summaryrefslogtreecommitdiffstats
path: root/drivers/acpi/processor_idle.c
blob: 3e053140599724c50f68853025a14cf34f617c7b (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
/*
 * processor_idle - idle state submodule to the ACPI processor driver
 *
 *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
 *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
 *  Copyright (C) 2004, 2005 Dominik Brodowski <linux@brodo.de>
 *  Copyright (C) 2004  Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 *  			- Added processor hotplug support
 *  Copyright (C) 2005  Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
 *  			- Added support for C3 on SMP
 *
 * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or (at
 *  your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful, but
 *  WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 *  General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License along
 *  with this program; if not, write to the Free Software Foundation, Inc.,
 *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
 *
 * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/cpufreq.h>
#include <linux/slab.h>
#include <linux/acpi.h>
#include <linux/dmi.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>	/* need_resched() */
#include <linux/pm_qos_params.h>
#include <linux/clockchips.h>
#include <linux/cpuidle.h>
#include <linux/irqflags.h>

/*
 * Include the apic definitions for x86 to have the APIC timer related defines
 * available also for UP (on SMP it gets magically included via linux/smp.h).
 * asm/acpi.h is not an option, as it would require more include magic. Also
 * creating an empty asm-ia64/apic.h would just trade pest vs. cholera.
 */
#ifdef CONFIG_X86
#include <asm/apic.h>
#endif

#include <asm/io.h>
#include <asm/uaccess.h>

#include <acpi/acpi_bus.h>
#include <acpi/processor.h>
#include <asm/processor.h>

#define PREFIX "ACPI: "

#define ACPI_PROCESSOR_CLASS            "processor"
#define _COMPONENT              ACPI_PROCESSOR_COMPONENT
ACPI_MODULE_NAME("processor_idle");
#define PM_TIMER_TICK_NS		(1000000000ULL/PM_TIMER_FREQUENCY)
#define C2_OVERHEAD			1	/* 1us */
#define C3_OVERHEAD			1	/* 1us */
#define PM_TIMER_TICKS_TO_US(p)		(((p) * 1000)/(PM_TIMER_FREQUENCY/1000))

static unsigned int max_cstate __read_mostly = ACPI_PROCESSOR_MAX_POWER;
module_param(max_cstate, uint, 0000);
static unsigned int nocst __read_mostly;
module_param(nocst, uint, 0000);
static int bm_check_disable __read_mostly;
module_param(bm_check_disable, uint, 0000);

static unsigned int latency_factor __read_mostly = 2;
module_param(latency_factor, uint, 0644);

static int disabled_by_idle_boot_param(void)
{
	return boot_option_idle_override == IDLE_POLL ||
		boot_option_idle_override == IDLE_FORCE_MWAIT ||
		boot_option_idle_override == IDLE_HALT;
}

/*
 * IBM ThinkPad R40e crashes mysteriously when going into C2 or C3.
 * For now disable this. Probably a bug somewhere else.
 *
 * To skip this limit, boot/load with a large max_cstate limit.
 */
static int set_max_cstate(const struct dmi_system_id *id)
{
	if (max_cstate > ACPI_PROCESSOR_MAX_POWER)
		return 0;

	printk(KERN_NOTICE PREFIX "%s detected - limiting to C%ld max_cstate."
	       " Override with \"processor.max_cstate=%d\"\n", id->ident,
	       (long)id->driver_data, ACPI_PROCESSOR_MAX_POWER + 1);

	max_cstate = (long)id->driver_data;

	return 0;
}

/* Actually this shouldn't be __cpuinitdata, would be better to fix the
   callers to only run once -AK */
static struct dmi_system_id __cpuinitdata processor_power_dmi_table[] = {
	{ set_max_cstate, "Clevo 5600D", {
	  DMI_MATCH(DMI_BIOS_VENDOR,"Phoenix Technologies LTD"),
	  DMI_MATCH(DMI_BIOS_VERSION,"SHE845M0.86C.0013.D.0302131307")},
	 (void *)2},
	{ set_max_cstate, "Pavilion zv5000", {
	  DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
	  DMI_MATCH(DMI_PRODUCT_NAME,"Pavilion zv5000 (DS502A#ABA)")},
	 (void *)1},
	{ set_max_cstate, "Asus L8400B", {
	  DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."),
	  DMI_MATCH(DMI_PRODUCT_NAME,"L8400B series Notebook PC")},
	 (void *)1},
	{},
};


