summaryrefslogtreecommitdiffstats
path: root/drivers/cpufreq/acpi-cpufreq.c
blob: 822ca03a87f796ae321cb9c2bd54ffe7380b5581 (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
/*
 * acpi-cpufreq.c - ACPI Processor P-States Driver
 *
 *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
 *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
 *  Copyright (C) 2002 - 2004 Dominik Brodowski <linux@brodo.de>
 *  Copyright (C) 2006       Denis Sadykov <denis.m.sadykov@intel.com>
 *
 * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *
 *  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/smp.h>
#include <linux/sched.h>
#include <linux/cpufreq.h>
#include <linux/compiler.h>
#include <linux/dmi.h>
#include <linux/slab.h>

#include <linux/acpi.h>
#include <linux/io.h>
#include <linux/delay.h>
#include <linux/uaccess.h>

#include <acpi/processor.h>

#include <asm/msr.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>

MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
MODULE_DESCRIPTION("ACPI Processor P-States Driver");
MODULE_LICENSE("GPL");

#define PFX "acpi-cpufreq: "

enum {
	UNDEFINED_CAPABLE = 0,
	SYSTEM_INTEL_MSR_CAPABLE,
	SYSTEM_AMD_MSR_CAPABLE,
	SYSTEM_IO_CAPABLE,
};

#define INTEL_MSR_RANGE		(0xffff)
#define AMD_MSR_RANGE		(0x7)

#define MSR_K7_HWCR_CPB_DIS	(1ULL << 25)

struct acpi_cpufreq_data {
	struct acpi_processor_performance *acpi_data;
	struct cpufreq_frequency_table *freq_table;
	unsigned int resume;
	unsigned int cpu_feature;
	cpumask_var_t freqdomain_cpus;
};

static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data);

/* acpi_perf_data is a pointer to percpu data. */
static struct acpi_processor_performance __percpu *acpi_perf_data;

static struct cpufreq_driver acpi_cpufreq_driver;

static unsigned int acpi_pstate_strict;
static struct msr __percpu *msrs;

static bool boost_state(unsigned int cpu)
{
	u32 lo, hi;
	u64 msr;

	switch (boot_cpu_data.x86_vendor) {
	case X86_VENDOR_INTEL:
		rdmsr_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &lo, &hi);
		msr = lo | ((u64)hi << 32);
		return !(msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
	case X86_VENDOR_AMD:
		rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
		msr = lo | ((u64)hi << 32);
		return !(msr & MSR_K7_HWCR_CPB_DIS);
	}
	return false;
}

static void boost_set_msrs(bool enable, const struct cpumask *cpumask)
{
	u32 cpu;
	u32 msr_addr;
	u64 msr_mask;

	switch (boot_cpu_data.x86_vendor) {
	case X86_VENDOR_INTEL:
		msr_addr = MSR_IA32_MISC_ENABLE;
		msr_mask = MSR_IA32_MISC_ENABLE_TURBO_DISABLE;
		break;
	case X86_VENDOR_AMD:
		msr_addr = MSR_K7_HWCR;
		msr_mask = MSR_K7_HWCR_CPB_DIS;
		break;
	default:
		return;
	}

	rdmsr_on_cpus(cpumask, msr_addr, msrs);

	for_each_cpu(cpu, cpumask) {
		struct msr *reg = per_cpu_ptr(msrs, cpu);
		if (enable)
			reg->q &= ~msr_mask;
		else
			reg->q |= msr_mask;
	}

	wrmsr_on_cpus(cpumask, msr_addr, msrs);
}

static int _store_boost(int val)
{
	get_online_cpus();
	boost_set_msrs(val, cpu_online_mask);
	put_online_cpus();
	pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis");

	return 0;
}

static ssize_t show_freqdomain_cpus(struct cpufreq_policy *policy, char *buf)
{
	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);

	return cpufreq_show_cpus(data->freqdomain_cpus, buf);
}

cpufreq_freq_attr_ro(freqdomain_cpus);

