summaryrefslogtreecommitdiff
path: root/arch/powerpc/platforms/powernv/idle.c
blob: 528a7e0cf83aac9961242fb07f3fc349a11b301d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * PowerNV cpuidle code
 *
 * Copyright 2015 IBM Corp.
 */

#include <linux/types.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/of.h>
#include <linux/device.h>
#include <linux/cpu.h>

#include <asm/asm-prototypes.h>
#include <asm/firmware.h>
#include <asm/interrupt.h>
#include <asm/machdep.h>
#include <asm/opal.h>
#include <asm/cputhreads.h>
#include <asm/cpuidle.h>
#include <asm/code-patching.h>
#include <asm/smp.h>
#include <asm/runlatch.h>
#include <asm/dbell.h>

#include "powernv.h"
#include "subcore.h"

/* Power ISA 3.0 allows for stop states 0x0 - 0xF */
#define MAX_STOP_STATE	0xF

#define P9_STOP_SPR_MSR 2000
#define P9_STOP_SPR_PSSCR      855

static u32 supported_cpuidle_states;
struct pnv_idle_states_t *pnv_idle_states;
int nr_pnv_idle_states;

/*
 * The default stop state that will be used by ppc_md.power_save
 * function on platforms that support stop instruction.
 */
static u64 pnv_default_stop_val;
static u64 pnv_default_stop_mask;
static bool default_stop_found;

/*
 * First stop state levels when SPR and TB loss can occur.
 */
static u64 pnv_first_tb_loss_level = MAX_STOP_STATE + 1;
static u64 deep_spr_loss_state = MAX_STOP_STATE + 1;

/*
 * psscr value and mask of the deepest stop idle state.
 * Used when a cpu is offlined.
 */
static u64 pnv_deepest_stop_psscr_val;
static u64 pnv_deepest_stop_psscr_mask;
static u64 pnv_deepest_stop_flag;
static bool deepest_stop_found;

static unsigned long power7_offline_type;

static int pnv_save_sprs_for_deep_states(void)
{
	int cpu;
	int rc;

	/*
	 * hid0, hid1, hid4, hid5, hmeer and lpcr values are symmetric across
	 * all cpus at boot. Get these reg values of current cpu and use the
	 * same across all cpus.
	 */
	uint64_t lpcr_val	= mfspr(SPRN_LPCR);
	uint64_t hid0_val	= mfspr(SPRN_HID0);
	uint64_t hmeer_val	= mfspr(SPRN_HMEER);
	uint64_t msr_val = MSR_IDLE;
	uint64_t psscr_val = pnv_deepest_stop_psscr_val;

	for_each_present_cpu(cpu) {
		uint64_t pir = get_hard_smp_processor_id(cpu);
		uint64_t hsprg0_val = (uint64_t)paca_ptrs[cpu];

		rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
		if (rc != 0)
			return rc;

		rc = opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
		if (rc != 0)
			return rc;

		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
			rc = opal_slw_set_reg(pir, P9_STOP_SPR_MSR, msr_val);
			if (rc)
				return rc;

			rc = opal_slw_set_reg(pir,
					      P9_STOP_SPR_PSSCR, psscr_val);

			if (rc)
				return rc;
		}

		/* HIDs are per core registers */
		if (cpu_thread_in_core(cpu) == 0) {

			rc = opal_slw_set_reg(pir, SPRN_HMEER, hmeer_val);
			if (rc != 0)
				return rc;

			rc = opal_slw_set_reg(pir, SPRN_HID0, hid0_val);
			if (rc != 0)
				return rc;

			/* Only p8 needs to set extra HID regiters */
			if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
				uint64_t hid1_val = mfspr(SPRN_HID1);
				uint64_t hid4_val = mfspr(SPRN_HID4);
				uint64_t hid5_val = mfspr(SPRN_HID5);

				rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val);
				if (rc != 0)
					return rc;

				rc = opal_slw_set_reg(pir, SPRN_HID4, hid4_val);
				if (rc != 0)
					return rc;

				rc = opal_slw_set_reg(pir, SPRN_HID5, hid5_val);
				if (rc != 0)
					return rc;
			}
		}
	}

	return 0;
}

u32 pnv_get_supported_cpuidle_states(void)
{
	return supported_cpuidle_states;
}
EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states);

static void pnv_fastsleep_workaround_apply(void *info)

{
	int rc;
	int *err = info;

	rc = opal_config_cpu_idle_state(OPAL_CONFIG_IDLE_FASTSLEEP,
					OPAL_CONFIG_IDLE_APPLY);
	if (rc)
		*err = 1;
}

static bool power7_fastsleep_workaround_entry = true;
static bool power7_fastsleep_workaround_exit = true;

/*
 * Used to store fastsleep workaround state
 * 0 - Workaround applied/undone at fastsleep entry/exit path (Default)
 * 1 - Workaround applied once, never undone.
 */
static u8 fastsleep_workaround_applyonce;

static ssize_t show_fastsleep_workaround_applyonce(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	return sprintf(buf, "%u\n", fastsleep_workaround_applyonce);
}

static ssize_t store_fastsleep_workaround_applyonce(struct device *dev,
		struct device_attribute *attr, const char *buf,
		size_t count)
{
	cpumask_t primary_thread_mask;
	int err;
	u8 val;

	if (kstrtou8(buf, 0, &val) || val != 1)
		return -EINVAL;

	if (fastsleep_workaround_applyonce == 1)
		return count;

