litmus-rt.git - The LITMUS^RT kernel.

The LITMUS^RT kernel.

Bjoern Brandenburg

about summary refs log tree commit diff stats

path: root/include/asm-m68knommu/mcfne.h

	Commit message (Expand)	Author	Age
*	Don't include linux/config.h from anywhere else in include/	David Woodhouse	2006-04-26
*	[PATCH] m68knommu: use board defines to distinguish boards	Greg Ungerer	2005-11-02
*	Linux-2.6.12-rc2v2.6.12-rc2	Linus Torvalds	2005-04-16

10
11

13
14
15

16
17

18
19

21
22

24
25
26

31
32

35
36
37

41
42

45
46

62
63

64
65

67
68
69

72
73
74

75
76
77

80
81
82

83
84
85

88
89

98
99

102
103

104
105

114
115
116

118
119

134
135

218
219

225
226

243
244

247
248
249

250
251

252
253
254

284
285

288
289
290

295
296

299
300
301

302
303
304

313
314

317
318

320
321
322

323
324

327
328

330
331

337
338

339
340

357
358
359

375
376
377

379
380

382
383

384
385

387
388

390
391

399
400
401

405
406
407

409
410

411
412

413
414
415

425
426

432
433

464
465
466

473
474

479
480

488
489
490

500
501
502

503
504
505

506
507

518
519
520

521
522

523
524

526
527
528

547
548

559
560

565
566
567

601
602

636
637

660
661

663
664
665

667
668
669

671
672
673

674
675

679
680

682
683

696
697
698

699
700

702
703

724
725
726

727
728
729

734
735
736

804
805

807
808

815
816

818
819
820

827
828
829

831
832

834
835

839
840

844
845

850
851
852

868
869
870

877
878

880
881

883
884
885

888
889

902
903

917
918

919
920

921
922

930
931
932

970
971

972
973
974

984
985
986

987
988

996
997

1008
1009
1010

1019
1020

1023
1024
1025

1026
1027

1029
1030

1033
1034

1084
1085
1086

1093
1094

1096
1097
1098

1111
1112

1115
1116
1117

1123
1124

1126
1127

1130
1131

1138
1139
1140

1144
1145

1146
1147
1148

1165
1166

1167
1168
1169

1178
1179
1180

1183
1184

1194
1195
1196

1209
1210

1217
1218

1232
1233

1238
1239
1240

1245
1246

1247
1248

1250
1251

1283
1284

1295
1296

1297
1298

1339
1340
1341

1344
1345

1361
1362

1365
1366
1367

1373
1374

1379
1380

1382
1383

1387
1388

1390
1391

1392
1393

1401
1402

1415
1416

1417
1418

1421
1422
1423

1425
1426
1427

1481
1482
1483

1484
1485

1492
1493

1495
1496
1497

1503
1504

1521
1522

1530
1531

1534
1535
1536

1538
1539

1545
1546
1547

1559
1560

1565
1566

1569
1570
1571

1576
1577

1578
1579
1580

1581
1582

1595
1596

1619
1620
1621

1622
1623

1624
1625

1628
1629

1630
1631

1641
1642
1643

1655
1656
1657

1658
1659

1662
1663

1664
1665

1687
1688
1689

1702
1703

1716
1717
1718

1726
1727

1729
1730

1759
1760
1761

1765
1766

1768
1769

1781
1782

1798
1799

1805
1806

1812
1813
1814

1826
1827
1828

1829
1830

1835
1836
1837

1838
1839
1840

1864
1865

1880
1881

1887
1888

1895
1896

1907
1908
1909

1913
1914

1925
1926

1930
1931

1946
1947

1955
1956

1957
1958
1959

1962
1963

1967
1968
1969

1974
1975

1987
1988

1994
1995
1996

2002
2003

2007
2008
2009

2025
2026

2030
2031
2032

2034
2035

2038
2039

2047
2048
2049

2053
2054

2067
2068
2069

2097
2098

2104
2105
2106

2125
2126

2133
2134

2136
2137

2138
2139
2140

2144
2145
2146

2151
2152

2158
2159
2160

2161
2162
2163

2170
2171
2172

2197
2198
2199

2207
2208

/*
 *  linux/drivers/cpufreq/cpufreq.c
 *
 *  Copyright (C) 2001 Russell King
 *            (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
 *            (C) 2013 Viresh Kumar <viresh.kumar@linaro.org>
 *
 *  Oct 2005 - Ashok Raj <ashok.raj@intel.com>
 *	Added handling for CPU hotplug
 *  Feb 2006 - Jacob Shin <jacob.shin@amd.com>
 *	Fix handling for CPU hotplug -- affected CPUs
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/cpu.h>
#include <linux/cpufreq.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/init.h>
#include <linux/kernel_stat.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/syscore_ops.h>
#include <linux/tick.h>
#include <trace/events/power.h>

/**
 * The "cpufreq driver" - the arch- or hardware-dependent low
 * level driver of CPUFreq support, and its spinlock. This lock
 * also protects the cpufreq_cpu_data array.
 */
static struct cpufreq_driver *cpufreq_driver;
static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data_fallback);
static DEFINE_RWLOCK(cpufreq_driver_lock);
static DEFINE_MUTEX(cpufreq_governor_lock);
static LIST_HEAD(cpufreq_policy_list);

#ifdef CONFIG_HOTPLUG_CPU
/* This one keeps track of the previously set governor of a removed CPU */
static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
#endif

/*
 * cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure
 * all cpufreq/hotplug/workqueue/etc related lock issues.
 *
 * The rules for this semaphore:
 * - Any routine that wants to read from the policy structure will
 *   do a down_read on this semaphore.
 * - Any routine that will write to the policy structure and/or may take away
 *   the policy altogether (eg. CPU hotplug), will hold this lock in write
 *   mode before doing so.
 *
 * Additional rules:
 * - Governor routines that can be called in cpufreq hotplug path should not
 *   take this sem as top level hotplug notifier handler takes this.
 * - Lock should not be held across
 *     __cpufreq_governor(data, CPUFREQ_GOV_STOP);
 */
static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem);

#define lock_policy_rwsem(mode, cpu)					\
static void lock_policy_rwsem_##mode(int cpu)				\
{									\
	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);	\
	BUG_ON(!policy);						\
	down_##mode(&per_cpu(cpu_policy_rwsem, policy->cpu));		\
}

lock_policy_rwsem(read, cpu);
lock_policy_rwsem(write, cpu);

#define unlock_policy_rwsem(mode, cpu)					\
static void unlock_policy_rwsem_##mode(int cpu)				\
{									\
	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);	\
	BUG_ON(!policy);						\
	up_##mode(&per_cpu(cpu_policy_rwsem, policy->cpu));		\
}

unlock_policy_rwsem(read, cpu);
unlock_policy_rwsem(write, cpu);

/*
 * rwsem to guarantee that cpufreq driver module doesn't unload during critical
 * sections
 */
static DECLARE_RWSEM(cpufreq_rwsem);

/* internal prototypes */
static int __cpufreq_governor(struct cpufreq_policy *policy,
		unsigned int event);
static unsigned int __cpufreq_get(unsigned int cpu);
static void handle_update(struct work_struct *work);

/**
 * Two notifier lists: the "policy" list is involved in the
 * validation process for a new CPU frequency policy; the
 * "transition" list for kernel code that needs to handle
 * changes to devices when the CPU clock speed changes.
 * The mutex locks both lists.
 */
static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
static struct srcu_notifier_head cpufreq_transition_notifier_list;

static bool init_cpufreq_transition_notifier_list_called;
static int __init init_cpufreq_transition_notifier_list(void)
{
	srcu_init_notifier_head(&cpufreq_transition_notifier_list);
	init_cpufreq_transition_notifier_list_called = true;
	return 0;
}
pure_initcall(init_cpufreq_transition_notifier_list);

static int off __read_mostly;
static int cpufreq_disabled(void)
{
	return off;
}
void disable_cpufreq(void)
{
	off = 1;
}
static LIST_HEAD(cpufreq_governor_list);
static DEFINE_MUTEX(cpufreq_governor_mutex);

bool have_governor_per_policy(void)
{
	return !!(cpufreq_driver->flags & CPUFREQ_HAVE_GOVERNOR_PER_POLICY);
}
EXPORT_SYMBOL_GPL(have_governor_per_policy);

struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
{
	if (have_governor_per_policy())
		return &policy->kobj;
	else
		return cpufreq_global_kobject;
}
EXPORT_SYMBOL_GPL(get_governor_parent_kobj);

static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
{
	u64 idle_time;
	u64 cur_wall_time;
	u64 busy_time;

