Merge back earlier 'pm-cpufreq' material.

39 files changed, 418 insertions, 391 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index d5a0d33c571..acb9bfc89b4 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -128,7 +128,7 @@ Description:	Discover cpuidle policy and mechanism
 
 What:		/sys/devices/system/cpu/cpu#/cpufreq/*
 Date:		pre-git history
-Contact:	cpufreq@vger.kernel.org
+Contact:	linux-pm@vger.kernel.org
 Description:	Discover and change clock speed of CPUs
 
 		Clock scaling allows you to change the clock speed of the
@@ -146,7 +146,7 @@ Description:	Discover and change clock speed of CPUs
 
 What:		/sys/devices/system/cpu/cpu#/cpufreq/freqdomain_cpus
 Date:		June 2013
-Contact:	cpufreq@vger.kernel.org
+Contact:	linux-pm@vger.kernel.org
 Description:	Discover CPUs in the same CPU frequency coordination domain
 
 		freqdomain_cpus is the list of CPUs (online+offline) that share
diff --git a/Documentation/cpu-freq/core.txt b/Documentation/cpu-freq/core.txt
index 0060d76b445..70933eadc30 100644
--- a/Documentation/cpu-freq/core.txt
+++ b/Documentation/cpu-freq/core.txt
@@ -20,6 +20,7 @@ Contents:
 ---------
 1.  CPUFreq core and interfaces
 2.  CPUFreq notifiers
+3.  CPUFreq Table Generation with Operating Performance Point (OPP)
 
 1. General Information
 =======================
@@ -92,3 +93,31 @@ values:
 cpu	- number of the affected CPU
 old	- old frequency
 new	- new frequency
+
+3. CPUFreq Table Generation with Operating Performance Point (OPP)
+==================================================================
+For details about OPP, see Documentation/power/opp.txt
+
+dev_pm_opp_init_cpufreq_table - cpufreq framework typically is initialized with
+	cpufreq_frequency_table_cpuinfo which is provided with the list of
+	frequencies that are available for operation. This function provides
+	a ready to use conversion routine to translate the OPP layer's internal
+	information about the available frequencies into a format readily
+	providable to cpufreq.
+
+	WARNING: Do not use this function in interrupt context.
+
+	Example:
+	 soc_pm_init()
+	 {
+		/* Do things */
+		r = dev_pm_opp_init_cpufreq_table(dev, &freq_table);
+		if (!r)
+			cpufreq_frequency_table_cpuinfo(policy, freq_table);
+		/* Do other things */
+	 }
+
+	NOTE: This function is available only if CONFIG_CPU_FREQ is enabled in
+	addition to CONFIG_PM_OPP.
+
+dev_pm_opp_free_cpufreq_table - Free up the table allocated by dev_pm_opp_init_cpufreq_table
diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt
index 48da5fdcb9f..b045fe54986 100644
--- a/Documentation/cpu-freq/cpu-drivers.txt
+++ b/Documentation/cpu-freq/cpu-drivers.txt
@@ -228,3 +228,22 @@ is the corresponding frequency table helper for the ->target
 stage. Just pass the values to this function, and the unsigned int
 index returns the number of the frequency table entry which contains
 the frequency the CPU shall be set to.
+
+The following macros can be used as iterators over cpufreq_frequency_table:
+
+cpufreq_for_each_entry(pos, table) - iterates over all entries of frequency
+table.
+
+cpufreq-for_each_valid_entry(pos, table) - iterates over all entries,
+excluding CPUFREQ_ENTRY_INVALID frequencies.
+Use arguments "pos" - a cpufreq_frequency_table * as a loop cursor and
+"table" - the cpufreq_frequency_table * you want to iterate over.
+
+For example:
+
+	struct cpufreq_frequency_table *pos, *driver_freq_table;
+
+	cpufreq_for_each_entry(pos, driver_freq_table) {
+		/* Do something with pos */
+		pos->frequency = ...
+	}
diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt
index 3d0b915035b..dc024ab4054 100644
--- a/Documentation/cpu-freq/index.txt
+++ b/Documentation/cpu-freq/index.txt
@@ -35,8 +35,8 @@ Mailing List
 ------------
 There is a CPU frequency changing CVS commit and general list where
 you can report bugs, problems or submit patches. To post a message,
-send an email to cpufreq@vger.kernel.org, to subscribe go to
-http://vger.kernel.org/vger-lists.html#cpufreq and follow the
+send an email to linux-pm@vger.kernel.org, to subscribe go to
+http://vger.kernel.org/vger-lists.html#linux-pm and follow the
 instructions there.
 
