Merge branch 'pm-opp'

* pm-opp:
  PM / OPP: passing NULL to PTR_ERR()
  PM / OPP: Move cpu specific code to opp/cpu.c
  PM / OPP: Move opp core to its own directory
  PM / OPP: Prefix exported opp routines with dev_pm_opp_
  PM / OPP: Rename opp init/free table routines
  PM / OPP: reuse of_parse_phandle()

13 files changed, 460 insertions, 466 deletions

diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index f94a6ccfe787..5998c53280f5 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -1,7 +1,7 @@
 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.o
+obj-$(CONFIG_PM_OPP)	+= opp/
 obj-$(CONFIG_PM_GENERIC_DOMAINS)	+=  domain.o domain_governor.o
 obj-$(CONFIG_HAVE_CLK)	+= clock_ops.o
 
diff --git a/drivers/base/power/opp/Makefile b/drivers/base/power/opp/Makefile
new file mode 100644
index 000000000000..33c1e18c41a4
--- /dev/null
+++ b/drivers/base/power/opp/Makefile
@@ -0,0 +1,2 @@
+ccflags-$(CONFIG_DEBUG_DRIVER)	:= -DDEBUG
+obj-y				+= core.o cpu.o
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp/core.c
index 7ae7cd990fbf..d5c1149ff123 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp/core.c
@@ -11,131 +11,14 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/cpu.h>
-#include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/device.h>
-#include <linux/list.h>
-#include <linux/rculist.h>
-#include <linux/rcupdate.h>
-#include <linux/pm_opp.h>
 #include <linux/of.h>
 #include <linux/export.h>
 
-/*
- * Internal data structure organization with the OPP layer library is as
- * follows:
- * dev_opp_list (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 dev_opp structure while each opp
- * is represented by the opp structure.
- */
-
-/**
- * struct dev_pm_opp - Generic OPP description structure
- * @node:	opp list 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.
- *		RCU usage: opp list is traversed with RCU locks. node
- *		modification is possible realtime, hence the modifications
- *		are protected by the dev_opp_list_lock for integrity.
- *		IMPORTANT: the opp nodes should be maintained in increasing
- *		order.
- * @dynamic:	not-created from static DT entries.
- * @available:	true/false - marks if this OPP as available or not
- * @turbo:	true if turbo (boost) OPP
- * @rate:	Frequency in hertz
- * @u_volt:	Target voltage in microvolts corresponding to this OPP
- * @u_volt_min:	Minimum voltage in microvolts corresponding to this OPP
- * @u_volt_max:	Maximum voltage in microvolts corresponding to this OPP
- * @u_amp:	Maximum current drawn by the device in microamperes
- * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
- *		frequency from any other OPP's frequency.
- * @dev_opp:	points back to the device_opp struct this opp belongs to
- * @rcu_head:	RCU callback head used for deferred freeing
- * @np:		OPP's device node.
- *
- * This structure stores the OPP information for a given device.
- */
-struct dev_pm_opp {
-	struct list_head node;
-
-	bool available;
-	bool dynamic;
-	bool turbo;
-	unsigned long rate;
-
-	unsigned long u_volt;
-	unsigned long u_volt_min;
-	unsigned long u_volt_max;
-	unsigned long u_amp;
-	unsigned long clock_latency_ns;
-
-	struct device_opp *dev_opp;
-	struct rcu_head rcu_head;
-
-	struct device_node *np;
-};
-
-/**
- * struct device_list_opp - devices managed by 'struct device_opp'
- * @node:	list node
- * @dev:	device to which the struct object belongs
- * @rcu_head:	RCU callback head used for deferred freeing
- *
- * This is an internal data structure maintaining the list of devices that are
- * managed by 'struct device_opp'.
- */
-struct device_list_opp {
-	struct list_head node;
-	const struct device *dev;
-	struct rcu_head rcu_head;
-};
-
-/**
- * struct device_opp - Device opp structure
- * @node:	list node - contains the devices with OPPs that
- *		have been registered. Nodes once added are not modified in this
- *		list.
- *		RCU usage: nodes are not modified in the list of device_opp,
- *		however addition is possible and is secured by dev_opp_list_lock
- * @srcu_head:	notifier head to notify the OPP availability changes.
- * @rcu_head:	RCU callback head used for deferred freeing
- * @dev_list:	list of devices that share these OPPs
- * @opp_list:	list of opps
- * @np:		struct device_node pointer for opp's DT node.
- * @shared_opp: OPP is shared between multiple devices.
- *
- * 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.
- *
- * Because the opp structures can be used from both rcu and srcu readers, we
- * need to wait for the grace period of both of them before freeing any
- * resources. And so we have used kfree_rcu() from within call_srcu() handlers.
- */
-struct device_opp {
-	struct list_head node;
-
-	struct srcu_notifier_head srcu_head;
-	struct rcu_head rcu_head;
-	struct list_head dev_list;
-	struct list_head opp_list;
-
-	struct device_node *np;
-	unsigned long clock_latency_ns_max;
-	bool shared_opp;
-	struct dev_pm_opp *suspend_opp;
-};
+#include "opp.h"
 