/*
 * Callers should disable interrupts before the call and enable
 * interrupts after return.
 */
static void acpi_safe_halt(void)
{
	current_thread_info()->status &= ~TS_POLLING;
	/*
	 * TS_POLLING-cleared state must be visible before we
	 * test NEED_RESCHED:
	 */
	smp_mb();
	if (!need_resched()) {
		safe_halt();
		local_irq_disable();
	}
	current_thread_info()->status |= TS_POLLING;
}

#ifdef ARCH_APICTIMER_STOPS_ON_C3

/*
 * Some BIOS implementations switch to C3 in the published C2 state.
 * This seems to be a common problem on AMD boxen, but other vendors
 * are affected too. We pick the most conservative approach: we assume
 * that the local APIC stops in both C2 and C3.
 */
static void lapic_timer_check_state(int state, struct acpi_processor *pr,
				   struct acpi_processor_cx *cx)
{
	struct acpi_processor_power *pwr = &pr->power;
	u8 type = local_apic_timer_c2_ok ? ACPI_STATE_C3 : ACPI_STATE_C2;

	if (cpu_has(&cpu_data(pr->id), X86_FEATURE_ARAT))
		return;

	if (amd_e400_c1e_detected)
		type = ACPI_STATE_C1;

	/*
	 * Check, if one of the previous states already marked the lapic
	 * unstable
	 */
	if (pwr->timer_broadcast_on_state < state)
		return;

	if (cx->type >= type)
		pr->power.timer_broadcast_on_state = state;
}

static void __lapic_timer_propagate_broadcast(void *arg)
{
	struct acpi_processor *pr = (struct acpi_processor *) arg;
	unsigned long reason;

	reason = pr->power.timer_broadcast_on_state < INT_MAX ?
		CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF;

	clockevents_notify(reason, &pr->id);
}

static void lapic_timer_propagate_broadcast(struct acpi_processor *pr)
{
	smp_call_function_single(pr->id, __lapic_timer_propagate_broadcast,
				 (void *)pr, 1);
}

/* Power(C) State timer broadcast control */
static void lapic_timer_state_broadcast(struct acpi_processor *pr,
				       struct acpi_processor_cx *cx,
				       int broadcast)
{
	int state = cx - pr->power.states;

	if (state >= pr->power.timer_broadcast_on_state) {
		unsigned long reason;

		reason = broadcast ?  CLOCK_EVT_NOTIFY_BROADCAST_ENTER :
			CLOCK_EVT_NOTIFY_BROADCAST_EXIT;
		clockevents_notify(reason, &pr->id);
	}
}

#else

static void lapic_timer_check_state(int state, struct acpi_processor *pr,
				   struct acpi_processor_cx *cstate) { }
static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) { }
static void lapic_timer_state_broadcast(struct acpi_processor *pr,
				       struct acpi_processor_cx *cx,
				       int broadcast)
{
}

#endif

/*
 * Suspend / resume control
 */
static int acpi_idle_suspend;
static u32 saved_bm_rld;

static void acpi_idle_bm_rld_save(void)
{
	acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &saved_bm_rld);
}
static void acpi_idle_bm_rld_restore(void)
{
	u32 resumed_bm_rld;

	acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &resumed_bm_rld);

	if (resumed_bm_rld != saved_bm_rld)
		acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, saved_bm_rld);
}

int acpi_processor_suspend(struct acpi_device * device, pm_message_t state)
{
	if (acpi_idle_suspend == 1)
		return 0;

	acpi_idle_bm_rld_save();
	acpi_idle_suspend = 1;
	return 0;
}

int acpi_processor_resume(struct acpi_device * device)
{
	if (acpi_idle_suspend == 0)
		return 0;

	acpi_idle_bm_rld_restore();
	acpi_idle_suspend = 0;
	return 0;
}

#if defined(CONFIG_X86)
static void tsc_check_state(int state)
{
	switch (boot_cpu_data.x86_vendor) {
	case X86_VENDOR_AMD:
	case X86_VENDOR_INTEL:
		/*
		 * AMD Fam10h TSC will tick in all
		 * C/P/S0/S1 states when this bit is set.
		 */
		if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
			return;