 Links
diff --git a/Documentation/power/opp.txt b/Documentation/power/opp.txt
index b8a907dc016..a9adad828cd 100644
--- a/Documentation/power/opp.txt
+++ b/Documentation/power/opp.txt
@@ -10,8 +10,7 @@ Contents
 3. OPP Search Functions
 4. OPP Availability Control Functions
 5. OPP Data Retrieval Functions
-6. Cpufreq Table Generation
-7. Data Structures
+6. Data Structures
 
 1. Introduction
 ===============
@@ -72,7 +71,6 @@ operations until that OPP could be re-enabled if possible.
 OPP library facilitates this concept in it's implementation. The following
 operational functions operate only on available opps:
 opp_find_freq_{ceil, floor}, dev_pm_opp_get_voltage, dev_pm_opp_get_freq, dev_pm_opp_get_opp_count
-and dev_pm_opp_init_cpufreq_table
 
 dev_pm_opp_find_freq_exact is meant to be used to find the opp pointer which can then
 be used for dev_pm_opp_enable/disable functions to make an opp available as required.
@@ -96,10 +94,9 @@ using RCU read locks. The opp_find_freq_{exact,ceil,floor},
 opp_get_{voltage, freq, opp_count} fall into this category.
 
 opp_{add,enable,disable} are updaters which use mutex and implement it's own
-RCU locking mechanisms. dev_pm_opp_init_cpufreq_table acts as an updater and uses
-mutex to implment RCU updater strategy. These functions should *NOT* be called
-under RCU locks and other contexts that prevent blocking functions in RCU or
-mutex operations from working.
+RCU locking mechanisms. These functions should *NOT* be called under RCU locks
+and other contexts that prevent blocking functions in RCU or mutex operations
+from working.
 
 2. Initial OPP List Registration
 ================================
@@ -311,34 +308,7 @@ dev_pm_opp_get_opp_count - Retrieve the number of available opps for a device
 		/* Do other things */
 	 }
 
-6. Cpufreq Table Generation
-===========================
-dev_pm_opp_init_cpufreq_table - cpufreq framework typically is initialized with
-	cpufreq_frequency_table_cpuinfo which is provided with the list of
-	frequencies that are available for operation. This function provides
-	a ready to use conversion routine to translate the OPP layer's internal
-	information about the available frequencies into a format readily
-	providable to cpufreq.
-
-	WARNING: Do not use this function in interrupt context.
-
-	Example:
-	 soc_pm_init()
-	 {
-		/* Do things */
-		r = dev_pm_opp_init_cpufreq_table(dev, &freq_table);
-		if (!r)
-			cpufreq_frequency_table_cpuinfo(policy, freq_table);
-		/* Do other things */
-	 }
-
-	NOTE: This function is available only if CONFIG_CPU_FREQ is enabled in
-	addition to CONFIG_PM as power management feature is required to
-	dynamically scale voltage and frequency in a system.
-
-dev_pm_opp_free_cpufreq_table - Free up the table allocated by dev_pm_opp_init_cpufreq_table
-
-7. Data Structures
+6. Data Structures
 ==================
 Typically an SoC contains multiple voltage domains which are variable. Each
 domain is represented by a device pointer. The relationship to OPP can be
diff --git a/MAINTAINERS b/MAINTAINERS
index 10662644212..06d2506a8d2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2415,7 +2415,6 @@ F:	drivers/net/ethernet/ti/cpmac.c
 CPU FREQUENCY DRIVERS
 M:	Rafael J. Wysocki <rjw@rjwysocki.net>
 M:	Viresh Kumar <viresh.kumar@linaro.org>
-L:	cpufreq@vger.kernel.org
 L:	linux-pm@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
@@ -2426,7 +2425,6 @@ F:	include/linux/cpufreq.h
 CPU FREQUENCY DRIVERS - ARM BIG LITTLE
 M:	Viresh Kumar <viresh.kumar@linaro.org>
 M:	Sudeep Holla <sudeep.holla@arm.com>
-L:	cpufreq@vger.kernel.org
 L:	linux-pm@vger.kernel.org
 W:	http://www.arm.com/products/processors/technologies/biglittleprocessing.php
 S:	Maintained
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 85399c98f84..45ce065e717 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -1092,20 +1092,21 @@ int da850_register_cpufreq(char *async_clk)
 