 /*
  * The root of the list of all devices. All device_opp structures branch off
@@ -200,7 +83,7 @@ static struct device_opp *_managed_opp(const struct device_node *np)
  * is a RCU protected pointer. This means that device_opp is valid as long
  * as we are under RCU lock.
  */
-static struct device_opp *_find_device_opp(struct device *dev)
+struct device_opp *_find_device_opp(struct device *dev)
 {
 	struct device_opp *dev_opp;
 
@@ -579,8 +462,8 @@ static void _remove_list_dev(struct device_list_opp *list_dev,
 		  _kfree_list_dev_rcu);
 }
 
-static struct device_list_opp *_add_list_dev(const struct device *dev,
-					     struct device_opp *dev_opp)
+struct device_list_opp *_add_list_dev(const struct device *dev,
+				      struct device_opp *dev_opp)
 {
 	struct device_list_opp *list_dev;
 
@@ -828,8 +711,8 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
  * The opp is made available by default and it can be controlled using
  * dev_pm_opp_enable/disable functions and may be removed by dev_pm_opp_remove.
  *
- * NOTE: "dynamic" parameter impacts OPPs added by the of_init_opp_table and
- * freed by of_free_opp_table.
+ * NOTE: "dynamic" parameter impacts OPPs added by the dev_pm_opp_of_add_table
+ * and freed by dev_pm_opp_of_remove_table.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -1220,7 +1103,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
 
 #ifdef CONFIG_OF
 /**
- * of_free_opp_table() - Free OPP table entries created from static DT entries
+ * dev_pm_opp_of_remove_table() - Free OPP table entries created from static DT
+ *				  entries
  * @dev:	device pointer used to lookup device OPPs.
  *
  * Free OPPs created using static entries present in DT.
@@ -1231,7 +1115,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
  */
-void of_free_opp_table(struct device *dev)
+void dev_pm_opp_of_remove_table(struct device *dev)
 {
 	struct device_opp *dev_opp;
 	struct dev_pm_opp *opp, *tmp;
@@ -1266,91 +1150,34 @@ void of_free_opp_table(struct device *dev)
 unlock:
 	mutex_unlock(&dev_opp_list_lock);
 }
-EXPORT_SYMBOL_GPL(of_free_opp_table);
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 
-void of_cpumask_free_opp_table(cpumask_var_t cpumask)
+/* Returns opp descriptor node for a device, caller must do of_node_put() */
+struct device_node *_of_get_opp_desc_node(struct device *dev)
 {
-	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;
-		}
-
-		of_free_opp_table(cpu_dev);
-	}
-}
-EXPORT_SYMBOL_GPL(of_cpumask_free_opp_table);
-
-/* Returns opp descriptor node from its phandle. Caller must do of_node_put() */
-static struct device_node *
-_of_get_opp_desc_node_from_prop(struct device *dev, const struct property *prop)
-{
-	struct device_node *opp_np;
-
-	opp_np = of_find_node_by_phandle(be32_to_cpup(prop->value));
-	if (!opp_np) {
-		dev_err(dev, "%s: Prop: %s contains invalid opp desc phandle\n",
-			__func__, prop->name);
-		return ERR_PTR(-EINVAL);
-	}
-
-	return opp_np;
-}
-
-/* Returns opp descriptor node for a device. Caller must do of_node_put() */
-static struct device_node *_of_get_opp_desc_node(struct device *dev)
-{
-	const struct property *prop;
-
-	prop = of_find_property(dev->of_node, "operating-points-v2", NULL);
-	if (!prop)
-		return ERR_PTR(-ENODEV);
-	if (!prop->value)
-		return ERR_PTR(-ENODATA);
-
 	/*
 	 * TODO: Support for multiple OPP tables.
 	 *
 	 * There should be only ONE phandle present in "operating-points-v2"
 	 * property.
 	 */
-	if (prop->length != sizeof(__be32)) {
-		dev_err(dev, "%s: Invalid opp desc phandle\n", __func__);
-		return ERR_PTR(-EINVAL);
-	}
 
