Merge branch 'pm-opp'

* pm-opp:
  PM / OPP: Drop unlikely before IS_ERR(_OR_NULL)
  PM / OPP: Fix static checker warning (broken 64bit big endian systems)
  PM / OPP: Free resources and properly return error on failure
  cpufreq-dt: make scaling_boost_freqs sysfs attr available when boost is enabled
  cpufreq: dt: Add support for turbo/boost mode
  cpufreq: dt: Add support for operating-points-v2 bindings
  cpufreq: Allow drivers to enable boost support after registering driver
  cpufreq: Update boost flag while initializing freq table from OPPs
  PM / OPP: add dev_pm_opp_is_turbo() helper
  PM / OPP: Add helpers for initializing CPU OPPs
  PM / OPP: Add support for opp-suspend
  PM / OPP: Add OPP sharing information to OPP library
  PM / OPP: Add clock-latency-ns support
  PM / OPP: Add support to parse "operating-points-v2" bindings
  PM / OPP: Break _opp_add_dynamic() into smaller functions
  PM / OPP: Allocate dev_opp from _add_device_opp()
  PM / OPP: Create _remove_device_opp() for freeing dev_opp
  PM / OPP: Relocate few routines
  PM / OPP: Create a directory for opp bindings
  PM / OPP: Update bindings to make opp-hz a 64 bit value

Documentation/devicetree/bindings/power/opp.txt → Documentation/devicetree/bindings/opp/opp.txt

@@ -88,7 +88,7 @@ This defines voltage-current-frequency combinations along with other related
 properties.
 
 Required properties:
-- opp-hz: Frequency in Hz
+- opp-hz: Frequency in Hz, expressed as a 64-bit big-endian integer.
 
 Optional properties:
 - opp-microvolt: voltage in micro Volts.
@@ -158,20 +158,20 @@ Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together.
 		opp-shared;
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
 		opp01 {
-			opp-hz = <1100000000>;
+			opp-hz = /bits/ 64 <1100000000>;
 			opp-microvolt = <980000 1000000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
 		opp02 {
-			opp-hz = <1200000000>;
+			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <1025000>;
 			clock-latency-ns = <290000>;
 			turbo-mode;
@@ -237,20 +237,20 @@ independently.
 		 */
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
 		opp01 {
-			opp-hz = <1100000000>;
+			opp-hz = /bits/ 64 <1100000000>;
 			opp-microvolt = <980000 1000000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
 		opp02 {
-			opp-hz = <1200000000>;
+			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <1025000>;
 			opp-microamp = <90000;
 			lock-latency-ns = <290000>;
@@ -313,20 +313,20 @@ DVFS state together.
 		opp-shared;
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>;
 			opp-microamp = <70000>;
 			clock-latency-ns = <300000>;
 			opp-suspend;
 		};
 		opp01 {
-			opp-hz = <1100000000>;
+			opp-hz = /bits/ 64 <1100000000>;
 			opp-microvolt = <980000 1000000 1010000>;
 			opp-microamp = <80000>;
 			clock-latency-ns = <310000>;
 		};
 		opp02 {
-			opp-hz = <1200000000>;
+			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <1025000>;
 			opp-microamp = <90000>;
 			clock-latency-ns = <290000>;
@@ -339,20 +339,20 @@ DVFS state together.
 		opp-shared;
 
 		opp10 {
-			opp-hz = <1300000000>;
+			opp-hz = /bits/ 64 <1300000000>;
 			opp-microvolt = <1045000 1050000 1055000>;
 			opp-microamp = <95000>;
 			clock-latency-ns = <400000>;
 			opp-suspend;
 		};
 		opp11 {
-			opp-hz = <1400000000>;
+			opp-hz = /bits/ 64 <1400000000>;
 			opp-microvolt = <1075000>;
 			opp-microamp = <100000>;
 			clock-latency-ns = <400000>;
 		};
 		opp12 {
-			opp-hz = <1500000000>;
+			opp-hz = /bits/ 64 <1500000000>;
 			opp-microvolt = <1010000 1100000 1110000>;
 			opp-microamp = <95000>;
 			clock-latency-ns = <400000>;
@@ -379,7 +379,7 @@ Example 4: Handling multiple regulators
 		opp-shared;
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000>, /* Supply 0 */
 					<960000>, /* Supply 1 */
 					<960000>; /* Supply 2 */
@@ -392,7 +392,7 @@ Example 4: Handling multiple regulators
 		/* OR */
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>, /* Supply 0 */
 					<960000 965000 975000>, /* Supply 1 */
 					<960000 965000 975000>; /* Supply 2 */
@@ -405,7 +405,7 @@ Example 4: Handling multiple regulators
 		/* OR */
 
 		opp00 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <970000 975000 985000>, /* Supply 0 */
 					<960000 965000 975000>, /* Supply 1 */
 					<960000 965000 975000>; /* Supply 2 */
@@ -437,12 +437,12 @@ Example 5: Multiple OPP tables
 		opp-shared;
 
 		opp00 {
-			opp-hz = <600000000>;
+			opp-hz = /bits/ 64 <600000000>;
 			...
 		};
 