#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
static ssize_t store_boost(const char *buf, size_t count)
{
	int ret;
	unsigned long val = 0;

	if (!acpi_cpufreq_driver.boost_supported)
		return -EINVAL;

	ret = kstrtoul(buf, 10, &val);
	if (ret || (val > 1))
		return -EINVAL;

	_store_boost((int) val);

	return count;
}

static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
			 size_t count)
{
	return store_boost(buf, count);
}

static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf)
{
	return sprintf(buf, "%u\n", acpi_cpufreq_driver.boost_enabled);
}

cpufreq_freq_attr_rw(cpb);
#endif

static int check_est_cpu(unsigned int cpuid)
{
	struct cpuinfo_x86 *cpu = &cpu_data(cpuid);

	return cpu_has(cpu, X86_FEATURE_EST);
}

static int check_amd_hwpstate_cpu(unsigned int cpuid)
{
	struct cpuinfo_x86 *cpu = &cpu_data(cpuid);

	return cpu_has(cpu, X86_FEATURE_HW_PSTATE);
}

static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
{
	struct acpi_processor_performance *perf;
	int i;

	perf = data->acpi_data;

	for (i = 0; i < perf->state_count; i++) {
		if (value == perf->states[i].status)
			return data->freq_table[i].frequency;
	}
	return 0;
}

static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
{
	int i;
	struct acpi_processor_performance *perf;

	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
		msr &= AMD_MSR_RANGE;
	else
		msr &= INTEL_MSR_RANGE;

	perf = data->acpi_data;

	for (i = 0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
		if (msr == perf->states[data->freq_table[i].driver_data].status)
			return data->freq_table[i].frequency;
	}
	return data->freq_table[0].frequency;
}

static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data)
{
	switch (data->cpu_feature) {
	case SYSTEM_INTEL_MSR_CAPABLE:
	case SYSTEM_AMD_MSR_CAPABLE:
		return extract_msr(val, data);
	case SYSTEM_IO_CAPABLE:
		return extract_io(val, data);
	default:
		return 0;
	}
}

struct msr_addr {
	u32 reg;
};

struct io_addr {
	u16 port;
	u8 bit_width;
};

struct drv_cmd {
	unsigned int type;
	const struct cpumask *mask;
	union {
		struct msr_addr msr;
		struct io_addr io;
	} addr;
	u32 val;
};

/* Called via smp_call_function_single(), on the target CPU */
static void do_drv_read(void *_cmd)
{
	struct drv_cmd *cmd = _cmd;
	u32 h;

	switch (cmd->type) {
	case SYSTEM_INTEL_MSR_CAPABLE:
	case SYSTEM_AMD_MSR_CAPABLE:
		rdmsr(cmd->addr.msr.reg, cmd->val, h);
		break;
	case SYSTEM_IO_CAPABLE:
		acpi_os_read_port((acpi_io_address)cmd->addr.io.port,
				&cmd->val,
				(u32)cmd->addr.io.bit_width);
		break;
	default:
		break;
	}
}

/* Called via smp_call_function_many(), on the target CPUs */
static void do_drv_write(void *_cmd)
{
	struct drv_cmd *cmd = _cmd;
	u32 lo, hi;

	switch (cmd->type) {
	case SYSTEM_INTEL_MSR_CAPABLE:
		rdmsr(cmd->addr.msr.reg, lo, hi);
		lo = (lo & ~INTEL_MSR_RANGE) | (cmd->val & INTEL_MSR_RANGE);
		wrmsr(cmd->addr.msr.reg, lo, hi);
		break;
	case SYSTEM_AMD_MSR_CAPABLE:
		wrmsr(cmd->addr.msr.reg, cmd->val, 0);
		break;
	case SYSTEM_IO_CAPABLE:
		acpi_os_write_port((acpi_io_address)cmd->addr.io.port,
				cmd->val,
				(u32)cmd->addr.io.bit_width);
		break;
	default:
		break;
	}
}

static void drv_read(struct drv_cmd *cmd)
{
	int err;
	cmd->val = 0;