	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());

	busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];

	idle_time = cur_wall_time - busy_time;
	if (wall)
		*wall = cputime_to_usecs(cur_wall_time);

	return cputime_to_usecs(idle_time);
}

u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
{
	u64 idle_time = get_cpu_idle_time_us(cpu, io_busy ? wall : NULL);

	if (idle_time == -1ULL)
		return get_cpu_idle_time_jiffy(cpu, wall);
	else if (!io_busy)
		idle_time += get_cpu_iowait_time_us(cpu, wall);

	return idle_time;
}
EXPORT_SYMBOL_GPL(get_cpu_idle_time);

/*
 * This is a generic cpufreq init() routine which can be used by cpufreq
 * drivers of SMP systems. It will do following:
 * - validate & show freq table passed
 * - set policies transition latency
 * - policy->cpus with all possible CPUs
 */
int cpufreq_generic_init(struct cpufreq_policy *policy,
		struct cpufreq_frequency_table *table,
		unsigned int transition_latency)
{
	int ret;

	ret = cpufreq_table_validate_and_show(policy, table);
	if (ret) {
		pr_err("%s: invalid frequency table: %d\n", __func__, ret);
		return ret;
	}

	policy->cpuinfo.transition_latency = transition_latency;

	/*
	 * The driver only supports the SMP configuartion where all processors
	 * share the clock and voltage and clock.
	 */
	cpumask_setall(policy->cpus);

	return 0;
}
EXPORT_SYMBOL_GPL(cpufreq_generic_init);

struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
{
	struct cpufreq_policy *policy = NULL;
	unsigned long flags;

	if (cpufreq_disabled() || (cpu >= nr_cpu_ids))
		return NULL;

	if (!down_read_trylock(&cpufreq_rwsem))
		return NULL;

	/* get the cpufreq driver */
	read_lock_irqsave(&cpufreq_driver_lock, flags);

	if (cpufreq_driver) {
		/* get the CPU */
		policy = per_cpu(cpufreq_cpu_data, cpu);
		if (policy)
			kobject_get(&policy->kobj);
	}

	read_unlock_irqrestore(&cpufreq_driver_lock, flags);

	if (!policy)
		up_read(&cpufreq_rwsem);

	return policy;
}
EXPORT_SYMBOL_GPL(cpufreq_cpu_get);

void cpufreq_cpu_put(struct cpufreq_policy *policy)
{
	if (cpufreq_disabled())
		return;

	kobject_put(&policy->kobj);
	up_read(&cpufreq_rwsem);
}
EXPORT_SYMBOL_GPL(cpufreq_cpu_put);

/*********************************************************************
 *            EXTERNALLY AFFECTING FREQUENCY CHANGES                 *
 *********************************************************************/

/**
 * adjust_jiffies - adjust the system "loops_per_jiffy"
 *
 * This function alters the system "loops_per_jiffy" for the clock
 * speed change. Note that loops_per_jiffy cannot be updated on SMP
 * systems as each CPU might be scaled differently. So, use the arch
 * per-CPU loops_per_jiffy value wherever possible.
 */
#ifndef CONFIG_SMP
static unsigned long l_p_j_ref;
static unsigned int l_p_j_ref_freq;

static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
{
	if (ci->flags & CPUFREQ_CONST_LOOPS)
		return;

	if (!l_p_j_ref_freq) {
		l_p_j_ref = loops_per_jiffy;
		l_p_j_ref_freq = ci->old;
		pr_debug("saving %lu as reference value for loops_per_jiffy; "
			"freq is %u kHz\n", l_p_j_ref, l_p_j_ref_freq);
	}
	if ((val == CPUFREQ_POSTCHANGE && ci->old != ci->new) ||
	    (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) {
		loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq,
								ci->new);
		pr_debug("scaling loops_per_jiffy to %lu "
			"for frequency %u kHz\n", loops_per_jiffy, ci->new);
	}
}
#else
static inline void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
{
	return;
}
#endif

static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
		struct cpufreq_freqs *freqs, unsigned int state)
{
	BUG_ON(irqs_disabled());

	if (cpufreq_disabled())
		return;

	freqs->flags = cpufreq_driver->flags;
	pr_debug("notification %u of frequency transition to %u kHz\n",
		state, freqs->new);

	switch (state) {

	case CPUFREQ_PRECHANGE:
		/* detect if the driver reported a value as "old frequency"
		 * which is not equal to what the cpufreq core thinks is
		 * "old frequency".
		 */
		if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
			if ((policy) && (policy->cpu == freqs->cpu) &&
			    (policy->cur) && (policy->cur != freqs->old)) {
				pr_debug("Warning: CPU frequency is"
					" %u, cpufreq assumed %u kHz.\n",
					freqs->old, policy->cur);
				freqs->old = policy->cur;
			}
		}
		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
				CPUFREQ_PRECHANGE, freqs);
		adjust_jiffies(CPUFREQ_PRECHANGE, freqs);
		break;

	case CPUFREQ_POSTCHANGE:
		adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
		pr_debug("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new,
			(unsigned long)freqs->cpu);
		trace_cpu_frequency(freqs->new, freqs->cpu);
		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
				CPUFREQ_POSTCHANGE, freqs);
		if (likely(policy) && likely(policy->cpu == freqs->cpu))
			policy->cur = freqs->new;
		break;
	}
}

/**
 * cpufreq_notify_transition - call notifier chain and adjust_jiffies
 * on frequency transition.
 *
 * This function calls the transition notifiers and the "adjust_jiffies"
 * function. It is called twice on all CPU frequency changes that have
 * external effects.
 */
void cpufreq_notify_transition(struct cpufreq_policy *policy,
		struct cpufreq_freqs *freqs, unsigned int state)
{
	for_each_cpu(freqs->cpu, policy->cpus)
		__cpufreq_notify_transition(policy, freqs, state);
}
EXPORT_SYMBOL_GPL(cpufreq_notify_transition);


/*********************************************************************
 *                          SYSFS INTERFACE                          *
 *********************************************************************/

static struct cpufreq_governor *__find_governor(const char *str_governor)
{
	struct cpufreq_governor *t;

	list_for_each_entry(t, &cpufreq_governor_list, governor_list)
		if (!strnicmp(str_governor, t->name, CPUFREQ_NAME_LEN))
			return t;

	return NULL;
}

/**
 * cpufreq_parse_governor - parse a governor string
 */
static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
				struct cpufreq_governor **governor)
{
	int err = -EINVAL;

	if (!cpufreq_driver)
		goto out;

	if (cpufreq_driver->setpolicy) {
		if (!strnicmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
			*policy = CPUFREQ_POLICY_PERFORMANCE;
			err = 0;
		} else if (!strnicmp(str_governor, "powersave",
						CPUFREQ_NAME_LEN)) {
			*policy = CPUFREQ_POLICY_POWERSAVE;
			err = 0;
		}
	} else if (cpufreq_driver->target) {
		struct cpufreq_governor *t;

		mutex_lock(&cpufreq_governor_mutex);

		t = __find_governor(str_governor);

		if (t == NULL) {
			int ret;

			mutex_unlock(&cpufreq_governor_mutex);
			ret = request_module("cpufreq_%s", str_governor);
			mutex_lock(&cpufreq_governor_mutex);

			if (ret == 0)
				t = __find_governor(str_governor);
		}

		if (t != NULL) {
			*governor = t;
			err = 0;
		}

		mutex_unlock(&cpufreq_governor_mutex);
	}
out:
	return err;
}

/**
 * cpufreq_per_cpu_attr_read() / show_##file_name() -
 * print out cpufreq information
 *
 * Write out information from cpufreq_driver->policy[cpu]; object must be
 * "unsigned int".
 */

#define show_one(file_name, object)			\
static ssize_t show_##file_name				\
(struct cpufreq_policy *policy, char *buf)		\
{							\
	return sprintf(buf, "%u\n", policy->object);	\
}

show_one(cpuinfo_min_freq, cpuinfo.min_freq);
show_one(cpuinfo_max_freq, cpuinfo.max_freq);
show_one(cpuinfo_transition_latency, cpuinfo.transition_latency);
show_one(scaling_min_freq, min);
show_one(scaling_max_freq, max);
show_one(scaling_cur_freq, cur);

static int cpufreq_set_policy(struct cpufreq_policy *policy,
				struct cpufreq_policy *new_policy);