 		opp01 {
-			opp-hz = <800000000>;
+			opp-hz = /bits/ 64 <800000000>;
 			...
 		};
 	};
@@ -453,12 +453,12 @@ Example 5: Multiple OPP tables
 		opp-shared;
 
 		opp10 {
-			opp-hz = <1000000000>;
+			opp-hz = /bits/ 64 <1000000000>;
 			...
 		};
 
 		opp11 {
-			opp-hz = <1100000000>;
+			opp-hz = /bits/ 64 <1100000000>;
 			...
 		};
 	};

drivers/base/power/opp.c

@@ -11,6 +11,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -51,10 +52,17 @@
  *		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:	Nominal voltage in microvolts corresponding to this OPP
+ * @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.
  */
@@ -63,11 +71,34 @@ struct dev_pm_opp {
 
 	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;
 };
 
 /**
@@ -77,10 +108,12 @@ struct dev_pm_opp {
  *		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
- * @dev:	device pointer
  * @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
@@ -93,10 +126,15 @@ struct dev_pm_opp {
 struct device_opp {
 	struct list_head node;
 
-	struct device *dev;
 	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;
 };
 
 /*
@@ -116,6 +154,38 @@ do {									\
 			   "dev_opp_list_lock protection");		\
 } while (0)
 
+static struct device_list_opp *_find_list_dev(const struct device *dev,
+					      struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	list_for_each_entry(list_dev, &dev_opp->dev_list, node)
+		if (list_dev->dev == dev)
+			return list_dev;
+
+	return NULL;
+}
+
+static struct device_opp *_managed_opp(const struct device_node *np)
+{
+	struct device_opp *dev_opp;
+
+	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node) {
+		if (dev_opp->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.
+			 */
+			return dev_opp->shared_opp ? dev_opp : NULL;
+		}
+	}
+
+	return NULL;
+}
+
 /**
  * _find_device_opp() - find device_opp struct using device pointer
  * @dev:	device pointer used to lookup device OPPs
@@ -132,21 +202,18 @@ do {									\
  */
 static struct device_opp *_find_device_opp(struct device *dev)
 {
-	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+	struct device_opp *dev_opp;
 
-	if (unlikely(IS_ERR_OR_NULL(dev))) {
+	if (IS_ERR_OR_NULL(dev)) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry_rcu(tmp_dev_opp, &dev_opp_list, node) {
-		if (tmp_dev_opp->dev == dev) {
-			dev_opp = tmp_dev_opp;
-			break;
-		}
-	}
-
+	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node)
+		if (_find_list_dev(dev, dev_opp))
 			return dev_opp;
+
+	return ERR_PTR(-ENODEV);
 }
 
 /**
@@ -172,7 +239,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		v = tmp_opp->u_volt;
@@ -204,7 +271,7 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		f = tmp_opp->rate;
@@ -213,6 +280,66 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
 
+/**
+ * dev_pm_opp_is_turbo() - Returns if opp is turbo OPP or not
+ * @opp: opp for which turbo mode is being verified
+ *
+ * Turbo OPPs are not for normal use, and can be enabled (under certain
+ * conditions) for short duration of times to finish high throughput work
+ * quickly. Running on them for longer times may overheat the chip.
+ *
+ * Return: true if opp is turbo opp, else false.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. This means that opp which could have been fetched by
+ * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp)
+{
+	struct dev_pm_opp *tmp_opp;
+
+	opp_rcu_lockdep_assert();
+
+	tmp_opp = rcu_dereference(opp);
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return false;
+	}
+
+	return tmp_opp->turbo;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
+
+/**
+ * dev_pm_opp_get_max_clock_latency() - Get max clock latency in nanoseconds
+ * @dev:	device for which we do this operation
+ *
+ * Return: This function returns the max clock latency in nanoseconds.
+ *
+ * Locking: This function takes rcu_read_lock().
+ */
+unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	unsigned long clock_latency_ns;
+
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		clock_latency_ns = 0;
+	else
+		clock_latency_ns = dev_opp->clock_latency_ns_max;
+
+	rcu_read_unlock();
+	return clock_latency_ns;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
+
 /**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list
  * @dev:	device for which we do this operation
@@ -407,18 +534,57 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
+/* List-dev Helpers */
+static void _kfree_list_dev_rcu(struct rcu_head *head)
+{
+	struct device_list_opp *list_dev;
+
+	list_dev = container_of(head, struct device_list_opp, rcu_head);
+	kfree_rcu(list_dev, rcu_head);
+}
+
+static void _remove_list_dev(struct device_list_opp *list_dev,
+			     struct device_opp *dev_opp)
+{
+	list_del(&list_dev->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &list_dev->rcu_head,
+		  _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 *list_dev;
+
+	list_dev = kzalloc(sizeof(*list_dev), GFP_KERNEL);
+	if (!list_dev)
+		return NULL;
+
+	/* Initialize list-dev */
+	list_dev->dev = dev;
+	list_add_rcu(&list_dev->node, &dev_opp->dev_list);
+
+	return list_dev;
+}
+
 /**
- * _add_device_opp() - Allocate a new device OPP table
+ * _add_device_opp() - Find device OPP table or allocate a new one
  * @dev:	device for which we do this operation
  *
- * New device node which uses OPPs - used when multiple devices with OPP tables
- * are maintained.
+ * It tries to find an existing table first, if it couldn't find one, it
+ * allocates a new OPP table and returns that.
  *
  * Return: valid device_opp pointer if success, else NULL.
  */
 static struct device_opp *_add_device_opp(struct device *dev)
 {
 	struct device_opp *dev_opp;
+	struct device_list_opp *list_dev;
+
+	/* Check for existing list for 'dev' first */
+	dev_opp = _find_device_opp(dev);
+	if (!IS_ERR(dev_opp))
+		return dev_opp;
 
