNO.
 */
int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
{
	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
	struct cpc_register_resource *highest_reg, *lowest_reg,
		*lowest_non_linear_reg, *nominal_reg, *guaranteed_reg,
		*low_freq_reg = NULL, *nom_freq_reg = NULL;
	u64 high, low, guaranteed, nom, min_nonlinear, low_f = 0, nom_f = 0;
	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
	struct cppc_pcc_data *pcc_ss_data = NULL;
	int ret = 0, regs_in_pcc = 0;

	if (!cpc_desc) {
		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
		return -ENODEV;
	}

	highest_reg = &cpc_desc->cpc_regs[HIGHEST_PERF];
	lowest_reg = &cpc_desc->cpc_regs[LOWEST_PERF];
	lowest_non_linear_reg = &cpc_desc->cpc_regs[LOW_NON_LINEAR_PERF];
	nominal_reg = &cpc_desc->cpc_regs[NOMINAL_PERF];
	low_freq_reg = &cpc_desc->cpc_regs[LOWEST_FREQ];
	nom_freq_reg = &cpc_desc->cpc_regs[NOMINAL_FREQ];
	guaranteed_reg = &cpc_desc->cpc_regs[GUARANTEED_PERF];

	/* Are any of the regs PCC ?*/
	if (CPC_IN_PCC(highest_reg) || CPC_IN_PCC(lowest_reg) ||
		CPC_IN_PCC(lowest_non_linear_reg) || CPC_IN_PCC(nominal_reg) ||
		CPC_IN_PCC(low_freq_reg) || CPC_IN_PCC(nom_freq_reg)) {
		if (pcc_ss_id < 0) {
			pr_debug("Invalid pcc_ss_id\n");
			return -ENODEV;
		}
		pcc_ss_data = pcc_data[pcc_ss_id];
		regs_in_pcc = 1;
		down_write(&pcc_ss_data->pcc_lock);
		/* Ring doorbell once to update PCC subspace */
		if (send_pcc_cmd(pcc_ss_id, CMD_READ) < 0) {
			ret = -EIO;
			goto out_err;
		}
	}

	cpc_read(cpunum, highest_reg, &high);
	perf_caps->highest_perf = high;

	cpc_read(cpunum, lowest_reg, &low);
	perf_caps->lowest_perf = low;

	cpc_read(cpunum, nominal_reg, &nom);
	perf_caps->nominal_perf = nom;

	if (guaranteed_reg->type != ACPI_TYPE_BUFFER  ||
	    IS_NULL_REG(&guaranteed_reg->cpc_entry.reg)) {
		perf_caps->guaranteed_perf = 0;
	} else {
		cpc_read(cpunum, guaranteed_reg, &guaranteed);
		perf_caps->guaranteed_perf = guaranteed;
	}

	cpc_read(cpunum, lowest_non_linear_reg, &min_nonlinear);
	perf_caps->lowest_nonlinear_perf = min_nonlinear;

	if (!high || !low || !nom || !min_nonlinear)
		ret = -EFAULT;

	/* Read optional lowest and nominal frequencies if present */
	if (CPC_SUPPORTED(low_freq_reg))
		cpc_read(cpunum, low_freq_reg, &low_f);

	if (CPC_SUPPORTED(nom_freq_reg))
		cpc_read(cpunum, nom_freq_reg, &nom_f);

	perf_caps->lowest_freq = low_f;
	perf_caps->nominal_freq = nom_f;


out_err:
	if (regs_in_pcc)
		up_write(&pcc_ss_data->pcc_lock);
	return ret;
}
EXPORT_SYMBOL_GPL(cppc_get_perf_caps);

/**
 * cppc_get_perf_ctrs - Read a CPU's performance feedback counters.
 * @cpunum: CPU from which to read counters.
 * @perf_fb_ctrs: ptr to cppc_perf_fb_ctrs. See cppc_acpi.h
 *
 * Return: 0 for success with perf_fb_ctrs populated else -ERRNO.
 */
int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
{
	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
	struct cpc_register_resource *delivered_reg, *reference_reg,
		*ref_perf_reg, *ctr_wrap_reg;
	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
	struct cppc_pcc_data *pcc_ss_data = NULL;
	u64 delivered, reference, ref_perf, ctr_wrap_time;
	int ret = 0, regs_in_pcc = 0;

	if (!cpc_desc) {
		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
		return -ENODEV;
	}

	delivered_reg = &cpc_desc->cpc_regs[DELIVERED_CTR];
	reference_reg = &cpc_desc->cpc_regs[REFERENCE_CTR];
	ref_perf_reg = &cpc_desc->cpc_regs[REFERENCE_PERF];
	ctr_wrap_reg = &cpc_desc->cpc_regs[CTR_WRAP_TIME];