/**
 * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access
 */
#define store_one(file_name, object)			\
static ssize_t store_##file_name					\
(struct cpufreq_policy *policy, const char *buf, size_t count)		\
{									\
	int ret;							\
	struct cpufreq_policy new_policy;				\
									\
	ret = cpufreq_get_policy(&new_policy, policy->cpu);		\
	if (ret)							\
		return -EINVAL;						\
									\
	ret = sscanf(buf, "%u", &new_policy.object);			\
	if (ret != 1)							\
		return -EINVAL;						\
									\
	ret = cpufreq_set_policy(policy, &new_policy);		\
	policy->user_policy.object = policy->object;			\
									\
	return ret ? ret : count;					\
}

store_one(scaling_min_freq, min);
store_one(scaling_max_freq, max);

/**
 * show_cpuinfo_cur_freq - current CPU frequency as detected by hardware
 */
static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
					char *buf)
{
	unsigned int cur_freq = __cpufreq_get(policy->cpu);
	if (!cur_freq)
		return sprintf(buf, "<unknown>");
	return sprintf(buf, "%u\n", cur_freq);
}

/**
 * show_scaling_governor - show the current policy for the specified CPU
 */
static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
{
	if (policy->policy == CPUFREQ_POLICY_POWERSAVE)
		return sprintf(buf, "powersave\n");
	else if (policy->policy == CPUFREQ_POLICY_PERFORMANCE)
		return sprintf(buf, "performance\n");
	else if (policy->governor)
		return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n",
				policy->governor->name);
	return -EINVAL;
}

/**
 * store_scaling_governor - store policy for the specified CPU
 */
static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
					const char *buf, size_t count)
{
	int ret;
	char	str_governor[16];
	struct cpufreq_policy new_policy;

	ret = cpufreq_get_policy(&new_policy, policy->cpu);
	if (ret)
		return ret;

	ret = sscanf(buf, "%15s", str_governor);
	if (ret != 1)
		return -EINVAL;

	if (cpufreq_parse_governor(str_governor, &new_policy.policy,
						&new_policy.governor))
		return -EINVAL;

	ret = cpufreq_set_policy(policy, &new_policy);

	policy->user_policy.policy = policy->policy;
	policy->user_policy.governor = policy->governor;

	if (ret)
		return ret;
	else
		return count;
}

/**
 * show_scaling_driver - show the cpufreq driver currently loaded
 */
static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf)
{
	return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", cpufreq_driver->name);
}

/**
 * show_scaling_available_governors - show the available CPUfreq governors
 */
static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
						char *buf)
{
	ssize_t i = 0;
	struct cpufreq_governor *t;

	if (!cpufreq_driver->target) {
		i += sprintf(buf, "performance powersave");
		goto out;
	}

	list_for_each_entry(t, &cpufreq_governor_list, governor_list) {
		if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char))
		    - (CPUFREQ_NAME_LEN + 2)))
			goto out;
		i += scnprintf(&buf[i], CPUFREQ_NAME_PLEN, "%s ", t->name);
	}
out:
	i += sprintf(&buf[i], "\n");
	return i;
}

ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf)
{
	ssize_t i = 0;
	unsigned int cpu;

	for_each_cpu(cpu, mask) {
		if (i)
			i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), " ");
		i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), "%u", cpu);
		if (i >= (PAGE_SIZE - 5))
			break;
	}
	i += sprintf(&buf[i], "\n");
	return i;
}
EXPORT_SYMBOL_GPL(cpufreq_show_cpus);

/**
 * show_related_cpus - show the CPUs affected by each transition even if
 * hw coordination is in use
 */
static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf)
{
	return cpufreq_show_cpus(policy->related_cpus, buf);
}

/**
 * show_affected_cpus - show the CPUs affected by each transition
 */
static ssize_t show_affected_cpus(struct cpufreq_policy *policy, char *buf)
{
	return cpufreq_show_cpus(policy->cpus, buf);
}

static ssize_t store_scaling_setspeed(struct cpufreq_policy *policy,
					const char *buf, size_t count)
{
	unsigned int freq = 0;
	unsigned int ret;

	if (!policy->governor || !policy->governor->store_setspeed)
		return -EINVAL;

	ret = sscanf(buf, "%u", &freq);
	if (ret != 1)
		return -EINVAL;

	policy->governor->store_setspeed(policy, freq);

	return count;
}

static ssize_t show_scaling_setspeed(struct cpufreq_policy *policy, char *buf)
{
	if (!policy->governor || !policy->governor->show_setspeed)
		return sprintf(buf, "<unsupported>\n");

	return policy->governor->show_setspeed(policy, buf);
}

/**
 * show_bios_limit - show the current cpufreq HW/BIOS limitation
 */
static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
{
	unsigned int limit;
	int ret;
	if (cpufreq_driver->bios_limit) {
		ret = cpufreq_driver->bios_limit(policy->cpu, &limit);
		if (!ret)
			return sprintf(buf, "%u\n", limit);
	}
	return sprintf(buf, "%u\n", policy->cpuinfo.max_freq);
}

cpufreq_freq_attr_ro_perm(cpuinfo_cur_freq, 0400);
cpufreq_freq_attr_ro(cpuinfo_min_freq);
cpufreq_freq_attr_ro(cpuinfo_max_freq);
cpufreq_freq_attr_ro(cpuinfo_transition_latency);
cpufreq_freq_attr_ro(scaling_available_governors);
cpufreq_freq_attr_ro(scaling_driver);
cpufreq_freq_attr_ro(scaling_cur_freq);
cpufreq_freq_attr_ro(bios_limit);
cpufreq_freq_attr_ro(related_cpus);
cpufreq_freq_attr_ro(affected_cpus);
cpufreq_freq_attr_rw(scaling_min_freq);
cpufreq_freq_attr_rw(scaling_max_freq);
cpufreq_freq_attr_rw(scaling_governor);
cpufreq_freq_attr_rw(scaling_setspeed);

static struct attribute *default_attrs[] = {
	&cpuinfo_min_freq.attr,
	&cpuinfo_max_freq.attr,
	&cpuinfo_transition_latency.attr,
	&scaling_min_freq.attr,
	&scaling_max_freq.attr,
	&affected_cpus.attr,
	&related_cpus.attr,
	&scaling_governor.attr,
	&scaling_driver.attr,
	&scaling_available_governors.attr,
	&scaling_setspeed.attr,
	NULL
};

#define to_policy(k) container_of(k, struct cpufreq_policy, kobj)
#define to_attr(a) container_of(a, struct freq_attr, attr)

static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
{
	struct cpufreq_policy *policy = to_policy(kobj);
	struct freq_attr *fattr = to_attr(attr);
	ssize_t ret;

	if (!down_read_trylock(&cpufreq_rwsem))
		return -EINVAL;

	lock_policy_rwsem_read(policy->cpu);

	if (fattr->show)
		ret = fattr->show(policy, buf);
	else
		ret = -EIO;

	unlock_policy_rwsem_read(policy->cpu);
	up_read(&cpufreq_rwsem);

	return ret;
}

static ssize_t store(struct kobject *kobj, struct attribute *attr,
		     const char *buf, size_t count)
{
	struct cpufreq_policy *policy = to_policy(kobj);
	struct freq_attr *fattr = to_attr(attr);
	ssize_t ret = -EINVAL;

	get_online_cpus();

	if (!cpu_online(policy->cpu))
		goto unlock;

	if (!down_read_trylock(&cpufreq_rwsem))
		goto unlock;

	lock_policy_rwsem_write(policy->cpu);

	if (fattr->store)
		ret = fattr->store(policy, buf, count);
	else
		ret = -EIO;

	unlock_policy_rwsem_write(policy->cpu);

	up_read(&cpufreq_rwsem);
unlock:
	put_online_cpus();

	return ret;
}

static void cpufreq_sysfs_release(struct kobject *kobj)
{
	struct cpufreq_policy *policy = to_policy(kobj);
	pr_debug("last reference is dropped\n");
	complete(&policy->kobj_unregister);
}