 	/*
 	 * Allocate a new device OPP table. In the infrequent case where a new
@@ -428,7 +594,14 @@ static struct device_opp *_add_device_opp(struct device *dev)
 	if (!dev_opp)
 		return NULL;
 
-	dev_opp->dev = dev;
+	INIT_LIST_HEAD(&dev_opp->dev_list);
+
+	list_dev = _add_list_dev(dev, dev_opp);
+	if (!list_dev) {
+		kfree(dev_opp);
+		return NULL;
+	}
+
 	srcu_init_notifier_head(&dev_opp->srcu_head);
 	INIT_LIST_HEAD(&dev_opp->opp_list);
 
@@ -438,136 +611,41 @@ static struct device_opp *_add_device_opp(struct device *dev)
 }
 
 /**
- * _opp_add_dynamic() - Allocate a dynamic OPP.
- * @dev:	device for which we do this operation
- * @freq:	Frequency in Hz for this OPP
- * @u_volt:	Voltage in uVolts for this OPP
- * @dynamic:	Dynamically added OPPs.
- *
- * This function adds an opp definition to the opp list and returns status.
- * 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.
- *
- * Locking: The internal device_opp and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
- *
- * 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
+ * _kfree_device_rcu() - Free device_opp RCU handler
+ * @head:	RCU head
  */
-static int _opp_add_dynamic(struct device *dev, unsigned long freq,
-			    long u_volt, bool dynamic)
+static void _kfree_device_rcu(struct rcu_head *head)
 {
-	struct device_opp *dev_opp = NULL;
-	struct dev_pm_opp *opp, *new_opp;
-	struct list_head *head;
-	int ret;
-
-	/* allocate new OPP node */
-	new_opp = kzalloc(sizeof(*new_opp), GFP_KERNEL);
-	if (!new_opp)
-		return -ENOMEM;
-
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
-
-	/* populate the opp table */
-	new_opp->rate = freq;
-	new_opp->u_volt = u_volt;
-	new_opp->available = true;
-	new_opp->dynamic = dynamic;
-
-	/* Check for existing list for 'dev' */
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		dev_opp = _add_device_opp(dev);
-		if (!dev_opp) {
-			ret = -ENOMEM;
-			goto free_opp;
-		}
+	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
 
-		head = &dev_opp->opp_list;
-		goto list_add;
-	}
+	kfree_rcu(device_opp, rcu_head);
+}
 
-	/*
-	 * Insert new OPP in order of increasing frequency
-	 * and discard if already present
+/**
+ * _remove_device_opp() - Removes a device OPP table
+ * @dev_opp: device OPP table to be removed.
+ *
+ * Removes/frees device OPP table it it doesn't contain any OPPs.
  */
-	head = &dev_opp->opp_list;
-	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
-		if (new_opp->rate <= opp->rate)
-			break;
-		else
-			head = &opp->node;
-	}
-
-	/* Duplicate OPPs ? */
-	if (new_opp->rate == opp->rate) {
-		ret = opp->available && new_opp->u_volt == opp->u_volt ?
-			0 : -EEXIST;
+static void _remove_device_opp(struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
 
-		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
-			 __func__, opp->rate, opp->u_volt, opp->available,
-			 new_opp->rate, new_opp->u_volt, new_opp->available);
-		goto free_opp;
-	}
+	if (!list_empty(&dev_opp->opp_list))
+		return;
 
-list_add:
-	new_opp->dev_opp = dev_opp;
-	list_add_rcu(&new_opp->node, head);
-	mutex_unlock(&dev_opp_list_lock);
+	list_dev = list_first_entry(&dev_opp->dev_list, struct device_list_opp,
+				    node);
 
-	/*
-	 * Notify the changes in the availability of the operable
-	 * frequency/voltage list.
-	 */
-	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
-	return 0;
+	_remove_list_dev(list_dev, dev_opp);
 
-free_opp:
-	mutex_unlock(&dev_opp_list_lock);
-	kfree(new_opp);
-	return ret;
-}
+	/* dev_list must be empty now */
+	WARN_ON(!list_empty(&dev_opp->dev_list));
 
