initial_commit

10 files changed, 5418 insertions, 0 deletions

diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
new file mode 100644
index 00000000..3647e114
--- /dev/null
+++ b/drivers/base/power/Makefile
@@ -0,0 +1,8 @@
+obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o
+obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
+obj-$(CONFIG_PM_RUNTIME)	+= runtime.o
+obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
+obj-$(CONFIG_PM_OPP)	+= opp.o
+obj-$(CONFIG_HAVE_CLK)	+= clock_ops.o
+
+ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
\ No newline at end of file
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
new file mode 100644
index 00000000..ad367c41
--- /dev/null
+++ b/drivers/base/power/clock_ops.c
@@ -0,0 +1,431 @@
+/*
+ * drivers/base/power/clock_ops.c - Generic clock manipulation PM callbacks
+ *
+ * Copyright (c) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/clk.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+
+#ifdef CONFIG_PM_RUNTIME
+
+struct pm_runtime_clk_data {
+	struct list_head clock_list;
+	struct mutex lock;
+};
+
+enum pce_status {
+	PCE_STATUS_NONE = 0,
+	PCE_STATUS_ACQUIRED,
+	PCE_STATUS_ENABLED,
+	PCE_STATUS_ERROR,
+};
+
+struct pm_clock_entry {
+	struct list_head node;
+	char *con_id;
+	struct clk *clk;
+	enum pce_status status;
+};
+
+static struct pm_runtime_clk_data *__to_prd(struct device *dev)
+{
+	return dev ? dev->power.subsys_data : NULL;
+}
+
+/**
+ * pm_runtime_clk_add - Start using a device clock for runtime PM.
+ * @dev: Device whose clock is going to be used for runtime PM.
+ * @con_id: Connection ID of the clock.
+ *
+ * Add the clock represented by @con_id to the list of clocks used for
+ * the runtime PM of @dev.
+ */
+int pm_runtime_clk_add(struct device *dev, const char *con_id)
+{
+	struct pm_runtime_clk_data *prd = __to_prd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!prd)
+		return -EINVAL;
+
+	ce = kzalloc(sizeof(*ce), GFP_KERNEL);
+	if (!ce) {
+		dev_err(dev, "Not enough memory for clock entry.\n");
+		return -ENOMEM;
+	}
+
+	if (con_id) {
+		ce->con_id = kstrdup(con_id, GFP_KERNEL);
+		if (!ce->con_id) {
+			dev_err(dev,
+				"Not enough memory for clock connection ID.\n");
+			kfree(ce);
+			return -ENOMEM;
+		}
+	}
+
+	mutex_lock(&prd->lock);
+	list_add_tail(&ce->node, &prd->clock_list);
+	mutex_unlock(&prd->lock);
+	return 0;
+}
+
+/**
+ * __pm_runtime_clk_remove - Destroy runtime PM clock entry.
+ * @ce: Runtime PM clock entry to destroy.
+ *
+ * This routine must be called under the mutex protecting the runtime PM list
+ * of clocks corresponding the the @ce's device.
+ */
+static void __pm_runtime_clk_remove(struct pm_clock_entry *ce)
+{
+	if (!ce)
+		return;
+
+	list_del(&ce->node);
+
+	if (ce->status < PCE_STATUS_ERROR) {
+		if (ce->status == PCE_STATUS_ENABLED)
+			clk_disable(ce->clk);
+
+		if (ce->status >= PCE_STATUS_ACQUIRED)
+			clk_put(ce->clk);
+	}
+
+	if (ce->con_id)
+		kfree(ce->con_id);
+
+	kfree(ce);
+}
+
+/**
+ * pm_runtime_clk_remove - Stop using a device clock for runtime PM.
+ * @dev: Device whose clock should not be used for runtime PM any more.
+ * @con_id: Connection ID of the clock.
+ *
+ * Remove the clock represented by @con_id from the list of clocks used for
+ * the runtime PM of @dev.
+ */
+void pm_runtime_clk_remove(struct device *dev, const char *con_id)
+{
+	struct pm_runtime_clk_data *prd = __to_prd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!prd)
+		return;
+
+	mutex_lock(&prd->lock);
+
+	list_for_each_entry(ce, &prd->clock_list, node) {
+		if (!con_id && !ce->con_id) {
+			__pm_runtime_clk_remove(ce);
+			break;
+		} else if (!con_id || !ce->con_id) {
+			continue;
+		} else if (!strcmp(con_id, ce->con_id)) {
+			__pm_runtime_clk_remove(ce);
+			break;
+		}
+	}
+
+	mutex_unlock(&prd->lock);
+}
+
+/**
+ * pm_runtime_clk_init - Initialize a device's list of runtime PM clocks.
+ * @dev: Device to initialize the list of runtime PM clocks for.
+ *
+ * Allocate a struct pm_runtime_clk_data object, initialize its lock member and
+ * make the @dev's power.subsys_data field point to it.
+ */
+int pm_runtime_clk_init(struct device *dev)
+{
+	struct pm_runtime_clk_data *prd;
+
+	prd = kzalloc(sizeof(*prd), GFP_KERNEL);
+	if (!prd) {
+		dev_err(dev, "Not enough memory fo runtime PM data.\n");
+		return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&prd->clock_list);
+	mutex_init(&prd->lock);
+	dev->power.subsys_data = prd;
+	return 0;
+}
+
+/**
+ * pm_runtime_clk_destroy - Destroy a device's list of runtime PM clocks.
+ * @dev: Device to destroy the list of runtime PM clocks for.
+ *
+ * Clear the @dev's power.subsys_data field, remove the list of clock entries
+ * from the struct pm_runtime_clk_data object pointed to by it before and free
+ * that object.
+ */
+void pm_runtime_clk_destroy(struct device *dev)
+{
+	struct pm_runtime_clk_data *prd = __to_prd(dev);
+	struct pm_clock_entry *ce, *c;
+
+	if (!prd)
+		return;
+
+	dev->power.subsys_data = NULL;
+
+	mutex_lock(&prd->lock);
+
+	list_for_each_entry_safe_reverse(ce, c, &prd->clock_list, node)
+		__pm_runtime_clk_remove(ce);
+
+	mutex_unlock(&prd->lock);
+
+	kfree(prd);
+}
+
+/**
+ * pm_runtime_clk_acquire - Acquire a device clock.
+ * @dev: Device whose clock is to be acquired.
+ * @con_id: Connection ID of the clock.
+ */
+static void pm_runtime_clk_acquire(struct device *dev,
+				    struct pm_clock_entry *ce)
+{
+	ce->clk = clk_get(dev, ce->con_id);
+	if (IS_ERR(ce->clk)) {
+		ce->status = PCE_STATUS_ERROR;
+	} else {
+		ce->status = PCE_STATUS_ACQUIRED;
+		dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
+	}
+}
+
+/**
+ * pm_runtime_clk_suspend - Disable clocks in a device's runtime PM clock list.
+ * @dev: Device to disable the clocks for.