	err = smp_call_function_any(cmd->mask, do_drv_read, cmd, 1);
	WARN_ON_ONCE(err);	/* smp_call_function_any() was buggy? */
}

static void drv_write(struct drv_cmd *cmd)
{
	int this_cpu;

	this_cpu = get_cpu();
	if (cpumask_test_cpu(this_cpu, cmd->mask))
		do_drv_write(cmd);
	smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
	put_cpu();
}

static u32 get_cur_val(const struct cpumask *mask)
{
	struct acpi_processor_performance *perf;
	struct drv_cmd cmd;

	if (unlikely(cpumask_empty(mask)))
		return 0;

	switch (per_cpu(acfreq_data, cpumask_first(mask))->cpu_feature) {
	case SYSTEM_INTEL_MSR_CAPABLE:
		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
		cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
		break;
	case SYSTEM_AMD_MSR_CAPABLE:
		cmd.type = SYSTEM_AMD_MSR_CAPABLE;
		cmd.addr.msr.reg = MSR_AMD_PERF_CTL;
		break;
	case SYSTEM_IO_CAPABLE:
		cmd.type = SYSTEM_IO_CAPABLE;
		perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data;
		cmd.addr.io.port = perf->control_register.address;
		cmd.addr.io.bit_width = perf->control_register.bit_width;
		break;
	default:
		return 0;
	}

	cmd.mask = mask;
	drv_read(&cmd);

	pr_debug("get_cur_val = %u\n", cmd.val);

	return cmd.val;
}

static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
{
	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
	unsigned int freq;
	unsigned int cached_freq;

	pr_debug("get_cur_freq_on_cpu (%d)\n", cpu);

	if (unlikely(data == NULL ||
		     data->acpi_data == NULL || data->freq_table == NULL)) {
		return 0;
	}

	cached_freq = data->freq_table[data->acpi_data->state].frequency;
	freq = extract_freq(get_cur_val(cpumask_of(cpu)), data);
	if (freq != cached_freq) {
		/*
		 * The dreaded BIOS frequency change behind our back.
		 * Force set the frequency on next target call.
		 */
		data->resume = 1;
	}

	pr_debug("cur freq = %u\n", freq);

	return freq;
}

static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
				struct acpi_cpufreq_data *data)
{
	unsigned int cur_freq;
	unsigned int i;

	for (i = 0; i < 100; i++) {
		cur_freq = extract_freq(get_cur_val(mask), data);
		if (cur_freq == freq)
			return 1;
		udelay(10);
	}
	return 0;
}

static int acpi_cpufreq_target(struct cpufreq_policy *policy,
			       unsigned int index)
{
	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
	struct acpi_processor_performance *perf;
	struct drv_cmd cmd;
	unsigned int next_perf_state = 0; /* Index into perf table */
	int result = 0;

	if (unlikely(data == NULL ||
	     data->acpi_data == NULL || data->freq_table == NULL)) {
		return -ENODEV;
	}

	perf = data->acpi_data;
	next_perf_state = data->freq_table[index].driver_data;
	if (perf->state == next_perf_state) {
		if (unlikely(data->resume)) {
			pr_debug("Called after resume, resetting to P%d\n",
				next_perf_state);
			data->resume = 0;
		} else {
			pr_debug("Already at target state (P%d)\n",
				next_perf_state);
			goto out;
		}
	}

	switch (data->cpu_feature) {
	case SYSTEM_INTEL_MSR_CAPABLE:
		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
		cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
		cmd.val = (u32) perf->states[next_perf_state].control;
		break;
	case SYSTEM_AMD_MSR_CAPABLE:
		cmd.type = SYSTEM_AMD_MSR_CAPABLE;
		cmd.addr.msr.reg = MSR_AMD_PERF_CTL;
		cmd.val = (u32) perf->states[next_perf_state].control;
		break;
	case SYSTEM_IO_CAPABLE:
		cmd.type = SYSTEM_IO_CAPABLE;
		cmd.addr.io.port = perf->control_register.address;
		cmd.addr.io.bit_width = perf->control_register.bit_width;
		cmd.val = (u32) perf->states[next_perf_state].control;
		break;
	default:
		result = -ENODEV;
		goto out;
	}