static const struct sysfs_ops sysfs_ops = {
	.show	= show,
	.store	= store,
};

static struct kobj_type ktype_cpufreq = {
	.sysfs_ops	= &sysfs_ops,
	.default_attrs	= default_attrs,
	.release	= cpufreq_sysfs_release,
};

struct kobject *cpufreq_global_kobject;
EXPORT_SYMBOL(cpufreq_global_kobject);

static int cpufreq_global_kobject_usage;

int cpufreq_get_global_kobject(void)
{
	if (!cpufreq_global_kobject_usage++)
		return kobject_add(cpufreq_global_kobject,
				&cpu_subsys.dev_root->kobj, "%s", "cpufreq");

	return 0;
}
EXPORT_SYMBOL(cpufreq_get_global_kobject);

void cpufreq_put_global_kobject(void)
{
	if (!--cpufreq_global_kobject_usage)
		kobject_del(cpufreq_global_kobject);
}
EXPORT_SYMBOL(cpufreq_put_global_kobject);

int cpufreq_sysfs_create_file(const struct attribute *attr)
{
	int ret = cpufreq_get_global_kobject();

	if (!ret) {
		ret = sysfs_create_file(cpufreq_global_kobject, attr);
		if (ret)
			cpufreq_put_global_kobject();
	}

	return ret;
}
EXPORT_SYMBOL(cpufreq_sysfs_create_file);

void cpufreq_sysfs_remove_file(const struct attribute *attr)
{
	sysfs_remove_file(cpufreq_global_kobject, attr);
	cpufreq_put_global_kobject();
}
EXPORT_SYMBOL(cpufreq_sysfs_remove_file);

/* symlink affected CPUs */
static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy)
{
	unsigned int j;
	int ret = 0;

	for_each_cpu(j, policy->cpus) {
		struct device *cpu_dev;

		if (j == policy->cpu)
			continue;

		pr_debug("Adding link for CPU: %u\n", j);
		cpu_dev = get_cpu_device(j);
		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
					"cpufreq");
		if (ret)
			break;
	}
	return ret;
}

static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
				     struct device *dev)
{
	struct freq_attr **drv_attr;
	int ret = 0;

	/* prepare interface data */
	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
				   &dev->kobj, "cpufreq");
	if (ret)
		return ret;

	/* set up files for this cpu device */
	drv_attr = cpufreq_driver->attr;
	while ((drv_attr) && (*drv_attr)) {
		ret = sysfs_create_file(&policy->kobj, &((*drv_attr)->attr));
		if (ret)
			goto err_out_kobj_put;
		drv_attr++;
	}
	if (cpufreq_driver->get) {
		ret = sysfs_create_file(&policy->kobj, &cpuinfo_cur_freq.attr);
		if (ret)
			goto err_out_kobj_put;
	}
	if (cpufreq_driver->target) {
		ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
		if (ret)
			goto err_out_kobj_put;
	}
	if (cpufreq_driver->bios_limit) {
		ret = sysfs_create_file(&policy->kobj, &bios_limit.attr);
		if (ret)
			goto err_out_kobj_put;
	}

	ret = cpufreq_add_dev_symlink(policy);
	if (ret)
		goto err_out_kobj_put;

	return ret;

err_out_kobj_put:
	kobject_put(&policy->kobj);
	wait_for_completion(&policy->kobj_unregister);
	return ret;
}

static void cpufreq_init_policy(struct cpufreq_policy *policy)
{
	struct cpufreq_policy new_policy;
	int ret = 0;

	memcpy(&new_policy, policy, sizeof(*policy));
	/* assure that the starting sequence is run in cpufreq_set_policy */
	policy->governor = NULL;

	/* set default policy */
	ret = cpufreq_set_policy(policy, &new_policy);
	policy->user_policy.policy = policy->policy;
	policy->user_policy.governor = policy->governor;

	if (ret) {
		pr_debug("setting policy failed\n");
		if (cpufreq_driver->exit)
			cpufreq_driver->exit(policy);
	}
}

#ifdef CONFIG_HOTPLUG_CPU
static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
				  unsigned int cpu, struct device *dev,
				  bool frozen)
{
	int ret = 0, has_target = !!cpufreq_driver->target;
	unsigned long flags;

	if (has_target) {
		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
		if (ret) {
			pr_err("%s: Failed to stop governor\n", __func__);
			return ret;
		}
	}

	lock_policy_rwsem_write(policy->cpu);

	write_lock_irqsave(&cpufreq_driver_lock, flags);

	cpumask_set_cpu(cpu, policy->cpus);
	per_cpu(cpufreq_cpu_data, cpu) = policy;
	write_unlock_irqrestore(&cpufreq_driver_lock, flags);

	unlock_policy_rwsem_write(policy->cpu);

	if (has_target) {
		if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) ||
			(ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) {
			pr_err("%s: Failed to start governor\n", __func__);
			return ret;
		}
	}

	/* Don't touch sysfs links during light-weight init */
	if (!frozen)
		ret = sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");

	return ret;
}
#endif

static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
{
	struct cpufreq_policy *policy;
	unsigned long flags;

	read_lock_irqsave(&cpufreq_driver_lock, flags);

	policy = per_cpu(cpufreq_cpu_data_fallback, cpu);

	read_unlock_irqrestore(&cpufreq_driver_lock, flags);

	return policy;
}

static struct cpufreq_policy *cpufreq_policy_alloc(void)
{
	struct cpufreq_policy *policy;

	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
	if (!policy)
		return NULL;

	if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL))
		goto err_free_policy;

	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
		goto err_free_cpumask;

	INIT_LIST_HEAD(&policy->policy_list);
	return policy;

err_free_cpumask:
	free_cpumask_var(policy->cpus);
err_free_policy:
	kfree(policy);

	return NULL;
}

static void cpufreq_policy_free(struct cpufreq_policy *policy)
{
	free_cpumask_var(policy->related_cpus);
	free_cpumask_var(policy->cpus);
	kfree(policy);
}

static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
{
	if (cpu == policy->cpu)
		return;

	/*
	 * Take direct locks as lock_policy_rwsem_write wouldn't work here.
	 * Also lock for last cpu is enough here as contention will happen only
	 * after policy->cpu is changed and after it is changed, other threads
	 * will try to acquire lock for new cpu. And policy is already updated
	 * by then.
	 */
	down_write(&per_cpu(cpu_policy_rwsem, policy->cpu));

	policy->last_cpu = policy->cpu;
	policy->cpu = cpu;

	up_write(&per_cpu(cpu_policy_rwsem, policy->last_cpu));

#ifdef CONFIG_CPU_FREQ_TABLE
	cpufreq_frequency_table_update_policy_cpu(policy);
#endif
	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
			CPUFREQ_UPDATE_POLICY_CPU, policy);
}

static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
			     bool frozen)
{
	unsigned int j, cpu = dev->id;
	int ret = -ENOMEM;
	struct cpufreq_policy *policy;
	unsigned long flags;
#ifdef CONFIG_HOTPLUG_CPU
	struct cpufreq_policy *tpolicy;
	struct cpufreq_governor *gov;
#endif

	if (cpu_is_offline(cpu))
		return 0;

	pr_debug("adding CPU %u\n", cpu);

#ifdef CONFIG_SMP
	/* check whether a different CPU already registered this
	 * CPU because it is in the same boat. */
	policy = cpufreq_cpu_get(cpu);
	if (unlikely(policy)) {
		cpufreq_cpu_put(policy);
		return 0;
	}
#endif

	if (!down_read_trylock(&cpufreq_rwsem))
		return 0;

#ifdef CONFIG_HOTPLUG_CPU
	/* Check if this cpu was hot-unplugged earlier and has siblings */
	read_lock_irqsave(&cpufreq_driver_lock, flags);
	list_for_each_entry(tpolicy, &cpufreq_policy_list, policy_list) {
		if (cpumask_test_cpu(cpu, tpolicy->related_cpus)) {
			read_unlock_irqrestore(&cpufreq_driver_lock, flags);
			ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev, frozen);
			up_read(&cpufreq_rwsem);
			return ret;
		}
	}
	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
#endif

	if (frozen)
		/* Restore the saved policy when doing light-weight init */
		policy = cpufreq_policy_restore(cpu);
	else
		policy = cpufreq_policy_alloc();

	if (!policy)
		goto nomem_out;