+ */
+int pm_runtime_clk_suspend(struct device *dev)
+{
+	struct pm_runtime_clk_data *prd = __to_prd(dev);
+	struct pm_clock_entry *ce;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (!prd)
+		return 0;
+
+	mutex_lock(&prd->lock);
+
+	list_for_each_entry_reverse(ce, &prd->clock_list, node) {
+		if (ce->status == PCE_STATUS_NONE)
+			pm_runtime_clk_acquire(dev, ce);
+
+		if (ce->status < PCE_STATUS_ERROR) {
+			clk_disable(ce->clk);
+			ce->status = PCE_STATUS_ACQUIRED;
+		}
+	}
+
+	mutex_unlock(&prd->lock);
+
+	return 0;
+}
+
+/**
+ * pm_runtime_clk_resume - Enable clocks in a device's runtime PM clock list.
+ * @dev: Device to enable the clocks for.
+ */
+int pm_runtime_clk_resume(struct device *dev)
+{
+	struct pm_runtime_clk_data *prd = __to_prd(dev);
+	struct pm_clock_entry *ce;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (!prd)
+		return 0;
+
+	mutex_lock(&prd->lock);
+
+	list_for_each_entry(ce, &prd->clock_list, node) {
+		if (ce->status == PCE_STATUS_NONE)
+			pm_runtime_clk_acquire(dev, ce);
+
+		if (ce->status < PCE_STATUS_ERROR) {
+			clk_enable(ce->clk);
+			ce->status = PCE_STATUS_ENABLED;
+		}
+	}
+
+	mutex_unlock(&prd->lock);
+
+	return 0;
+}
+
+/**
+ * pm_runtime_clk_notify - Notify routine for device addition and removal.
+ * @nb: Notifier block object this function is a member of.
+ * @action: Operation being carried out by the caller.
+ * @data: Device the routine is being run for.
+ *
+ * For this function to work, @nb must be a member of an object of type
+ * struct pm_clk_notifier_block containing all of the requisite data.
+ * Specifically, the pwr_domain member of that object is copied to the device's
+ * pwr_domain field and its con_ids member is used to populate the device's list
+ * of runtime PM clocks, depending on @action.
+ *
+ * If the device's pwr_domain field is already populated with a value different
+ * from the one stored in the struct pm_clk_notifier_block object, the function
+ * does nothing.
+ */
+static int pm_runtime_clk_notify(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct pm_clk_notifier_block *clknb;
+	struct device *dev = data;
+	char **con_id;
+	int error;
+
+	dev_dbg(dev, "%s() %ld\n", __func__, action);
+
+	clknb = container_of(nb, struct pm_clk_notifier_block, nb);
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		if (dev->pwr_domain)
+			break;
+
+		error = pm_runtime_clk_init(dev);
+		if (error)
+			break;
+
+		dev->pwr_domain = clknb->pwr_domain;
+		if (clknb->con_ids[0]) {
+			for (con_id = clknb->con_ids; *con_id; con_id++)
+				pm_runtime_clk_add(dev, *con_id);
+		} else {
+			pm_runtime_clk_add(dev, NULL);
+		}
+
+		break;
+	case BUS_NOTIFY_DEL_DEVICE:
+		if (dev->pwr_domain != clknb->pwr_domain)
+			break;
+
+		dev->pwr_domain = NULL;
+		pm_runtime_clk_destroy(dev);
+		break;
+	}
+
+	return 0;
+}
+
+#else /* !CONFIG_PM_RUNTIME */
+
+/**
+ * enable_clock - Enable a device clock.
+ * @dev: Device whose clock is to be enabled.
+ * @con_id: Connection ID of the clock.
+ */
+static void enable_clock(struct device *dev, const char *con_id)
+{
+	struct clk *clk;
+
+	clk = clk_get(dev, con_id);
+	if (!IS_ERR(clk)) {
+		clk_enable(clk);
+		clk_put(clk);
+		dev_info(dev, "Runtime PM disabled, clock forced on.\n");
+	}
+}
+
+/**
+ * disable_clock - Disable a device clock.
+ * @dev: Device whose clock is to be disabled.
+ * @con_id: Connection ID of the clock.
+ */
+static void disable_clock(struct device *dev, const char *con_id)
+{
+	struct clk *clk;
+
+	clk = clk_get(dev, con_id);
+	if (!IS_ERR(clk)) {
+		clk_disable(clk);
+		clk_put(clk);
+		dev_info(dev, "Runtime PM disabled, clock forced off.\n");
+	}
+}
+
+/**
+ * pm_runtime_clk_notify - Notify routine for device addition and removal.
+ * @nb: Notifier block object this function is a member of.
+ * @action: Operation being carried out by the caller.
+ * @data: Device the routine is being run for.
+ *
+ * For this function to work, @nb must be a member of an object of type
+ * struct pm_clk_notifier_block containing all of the requisite data.
+ * Specifically, the con_ids member of that object is used to enable or disable
+ * the device's clocks, depending on @action.
+ */
+static int pm_runtime_clk_notify(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct pm_clk_notifier_block *clknb;
+	struct device *dev = data;
+	char **con_id;
+
+	dev_dbg(dev, "%s() %ld\n", __func__, action);
+
+	clknb = container_of(nb, struct pm_clk_notifier_block, nb);
+
+	switch (action) {
+	case BUS_NOTIFY_BIND_DRIVER:
+		if (clknb->con_ids[0]) {
+			for (con_id = clknb->con_ids; *con_id; con_id++)
+				enable_clock(dev, *con_id);
+		} else {
+			enable_clock(dev, NULL);
+		}
+		break;
+	case BUS_NOTIFY_UNBOUND_DRIVER:
+		if (clknb->con_ids[0]) {
+			for (con_id = clknb->con_ids; *con_id; con_id++)
+				disable_clock(dev, *con_id);
+		} else {
+			disable_clock(dev, NULL);
+		}
+		break;
+	}
+
+	return 0;
+}
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+/**
+ * pm_runtime_clk_add_notifier - Add bus type notifier for runtime PM clocks.
+ * @bus: Bus type to add the notifier to.
+ * @clknb: Notifier to be added to the given bus type.
+ *
+ * The nb member of @clknb is not expected to be initialized and its
+ * notifier_call member will be replaced with pm_runtime_clk_notify().  However,
+ * the remaining members of @clknb should be populated prior to calling this
+ * routine.
+ */
+void pm_runtime_clk_add_notifier(struct bus_type *bus,
+				 struct pm_clk_notifier_block *clknb)
+{
+	if (!bus || !clknb)
+		return;
+
+	clknb->nb.notifier_call = pm_runtime_clk_notify;
+	bus_register_notifier(bus, &clknb->nb);
+}
diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c
new file mode 100644
index 00000000..cb3bb368
--- /dev/null
+++ b/drivers/base/power/generic_ops.c
@@ -0,0 +1,272 @@
+/*
+ * drivers/base/power/generic_ops.c - Generic PM callbacks for subsystems
+ *
+ * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+
+#ifdef CONFIG_PM_RUNTIME
+/**
+ * pm_generic_runtime_idle - Generic runtime idle callback for subsystems.
+ * @dev: Device to handle.
+ *
+ * If PM operations are defined for the @dev's driver and they include
+ * ->runtime_idle(), execute it and return its error code, if nonzero.