	/*
	 * fastsleep_workaround_applyonce = 1 implies
	 * fastsleep workaround needs to be left in 'applied' state on all
	 * the cores. Do this by-
	 * 1. Disable the 'undo' workaround in fastsleep exit path
	 * 2. Sendi IPIs to all the cores which have at least one online thread
	 * 3. Disable the 'apply' workaround in fastsleep entry path
	 *
	 * There is no need to send ipi to cores which have all threads
	 * offlined, as last thread of the core entering fastsleep or deeper
	 * state would have applied workaround.
	 */
	power7_fastsleep_workaround_exit = false;

	get_online_cpus();
	primary_thread_mask = cpu_online_cores_map();
	on_each_cpu_mask(&primary_thread_mask,
				pnv_fastsleep_workaround_apply,
				&err, 1);
	put_online_cpus();
	if (err) {
		pr_err("fastsleep_workaround_applyonce change failed while running pnv_fastsleep_workaround_apply");
		goto fail;
	}

	power7_fastsleep_workaround_entry = false;

	fastsleep_workaround_applyonce = 1;

	return count;
fail:
	return -EIO;
}

static DEVICE_ATTR(fastsleep_workaround_applyonce, 0600,
			show_fastsleep_workaround_applyonce,
			store_fastsleep_workaround_applyonce);

static inline void atomic_start_thread_idle(void)
{
	int cpu = raw_smp_processor_id();
	int first = cpu_first_thread_sibling(cpu);
	int thread_nr = cpu_thread_in_core(cpu);
	unsigned long *state = &paca_ptrs[first]->idle_state;

	clear_bit(thread_nr, state);
}

static inline void atomic_stop_thread_idle(void)
{
	int cpu = raw_smp_processor_id();
	int first = cpu_first_thread_sibling(cpu);
	int thread_nr = cpu_thread_in_core(cpu);
	unsigned long *state = &paca_ptrs[first]->idle_state;

	set_bit(thread_nr, state);
}

static inline void atomic_lock_thread_idle(void)
{
	int cpu = raw_smp_processor_id();
	int first = cpu_first_thread_sibling(cpu);
	unsigned long *state = &paca_ptrs[first]->idle_state;

	while (unlikely(test_and_set_bit_lock(NR_PNV_CORE_IDLE_LOCK_BIT, state)))
		barrier();
}

static inline void atomic_unlock_and_stop_thread_idle(void)
{
	int cpu = raw_smp_processor_id();
	int first = cpu_first_thread_sibling(cpu);
	unsigned long thread = 1UL << cpu_thread_in_core(cpu);
	unsigned long *state = &paca_ptrs[first]->idle_state;
	u64 s = READ_ONCE(*state);
	u64 new, tmp;

	BUG_ON(!(s & PNV_CORE_IDLE_LOCK_BIT));
	BUG_ON(s & thread);

again:
	new = (s | thread) & ~PNV_CORE_IDLE_LOCK_BIT;
	tmp = cmpxchg(state, s, new);
	if (unlikely(tmp != s)) {
		s = tmp;
		goto again;
	}
}

static inline void atomic_unlock_thread_idle(void)
{
	int cpu = raw_smp_processor_id();
	int first = cpu_first_thread_sibling(cpu);
	unsigned long *state = &paca_ptrs[first]->idle_state;

	BUG_ON(!test_bit(NR_PNV_CORE_IDLE_LOCK_BIT, state));
	clear_bit_unlock(NR_PNV_CORE_IDLE_LOCK_BIT, state);
}

/* P7 and P8 */
struct p7_sprs {
	/* per core */
	u64 tscr;
	u64 worc;

	/* per subcore */
	u64 sdr1;
	u64 rpr;

	/* per thread */
	u64 lpcr;
	u64 hfscr;
	u64 fscr;
	u64 purr;
	u64 spurr;
	u64 dscr;
	u64 wort;

	/* per thread SPRs that get lost in shallow states */
	u64 amr;
	u64 iamr;
	u64 amor;
	u64 uamor;
};

static unsigned long power7_idle_insn(unsigned long type)
{
	int cpu = raw_smp_processor_id();
	int first = cpu_first_thread_sibling(cpu);
	unsigned long *state = &paca_ptrs[first]->idle_state;
	unsigned long thread = 1UL << cpu_thread_in_core(cpu);
	unsigned long core_thread_mask = (1UL << threads_per_core) - 1;
	unsigned long srr1;
	bool full_winkle;
	struct p7_sprs sprs = {}; /* avoid false use-uninitialised */
	bool sprs_saved = false;
	int rc;

	if (unlikely(type != PNV_THREAD_NAP)) {
		atomic_lock_thread_idle();

		BUG_ON(!(*state & thread));
		*state &= ~thread;

		if (power7_fastsleep_workaround_entry) {
			if ((*state & core_thread_mask) == 0) {
				rc = opal_config_cpu_idle_state(
						OPAL_CONFIG_IDLE_FASTSLEEP,
						OPAL_CONFIG_IDLE_APPLY);
				BUG_ON(rc);
			}
		}

		if (type == PNV_THREAD_WINKLE) {
			sprs.tscr	= mfspr(SPRN_TSCR);
			sprs.worc	= mfspr(SPRN_WORC);

			sprs.sdr1	= mfspr(SPRN_SDR1);
			sprs.rpr	= mfspr(SPRN_RPR);

			sprs.lpcr	= mfspr(SPRN_LPCR);
			if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
				sprs.hfscr	= mfspr(SPRN_HFSCR);
				sprs.fscr	= mfspr(SPRN_FSCR);
			}
			sprs.purr	= mfspr(SPRN_PURR);
			sprs.spurr	= mfspr(SPRN_SPURR);
			sprs.dscr	= mfspr(SPRN_DSCR);
			sprs.wort	= mfspr(SPRN_WORT);

			sprs_saved = true;

			/*
			 * Increment winkle counter and set all winkle bits if
			 * all threads are winkling. This allows wakeup side to
			 * distinguish between fast sleep and winkle state
			 * loss. Fast sleep still has to resync the timebase so
			 * this may not be a really big win.
			 */
			*state += 1 << PNV_CORE_IDLE_WINKLE_COUNT_SHIFT;
			if ((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS)
					>> PNV_CORE_IDLE_WINKLE_COUNT_SHIFT
					== threads_per_core)
				*state |= PNV_CORE_IDLE_THREAD_WINKLE_BITS;
			WARN_ON((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS) == 0);
		}

		atomic_unlock_thread_idle();
	}

	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
		sprs.amr	= mfspr(SPRN_AMR);
		sprs.iamr	= mfspr(SPRN_IAMR);
		sprs.amor	= mfspr(SPRN_AMOR);
		sprs.uamor	= mfspr(SPRN_UAMOR);
	}

	local_paca->thread_idle_state = type;
	srr1 = isa206_idle_insn_mayloss(type);		/* go idle */
	local_paca->thread_idle_state = PNV_THREAD_RUNNING;

	WARN_ON_ONCE(!srr1);
	WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR));