	/*
	 * In the resume path, since we restore a saved policy, the assignment
	 * to policy->cpu is like an update of the existing policy, rather than
	 * the creation of a brand new one. So we need to perform this update
	 * by invoking update_policy_cpu().
	 */
	if (frozen && cpu != policy->cpu)
		update_policy_cpu(policy, cpu);
	else
		policy->cpu = cpu;

	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
	cpumask_copy(policy->cpus, cpumask_of(cpu));

	init_completion(&policy->kobj_unregister);
	INIT_WORK(&policy->update, handle_update);

	/* call driver. From then on the cpufreq must be able
	 * to accept all calls to ->verify and ->setpolicy for this CPU
	 */
	ret = cpufreq_driver->init(policy);
	if (ret) {
		pr_debug("initialization failed\n");
		goto err_set_policy_cpu;
	}

	if (cpufreq_driver->get) {
		policy->cur = cpufreq_driver->get(policy->cpu);
		if (!policy->cur) {
			pr_err("%s: ->get() failed\n", __func__);
			goto err_get_freq;
		}
	}

	/* related cpus should atleast have policy->cpus */
	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);

	/*
	 * affected cpus must always be the one, which are online. We aren't
	 * managing offline cpus here.
	 */
	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);

	policy->user_policy.min = policy->min;
	policy->user_policy.max = policy->max;

	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
				     CPUFREQ_START, policy);

#ifdef CONFIG_HOTPLUG_CPU
	gov = __find_governor(per_cpu(cpufreq_cpu_governor, cpu));
	if (gov) {
		policy->governor = gov;
		pr_debug("Restoring governor %s for cpu %d\n",
		       policy->governor->name, cpu);
	}
#endif

	write_lock_irqsave(&cpufreq_driver_lock, flags);
	for_each_cpu(j, policy->cpus)
		per_cpu(cpufreq_cpu_data, j) = policy;
	write_unlock_irqrestore(&cpufreq_driver_lock, flags);

	if (!frozen) {
		ret = cpufreq_add_dev_interface(policy, dev);
		if (ret)
			goto err_out_unregister;
	}

	write_lock_irqsave(&cpufreq_driver_lock, flags);
	list_add(&policy->policy_list, &cpufreq_policy_list);
	write_unlock_irqrestore(&cpufreq_driver_lock, flags);

	cpufreq_init_policy(policy);

	kobject_uevent(&policy->kobj, KOBJ_ADD);
	up_read(&cpufreq_rwsem);

	pr_debug("initialization complete\n");

	return 0;

err_out_unregister:
	write_lock_irqsave(&cpufreq_driver_lock, flags);
	for_each_cpu(j, policy->cpus)
		per_cpu(cpufreq_cpu_data, j) = NULL;
	write_unlock_irqrestore(&cpufreq_driver_lock, flags);

err_get_freq:
	if (cpufreq_driver->exit)
		cpufreq_driver->exit(policy);
err_set_policy_cpu:
	cpufreq_policy_free(policy);
nomem_out:
	up_read(&cpufreq_rwsem);

	return ret;
}

/**
 * cpufreq_add_dev - add a CPU device
 *
 * Adds the cpufreq interface for a CPU device.
 *
 * The Oracle says: try running cpufreq registration/unregistration concurrently
 * with with cpu hotplugging and all hell will break loose. Tried to clean this
 * mess up, but more thorough testing is needed. - Mathieu
 */
static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
{
	return __cpufreq_add_dev(dev, sif, false);
}

static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,
					   unsigned int old_cpu, bool frozen)
{
	struct device *cpu_dev;
	int ret;

	/* first sibling now owns the new sysfs dir */
	cpu_dev = get_cpu_device(cpumask_any_but(policy->cpus, old_cpu));

	/* Don't touch sysfs files during light-weight tear-down */
	if (frozen)
		return cpu_dev->id;

	sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
	ret = kobject_move(&policy->kobj, &cpu_dev->kobj);
	if (ret) {
		pr_err("%s: Failed to move kobj: %d", __func__, ret);

		lock_policy_rwsem_write(old_cpu);
		cpumask_set_cpu(old_cpu, policy->cpus);
		unlock_policy_rwsem_write(old_cpu);

		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
					"cpufreq");

		return -EINVAL;
	}

	return cpu_dev->id;
}

static int __cpufreq_remove_dev_prepare(struct device *dev,
					struct subsys_interface *sif,
					bool frozen)
{
	unsigned int cpu = dev->id, cpus;
	int new_cpu, ret;
	unsigned long flags;
	struct cpufreq_policy *policy;

	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);

	write_lock_irqsave(&cpufreq_driver_lock, flags);

	policy = per_cpu(cpufreq_cpu_data, cpu);

	/* Save the policy somewhere when doing a light-weight tear-down */
	if (frozen)
		per_cpu(cpufreq_cpu_data_fallback, cpu) = policy;

	write_unlock_irqrestore(&cpufreq_driver_lock, flags);

	if (!policy) {
		pr_debug("%s: No cpu_data found\n", __func__);
		return -EINVAL;
	}

	if (cpufreq_driver->target) {
		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
		if (ret) {
			pr_err("%s: Failed to stop governor\n", __func__);
			return ret;
		}
	}

#ifdef CONFIG_HOTPLUG_CPU
	if (!cpufreq_driver->setpolicy)
		strncpy(per_cpu(cpufreq_cpu_governor, cpu),
			policy->governor->name, CPUFREQ_NAME_LEN);
#endif

	lock_policy_rwsem_read(cpu);
	cpus = cpumask_weight(policy->cpus);
	unlock_policy_rwsem_read(cpu);

	if (cpu != policy->cpu) {
		if (!frozen)
			sysfs_remove_link(&dev->kobj, "cpufreq");
	} else if (cpus > 1) {
		new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu, frozen);
		if (new_cpu >= 0) {
			update_policy_cpu(policy, new_cpu);

			if (!frozen) {
				pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
						__func__, new_cpu, cpu);
			}
		}
	}

	return 0;
}

static int __cpufreq_remove_dev_finish(struct device *dev,
				       struct subsys_interface *sif,
				       bool frozen)
{
	unsigned int cpu = dev->id, cpus;
	int ret;
	unsigned long flags;
	struct cpufreq_policy *policy;
	struct kobject *kobj;
	struct completion *cmp;

	read_lock_irqsave(&cpufreq_driver_lock, flags);
	policy = per_cpu(cpufreq_cpu_data, cpu);
	read_unlock_irqrestore(&cpufreq_driver_lock, flags);

	if (!policy) {
		pr_debug("%s: No cpu_data found\n", __func__);
		return -EINVAL;
	}

	lock_policy_rwsem_write(cpu);
	cpus = cpumask_weight(policy->cpus);

	if (cpus > 1)
		cpumask_clear_cpu(cpu, policy->cpus);
	unlock_policy_rwsem_write(cpu);

	/* If cpu is last user of policy, free policy */
	if (cpus == 1) {
		if (cpufreq_driver->target) {
			ret = __cpufreq_governor(policy,
					CPUFREQ_GOV_POLICY_EXIT);
			if (ret) {
				pr_err("%s: Failed to exit governor\n",
						__func__);
				return ret;
			}
		}

		if (!frozen) {
			lock_policy_rwsem_read(cpu);
			kobj = &policy->kobj;
			cmp = &policy->kobj_unregister;
			unlock_policy_rwsem_read(cpu);
			kobject_put(kobj);

			/*
			 * We need to make sure that the underlying kobj is
			 * actually not referenced anymore by anybody before we
			 * proceed with unloading.
			 */
			pr_debug("waiting for dropping of refcount\n");
			wait_for_completion(cmp);
			pr_debug("wait complete\n");
		}

		/*
		 * Perform the ->exit() even during light-weight tear-down,
		 * since this is a core component, and is essential for the
		 * subsequent light-weight ->init() to succeed.
		 */
		if (cpufreq_driver->exit)
			cpufreq_driver->exit(policy);