+ * Otherwise, execute pm_runtime_suspend() for the device and return 0.
+ */
+int pm_generic_runtime_idle(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	if (pm && pm->runtime_idle) {
+		int ret = pm->runtime_idle(dev);
+		if (ret)
+			return ret;
+	}
+
+	pm_runtime_suspend(dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_runtime_idle);
+
+/**
+ * pm_generic_runtime_suspend - Generic runtime suspend callback for subsystems.
+ * @dev: Device to suspend.
+ *
+ * If PM operations are defined for the @dev's driver and they include
+ * ->runtime_suspend(), execute it and return its error code.  Otherwise,
+ * return 0.
+ */
+int pm_generic_runtime_suspend(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	int ret;
+
+	ret = pm && pm->runtime_suspend ? pm->runtime_suspend(dev) : 0;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_generic_runtime_suspend);
+
+/**
+ * pm_generic_runtime_resume - Generic runtime resume callback for subsystems.
+ * @dev: Device to resume.
+ *
+ * If PM operations are defined for the @dev's driver and they include
+ * ->runtime_resume(), execute it and return its error code.  Otherwise,
+ * return 0.
+ */
+int pm_generic_runtime_resume(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	int ret;
+
+	ret = pm && pm->runtime_resume ? pm->runtime_resume(dev) : 0;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_generic_runtime_resume);
+#endif /* CONFIG_PM_RUNTIME */
+
+#ifdef CONFIG_PM_SLEEP
+/**
+ * pm_generic_prepare - Generic routine preparing a device for power transition.
+ * @dev: Device to prepare.
+ *
+ * Prepare a device for a system-wide power transition.
+ */
+int pm_generic_prepare(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (drv && drv->pm && drv->pm->prepare)
+		ret = drv->pm->prepare(dev);
+
+	return ret;
+}
+
+/**
+ * __pm_generic_call - Generic suspend/freeze/poweroff/thaw subsystem callback.
+ * @dev: Device to handle.
+ * @event: PM transition of the system under way.
+ *
+ * If the device has not been suspended at run time, execute the
+ * suspend/freeze/poweroff/thaw callback provided by its driver, if defined, and
+ * return its error code.  Otherwise, return zero.
+ */
+static int __pm_generic_call(struct device *dev, int event)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	int (*callback)(struct device *);
+
+	if (!pm || pm_runtime_suspended(dev))
+		return 0;
+
+	switch (event) {
+	case PM_EVENT_SUSPEND:
+		callback = pm->suspend;
+		break;
+	case PM_EVENT_FREEZE:
+		callback = pm->freeze;
+		break;
+	case PM_EVENT_HIBERNATE:
+		callback = pm->poweroff;
+		break;
+	case PM_EVENT_THAW:
+		callback = pm->thaw;
+		break;
+	default:
+		callback = NULL;
+		break;
+	}
+
+	return callback ? callback(dev) : 0;
+}
+
+/**
+ * pm_generic_suspend - Generic suspend callback for subsystems.
+ * @dev: Device to suspend.
+ */
+int pm_generic_suspend(struct device *dev)
+{
+	return __pm_generic_call(dev, PM_EVENT_SUSPEND);
+}
+EXPORT_SYMBOL_GPL(pm_generic_suspend);
+
+/**
+ * pm_generic_freeze - Generic freeze callback for subsystems.
+ * @dev: Device to freeze.
+ */
+int pm_generic_freeze(struct device *dev)
+{
+	return __pm_generic_call(dev, PM_EVENT_FREEZE);
+}
+EXPORT_SYMBOL_GPL(pm_generic_freeze);
+
+/**
+ * pm_generic_poweroff - Generic poweroff callback for subsystems.
+ * @dev: Device to handle.
+ */
+int pm_generic_poweroff(struct device *dev)
+{
+	return __pm_generic_call(dev, PM_EVENT_HIBERNATE);
+}
+EXPORT_SYMBOL_GPL(pm_generic_poweroff);
+
+/**
+ * pm_generic_thaw - Generic thaw callback for subsystems.
+ * @dev: Device to thaw.
+ */
+int pm_generic_thaw(struct device *dev)
+{
+	return __pm_generic_call(dev, PM_EVENT_THAW);
+}
+EXPORT_SYMBOL_GPL(pm_generic_thaw);
+
+/**
+ * __pm_generic_resume - Generic resume/restore callback for subsystems.
+ * @dev: Device to handle.
+ * @event: PM transition of the system under way.
+ *
+ * Execute the resume/resotre callback provided by the @dev's driver, if
+ * defined.  If it returns 0, change the device's runtime PM status to 'active'.
+ * Return the callback's error code.
+ */
+static int __pm_generic_resume(struct device *dev, int event)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	int (*callback)(struct device *);
+	int ret;
+
+	if (!pm)
+		return 0;
+
+	switch (event) {
+	case PM_EVENT_RESUME:
+		callback = pm->resume;
+		break;
+	case PM_EVENT_RESTORE:
+		callback = pm->restore;
+		break;
+	default:
+		callback = NULL;
+		break;
+	}
+
+	if (!callback)
+		return 0;
+
+	ret = callback(dev);
+	if (!ret && pm_runtime_enabled(dev)) {
+		pm_runtime_disable(dev);
+		pm_runtime_set_active(dev);
+		pm_runtime_enable(dev);
+	}
+
+	return ret;
+}
+
+/**
+ * pm_generic_resume - Generic resume callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_resume(struct device *dev)
+{
+	return __pm_generic_resume(dev, PM_EVENT_RESUME);
+}
+EXPORT_SYMBOL_GPL(pm_generic_resume);
+
+/**
+ * pm_generic_restore - Generic restore callback for subsystems.
+ * @dev: Device to restore.
+ */
+int pm_generic_restore(struct device *dev)
+{
+	return __pm_generic_resume(dev, PM_EVENT_RESTORE);
+}
+EXPORT_SYMBOL_GPL(pm_generic_restore);
+
+/**
+ * pm_generic_complete - Generic routine competing a device power transition.
+ * @dev: Device to handle.
+ *
+ * Complete a device power transition during a system-wide power transition.
+ */
+void pm_generic_complete(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+
+	if (drv && drv->pm && drv->pm->complete)
+		drv->pm->complete(dev);
+
+	/*
+	 * Let runtime PM try to suspend devices that haven't been in use before
+	 * going into the system-wide sleep state we're resuming from.
+	 */
+	pm_runtime_idle(dev);
+}
+#endif /* CONFIG_PM_SLEEP */
+
+struct dev_pm_ops generic_subsys_pm_ops = {
+#ifdef CONFIG_PM_SLEEP
+	.prepare = pm_generic_prepare,
+	.suspend = pm_generic_suspend,
+	.resume = pm_generic_resume,
+	.freeze = pm_generic_freeze,
+	.thaw = pm_generic_thaw,
+	.poweroff = pm_generic_poweroff,
+	.restore = pm_generic_restore,
+	.complete = pm_generic_complete,
+#endif
+#ifdef CONFIG_PM_RUNTIME
+	.runtime_suspend = pm_generic_runtime_suspend,
+	.runtime_resume = pm_generic_runtime_resume,
+	.runtime_idle = pm_generic_runtime_idle,
+#endif
+};
+EXPORT_SYMBOL_GPL(generic_subsys_pm_ops);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
new file mode 100644
index 00000000..b4e94fce
--- /dev/null
+++ b/drivers/base/power/main.c
@@ -0,0 +1,1188 @@
+/*
+ * drivers/base/power/main.c - Where the driver meets power management.