	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
		if ((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS) {
			/*
			 * We don't need an isync after the mtsprs here because
			 * the upcoming mtmsrd is execution synchronizing.
			 */
			mtspr(SPRN_AMR,		sprs.amr);
			mtspr(SPRN_IAMR,	sprs.iamr);
			mtspr(SPRN_AMOR,	sprs.amor);
			mtspr(SPRN_UAMOR,	sprs.uamor);
		}
	}

	if (unlikely((srr1 & SRR1_WAKEMASK_P8) == SRR1_WAKEHMI))
		hmi_exception_realmode(NULL);

	if (likely((srr1 & SRR1_WAKESTATE) != SRR1_WS_HVLOSS)) {
		if (unlikely(type != PNV_THREAD_NAP)) {
			atomic_lock_thread_idle();
			if (type == PNV_THREAD_WINKLE) {
				WARN_ON((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS) == 0);
				*state -= 1 << PNV_CORE_IDLE_WINKLE_COUNT_SHIFT;
				*state &= ~(thread << PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT);
			}
			atomic_unlock_and_stop_thread_idle();
		}
		return srr1;
	}

	/* HV state loss */
	BUG_ON(type == PNV_THREAD_NAP);

	atomic_lock_thread_idle();

	full_winkle = false;
	if (type == PNV_THREAD_WINKLE) {
		WARN_ON((*state & PNV_CORE_IDLE_WINKLE_COUNT_BITS) == 0);
		*state -= 1 << PNV_CORE_IDLE_WINKLE_COUNT_SHIFT;
		if (*state & (thread << PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT)) {
			*state &= ~(thread << PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT);
			full_winkle = true;
			BUG_ON(!sprs_saved);
		}
	}

	WARN_ON(*state & thread);

	if ((*state & core_thread_mask) != 0)
		goto core_woken;

	/* Per-core SPRs */
	if (full_winkle) {
		mtspr(SPRN_TSCR,	sprs.tscr);
		mtspr(SPRN_WORC,	sprs.worc);
	}

	if (power7_fastsleep_workaround_exit) {
		rc = opal_config_cpu_idle_state(OPAL_CONFIG_IDLE_FASTSLEEP,
						OPAL_CONFIG_IDLE_UNDO);
		BUG_ON(rc);
	}

	/* TB */
	if (opal_resync_timebase() != OPAL_SUCCESS)
		BUG();

core_woken:
	if (!full_winkle)
		goto subcore_woken;

	if ((*state & local_paca->subcore_sibling_mask) != 0)
		goto subcore_woken;

	/* Per-subcore SPRs */
	mtspr(SPRN_SDR1,	sprs.sdr1);
	mtspr(SPRN_RPR,		sprs.rpr);

subcore_woken:
	/*
	 * isync after restoring shared SPRs and before unlocking. Unlock
	 * only contains hwsync which does not necessarily do the right
	 * thing for SPRs.
	 */
	isync();
	atomic_unlock_and_stop_thread_idle();

	/* Fast sleep does not lose SPRs */
	if (!full_winkle)
		return srr1;

	/* Per-thread SPRs */
	mtspr(SPRN_LPCR,	sprs.lpcr);
	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
		mtspr(SPRN_HFSCR,	sprs.hfscr);
		mtspr(SPRN_FSCR,	sprs.fscr);
	}
	mtspr(SPRN_PURR,	sprs.purr);
	mtspr(SPRN_SPURR,	sprs.spurr);
	mtspr(SPRN_DSCR,	sprs.dscr);
	mtspr(SPRN_WORT,	sprs.wort);

	mtspr(SPRN_SPRG3,	local_paca->sprg_vdso);

	/*
	 * The SLB has to be restored here, but it sometimes still
	 * contains entries, so the __ variant must be used to prevent
	 * multi hits.
	 */
	__slb_restore_bolted_realmode();

	return srr1;
}

extern unsigned long idle_kvm_start_guest(unsigned long srr1);

#ifdef CONFIG_HOTPLUG_CPU
static unsigned long power7_offline(void)
{
	unsigned long srr1;

	mtmsr(MSR_IDLE);

#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
	/* Tell KVM we're entering idle. */
	/******************************************************/
	/*  N O T E   W E L L    ! ! !    N O T E   W E L L   */
	/* The following store to HSTATE_HWTHREAD_STATE(r13)  */
	/* MUST occur in real mode, i.e. with the MMU off,    */
	/* and the MMU must stay off until we clear this flag */
	/* and test HSTATE_HWTHREAD_REQ(r13) in               */
	/* pnv_powersave_wakeup in this file.                 */
	/* The reason is that another thread can switch the   */
	/* MMU to a guest context whenever this flag is set   */
	/* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on,    */
	/* that would potentially cause this thread to start  */
	/* executing instructions from guest memory in        */
	/* hypervisor mode, leading to a host crash or data   */
	/* corruption, or worse.                              */
	/******************************************************/
	local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE;
#endif

	__ppc64_runlatch_off();
	srr1 = power7_idle_insn(power7_offline_type);
	__ppc64_runlatch_on();

#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
	local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL;
	/* Order setting hwthread_state vs. testing hwthread_req */
	smp_mb();
	if (local_paca->kvm_hstate.hwthread_req)
		srr1 = idle_kvm_start_guest(srr1);
#endif

	mtmsr(MSR_KERNEL);

	return srr1;
}
#endif

void power7_idle_type(unsigned long type)
{
	unsigned long srr1;

	if (!prep_irq_for_idle_irqsoff())
		return;

	mtmsr(MSR_IDLE);
	__ppc64_runlatch_off();
	srr1 = power7_idle_insn(type);
	__ppc64_runlatch_on();
	mtmsr(MSR_KERNEL);

	fini_irq_for_idle_irqsoff();
	irq_set_pending_from_srr1(srr1);
}

static void power7_idle(void)
{
	if (!powersave_nap)
		return;

	power7_idle_type(PNV_THREAD_NAP);
}

struct p9_sprs {
	/* per core */
	u64 ptcr;
	u64 rpr;
	u64 tscr;
	u64 ldbar;