-	return _of_get_opp_desc_node_from_prop(dev, prop);
+	return of_parse_phandle(dev->of_node, "operating-points-v2", 0);
 }
 
 /* Initializes OPP tables based on new bindings */
-static int _of_init_opp_table_v2(struct device *dev,
-				 const struct property *prop)
+static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 {
-	struct device_node *opp_np, *np;
+	struct device_node *np;
 	struct device_opp *dev_opp;
 	int ret = 0, count = 0;
 
-	if (!prop->value)
-		return -ENODATA;
-
-	/* Get opp node */
-	opp_np = _of_get_opp_desc_node_from_prop(dev, prop);
-	if (IS_ERR(opp_np))
-		return PTR_ERR(opp_np);
-
 	dev_opp = _managed_opp(opp_np);
 	if (dev_opp) {
 		/* OPPs are already managed */
 		if (!_add_list_dev(dev, dev_opp))
 			ret = -ENOMEM;
-		goto put_opp_np;
+		return ret;
 	}
 
 	/* We have opp-list node now, iterate over it and add OPPs */
@@ -1366,10 +1193,8 @@ static int _of_init_opp_table_v2(struct device *dev,
 	}
 
 	/* There should be one of more OPP defined */
-	if (WARN_ON(!count)) {
-		ret = -ENOENT;
-		goto put_opp_np;
-	}
+	if (WARN_ON(!count))
+		return -ENOENT;
 
 	dev_opp = _find_device_opp(dev);
 	if (WARN_ON(IS_ERR(dev_opp))) {
@@ -1380,19 +1205,16 @@ static int _of_init_opp_table_v2(struct device *dev,
 	dev_opp->np = opp_np;
 	dev_opp->shared_opp = of_property_read_bool(opp_np, "opp-shared");
 
-	of_node_put(opp_np);
 	return 0;
 
 free_table:
-	of_free_opp_table(dev);
-put_opp_np:
-	of_node_put(opp_np);
+	dev_pm_opp_of_remove_table(dev);
 
 	return ret;
 }
 
 /* Initializes OPP tables based on old-deprecated bindings */
-static int _of_init_opp_table_v1(struct device *dev)
+static int _of_add_opp_table_v1(struct device *dev)
 {
 	const struct property *prop;
 	const __be32 *val;
@@ -1429,7 +1251,7 @@ static int _of_init_opp_table_v1(struct device *dev)
 }
 
 /**
- * of_init_opp_table() - Initialize opp table from device tree
+ * dev_pm_opp_of_add_table() - Initialize opp table from device tree
  * @dev:	device pointer used to lookup device OPPs.
  *
  * Register the initial OPP table with the OPP library for given device.
@@ -1451,153 +1273,28 @@ static int _of_init_opp_table_v1(struct device *dev)
  * -ENODATA	when empty 'operating-points' property is found
  * -EINVAL	when invalid entries are found in opp-v2 table
  */
-int of_init_opp_table(struct device *dev)
+int dev_pm_opp_of_add_table(struct device *dev)
 {
-	const struct property *prop;
+	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.
 	 */
-	prop = of_find_property(dev->of_node, "operating-points-v2", NULL);
-	if (!prop) {
+	opp_np = _of_get_opp_desc_node(dev);
+	if (!opp_np) {
 		/*
 		 * Try old-deprecated bindings for backward compatibility with
 		 * older dtbs.
 		 */
-		return _of_init_opp_table_v1(dev);
-	}
-
-	return _of_init_opp_table_v2(dev, prop);
-}
-EXPORT_SYMBOL_GPL(of_init_opp_table);
-
-int of_cpumask_init_opp_table(cpumask_var_t 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 = of_init_opp_table(cpu_dev);
-		if (ret) {
-			pr_err("%s: couldn't find opp table for cpu:%d, %d\n",
-			       __func__, cpu, ret);
-
-			/* Free all other OPPs */
-			of_cpumask_free_opp_table(cpumask);
-			break;
-		}
+		return _of_add_opp_table_v1(dev);
 	}
 
