Merge branches 'pm-cpufreq-sched' and 'pm-opp'

* pm-cpufreq-sched:
  cpufreq: schedutil: Reset cached_raw_freq when not in sync with next_freq

* pm-opp:
  PM / OPP: Add dev_pm_opp_{un}register_get_pstate_helper()
  PM / OPP: Support updating performance state of device's power domain
  PM / OPP: add missing of_node_put() for of_get_cpu_node()
  PM / OPP: Rename dev_pm_opp_register_put_opp_helper()
  PM / OPP: Add missing of_node_put(np)
  PM / OPP: Move error message to debug level
  PM / OPP: Use snprintf() to avoid kasprintf() and kfree()
  PM / OPP: Move the OPP directory out of power/

MAINTAINERS

@@ -10049,7 +10049,7 @@ M:	Stephen Boyd <sboyd@codeaurora.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm.git
-F:	drivers/base/power/opp/
+F:	drivers/opp/
 F:	include/linux/pm_opp.h
 F:	Documentation/power/opp.txt
 F:	Documentation/devicetree/bindings/opp/

drivers/Kconfig

@@ -209,4 +209,6 @@ source "drivers/tee/Kconfig"
 
 source "drivers/mux/Kconfig"
 
+source "drivers/opp/Kconfig"
+
 endmenu

drivers/Makefile

@@ -126,6 +126,7 @@ obj-$(CONFIG_ACCESSIBILITY)	+= accessibility/
 obj-$(CONFIG_ISDN)		+= isdn/
 obj-$(CONFIG_EDAC)		+= edac/
 obj-$(CONFIG_EISA)		+= eisa/
+obj-$(CONFIG_PM_OPP)		+= opp/
 obj-$(CONFIG_CPU_FREQ)		+= cpufreq/
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle/
 obj-y				+= mmc/

drivers/base/power/Makefile

@@ -2,7 +2,6 @@
 obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o runtime.o wakeirq.o
 obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
-obj-$(CONFIG_PM_OPP)	+= opp/
 obj-$(CONFIG_PM_GENERIC_DOMAINS)	+=  domain.o domain_governor.o
 obj-$(CONFIG_HAVE_CLK)	+= clock_ops.o
 

drivers/opp/Kconfig

@@ -0,0 +1,13 @@
+config PM_OPP
+	bool
+	select SRCU
+	---help---
+	  SOCs have a standard set of tuples consisting of frequency and
+	  voltage pairs that the device will support per voltage domain. This
+	  is called Operating Performance Point or OPP. The actual definitions
+	  of OPP varies over silicon within the same family of devices.
+
+	  OPP layer organizes the data internally using device pointers
+	  representing individual voltage domains and provides SOC
+	  implementations a ready to use framework to manage OPPs.
+	  For more information, read <file:Documentation/power/opp.txt>

drivers/opp/Makefile

@@ -0,0 +1,4 @@
+ccflags-$(CONFIG_DEBUG_DRIVER)	:= -DDEBUG
+obj-y				+= core.o cpu.o
+obj-$(CONFIG_OF)		+= of.o
+obj-$(CONFIG_DEBUG_FS)		+= debugfs.o

drivers/opp/cpu.c

@@ -0,0 +1,236 @@
+/*
+ * Generic OPP helper interface for CPU device
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+
+#include "opp.h"
+
+#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 table 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.
+ */
+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;
+
+	max_opps = dev_pm_opp_get_opp_count(dev);
+	if (max_opps <= 0)
+		return max_opps ? max_opps : -ENODATA;
+
+	freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC);
+	if (!freq_table)
+		return -ENOMEM;
+
+	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;
+
+		/* Is Boost/turbo opp ? */
+		if (dev_pm_opp_is_turbo(opp))
+			freq_table[i].flags = CPUFREQ_BOOST_FREQ;
+
+		dev_pm_opp_put(opp);
+	}
+
+	freq_table[i].driver_data = i;
+	freq_table[i].frequency = CPUFREQ_TABLE_END;
+
+	*table = &freq_table[0];
+
+out:
+	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);
+#endif	/* CONFIG_CPU_FREQ */
+
+void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of)
+{
+	struct device *cpu_dev;
+	int cpu;
+
+	WARN_ON(cpumask_empty(cpumask));
+
+	for_each_cpu(cpu, cpumask) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__,
+			       cpu);
+			continue;
+		}
+
+		if (of)
+			dev_pm_opp_of_remove_table(cpu_dev);
+		else
+			dev_pm_opp_remove_table(cpu_dev);
+	}
+}
+
+/**
+ * dev_pm_opp_cpumask_remove_table() - Removes OPP table for @cpumask
+ * @cpumask:	cpumask for which OPP table needs to be removed
+ *
+ * This removes the OPP tables for CPUs present in the @cpumask.
+ * This should be used to remove all the OPPs entries associated with
+ * the cpus in @cpumask.
+ */
+void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask)
+{
+	_dev_pm_opp_cpumask_remove_table(cpumask, false);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_cpumask_remove_table);
+
+/**
+ * dev_pm_opp_set_sharing_cpus() - Mark OPP table as shared by few CPUs
+ * @cpu_dev:	CPU device for which we do this operation
+ * @cpumask:	cpumask of the CPUs which share the OPP table with @cpu_dev
+ *
+ * This marks OPP table of the @cpu_dev as shared by the CPUs present in
+ * @cpumask.
+ *
+ * Returns -ENODEV if OPP table isn't already present.
+ */
+int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
+				const struct cpumask *cpumask)
+{
+	struct opp_device *opp_dev;
+	struct opp_table *opp_table;
+	struct device *dev;
+	int cpu, ret = 0;
+
+	opp_table = _find_opp_table(cpu_dev);
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
+
+	for_each_cpu(cpu, cpumask) {
+		if (cpu == cpu_dev->id)
+			continue;
+
+		dev = get_cpu_device(cpu);
+		if (!dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
+
+		opp_dev = _add_opp_dev(dev, opp_table);
+		if (!opp_dev) {
+			dev_err(dev, "%s: failed to add opp-dev for cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
+
+		/* Mark opp-table as multiple CPUs are sharing it now */
+		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
+	}
+
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus);
+
+/**
+ * dev_pm_opp_get_sharing_cpus() - Get cpumask of CPUs sharing OPPs with @cpu_dev
+ * @cpu_dev:	CPU device for which we do this operation
+ * @cpumask:	cpumask to update with information of sharing CPUs
+ *
+ * This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev.
+ *
+ * Returns -ENODEV if OPP table isn't already present and -EINVAL if the OPP
+ * table's status is access-unknown.
+ */
+int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
+{
+	struct opp_device *opp_dev;
+	struct opp_table *opp_table;
+	int ret = 0;
+
+	opp_table = _find_opp_table(cpu_dev);
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
+
+	if (opp_table->shared_opp == OPP_TABLE_ACCESS_UNKNOWN) {
+		ret = -EINVAL;
+		goto put_opp_table;
+	}
+
+	cpumask_clear(cpumask);
+
+	if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) {
+		list_for_each_entry(opp_dev, &opp_table->dev_list, node)
+			cpumask_set_cpu(opp_dev->dev->id, cpumask);
+	} else {
+		cpumask_set_cpu(cpu_dev->id, cpumask);
+	}
+
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_sharing_cpus);