	/* per thread */
	u64 lpcr;
	u64 hfscr;
	u64 fscr;
	u64 pid;
	u64 purr;
	u64 spurr;
	u64 dscr;
	u64 wort;
	u64 ciabr;

	u64 mmcra;
	u32 mmcr0;
	u32 mmcr1;
	u64 mmcr2;

	/* per thread SPRs that get lost in shallow states */
	u64 amr;
	u64 iamr;
	u64 amor;
	u64 uamor;
};

static unsigned long power9_idle_stop(unsigned long psscr)
{
	int cpu = raw_smp_processor_id();
	int first = cpu_first_thread_sibling(cpu);
	unsigned long *state = &paca_ptrs[first]->idle_state;
	unsigned long core_thread_mask = (1UL << threads_per_core) - 1;
	unsigned long srr1;
	unsigned long pls;
	unsigned long mmcr0 = 0;
	unsigned long mmcra = 0;
	struct p9_sprs sprs = {}; /* avoid false used-uninitialised */
	bool sprs_saved = false;

	if (!(psscr & (PSSCR_EC|PSSCR_ESL))) {
		/* EC=ESL=0 case */

		/*
		 * Wake synchronously. SRESET via xscom may still cause
		 * a 0x100 powersave wakeup with SRR1 reason!
		 */
		srr1 = isa300_idle_stop_noloss(psscr);		/* go idle */
		if (likely(!srr1))
			return 0;

		/*
		 * Registers not saved, can't recover!
		 * This would be a hardware bug
		 */
		BUG_ON((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS);

		goto out;
	}

	/* EC=ESL=1 case */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
	if (cpu_has_feature(CPU_FTR_P9_TM_XER_SO_BUG)) {
		local_paca->requested_psscr = psscr;
		/* order setting requested_psscr vs testing dont_stop */
		smp_mb();
		if (atomic_read(&local_paca->dont_stop)) {
			local_paca->requested_psscr = 0;
			return 0;
		}
	}
#endif

	if (!cpu_has_feature(CPU_FTR_POWER9_DD2_1)) {
		 /*
		  * POWER9 DD2 can incorrectly set PMAO when waking up
		  * after a state-loss idle. Saving and restoring MMCR0
		  * over idle is a workaround.
		  */
		mmcr0		= mfspr(SPRN_MMCR0);
	}

	if ((psscr & PSSCR_RL_MASK) >= deep_spr_loss_state) {
		sprs.lpcr	= mfspr(SPRN_LPCR);
		sprs.hfscr	= mfspr(SPRN_HFSCR);
		sprs.fscr	= mfspr(SPRN_FSCR);
		sprs.pid	= mfspr(SPRN_PID);
		sprs.purr	= mfspr(SPRN_PURR);
		sprs.spurr	= mfspr(SPRN_SPURR);
		sprs.dscr	= mfspr(SPRN_DSCR);
		sprs.wort	= mfspr(SPRN_WORT);
		sprs.ciabr	= mfspr(SPRN_CIABR);

		sprs.mmcra	= mfspr(SPRN_MMCRA);
		sprs.mmcr0	= mfspr(SPRN_MMCR0);
		sprs.mmcr1	= mfspr(SPRN_MMCR1);
		sprs.mmcr2	= mfspr(SPRN_MMCR2);

		sprs.ptcr	= mfspr(SPRN_PTCR);
		sprs.rpr	= mfspr(SPRN_RPR);
		sprs.tscr	= mfspr(SPRN_TSCR);
		if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR))
			sprs.ldbar = mfspr(SPRN_LDBAR);

		sprs_saved = true;

		atomic_start_thread_idle();
	}

	sprs.amr	= mfspr(SPRN_AMR);
	sprs.iamr	= mfspr(SPRN_IAMR);
	sprs.amor	= mfspr(SPRN_AMOR);
	sprs.uamor	= mfspr(SPRN_UAMOR);

	srr1 = isa300_idle_stop_mayloss(psscr);		/* go idle */

#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
	local_paca->requested_psscr = 0;
#endif

	psscr = mfspr(SPRN_PSSCR);

	WARN_ON_ONCE(!srr1);
	WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR));

	if ((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS) {
		/*
		 * We don't need an isync after the mtsprs here because the
		 * upcoming mtmsrd is execution synchronizing.
		 */
		mtspr(SPRN_AMR,		sprs.amr);
		mtspr(SPRN_IAMR,	sprs.iamr);
		mtspr(SPRN_AMOR,	sprs.amor);
		mtspr(SPRN_UAMOR,	sprs.uamor);

		/*
		 * Workaround for POWER9 DD2.0, if we lost resources, the ERAT
		 * might have been corrupted and needs flushing. We also need
		 * to reload MMCR0 (see mmcr0 comment above).
		 */
		if (!cpu_has_feature(CPU_FTR_POWER9_DD2_1)) {
			asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT);
			mtspr(SPRN_MMCR0, mmcr0);
		}

		/*
		 * DD2.2 and earlier need to set then clear bit 60 in MMCRA
		 * to ensure the PMU starts running.
		 */
		mmcra = mfspr(SPRN_MMCRA);
		mmcra |= PPC_BIT(60);
		mtspr(SPRN_MMCRA, mmcra);
		mmcra &= ~PPC_BIT(60);
		mtspr(SPRN_MMCRA, mmcra);
	}

	if (unlikely((srr1 & SRR1_WAKEMASK_P8) == SRR1_WAKEHMI))
		hmi_exception_realmode(NULL);

	/*
	 * On POWER9, SRR1 bits do not match exactly as expected.
	 * SRR1_WS_GPRLOSS (10b) can also result in SPR loss, so
	 * just always test PSSCR for SPR/TB state loss.
	 */
	pls = (psscr & PSSCR_PLS) >> PSSCR_PLS_SHIFT;
	if (likely(pls < deep_spr_loss_state)) {
		if (sprs_saved)
			atomic_stop_thread_idle();
		goto out;
	}

	/* HV state loss */
	BUG_ON(!sprs_saved);

	atomic_lock_thread_idle();

	if ((*state & core_thread_mask) != 0)
		goto core_woken;

	/* Per-core SPRs */
	mtspr(SPRN_PTCR,	sprs.ptcr);
	mtspr(SPRN_RPR,		sprs.rpr);
	mtspr(SPRN_TSCR,	sprs.tscr);

	if (pls >= pnv_first_tb_loss_level) {
		/* TB loss */
		if (opal_resync_timebase() != OPAL_SUCCESS)
			BUG();
	}