	/*
	 * If reference perf register is not supported then we should
	 * use the nominal perf value
	 */
	if (!CPC_SUPPORTED(ref_perf_reg))
		ref_perf_reg = &cpc_desc->cpc_regs[NOMINAL_PERF];

	/* Are any of the regs PCC ?*/
	if (CPC_IN_PCC(delivered_reg) || CPC_IN_PCC(reference_reg) ||
		CPC_IN_PCC(ctr_wrap_reg) || CPC_IN_PCC(ref_perf_reg)) {
		if (pcc_ss_id < 0) {
			pr_debug("Invalid pcc_ss_id\n");
			return -ENODEV;
		}
		pcc_ss_data = pcc_data[pcc_ss_id];
		down_write(&pcc_ss_data->pcc_lock);
		regs_in_pcc = 1;
		/* Ring doorbell once to update PCC subspace */
		if (send_pcc_cmd(pcc_ss_id, CMD_READ) < 0) {
			ret = -EIO;
			goto out_err;
		}
	}

	cpc_read(cpunum, delivered_reg, &delivered);
	cpc_read(cpunum, reference_reg, &reference);
	cpc_read(cpunum, ref_perf_reg, &ref_perf);

	/*
	 * Per spec, if ctr_wrap_time optional register is unsupported, then the
	 * performance counters are assumed to never wrap during the lifetime of
	 * platform
	 */
	ctr_wrap_time = (u64)(~((u64)0));
	if (CPC_SUPPORTED(ctr_wrap_reg))
		cpc_read(cpunum, ctr_wrap_reg, &ctr_wrap_time);

	if (!delivered || !reference ||	!ref_perf) {
		ret = -EFAULT;
		goto out_err;
	}

	perf_fb_ctrs->delivered = delivered;
	perf_fb_ctrs->reference = reference;
	perf_fb_ctrs->reference_perf = ref_perf;
	perf_fb_ctrs->wraparound_time = ctr_wrap_time;
out_err:
	if (regs_in_pcc)
		up_write(&pcc_ss_data->pcc_lock);
	return ret;
}
EXPORT_SYMBOL_GPL(cppc_get_perf_ctrs);

/**
 * cppc_set_perf - Set a CPU's performance controls.
 * @cpu: CPU for which to set performance controls.
 * @perf_ctrls: ptr to cppc_perf_ctrls. See cppc_acpi.h
 *
 * Return: 0 for success, -ERRNO otherwise.
 */
int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
{
	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
	struct cpc_register_resource *desired_reg;
	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
	struct cppc_pcc_data *pcc_ss_data = NULL;
	int ret = 0;

	if (!cpc_desc) {
		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
		return -ENODEV;
	}

	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];

	/*
	 * This is Phase-I where we want to write to CPC registers
	 * -> We want all CPUs to be able to execute this phase in parallel
	 *
	 * Since read_lock can be acquired by multiple CPUs simultaneously we
	 * achieve that goal here
	 */
	if (CPC_IN_PCC(desired_reg)) {
		if (pcc_ss_id < 0) {
			pr_debug("Invalid pcc_ss_id\n");
			return -ENODEV;
		}
		pcc_ss_data = pcc_data[pcc_ss_id];
		down_read(&pcc_ss_data->pcc_lock); /* BEGIN Phase-I */
		if (pcc_ss_data->platform_owns_pcc) {
			ret = check_pcc_chan(pcc_ss_id, false);
			if (ret) {
				up_read(&pcc_ss_data->pcc_lock);
				return ret;
			}
		}
		/*
		 * Update the pending_write to make sure a PCC CMD_READ will not
		 * arrive and steal the channel during the switch to write lock
		 */
		pcc_ss_data->pending_pcc_write_cmd = true;
		cpc_desc->write_cmd_id = pcc_ss_data->pcc_write_cnt;
		cpc_desc->write_cmd_status = 0;
	}

	/*
	 * Skip writing MIN/MAX until Linux knows how to come up with
	 * useful values.
	 */
	cpc_write(cpu, desired_reg, perf_ctrls->desired_perf);