-	return ret;
-}
-EXPORT_SYMBOL_GPL(of_cpumask_init_opp_table);
-
-/* Required only for V1 bindings, as v2 can manage it from DT itself */
-int set_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask)
-{
-	struct device_list_opp *list_dev;
-	struct device_opp *dev_opp;
-	struct device *dev;
-	int cpu, ret = 0;
-
-	rcu_read_lock();
-
-	dev_opp = _find_device_opp(cpu_dev);
-	if (IS_ERR(dev_opp)) {
-		ret = -EINVAL;
-		goto out_rcu_read_unlock;
-	}
-
-	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;
-		}
-
-		list_dev = _add_list_dev(dev, dev_opp);
-		if (!list_dev) {
-			dev_err(dev, "%s: failed to add list-dev for cpu%d device\n",
-				__func__, cpu);
-			continue;
-		}
-	}
-out_rcu_read_unlock:
-	rcu_read_unlock();
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(set_cpus_sharing_opps);
-
-/*
- * Works only for OPP v2 bindings.
- *
- * cpumask should be already set to mask of cpu_dev->id.
- * Returns -ENOENT if operating-points-v2 bindings aren't supported.
- */
-int of_get_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask)
-{
-	struct device_node *np, *tmp_np;
-	struct device *tcpu_dev;
-	int cpu, ret = 0;
-
-	/* Get OPP descriptor node */
-	np = _of_get_opp_desc_node(cpu_dev);
-	if (IS_ERR(np)) {
-		dev_dbg(cpu_dev, "%s: Couldn't find opp node: %ld\n", __func__,
-			PTR_ERR(np));
-		return -ENOENT;
-	}
-
-	/* 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;
-
-		tcpu_dev = get_cpu_device(cpu);
-		if (!tcpu_dev) {
-			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
-				__func__, cpu);
-			ret = -ENODEV;
-			goto put_cpu_node;
-		}
-
-		/* Get OPP descriptor node */
-		tmp_np = _of_get_opp_desc_node(tcpu_dev);
-		if (IS_ERR(tmp_np)) {
-			dev_err(tcpu_dev, "%s: Couldn't find opp node: %ld\n",
-				__func__, PTR_ERR(tmp_np));
-			ret = PTR_ERR(tmp_np);
-			goto put_cpu_node;
-		}
-
-		/* CPUs are sharing opp node */
-		if (np == tmp_np)
-			cpumask_set_cpu(cpu, cpumask);
-
-		of_node_put(tmp_np);
-	}
+	ret = _of_add_opp_table_v2(dev, opp_np);
+	of_node_put(opp_np);
 