-/**
- * dev_pm_opp_add()  - Add an OPP table from a table definitions
- * @dev:	device for which we do this operation
- * @freq:	Frequency in Hz for this OPP
- * @u_volt:	Voltage in uVolts for this OPP
- *
- * This function adds an opp definition to the opp list and returns status.
- * The opp is made available by default and it can be controlled using
- * dev_pm_opp_enable/disable functions.
- *
- * Locking: The internal device_opp and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
- *
- * 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
- */
-int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
-{
-	return _opp_add_dynamic(dev, freq, u_volt, true);
+	list_del_rcu(&dev_opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
+		  _kfree_device_rcu);
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 
 /**
  * _kfree_opp_rcu() - Free OPP RCU handler
@@ -580,21 +658,11 @@ static void _kfree_opp_rcu(struct rcu_head *head)
 	kfree_rcu(opp, rcu_head);
 }
 
-/**
- * _kfree_device_rcu() - Free device_opp RCU handler
- * @head:	RCU head
- */
-static void _kfree_device_rcu(struct rcu_head *head)
-{
-	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
-
-	kfree_rcu(device_opp, rcu_head);
-}
-
 /**
  * _opp_remove()  - Remove an OPP from a table definition
  * @dev_opp:	points back to the device_opp struct this opp belongs to
  * @opp:	pointer to the OPP to remove
+ * @notify:	OPP_EVENT_REMOVE notification should be sent or not
  *
  * This function removes an opp definition from the opp list.
  *
@@ -603,21 +671,18 @@ static void _kfree_device_rcu(struct rcu_head *head)
  * strategy.
  */
 static void _opp_remove(struct device_opp *dev_opp,
-			struct dev_pm_opp *opp)
+			struct dev_pm_opp *opp, bool notify)
 {
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
+	if (notify)
 		srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
 	list_del_rcu(&opp->node);
 	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
 
-	if (list_empty(&dev_opp->opp_list)) {
-		list_del_rcu(&dev_opp->node);
-		call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
-			  _kfree_device_rcu);
-	}
+	_remove_device_opp(dev_opp);
 }
 
 /**
@@ -659,40 +724,335 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 		goto unlock;
 	}
 
-	_opp_remove(dev_opp, opp);
+	_opp_remove(dev_opp, opp, true);
 unlock:
 	mutex_unlock(&dev_opp_list_lock);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
 
-/**
- * _opp_set_availability() - helper to set the availability of an opp
- * @dev:		device for which we do this operation
- * @freq:		OPP frequency to modify availability
- * @availability_req:	availability status requested for this opp
- *
- * Set the availability of an OPP with an RCU operation, opp_{enable,disable}
- * share a common logic which is isolated here.
- *
- * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
- * successful.
- *
- * Locking: The internal device_opp and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks to
- * keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex locking or synchronize_rcu() blocking calls cannot be used.
- */
-static int _opp_set_availability(struct device *dev, unsigned long freq,
-				 bool availability_req)
+static struct dev_pm_opp *_allocate_opp(struct device *dev,
+					struct device_opp **dev_opp)
 {
-	struct device_opp *dev_opp;
-	struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
-	int r = 0;
+	struct dev_pm_opp *opp;
 