drivers/opp/debugfs.c

@@ -0,0 +1,251 @@
+/*
+ * Generic OPP debugfs interface
+ *
+ * Copyright (C) 2015-2016 Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * 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/debugfs.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/limits.h>
+#include <linux/slab.h>
+
+#include "opp.h"
+
+static struct dentry *rootdir;
+
+static void opp_set_dev_name(const struct device *dev, char *name)
+{
+	if (dev->parent)
+		snprintf(name, NAME_MAX, "%s-%s", dev_name(dev->parent),
+			 dev_name(dev));
+	else
+		snprintf(name, NAME_MAX, "%s", dev_name(dev));
+}
+
+void opp_debug_remove_one(struct dev_pm_opp *opp)
+{
+	debugfs_remove_recursive(opp->dentry);
+}
+
+static bool opp_debug_create_supplies(struct dev_pm_opp *opp,
+				      struct opp_table *opp_table,
+				      struct dentry *pdentry)
+{
+	struct dentry *d;
+	int i;
+
+	for (i = 0; i < opp_table->regulator_count; i++) {
+		char name[15];
+
+		snprintf(name, sizeof(name), "supply-%d", i);
+
+		/* Create per-opp directory */
+		d = debugfs_create_dir(name, pdentry);
+
+		if (!d)
+			return false;
+
+		if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d,
+					  &opp->supplies[i].u_volt))
+			return false;
+
+		if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d,
+					  &opp->supplies[i].u_volt_min))
+			return false;
+
+		if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d,
+					  &opp->supplies[i].u_volt_max))
+			return false;
+
+		if (!debugfs_create_ulong("u_amp", S_IRUGO, d,
+					  &opp->supplies[i].u_amp))
+			return false;
+	}
+
+	return true;
+}
+
+int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
+{
+	struct dentry *pdentry = opp_table->dentry;
+	struct dentry *d;
+	char name[25];	/* 20 chars for 64 bit value + 5 (opp:\0) */
+
+	/* Rate is unique to each OPP, use it to give opp-name */
+	snprintf(name, sizeof(name), "opp:%lu", opp->rate);
+
+	/* Create per-opp directory */
+	d = debugfs_create_dir(name, pdentry);
+	if (!d)
+		return -ENOMEM;
+
+	if (!debugfs_create_bool("available", S_IRUGO, d, &opp->available))
+		return -ENOMEM;
+
+	if (!debugfs_create_bool("dynamic", S_IRUGO, d, &opp->dynamic))
+		return -ENOMEM;
+
+	if (!debugfs_create_bool("turbo", S_IRUGO, d, &opp->turbo))
+		return -ENOMEM;
+
+	if (!debugfs_create_bool("suspend", S_IRUGO, d, &opp->suspend))
+		return -ENOMEM;
+
+	if (!debugfs_create_u32("performance_state", S_IRUGO, d, &opp->pstate))
+		return -ENOMEM;
+
+	if (!debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate))
+		return -ENOMEM;
+
+	if (!opp_debug_create_supplies(opp, opp_table, d))
+		return -ENOMEM;
+
+	if (!debugfs_create_ulong("clock_latency_ns", S_IRUGO, d,
+				  &opp->clock_latency_ns))
+		return -ENOMEM;
+
+	opp->dentry = d;
+	return 0;
+}
+
+static int opp_list_debug_create_dir(struct opp_device *opp_dev,
+				     struct opp_table *opp_table)
+{
+	const struct device *dev = opp_dev->dev;
+	struct dentry *d;
+
+	opp_set_dev_name(dev, opp_table->dentry_name);
+
+	/* Create device specific directory */
+	d = debugfs_create_dir(opp_table->dentry_name, rootdir);
+	if (!d) {