-put_cpu_node:
-	of_node_put(np);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(of_get_cpus_sharing_opps);
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
 #endif
diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c
new file mode 100644
index 000000000000..7654c5606307
--- /dev/null
+++ b/drivers/base/power/opp/cpu.c
@@ -0,0 +1,267 @@
+/*
+ * 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.
+ */
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/of.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 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 = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC);
+	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;
+
+		/* Is Boost/turbo opp ? */
+		if (dev_pm_opp_is_turbo(opp))
+			freq_table[i].flags = CPUFREQ_BOOST_FREQ;
+	}
+
+	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);
+#endif	/* CONFIG_CPU_FREQ */
+
+/* Required only for V1 bindings, as v2 can manage it from DT itself */
+int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask)
+{
+	struct device_list_opp *list_dev;
+	struct device_opp *dev_opp;
+	struct device *dev;
+	int cpu, ret = 0;
+
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(cpu_dev);
+	if (IS_ERR(dev_opp)) {
+		ret = -EINVAL;
+		goto out_rcu_read_unlock;
+	}
+
+	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;
+		}
+
+		list_dev = _add_list_dev(dev, dev_opp);
+		if (!list_dev) {
+			dev_err(dev, "%s: failed to add list-dev for cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
+	}
+out_rcu_read_unlock:
+	rcu_read_unlock();
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus);
+
+#ifdef CONFIG_OF
+void dev_pm_opp_of_cpumask_remove_table(cpumask_var_t cpumask)
+{
+	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;
+		}
+
+		dev_pm_opp_of_remove_table(cpu_dev);
+	}
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table);
+
+int dev_pm_opp_of_cpumask_add_table(cpumask_var_t 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) {
+			pr_err("%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.
+ *
+ * cpumask should be already set to mask of cpu_dev->id.
+ * Returns -ENOENT if operating-points-v2 bindings aren't supported.
+ */
+int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask)
+{
+	struct device_node *np, *tmp_np;
+	struct device *tcpu_dev;
+	int cpu, ret = 0;
+
+	/* Get OPP descriptor node */
+	np = _of_get_opp_desc_node(cpu_dev);
+	if (!np) {
+		dev_dbg(cpu_dev, "%s: Couldn't find cpu_dev node.\n", __func__);
+		return -ENOENT;
+	}
+
+	/* 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;
+
+		tcpu_dev = get_cpu_device(cpu);
+		if (!tcpu_dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			ret = -ENODEV;
+			goto put_cpu_node;
+		}
+
+		/* Get OPP descriptor node */
+		tmp_np = _of_get_opp_desc_node(tcpu_dev);
+		if (!tmp_np) {
+			dev_err(tcpu_dev, "%s: Couldn't find tcpu_dev node.\n",
+				__func__);
+			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);
+#endif
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
new file mode 100644
index 000000000000..dcb38f78dae4
--- /dev/null
+++ b/drivers/base/power/opp/opp.h
@@ -0,0 +1,143 @@
+/*
+ * 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/list.h>
+#include <linux/pm_opp.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+
+/*
+ * Internal data structure organization with the OPP layer library is as
+ * follows:
+ * dev_opp_list (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 dev_opp structure while each opp
+ * is represented by the opp structure.
+ */
+
+/**
+ * struct dev_pm_opp - Generic OPP description structure
+ * @node:	opp list 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.
+ *		RCU usage: opp list is traversed with RCU locks. node
+ *		modification is possible realtime, hence the modifications
+ *		are protected by the dev_opp_list_lock for integrity.
+ *		IMPORTANT: the opp nodes should be maintained in increasing
+ *		order.
+ * @dynamic:	not-created from static DT entries.
+ * @available:	true/false - marks if this OPP as available or not
+ * @turbo:	true if turbo (boost) OPP
+ * @rate:	Frequency in hertz
+ * @u_volt:	Target voltage in microvolts corresponding to this OPP
+ * @u_volt_min:	Minimum voltage in microvolts corresponding to this OPP
+ * @u_volt_max:	Maximum voltage in microvolts corresponding to this OPP
+ * @u_amp:	Maximum current drawn by the device in microamperes
+ * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
+ *		frequency from any other OPP's frequency.
+ * @dev_opp:	points back to the device_opp struct this opp belongs to
+ * @rcu_head:	RCU callback head used for deferred freeing
+ * @np:		OPP's device node.
+ *
+ * This structure stores the OPP information for a given device.
+ */
+struct dev_pm_opp {
+	struct list_head node;
+
+	bool available;
+	bool dynamic;
+	bool turbo;
+	unsigned long rate;
+
+	unsigned long u_volt;
+	unsigned long u_volt_min;
+	unsigned long u_volt_max;
+	unsigned long u_amp;
+	unsigned long clock_latency_ns;
+
+	struct device_opp *dev_opp;
+	struct rcu_head rcu_head;
+
+	struct device_node *np;
+};
+
+/**
+ * struct device_list_opp - devices managed by 'struct device_opp'
+ * @node:	list node
+ * @dev:	device to which the struct object belongs
+ * @rcu_head:	RCU callback head used for deferred freeing
+ *
+ * This is an internal data structure maintaining the list of devices that are
+ * managed by 'struct device_opp'.
+ */
+struct device_list_opp {
+	struct list_head node;
+	const struct device *dev;
+	struct rcu_head rcu_head;
+};
+
+/**
+ * struct device_opp - Device opp structure
+ * @node:	list node - contains the devices with OPPs that
+ *		have been registered. Nodes once added are not modified in this
+ *		list.
+ *		RCU usage: nodes are not modified in the list of device_opp,
+ *		however addition is possible and is secured by dev_opp_list_lock
+ * @srcu_head:	notifier head to notify the OPP availability changes.
+ * @rcu_head:	RCU callback head used for deferred freeing
+ * @dev_list:	list of devices that share these OPPs
+ * @opp_list:	list of opps
+ * @np:		struct device_node pointer for opp's DT node.
+ * @shared_opp: OPP is shared between multiple devices.
+ *
+ * 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.
+ *
+ * Because the opp structures can be used from both rcu and srcu readers, we
+ * need to wait for the grace period of both of them before freeing any
+ * resources. And so we have used kfree_rcu() from within call_srcu() handlers.
+ */
+struct device_opp {
+	struct list_head node;
+
+	struct srcu_notifier_head srcu_head;
+	struct rcu_head rcu_head;
+	struct list_head dev_list;
+	struct list_head opp_list;
+
+	struct device_node *np;
+	unsigned long clock_latency_ns_max;
+	bool shared_opp;
+	struct dev_pm_opp *suspend_opp;
+};
+
+/* Routines internal to opp core */
+struct device_opp *_find_device_opp(struct device *dev);
+struct device_list_opp *_add_list_dev(const struct device *dev,
+				      struct device_opp *dev_opp);
+struct device_node *_of_get_opp_desc_node(struct device *dev);
+
+#endif		/* __DRIVER_OPP_H__ */
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 47a7ebbcf998..d11309c487d0 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -1,6 +1,5 @@
 # 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/arm_big_little.h b/drivers/cpufreq/arm_big_little.h
index a211f7db9d32..b88889d9387e 100644
--- a/drivers/cpufreq/arm_big_little.h
+++ b/drivers/cpufreq/arm_big_little.h
@@ -28,7 +28,7 @@ struct cpufreq_arm_bL_ops {
 