-	/* keep the node allocated */
-	new_opp = kmalloc(sizeof(*new_opp), GFP_KERNEL);
+	/* allocate new OPP node */
+	opp = kzalloc(sizeof(*opp), GFP_KERNEL);
+	if (!opp)
+		return NULL;
+
+	INIT_LIST_HEAD(&opp->node);
+
+	*dev_opp = _add_device_opp(dev);
+	if (!*dev_opp) {
+		kfree(opp);
+		return NULL;
+	}
+
+	return opp;
+}
+
+static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
+		    struct device_opp *dev_opp)
+{
+	struct dev_pm_opp *opp;
+	struct list_head *head = &dev_opp->opp_list;
+
+	/*
+	 * Insert new OPP in order of increasing frequency and discard if
+	 * already present.
+	 *
+	 * Need to use &dev_opp->opp_list in the condition part of the 'for'
+	 * loop, don't replace it with head otherwise it will become an infinite
+	 * loop.
+	 */
+	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
+		if (new_opp->rate > opp->rate) {
+			head = &opp->node;
+			continue;
+		}
+
+		if (new_opp->rate < opp->rate)
+			break;
+
+		/* Duplicate OPPs */
+		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
+			 __func__, opp->rate, opp->u_volt, opp->available,
+			 new_opp->rate, new_opp->u_volt, new_opp->available);
+
+		return opp->available && new_opp->u_volt == opp->u_volt ?
+			0 : -EEXIST;
+	}
+
+	new_opp->dev_opp = dev_opp;
+	list_add_rcu(&new_opp->node, head);
+
+	return 0;
+}
+
+/**
+ * _opp_add_dynamic() - Allocate a dynamic OPP.
+ * @dev:	device for which we do this operation
+ * @freq:	Frequency in Hz for this OPP
+ * @u_volt:	Voltage in uVolts for this OPP
+ * @dynamic:	Dynamically added OPPs.
+ *
+ * This function adds an opp definition to the opp list and returns status.
+ * 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.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ *
+ * 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
+ */
+static int _opp_add_dynamic(struct device *dev, unsigned long freq,
+			    long u_volt, bool dynamic)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp;
+	int ret;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	new_opp = _allocate_opp(dev, &dev_opp);
+	if (!new_opp) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	/* populate the opp table */
+	new_opp->rate = freq;
+	new_opp->u_volt = u_volt;
+	new_opp->available = true;
+	new_opp->dynamic = dynamic;
+
+	ret = _opp_add(dev, new_opp, dev_opp);
+	if (ret)
+		goto free_opp;
+
+	mutex_unlock(&dev_opp_list_lock);
+
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
+	return 0;
+
+free_opp:
+	_opp_remove(dev_opp, new_opp, false);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+	return ret;
+}
+
+/* TODO: Support multiple regulators */
+static int opp_get_microvolt(struct dev_pm_opp *opp, struct device *dev)
+{
+	u32 microvolt[3] = {0};
+	int count, ret;
+
+	count = of_property_count_u32_elems(opp->np, "opp-microvolt");
+	if (!count)
+		return 0;
+
+	/* There can be one or three elements here */
+	if (count != 1 && count != 3) {
+		dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n",
+			__func__, count);
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32_array(opp->np, "opp-microvolt", microvolt,
+					 count);
+	if (ret) {
+		dev_err(dev, "%s: error parsing opp-microvolt: %d\n", __func__,
+			ret);
+		return -EINVAL;
+	}
+
+	opp->u_volt = microvolt[0];
+	opp->u_volt_min = microvolt[1];
+	opp->u_volt_max = microvolt[2];
+
+	return 0;
+}
+
+/**
+ * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
+ * @dev:	device for which we do this operation
+ * @np:		device node
+ *
+ * This function adds an opp definition to the opp list and returns status. The
+ * opp can be controlled using dev_pm_opp_enable/disable functions and may be
+ * removed by dev_pm_opp_remove.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ *
+ * 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 device *dev, struct device_node *np)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp;
+	u64 rate;
+	u32 val;
+	int ret;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	new_opp = _allocate_opp(dev, &dev_opp);
+	if (!new_opp) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	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;
+	}
+
+	/*
+	 * 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_get_microvolt(new_opp, dev);
+	if (ret)
+		goto free_opp;
+
+	if (!of_property_read_u32(new_opp->np, "opp-microamp", &val))
+		new_opp->u_amp = val;
+
+	ret = _opp_add(dev, new_opp, dev_opp);
+	if (ret)
+		goto free_opp;
+
+	/* OPP to select on device suspend */
+	if (of_property_read_bool(np, "opp-suspend")) {
+		if (dev_opp->suspend_opp)
+			dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n",
+				 __func__, dev_opp->suspend_opp->rate,
+				 new_opp->rate);
+		else
+			dev_opp->suspend_opp = new_opp;
+	}
+
+	if (new_opp->clock_latency_ns > dev_opp->clock_latency_ns_max)
+		dev_opp->clock_latency_ns_max = new_opp->clock_latency_ns;
+
+	mutex_unlock(&dev_opp_list_lock);
+
+	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->u_volt,
+		 new_opp->u_volt_min, new_opp->u_volt_max,
+		 new_opp->clock_latency_ns);
+
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
+	return 0;
+
+free_opp:
+	_opp_remove(dev_opp, new_opp, false);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+	return ret;
+}
+
+/**
+ * dev_pm_opp_add()  - Add an OPP table from a table definitions
+ * @dev:	device for which we do this operation
+ * @freq:	Frequency in Hz for this OPP
+ * @u_volt:	Voltage in uVolts for this OPP
+ *
+ * This function adds an opp definition to the opp list and returns status.
+ * The opp is made available by default and it can be controlled using
+ * dev_pm_opp_enable/disable functions.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ *
+ * 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
+ */
+int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+{
+	return _opp_add_dynamic(dev, freq, u_volt, true);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_add);
+
+/**
+ * _opp_set_availability() - helper to set the availability of an opp
+ * @dev:		device for which we do this operation
+ * @freq:		OPP frequency to modify availability
+ * @availability_req:	availability status requested for this opp
+ *
+ * Set the availability of an OPP with an RCU operation, opp_{enable,disable}
+ * share a common logic which is isolated here.
+ *
+ * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
+ * copy operation, returns 0 if no modifcation was done OR modification was
+ * successful.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks to
+ * keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+static int _opp_set_availability(struct device *dev, unsigned long freq,
+				 bool availability_req)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
+	int r = 0;
+
+	/* keep the node allocated */
+	new_opp = kmalloc(sizeof(*new_opp), GFP_KERNEL);
 	if (!new_opp)
 		return -ENOMEM;
 