+		dev_err(dev, "%s: Failed to create debugfs dir\n", __func__);
+		return -ENOMEM;
+	}
+
+	opp_dev->dentry = d;
+	opp_table->dentry = d;
+
+	return 0;
+}
+
+static int opp_list_debug_create_link(struct opp_device *opp_dev,
+				      struct opp_table *opp_table)
+{
+	const struct device *dev = opp_dev->dev;
+	char name[NAME_MAX];
+	struct dentry *d;
+
+	opp_set_dev_name(opp_dev->dev, name);
+
+	/* Create device specific directory link */
+	d = debugfs_create_symlink(name, rootdir, opp_table->dentry_name);
+	if (!d) {
+		dev_err(dev, "%s: Failed to create link\n", __func__);
+		return -ENOMEM;
+	}
+
+	opp_dev->dentry = d;
+
+	return 0;
+}
+
+/**
+ * opp_debug_register - add a device opp node to the debugfs 'opp' directory
+ * @opp_dev: opp-dev pointer for device
+ * @opp_table: the device-opp being added
+ *
+ * Dynamically adds device specific directory in debugfs 'opp' directory. If the
+ * device-opp is shared with other devices, then links will be created for all
+ * devices except the first.
+ *
+ * Return: 0 on success, otherwise negative error.
+ */
+int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table)
+{
+	if (!rootdir) {
+		pr_debug("%s: Uninitialized rootdir\n", __func__);
+		return -EINVAL;
+	}
+
+	if (opp_table->dentry)
+		return opp_list_debug_create_link(opp_dev, opp_table);
+
+	return opp_list_debug_create_dir(opp_dev, opp_table);
+}
+
+static void opp_migrate_dentry(struct opp_device *opp_dev,
+			       struct opp_table *opp_table)
+{
+	struct opp_device *new_dev;
+	const struct device *dev;
+	struct dentry *dentry;
+
+	/* Look for next opp-dev */
+	list_for_each_entry(new_dev, &opp_table->dev_list, node)
+		if (new_dev != opp_dev)
+			break;
+
+	/* new_dev is guaranteed to be valid here */
+	dev = new_dev->dev;
+	debugfs_remove_recursive(new_dev->dentry);
+
+	opp_set_dev_name(dev, opp_table->dentry_name);
+
+	dentry = debugfs_rename(rootdir, opp_dev->dentry, rootdir,
+				opp_table->dentry_name);
+	if (!dentry) {
+		dev_err(dev, "%s: Failed to rename link from: %s to %s\n",
+			__func__, dev_name(opp_dev->dev), dev_name(dev));
+		return;
+	}
+
+	new_dev->dentry = dentry;
+	opp_table->dentry = dentry;
+}
+
+/**
+ * opp_debug_unregister - remove a device opp node from debugfs opp directory
+ * @opp_dev: opp-dev pointer for device
+ * @opp_table: the device-opp being removed
+ *
+ * Dynamically removes device specific directory from debugfs 'opp' directory.
+ */
+void opp_debug_unregister(struct opp_device *opp_dev,
+			  struct opp_table *opp_table)
+{
+	if (opp_dev->dentry == opp_table->dentry) {
+		/* Move the real dentry object under another device */
+		if (!list_is_singular(&opp_table->dev_list)) {
+			opp_migrate_dentry(opp_dev, opp_table);
+			goto out;
+		}
+		opp_table->dentry = NULL;
+	}
+
+	debugfs_remove_recursive(opp_dev->dentry);
+
+out:
+	opp_dev->dentry = NULL;
+}
+
+static int __init opp_debug_init(void)
+{
+	/* Create /sys/kernel/debug/opp directory */
+	rootdir = debugfs_create_dir("opp", NULL);
+	if (!rootdir) {
+		pr_err("%s: Failed to create root directory\n", __func__);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+core_initcall(opp_debug_init);

