Merge branch 'pm-devfreq' into pm-for-linus

* pm-devfreq:
  PM / devfreq: Add basic governors
  PM / devfreq: Add common sysfs interfaces
  PM: Introduce devfreq: generic DVFS framework with device-specific OPPs
  PM / OPP: Add OPP availability change notifier.

Documentation/ABI/testing/sysfs-class-devfreq

@@ -0,0 +1,52 @@
+What:		/sys/class/devfreq/.../
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		Provide a place in sysfs for the devfreq objects.
+		This allows accessing various devfreq specific variables.
+		The name of devfreq object denoted as ... is same as the
+		name of device using devfreq.
+
+What:		/sys/class/devfreq/.../governor
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../governor shows the name of the
+		governor used by the corresponding devfreq object.
+
+What:		/sys/class/devfreq/.../cur_freq
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../cur_freq shows the current
+		frequency of the corresponding devfreq object.
+
+What:		/sys/class/devfreq/.../central_polling
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../central_polling shows whether
+		the devfreq ojbect is using devfreq-provided central
+		polling mechanism or not.
+
+What:		/sys/class/devfreq/.../polling_interval
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../polling_interval shows and sets
+		the requested polling interval of the corresponding devfreq
+		object. The values are represented in ms. If the value is
+		less than 1 jiffy, it is considered to be 0, which means
+		no polling. This value is meaningless if the governor is
+		not polling; thus. If the governor is not using
+		devfreq-provided central polling
+		(/sys/class/devfreq/.../central_polling is 0), this value
+		may be useless.
+
+What:		/sys/class/devfreq/.../userspace/set_freq
+Date:		September 2011
+Contact:	MyungJoo Ham <myungjoo.ham@samsung.com>
+Description:
+		The /sys/class/devfreq/.../userspace/set_freq shows and
+		sets the requested frequency for the devfreq object if
+		userspace governor is in effect.

drivers/Kconfig

@@ -130,4 +130,6 @@ source "drivers/iommu/Kconfig"
 
 source "drivers/virt/Kconfig"
 
+source "drivers/devfreq/Kconfig"
+
 endmenu

drivers/Makefile

@@ -127,3 +127,5 @@ obj-$(CONFIG_IOMMU_SUPPORT)	+= iommu/
 
 # Virtualization drivers
 obj-$(CONFIG_VIRT_DRIVERS)	+= virt/
+
+obj-$(CONFIG_PM_DEVFREQ)	+= devfreq/

drivers/base/power/opp.c

@@ -73,6 +73,7 @@ struct opp {
  *		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
+ * @head:	notifier head to notify the OPP availability changes.
  * @opp_list:	list of opps
  *
  * This is an internal data structure maintaining the link to opps attached to
@@ -83,6 +84,7 @@ struct device_opp {
 	struct list_head node;
 
 	struct device *dev;
+	struct srcu_notifier_head head;
 	struct list_head opp_list;
 };
 
@@ -404,6 +406,7 @@ int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 		}
 
 		dev_opp->dev = dev;
+		srcu_init_notifier_head(&dev_opp->head);
 		INIT_LIST_HEAD(&dev_opp->opp_list);
 
 		/* Secure the device list modification */
@@ -428,6 +431,11 @@ int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 	list_add_rcu(&new_opp->node, head);
 	mutex_unlock(&dev_opp_list_lock);
 
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_ADD, new_opp);
 	return 0;
 }
 
@@ -504,6 +512,14 @@ static int opp_set_availability(struct device *dev, unsigned long freq,
 	mutex_unlock(&dev_opp_list_lock);
 	synchronize_rcu();
 