+ *
+ * Copyright (c) 2003 Patrick Mochel
+ * Copyright (c) 2003 Open Source Development Lab
+ *
+ * This file is released under the GPLv2
+ *
+ *
+ * The driver model core calls device_pm_add() when a device is registered.
+ * This will initialize the embedded device_pm_info object in the device
+ * and add it to the list of power-controlled devices. sysfs entries for
+ * controlling device power management will also be added.
+ *
+ * A separate list is used for keeping track of power info, because the power
+ * domain dependencies may differ from the ancestral dependencies that the
+ * subsystem list maintains.
+ */
+
+#include <linux/device.h>
+#include <linux/kallsyms.h>
+#include <linux/mutex.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/resume-trace.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/async.h>
+#include <linux/suspend.h>
+#include <linux/timer.h>
+
+#include "../base.h"
+#include "power.h"
+
+/*
+ * The entries in the dpm_list list are in a depth first order, simply
+ * because children are guaranteed to be discovered after parents, and
+ * are inserted at the back of the list on discovery.
+ *
+ * Since device_pm_add() may be called with a device lock held,
+ * we must never try to acquire a device lock while holding
+ * dpm_list_mutex.
+ */
+
+LIST_HEAD(dpm_list);
+LIST_HEAD(dpm_prepared_list);
+LIST_HEAD(dpm_suspended_list);
+LIST_HEAD(dpm_noirq_list);
+
+static DEFINE_MUTEX(dpm_list_mtx);
+static pm_message_t pm_transition;
+
+static void dpm_drv_timeout(unsigned long data);
+struct dpm_drv_wd_data {
+	struct device *dev;
+	struct task_struct *tsk;
+};
+
+static int async_error;
+
+/**
+ * device_pm_init - Initialize the PM-related part of a device object.
+ * @dev: Device object being initialized.
+ */
+void device_pm_init(struct device *dev)
+{
+	dev->power.is_prepared = false;
+	dev->power.is_suspended = false;
+	init_completion(&dev->power.completion);
+	complete_all(&dev->power.completion);
+	dev->power.wakeup = NULL;
+	spin_lock_init(&dev->power.lock);
+	pm_runtime_init(dev);
+	INIT_LIST_HEAD(&dev->power.entry);
+}
+
+/**
+ * device_pm_lock - Lock the list of active devices used by the PM core.
+ */
+void device_pm_lock(void)
+{
+	mutex_lock(&dpm_list_mtx);
+}
+
+/**
+ * device_pm_unlock - Unlock the list of active devices used by the PM core.
+ */
+void device_pm_unlock(void)
+{
+	mutex_unlock(&dpm_list_mtx);
+}
+
+/**
+ * device_pm_add - Add a device to the PM core's list of active devices.
+ * @dev: Device to add to the list.
+ */
+void device_pm_add(struct device *dev)
+{
+	pr_debug("PM: Adding info for %s:%s\n",
+		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
+	mutex_lock(&dpm_list_mtx);
+	if (dev->parent && dev->parent->power.is_prepared)
+		dev_warn(dev, "parent %s should not be sleeping\n",
+			dev_name(dev->parent));
+	list_add_tail(&dev->power.entry, &dpm_list);
+	mutex_unlock(&dpm_list_mtx);
+}
+
+/**
+ * device_pm_remove - Remove a device from the PM core's list of active devices.
+ * @dev: Device to be removed from the list.
+ */
+void device_pm_remove(struct device *dev)
+{
+	pr_debug("PM: Removing info for %s:%s\n",
+		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
+	complete_all(&dev->power.completion);
+	mutex_lock(&dpm_list_mtx);
+	list_del_init(&dev->power.entry);
+	mutex_unlock(&dpm_list_mtx);
+	device_wakeup_disable(dev);
+	pm_runtime_remove(dev);
+}
+
+/**
+ * device_pm_move_before - Move device in the PM core's list of active devices.
+ * @deva: Device to move in dpm_list.
+ * @devb: Device @deva should come before.
+ */
+void device_pm_move_before(struct device *deva, struct device *devb)
+{
+	pr_debug("PM: Moving %s:%s before %s:%s\n",
+		 deva->bus ? deva->bus->name : "No Bus", dev_name(deva),
+		 devb->bus ? devb->bus->name : "No Bus", dev_name(devb));
+	/* Delete deva from dpm_list and reinsert before devb. */
+	list_move_tail(&deva->power.entry, &devb->power.entry);
+}
+
+/**
+ * device_pm_move_after - Move device in the PM core's list of active devices.
+ * @deva: Device to move in dpm_list.
+ * @devb: Device @deva should come after.
+ */
+void device_pm_move_after(struct device *deva, struct device *devb)
+{
+	pr_debug("PM: Moving %s:%s after %s:%s\n",
+		 deva->bus ? deva->bus->name : "No Bus", dev_name(deva),
+		 devb->bus ? devb->bus->name : "No Bus", dev_name(devb));
+	/* Delete deva from dpm_list and reinsert after devb. */
+	list_move(&deva->power.entry, &devb->power.entry);
+}
+
+/**
+ * device_pm_move_last - Move device to end of the PM core's list of devices.
+ * @dev: Device to move in dpm_list.
+ */
+void device_pm_move_last(struct device *dev)
+{
+	pr_debug("PM: Moving %s:%s to end of list\n",
+		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
+	list_move_tail(&dev->power.entry, &dpm_list);
+}
+
+static ktime_t initcall_debug_start(struct device *dev)
+{
+	ktime_t calltime = ktime_set(0, 0);
+
+	if (initcall_debug) {
+		pr_info("calling  %s+ @ %i\n",
+				dev_name(dev), task_pid_nr(current));
+		calltime = ktime_get();
+	}
+
+	return calltime;
+}
+
+static void initcall_debug_report(struct device *dev, ktime_t calltime,
+				  int error)
+{
+	ktime_t delta, rettime;
+
+	if (initcall_debug) {
+		rettime = ktime_get();
+		delta = ktime_sub(rettime, calltime);
+		pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev),
+			error, (unsigned long long)ktime_to_ns(delta) >> 10);
+	}
+}
+#ifdef CONFIG_SUSPEND_DEVICE_TIME_DEBUG
+static void suspend_time_debug_start(ktime_t *start)
+{
+	*start = ktime_get();
+}
+
+static void suspend_time_debug_report(const char *name, struct device *dev,
+				      ktime_t starttime)
+{
+	ktime_t rettime;
+	s64 usecs64;
+	int usecs;
+
+	if (!dev->driver)
+		return;
+
+	rettime = ktime_get();
+	usecs64 = ktime_to_us(ktime_sub(rettime, starttime));
+	usecs = usecs64;
+	if (usecs == 0)
+		usecs = 1;
+
+	if (device_suspend_time_threshold
+	    && usecs > device_suspend_time_threshold)
+		pr_info("PM: device %s:%s %s too slow, it takes \t %ld.%03ld msecs\n",
+			dev->bus->name, dev_name(dev), name,
+			usecs / USEC_PER_MSEC, usecs % USEC_PER_MSEC);
+}
+#else
+static void suspend_time_debug_start(ktime_t *start) {}
+static void suspend_time_debug_report(const char *name, struct device *dev,
+				      ktime_t starttime) {}
+#endif /* CONFIG_SUSPEND_DEVICE_TIME_DEBUG */
+
+/**
+ * dpm_wait - Wait for a PM operation to complete.