drivers/opp/of.c

@@ -0,0 +1,635 @@
+/*
+ * Generic OPP OF helpers
+ *
+ * Copyright (C) 2009-2010 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+
+#include "opp.h"
+
+static struct opp_table *_managed_opp(const struct device_node *np)
+{
+	struct opp_table *opp_table, *managed_table = NULL;
+
+	mutex_lock(&opp_table_lock);
+
+	list_for_each_entry(opp_table, &opp_tables, node) {
+		if (opp_table->np == np) {
+			/*
+			 * Multiple devices can point to the same OPP table and
+			 * so will have same node-pointer, np.
+			 *
+			 * But the OPPs will be considered as shared only if the
+			 * OPP table contains a "opp-shared" property.
+			 */
+			if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) {
+				_get_opp_table_kref(opp_table);
+				managed_table = opp_table;
+			}
+
+			break;
+		}
+	}
+
+	mutex_unlock(&opp_table_lock);
+
+	return managed_table;
+}
+
+void _of_init_opp_table(struct opp_table *opp_table, struct device *dev)
+{
+	struct device_node *np;
+
+	/*
+	 * Only required for backward compatibility with v1 bindings, but isn't
+	 * harmful for other cases. And so we do it unconditionally.
+	 */
+	np = of_node_get(dev->of_node);
+	if (np) {
+		u32 val;
+
+		if (!of_property_read_u32(np, "clock-latency", &val))
+			opp_table->clock_latency_ns_max = val;
+		of_property_read_u32(np, "voltage-tolerance",
+				     &opp_table->voltage_tolerance_v1);
+		of_node_put(np);
+	}
+}
+
+static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table,
+			      struct device_node *np)
+{
+	unsigned int count = opp_table->supported_hw_count;
+	u32 version;
+	int ret;
+
+	if (!opp_table->supported_hw) {
+		/*
+		 * In the case that no supported_hw has been set by the
+		 * platform but there is an opp-supported-hw value set for
+		 * an OPP then the OPP should not be enabled as there is
+		 * no way to see if the hardware supports it.
+		 */
+		if (of_find_property(np, "opp-supported-hw", NULL))
+			return false;
+		else
+			return true;
+	}
+
+	while (count--) {
+		ret = of_property_read_u32_index(np, "opp-supported-hw", count,
+						 &version);
+		if (ret) {
+			dev_warn(dev, "%s: failed to read opp-supported-hw property at index %d: %d\n",
+				 __func__, count, ret);
+			return false;
+		}
+
+		/* Both of these are bitwise masks of the versions */
+		if (!(version & opp_table->supported_hw[count]))
+			return false;
+	}
+
+	return true;
+}
+
+static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
+			      struct opp_table *opp_table)
+{
+	u32 *microvolt, *microamp = NULL;
+	int supplies, vcount, icount, ret, i, j;
+	struct property *prop = NULL;
+	char name[NAME_MAX];
+
+	supplies = opp_table->regulator_count ? opp_table->regulator_count : 1;
+
+	/* Search for "opp-microvolt-<name>" */
+	if (opp_table->prop_name) {
+		snprintf(name, sizeof(name), "opp-microvolt-%s",
+			 opp_table->prop_name);
+		prop = of_find_property(opp->np, name, NULL);
+	}
+
+	if (!prop) {
+		/* Search for "opp-microvolt" */
+		sprintf(name, "opp-microvolt");
+		prop = of_find_property(opp->np, name, NULL);
+
+		/* Missing property isn't a problem, but an invalid entry is */
+		if (!prop) {
+			if (!opp_table->regulator_count)
+				return 0;
+
+			dev_err(dev, "%s: opp-microvolt missing although OPP managing regulators\n",
+				__func__);
+			return -EINVAL;
+		}
+	}
+
+	vcount = of_property_count_u32_elems(opp->np, name);
+	if (vcount < 0) {
+		dev_err(dev, "%s: Invalid %s property (%d)\n",
+			__func__, name, vcount);
+		return vcount;
+	}
+
+	/* There can be one or three elements per supply */
+	if (vcount != supplies && vcount != supplies * 3) {
+		dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n",
+			__func__, name, vcount, supplies);
+		return -EINVAL;
+	}
+
+	microvolt = kmalloc_array(vcount, sizeof(*microvolt), GFP_KERNEL);
+	if (!microvolt)
+		return -ENOMEM;
+
+	ret = of_property_read_u32_array(opp->np, name, microvolt, vcount);
+	if (ret) {
+		dev_err(dev, "%s: error parsing %s: %d\n", __func__, name, ret);
+		ret = -EINVAL;
+		goto free_microvolt;
+	}
+
+	/* Search for "opp-microamp-<name>" */
+	prop = NULL;
+	if (opp_table->prop_name) {
+		snprintf(name, sizeof(name), "opp-microamp-%s",
+			 opp_table->prop_name);
+		prop = of_find_property(opp->np, name, NULL);
+	}
+
+	if (!prop) {
+		/* Search for "opp-microamp" */
+		sprintf(name, "opp-microamp");
+		prop = of_find_property(opp->np, name, NULL);
+	}
+
+	if (prop) {
+		icount = of_property_count_u32_elems(opp->np, name);
+		if (icount < 0) {
+			dev_err(dev, "%s: Invalid %s property (%d)\n", __func__,
+				name, icount);
+			ret = icount;
+			goto free_microvolt;
+		}
+
+		if (icount != supplies) {
+			dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n",
+				__func__, name, icount, supplies);
+			ret = -EINVAL;
+			goto free_microvolt;
+		}
+
+		microamp = kmalloc_array(icount, sizeof(*microamp), GFP_KERNEL);
+		if (!microamp) {
+			ret = -EINVAL;
+			goto free_microvolt;
+		}
+
+		ret = of_property_read_u32_array(opp->np, name, microamp,
+						 icount);
+		if (ret) {
+			dev_err(dev, "%s: error parsing %s: %d\n", __func__,
+				name, ret);
+			ret = -EINVAL;
+			goto free_microamp;
+		}
+	}
+
+	for (i = 0, j = 0; i < supplies; i++) {