 static int da850_round_armrate(struct clk *clk, unsigned long rate)
 {
-	int i, ret = 0, diff;
+	int ret = 0, diff;
 	unsigned int best = (unsigned int) -1;
 	struct cpufreq_frequency_table *table = cpufreq_info.freq_table;
+	struct cpufreq_frequency_table *pos;
 
 	rate /= 1000; /* convert to kHz */
 
-	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
-		diff = table[i].frequency - rate;
+	cpufreq_for_each_entry(pos, table) {
+		diff = pos->frequency - rate;
 		if (diff < 0)
 			diff = -diff;
 
 		if (diff < best) {
 			best = diff;
-			ret = table[i].frequency;
+			ret = pos->frequency;
 		}
 	}
 
diff --git a/arch/mips/loongson/lemote-2f/clock.c b/arch/mips/loongson/lemote-2f/clock.c
index e1f427f4f5f..1eed38e28b1 100644
--- a/arch/mips/loongson/lemote-2f/clock.c
+++ b/arch/mips/loongson/lemote-2f/clock.c
@@ -91,9 +91,9 @@ EXPORT_SYMBOL(clk_put);
 
 int clk_set_rate(struct clk *clk, unsigned long rate)
 {
+	struct cpufreq_frequency_table *pos;
 	int ret = 0;
 	int regval;
-	int i;
 
 	if (likely(clk->ops && clk->ops->set_rate)) {
 		unsigned long flags;
@@ -106,22 +106,16 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 	if (unlikely(clk->flags & CLK_RATE_PROPAGATES))
 		propagate_rate(clk);
 
-	for (i = 0; loongson2_clockmod_table[i].frequency != CPUFREQ_TABLE_END;
-	     i++) {
-		if (loongson2_clockmod_table[i].frequency ==
-		    CPUFREQ_ENTRY_INVALID)
-			continue;
-		if (rate == loongson2_clockmod_table[i].frequency)
+	cpufreq_for_each_valid_entry(pos, loongson2_clockmod_table)
+		if (rate == pos->frequency)
 			break;
-	}
-	if (rate != loongson2_clockmod_table[i].frequency)
+	if (rate != pos->frequency)
 		return -ENOTSUPP;
 
 	clk->rate = rate;
 
 	regval = LOONGSON_CHIPCFG0;
-	regval = (regval & ~0x7) |
-		(loongson2_clockmod_table[i].driver_data - 1);
+	regval = (regval & ~0x7) | (pos->driver_data - 1);
 	LOONGSON_CHIPCFG0 = regval;
 
 	return ret;
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index 25538675d59..d9e376a6d19 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -15,7 +15,6 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/slab.h>
-#include <linux/cpufreq.h>
 #include <linux/device.h>
 #include <linux/list.h>
 #include <linux/rculist.h>
@@ -596,96 +595,6 @@ int dev_pm_opp_disable(struct device *dev, unsigned long freq)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_disable);
 