 	/*
 	 * This must set opp table for cpu_dev in a similar way as done by
-	 * of_init_opp_table().
+	 * dev_pm_opp_of_add_table().
 	 */
 	int (*init_opp_table)(struct device *cpu_dev);
 
diff --git a/drivers/cpufreq/arm_big_little_dt.c b/drivers/cpufreq/arm_big_little_dt.c
index 36d91dba2965..16ddeefe9443 100644
--- a/drivers/cpufreq/arm_big_little_dt.c
+++ b/drivers/cpufreq/arm_big_little_dt.c
@@ -54,7 +54,7 @@ static int dt_init_opp_table(struct device *cpu_dev)
 		return -ENOENT;
 	}
 
-	ret = of_init_opp_table(cpu_dev);
+	ret = dev_pm_opp_of_add_table(cpu_dev);
 	of_node_put(np);
 
 	return ret;
@@ -82,7 +82,7 @@ static struct cpufreq_arm_bL_ops dt_bL_ops = {
 	.name	= "dt-bl",
 	.get_transition_latency = dt_get_transition_latency,
 	.init_opp_table = dt_init_opp_table,
-	.free_opp_table = of_free_opp_table,
+	.free_opp_table = dev_pm_opp_of_remove_table,
 };
 
 static int generic_bL_probe(struct platform_device *pdev)
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 7c0d70e2a861..90d64081ddb3 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -216,7 +216,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	}
 
 	/* Get OPP-sharing information from "operating-points-v2" bindings */
-	ret = of_get_cpus_sharing_opps(cpu_dev, policy->cpus);
+	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, policy->cpus);
 	if (ret) {
 		/*
 		 * operating-points-v2 not supported, fallback to old method of
@@ -238,7 +238,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	 *
 	 * OPPs might be populated at runtime, don't check for error here
 	 */
-	of_cpumask_init_opp_table(policy->cpus);
+	dev_pm_opp_of_cpumask_add_table(policy->cpus);
 