		/*FALL THROUGH*/
	default:
		/* TSC could halt in idle, so notify users */
		if (state > ACPI_STATE_C1)
			mark_tsc_unstable("TSC halts in idle");
	}
}
#else
static void tsc_check_state(int state) { return; }
#endif

static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr)
{

	if (!pr)
		return -EINVAL;

	if (!pr->pblk)
		return -ENODEV;

	/* if info is obtained from pblk/fadt, type equals state */
	pr->power.states[ACPI_STATE_C2].type = ACPI_STATE_C2;
	pr->power.states[ACPI_STATE_C3].type = ACPI_STATE_C3;

#ifndef CONFIG_HOTPLUG_CPU
	/*
	 * Check for P_LVL2_UP flag before entering C2 and above on
	 * an SMP system.
	 */
	if ((num_online_cpus() > 1) &&
	    !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED))
		return -ENODEV;
#endif

	/* determine C2 and C3 address from pblk */
	pr->power.states[ACPI_STATE_C2].address = pr->pblk + 4;
	pr->power.states[ACPI_STATE_C3].address = pr->pblk + 5;

	/* determine latencies from FADT */
	pr->power.states[ACPI_STATE_C2].latency = acpi_gbl_FADT.C2latency;
	pr->power.states[ACPI_STATE_C3].latency = acpi_gbl_FADT.C3latency;

	/*
	 * FADT specified C2 latency must be less than or equal to
	 * 100 microseconds.
	 */
	if (acpi_gbl_FADT.C2latency > ACPI_PROCESSOR_MAX_C2_LATENCY) {
		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
			"C2 latency too large [%d]\n", acpi_gbl_FADT.C2latency));
		/* invalidate C2 */
		pr->power.states[ACPI_STATE_C2].address = 0;
	}

	/*
	 * FADT supplied C3 latency must be less than or equal to
	 * 1000 microseconds.
	 */
	if (acpi_gbl_FADT.C3latency > ACPI_PROCESSOR_MAX_C3_LATENCY) {
		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
			"C3 latency too large [%d]\n", acpi_gbl_FADT.C3latency));
		/* invalidate C3 */
		pr->power.states[ACPI_STATE_C3].address = 0;
	}

	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
			  "lvl2[0x%08x] lvl3[0x%08x]\n",
			  pr->power.states[ACPI_STATE_C2].address,
			  pr->power.states[ACPI_STATE_C3].address));

	return 0;
}

static int acpi_processor_get_power_info_default(struct acpi_processor *pr)
{
	if (!pr->power.states[ACPI_STATE_C1].valid) {
		/* set the first C-State to C1 */
		/* all processors need to support C1 */
		pr->power.states[ACPI_STATE_C1].type = ACPI_STATE_C1;
		pr->power.states[ACPI_STATE_C1].valid = 1;
		pr->power.states[ACPI_STATE_C1].entry_method = ACPI_CSTATE_HALT;
	}
	/* the C0 state only exists as a filler in our array */
	pr->power.states[ACPI_STATE_C0].valid = 1;
	return 0;
}

static int acpi_processor_get_power_info_cst(struct acpi_processor *pr)
{
	acpi_status status = 0;
	u64 count;
	int current_count;
	int i;
	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
	union acpi_object *cst;


	if (nocst)
		return -ENODEV;

	current_count = 0;

	status = acpi_evaluate_object(pr->handle, "_CST", NULL, &buffer);
	if (ACPI_FAILURE(status)) {
		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No _CST, giving up\n"));
		return -ENODEV;
	}

	cst = buffer.pointer;

	/* There must be at least 2 elements */
	if (!cst || (cst->type != ACPI_TYPE_PACKAGE) || cst->package.count < 2) {
		printk(KERN_ERR PREFIX "not enough elements in _CST\n");
		status = -EFAULT;
		goto end;
	}

	count = cst->package.elements[0].integer.value;

	/* Validate number of power states. */
	if (count < 1 || count != cst->package.count - 1) {
		printk(KERN_ERR PREFIX "count given by _CST is not valid\n");
		status = -EFAULT;
		goto end;
	}