@@ -825,28 +1185,179 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
 
 #ifdef CONFIG_OF
 /**
- * of_init_opp_table() - Initialize opp table from device tree
+ * of_free_opp_table() - Free OPP table entries created from static DT entries
  * @dev:	device pointer used to lookup device OPPs.
  *
- * Register the initial OPP table with the OPP library for given device.
+ * Free OPPs created using static entries present in DT.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function indirectly uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * 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)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *opp, *tmp;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Check for existing list for 'dev' */
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int error = PTR_ERR(dev_opp);
+
+		if (error != -ENODEV)
+			WARN(1, "%s: dev_opp: %d\n",
+			     IS_ERR_OR_NULL(dev) ?
+					"Invalid device" : dev_name(dev),
+			     error);
+		goto unlock;
+	}
+
+	/* Find if dev_opp manages a single device */
+	if (list_is_singular(&dev_opp->dev_list)) {
+		/* Free static OPPs */
+		list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
+			if (!opp->dynamic)
+				_opp_remove(dev_opp, opp, true);
+		}
+	} else {
+		_remove_list_dev(_find_list_dev(dev, dev_opp), dev_opp);
+	}
+
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(of_free_opp_table);
+
+void of_cpumask_free_opp_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;
+		}
+
+		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.
 	 *
- * 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
+	 * There should be only ONE phandle present in "operating-points-v2"
+	 * property.
 	 */
-int of_init_opp_table(struct device *dev)
+	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);
+}
+
+/* Initializes OPP tables based on new bindings */
+static int _of_init_opp_table_v2(struct device *dev,
+				 const struct property *prop)
+{
+	struct device_node *opp_np, *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;
+	}
+
+	/* We have opp-list node now, iterate over it and add OPPs */
+	for_each_available_child_of_node(opp_np, np) {
+		count++;
+
+		ret = _opp_add_static_v2(dev, np);
+		if (ret) {
+			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
+				ret);
+			goto free_table;
+		}
+	}
+
+	/* There should be one of more OPP defined */
+	if (WARN_ON(!count)) {
+		ret = -ENOENT;
+		goto put_opp_np;
+	}
+
+	dev_opp = _find_device_opp(dev);
+	if (WARN_ON(IS_ERR(dev_opp))) {
+		ret = PTR_ERR(dev_opp);
+		goto free_table;
+	}
+
+	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);
+
+	return ret;
+}
+
+/* Initializes OPP tables based on old-deprecated bindings */
+static int _of_init_opp_table_v1(struct device *dev)
 {
 	const struct property *prop;
 	const __be32 *val;
@@ -881,47 +1392,177 @@ int of_init_opp_table(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(of_init_opp_table);
 
 /**
- * of_free_opp_table() - Free OPP table entries created from static DT entries
+ * of_init_opp_table() - Initialize opp table from device tree
  * @dev:	device pointer used to lookup device OPPs.
  *
- * Free OPPs created using static entries present in DT.
+ * Register the initial OPP table with the OPP library for given device.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function indirectly uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
+ *
+ * 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
  */
-void of_free_opp_table(struct device *dev)
+int of_init_opp_table(struct device *dev)
+{
+	const struct property *prop;
+
+	/*
+	 * 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) {
+		/*
+		 * 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 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 dev_pm_opp *opp, *tmp;
+	struct device *dev;
+	int cpu, ret = 0;
 
-	/* Check for existing list for 'dev' */
-	dev_opp = _find_device_opp(dev);
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(cpu_dev);
 	if (IS_ERR(dev_opp)) {
-		int error = PTR_ERR(dev_opp);
-		if (error != -ENODEV)
-			WARN(1, "%s: dev_opp: %d\n",
-			     IS_ERR_OR_NULL(dev) ?
-					"Invalid device" : dev_name(dev),
-			     error);
-		return;
+		ret = -EINVAL;
+		goto out_rcu_read_unlock;
 	}
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	for_each_cpu(cpu, cpumask) {
+		if (cpu == cpu_dev->id)
+			continue;
 
-	/* Free static OPPs */
-	list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
-		if (!opp->dynamic)
-			_opp_remove(dev_opp, opp);
+		dev = get_cpu_device(cpu);
+		if (!dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			continue;
 		}
 
-	mutex_unlock(&dev_opp_list_lock);
+		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(of_free_opp_table);
+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);
+	}
+
+put_cpu_node:
+	of_node_put(np);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_get_cpus_sharing_opps);
 #endif

drivers/cpufreq/cpufreq-dt.c

@@ -36,6 +36,12 @@ struct private_data {
 	unsigned int voltage_tolerance; /* in percentage */
 };
 
+static struct freq_attr *cpufreq_dt_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,   /* Extra space for boost-attr if required */
+	NULL,
+};
+
 static int set_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct dev_pm_opp *opp;
@@ -184,7 +190,6 @@ static int allocate_resources(int cpu, struct device **cdev,
 
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
-	struct cpufreq_dt_platform_data *pd;
 	struct cpufreq_frequency_table *freq_table;
 	struct device_node *np;
 	struct private_data *priv;
@@ -193,6 +198,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	struct clk *cpu_clk;
 	unsigned long min_uV = ~0, max_uV = 0;
 	unsigned int transition_latency;
+	bool need_update = false;
 	int ret;
 
 	ret = allocate_resources(policy->cpu, &cpu_dev, &cpu_reg, &cpu_clk);
@@ -208,8 +214,47 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_put_reg_clk;
 	}
 