	/*
	 * isync after restoring shared SPRs and before unlocking. Unlock
	 * only contains hwsync which does not necessarily do the right
	 * thing for SPRs.
	 */
	isync();

core_woken:
	atomic_unlock_and_stop_thread_idle();

	/* Per-thread SPRs */
	mtspr(SPRN_LPCR,	sprs.lpcr);
	mtspr(SPRN_HFSCR,	sprs.hfscr);
	mtspr(SPRN_FSCR,	sprs.fscr);
	mtspr(SPRN_PID,		sprs.pid);
	mtspr(SPRN_PURR,	sprs.purr);
	mtspr(SPRN_SPURR,	sprs.spurr);
	mtspr(SPRN_DSCR,	sprs.dscr);
	mtspr(SPRN_WORT,	sprs.wort);
	mtspr(SPRN_CIABR,	sprs.ciabr);

	mtspr(SPRN_MMCRA,	sprs.mmcra);
	mtspr(SPRN_MMCR0,	sprs.mmcr0);
	mtspr(SPRN_MMCR1,	sprs.mmcr1);
	mtspr(SPRN_MMCR2,	sprs.mmcr2);
	if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR))
		mtspr(SPRN_LDBAR, sprs.ldbar);

	mtspr(SPRN_SPRG3,	local_paca->sprg_vdso);

	if (!radix_enabled())
		__slb_restore_bolted_realmode();

out:
	mtmsr(MSR_KERNEL);

	return srr1;
}

#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/*
 * This is used in working around bugs in thread reconfiguration
 * on POWER9 (at least up to Nimbus DD2.2) relating to transactional
 * memory and the way that XER[SO] is checkpointed.
 * This function forces the core into SMT4 in order by asking
 * all other threads not to stop, and sending a message to any
 * that are in a stop state.
 * Must be called with preemption disabled.
 */
void pnv_power9_force_smt4_catch(void)
{
	int cpu, cpu0, thr;
	int awake_threads = 1;		/* this thread is awake */
	int poke_threads = 0;
	int need_awake = threads_per_core;

	cpu = smp_processor_id();
	cpu0 = cpu & ~(threads_per_core - 1);
	for (thr = 0; thr < threads_per_core; ++thr) {
		if (cpu != cpu0 + thr)
			atomic_inc(&paca_ptrs[cpu0+thr]->dont_stop);
	}
	/* order setting dont_stop vs testing requested_psscr */
	smp_mb();
	for (thr = 0; thr < threads_per_core; ++thr) {
		if (!paca_ptrs[cpu0+thr]->requested_psscr)
			++awake_threads;
		else
			poke_threads |= (1 << thr);
	}

	/* If at least 3 threads are awake, the core is in SMT4 already */
	if (awake_threads < need_awake) {
		/* We have to wake some threads; we'll use msgsnd */
		for (thr = 0; thr < threads_per_core; ++thr) {
			if (poke_threads & (1 << thr)) {
				ppc_msgsnd_sync();
				ppc_msgsnd(PPC_DBELL_MSGTYPE, 0,
					   paca_ptrs[cpu0+thr]->hw_cpu_id);
			}
		}
		/* now spin until at least 3 threads are awake */
		do {
			for (thr = 0; thr < threads_per_core; ++thr) {
				if ((poke_threads & (1 << thr)) &&
				    !paca_ptrs[cpu0+thr]->requested_psscr) {
					++awake_threads;
					poke_threads &= ~(1 << thr);
				}
			}
		} while (awake_threads < need_awake);
	}
}
EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_catch);

void pnv_power9_force_smt4_release(void)
{
	int cpu, cpu0, thr;

	cpu = smp_processor_id();
	cpu0 = cpu & ~(threads_per_core - 1);

	/* clear all the dont_stop flags */
	for (thr = 0; thr < threads_per_core; ++thr) {
		if (cpu != cpu0 + thr)
			atomic_dec(&paca_ptrs[cpu0+thr]->dont_stop);
	}
}
EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_release);
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */

struct p10_sprs {
	/*
	 * SPRs that get lost in shallow states:
	 *
	 * P10 loses CR, LR, CTR, FPSCR, VSCR, XER, TAR, SPRG2, and HSPRG1
	 * isa300 idle routines restore CR, LR.
	 * CTR is volatile
	 * idle thread doesn't use FP or VEC
	 * kernel doesn't use TAR
	 * HSPRG1 is only live in HV interrupt entry
	 * SPRG2 is only live in KVM guests, KVM handles it.
	 */
};

static unsigned long power10_idle_stop(unsigned long psscr)
{
	int cpu = raw_smp_processor_id();
	int first = cpu_first_thread_sibling(cpu);
	unsigned long *state = &paca_ptrs[first]->idle_state;
	unsigned long core_thread_mask = (1UL << threads_per_core) - 1;
	unsigned long srr1;
	unsigned long pls;
//	struct p10_sprs sprs = {}; /* avoid false used-uninitialised */
	bool sprs_saved = false;

	if (!(psscr & (PSSCR_EC|PSSCR_ESL))) {
		/* EC=ESL=0 case */

		/*
		 * Wake synchronously. SRESET via xscom may still cause
		 * a 0x100 powersave wakeup with SRR1 reason!
		 */
		srr1 = isa300_idle_stop_noloss(psscr);		/* go idle */
		if (likely(!srr1))
			return 0;

		/*
		 * Registers not saved, can't recover!
		 * This would be a hardware bug
		 */
		BUG_ON((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS);

		goto out;
	}

	/* EC=ESL=1 case */
	if ((psscr & PSSCR_RL_MASK) >= deep_spr_loss_state) {
		/* XXX: save SPRs for deep state loss here. */

		sprs_saved = true;

		atomic_start_thread_idle();
	}

	srr1 = isa300_idle_stop_mayloss(psscr);		/* go idle */

	psscr = mfspr(SPRN_PSSCR);

	WARN_ON_ONCE(!srr1);
	WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR));

	if (unlikely((srr1 & SRR1_WAKEMASK_P8) == SRR1_WAKEHMI))
		hmi_exception_realmode(NULL);