	/* Tell driver that at least _CST is supported. */
	pr->flags.has_cst = 1;

	for (i = 1; i <= count; i++) {
		union acpi_object *element;
		union acpi_object *obj;
		struct acpi_power_register *reg;
		struct acpi_processor_cx cx;

		memset(&cx, 0, sizeof(cx));

		element = &(cst->package.elements[i]);
		if (element->type != ACPI_TYPE_PACKAGE)
			continue;

		if (element->package.count != 4)
			continue;

		obj = &(element->package.elements[0]);

		if (obj->type != ACPI_TYPE_BUFFER)
			continue;

		reg = (struct acpi_power_register *)obj->buffer.pointer;

		if (reg->space_id != ACPI_ADR_SPACE_SYSTEM_IO &&
		    (reg->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE))
			continue;

		/* There should be an easy way to extract an integer... */
		obj = &(element->package.elements[1]);
		if (obj->type != ACPI_TYPE_INTEGER)
			continue;

		cx.type = obj->integer.value;
		/*
		 * Some buggy BIOSes won't list C1 in _CST -
		 * Let acpi_processor_get_power_info_default() handle them later
		 */
		if (i == 1 && cx.type != ACPI_STATE_C1)
			current_count++;

		cx.address = reg->address;
		cx.index = current_count + 1;

		cx.entry_method = ACPI_CSTATE_SYSTEMIO;
		if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) {
			if (acpi_processor_ffh_cstate_probe
					(pr->id, &cx, reg) == 0) {
				cx.entry_method = ACPI_CSTATE_FFH;
			} else if (cx.type == ACPI_STATE_C1) {
				/*
				 * C1 is a special case where FIXED_HARDWARE
				 * can be handled in non-MWAIT way as well.
				 * In that case, save this _CST entry info.
				 * Otherwise, ignore this info and continue.
				 */
				cx.entry_method = ACPI_CSTATE_HALT;
				snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI HLT");
			} else {
				continue;
			}
			if (cx.type == ACPI_STATE_C1 &&
			    (boot_option_idle_override == IDLE_NOMWAIT)) {
				/*
				 * In most cases the C1 space_id obtained from
				 * _CST object is FIXED_HARDWARE access mode.
				 * But when the option of idle=halt is added,
				 * the entry_method type should be changed from
				 * CSTATE_FFH to CSTATE_HALT.
				 * When the option of idle=nomwait is added,
				 * the C1 entry_method type should be
				 * CSTATE_HALT.
				 */
				cx.entry_method = ACPI_CSTATE_HALT;
				snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI HLT");
			}
		} else {
			snprintf(cx.desc, ACPI_CX_DESC_LEN, "ACPI IOPORT 0x%x",
				 cx.address);
		}

		if (cx.type == ACPI_STATE_C1) {
			cx.valid = 1;
		}

		obj = &(element->package.elements[2]);
		if (obj->type != ACPI_TYPE_INTEGER)
			continue;

		cx.latency = obj->integer.value;

		obj = &(element->package.elements[3]);
		if (obj->type != ACPI_TYPE_INTEGER)
			continue;

		cx.power = obj->integer.value;

		current_count++;
		memcpy(&(pr->power.states[current_count]), &cx, sizeof(cx));

		/*
		 * We support total ACPI_PROCESSOR_MAX_POWER - 1
		 * (From 1 through ACPI_PROCESSOR_MAX_POWER - 1)
		 */
		if (current_count >= (ACPI_PROCESSOR_MAX_POWER - 1)) {
			printk(KERN_WARNING
			       "Limiting number of power states to max (%d)\n",
			       ACPI_PROCESSOR_MAX_POWER);
			printk(KERN_WARNING
			       "Please increase ACPI_PROCESSOR_MAX_POWER if needed.\n");
			break;
		}
	}

	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found %d power states\n",
			  current_count));

	/* Validate number of power states discovered */
	if (current_count < 2)
		status = -EFAULT;

      end:
	kfree(buffer.pointer);

	return status;
}

static void acpi_processor_power_verify_c3(struct acpi_processor *pr,
					   struct acpi_processor_cx *cx)
{
	static int bm_check_flag = -1;
	static int bm_control_flag = -1;


	if (!cx->address)
		return;

	/*
	 * PIIX4 Erratum #18: We don't support C3 when Type-F (fast)
	 * DMA transfers are used by any ISA device to avoid livelock.
	 * Note that we could disable Type-F DMA (as recommended by
	 * the erratum), but this is known to disrupt certain ISA
	 * devices thus we take the conservative approach.
	 */
	else if (errata.piix4.fdma) {
		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
				  "C3 not supported on PIIX4 with Type-F DMA\n"));
		return;
	}