-	/* OPPs might be populated at runtime, don't check for error here */
-	of_init_opp_table(cpu_dev);
+	/* Get OPP-sharing information from "operating-points-v2" bindings */
+	ret = of_get_cpus_sharing_opps(cpu_dev, policy->cpus);
+	if (ret) {
+		/*
+		 * operating-points-v2 not supported, fallback to old method of
+		 * finding shared-OPPs for backward compatibility.
+		 */
+		if (ret == -ENOENT)
+			need_update = true;
+		else
+			goto out_node_put;
+	}
+
+	/*
+	 * Initialize OPP tables for all policy->cpus. They will be shared by
+	 * all CPUs which have marked their CPUs shared with OPP bindings.
+	 *
+	 * For platforms not using operating-points-v2 bindings, we do this
+	 * before updating policy->cpus. Otherwise, we will end up creating
+	 * duplicate OPPs for policy->cpus.
+	 *
+	 * OPPs might be populated at runtime, don't check for error here
+	 */
+	of_cpumask_init_opp_table(policy->cpus);
+
+	if (need_update) {
+		struct cpufreq_dt_platform_data *pd = cpufreq_get_driver_data();
+
+		if (!pd || !pd->independent_clocks)
+			cpumask_setall(policy->cpus);
+
+		/*
+		 * OPP tables are initialized only for policy->cpu, do it for
+		 * others as well.
+		 */
+		set_cpus_sharing_opps(cpu_dev, policy->cpus);
+
+		of_property_read_u32(np, "clock-latency", &transition_latency);
+	} else {
+		transition_latency = dev_pm_opp_get_max_clock_latency(cpu_dev);
+	}
 
 	/*
 	 * But we need OPP table to function so if it is not there let's
@@ -230,7 +275,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 
 	of_property_read_u32(np, "voltage-tolerance", &priv->voltage_tolerance);
 
-	if (of_property_read_u32(np, "clock-latency", &transition_latency))
+	if (!transition_latency)
 		transition_latency = CPUFREQ_ETERNAL;
 
 	if (!IS_ERR(cpu_reg)) {
@@ -291,11 +336,16 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_free_cpufreq_table;
 	}
 
-	policy->cpuinfo.transition_latency = transition_latency;
+	/* Support turbo/boost mode */
+	if (policy_has_boost_freq(policy)) {
+		/* This gets disabled by core on driver unregister */
+		ret = cpufreq_enable_boost_support();
+		if (ret)
+			goto out_free_cpufreq_table;
+		cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
+	}
 
-	pd = cpufreq_get_driver_data();
-	if (!pd || !pd->independent_clocks)
-		cpumask_setall(policy->cpus);
+	policy->cpuinfo.transition_latency = transition_latency;
 
 	of_node_put(np);
 
@@ -306,7 +356,8 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 out_free_priv:
 	kfree(priv);
 out_free_opp:
-	of_free_opp_table(cpu_dev);
+	of_cpumask_free_opp_table(policy->cpus);
+out_node_put:
 	of_node_put(np);
 out_put_reg_clk:
 	clk_put(cpu_clk);
@@ -322,7 +373,7 @@ 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_free_opp_table(priv->cpu_dev);
+	of_cpumask_free_opp_table(policy->related_cpus);
 	clk_put(policy->clk);
 	if (!IS_ERR(priv->cpu_reg))
 		regulator_put(priv->cpu_reg);
@@ -367,7 +418,7 @@ static struct cpufreq_driver dt_cpufreq_driver = {
 	.exit = cpufreq_exit,
 	.ready = cpufreq_ready,
 	.name = "cpufreq-dt",
-	.attr = cpufreq_generic_attr,
+	.attr = cpufreq_dt_attr,
 };
 
 static int dt_cpufreq_probe(struct platform_device *pdev)

drivers/cpufreq/cpufreq.c

@@ -2412,6 +2412,49 @@ int cpufreq_boost_supported(void)
 }
 EXPORT_SYMBOL_GPL(cpufreq_boost_supported);
 
+static int create_boost_sysfs_file(void)
+{
+	int ret;
+
+	if (!cpufreq_boost_supported())
+		return 0;
+
+	/*
+	 * Check if driver provides function to enable boost -
+	 * if not, use cpufreq_boost_set_sw as default
+	 */
+	if (!cpufreq_driver->set_boost)
+		cpufreq_driver->set_boost = cpufreq_boost_set_sw;
+
+	ret = cpufreq_sysfs_create_file(&boost.attr);
+	if (ret)
+		pr_err("%s: cannot register global BOOST sysfs file\n",
+		       __func__);
+
+	return ret;
+}
+
+static void remove_boost_sysfs_file(void)
+{
+	if (cpufreq_boost_supported())
+		cpufreq_sysfs_remove_file(&boost.attr);
+}
+
+int cpufreq_enable_boost_support(void)
+{
+	if (!cpufreq_driver)
+		return -EINVAL;
+
+	if (cpufreq_boost_supported())
+		return 0;
+
+	cpufreq_driver->boost_supported = true;
+
+	/* This will get removed on driver unregister */
+	return create_boost_sysfs_file();
+}
+EXPORT_SYMBOL_GPL(cpufreq_enable_boost_support);
+
 int cpufreq_boost_enabled(void)
 {
 	return cpufreq_driver->boost_enabled;
@@ -2465,21 +2508,9 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
 