	/*
	 * On POWER10, SRR1 bits do not match exactly as expected.
	 * SRR1_WS_GPRLOSS (10b) can also result in SPR loss, so
	 * just always test PSSCR for SPR/TB state loss.
	 */
	pls = (psscr & PSSCR_PLS) >> PSSCR_PLS_SHIFT;
	if (likely(pls < deep_spr_loss_state)) {
		if (sprs_saved)
			atomic_stop_thread_idle();
		goto out;
	}

	/* HV state loss */
	BUG_ON(!sprs_saved);

	atomic_lock_thread_idle();

	if ((*state & core_thread_mask) != 0)
		goto core_woken;

	/* XXX: restore per-core SPRs here */

	if (pls >= pnv_first_tb_loss_level) {
		/* TB loss */
		if (opal_resync_timebase() != OPAL_SUCCESS)
			BUG();
	}

	/*
	 * isync after restoring shared SPRs and before unlocking. Unlock
	 * only contains hwsync which does not necessarily do the right
	 * thing for SPRs.
	 */
	isync();

core_woken:
	atomic_unlock_and_stop_thread_idle();

	/* XXX: restore per-thread SPRs here */

	if (!radix_enabled())
		__slb_restore_bolted_realmode();

out:
	mtmsr(MSR_KERNEL);

	return srr1;
}

#ifdef CONFIG_HOTPLUG_CPU
static unsigned long arch300_offline_stop(unsigned long psscr)
{
	unsigned long srr1;

	if (cpu_has_feature(CPU_FTR_ARCH_31))
		srr1 = power10_idle_stop(psscr);
	else
		srr1 = power9_idle_stop(psscr);

	return srr1;
}
#endif

void arch300_idle_type(unsigned long stop_psscr_val,
				      unsigned long stop_psscr_mask)
{
	unsigned long psscr;
	unsigned long srr1;

	if (!prep_irq_for_idle_irqsoff())
		return;

	psscr = mfspr(SPRN_PSSCR);
	psscr = (psscr & ~stop_psscr_mask) | stop_psscr_val;

	__ppc64_runlatch_off();
	if (cpu_has_feature(CPU_FTR_ARCH_31))
		srr1 = power10_idle_stop(psscr);
	else
		srr1 = power9_idle_stop(psscr);
	__ppc64_runlatch_on();

	fini_irq_for_idle_irqsoff();

	irq_set_pending_from_srr1(srr1);
}

/*
 * Used for ppc_md.power_save which needs a function with no parameters
 */
static void arch300_idle(void)
{
	arch300_idle_type(pnv_default_stop_val, pnv_default_stop_mask);
}

#ifdef CONFIG_HOTPLUG_CPU

void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val)
{
	u64 pir = get_hard_smp_processor_id(cpu);

	mtspr(SPRN_LPCR, lpcr_val);

	/*
	 * Program the LPCR via stop-api only if the deepest stop state
	 * can lose hypervisor context.
	 */
	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT)
		opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
}

/*
 * pnv_cpu_offline: A function that puts the CPU into the deepest
 * available platform idle state on a CPU-Offline.
 * interrupts hard disabled and no lazy irq pending.
 */
unsigned long pnv_cpu_offline(unsigned int cpu)
{
	unsigned long srr1;

	__ppc64_runlatch_off();

	if (cpu_has_feature(CPU_FTR_ARCH_300) && deepest_stop_found) {
		unsigned long psscr;

		psscr = mfspr(SPRN_PSSCR);
		psscr = (psscr & ~pnv_deepest_stop_psscr_mask) |
						pnv_deepest_stop_psscr_val;
		srr1 = arch300_offline_stop(psscr);
	} else if (cpu_has_feature(CPU_FTR_ARCH_206) && power7_offline_type) {
		srr1 = power7_offline();
	} else {
		/* This is the fallback method. We emulate snooze */
		while (!generic_check_cpu_restart(cpu)) {
			HMT_low();
			HMT_very_low();
		}
		srr1 = 0;
		HMT_medium();
	}

	__ppc64_runlatch_on();

	return srr1;
}
#endif

/*
 * Power ISA 3.0 idle initialization.
 *
 * POWER ISA 3.0 defines a new SPR Processor stop Status and Control
 * Register (PSSCR) to control idle behavior.
 *
 * PSSCR layout:
 * ----------------------------------------------------------
 * | PLS | /// | SD | ESL | EC | PSLL | /// | TR | MTL | RL |
 * ----------------------------------------------------------
 * 0      4     41   42    43   44     48    54   56    60
 *
 * PSSCR key fields:
 *	Bits 0:3  - Power-Saving Level Status (PLS). This field indicates the
 *	lowest power-saving state the thread entered since stop instruction was
 *	last executed.
 *
 *	Bit 41 - Status Disable(SD)
 *	0 - Shows PLS entries
 *	1 - PLS entries are all 0
 *
 *	Bit 42 - Enable State Loss
 *	0 - No state is lost irrespective of other fields
 *	1 - Allows state loss
 *
 *	Bit 43 - Exit Criterion
 *	0 - Exit from power-save mode on any interrupt
 *	1 - Exit from power-save mode controlled by LPCR's PECE bits
 *
 *	Bits 44:47 - Power-Saving Level Limit
 *	This limits the power-saving level that can be entered into.
 *
 *	Bits 60:63 - Requested Level
 *	Used to specify which power-saving level must be entered on executing
 *	stop instruction
 */

int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags)
{
	int err = 0;

	/*
	 * psscr_mask == 0xf indicates an older firmware.
	 * Set remaining fields of psscr to the default values.
	 * See NOTE above definition of PSSCR_HV_DEFAULT_VAL
	 */
	if (*psscr_mask == 0xf) {
		*psscr_val = *psscr_val | PSSCR_HV_DEFAULT_VAL;
		*psscr_mask = PSSCR_HV_DEFAULT_MASK;
		return err;
	}