	/* All the logic here assumes flags.bm_check is same across all CPUs */
	if (bm_check_flag == -1) {
		/* Determine whether bm_check is needed based on CPU  */
		acpi_processor_power_init_bm_check(&(pr->flags), pr->id);
		bm_check_flag = pr->flags.bm_check;
		bm_control_flag = pr->flags.bm_control;
	} else {
		pr->flags.bm_check = bm_check_flag;
		pr->flags.bm_control = bm_control_flag;
	}

	if (pr->flags.bm_check) {
		if (!pr->flags.bm_control) {
			if (pr->flags.has_cst != 1) {
				/* bus mastering control is necessary */
				ACPI_DEBUG_PRINT((ACPI_DB_INFO,
					"C3 support requires BM control\n"));
				return;
			} else {
				/* Here we enter C3 without bus mastering */
				ACPI_DEBUG_PRINT((ACPI_DB_INFO,
					"C3 support without BM control\n"));
			}
		}
	} else {
		/*
		 * WBINVD should be set in fadt, for C3 state to be
		 * supported on when bm_check is not required.
		 */
		if (!(acpi_gbl_FADT.flags & ACPI_FADT_WBINVD)) {
			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
					  "Cache invalidation should work properly"
					  " for C3 to be enabled on SMP systems\n"));
			return;
		}
	}

	/*
	 * Otherwise we've met all of our C3 requirements.
	 * Normalize the C3 latency to expidite policy.  Enable
	 * checking of bus mastering status (bm_check) so we can
	 * use this in our C3 policy
	 */
	cx->valid = 1;

	cx->latency_ticks = cx->latency;
	/*
	 * On older chipsets, BM_RLD needs to be set
	 * in order for Bus Master activity to wake the
	 * system from C3.  Newer chipsets handle DMA
	 * during C3 automatically and BM_RLD is a NOP.
	 * In either case, the proper way to
	 * handle BM_RLD is to set it and leave it set.
	 */
	acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, 1);

	return;
}

static int acpi_processor_power_verify(struct acpi_processor *pr)
{
	unsigned int i;
	unsigned int working = 0;

	pr->power.timer_broadcast_on_state = INT_MAX;

	for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) {
		struct acpi_processor_cx *cx = &pr->power.states[i];

		switch (cx->type) {
		case ACPI_STATE_C1:
			cx->valid = 1;
			break;

		case ACPI_STATE_C2:
			if (!cx->address)
				break;
			cx->valid = 1; 
			cx->latency_ticks = cx->latency; /* Normalize latency */
			break;

		case ACPI_STATE_C3:
			acpi_processor_power_verify_c3(pr, cx);
			break;
		}
		if (!cx->valid)
			continue;

		lapic_timer_check_state(i, pr, cx);
		tsc_check_state(cx->type);
		working++;
	}

	lapic_timer_propagate_broadcast(pr);

	return (working);
}

static int acpi_processor_get_power_info(struct acpi_processor *pr)
{
	unsigned int i;
	int result;


	/* NOTE: the idle thread may not be running while calling
	 * this function */

	/* Zero initialize all the C-states info. */
	memset(pr->power.states, 0, sizeof(pr->power.states));

	result = acpi_processor_get_power_info_cst(pr);
	if (result == -ENODEV)
		result = acpi_processor_get_power_info_fadt(pr);

	if (result)
		return result;

	acpi_processor_get_power_info_default(pr);

	pr->power.count = acpi_processor_power_verify(pr);

	/*
	 * if one state of type C2 or C3 is available, mark this
	 * CPU as being "idle manageable"
	 */
	for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) {
		if (pr->power.states[i].valid) {
			pr->power.count = i;
			if (pr->power.states[i].type >= ACPI_STATE_C2)
				pr->flags.power = 1;
		}
	}

	return 0;
}

/**
 * acpi_idle_bm_check - checks if bus master activity was detected
 */
static int acpi_idle_bm_check(void)
{
	u32 bm_status = 0;

	if (bm_check_disable)
		return 0;

	acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_STATUS, &bm_status);
	if (bm_status)
		acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_STATUS, 1);
	/*
	 * PIIX4 Erratum #18: Note that BM_STS doesn't always reflect
	 * the true state of bus mastering activity; forcing us to
	 * manually check the BMIDEA bit of each IDE channel.
	 */
	else if (errata.piix4.bmisx) {
		if ((inb_p(errata.piix4.bmisx + 0x02) & 0x01)
		    || (inb_p(errata.piix4.bmisx + 0x0A) & 0x01))
			bm_status = 1;
	}
	return bm_status;
}