-	if (cpufreq_boost_supported()) {
-		/*
-		 * Check if driver provides function to enable boost -
-		 * if not, use cpufreq_boost_set_sw as default
-		 */
-		if (!cpufreq_driver->set_boost)
-			cpufreq_driver->set_boost = cpufreq_boost_set_sw;
-
-		ret = cpufreq_sysfs_create_file(&boost.attr);
-		if (ret) {
-			pr_err("%s: cannot register global BOOST sysfs file\n",
-			       __func__);
+	ret = create_boost_sysfs_file();
+	if (ret)
 		goto err_null_driver;
-		}
-	}
 
 	ret = subsys_interface_register(&cpufreq_interface);
 	if (ret)
@@ -2503,8 +2534,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 err_if_unreg:
 	subsys_interface_unregister(&cpufreq_interface);
 err_boost_unreg:
-	if (cpufreq_boost_supported())
-		cpufreq_sysfs_remove_file(&boost.attr);
+	remove_boost_sysfs_file();
 err_null_driver:
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	cpufreq_driver = NULL;
@@ -2533,9 +2563,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	/* Protect against concurrent cpu hotplug */
 	get_online_cpus();
 	subsys_interface_unregister(&cpufreq_interface);
-	if (cpufreq_boost_supported())
-		cpufreq_sysfs_remove_file(&boost.attr);
-
+	remove_boost_sysfs_file();
 	unregister_hotcpu_notifier(&cpufreq_cpu_notifier);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);

drivers/cpufreq/cpufreq_opp.c

@@ -75,6 +75,10 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 		}
 		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;

drivers/cpufreq/freq_table.c

@@ -18,6 +18,21 @@
  *                     FREQUENCY TABLE HELPERS                       *
  *********************************************************************/
 
+bool policy_has_boost_freq(struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *pos, *table = policy->freq_table;
+
+	if (!table)
+		return false;
+
+	cpufreq_for_each_valid_entry(pos, table)
+		if (pos->flags & CPUFREQ_BOOST_FREQ)
+			return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(policy_has_boost_freq);
+
 int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 				    struct cpufreq_frequency_table *table)
 {

include/linux/cpufreq.h

@@ -575,6 +575,8 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf);
 int cpufreq_boost_trigger_state(int state);
 int cpufreq_boost_supported(void);
 int cpufreq_boost_enabled(void);
+int cpufreq_enable_boost_support(void);
+bool policy_has_boost_freq(struct cpufreq_policy *policy);
 #else
 static inline int cpufreq_boost_trigger_state(int state)
 {
@@ -588,12 +590,23 @@ static inline int cpufreq_boost_enabled(void)
 {
 	return 0;
 }
+
+static inline int cpufreq_enable_boost_support(void)
+{
+	return -EINVAL;
+}
+
+static inline bool policy_has_boost_freq(struct cpufreq_policy *policy)
+{
+	return false;
+}
 #endif
 /* the following funtion is for cpufreq core use only */
 struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu);
 
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
+extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs;
 extern struct freq_attr *cpufreq_generic_attr[];
 int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 				      struct cpufreq_frequency_table *table);

include/linux/pm_opp.h

@@ -30,7 +30,10 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp);
 
 unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp);
 
+bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp);
+
 int dev_pm_opp_get_opp_count(struct device *dev);
+unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev);
 
 struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					      unsigned long freq,
@@ -62,11 +65,21 @@ static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 	return 0;
 }
 
+static inline bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp)
+{
+	return false;
+}
+
 static inline int dev_pm_opp_get_opp_count(struct device *dev)
 {
 	return 0;
 }
 
+static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
+{
+	return 0;
+}
+
 static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					unsigned long freq, bool available)
 {
@@ -115,6 +128,10 @@ static inline struct srcu_notifier_head *dev_pm_opp_get_notifier(
 #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF)
 int of_init_opp_table(struct device *dev);
 void of_free_opp_table(struct device *dev);
+int of_cpumask_init_opp_table(cpumask_var_t cpumask);
+void of_cpumask_free_opp_table(cpumask_var_t cpumask);
+int of_get_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask);
+int set_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask);
 #else
 static inline int of_init_opp_table(struct device *dev)
 {
@@ -124,6 +141,25 @@ static inline int of_init_opp_table(struct device *dev)
 static inline void of_free_opp_table(struct device *dev)
 {
 }
+
+static inline int of_cpumask_init_opp_table(cpumask_var_t cpumask)
+{
+	return -ENOSYS;
+}
+
+static inline void of_cpumask_free_opp_table(cpumask_var_t cpumask)
+{
+}
+
+static inline int of_get_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask)
+{
+	return -ENOSYS;
+}
+
+static inline int set_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask)
+{
+	return -ENOSYS;
+}
 #endif
 
 #endif		/* __LINUX_OPP_H__ */