+		opp->supplies[i].u_volt = microvolt[j++];
+
+		if (vcount == supplies) {
+			opp->supplies[i].u_volt_min = opp->supplies[i].u_volt;
+			opp->supplies[i].u_volt_max = opp->supplies[i].u_volt;
+		} else {
+			opp->supplies[i].u_volt_min = microvolt[j++];
+			opp->supplies[i].u_volt_max = microvolt[j++];
+		}
+
+		if (microamp)
+			opp->supplies[i].u_amp = microamp[i];
+	}
+
+free_microamp:
+	kfree(microamp);
+free_microvolt:
+	kfree(microvolt);
+
+	return ret;
+}
+
+/**
+ * dev_pm_opp_of_remove_table() - Free OPP table entries created from static DT
+ *				  entries
+ * @dev:	device pointer used to lookup OPP table.
+ *
+ * Free OPPs created using static entries present in DT.
+ */
+void dev_pm_opp_of_remove_table(struct device *dev)
+{
+	_dev_pm_opp_find_and_remove_table(dev, false);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
+
+/* Returns opp descriptor node for a device node, caller must
+ * do of_node_put() */
+static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np)
+{
+	/*
+	 * There should be only ONE phandle present in "operating-points-v2"
+	 * property.
+	 */
+
+	return of_parse_phandle(np, "operating-points-v2", 0);
+}
+
+/* Returns opp descriptor node for a device, caller must do of_node_put() */
+struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev)
+{
+	return _opp_of_get_opp_desc_node(dev->of_node);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node);
+
+/**
+ * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
+ * @opp_table:	OPP table
+ * @dev:	device for which we do this operation
+ * @np:		device node
+ *
+ * This function adds an opp definition to the opp table and returns status. The
+ * opp can be controlled using dev_pm_opp_enable/disable functions and may be
+ * removed by dev_pm_opp_remove.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -EINVAL	Failed parsing the OPP node
+ */
+static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
+			      struct device_node *np)
+{
+	struct dev_pm_opp *new_opp;
+	u64 rate;
+	u32 val;
+	int ret;
+
+	new_opp = _opp_allocate(opp_table);
+	if (!new_opp)
+		return -ENOMEM;
+
+	ret = of_property_read_u64(np, "opp-hz", &rate);
+	if (ret < 0) {
+		dev_err(dev, "%s: opp-hz not found\n", __func__);
+		goto free_opp;
+	}
+
+	/* Check if the OPP supports hardware's hierarchy of versions or not */
+	if (!_opp_is_supported(dev, opp_table, np)) {
+		dev_dbg(dev, "OPP not supported by hardware: %llu\n", rate);
+		goto free_opp;
+	}
+
+	/*
+	 * Rate is defined as an unsigned long in clk API, and so casting
+	 * explicitly to its type. Must be fixed once rate is 64 bit
+	 * guaranteed in clk API.
+	 */
+	new_opp->rate = (unsigned long)rate;
+	new_opp->turbo = of_property_read_bool(np, "turbo-mode");
+
+	new_opp->np = np;
+	new_opp->dynamic = false;
+	new_opp->available = true;
+
+	if (!of_property_read_u32(np, "clock-latency-ns", &val))
+		new_opp->clock_latency_ns = val;
+
+	ret = opp_parse_supplies(new_opp, dev, opp_table);
+	if (ret)
+		goto free_opp;
+
+	ret = _opp_add(dev, new_opp, opp_table);
+	if (ret) {
+		/* Don't return error for duplicate OPPs */
+		if (ret == -EBUSY)
+			ret = 0;
+		goto free_opp;
+	}
+
+	/* OPP to select on device suspend */
+	if (of_property_read_bool(np, "opp-suspend")) {
+		if (opp_table->suspend_opp) {
+			dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n",
+				 __func__, opp_table->suspend_opp->rate,
+				 new_opp->rate);
+		} else {
+			new_opp->suspend = true;
+			opp_table->suspend_opp = new_opp;
+		}
+	}
+
+	if (new_opp->clock_latency_ns > opp_table->clock_latency_ns_max)
+		opp_table->clock_latency_ns_max = new_opp->clock_latency_ns;
+
+	pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n",
+		 __func__, new_opp->turbo, new_opp->rate,
+		 new_opp->supplies[0].u_volt, new_opp->supplies[0].u_volt_min,
+		 new_opp->supplies[0].u_volt_max, new_opp->clock_latency_ns);
+
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADD, new_opp);
+	return 0;
+
+free_opp:
+	_opp_free(new_opp);
+
+	return ret;
+}
+
+/* Initializes OPP tables based on new bindings */
+static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
+{
+	struct device_node *np;
+	struct opp_table *opp_table;
+	int ret = 0, count = 0;
+
+	opp_table = _managed_opp(opp_np);
+	if (opp_table) {
+		/* OPPs are already managed */
+		if (!_add_opp_dev(dev, opp_table))
+			ret = -ENOMEM;
+		goto put_opp_table;
+	}
+
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
+
+	/* We have opp-table node now, iterate over it and add OPPs */
+	for_each_available_child_of_node(opp_np, np) {
+		count++;
+
+		ret = _opp_add_static_v2(opp_table, dev, np);
+		if (ret) {
+			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
+				ret);
+			_dev_pm_opp_remove_table(opp_table, dev, false);
+			of_node_put(np);
+			goto put_opp_table;
+		}
+	}
+
+	/* There should be one of more OPP defined */
+	if (WARN_ON(!count)) {
+		ret = -ENOENT;
+		goto put_opp_table;
+	}
+
+	opp_table->np = opp_np;
+	if (of_property_read_bool(opp_np, "opp-shared"))
+		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
+	else
+		opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE;
+
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return ret;
+}
+