+ * @dev: Device to wait for.
+ * @async: If unset, wait only if the device's power.async_suspend flag is set.
+ */
+static void dpm_wait(struct device *dev, bool async)
+{
+	if (!dev)
+		return;
+
+	if (async || (pm_async_enabled && dev->power.async_suspend))
+		wait_for_completion(&dev->power.completion);
+}
+
+static int dpm_wait_fn(struct device *dev, void *async_ptr)
+{
+	dpm_wait(dev, *((bool *)async_ptr));
+	return 0;
+}
+
+static void dpm_wait_for_children(struct device *dev, bool async)
+{
+       device_for_each_child(dev, &async, dpm_wait_fn);
+}
+
+/**
+ * pm_op - Execute the PM operation appropriate for given PM event.
+ * @dev: Device to handle.
+ * @ops: PM operations to choose from.
+ * @state: PM transition of the system being carried out.
+ */
+static int pm_op(struct device *dev,
+		 const struct dev_pm_ops *ops,
+		 pm_message_t state)
+{
+	int error = 0;
+	ktime_t calltime, starttime;
+
+	calltime = initcall_debug_start(dev);
+
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		if (ops->suspend) {
+			suspend_time_debug_start(&starttime);
+			error = ops->suspend(dev);
+			suspend_time_debug_report("suspend", dev, starttime);
+			suspend_report_result(ops->suspend, error);
+		}
+		break;
+	case PM_EVENT_RESUME:
+		if (ops->resume) {
+			suspend_time_debug_start(&starttime);
+			error = ops->resume(dev);
+			suspend_time_debug_report("resume", dev, starttime);
+			suspend_report_result(ops->resume, error);
+		}
+		break;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		if (ops->freeze) {
+			error = ops->freeze(dev);
+			suspend_report_result(ops->freeze, error);
+		}
+		break;
+	case PM_EVENT_HIBERNATE:
+		if (ops->poweroff) {
+			error = ops->poweroff(dev);
+			suspend_report_result(ops->poweroff, error);
+		}
+		break;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		if (ops->thaw) {
+			error = ops->thaw(dev);
+			suspend_report_result(ops->thaw, error);
+		}
+		break;
+	case PM_EVENT_RESTORE:
+		if (ops->restore) {
+			error = ops->restore(dev);
+			suspend_report_result(ops->restore, error);
+		}
+		break;
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
+	default:
+		error = -EINVAL;
+	}
+
+	initcall_debug_report(dev, calltime, error);
+
+	return error;
+}
+
+/**
+ * pm_noirq_op - Execute the PM operation appropriate for given PM event.
+ * @dev: Device to handle.
+ * @ops: PM operations to choose from.
+ * @state: PM transition of the system being carried out.
+ *
+ * The driver of @dev will not receive interrupts while this function is being
+ * executed.
+ */
+static int pm_noirq_op(struct device *dev,
+			const struct dev_pm_ops *ops,
+			pm_message_t state)
+{
+	int error = 0;
+	ktime_t calltime = ktime_set(0, 0), delta, rettime;
+
+	if (initcall_debug) {
+		pr_info("calling  %s+ @ %i, parent: %s\n",
+				dev_name(dev), task_pid_nr(current),
+				dev->parent ? dev_name(dev->parent) : "none");
+		calltime = ktime_get();
+	}
+
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		if (ops->suspend_noirq) {
+			error = ops->suspend_noirq(dev);
+			suspend_report_result(ops->suspend_noirq, error);
+		}
+		break;
+	case PM_EVENT_RESUME:
+		if (ops->resume_noirq) {
+			error = ops->resume_noirq(dev);
+			suspend_report_result(ops->resume_noirq, error);
+		}
+		break;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		if (ops->freeze_noirq) {
+			error = ops->freeze_noirq(dev);
+			suspend_report_result(ops->freeze_noirq, error);
+		}
+		break;
+	case PM_EVENT_HIBERNATE:
+		if (ops->poweroff_noirq) {
+			error = ops->poweroff_noirq(dev);
+			suspend_report_result(ops->poweroff_noirq, error);
+		}
+		break;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		if (ops->thaw_noirq) {
+			error = ops->thaw_noirq(dev);
+			suspend_report_result(ops->thaw_noirq, error);
+		}
+		break;
+	case PM_EVENT_RESTORE:
+		if (ops->restore_noirq) {
+			error = ops->restore_noirq(dev);
+			suspend_report_result(ops->restore_noirq, error);
+		}
+		break;
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
+	default:
+		error = -EINVAL;
+	}
+
+	if (initcall_debug) {
+		rettime = ktime_get();
+		delta = ktime_sub(rettime, calltime);
+		printk("initcall %s_i+ returned %d after %Ld usecs\n",
+			dev_name(dev), error,
+			(unsigned long long)ktime_to_ns(delta) >> 10);
+	}
+
+	return error;
+}
+
+static char *pm_verb(int event)
+{
+	switch (event) {
+	case PM_EVENT_SUSPEND:
+		return "suspend";
+	case PM_EVENT_RESUME:
+		return "resume";
+	case PM_EVENT_FREEZE:
+		return "freeze";
+	case PM_EVENT_QUIESCE:
+		return "quiesce";
+	case PM_EVENT_HIBERNATE:
+		return "hibernate";
+	case PM_EVENT_THAW:
+		return "thaw";
+	case PM_EVENT_RESTORE:
+		return "restore";
+	case PM_EVENT_RECOVER:
+		return "recover";
+	default:
+		return "(unknown PM event)";
+	}
+}
+
+static void pm_dev_dbg(struct device *dev, pm_message_t state, char *info)
+{
+	dev_dbg(dev, "%s%s%s\n", info, pm_verb(state.event),
+		((state.event & PM_EVENT_SLEEP) && device_may_wakeup(dev)) ?