		/* Remove policy from list of active policies */
		write_lock_irqsave(&cpufreq_driver_lock, flags);
		list_del(&policy->policy_list);
		write_unlock_irqrestore(&cpufreq_driver_lock, flags);

		if (!frozen)
			cpufreq_policy_free(policy);
	} else {
		if (cpufreq_driver->target) {
			if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) ||
					(ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) {
				pr_err("%s: Failed to start governor\n",
						__func__);
				return ret;
			}
		}
	}

	per_cpu(cpufreq_cpu_data, cpu) = NULL;
	return 0;
}

/**
 * cpufreq_remove_dev - remove a CPU device
 *
 * Removes the cpufreq interface for a CPU device.
 */
static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
{
	unsigned int cpu = dev->id;
	int ret;

	if (cpu_is_offline(cpu))
		return 0;

	ret = __cpufreq_remove_dev_prepare(dev, sif, false);

	if (!ret)
		ret = __cpufreq_remove_dev_finish(dev, sif, false);

	return ret;
}

static void handle_update(struct work_struct *work)
{
	struct cpufreq_policy *policy =
		container_of(work, struct cpufreq_policy, update);
	unsigned int cpu = policy->cpu;
	pr_debug("handle_update for cpu %u called\n", cpu);
	cpufreq_update_policy(cpu);
}

/**
 *	cpufreq_out_of_sync - If actual and saved CPU frequency differs, we're
 *	in deep trouble.
 *	@cpu: cpu number
 *	@old_freq: CPU frequency the kernel thinks the CPU runs at
 *	@new_freq: CPU frequency the CPU actually runs at
 *
 *	We adjust to current frequency first, and need to clean up later.
 *	So either call to cpufreq_update_policy() or schedule handle_update()).
 */
static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq,
				unsigned int new_freq)
{
	struct cpufreq_policy *policy;
	struct cpufreq_freqs freqs;
	unsigned long flags;

	pr_debug("Warning: CPU frequency out of sync: cpufreq and timing "
	       "core thinks of %u, is %u kHz.\n", old_freq, new_freq);

	freqs.old = old_freq;
	freqs.new = new_freq;

	read_lock_irqsave(&cpufreq_driver_lock, flags);
	policy = per_cpu(cpufreq_cpu_data, cpu);
	read_unlock_irqrestore(&cpufreq_driver_lock, flags);

	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
}

/**
 * cpufreq_quick_get - get the CPU frequency (in kHz) from policy->cur
 * @cpu: CPU number
 *
 * This is the last known freq, without actually getting it from the driver.
 * Return value will be same as what is shown in scaling_cur_freq in sysfs.
 */
unsigned int cpufreq_quick_get(unsigned int cpu)
{
	struct cpufreq_policy *policy;
	unsigned int ret_freq = 0;

	if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get)
		return cpufreq_driver->get(cpu);

	policy = cpufreq_cpu_get(cpu);
	if (policy) {
		ret_freq = policy->cur;
		cpufreq_cpu_put(policy);
	}

	return ret_freq;
}
EXPORT_SYMBOL(cpufreq_quick_get);

/**
 * cpufreq_quick_get_max - get the max reported CPU frequency for this CPU
 * @cpu: CPU number
 *
 * Just return the max possible frequency for a given CPU.
 */
unsigned int cpufreq_quick_get_max(unsigned int cpu)
{
	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
	unsigned int ret_freq = 0;

	if (policy) {
		ret_freq = policy->max;
		cpufreq_cpu_put(policy);
	}

	return ret_freq;
}
EXPORT_SYMBOL(cpufreq_quick_get_max);

static unsigned int __cpufreq_get(unsigned int cpu)
{
	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
	unsigned int ret_freq = 0;

	if (!cpufreq_driver->get)
		return ret_freq;

	ret_freq = cpufreq_driver->get(cpu);

	if (ret_freq && policy->cur &&
		!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
		/* verify no discrepancy between actual and
					saved value exists */
		if (unlikely(ret_freq != policy->cur)) {
			cpufreq_out_of_sync(cpu, policy->cur, ret_freq);
			schedule_work(&policy->update);
		}
	}

	return ret_freq;
}

/**
 * cpufreq_get - get the current CPU frequency (in kHz)
 * @cpu: CPU number
 *
 * Get the CPU current (static) CPU frequency
 */
unsigned int cpufreq_get(unsigned int cpu)
{
	unsigned int ret_freq = 0;

	if (cpufreq_disabled() || !cpufreq_driver)
		return -ENOENT;

	if (!down_read_trylock(&cpufreq_rwsem))
		return 0;

	lock_policy_rwsem_read(cpu);

	ret_freq = __cpufreq_get(cpu);

	unlock_policy_rwsem_read(cpu);
	up_read(&cpufreq_rwsem);

	return ret_freq;
}
EXPORT_SYMBOL(cpufreq_get);

static struct subsys_interface cpufreq_interface = {
	.name		= "cpufreq",
	.subsys		= &cpu_subsys,
	.add_dev	= cpufreq_add_dev,
	.remove_dev	= cpufreq_remove_dev,
};

/**
 * cpufreq_bp_suspend - Prepare the boot CPU for system suspend.
 *
 * This function is only executed for the boot processor.  The other CPUs
 * have been put offline by means of CPU hotplug.
 */
static int cpufreq_bp_suspend(void)
{
	int ret = 0;

	int cpu = smp_processor_id();
	struct cpufreq_policy *policy;

	pr_debug("suspending cpu %u\n", cpu);

	/* If there's no policy for the boot CPU, we have nothing to do. */
	policy = cpufreq_cpu_get(cpu);
	if (!policy)
		return 0;

	if (cpufreq_driver->suspend) {
		ret = cpufreq_driver->suspend(policy);
		if (ret)
			printk(KERN_ERR "cpufreq: suspend failed in ->suspend "
					"step on CPU %u\n", policy->cpu);
	}

	cpufreq_cpu_put(policy);
	return ret;
}

/**
 * cpufreq_bp_resume - Restore proper frequency handling of the boot CPU.
 *
 *	1.) resume CPUfreq hardware support (cpufreq_driver->resume())
 *	2.) schedule call cpufreq_update_policy() ASAP as interrupts are
 *	    restored. It will verify that the current freq is in sync with
 *	    what we believe it to be. This is a bit later than when it
 *	    should be, but nonethteless it's better than calling
 *	    cpufreq_driver->get() here which might re-enable interrupts...
 *
 * This function is only executed for the boot CPU.  The other CPUs have not
 * been turned on yet.
 */
static void cpufreq_bp_resume(void)
{
	int ret = 0;

	int cpu = smp_processor_id();
	struct cpufreq_policy *policy;

	pr_debug("resuming cpu %u\n", cpu);

	/* If there's no policy for the boot CPU, we have nothing to do. */
	policy = cpufreq_cpu_get(cpu);
	if (!policy)
		return;

	if (cpufreq_driver->resume) {
		ret = cpufreq_driver->resume(policy);
		if (ret) {
			printk(KERN_ERR "cpufreq: resume failed in ->resume "
					"step on CPU %u\n", policy->cpu);
			goto fail;
		}
	}

	schedule_work(&policy->update);

fail:
	cpufreq_cpu_put(policy);
}

static struct syscore_ops cpufreq_syscore_ops = {
	.suspend	= cpufreq_bp_suspend,
	.resume		= cpufreq_bp_resume,
};

/**
 *	cpufreq_get_current_driver - return current driver's name
 *
 *	Return the name string of the currently loaded cpufreq driver
 *	or NULL, if none.
 */
const char *cpufreq_get_current_driver(void)
{
	if (cpufreq_driver)
		return cpufreq_driver->name;

	return NULL;
}
EXPORT_SYMBOL_GPL(cpufreq_get_current_driver);

/*********************************************************************
 *                     NOTIFIER LISTS INTERFACE                      *
 *********************************************************************/

/**
 *	cpufreq_register_notifier - register a driver with cpufreq
 *	@nb: notifier function to register
 *      @list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER
 *
 *	Add a driver to one of two lists: either a list of drivers that
 *      are notified about clock rate changes (once before and once after
 *      the transition), or a list of drivers that are notified about
 *      changes in cpufreq policy.
 *
 *	This function may sleep, and has the same return conditions as
 *	blocking_notifier_chain_register.
 */
int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
{
	int ret;

	if (cpufreq_disabled())
		return -EINVAL;

	WARN_ON(!init_cpufreq_transition_notifier_list_called);

	switch (list) {
	case CPUFREQ_TRANSITION_NOTIFIER:
		ret = srcu_notifier_chain_register(
				&cpufreq_transition_notifier_list, nb);
		break;
	case CPUFREQ_POLICY_NOTIFIER:
		ret = blocking_notifier_chain_register(
				&cpufreq_policy_notifier_list, nb);
		break;
	default:
		ret = -EINVAL;
	}

	return ret;
}
EXPORT_SYMBOL(cpufreq_register_notifier);