+/* Initializes OPP tables based on old-deprecated bindings */
+static int _of_add_opp_table_v1(struct device *dev)
+{
+	struct opp_table *opp_table;
+	const struct property *prop;
+	const __be32 *val;
+	int nr, ret = 0;
+
+	prop = of_find_property(dev->of_node, "operating-points", NULL);
+	if (!prop)
+		return -ENODEV;
+	if (!prop->value)
+		return -ENODATA;
+
+	/*
+	 * Each OPP is a set of tuples consisting of frequency and
+	 * voltage like <freq-kHz vol-uV>.
+	 */
+	nr = prop->length / sizeof(u32);
+	if (nr % 2) {
+		dev_err(dev, "%s: Invalid OPP table\n", __func__);
+		return -EINVAL;
+	}
+
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
+
+	val = prop->value;
+	while (nr) {
+		unsigned long freq = be32_to_cpup(val++) * 1000;
+		unsigned long volt = be32_to_cpup(val++);
+
+		ret = _opp_add_v1(opp_table, dev, freq, volt, false);
+		if (ret) {
+			dev_err(dev, "%s: Failed to add OPP %ld (%d)\n",
+				__func__, freq, ret);
+			_dev_pm_opp_remove_table(opp_table, dev, false);
+			break;
+		}
+		nr -= 2;
+	}
+
+	dev_pm_opp_put_opp_table(opp_table);
+	return ret;
+}
+
+/**
+ * dev_pm_opp_of_add_table() - Initialize opp table from device tree
+ * @dev:	device pointer used to lookup OPP table.
+ *
+ * Register the initial OPP table with the OPP library for given device.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -ENODEV	when 'operating-points' property is not found or is invalid data
+ *		in device node.
+ * -ENODATA	when empty 'operating-points' property is found
+ * -EINVAL	when invalid entries are found in opp-v2 table
+ */
+int dev_pm_opp_of_add_table(struct device *dev)
+{
+	struct device_node *opp_np;
+	int ret;
+
+	/*
+	 * OPPs have two version of bindings now. The older one is deprecated,
+	 * try for the new binding first.
+	 */
+	opp_np = dev_pm_opp_of_get_opp_desc_node(dev);
+	if (!opp_np) {
+		/*
+		 * Try old-deprecated bindings for backward compatibility with
+		 * older dtbs.
+		 */
+		return _of_add_opp_table_v1(dev);
+	}
+
+	ret = _of_add_opp_table_v2(dev, opp_np);
+	of_node_put(opp_np);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
+
+/* CPU device specific helpers */
+
+/**
+ * dev_pm_opp_of_cpumask_remove_table() - Removes OPP table for @cpumask
+ * @cpumask:	cpumask for which OPP table needs to be removed
+ *
+ * This removes the OPP tables for CPUs present in the @cpumask.
+ * This should be used only to remove static entries created from DT.
+ */
+void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask)
+{
+	_dev_pm_opp_cpumask_remove_table(cpumask, true);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table);
+
+/**
+ * dev_pm_opp_of_cpumask_add_table() - Adds OPP table for @cpumask
+ * @cpumask:	cpumask for which OPP table needs to be added.
+ *
+ * This adds the OPP tables for CPUs present in the @cpumask.
+ */
+int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask)
+{
+	struct device *cpu_dev;
+	int cpu, ret = 0;
+
+	WARN_ON(cpumask_empty(cpumask));
+
+	for_each_cpu(cpu, cpumask) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__,
+			       cpu);
+			continue;
+		}
+
+		ret = dev_pm_opp_of_add_table(cpu_dev);
+		if (ret) {
+			/*
+			 * OPP may get registered dynamically, don't print error
+			 * message here.
+			 */
+			pr_debug("%s: couldn't find opp table for cpu:%d, %d\n",
+				 __func__, cpu, ret);
+
+			/* Free all other OPPs */
+			dev_pm_opp_of_cpumask_remove_table(cpumask);
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_add_table);
+
+/*
+ * Works only for OPP v2 bindings.
+ *
+ * Returns -ENOENT if operating-points-v2 bindings aren't supported.
+ */
+/**
+ * dev_pm_opp_of_get_sharing_cpus() - Get cpumask of CPUs sharing OPPs with
+ *				      @cpu_dev using operating-points-v2
+ *				      bindings.
+ *
+ * @cpu_dev:	CPU device for which we do this operation
+ * @cpumask:	cpumask to update with information of sharing CPUs
+ *
+ * This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev.
+ *
+ * Returns -ENOENT if operating-points-v2 isn't present for @cpu_dev.
+ */
+int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
+				   struct cpumask *cpumask)
+{
+	struct device_node *np, *tmp_np, *cpu_np;
+	int cpu, ret = 0;
+
+	/* Get OPP descriptor node */
+	np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
+	if (!np) {
+		dev_dbg(cpu_dev, "%s: Couldn't find opp node.\n", __func__);
+		return -ENOENT;
+	}
+
+	cpumask_set_cpu(cpu_dev->id, cpumask);
+
+	/* OPPs are shared ? */
+	if (!of_property_read_bool(np, "opp-shared"))
+		goto put_cpu_node;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == cpu_dev->id)
+			continue;
+
+		cpu_np = of_cpu_device_node_get(cpu);
+		if (!cpu_np) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d node\n",
+				__func__, cpu);
+			ret = -ENOENT;
+			goto put_cpu_node;
+		}
+
+		/* Get OPP descriptor node */
+		tmp_np = _opp_of_get_opp_desc_node(cpu_np);
+		of_node_put(cpu_np);
+		if (!tmp_np) {
+			pr_err("%pOF: Couldn't find opp node\n", cpu_np);
+			ret = -ENOENT;
+			goto put_cpu_node;
+		}
+
+		/* CPUs are sharing opp node */
+		if (np == tmp_np)
+			cpumask_set_cpu(cpu, cpumask);
+
+		of_node_put(tmp_np);
+	}
+
+put_cpu_node:
+	of_node_put(np);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_sharing_cpus);

