PM: Add support for device power domains

The platform bus type is often used to handle Systems-on-a-Chip (SoC)
where all devices are represented by objects of type struct
platform_device.  In those cases the same "platform" device driver
may be used with multiple different system configurations, but the
actions needed to put the devices it handles into a low-power state
and back into the full-power state may depend on the design of the
given SoC.  The driver, however, cannot possibly include all the
information necessary for the power management of its device on all
the systems it is used with.  Moreover, the device hierarchy in its
current form also is not suitable for representing this kind of
information.

The patch below attempts to address this problem by introducing
objects of type struct dev_power_domain that can be used for
representing power domains within a SoC.  Every struct
dev_power_domain object provides a sets of device power
management callbacks that can be used to perform what's needed for
device power management in addition to the operations carried out by
the device's driver and subsystem.

Namely, if a struct dev_power_domain object is pointed to by the
pwr_domain field in a struct device, the callbacks provided by its
ops member will be executed in addition to the corresponding
callbacks provided by the device's subsystem and driver during all
power transitions.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Tested-and-acked-by: Kevin Hilman <khilman@ti.com>

Documentation/power/devices.txt

 Device Power Management
 
-Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+Copyright (c) 2010-2011 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
 Copyright (c) 2010 Alan Stern <stern@rowland.harvard.edu>
 
 
@@ -507,6 +507,49 @@ routines.  Nevertheless, different callback pointers are used in case there is a
 situation where it actually matters.
 
 
+Device Power Domains
+--------------------
+Sometimes devices share reference clocks or other power resources.  In those
+cases it generally is not possible to put devices into low-power states
+individually.  Instead, a set of devices sharing a power resource can be put
+into a low-power state together at the same time by turning off the shared
+power resource.  Of course, they also need to be put into the full-power state
+together, by turning the shared power resource on.  A set of devices with this
+property is often referred to as a power domain.
+
+Support for power domains is provided through the pwr_domain field of struct
+device.  This field is a pointer to an object of type struct dev_power_domain,
+defined in include/linux/pm.h, providing a set of power management callbacks
+analogous to the subsystem-level and device driver callbacks that are executed
+for the given device during all power transitions, in addition to the respective
+subsystem-level callbacks.  Specifically, the power domain "suspend" callbacks
+(i.e. ->runtime_suspend(), ->suspend(), ->freeze(), ->poweroff(), etc.) are
+executed after the analogous subsystem-level callbacks, while the power domain
+"resume" callbacks (i.e. ->runtime_resume(), ->resume(), ->thaw(), ->restore,
+etc.) are executed before the analogous subsystem-level callbacks.  Error codes
+returned by the "suspend" and "resume" power domain callbacks are ignored.
+
+Power domain ->runtime_idle() callback is executed before the subsystem-level
+->runtime_idle() callback and the result returned by it is not ignored.  Namely,
+if it returns error code, the subsystem-level ->runtime_idle() callback will not
+be called and the helper function rpm_idle() executing it will return error
+code.  This mechanism is intended to help platforms where saving device state
+is a time consuming operation and should only be carried out if all devices
+in the power domain are idle, before turning off the shared power resource(s).
+Namely, the power domain ->runtime_idle() callback may return error code until
+the pm_runtime_idle() helper (or its asychronous version) has been called for
+all devices in the power domain (it is recommended that the returned error code
+be -EBUSY in those cases), preventing the subsystem-level ->runtime_idle()
+callback from being run prematurely.
+
+The support for device power domains is only relevant to platforms needing to
+use the same subsystem-level (e.g. platform bus type) and device driver power
+management callbacks in many different power domain configurations and wanting
+to avoid incorporating the support for power domains into the subsystem-level
+callbacks.  The other platforms need not implement it or take it into account
+in any way.
+
+
 System Devices
 --------------
 System devices (sysdevs) follow a slightly different API, which can be found in

drivers/base/power/main.c

@@ -423,6 +423,11 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
 	TRACE_DEVICE(dev);
 	TRACE_RESUME(0);
 
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "EARLY power domain ");
+		pm_noirq_op(dev, &dev->pwr_domain->ops, state);
+	}
+
 	if (dev->bus && dev->bus->pm) {
 		pm_dev_dbg(dev, state, "EARLY ");
 		error = pm_noirq_op(dev, dev->bus->pm, state);
@@ -518,6 +523,11 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 
 	dev->power.in_suspend = false;
 