/**
 *	cpufreq_unregister_notifier - unregister a driver with cpufreq
 *	@nb: notifier block to be unregistered
 *	@list: CPUFREQ_TRANSITION_NOTIFIER or CPUFREQ_POLICY_NOTIFIER
 *
 *	Remove a driver from the CPU frequency notifier list.
 *
 *	This function may sleep, and has the same return conditions as
 *	blocking_notifier_chain_unregister.
 */
int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list)
{
	int ret;

	if (cpufreq_disabled())
		return -EINVAL;

	switch (list) {
	case CPUFREQ_TRANSITION_NOTIFIER:
		ret = srcu_notifier_chain_unregister(
				&cpufreq_transition_notifier_list, nb);
		break;
	case CPUFREQ_POLICY_NOTIFIER:
		ret = blocking_notifier_chain_unregister(
				&cpufreq_policy_notifier_list, nb);
		break;
	default:
		ret = -EINVAL;
	}

	return ret;
}
EXPORT_SYMBOL(cpufreq_unregister_notifier);


/*********************************************************************
 *                              GOVERNORS                            *
 *********************************************************************/

int __cpufreq_driver_target(struct cpufreq_policy *policy,
			    unsigned int target_freq,
			    unsigned int relation)
{
	int retval = -EINVAL;
	unsigned int old_target_freq = target_freq;

	if (cpufreq_disabled())
		return -ENODEV;

	/* Make sure that target_freq is within supported range */
	if (target_freq > policy->max)
		target_freq = policy->max;
	if (target_freq < policy->min)
		target_freq = policy->min;

	pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
			policy->cpu, target_freq, relation, old_target_freq);

	if (target_freq == policy->cur)
		return 0;

	if (cpufreq_driver->target)
		retval = cpufreq_driver->target(policy, target_freq, relation);

	return retval;
}
EXPORT_SYMBOL_GPL(__cpufreq_driver_target);

int cpufreq_driver_target(struct cpufreq_policy *policy,
			  unsigned int target_freq,
			  unsigned int relation)
{
	int ret = -EINVAL;

	lock_policy_rwsem_write(policy->cpu);

	ret = __cpufreq_driver_target(policy, target_freq, relation);

	unlock_policy_rwsem_write(policy->cpu);

	return ret;
}
EXPORT_SYMBOL_GPL(cpufreq_driver_target);

/*
 * when "event" is CPUFREQ_GOV_LIMITS
 */

static int __cpufreq_governor(struct cpufreq_policy *policy,
					unsigned int event)
{
	int ret;

	/* Only must be defined when default governor is known to have latency
	   restrictions, like e.g. conservative or ondemand.
	   That this is the case is already ensured in Kconfig
	*/
#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE
	struct cpufreq_governor *gov = &cpufreq_gov_performance;
#else
	struct cpufreq_governor *gov = NULL;
#endif

	if (policy->governor->max_transition_latency &&
	    policy->cpuinfo.transition_latency >
	    policy->governor->max_transition_latency) {
		if (!gov)
			return -EINVAL;
		else {
			printk(KERN_WARNING "%s governor failed, too long"
			       " transition latency of HW, fallback"
			       " to %s governor\n",
			       policy->governor->name,
			       gov->name);
			policy->governor = gov;
		}
	}

	if (event == CPUFREQ_GOV_POLICY_INIT)
		if (!try_module_get(policy->governor->owner))
			return -EINVAL;

	pr_debug("__cpufreq_governor for CPU %u, event %u\n",
						policy->cpu, event);

	mutex_lock(&cpufreq_governor_lock);
	if ((policy->governor_enabled && event == CPUFREQ_GOV_START)
	    || (!policy->governor_enabled
	    && (event == CPUFREQ_GOV_LIMITS || event == CPUFREQ_GOV_STOP))) {
		mutex_unlock(&cpufreq_governor_lock);
		return -EBUSY;
	}

	if (event == CPUFREQ_GOV_STOP)
		policy->governor_enabled = false;
	else if (event == CPUFREQ_GOV_START)
		policy->governor_enabled = true;

	mutex_unlock(&cpufreq_governor_lock);

	ret = policy->governor->governor(policy, event);

	if (!ret) {
		if (event == CPUFREQ_GOV_POLICY_INIT)
			policy->governor->initialized++;
		else if (event == CPUFREQ_GOV_POLICY_EXIT)
			policy->governor->initialized--;
	} else {
		/* Restore original values */
		mutex_lock(&cpufreq_governor_lock);
		if (event == CPUFREQ_GOV_STOP)
			policy->governor_enabled = true;
		else if (event == CPUFREQ_GOV_START)
			policy->governor_enabled = false;
		mutex_unlock(&cpufreq_governor_lock);
	}

	if (((event == CPUFREQ_GOV_POLICY_INIT) && ret) ||
			((event == CPUFREQ_GOV_POLICY_EXIT) && !ret))
		module_put(policy->governor->owner);

	return ret;
}

int cpufreq_register_governor(struct cpufreq_governor *governor)
{
	int err;

	if (!governor)
		return -EINVAL;

	if (cpufreq_disabled())
		return -ENODEV;

	mutex_lock(&cpufreq_governor_mutex);

	governor->initialized = 0;
	err = -EBUSY;
	if (__find_governor(governor->name) == NULL) {
		err = 0;
		list_add(&governor->governor_list, &cpufreq_governor_list);
	}

	mutex_unlock(&cpufreq_governor_mutex);
	return err;
}
EXPORT_SYMBOL_GPL(cpufreq_register_governor);

void cpufreq_unregister_governor(struct cpufreq_governor *governor)
{
#ifdef CONFIG_HOTPLUG_CPU
	int cpu;
#endif

	if (!governor)
		return;

	if (cpufreq_disabled())
		return;

#ifdef CONFIG_HOTPLUG_CPU
	for_each_present_cpu(cpu) {
		if (cpu_online(cpu))
			continue;
		if (!strcmp(per_cpu(cpufreq_cpu_governor, cpu), governor->name))
			strcpy(per_cpu(cpufreq_cpu_governor, cpu), "\0");
	}
#endif

	mutex_lock(&cpufreq_governor_mutex);
	list_del(&governor->governor_list);
	mutex_unlock(&cpufreq_governor_mutex);
	return;
}
EXPORT_SYMBOL_GPL(cpufreq_unregister_governor);


/*********************************************************************
 *                          POLICY INTERFACE                         *
 *********************************************************************/

/**
 * cpufreq_get_policy - get the current cpufreq_policy
 * @policy: struct cpufreq_policy into which the current cpufreq_policy
 *	is written
 *
 * Reads the current cpufreq policy.
 */
int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu)
{
	struct cpufreq_policy *cpu_policy;
	if (!policy)
		return -EINVAL;

	cpu_policy = cpufreq_cpu_get(cpu);
	if (!cpu_policy)
		return -EINVAL;

	memcpy(policy, cpu_policy, sizeof(*policy));

	cpufreq_cpu_put(cpu_policy);
	return 0;
}
EXPORT_SYMBOL(cpufreq_get_policy);

/*
 * policy : current policy.
 * new_policy: policy to be set.
 */
static int cpufreq_set_policy(struct cpufreq_policy *policy,
				struct cpufreq_policy *new_policy)
{
	int ret = 0, failed = 1;

	pr_debug("setting new policy for CPU %u: %u - %u kHz\n", new_policy->cpu,
		new_policy->min, new_policy->max);

	memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo));

	if (new_policy->min > policy->max || new_policy->max < policy->min) {
		ret = -EINVAL;
		goto error_out;
	}

	/* verify the cpu speed can be set within this limit */
	ret = cpufreq_driver->verify(new_policy);
	if (ret)
		goto error_out;

	/* adjust if necessary - all reasons */
	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
			CPUFREQ_ADJUST, new_policy);

	/* adjust if necessary - hardware incompatibility*/
	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
			CPUFREQ_INCOMPATIBLE, new_policy);

	/*
	 * verify the cpu speed can be set within this limit, which might be
	 * different to the first one
	 */
	ret = cpufreq_driver->verify(new_policy);
	if (ret)
		goto error_out;