	/* cpufreq holds the hotplug lock, so we are safe from here on */
	if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY)
		cmd.mask = policy->cpus;
	else
		cmd.mask = cpumask_of(policy->cpu);

	drv_write(&cmd);

	if (acpi_pstate_strict) {
		if (!check_freqs(cmd.mask, data->freq_table[index].frequency,
					data)) {
			pr_debug("acpi_cpufreq_target failed (%d)\n",
				policy->cpu);
			result = -EAGAIN;
		}
	}

	if (!result)
		perf->state = next_perf_state;

out:
	return result;
}

static unsigned long
acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
{
	struct acpi_processor_performance *perf = data->acpi_data;

	if (cpu_khz) {
		/* search the closest match to cpu_khz */
		unsigned int i;
		unsigned long freq;
		unsigned long freqn = perf->states[0].core_frequency * 1000;

		for (i = 0; i < (perf->state_count-1); i++) {
			freq = freqn;
			freqn = perf->states[i+1].core_frequency * 1000;
			if ((2 * cpu_khz) > (freqn + freq)) {
				perf->state = i;
				return freq;
			}
		}
		perf->state = perf->state_count-1;
		return freqn;
	} else {
		/* assume CPU is at P0... */
		perf->state = 0;
		return perf->states[0].core_frequency * 1000;
	}
}

static void free_acpi_perf_data(void)
{
	unsigned int i;

	/* Freeing a NULL pointer is OK, and alloc_percpu zeroes. */
	for_each_possible_cpu(i)
		free_cpumask_var(per_cpu_ptr(acpi_perf_data, i)
				 ->shared_cpu_map);
	free_percpu(acpi_perf_data);
}

static int boost_notify(struct notifier_block *nb, unsigned long action,
		      void *hcpu)
{
	unsigned cpu = (long)hcpu;
	const struct cpumask *cpumask;

	cpumask = get_cpu_mask(cpu);

	/*
	 * Clear the boost-disable bit on the CPU_DOWN path so that
	 * this cpu cannot block the remaining ones from boosting. On
	 * the CPU_UP path we simply keep the boost-disable flag in
	 * sync with the current global state.
	 */

	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
		break;

	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
		boost_set_msrs(1, cpumask);
		break;

	default:
		break;
	}

	return NOTIFY_OK;
}


static struct notifier_block boost_nb = {
	.notifier_call          = boost_notify,
};

/*
 * acpi_cpufreq_early_init - initialize ACPI P-States library
 *
 * Initialize the ACPI P-States library (drivers/acpi/processor_perflib.c)
 * in order to determine correct frequency and voltage pairings. We can
 * do _PDC and _PSD and find out the processor dependency for the
 * actual init that will happen later...
 */
static int __init acpi_cpufreq_early_init(void)
{
	unsigned int i;
	pr_debug("acpi_cpufreq_early_init\n");

	acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
	if (!acpi_perf_data) {
		pr_debug("Memory allocation error for acpi_perf_data.\n");
		return -ENOMEM;
	}
	for_each_possible_cpu(i) {
		if (!zalloc_cpumask_var_node(
			&per_cpu_ptr(acpi_perf_data, i)->shared_cpu_map,
			GFP_KERNEL, cpu_to_node(i))) {

			/* Freeing a NULL pointer is OK: alloc_percpu zeroes. */
			free_acpi_perf_data();
			return -ENOMEM;
		}
	}

	/* Do initialization in ACPI core */
	acpi_processor_preregister_performance(acpi_perf_data);
	return 0;
}