-#ifdef CONFIG_CPU_FREQ
-/**
- * dev_pm_opp_init_cpufreq_table() - create a cpufreq table for a device
- * @dev:	device for which we do this operation
- * @table:	Cpufreq table returned back to caller
- *
- * Generate a cpufreq table for a provided device- this assumes that the
- * opp list is already initialized and ready for usage.
- *
- * This function allocates required memory for the cpufreq table. It is
- * expected that the caller does the required maintenance such as freeing
- * the table as required.
- *
- * Returns -EINVAL for bad pointers, -ENODEV if the device is not found, -ENOMEM
- * if no memory available for the operation (table is not populated), returns 0
- * if successful and table is populated.
- *
- * WARNING: It is  important for the callers to ensure refreshing their copy of
- * the table if any of the mentioned functions have been invoked in the interim.
- *
- * Locking: The internal device_opp and opp structures are RCU protected.
- * To simplify the logic, we pretend we are updater and hold relevant mutex here
- * Callers should ensure that this function is *NOT* called under RCU protection
- * or in contexts where mutex locking cannot be used.
- */
-int dev_pm_opp_init_cpufreq_table(struct device *dev,
-			    struct cpufreq_frequency_table **table)
-{
-	struct device_opp *dev_opp;
-	struct dev_pm_opp *opp;
-	struct cpufreq_frequency_table *freq_table;
-	int i = 0;
-
-	/* Pretend as if I am an updater */
-	mutex_lock(&dev_opp_list_lock);
-
-	dev_opp = find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		int r = PTR_ERR(dev_opp);
-		mutex_unlock(&dev_opp_list_lock);
-		dev_err(dev, "%s: Device OPP not found (%d)\n", __func__, r);
-		return r;
-	}
-
-	freq_table = kzalloc(sizeof(struct cpufreq_frequency_table) *
-			     (dev_pm_opp_get_opp_count(dev) + 1), GFP_KERNEL);
-	if (!freq_table) {
-		mutex_unlock(&dev_opp_list_lock);
-		dev_warn(dev, "%s: Unable to allocate frequency table\n",
-			__func__);
-		return -ENOMEM;
-	}
-
-	list_for_each_entry(opp, &dev_opp->opp_list, node) {
-		if (opp->available) {
-			freq_table[i].driver_data = i;
-			freq_table[i].frequency = opp->rate / 1000;
-			i++;
-		}
-	}
-	mutex_unlock(&dev_opp_list_lock);
-
-	freq_table[i].driver_data = i;
-	freq_table[i].frequency = CPUFREQ_TABLE_END;
-
-	*table = &freq_table[0];
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_init_cpufreq_table);
-
-/**
- * dev_pm_opp_free_cpufreq_table() - free the cpufreq table
- * @dev:	device for which we do this operation
- * @table:	table to free
- *
- * Free up the table allocated by dev_pm_opp_init_cpufreq_table
- */
-void dev_pm_opp_free_cpufreq_table(struct device *dev,
-				struct cpufreq_frequency_table **table)
-{
-	if (!table)
-		return;
-
-	kfree(*table);
-	*table = NULL;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_free_cpufreq_table);
-#endif		/* CONFIG_CPU_FREQ */
-
 /**
  * dev_pm_opp_get_notifier() - find notifier_head of the device with opp
  * @dev:	device pointer used to lookup device OPPs.
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 580503513f0..6e05a1e18e5 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -85,7 +85,7 @@ config ARM_EXYNOS_CPU_FREQ_BOOST_SW
 	  It allows usage of special frequencies for Samsung Exynos
 	  processors if thermal conditions are appropriate.
 
-	  It reguires, for safe operation, thermal framework with properly
+	  It requires, for safe operation, thermal framework with properly
 	  defined trip points.
 
 	  If in doubt, say N.
@@ -186,7 +186,7 @@ config ARM_S3C2416_CPUFREQ
 	  S3C2450 SoC. The S3C2416 supports changing the rate of the
 	  armdiv clock source and also entering a so called dynamic
 	  voltage scaling mode in which it is possible to reduce the
-	  core voltage of the cpu.
+	  core voltage of the CPU.
 
 	  If in doubt, say N.
 
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index d369349eeaa..89ae88f9189 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -10,7 +10,7 @@ config X86_INTEL_PSTATE
 	  The driver implements an internal governor and will become
           the scaling driver and governor for Sandy bridge processors.
 
-	  When this driver is enabled it will become the perferred
+	  When this driver is enabled it will become the preferred
           scaling driver for Sandy bridge processors.
 
 	  If in doubt, say N.
@@ -52,7 +52,7 @@ config X86_ACPI_CPUFREQ_CPB
 	help
 	  The powernow-k8 driver used to provide a sysfs knob called "cpb"
 	  to disable the Core Performance Boosting feature of AMD CPUs. This
-	  file has now been superseeded by the more generic "boost" entry.
+	  file has now been superseded by the more generic "boost" entry.
 