drivers/opp/opp.h

@@ -0,0 +1,228 @@
+/*
+ * Generic OPP Interface
+ *
+ * Copyright (C) 2009-2010 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.
+ */
+
+#ifndef __DRIVER_OPP_H__
+#define __DRIVER_OPP_H__
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/limits.h>
+#include <linux/pm_opp.h>
+#include <linux/notifier.h>
+
+struct clk;
+struct regulator;
+
+/* Lock to allow exclusive modification to the device and opp lists */
+extern struct mutex opp_table_lock;
+
+extern struct list_head opp_tables;
+
+/*
+ * Internal data structure organization with the OPP layer library is as
+ * follows:
+ * opp_tables (root)
+ *	|- device 1 (represents voltage domain 1)
+ *	|	|- opp 1 (availability, freq, voltage)
+ *	|	|- opp 2 ..
+ *	...	...
+ *	|	`- opp n ..
+ *	|- device 2 (represents the next voltage domain)
+ *	...
+ *	`- device m (represents mth voltage domain)
+ * device 1, 2.. are represented by opp_table structure while each opp
+ * is represented by the opp structure.
+ */
+
+/**
+ * struct dev_pm_opp - Generic OPP description structure
+ * @node:	opp table node. The nodes are maintained throughout the lifetime
+ *		of boot. It is expected only an optimal set of OPPs are
+ *		added to the library by the SoC framework.
+ *		IMPORTANT: the opp nodes should be maintained in increasing
+ *		order.
+ * @kref:	for reference count of the OPP.
+ * @available:	true/false - marks if this OPP as available or not
+ * @dynamic:	not-created from static DT entries.
+ * @turbo:	true if turbo (boost) OPP
+ * @suspend:	true if suspend OPP
+ * @pstate: Device's power domain's performance state.
+ * @rate:	Frequency in hertz
+ * @supplies:	Power supplies voltage/current values
+ * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
+ *		frequency from any other OPP's frequency.
+ * @opp_table:	points back to the opp_table struct this opp belongs to
+ * @np:		OPP's device node.
+ * @dentry:	debugfs dentry pointer (per opp)
+ *
+ * This structure stores the OPP information for a given device.
+ */
+struct dev_pm_opp {
+	struct list_head node;
+	struct kref kref;
+
+	bool available;
+	bool dynamic;
+	bool turbo;
+	bool suspend;
+	unsigned int pstate;
+	unsigned long rate;
+
+	struct dev_pm_opp_supply *supplies;
+
+	unsigned long clock_latency_ns;
+
+	struct opp_table *opp_table;
+
+	struct device_node *np;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *dentry;
+#endif
+};
+
+/**
+ * struct opp_device - devices managed by 'struct opp_table'
+ * @node:	list node
+ * @dev:	device to which the struct object belongs
+ * @dentry:	debugfs dentry pointer (per device)
+ *
+ * This is an internal data structure maintaining the devices that are managed
+ * by 'struct opp_table'.
+ */
+struct opp_device {
+	struct list_head node;
+	const struct device *dev;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *dentry;
+#endif
+};
+
+enum opp_table_access {
+	OPP_TABLE_ACCESS_UNKNOWN = 0,
+	OPP_TABLE_ACCESS_EXCLUSIVE = 1,
+	OPP_TABLE_ACCESS_SHARED = 2,
+};
+
+/**
+ * struct opp_table - Device opp structure
+ * @node:	table node - contains the devices with OPPs that
+ *		have been registered. Nodes once added are not modified in this
+ *		table.
+ * @head:	notifier head to notify the OPP availability changes.
+ * @dev_list:	list of devices that share these OPPs
+ * @opp_list:	table of opps
+ * @kref:	for reference count of the table.
+ * @lock:	mutex protecting the opp_list.
+ * @np:		struct device_node pointer for opp's DT node.
+ * @clock_latency_ns_max: Max clock latency in nanoseconds.
+ * @shared_opp: OPP is shared between multiple devices.
+ * @suspend_opp: Pointer to OPP to be used during device suspend.
+ * @supported_hw: Array of version number to support.
+ * @supported_hw_count: Number of elements in supported_hw array.
+ * @prop_name: A name to postfix to many DT properties, while parsing them.
+ * @clk: Device's clock handle
+ * @regulators: Supply regulators
+ * @regulator_count: Number of power supply regulators
+ * @genpd_performance_state: Device's power domain support performance state.
+ * @set_opp: Platform specific set_opp callback
+ * @set_opp_data: Data to be passed to set_opp callback
+ * @get_pstate: Platform specific get_pstate callback
+ * @dentry:	debugfs dentry pointer of the real device directory (not links).
+ * @dentry_name: Name of the real dentry.
+ *
+ * @voltage_tolerance_v1: In percentage, for v1 bindings only.
+ *
+ * This is an internal data structure maintaining the link to opps attached to
+ * a device. This structure is not meant to be shared to users as it is
+ * meant for book keeping and private to OPP library.
+ */
+struct opp_table {
+	struct list_head node;
+
+	struct blocking_notifier_head head;
+	struct list_head dev_list;
+	struct list_head opp_list;
+	struct kref kref;
+	struct mutex lock;
+
+	struct device_node *np;
+	unsigned long clock_latency_ns_max;
+
+	/* For backward compatibility with v1 bindings */
+	unsigned int voltage_tolerance_v1;
+
+	enum opp_table_access shared_opp;
+	struct dev_pm_opp *suspend_opp;
+
+	unsigned int *supported_hw;
+	unsigned int supported_hw_count;
+	const char *prop_name;
+	struct clk *clk;
+	struct regulator **regulators;
+	unsigned int regulator_count;
+	bool genpd_performance_state;
+
+	int (*set_opp)(struct dev_pm_set_opp_data *data);
+	struct dev_pm_set_opp_data *set_opp_data;
+	int (*get_pstate)(struct device *dev, unsigned long rate);
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *dentry;
+	char dentry_name[NAME_MAX];
+#endif
+};
+
+/* Routines internal to opp core */
+void _get_opp_table_kref(struct opp_table *opp_table);
+struct opp_table *_find_opp_table(struct device *dev);
+struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
+void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev, bool remove_all);
+void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all);
+struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table);
+void _opp_free(struct dev_pm_opp *opp);
+int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
+int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic);
+void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of);
+struct opp_table *_add_opp_table(struct device *dev);
+
+#ifdef CONFIG_OF
+void _of_init_opp_table(struct opp_table *opp_table, struct device *dev);
+#else
+static inline void _of_init_opp_table(struct opp_table *opp_table, struct device *dev) {}
+#endif
+
+#ifdef CONFIG_DEBUG_FS
+void opp_debug_remove_one(struct dev_pm_opp *opp);
+int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table);
+int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table);
+void opp_debug_unregister(struct opp_device *opp_dev, struct opp_table *opp_table);
+#else
+static inline void opp_debug_remove_one(struct dev_pm_opp *opp) {}
+
+static inline int opp_debug_create_one(struct dev_pm_opp *opp,
+				       struct opp_table *opp_table)
+{ return 0; }
+static inline int opp_debug_register(struct opp_device *opp_dev,
+				     struct opp_table *opp_table)
+{ return 0; }
+
+static inline void opp_debug_unregister(struct opp_device *opp_dev,
+					struct opp_table *opp_table)
+{ }
+#endif		/* DEBUG_FS */
+
+#endif		/* __DRIVER_OPP_H__ */