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "power domain ");
+		pm_op(dev, &dev->pwr_domain->ops, state);
+	}
+
 	if (dev->bus) {
 		if (dev->bus->pm) {
 			pm_dev_dbg(dev, state, "");
@@ -629,6 +639,11 @@ static void device_complete(struct device *dev, pm_message_t state)
 {
 	device_lock(dev);
 
+	if (dev->pwr_domain && dev->pwr_domain->ops.complete) {
+		pm_dev_dbg(dev, state, "completing power domain ");
+		dev->pwr_domain->ops.complete(dev);
+	}
+
 	if (dev->class && dev->class->pm && dev->class->pm->complete) {
 		pm_dev_dbg(dev, state, "completing class ");
 		dev->class->pm->complete(dev);
@@ -745,6 +760,13 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 	if (dev->bus && dev->bus->pm) {
 		pm_dev_dbg(dev, state, "LATE ");
 		error = pm_noirq_op(dev, dev->bus->pm, state);
+		if (error)
+			goto End;
+	}
+
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "LATE power domain ");
+		pm_noirq_op(dev, &dev->pwr_domain->ops, state);
 	}
 
 End:
@@ -864,6 +886,13 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 			pm_dev_dbg(dev, state, "legacy ");
 			error = legacy_suspend(dev, state, dev->bus->suspend);
 		}
+		if (error)
+			goto End;
+	}
+
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "power domain ");
+		pm_op(dev, &dev->pwr_domain->ops, state);
 	}
 
  End:
@@ -976,7 +1005,15 @@ static int device_prepare(struct device *dev, pm_message_t state)
 		pm_dev_dbg(dev, state, "preparing class ");
 		error = dev->class->pm->prepare(dev);
 		suspend_report_result(dev->class->pm->prepare, error);
+		if (error)
+			goto End;
+	}
+
+	if (dev->pwr_domain && dev->pwr_domain->ops.prepare) {
+		pm_dev_dbg(dev, state, "preparing power domain ");
+		dev->pwr_domain->ops.prepare(dev);
 	}
+
  End:
 	device_unlock(dev);
 

drivers/base/power/runtime.c

@@ -168,6 +168,7 @@ static int rpm_check_suspend_allowed(struct device *dev)
 static int rpm_idle(struct device *dev, int rpmflags)
 {
 	int (*callback)(struct device *);
+	int (*domain_callback)(struct device *);
 	int retval;
 
 	retval = rpm_check_suspend_allowed(dev);
@@ -222,10 +223,19 @@ static int rpm_idle(struct device *dev, int rpmflags)
 	else
 		callback = NULL;
 
-	if (callback) {
+	if (dev->pwr_domain)
+		domain_callback = dev->pwr_domain->ops.runtime_idle;
+	else
+		domain_callback = NULL;
+
+	if (callback || domain_callback) {
 		spin_unlock_irq(&dev->power.lock);
 
-		callback(dev);
+		if (domain_callback)
+			retval = domain_callback(dev);
+
+		if (!retval && callback)
+			callback(dev);
 
 		spin_lock_irq(&dev->power.lock);
 	}
@@ -390,6 +400,8 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 		else
 			pm_runtime_cancel_pending(dev);
 	} else {
+		if (dev->pwr_domain)
+			rpm_callback(dev->pwr_domain->ops.runtime_suspend, dev);
  no_callback:
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_deactivate_timer(dev);
@@ -569,6 +581,9 @@ static int rpm_resume(struct device *dev, int rpmflags)
 
 	__update_runtime_status(dev, RPM_RESUMING);
 
+	if (dev->pwr_domain)
+		rpm_callback(dev->pwr_domain->ops.runtime_resume, dev);
+
 	if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume)
 		callback = dev->bus->pm->runtime_resume;
 	else if (dev->type && dev->type->pm && dev->type->pm->runtime_resume)

include/linux/device.h

@@ -422,6 +422,7 @@ struct device {
 	void		*platform_data;	/* Platform specific data, device
 					   core doesn't touch it */
 	struct dev_pm_info	power;
+	struct dev_power_domain	*pwr_domain;
 
 #ifdef CONFIG_NUMA
 	int		numa_node;	/* NUMA node this device is close to */

include/linux/pm.h

@@ -465,6 +465,14 @@ struct dev_pm_info {
 
 extern void update_pm_runtime_accounting(struct device *dev);
 
+/*
+ * Power domains provide callbacks that are executed during system suspend,
+ * hibernation, system resume and during runtime PM transitions along with
+ * subsystem-level and driver-level callbacks.
+ */
+struct dev_power_domain {
+	struct dev_pm_ops	ops;
+};
 
 /*
  * The PM_EVENT_ messages are also used by drivers implementing the legacy