 	  By enabling this option the acpi_cpufreq driver provides the old
 	  entry in addition to the new boost ones, for compatibility reasons.
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 0dbb963c1ae..738c8b7b17d 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -1,5 +1,7 @@
 # CPUfreq core
 obj-$(CONFIG_CPU_FREQ)			+= cpufreq.o freq_table.o
+obj-$(CONFIG_PM_OPP)			+= cpufreq_opp.o
+
 # CPUfreq stats
 obj-$(CONFIG_CPU_FREQ_STAT)             += cpufreq_stats.o
 
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 000e4e0afd7..b0c18ed8d83 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -213,7 +213,7 @@ static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
 
 static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
 {
-	int i;
+	struct cpufreq_frequency_table *pos;
 	struct acpi_processor_performance *perf;
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
@@ -223,10 +223,9 @@ static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
 
 	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;
-	}
+	cpufreq_for_each_entry(pos, data->freq_table)
+		if (msr == perf->states[pos->driver_data].status)
+			return pos->frequency;
 	return data->freq_table[0].frequency;
 }
 
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index bad2ed317ba..1f4d4e31505 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -226,22 +226,22 @@ static inline u32 get_table_count(struct cpufreq_frequency_table *table)
 /* get the minimum frequency in the cpufreq_frequency_table */
 static inline u32 get_table_min(struct cpufreq_frequency_table *table)
 {
-	int i;
+	struct cpufreq_frequency_table *pos;
 	uint32_t min_freq = ~0;
-	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++)
-		if (table[i].frequency < min_freq)
-			min_freq = table[i].frequency;
+	cpufreq_for_each_entry(pos, table)
+		if (pos->frequency < min_freq)
+			min_freq = pos->frequency;
 	return min_freq;
 }
 
 /* get the maximum frequency in the cpufreq_frequency_table */
 static inline u32 get_table_max(struct cpufreq_frequency_table *table)
 {
-	int i;
+	struct cpufreq_frequency_table *pos;
 	uint32_t max_freq = 0;
-	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++)
-		if (table[i].frequency > max_freq)
-			max_freq = table[i].frequency;
+	cpufreq_for_each_entry(pos, table)
+		if (pos->frequency > max_freq)
+			max_freq = pos->frequency;
 	return max_freq;
 }
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index abda6609d3e..bfe82b63875 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -237,6 +237,17 @@ void cpufreq_cpu_put(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_put);
 
+bool cpufreq_next_valid(struct cpufreq_frequency_table **pos)
+{
+	while ((*pos)->frequency != CPUFREQ_TABLE_END)
+		if ((*pos)->frequency != CPUFREQ_ENTRY_INVALID)
+			return true;
+		else
+			(*pos)++;
+	return false;
+}
+EXPORT_SYMBOL_GPL(cpufreq_next_valid);
+
 /*********************************************************************
  *            EXTERNALLY AFFECTING FREQUENCY CHANGES                 *
  *********************************************************************/
@@ -354,6 +365,18 @@ static void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
 void cpufreq_freq_transition_begin(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs)
 {
+
+	/*
+	 * Catch double invocations of _begin() which lead to self-deadlock.
+	 * ASYNC_NOTIFICATION drivers are left out because the cpufreq core
+	 * doesn't invoke _begin() on their behalf, and hence the chances of
+	 * double invocations are very low. Moreover, there are scenarios
+	 * where these checks can emit false-positive warnings in these
+	 * drivers; so we avoid that by skipping them altogether.
+	 */
+	WARN_ON(!(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION)
+				&& current == policy->transition_task);
+
 wait:
 	wait_event(policy->transition_wait, !policy->transition_ongoing);
 
@@ -365,6 +388,7 @@ wait:
 	}
 
 	policy->transition_ongoing = true;
+	policy->transition_task = current;
 
 	spin_unlock(&policy->transition_lock);
 
@@ -381,6 +405,7 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
 	cpufreq_notify_post_transition(policy, freqs, transition_failed);
 
 	policy->transition_ongoing = false;
+	policy->transition_task = NULL;
 