#ifdef CONFIG_SMP
/*
 * Some BIOSes do SW_ANY coordination internally, either set it up in hw
 * or do it in BIOS firmware and won't inform about it to OS. If not
 * detected, this has a side effect of making CPU run at a different speed
 * than OS intended it to run at. Detect it and handle it cleanly.
 */
static int bios_with_sw_any_bug;

static int sw_any_bug_found(const struct dmi_system_id *d)
{
	bios_with_sw_any_bug = 1;
	return 0;
}

static const struct dmi_system_id sw_any_bug_dmi_table[] = {
	{
		.callback = sw_any_bug_found,
		.ident = "Supermicro Server X6DLP",
		.matches = {
			DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"),
			DMI_MATCH(DMI_BIOS_VERSION, "080010"),
			DMI_MATCH(DMI_PRODUCT_NAME, "X6DLP"),
		},
	},
	{ }
};

static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c)
{
	/* Intel Xeon Processor 7100 Series Specification Update
	 * http://www.intel.com/Assets/PDF/specupdate/314554.pdf
	 * AL30: A Machine Check Exception (MCE) Occurring during an
	 * Enhanced Intel SpeedStep Technology Ratio Change May Cause
	 * Both Processor Cores to Lock Up. */
	if (c->x86_vendor == X86_VENDOR_INTEL) {
		if ((c->x86 == 15) &&
		    (c->x86_model == 6) &&
		    (c->x86_mask == 8)) {
			printk(KERN_INFO "acpi-cpufreq: Intel(R) "
			    "Xeon(R) 7100 Errata AL30, processors may "
			    "lock up on frequency changes: disabling "
			    "acpi-cpufreq.\n");
			return -ENODEV;
		    }
		}
	return 0;
}
#endif

static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
{
	unsigned int i;
	unsigned int valid_states = 0;
	unsigned int cpu = policy->cpu;
	struct acpi_cpufreq_data *data;
	unsigned int result = 0;
	struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
	struct acpi_processor_performance *perf;
#ifdef CONFIG_SMP
	static int blacklisted;
#endif

	pr_debug("acpi_cpufreq_cpu_init\n");

#ifdef CONFIG_SMP
	if (blacklisted)
		return blacklisted;
	blacklisted = acpi_cpufreq_blacklist(c);
	if (blacklisted)
		return blacklisted;
#endif

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

	if (!zalloc_cpumask_var(&data->freqdomain_cpus, GFP_KERNEL)) {
		result = -ENOMEM;
		goto err_free;
	}

	data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu);
	per_cpu(acfreq_data, cpu) = data;

	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
		acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;

	result = acpi_processor_register_performance(data->acpi_data, cpu);
	if (result)
		goto err_free_mask;

	perf = data->acpi_data;
	policy->shared_type = perf->shared_type;

	/*
	 * Will let policy->cpus know about dependency only when software
	 * coordination is required.
	 */
	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL ||
	    policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
		cpumask_copy(policy->cpus, perf->shared_cpu_map);
	}
	cpumask_copy(data->freqdomain_cpus, perf->shared_cpu_map);

#ifdef CONFIG_SMP
	dmi_check_system(sw_any_bug_dmi_table);
	if (bios_with_sw_any_bug && !policy_is_shared(policy)) {
		policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
		cpumask_copy(policy->cpus, cpu_core_mask(cpu));
	}

	if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
		cpumask_clear(policy->cpus);
		cpumask_set_cpu(cpu, policy->cpus);
		cpumask_copy(data->freqdomain_cpus, cpu_sibling_mask(cpu));
		policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
		pr_info_once(PFX "overriding BIOS provided _PSD data\n");
	}
#endif

	/* capability check */
	if (perf->state_count <= 1) {
		pr_debug("No P-States\n");
		result = -ENODEV;
		goto err_unreg;
	}

	if (perf->control_register.space_id != perf->status_register.space_id) {
		result = -ENODEV;
		goto err_unreg;
	}

	switch (perf->control_register.space_id) {
	case ACPI_ADR_SPACE_SYSTEM_IO:
		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
		    boot_cpu_data.x86 == 0xf) {
			pr_debug("AMD K8 systems must use native drivers.\n");
			result = -ENODEV;
			goto err_unreg;
		}
		pr_debug("SYSTEM IO addr space\n");
		data->cpu_feature = SYSTEM_IO_CAPABLE;
		break;
	case ACPI_ADR_SPACE_FIXED_HARDWARE:
		pr_debug("HARDWARE addr space\n");
		if (check_est_cpu(cpu)) {
			data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE;
			break;
		}
		if (check_amd_hwpstate_cpu(cpu)) {
			data->cpu_feature = SYSTEM_AMD_MSR_CAPABLE;
			break;
		}
		result = -ENODEV;
		goto err_unreg;
	default:
		pr_debug("Unknown addr space %d\n",
			(u32) (perf->control_register.space_id));
		result = -ENODEV;
		goto err_unreg;
	}