/**
 * acpi_idle_do_entry - a helper function that does C2 and C3 type entry
 * @cx: cstate data
 *
 * Caller disables interrupt before call and enables interrupt after return.
 */
static inline void acpi_idle_do_entry(struct acpi_processor_cx *cx)
{
	/* Don't trace irqs off for idle */
	stop_critical_timings();
	if (cx->entry_method == ACPI_CSTATE_FFH) {
		/* Call into architectural FFH based C-state */
		acpi_processor_ffh_cstate_enter(cx);
	} else if (cx->entry_method == ACPI_CSTATE_HALT) {
		acpi_safe_halt();
	} else {
		/* IO port based C-state */
		inb(cx->address);
		/* Dummy wait op - must do something useless after P_LVL2 read
		   because chipsets cannot guarantee that STPCLK# signal
		   gets asserted in time to freeze execution properly. */
		inl(acpi_gbl_FADT.xpm_timer_block.address);
	}
	start_critical_timings();
}

/**
 * acpi_idle_enter_c1 - enters an ACPI C1 state-type
 * @dev: the target CPU
 * @state: the state data
 *
 * This is equivalent to the HALT instruction.
 */
static int acpi_idle_enter_c1(struct cpuidle_device *dev,
			      struct cpuidle_state *state)
{
	ktime_t  kt1, kt2;
	s64 idle_time;
	struct acpi_processor *pr;
	struct acpi_processor_cx *cx = cpuidle_get_statedata(state);

	pr = __this_cpu_read(processors);

	if (unlikely(!pr))
		return 0;

	local_irq_disable();

	/* Do not access any ACPI IO ports in suspend path */
	if (acpi_idle_suspend) {
		local_irq_enable();
		cpu_relax();
		return 0;
	}

	lapic_timer_state_broadcast(pr, cx, 1);
	kt1 = ktime_get_real();
	acpi_idle_do_entry(cx);
	kt2 = ktime_get_real();
	idle_time =  ktime_to_us(ktime_sub(kt2, kt1));

	local_irq_enable();
	cx->usage++;
	lapic_timer_state_broadcast(pr, cx, 0);

	return idle_time;
}

/**
 * acpi_idle_enter_simple - enters an ACPI state without BM handling
 * @dev: the target CPU
 * @state: the state data
 */
static int acpi_idle_enter_simple(struct cpuidle_device *dev,
				  struct cpuidle_state *state)
{
	struct acpi_processor *pr;
	struct acpi_processor_cx *cx = cpuidle_get_statedata(state);
	ktime_t  kt1, kt2;
	s64 idle_time_ns;
	s64 idle_time;

	pr = __this_cpu_read(processors);

	if (unlikely(!pr))
		return 0;

	if (acpi_idle_suspend)
		return(acpi_idle_enter_c1(dev, state));

	local_irq_disable();

	if (cx->entry_method != ACPI_CSTATE_FFH) {
		current_thread_info()->status &= ~TS_POLLING;
		/*
		 * TS_POLLING-cleared state must be visible before we test
		 * NEED_RESCHED:
		 */
		smp_mb();

		if (unlikely(need_resched())) {
			current_thread_info()->status |= TS_POLLING;
			local_irq_enable();
			return 0;
		}
	}

	/*
	 * Must be done before busmaster disable as we might need to
	 * access HPET !
	 */
	lapic_timer_state_broadcast(pr, cx, 1);

	if (cx->type == ACPI_STATE_C3)
		ACPI_FLUSH_CPU_CACHE();

	kt1 = ktime_get_real();
	/* Tell the scheduler that we are going deep-idle: */
	sched_clock_idle_sleep_event();
	acpi_idle_do_entry(cx);
	kt2 = ktime_get_real();
	idle_time_ns = ktime_to_ns(ktime_sub(kt2, kt1));
	idle_time = idle_time_ns;
	do_div(idle_time, NSEC_PER_USEC);

	/* Tell the scheduler how much we idled: */
	sched_clock_idle_wakeup_event(idle_time_ns);

	local_irq_enable();
	if (cx->entry_method != ACPI_CSTATE_FFH)
		current_thread_info()->status |= TS_POLLING;

	cx->usage++;

	lapic_timer_state_broadcast(pr, cx, 0);
	cx->time += idle_time;
	return idle_time;
}

static int c3_cpu_count;
static DEFINE_RAW_SPINLOCK(c3_lock);