+		", may wakeup" : "");
+}
+
+static void pm_dev_err(struct device *dev, pm_message_t state, char *info,
+			int error)
+{
+	printk(KERN_ERR "PM: Device %s failed to %s%s: error %d\n",
+		dev_name(dev), pm_verb(state.event), info, error);
+}
+
+static void dpm_show_time(ktime_t starttime, pm_message_t state, char *info)
+{
+	ktime_t calltime;
+	u64 usecs64;
+	int usecs;
+
+	calltime = ktime_get();
+	usecs64 = ktime_to_ns(ktime_sub(calltime, starttime));
+	do_div(usecs64, NSEC_PER_USEC);
+	usecs = usecs64;
+	if (usecs == 0)
+		usecs = 1;
+	pr_info("PM: %s%s%s of devices complete after %ld.%03ld msecs\n",
+		info ?: "", info ? " " : "", pm_verb(state.event),
+		usecs / USEC_PER_MSEC, usecs % USEC_PER_MSEC);
+}
+
+/*------------------------- Resume routines -------------------------*/
+
+/**
+ * device_resume_noirq - Execute an "early resume" callback for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ *
+ * The driver of @dev will not receive interrupts while this function is being
+ * executed.
+ */
+static int device_resume_noirq(struct device *dev, pm_message_t state)
+{
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_RESUME(0);
+
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "EARLY power domain ");
+		error = pm_noirq_op(dev, &dev->pwr_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		pm_dev_dbg(dev, state, "EARLY type ");
+		error = pm_noirq_op(dev, dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		pm_dev_dbg(dev, state, "EARLY class ");
+		error = pm_noirq_op(dev, dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		pm_dev_dbg(dev, state, "EARLY ");
+		error = pm_noirq_op(dev, dev->bus->pm, state);
+	}
+
+	TRACE_RESUME(error);
+	return error;
+}
+
+/**
+ * dpm_resume_noirq - Execute "early resume" callbacks for non-sysdev devices.
+ * @state: PM transition of the system being carried out.
+ *
+ * Call the "noirq" resume handlers for all devices marked as DPM_OFF_IRQ and
+ * enable device drivers to receive interrupts.
+ */
+void dpm_resume_noirq(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+
+	mutex_lock(&dpm_list_mtx);
+	while (!list_empty(&dpm_noirq_list)) {
+		struct device *dev = to_device(dpm_noirq_list.next);
+		int error;
+
+		get_device(dev);
+		list_move_tail(&dev->power.entry, &dpm_suspended_list);
+		mutex_unlock(&dpm_list_mtx);
+
+		error = device_resume_noirq(dev, state);
+		if (error)
+			pm_dev_err(dev, state, " early", error);
+
+		mutex_lock(&dpm_list_mtx);
+		put_device(dev);
+	}
+	mutex_unlock(&dpm_list_mtx);
+	dpm_show_time(starttime, state, "early");
+	resume_device_irqs();
+}
+EXPORT_SYMBOL_GPL(dpm_resume_noirq);
+
+/**
+ * legacy_resume - Execute a legacy (bus or class) resume callback for device.
+ * @dev: Device to resume.
+ * @cb: Resume callback to execute.
+ */
+static int legacy_resume(struct device *dev, int (*cb)(struct device *dev))
+{
+	int error;
+	ktime_t calltime;
+
+	calltime = initcall_debug_start(dev);
+
+	error = cb(dev);
+	suspend_report_result(cb, error);
+
+	initcall_debug_report(dev, calltime, error);
+
+	return error;
+}
+
+/**
+ * device_resume - Execute "resume" callbacks for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ * @async: If true, the device is being resumed asynchronously.
+ */
+static int device_resume(struct device *dev, pm_message_t state, bool async)
+{
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_RESUME(0);
+
+	dpm_wait(dev->parent, async);
+	device_lock(dev);
+
+	/*
+	 * This is a fib.  But we'll allow new children to be added below
+	 * a resumed device, even if the device hasn't been completed yet.
+	 */
+	dev->power.is_prepared = false;
+
+	if (!dev->power.is_suspended)
+		goto Unlock;
+
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "power domain ");
+		error = pm_op(dev, &dev->pwr_domain->ops, state);
+		goto End;
+	}
+
+	if (dev->type && dev->type->pm) {
+		pm_dev_dbg(dev, state, "type ");
+		error = pm_op(dev, dev->type->pm, state);
+		goto End;
+	}
+
+	if (dev->class) {
+		if (dev->class->pm) {
+			pm_dev_dbg(dev, state, "class ");
+			error = pm_op(dev, dev->class->pm, state);
+			goto End;
+		} else if (dev->class->resume) {
+			pm_dev_dbg(dev, state, "legacy class ");
+			error = legacy_resume(dev, dev->class->resume);
+			goto End;
+		}
+	}
+
+	if (dev->bus) {
+		if (dev->bus->pm) {
+			pm_dev_dbg(dev, state, "");
+			error = pm_op(dev, dev->bus->pm, state);
+		} else if (dev->bus->resume) {
+			pm_dev_dbg(dev, state, "legacy ");
+			error = legacy_resume(dev, dev->bus->resume);
+		}
+	}
+
+ End:
+	dev->power.is_suspended = false;
+
+ Unlock:
+	device_unlock(dev);
+	complete_all(&dev->power.completion);
+
+	TRACE_RESUME(error);
+	return error;
+}
+
+static void async_resume(void *data, async_cookie_t cookie)
+{
+	struct device *dev = (struct device *)data;
+	int error;
+
+	error = device_resume(dev, pm_transition, true);
+	if (error)
+		pm_dev_err(dev, pm_transition, " async", error);
+	put_device(dev);
+}
+
+static bool is_async(struct device *dev)
+{
+	return dev->power.async_suspend && pm_async_enabled
+		&& !pm_trace_is_enabled();
+}
+
+/**
+ *	dpm_drv_timeout - Driver suspend / resume watchdog handler
+ *	@data: struct device which timed out
+ *
+ * 	Called when a driver has timed out suspending or resuming.
+ * 	There's not much we can do here to recover so
+ * 	BUG() out for a crash-dump
+ *
+ */
+static void dpm_drv_timeout(unsigned long data)
+{
+	struct dpm_drv_wd_data *wd_data = (void *)data;
+	struct device *dev = wd_data->dev;
+	struct task_struct *tsk = wd_data->tsk;
+
+	printk(KERN_EMERG "**** DPM device timeout: %s (%s)\n", dev_name(dev),
+	       (dev->driver ? dev->driver->name : "no driver"));
+
+	printk(KERN_EMERG "dpm suspend stack:\n");
+	show_stack(tsk, NULL);
+
+	BUG();
+}
+
+/**
+ * dpm_resume - Execute "resume" callbacks for non-sysdev devices.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute the appropriate "resume" callback for all devices whose status
+ * indicates that they are suspended.