	if (CPC_IN_PCC(desired_reg))
		up_read(&pcc_ss_data->pcc_lock);	/* END Phase-I */
	/*
	 * This is Phase-II where we transfer the ownership of PCC to Platform
	 *
	 * Short Summary: Basically if we think of a group of cppc_set_perf
	 * requests that happened in short overlapping interval. The last CPU to
	 * come out of Phase-I will enter Phase-II and ring the doorbell.
	 *
	 * We have the following requirements for Phase-II:
	 *     1. We want to execute Phase-II only when there are no CPUs
	 * currently executing in Phase-I
	 *     2. Once we start Phase-II we want to avoid all other CPUs from
	 * entering Phase-I.
	 *     3. We want only one CPU among all those who went through Phase-I
	 * to run phase-II
	 *
	 * If write_trylock fails to get the lock and doesn't transfer the
	 * PCC ownership to the platform, then one of the following will be TRUE
	 *     1. There is at-least one CPU in Phase-I which will later execute
	 * write_trylock, so the CPUs in Phase-I will be responsible for
	 * executing the Phase-II.
	 *     2. Some other CPU has beaten this CPU to successfully execute the
	 * write_trylock and has already acquired the write_lock. We know for a
	 * fact it (other CPU acquiring the write_lock) couldn't have happened
	 * before this CPU's Phase-I as we held the read_lock.
	 *     3. Some other CPU executing pcc CMD_READ has stolen the
	 * down_write, in which case, send_pcc_cmd will check for pending
	 * CMD_WRITE commands by checking the pending_pcc_write_cmd.
	 * So this CPU can be certain that its request will be delivered
	 *    So in all cases, this CPU knows that its request will be delivered
	 * by another CPU and can return
	 *
	 * After getting the down_write we still need to check for
	 * pending_pcc_write_cmd to take care of the following scenario
	 *    The thread running this code could be scheduled out between
	 * Phase-I and Phase-II. Before it is scheduled back on, another CPU
	 * could have delivered the request to Platform by triggering the
	 * doorbell and transferred the ownership of PCC to platform. So this
	 * avoids triggering an unnecessary doorbell and more importantly before
	 * triggering the doorbell it makes sure that the PCC channel ownership
	 * is still with OSPM.
	 *   pending_pcc_write_cmd can also be cleared by a different CPU, if
	 * there was a pcc CMD_READ waiting on down_write and it steals the lock
	 * before the pcc CMD_WRITE is completed. send_pcc_cmd checks for this
	 * case during a CMD_READ and if there are pending writes it delivers
	 * the write command before servicing the read command
	 */
	if (CPC_IN_PCC(desired_reg)) {
		if (down_write_trylock(&pcc_ss_data->pcc_lock)) {/* BEGIN Phase-II */
			/* Update only if there are pending write commands */
			if (pcc_ss_data->pending_pcc_write_cmd)
				send_pcc_cmd(pcc_ss_id, CMD_WRITE);
			up_write(&pcc_ss_data->pcc_lock);	/* END Phase-II */
		} else
			/* Wait until pcc_write_cnt is updated by send_pcc_cmd */
			wait_event(pcc_ss_data->pcc_write_wait_q,
				   cpc_desc->write_cmd_id != pcc_ss_data->pcc_write_cnt);

		/* send_pcc_cmd updates the status in case of failure */
		ret = cpc_desc->write_cmd_status;
	}
	return ret;
}
EXPORT_SYMBOL_GPL(cppc_set_perf);

/**
 * cppc_get_transition_latency - returns frequency transition latency in ns
 *
 * ACPI CPPC does not explicitly specify how a platform can specify the
 * transition latency for performance change requests. The closest we have
 * is the timing information from the PCCT tables which provides the info
 * on the number and frequency of PCC commands the platform can handle.
 */
unsigned int cppc_get_transition_latency(int cpu_num)
{
	/*
	 * Expected transition latency is based on the PCCT timing values
	 * Below are definition from ACPI spec:
	 * pcc_nominal- Expected latency to process a command, in microseconds
	 * pcc_mpar   - The maximum number of periodic requests that the subspace
	 *              channel can support, reported in commands per minute. 0
	 *              indicates no limitation.
	 * pcc_mrtt   - The minimum amount of time that OSPM must wait after the
	 *              completion of a command before issuing the next command,
	 *              in microseconds.
	 */
	unsigned int latency_ns = 0;
	struct cpc_desc *cpc_desc;
	struct cpc_register_resource *desired_reg;
	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu_num);
	struct cppc_pcc_data *pcc_ss_data;

	cpc_desc = per_cpu(cpc_desc_ptr, cpu_num);
	if (!cpc_desc)
		return CPUFREQ_ETERNAL;

	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
	if (!CPC_IN_PCC(desired_reg))
		return CPUFREQ_ETERNAL;

	if (pcc_ss_id < 0)
		return CPUFREQ_ETERNAL;

	pcc_ss_data = pcc_data[pcc_ss_id];
	if (pcc_ss_data->pcc_mpar)
		latency_ns = 60 * (1000 * 1000 * 1000 / pcc_ss_data->pcc_mpar);

	latency_ns = max(latency_ns, pcc_ss_data->pcc_nominal * 1000);
	latency_ns = max(latency_ns, pcc_ss_data->pcc_mrtt * 1000);

	return latency_ns;
}
EXPORT_SYMBOL_GPL(cppc_get_transition_latency);