/**
 * acpi_idle_enter_bm - enters C3 with proper BM handling
 * @dev: the target CPU
 * @state: the state data
 *
 * If BM is detected, the deepest non-C3 idle state is entered instead.
 */
static int acpi_idle_enter_bm(struct cpuidle_device *dev,
			      struct cpuidle_state *state)
{
	struct acpi_processor *pr;
	struct acpi_processor_cx *cx = cpuidle_get_statedata(state);
	ktime_t  kt1, kt2;
	s64 idle_time_ns;
	s64 idle_time;


	pr = __this_cpu_read(processors);

	if (unlikely(!pr))
		return 0;

	if (acpi_idle_suspend)
		return(acpi_idle_enter_c1(dev, state));

	if (!cx->bm_sts_skip && acpi_idle_bm_check()) {
		if (dev->safe_state) {
			dev->last_state = dev->safe_state;
			return dev->safe_state->enter(dev, dev->safe_state);
		} else {
			local_irq_disable();
			acpi_safe_halt();
			local_irq_enable();
			return 0;
		}
	}

	local_irq_disable();

	if (cx->entry_method != ACPI_CSTATE_FFH) {
		current_thread_info()->status &= ~TS_POLLING;
		/*
		 * TS_POLLING-cleared state must be visible before we test
		 * NEED_RESCHED:
		 */
		smp_mb();

		if (unlikely(need_resched())) {
			current_thread_info()->status |= TS_POLLING;
			local_irq_enable();
			return 0;
		}
	}

	acpi_unlazy_tlb(smp_processor_id());

	/* Tell the scheduler that we are going deep-idle: */
	sched_clock_idle_sleep_event();
	/*
	 * Must be done before busmaster disable as we might need to
	 * access HPET !
	 */
	lapic_timer_state_broadcast(pr, cx, 1);

	kt1 = ktime_get_real();
	/*
	 * disable bus master
	 * bm_check implies we need ARB_DIS
	 * !bm_check implies we need cache flush
	 * bm_control implies whether we can do ARB_DIS
	 *
	 * That leaves a case where bm_check is set and bm_control is
	 * not set. In that case we cannot do much, we enter C3
	 * without doing anything.
	 */
	if (pr->flags.bm_check && pr->flags.bm_control) {
		raw_spin_lock(&c3_lock);
		c3_cpu_count++;
		/* Disable bus master arbitration when all CPUs are in C3 */
		if (c3_cpu_count == num_online_cpus())
			acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1);
		raw_spin_unlock(&c3_lock);
	} else if (!pr->flags.bm_check) {
		ACPI_FLUSH_CPU_CACHE();
	}

	acpi_idle_do_entry(cx);

	/* Re-enable bus master arbitration */
	if (pr->flags.bm_check && pr->flags.bm_control) {
		raw_spin_lock(&c3_lock);
		acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0);
		c3_cpu_count--;
		raw_spin_unlock(&c3_lock);
	}
	kt2 = ktime_get_real();
	idle_time_ns = ktime_to_ns(ktime_sub(kt2, kt1));
	idle_time = idle_time_ns;
	do_div(idle_time, NSEC_PER_USEC);

	/* Tell the scheduler how much we idled: */
	sched_clock_idle_wakeup_event(idle_time_ns);

	local_irq_enable();
	if (cx->entry_method != ACPI_CSTATE_FFH)
		current_thread_info()->status |= TS_POLLING;

	cx->usage++;

	lapic_timer_state_broadcast(pr, cx, 0);
	cx->time += idle_time;
	return idle_time;
}

struct cpuidle_driver acpi_idle_driver = {
	.name =		"acpi_idle",
	.owner =	THIS_MODULE,
};