include/linux/pm_opp.h

@@ -124,7 +124,9 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table);
 struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name);
 void dev_pm_opp_put_clkname(struct opp_table *opp_table);
 struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data));
-void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table);
+void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table);
+struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev, int (*get_pstate)(struct device *dev, unsigned long rate));
+void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table);
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
 int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask);
 int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
@@ -243,7 +245,15 @@ static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device
 	return ERR_PTR(-ENOTSUPP);
 }
 
-static inline void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table) {}
+static inline void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) {}
+
+static inline struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev,
+		int (*get_pstate)(struct device *dev, unsigned long rate))
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+
+static inline void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table) {}
 
 static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {

kernel/power/Kconfig

@@ -259,20 +259,6 @@ config APM_EMULATION
 	  anything, try disabling/enabling this option (or disabling/enabling
 	  APM in your BIOS).
 
-config PM_OPP
-	bool
-	select SRCU
-	---help---
-	  SOCs have a standard set of tuples consisting of frequency and
-	  voltage pairs that the device will support per voltage domain. This
-	  is called Operating Performance Point or OPP. The actual definitions
-	  of OPP varies over silicon within the same family of devices.
-
-	  OPP layer organizes the data internally using device pointers
-	  representing individual voltage domains and provides SOC
-	  implementations a ready to use framework to manage OPPs.
-	  For more information, read <file:Documentation/power/opp.txt>
-
 config PM_CLK
 	def_bool y
 	depends on PM && HAVE_CLK

kernel/sched/cpufreq_schedutil.c

@@ -282,8 +282,12 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 		 * Do not reduce the frequency if the CPU has not been idle
 		 * recently, as the reduction is likely to be premature then.
 		 */
-		if (busy && next_f < sg_policy->next_freq)
+		if (busy && next_f < sg_policy->next_freq) {
 			next_f = sg_policy->next_freq;
+
+			/* Reset cached freq as next_freq has changed */
+			sg_policy->cached_raw_freq = 0;
+		}
 	}
 	sugov_update_commit(sg_policy, time, next_f);
 }