	data->freq_table = kmalloc(sizeof(*data->freq_table) *
		    (perf->state_count+1), GFP_KERNEL);
	if (!data->freq_table) {
		result = -ENOMEM;
		goto err_unreg;
	}

	/* detect transition latency */
	policy->cpuinfo.transition_latency = 0;
	for (i = 0; i < perf->state_count; i++) {
		if ((perf->states[i].transition_latency * 1000) >
		    policy->cpuinfo.transition_latency)
			policy->cpuinfo.transition_latency =
			    perf->states[i].transition_latency * 1000;
	}

	/* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
	if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
	    policy->cpuinfo.transition_latency > 20 * 1000) {
		policy->cpuinfo.transition_latency = 20 * 1000;
		printk_once(KERN_INFO
			    "P-state transition latency capped at 20 uS\n");
	}

	/* table init */
	for (i = 0; i < perf->state_count; i++) {
		if (i > 0 && perf->states[i].core_frequency >=
		    data->freq_table[valid_states-1].frequency / 1000)
			continue;

		data->freq_table[valid_states].driver_data = i;
		data->freq_table[valid_states].frequency =
		    perf->states[i].core_frequency * 1000;
		valid_states++;
	}
	data->freq_table[valid_states].frequency = CPUFREQ_TABLE_END;
	perf->state = 0;

	result = cpufreq_table_validate_and_show(policy, data->freq_table);
	if (result)
		goto err_freqfree;

	if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
		printk(KERN_WARNING FW_WARN "P-state 0 is not max freq\n");

	switch (perf->control_register.space_id) {
	case ACPI_ADR_SPACE_SYSTEM_IO:
		/*
		 * The core will not set policy->cur, because
		 * cpufreq_driver->get is NULL, so we need to set it here.
		 * However, we have to guess it, because the current speed is
		 * unknown and not detectable via IO ports.
		 */
		policy->cur = acpi_cpufreq_guess_freq(data, policy->cpu);
		break;
	case ACPI_ADR_SPACE_FIXED_HARDWARE:
		acpi_cpufreq_driver.get = get_cur_freq_on_cpu;
		break;
	default:
		break;
	}

	/* notify BIOS that we exist */
	acpi_processor_notify_smm(THIS_MODULE);

	pr_debug("CPU%u - ACPI performance management activated.\n", cpu);
	for (i = 0; i < perf->state_count; i++)
		pr_debug("     %cP%d: %d MHz, %d mW, %d uS\n",
			(i == perf->state ? '*' : ' '), i,
			(u32) perf->states[i].core_frequency,
			(u32) perf->states[i].power,
			(u32) perf->states[i].transition_latency);

	/*
	 * the first call to ->target() should result in us actually
	 * writing something to the appropriate registers.
	 */
	data->resume = 1;

	return result;

err_freqfree:
	kfree(data->freq_table);
err_unreg:
	acpi_processor_unregister_performance(perf, cpu);
err_free_mask:
	free_cpumask_var(data->freqdomain_cpus);
err_free:
	kfree(data);
	per_cpu(acfreq_data, cpu) = NULL;

	return result;
}

static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
{
	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);

	pr_debug("acpi_cpufreq_cpu_exit\n");

	if (data) {
		per_cpu(acfreq_data, policy->cpu) = NULL;
		acpi_processor_unregister_performance(data->acpi_data,
						      policy->cpu);
		free_cpumask_var(data->freqdomain_cpus);
		kfree(data->freq_table);
		kfree(data);
	}

	return 0;
}

static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
{
	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);