/**
 * acpi_processor_setup_cpuidle - prepares and configures CPUIDLE
 * @pr: the ACPI processor
 */
static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
{
	int i, count = CPUIDLE_DRIVER_STATE_START;
	struct acpi_processor_cx *cx;
	struct cpuidle_state *state;
	struct cpuidle_device *dev = &pr->power.dev;

	if (!pr->flags.power_setup_done)
		return -EINVAL;

	if (pr->flags.power == 0) {
		return -EINVAL;
	}

	dev->cpu = pr->id;
	for (i = 0; i < CPUIDLE_STATE_MAX; i++) {
		dev->states[i].name[0] = '\0';
		dev->states[i].desc[0] = '\0';
	}

	if (max_cstate == 0)
		max_cstate = 1;

	for (i = 1; i < ACPI_PROCESSOR_MAX_POWER && i <= max_cstate; i++) {
		cx = &pr->power.states[i];
		state = &dev->states[count];

		if (!cx->valid)
			continue;

#ifdef CONFIG_HOTPLUG_CPU
		if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) &&
		    !pr->flags.has_cst &&
		    !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED))
			continue;
#endif
		cpuidle_set_statedata(state, cx);

		snprintf(state->name, CPUIDLE_NAME_LEN, "C%d", i);
		strncpy(state->desc, cx->desc, CPUIDLE_DESC_LEN);
		state->exit_latency = cx->latency;
		state->target_residency = cx->latency * latency_factor;

		state->flags = 0;
		switch (cx->type) {
			case ACPI_STATE_C1:
			if (cx->entry_method == ACPI_CSTATE_FFH)
				state->flags |= CPUIDLE_FLAG_TIME_VALID;

			state->enter = acpi_idle_enter_c1;
			dev->safe_state = state;
			break;

			case ACPI_STATE_C2:
			state->flags |= CPUIDLE_FLAG_TIME_VALID;
			state->enter = acpi_idle_enter_simple;
			dev->safe_state = state;
			break;

			case ACPI_STATE_C3:
			state->flags |= CPUIDLE_FLAG_TIME_VALID;
			state->enter = pr->flags.bm_check ?
					acpi_idle_enter_bm :
					acpi_idle_enter_simple;
			break;
		}

		count++;
		if (count == CPUIDLE_STATE_MAX)
			break;
	}

	dev->state_count = count;

	if (!count)
		return -EINVAL;

	return 0;
}

int acpi_processor_cst_has_changed(struct acpi_processor *pr)
{
	int ret = 0;

	if (disabled_by_idle_boot_param())
		return 0;

	if (!pr)
		return -EINVAL;

	if (nocst) {
		return -ENODEV;
	}

	if (!pr->flags.power_setup_done)
		return -ENODEV;

	cpuidle_pause_and_lock();
	cpuidle_disable_device(&pr->power.dev);
	acpi_processor_get_power_info(pr);
	if (pr->flags.power) {
		acpi_processor_setup_cpuidle(pr);
		ret = cpuidle_enable_device(&pr->power.dev);
	}
	cpuidle_resume_and_unlock();

	return ret;
}

int __cpuinit acpi_processor_power_init(struct acpi_processor *pr,
			      struct acpi_device *device)
{
	acpi_status status = 0;
	static int first_run;

	if (disabled_by_idle_boot_param())
		return 0;

	if (!first_run) {
		dmi_check_system(processor_power_dmi_table);
		max_cstate = acpi_processor_cstate_check(max_cstate);
		if (max_cstate < ACPI_C_STATES_MAX)
			printk(KERN_NOTICE
			       "ACPI: processor limited to max C-state %d\n",
			       max_cstate);
		first_run++;
	}

	if (!pr)
		return -EINVAL;

	if (acpi_gbl_FADT.cst_control && !nocst) {
		status =
		    acpi_os_write_port(acpi_gbl_FADT.smi_command, acpi_gbl_FADT.cst_control, 8);
		if (ACPI_FAILURE(status)) {
			ACPI_EXCEPTION((AE_INFO, status,
					"Notifying BIOS of _CST ability failed"));
		}
	}

	acpi_processor_get_power_info(pr);
	pr->flags.power_setup_done = 1;

	/*
	 * Install the idle handler if processor power management is supported.
	 * Note that we use previously set idle handler will be used on
	 * platforms that only support C1.
	 */
	if (pr->flags.power) {
		acpi_processor_setup_cpuidle(pr);
		if (cpuidle_register_device(&pr->power.dev))
			return -EIO;
	}
	return 0;
}

int acpi_processor_power_exit(struct acpi_processor *pr,
			      struct acpi_device *device)
{
	if (disabled_by_idle_boot_param())
		return 0;

	cpuidle_unregister_device(&pr->power.dev);
	pr->flags.power_setup_done = 0;

	return 0;
}