+ */
+void dpm_resume(pm_message_t state)
+{
+	struct device *dev;
+	ktime_t starttime = ktime_get();
+
+	might_sleep();
+
+	mutex_lock(&dpm_list_mtx);
+	pm_transition = state;
+	async_error = 0;
+
+	list_for_each_entry(dev, &dpm_suspended_list, power.entry) {
+		INIT_COMPLETION(dev->power.completion);
+		if (is_async(dev)) {
+			get_device(dev);
+			async_schedule(async_resume, dev);
+		}
+	}
+
+	while (!list_empty(&dpm_suspended_list)) {
+		dev = to_device(dpm_suspended_list.next);
+		get_device(dev);
+		if (!is_async(dev)) {
+			int error;
+
+			mutex_unlock(&dpm_list_mtx);
+
+			error = device_resume(dev, state, false);
+			if (error)
+				pm_dev_err(dev, state, "", error);
+
+			mutex_lock(&dpm_list_mtx);
+		}
+		if (!list_empty(&dev->power.entry))
+			list_move_tail(&dev->power.entry, &dpm_prepared_list);
+		put_device(dev);
+	}
+	mutex_unlock(&dpm_list_mtx);
+	async_synchronize_full();
+	dpm_show_time(starttime, state, NULL);
+}
+
+/**
+ * device_complete - Complete a PM transition for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ */
+static void device_complete(struct device *dev, pm_message_t state)
+{
+	device_lock(dev);
+
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "completing power domain ");
+		if (dev->pwr_domain->ops.complete)
+			dev->pwr_domain->ops.complete(dev);
+	} else if (dev->type && dev->type->pm) {
+		pm_dev_dbg(dev, state, "completing type ");
+		if (dev->type->pm->complete)
+			dev->type->pm->complete(dev);
+	} else if (dev->class && dev->class->pm) {
+		pm_dev_dbg(dev, state, "completing class ");
+		if (dev->class->pm->complete)
+			dev->class->pm->complete(dev);
+	} else if (dev->bus && dev->bus->pm) {
+		pm_dev_dbg(dev, state, "completing ");
+		if (dev->bus->pm->complete)
+			dev->bus->pm->complete(dev);
+	}
+
+	device_unlock(dev);
+}
+
+/**
+ * dpm_complete - Complete a PM transition for all non-sysdev devices.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute the ->complete() callbacks for all devices whose PM status is not
+ * DPM_ON (this allows new devices to be registered).
+ */
+void dpm_complete(pm_message_t state)
+{
+	struct list_head list;
+
+	might_sleep();
+
+	INIT_LIST_HEAD(&list);
+	mutex_lock(&dpm_list_mtx);
+	while (!list_empty(&dpm_prepared_list)) {
+		struct device *dev = to_device(dpm_prepared_list.prev);
+
+		get_device(dev);
+		dev->power.is_prepared = false;
+		list_move(&dev->power.entry, &list);
+		mutex_unlock(&dpm_list_mtx);
+
+		device_complete(dev, state);
+
+		mutex_lock(&dpm_list_mtx);
+		put_device(dev);
+	}
+	list_splice(&list, &dpm_list);
+	mutex_unlock(&dpm_list_mtx);
+}
+
+/**
+ * dpm_resume_end - Execute "resume" callbacks and complete system transition.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute "resume" callbacks for all devices and complete the PM transition of
+ * the system.
+ */
+void dpm_resume_end(pm_message_t state)
+{
+	dpm_resume(state);
+	dpm_complete(state);
+}
+EXPORT_SYMBOL_GPL(dpm_resume_end);
+
+
+/*------------------------- Suspend routines -------------------------*/
+
+/**
+ * resume_event - Return a "resume" message for given "suspend" sleep state.
+ * @sleep_state: PM message representing a sleep state.
+ *
+ * Return a PM message representing the resume event corresponding to given
+ * sleep state.
+ */
+static pm_message_t resume_event(pm_message_t sleep_state)
+{
+	switch (sleep_state.event) {
+	case PM_EVENT_SUSPEND:
+		return PMSG_RESUME;
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		return PMSG_RECOVER;
+	case PM_EVENT_HIBERNATE:
+		return PMSG_RESTORE;
+	}
+	return PMSG_ON;
+}
+
+/**
+ * device_suspend_noirq - Execute a "late suspend" callback for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ *
+ * The driver of @dev will not receive interrupts while this function is being
+ * executed.
+ */
+static int device_suspend_noirq(struct device *dev, pm_message_t state)
+{
+	int error;
+
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "LATE power domain ");
+		error = pm_noirq_op(dev, &dev->pwr_domain->ops, state);
+		if (error)
+			return error;
+	} else if (dev->type && dev->type->pm) {
+		pm_dev_dbg(dev, state, "LATE type ");
+		error = pm_noirq_op(dev, dev->type->pm, state);
+		if (error)
+			return error;
+	} else if (dev->class && dev->class->pm) {
+		pm_dev_dbg(dev, state, "LATE class ");
+		error = pm_noirq_op(dev, dev->class->pm, state);
+		if (error)
+			return error;
+	} else if (dev->bus && dev->bus->pm) {
+		pm_dev_dbg(dev, state, "LATE ");
+		error = pm_noirq_op(dev, dev->bus->pm, state);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/**
+ * dpm_suspend_noirq - Execute "late suspend" callbacks for non-sysdev devices.
+ * @state: PM transition of the system being carried out.
+ *
+ * Prevent device drivers from receiving interrupts and call the "noirq" suspend
+ * handlers for all non-sysdev devices.
+ */
+int dpm_suspend_noirq(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+	int error = 0;
+
+	suspend_device_irqs();
+	mutex_lock(&dpm_list_mtx);
+	while (!list_empty(&dpm_suspended_list)) {
+		struct device *dev = to_device(dpm_suspended_list.prev);
+
+		get_device(dev);
+		mutex_unlock(&dpm_list_mtx);
+
+		error = device_suspend_noirq(dev, state);
+
+		mutex_lock(&dpm_list_mtx);
+		if (error) {
+			pm_dev_err(dev, state, " late", error);
+			put_device(dev);
+			break;
+		}
+		if (!list_empty(&dev->power.entry))
+			list_move(&dev->power.entry, &dpm_noirq_list);
+		put_device(dev);
+	}
+	mutex_unlock(&dpm_list_mtx);
+	if (error) {
+		resume_irqs(true);
+		dpm_resume_noirq(resume_event(state));
+	}
+	else
+		dpm_show_time(starttime, state, "late");
+	return error;
+}
+EXPORT_SYMBOL_GPL(dpm_suspend_noirq);
+
+/**
+ * legacy_suspend - Execute a legacy (bus or class) suspend callback for device.
+ * @dev: Device to suspend.
+ * @state: PM transition of the system being carried out.
+ * @cb: Suspend callback to execute.
+ */
+static int legacy_suspend(struct device *dev, pm_message_t state,
+			  int (*cb)(struct device *dev, pm_message_t state))
+{
+	int error;
+	ktime_t calltime;
+
+	calltime = initcall_debug_start(dev);
+
+	error = cb(dev, state);
+	suspend_report_result(cb, error);
+
+	initcall_debug_report(dev, calltime, error);
+
+	return error;
+}
+
+/**
+ * device_suspend - Execute "suspend" callbacks for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ * @async: If true, the device is being suspended asynchronously.