	/*
	 * New firmware is expected to set the psscr_val bits correctly.
	 * Validate that the following invariants are correctly maintained by
	 * the new firmware.
	 * - ESL bit value matches the EC bit value.
	 * - ESL bit is set for all the deep stop states.
	 */
	if (GET_PSSCR_ESL(*psscr_val) != GET_PSSCR_EC(*psscr_val)) {
		err = ERR_EC_ESL_MISMATCH;
	} else if ((flags & OPAL_PM_LOSE_FULL_CONTEXT) &&
		GET_PSSCR_ESL(*psscr_val) == 0) {
		err = ERR_DEEP_STATE_ESL_MISMATCH;
	}

	return err;
}

/*
 * pnv_arch300_idle_init: Initializes the default idle state, first
 *                        deep idle state and deepest idle state on
 *                        ISA 3.0 CPUs.
 *
 * @np: /ibm,opal/power-mgt device node
 * @flags: cpu-idle-state-flags array
 * @dt_idle_states: Number of idle state entries
 * Returns 0 on success
 */
static void __init pnv_arch300_idle_init(void)
{
	u64 max_residency_ns = 0;
	int i;

	/* stop is not really architected, we only have p9,p10 drivers */
	if (!pvr_version_is(PVR_POWER10) && !pvr_version_is(PVR_POWER9))
		return;

	/*
	 * pnv_deepest_stop_{val,mask} should be set to values corresponding to
	 * the deepest stop state.
	 *
	 * pnv_default_stop_{val,mask} should be set to values corresponding to
	 * the deepest loss-less (OPAL_PM_STOP_INST_FAST) stop state.
	 */
	pnv_first_tb_loss_level = MAX_STOP_STATE + 1;
	deep_spr_loss_state = MAX_STOP_STATE + 1;
	for (i = 0; i < nr_pnv_idle_states; i++) {
		int err;
		struct pnv_idle_states_t *state = &pnv_idle_states[i];
		u64 psscr_rl = state->psscr_val & PSSCR_RL_MASK;

		/* No deep loss driver implemented for POWER10 yet */
		if (pvr_version_is(PVR_POWER10) &&
				state->flags & (OPAL_PM_TIMEBASE_STOP|OPAL_PM_LOSE_FULL_CONTEXT))
			continue;

		if ((state->flags & OPAL_PM_TIMEBASE_STOP) &&
		     (pnv_first_tb_loss_level > psscr_rl))
			pnv_first_tb_loss_level = psscr_rl;

		if ((state->flags & OPAL_PM_LOSE_FULL_CONTEXT) &&
		     (deep_spr_loss_state > psscr_rl))
			deep_spr_loss_state = psscr_rl;

		/*
		 * The idle code does not deal with TB loss occurring
		 * in a shallower state than SPR loss, so force it to
		 * behave like SPRs are lost if TB is lost. POWER9 would
		 * never encouter this, but a POWER8 core would if it
		 * implemented the stop instruction. So this is for forward
		 * compatibility.
		 */
		if ((state->flags & OPAL_PM_TIMEBASE_STOP) &&
		     (deep_spr_loss_state > psscr_rl))
			deep_spr_loss_state = psscr_rl;

		err = validate_psscr_val_mask(&state->psscr_val,
					      &state->psscr_mask,
					      state->flags);
		if (err) {
			report_invalid_psscr_val(state->psscr_val, err);
			continue;
		}

		state->valid = true;

		if (max_residency_ns < state->residency_ns) {
			max_residency_ns = state->residency_ns;
			pnv_deepest_stop_psscr_val = state->psscr_val;
			pnv_deepest_stop_psscr_mask = state->psscr_mask;
			pnv_deepest_stop_flag = state->flags;
			deepest_stop_found = true;
		}

		if (!default_stop_found &&
		    (state->flags & OPAL_PM_STOP_INST_FAST)) {
			pnv_default_stop_val = state->psscr_val;
			pnv_default_stop_mask = state->psscr_mask;
			default_stop_found = true;
			WARN_ON(state->flags & OPAL_PM_LOSE_FULL_CONTEXT);
		}
	}

	if (unlikely(!default_stop_found)) {
		pr_warn("cpuidle-powernv: No suitable default stop state found. Disabling platform idle.\n");
	} else {
		ppc_md.power_save = arch300_idle;
		pr_info("cpuidle-powernv: Default stop: psscr = 0x%016llx,mask=0x%016llx\n",
			pnv_default_stop_val, pnv_default_stop_mask);
	}

	if (unlikely(!deepest_stop_found)) {
		pr_warn("cpuidle-powernv: No suitable stop state for CPU-Hotplug. Offlined CPUs will busy wait");
	} else {
		pr_info("cpuidle-powernv: Deepest stop: psscr = 0x%016llx,mask=0x%016llx\n",
			pnv_deepest_stop_psscr_val,
			pnv_deepest_stop_psscr_mask);
	}

	pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%llx\n",
		deep_spr_loss_state);

	pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%llx\n",
		pnv_first_tb_loss_level);
}

static void __init pnv_disable_deep_states(void)
{
	/*
	 * The stop-api is unable to restore hypervisor
	 * resources on wakeup from platform idle states which
	 * lose full context. So disable such states.
	 */
	supported_cpuidle_states &= ~OPAL_PM_LOSE_FULL_CONTEXT;
	pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n");
	pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n");

	if (cpu_has_feature(CPU_FTR_ARCH_300) &&
	    (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) {
		/*
		 * Use the default stop state for CPU-Hotplug
		 * if available.
		 */
		if (default_stop_found) {
			pnv_deepest_stop_psscr_val = pnv_default_stop_val;
			pnv_deepest_stop_psscr_mask = pnv_default_stop_mask;
			pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n",
				pnv_deepest_stop_psscr_val);
		} else { /* Fallback to snooze loop for CPU-Hotplug */
			deepest_stop_found = false;
			pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n");
		}
	}
}

/*
 * Probe device tree for supported idle states
 */
static void __init pnv_probe_idle_states(void)
{
	int i;

	if (nr_pnv_idle_states < 0) {
		pr_warn("cpuidle-powernv: no idle states found in the DT\n");
		return;
	}

	if (cpu_has_feature(CPU_FTR_ARCH_300))
		pnv_arch300_idle_init();

	for (i = 0; i < nr_pnv_idle_states; i++)
		supported_cpuidle_states |= pnv_idle_states[i].flags;
}