+	/* Notify the change of the OPP availability */
+	if (availability_req)
+		srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_ENABLE,
+					 new_opp);
+	else
+		srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_DISABLE,
+					 new_opp);
+
 	/* clean up old opp */
 	new_opp = opp;
 	goto out;
@@ -643,3 +659,17 @@ void opp_free_cpufreq_table(struct device *dev,
 	*table = NULL;
 }
 #endif		/* CONFIG_CPU_FREQ */
+
+/**
+ * opp_get_notifier() - find notifier_head of the device with opp
+ * @dev:	device pointer used to lookup device OPPs.
+ */
+struct srcu_notifier_head *opp_get_notifier(struct device *dev)
+{
+	struct device_opp *dev_opp = find_device_opp(dev);
+
+	if (IS_ERR(dev_opp))
+		return ERR_PTR(PTR_ERR(dev_opp)); /* matching type */
+
+	return &dev_opp->head;
+}

drivers/devfreq/Kconfig

@@ -0,0 +1,75 @@
+config ARCH_HAS_DEVFREQ
+	bool
+	depends on ARCH_HAS_OPP
+	help
+	  Denotes that the architecture supports DEVFREQ. If the architecture
+	  supports multiple OPP entries per device and the frequency of the
+	  devices with OPPs may be altered dynamically, the architecture
+	  supports DEVFREQ.
+
+menuconfig PM_DEVFREQ
+	bool "Generic Dynamic Voltage and Frequency Scaling (DVFS) support"
+	depends on PM_OPP && ARCH_HAS_DEVFREQ
+	help
+	  With OPP support, a device may have a list of frequencies and
+	  voltages available. DEVFREQ, a generic DVFS framework can be
+	  registered for a device with OPP support in order to let the
+	  governor provided to DEVFREQ choose an operating frequency
+	  based on the OPP's list and the policy given with DEVFREQ.
+
+	  Each device may have its own governor and policy. DEVFREQ can
+	  reevaluate the device state periodically and/or based on the
+	  OPP list changes (each frequency/voltage pair in OPP may be
+	  disabled or enabled).
+
+	  Like some CPUs with CPUFREQ, a device may have multiple clocks.
+	  However, because the clock frequencies of a single device are
+	  determined by the single device's state, an instance of DEVFREQ
+	  is attached to a single device and returns a "representative"
+	  clock frequency from the OPP of the device, which is also attached
+	  to a device by 1-to-1. The device registering DEVFREQ takes the
+	  responsiblity to "interpret" the frequency listed in OPP and
+	  to set its every clock accordingly with the "target" callback
+	  given to DEVFREQ.
+
+if PM_DEVFREQ
+
+comment "DEVFREQ Governors"
+
+config DEVFREQ_GOV_SIMPLE_ONDEMAND
+	bool "Simple Ondemand"
+	help
+	  Chooses frequency based on the recent load on the device. Works
+	  similar as ONDEMAND governor of CPUFREQ does. A device with
+	  Simple-Ondemand should be able to provide busy/total counter
+	  values that imply the usage rate. A device may provide tuned
+	  values to the governor with data field at devfreq_add_device().
+
+config DEVFREQ_GOV_PERFORMANCE
+	bool "Performance"
+	help
+	  Sets the frequency at the maximum available frequency.
+	  This governor always returns UINT_MAX as frequency so that
+	  the DEVFREQ framework returns the highest frequency available
+	  at any time.
+
+config DEVFREQ_GOV_POWERSAVE
+	bool "Powersave"
+	help
+	  Sets the frequency at the minimum available frequency.
+	  This governor always returns 0 as frequency so that
+	  the DEVFREQ framework returns the lowest frequency available
+	  at any time.
+
+config DEVFREQ_GOV_USERSPACE
+	bool "Userspace"
+	help
+	  Sets the frequency at the user specified one.
+	  This governor returns the user configured frequency if there
+	  has been an input to /sys/devices/.../power/devfreq_set_freq.
+	  Otherwise, the governor does not change the frequnecy
+	  given at the initialization.
+
+comment "DEVFREQ Drivers"
+
+endif # PM_DEVFREQ

drivers/devfreq/Makefile

@@ -0,0 +1,5 @@
+obj-$(CONFIG_PM_DEVFREQ)	+= devfreq.o
+obj-$(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)	+= governor_simpleondemand.o
+obj-$(CONFIG_DEVFREQ_GOV_PERFORMANCE)	+= governor_performance.o
+obj-$(CONFIG_DEVFREQ_GOV_POWERSAVE)	+= governor_powersave.o
+obj-$(CONFIG_DEVFREQ_GOV_USERSPACE)	+= governor_userspace.o