 	/*
 	 * But we need OPP table to function so if it is not there let's
@@ -261,7 +261,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		 * OPP tables are initialized only for policy->cpu, do it for
 		 * others as well.
 		 */
-		ret = set_cpus_sharing_opps(cpu_dev, policy->cpus);
+		ret = dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
 		if (ret)
 			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
 				__func__, ret);
@@ -368,7 +368,7 @@ out_free_cpufreq_table:
 out_free_priv:
 	kfree(priv);
 out_free_opp:
-	of_cpumask_free_opp_table(policy->cpus);
+	dev_pm_opp_of_cpumask_remove_table(policy->cpus);
 out_node_put:
 	of_node_put(np);
 out_put_reg_clk:
@@ -385,7 +385,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 
 	cpufreq_cooling_unregister(priv->cdev);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
-	of_cpumask_free_opp_table(policy->related_cpus);
+	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
 	clk_put(policy->clk);
 	if (!IS_ERR(priv->cpu_reg))
 		regulator_put(priv->cpu_reg);
diff --git a/drivers/cpufreq/cpufreq_opp.c b/drivers/cpufreq/cpufreq_opp.c
deleted file mode 100644
index 0f5e6d5f6da0..000000000000
--- a/drivers/cpufreq/cpufreq_opp.c
+++ /dev/null
@@ -1,114 +0,0 @@
-/*
- * 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 = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC);
-	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;
-
-		/* Is Boost/turbo opp ? */
-		if (dev_pm_opp_is_turbo(opp))
-			freq_table[i].flags = CPUFREQ_BOOST_FREQ;
-	}
-
-	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/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index 21a90ed7f3d8..c0f3373706f4 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -360,7 +360,7 @@ static int exynos_cpufreq_probe(struct platform_device *pdev)
 		goto err_put_node;
 	}
 
-	ret = of_init_opp_table(dvfs_info->dev);
+	ret = dev_pm_opp_of_add_table(dvfs_info->dev);
 	if (ret) {
 		dev_err(dvfs_info->dev, "failed to init OPP table: %d\n", ret);
 		goto err_put_node;
@@ -424,7 +424,7 @@ static int exynos_cpufreq_probe(struct platform_device *pdev)
 err_free_table:
 	dev_pm_opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
 err_free_opp:
-	of_free_opp_table(dvfs_info->dev);
+	dev_pm_opp_of_remove_table(dvfs_info->dev);
 err_put_node:
 	of_node_put(np);
 	dev_err(&pdev->dev, "%s: failed initialization\n", __func__);
@@ -435,7 +435,7 @@ static int exynos_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&exynos_driver);
 	dev_pm_opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
-	of_free_opp_table(dvfs_info->dev);
+	dev_pm_opp_of_remove_table(dvfs_info->dev);
 	return 0;
 }
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 9b4a7bd04dea..ef1fa8145419 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -236,7 +236,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	 */
 	num = dev_pm_opp_get_opp_count(cpu_dev);
 	if (num < 0) {
-		ret = of_init_opp_table(cpu_dev);
+		ret = dev_pm_opp_of_add_table(cpu_dev);
 		if (ret < 0) {
 			dev_err(cpu_dev, "failed to init OPP table: %d\n", ret);
 			goto put_reg;
@@ -346,7 +346,7 @@ free_freq_table:
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 out_free_opp:
 	if (free_opp)
-		of_free_opp_table(cpu_dev);
+		dev_pm_opp_of_remove_table(cpu_dev);
 put_reg:
 	if (!IS_ERR(arm_reg))
 		regulator_put(arm_reg);
@@ -378,7 +378,7 @@ static int imx6q_cpufreq_remove(struct platform_device *pdev)
 	cpufreq_unregister_driver(&imx6q_cpufreq_driver);
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 	if (free_opp)
-		of_free_opp_table(cpu_dev);
+		dev_pm_opp_of_remove_table(cpu_dev);
 	regulator_put(arm_reg);
 	if (!IS_ERR(pu_reg))
 		regulator_put(pu_reg);
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index 49caed293a3b..83001dc5b646 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -344,7 +344,7 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
 	/* Both presence and absence of sram regulator are valid cases. */
 	sram_reg = regulator_get_exclusive(cpu_dev, "sram");
 
-	ret = of_init_opp_table(cpu_dev);
+	ret = dev_pm_opp_of_add_table(cpu_dev);
 	if (ret) {
 		pr_warn("no OPP table for cpu%d\n", cpu);
 		goto out_free_resources;
@@ -378,7 +378,7 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
 	return 0;
 
 out_free_opp_table:
-	of_free_opp_table(cpu_dev);
+	dev_pm_opp_of_remove_table(cpu_dev);
 
 out_free_resources:
 	if (!IS_ERR(proc_reg))
@@ -404,7 +404,7 @@ static void mtk_cpu_dvfs_info_release(struct mtk_cpu_dvfs_info *info)
 	if (!IS_ERR(info->inter_clk))
 		clk_put(info->inter_clk);
 
-	of_free_opp_table(info->cpu_dev);
+	dev_pm_opp_of_remove_table(info->cpu_dev);
 }
 
 static int mtk_cpufreq_init(struct cpufreq_policy *policy)