/*
 * This function parses device-tree and populates all the information
 * into pnv_idle_states structure. It also sets up nr_pnv_idle_states
 * which is the number of cpuidle states discovered through device-tree.
 */

static int pnv_parse_cpuidle_dt(void)
{
	struct device_node *np;
	int nr_idle_states, i;
	int rc = 0;
	u32 *temp_u32;
	u64 *temp_u64;
	const char **temp_string;

	np = of_find_node_by_path("/ibm,opal/power-mgt");
	if (!np) {
		pr_warn("opal: PowerMgmt Node not found\n");
		return -ENODEV;
	}
	nr_idle_states = of_property_count_u32_elems(np,
						"ibm,cpu-idle-state-flags");

	pnv_idle_states = kcalloc(nr_idle_states, sizeof(*pnv_idle_states),
				  GFP_KERNEL);
	temp_u32 = kcalloc(nr_idle_states, sizeof(u32),  GFP_KERNEL);
	temp_u64 = kcalloc(nr_idle_states, sizeof(u64),  GFP_KERNEL);
	temp_string = kcalloc(nr_idle_states, sizeof(char *),  GFP_KERNEL);

	if (!(pnv_idle_states && temp_u32 && temp_u64 && temp_string)) {
		pr_err("Could not allocate memory for dt parsing\n");
		rc = -ENOMEM;
		goto out;
	}

	/* Read flags */
	if (of_property_read_u32_array(np, "ibm,cpu-idle-state-flags",
				       temp_u32, nr_idle_states)) {
		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n");
		rc = -EINVAL;
		goto out;
	}
	for (i = 0; i < nr_idle_states; i++)
		pnv_idle_states[i].flags = temp_u32[i];

	/* Read latencies */
	if (of_property_read_u32_array(np, "ibm,cpu-idle-state-latencies-ns",
				       temp_u32, nr_idle_states)) {
		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-latencies-ns in DT\n");
		rc = -EINVAL;
		goto out;
	}
	for (i = 0; i < nr_idle_states; i++)
		pnv_idle_states[i].latency_ns = temp_u32[i];

	/* Read residencies */
	if (of_property_read_u32_array(np, "ibm,cpu-idle-state-residency-ns",
				       temp_u32, nr_idle_states)) {
		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-residency-ns in DT\n");
		rc = -EINVAL;
		goto out;
	}
	for (i = 0; i < nr_idle_states; i++)
		pnv_idle_states[i].residency_ns = temp_u32[i];

	/* For power9 and later */
	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
		/* Read pm_crtl_val */
		if (of_property_read_u64_array(np, "ibm,cpu-idle-state-psscr",
					       temp_u64, nr_idle_states)) {
			pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n");
			rc = -EINVAL;
			goto out;
		}
		for (i = 0; i < nr_idle_states; i++)
			pnv_idle_states[i].psscr_val = temp_u64[i];

		/* Read pm_crtl_mask */
		if (of_property_read_u64_array(np, "ibm,cpu-idle-state-psscr-mask",
					       temp_u64, nr_idle_states)) {
			pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr-mask in DT\n");
			rc = -EINVAL;
			goto out;
		}
		for (i = 0; i < nr_idle_states; i++)
			pnv_idle_states[i].psscr_mask = temp_u64[i];
	}

	/*
	 * power8 specific properties ibm,cpu-idle-state-pmicr-mask and
	 * ibm,cpu-idle-state-pmicr-val were never used and there is no
	 * plan to use it in near future. Hence, not parsing these properties
	 */

	if (of_property_read_string_array(np, "ibm,cpu-idle-state-names",
					  temp_string, nr_idle_states) < 0) {
		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-names in DT\n");
		rc = -EINVAL;
		goto out;
	}
	for (i = 0; i < nr_idle_states; i++)
		strlcpy(pnv_idle_states[i].name, temp_string[i],
			PNV_IDLE_NAME_LEN);
	nr_pnv_idle_states = nr_idle_states;
	rc = 0;
out:
	kfree(temp_u32);
	kfree(temp_u64);
	kfree(temp_string);
	return rc;
}

static int __init pnv_init_idle_states(void)
{
	int cpu;
	int rc = 0;

	/* Set up PACA fields */
	for_each_present_cpu(cpu) {
		struct paca_struct *p = paca_ptrs[cpu];

		p->idle_state = 0;
		if (cpu == cpu_first_thread_sibling(cpu))
			p->idle_state = (1 << threads_per_core) - 1;

		if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
			/* P7/P8 nap */
			p->thread_idle_state = PNV_THREAD_RUNNING;
		} else if (pvr_version_is(PVR_POWER9)) {
			/* P9 stop workarounds */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
			p->requested_psscr = 0;
			atomic_set(&p->dont_stop, 0);
#endif
		}
	}

	/* In case we error out nr_pnv_idle_states will be zero */
	nr_pnv_idle_states = 0;
	supported_cpuidle_states = 0;

	if (cpuidle_disable != IDLE_NO_OVERRIDE)
		goto out;
	rc = pnv_parse_cpuidle_dt();
	if (rc)
		return rc;
	pnv_probe_idle_states();

	if (!cpu_has_feature(CPU_FTR_ARCH_300)) {
		if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
			power7_fastsleep_workaround_entry = false;
			power7_fastsleep_workaround_exit = false;
		} else {
			/*
			 * OPAL_PM_SLEEP_ENABLED_ER1 is set. It indicates that
			 * workaround is needed to use fastsleep. Provide sysfs
			 * control to choose how this workaround has to be
			 * applied.
			 */
			device_create_file(cpu_subsys.dev_root,
				&dev_attr_fastsleep_workaround_applyonce);
		}

		update_subcore_sibling_mask();

		if (supported_cpuidle_states & OPAL_PM_NAP_ENABLED) {
			ppc_md.power_save = power7_idle;
			power7_offline_type = PNV_THREAD_NAP;
		}

		if ((supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED) &&
			   (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT))
			power7_offline_type = PNV_THREAD_WINKLE;
		else if ((supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED) ||
			   (supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1))
			power7_offline_type = PNV_THREAD_SLEEP;
	}

	if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) {
		if (pnv_save_sprs_for_deep_states())
			pnv_disable_deep_states();
	}

out:
	return 0;
}
machine_subsys_initcall(powernv, pnv_init_idle_states);