	/* notification of the new policy */
	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
			CPUFREQ_NOTIFY, new_policy);

	policy->min = new_policy->min;
	policy->max = new_policy->max;

	pr_debug("new min and max freqs are %u - %u kHz\n",
					policy->min, policy->max);

	if (cpufreq_driver->setpolicy) {
		policy->policy = new_policy->policy;
		pr_debug("setting range\n");
		ret = cpufreq_driver->setpolicy(new_policy);
	} else {
		if (new_policy->governor != policy->governor) {
			/* save old, working values */
			struct cpufreq_governor *old_gov = policy->governor;

			pr_debug("governor switch\n");

			/* end old governor */
			if (policy->governor) {
				__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
				unlock_policy_rwsem_write(new_policy->cpu);
				__cpufreq_governor(policy,
						CPUFREQ_GOV_POLICY_EXIT);
				lock_policy_rwsem_write(new_policy->cpu);
			}

			/* start new governor */
			policy->governor = new_policy->governor;
			if (!__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) {
				if (!__cpufreq_governor(policy, CPUFREQ_GOV_START)) {
					failed = 0;
				} else {
					unlock_policy_rwsem_write(new_policy->cpu);
					__cpufreq_governor(policy,
							CPUFREQ_GOV_POLICY_EXIT);
					lock_policy_rwsem_write(new_policy->cpu);
				}
			}

			if (failed) {
				/* new governor failed, so re-start old one */
				pr_debug("starting governor %s failed\n",
							policy->governor->name);
				if (old_gov) {
					policy->governor = old_gov;
					__cpufreq_governor(policy,
							CPUFREQ_GOV_POLICY_INIT);
					__cpufreq_governor(policy,
							   CPUFREQ_GOV_START);
				}
				ret = -EINVAL;
				goto error_out;
			}
			/* might be a policy change, too, so fall through */
		}
		pr_debug("governor: change or update limits\n");
		ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
	}

error_out:
	return ret;
}

/**
 *	cpufreq_update_policy - re-evaluate an existing cpufreq policy
 *	@cpu: CPU which shall be re-evaluated
 *
 *	Useful for policy notifiers which have different necessities
 *	at different times.
 */
int cpufreq_update_policy(unsigned int cpu)
{
	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
	struct cpufreq_policy new_policy;
	int ret;

	if (!policy) {
		ret = -ENODEV;
		goto no_policy;
	}

	lock_policy_rwsem_write(cpu);

	pr_debug("updating policy for CPU %u\n", cpu);
	memcpy(&new_policy, policy, sizeof(*policy));
	new_policy.min = policy->user_policy.min;
	new_policy.max = policy->user_policy.max;
	new_policy.policy = policy->user_policy.policy;
	new_policy.governor = policy->user_policy.governor;

	/*
	 * BIOS might change freq behind our back
	 * -> ask driver for current freq and notify governors about a change
	 */
	if (cpufreq_driver->get) {
		new_policy.cur = cpufreq_driver->get(cpu);
		if (!policy->cur) {
			pr_debug("Driver did not initialize current freq");
			policy->cur = new_policy.cur;
		} else {
			if (policy->cur != new_policy.cur && cpufreq_driver->target)
				cpufreq_out_of_sync(cpu, policy->cur,
								new_policy.cur);
		}
	}

	ret = cpufreq_set_policy(policy, &new_policy);

	unlock_policy_rwsem_write(cpu);

	cpufreq_cpu_put(policy);
no_policy:
	return ret;
}
EXPORT_SYMBOL(cpufreq_update_policy);

static int cpufreq_cpu_callback(struct notifier_block *nfb,
					unsigned long action, void *hcpu)
{
	unsigned int cpu = (unsigned long)hcpu;
	struct device *dev;
	bool frozen = false;

	dev = get_cpu_device(cpu);
	if (dev) {

		if (action & CPU_TASKS_FROZEN)
			frozen = true;

		switch (action & ~CPU_TASKS_FROZEN) {
		case CPU_ONLINE:
			__cpufreq_add_dev(dev, NULL, frozen);
			cpufreq_update_policy(cpu);
			break;

		case CPU_DOWN_PREPARE:
			__cpufreq_remove_dev_prepare(dev, NULL, frozen);
			break;

		case CPU_POST_DEAD:
			__cpufreq_remove_dev_finish(dev, NULL, frozen);
			break;

		case CPU_DOWN_FAILED:
			__cpufreq_add_dev(dev, NULL, frozen);
			break;
		}
	}
	return NOTIFY_OK;
}

static struct notifier_block __refdata cpufreq_cpu_notifier = {
	.notifier_call = cpufreq_cpu_callback,
};

/*********************************************************************
 *               REGISTER / UNREGISTER CPUFREQ DRIVER                *
 *********************************************************************/

/**
 * cpufreq_register_driver - register a CPU Frequency driver
 * @driver_data: A struct cpufreq_driver containing the values#
 * submitted by the CPU Frequency driver.
 *
 * Registers a CPU Frequency driver to this core code. This code
 * returns zero on success, -EBUSY when another driver got here first
 * (and isn't unregistered in the meantime).
 *
 */
int cpufreq_register_driver(struct cpufreq_driver *driver_data)
{
	unsigned long flags;
	int ret;

	if (cpufreq_disabled())
		return -ENODEV;

	if (!driver_data || !driver_data->verify || !driver_data->init ||
	    ((!driver_data->setpolicy) && (!driver_data->target)))
		return -EINVAL;

	pr_debug("trying to register driver %s\n", driver_data->name);

	if (driver_data->setpolicy)
		driver_data->flags |= CPUFREQ_CONST_LOOPS;

	write_lock_irqsave(&cpufreq_driver_lock, flags);
	if (cpufreq_driver) {
		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
		return -EEXIST;
	}
	cpufreq_driver = driver_data;
	write_unlock_irqrestore(&cpufreq_driver_lock, flags);

	ret = subsys_interface_register(&cpufreq_interface);
	if (ret)
		goto err_null_driver;

	if (!(cpufreq_driver->flags & CPUFREQ_STICKY)) {
		int i;
		ret = -ENODEV;

		/* check for at least one working CPU */
		for (i = 0; i < nr_cpu_ids; i++)
			if (cpu_possible(i) && per_cpu(cpufreq_cpu_data, i)) {
				ret = 0;
				break;
			}

		/* if all ->init() calls failed, unregister */
		if (ret) {
			pr_debug("no CPU initialized for driver %s\n",
							driver_data->name);
			goto err_if_unreg;
		}
	}

	register_hotcpu_notifier(&cpufreq_cpu_notifier);
	pr_debug("driver %s up and running\n", driver_data->name);

	return 0;
err_if_unreg:
	subsys_interface_unregister(&cpufreq_interface);
err_null_driver:
	write_lock_irqsave(&cpufreq_driver_lock, flags);
	cpufreq_driver = NULL;
	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
	return ret;
}
EXPORT_SYMBOL_GPL(cpufreq_register_driver);

/**
 * cpufreq_unregister_driver - unregister the current CPUFreq driver
 *
 * Unregister the current CPUFreq driver. Only call this if you have
 * the right to do so, i.e. if you have succeeded in initialising before!
 * Returns zero if successful, and -EINVAL if the cpufreq_driver is
 * currently not initialised.
 */
int cpufreq_unregister_driver(struct cpufreq_driver *driver)
{
	unsigned long flags;

	if (!cpufreq_driver || (driver != cpufreq_driver))
		return -EINVAL;

	pr_debug("unregistering driver %s\n", driver->name);

	subsys_interface_unregister(&cpufreq_interface);
	unregister_hotcpu_notifier(&cpufreq_cpu_notifier);

	down_write(&cpufreq_rwsem);
	write_lock_irqsave(&cpufreq_driver_lock, flags);

	cpufreq_driver = NULL;

	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
	up_write(&cpufreq_rwsem);

	return 0;
}
EXPORT_SYMBOL_GPL(cpufreq_unregister_driver);

static int __init cpufreq_core_init(void)
{
	int cpu;

	if (cpufreq_disabled())
		return -ENODEV;

	for_each_possible_cpu(cpu)
		init_rwsem(&per_cpu(cpu_policy_rwsem, cpu));

	cpufreq_global_kobject = kobject_create();
	BUG_ON(!cpufreq_global_kobject);
	register_syscore_ops(&cpufreq_syscore_ops);

	return 0;
}
core_initcall(cpufreq_core_init);