	pr_debug("acpi_cpufreq_resume\n");

	data->resume = 1;

	return 0;
}

static struct freq_attr *acpi_cpufreq_attr[] = {
	&cpufreq_freq_attr_scaling_available_freqs,
	&freqdomain_cpus,
	NULL,	/* this is a placeholder for cpb, do not remove */
	NULL,
};

static struct cpufreq_driver acpi_cpufreq_driver = {
	.verify		= cpufreq_generic_frequency_table_verify,
	.target_index	= acpi_cpufreq_target,
	.bios_limit	= acpi_processor_get_bios_limit,
	.init		= acpi_cpufreq_cpu_init,
	.exit		= acpi_cpufreq_cpu_exit,
	.resume		= acpi_cpufreq_resume,
	.name		= "acpi-cpufreq",
	.attr		= acpi_cpufreq_attr,
	.set_boost      = _store_boost,
};

static void __init acpi_cpufreq_boost_init(void)
{
	if (boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)) {
		msrs = msrs_alloc();

		if (!msrs)
			return;

		acpi_cpufreq_driver.boost_supported = true;
		acpi_cpufreq_driver.boost_enabled = boost_state(0);
		get_online_cpus();

		/* Force all MSRs to the same value */
		boost_set_msrs(acpi_cpufreq_driver.boost_enabled,
			       cpu_online_mask);

		register_cpu_notifier(&boost_nb);

		put_online_cpus();
	}
}

static void acpi_cpufreq_boost_exit(void)
{
	if (msrs) {
		unregister_cpu_notifier(&boost_nb);

		msrs_free(msrs);
		msrs = NULL;
	}
}

static int __init acpi_cpufreq_init(void)
{
	int ret;

	if (acpi_disabled)
		return -ENODEV;

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

	pr_debug("acpi_cpufreq_init\n");

	ret = acpi_cpufreq_early_init();
	if (ret)
		return ret;

#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
	/* this is a sysfs file with a strange name and an even stranger
	 * semantic - per CPU instantiation, but system global effect.
	 * Lets enable it only on AMD CPUs for compatibility reasons and
	 * only if configured. This is considered legacy code, which
	 * will probably be removed at some point in the future.
	 */
	if (check_amd_hwpstate_cpu(0)) {
		struct freq_attr **iter;

		pr_debug("adding sysfs entry for cpb\n");

		for (iter = acpi_cpufreq_attr; *iter != NULL; iter++)
			;

		/* make sure there is a terminator behind it */
		if (iter[1] == NULL)
			*iter = &cpb;
	}
#endif
	acpi_cpufreq_boost_init();

	ret = cpufreq_register_driver(&acpi_cpufreq_driver);
	if (ret) {
		free_acpi_perf_data();
		acpi_cpufreq_boost_exit();
	}
	return ret;
}

static void __exit acpi_cpufreq_exit(void)
{
	pr_debug("acpi_cpufreq_exit\n");

	acpi_cpufreq_boost_exit();

	cpufreq_unregister_driver(&acpi_cpufreq_driver);

	free_acpi_perf_data();
}

module_param(acpi_pstate_strict, uint, 0644);
MODULE_PARM_DESC(acpi_pstate_strict,
	"value 0 or non-zero. non-zero -> strict ACPI checks are "
	"performed during frequency changes.");

late_initcall(acpi_cpufreq_init);
module_exit(acpi_cpufreq_exit);

static const struct x86_cpu_id acpi_cpufreq_ids[] = {
	X86_FEATURE_MATCH(X86_FEATURE_ACPI),
	X86_FEATURE_MATCH(X86_FEATURE_HW_PSTATE),
	{}
};
MODULE_DEVICE_TABLE(x86cpu, acpi_cpufreq_ids);

static const struct acpi_device_id processor_device_ids[] = {
	{ACPI_PROCESSOR_OBJECT_HID, },
	{ACPI_PROCESSOR_DEVICE_HID, },
	{},
};
MODULE_DEVICE_TABLE(acpi, processor_device_ids);

MODULE_ALIAS("acpi");