 	wake_up(&policy->transition_wait);
 }
diff --git a/drivers/cpufreq/cpufreq_opp.c b/drivers/cpufreq/cpufreq_opp.c
new file mode 100644
index 00000000000..c0c6f4a4ecc
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_opp.c
@@ -0,0 +1,110 @@
+/*
+ * Generic OPP helper interface for CPUFreq drivers
+ *
+ * Copyright (C) 2009-2014 Texas Instruments Incorporated.
+ *	Nishanth Menon
+ *	Romit Dasgupta
+ *	Kevin Hilman
+ *
+ * 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.
+ */
+#include <linux/cpufreq.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/pm_opp.h>
+#include <linux/rcupdate.h>
+#include <linux/slab.h>
+
+/**
+ * dev_pm_opp_init_cpufreq_table() - create a cpufreq table for a device
+ * @dev:	device for which we do this operation
+ * @table:	Cpufreq table returned back to caller
+ *
+ * Generate a cpufreq table for a provided device- this assumes that the
+ * opp list is already initialized and ready for usage.
+ *
+ * This function allocates required memory for the cpufreq table. It is
+ * expected that the caller does the required maintenance such as freeing
+ * the table as required.
+ *
+ * Returns -EINVAL for bad pointers, -ENODEV if the device is not found, -ENOMEM
+ * if no memory available for the operation (table is not populated), returns 0
+ * if successful and table is populated.
+ *
+ * WARNING: It is  important for the callers to ensure refreshing their copy of
+ * the table if any of the mentioned functions have been invoked in the interim.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Since we just use the regular accessor functions to access the internal data
+ * structures, we use RCU read lock inside this function. As a result, users of
+ * this function DONOT need to use explicit locks for invoking.
+ */
+int dev_pm_opp_init_cpufreq_table(struct device *dev,
+				  struct cpufreq_frequency_table **table)
+{
+	struct dev_pm_opp *opp;
+	struct cpufreq_frequency_table *freq_table = NULL;
+	int i, max_opps, ret = 0;
+	unsigned long rate;
+
+	rcu_read_lock();
+
+	max_opps = dev_pm_opp_get_opp_count(dev);
+	if (max_opps <= 0) {
+		ret = max_opps ? max_opps : -ENODATA;
+		goto out;
+	}
+
+	freq_table = kzalloc(sizeof(*freq_table) * (max_opps + 1), GFP_KERNEL);
+	if (!freq_table) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0, rate = 0; i < max_opps; i++, rate++) {
+		/* find next rate */
+		opp = dev_pm_opp_find_freq_ceil(dev, &rate);
+		if (IS_ERR(opp)) {
+			ret = PTR_ERR(opp);
+			goto out;
+		}
+		freq_table[i].driver_data = i;
+		freq_table[i].frequency = rate / 1000;
+	}
+
+	freq_table[i].driver_data = i;
+	freq_table[i].frequency = CPUFREQ_TABLE_END;
+
+	*table = &freq_table[0];
+
+out:
+	rcu_read_unlock();
+	if (ret)
+		kfree(freq_table);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_init_cpufreq_table);
+
+/**
+ * dev_pm_opp_free_cpufreq_table() - free the cpufreq table
+ * @dev:	device for which we do this operation
+ * @table:	table to free
+ *
+ * Free up the table allocated by dev_pm_opp_init_cpufreq_table
+ */
+void dev_pm_opp_free_cpufreq_table(struct device *dev,
+				   struct cpufreq_frequency_table **table)
+{
+	if (!table)
+		return;
+
+	kfree(*table);
+	*table = NULL;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_free_cpufreq_table);
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index ecaaebf969f..0cd9b4dcef9 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -182,11 +182,11 @@ static void cpufreq_stats_free_table(unsigned int cpu)
 
 static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
 {
-	unsigned int i, j, count = 0, ret = 0;
+	unsigned int i, count = 0, ret = 0;
 	struct cpufreq_stats *stat;
 	unsigned int alloc_size;
 	unsigned int cpu = policy->cpu;
-	struct cpufreq_frequency_table *table;
+	struct cpufreq_frequency_table *pos, *table;
 
 	table = cpufreq_frequency_get_table(cpu);
 	if (unlikely(!table))
@@ -205,12 +205,8 @@ static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	stat->cpu = cpu;
 	per_cpu(cpufreq_stats_table, cpu) = stat;
 
-	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
-		unsigned int freq = table[i].frequency;
-		if (freq == CPUFREQ_ENTRY_INVALID)
-			continue;
+	cpufreq_for_each_valid_entry(pos, table)
 		count++;
-	}
 
 	alloc_size = count * sizeof(int) + count * sizeof(u64);
 
@@ -228,15 +224,11 @@ static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	stat->trans_table = stat->freq_table + count;
 #endif
-	j = 0;
-	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
-		unsigned int freq = table[i].frequency;
-		if (freq == CPUFREQ_ENTRY_INVALID)
-			continue;
-		if (freq_table_get_index(stat, freq) == -1)
-			stat->freq_table[j++] = freq;
-	}
-	stat->state_num = j;
+	i = 0;