+ */
+static int __device_suspend(struct device *dev, pm_message_t state, bool async)
+{
+	int error = 0;
+	struct timer_list timer;
+	struct dpm_drv_wd_data data;
+
+	dpm_wait_for_children(dev, async);
+
+	data.dev = dev;
+	data.tsk = get_current();
+	init_timer_on_stack(&timer);
+	timer.expires = jiffies + HZ * 12;
+	timer.function = dpm_drv_timeout;
+	timer.data = (unsigned long)&data;
+	add_timer(&timer);
+
+	device_lock(dev);
+
+	if (async_error)
+		goto Unlock;
+
+	if (pm_wakeup_pending()) {
+		async_error = -EBUSY;
+		goto Unlock;
+	}
+
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "power domain ");
+		error = pm_op(dev, &dev->pwr_domain->ops, state);
+		goto End;
+	}
+
+	if (dev->type && dev->type->pm) {
+		pm_dev_dbg(dev, state, "type ");
+		error = pm_op(dev, dev->type->pm, state);
+		goto End;
+	}
+
+	if (dev->class) {
+		if (dev->class->pm) {
+			pm_dev_dbg(dev, state, "class ");
+			error = pm_op(dev, dev->class->pm, state);
+			goto End;
+		} else if (dev->class->suspend) {
+			pm_dev_dbg(dev, state, "legacy class ");
+			error = legacy_suspend(dev, state, dev->class->suspend);
+			goto End;
+		}
+	}
+
+	if (dev->bus) {
+		if (dev->bus->pm) {
+			pm_dev_dbg(dev, state, "");
+			error = pm_op(dev, dev->bus->pm, state);
+		} else if (dev->bus->suspend) {
+			pm_dev_dbg(dev, state, "legacy ");
+			error = legacy_suspend(dev, state, dev->bus->suspend);
+		}
+	}
+
+ End:
+	dev->power.is_suspended = !error;
+
+ Unlock:
+	device_unlock(dev);
+
+	del_timer_sync(&timer);
+	destroy_timer_on_stack(&timer);
+
+	complete_all(&dev->power.completion);
+
+	if (error)
+		async_error = error;
+
+	return error;
+}
+
+static void async_suspend(void *data, async_cookie_t cookie)
+{
+	struct device *dev = (struct device *)data;
+	int error;
+
+	error = __device_suspend(dev, pm_transition, true);
+	if (error)
+		pm_dev_err(dev, pm_transition, " async", error);
+
+	put_device(dev);
+}
+
+static int device_suspend(struct device *dev)
+{
+	INIT_COMPLETION(dev->power.completion);
+
+	if (pm_async_enabled && dev->power.async_suspend) {
+		get_device(dev);
+		async_schedule(async_suspend, dev);
+		return 0;
+	}
+
+	return __device_suspend(dev, pm_transition, false);
+}
+
+/**
+ * dpm_suspend - Execute "suspend" callbacks for all non-sysdev devices.
+ * @state: PM transition of the system being carried out.
+ */
+int dpm_suspend(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+	int error = 0;
+
+	might_sleep();
+
+	mutex_lock(&dpm_list_mtx);
+	pm_transition = state;
+	async_error = 0;
+	while (!list_empty(&dpm_prepared_list)) {
+		struct device *dev = to_device(dpm_prepared_list.prev);
+
+		get_device(dev);
+		mutex_unlock(&dpm_list_mtx);
+
+		error = device_suspend(dev);
+
+		mutex_lock(&dpm_list_mtx);
+		if (error) {
+			pm_dev_err(dev, state, "", error);
+			put_device(dev);
+			break;
+		}
+		if (!list_empty(&dev->power.entry))
+			list_move(&dev->power.entry, &dpm_suspended_list);
+		put_device(dev);
+		if (async_error)
+			break;
+	}
+	mutex_unlock(&dpm_list_mtx);
+	async_synchronize_full();
+	if (!error)
+		error = async_error;
+	if (!error)
+		dpm_show_time(starttime, state, NULL);
+	return error;
+}
+
+/**
+ * device_prepare - Prepare a device for system power transition.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute the ->prepare() callback(s) for given device.  No new children of the
+ * device may be registered after this function has returned.
+ */
+static int device_prepare(struct device *dev, pm_message_t state)
+{
+	int error = 0;
+
+	device_lock(dev);
+
+	if (dev->pwr_domain) {
+		pm_dev_dbg(dev, state, "preparing power domain ");
+		if (dev->pwr_domain->ops.prepare)
+			error = dev->pwr_domain->ops.prepare(dev);
+		suspend_report_result(dev->pwr_domain->ops.prepare, error);
+		if (error)
+			goto End;
+	} else if (dev->type && dev->type->pm) {
+		pm_dev_dbg(dev, state, "preparing type ");
+		if (dev->type->pm->prepare)
+			error = dev->type->pm->prepare(dev);
+		suspend_report_result(dev->type->pm->prepare, error);
+		if (error)
+			goto End;
+	} else if (dev->class && dev->class->pm) {
+		pm_dev_dbg(dev, state, "preparing class ");
+		if (dev->class->pm->prepare)
+			error = dev->class->pm->prepare(dev);
+		suspend_report_result(dev->class->pm->prepare, error);
+		if (error)
+			goto End;
+	} else if (dev->bus && dev->bus->pm) {
+		pm_dev_dbg(dev, state, "preparing ");
+		if (dev->bus->pm->prepare)
+			error = dev->bus->pm->prepare(dev);
+		suspend_report_result(dev->bus->pm->prepare, error);
+	}
+
+ End:
+	device_unlock(dev);
+
+	return error;
+}
+
+/**
+ * dpm_prepare - Prepare all non-sysdev devices for a system PM transition.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute the ->prepare() callback(s) for all devices.
+ */
+int dpm_prepare(pm_message_t state)
+{
+	int error = 0;
+
+	might_sleep();
+
+	mutex_lock(&dpm_list_mtx);
+	while (!list_empty(&dpm_list)) {
+		struct device *dev = to_device(dpm_list.next);
+
+		get_device(dev);
+		mutex_unlock(&dpm_list_mtx);
+
+		pm_runtime_get_noresume(dev);
+		if (pm_runtime_barrier(dev) && device_may_wakeup(dev))
+			pm_wakeup_event(dev, 0);
+
+		pm_runtime_put_sync(dev);
+		error = pm_wakeup_pending() ?
+				-EBUSY : device_prepare(dev, state);
+
+		mutex_lock(&dpm_list_mtx);
+		if (error) {
+			if (error == -EAGAIN) {
+				put_device(dev);
+				error = 0;
+				continue;
+			}
+			printk(KERN_INFO "PM: Device %s not prepared "
+				"for power transition: code %d\n",
+				dev_name(dev), error);
+			put_device(dev);
+			break;
+		}
+		dev->power.is_prepared = true;
+		if (!list_empty(&dev->power.entry))
+			list_move_tail(&dev->power.entry, &dpm_prepared_list);
+		put_device(dev);
+	}
+	mutex_unlock(&dpm_list_mtx);
+	return error;
+}
+
+/**
+ * dpm_suspend_start - Prepare devices for PM transition and suspend them.
+ * @state: PM transition of the system being carried out.
+ *
+ * Prepare all non-sysdev devices for system PM transition and execute "suspend"
+ * callbacks for them.
+ */
+int dpm_suspend_start(pm_message_t state)
+{
+	int error;
+
+	error = dpm_prepare(state);
+	if (!error)
+		error = dpm_suspend(state);
+	return error;
+}
+EXPORT_SYMBOL_GPL(dpm_suspend_start);
+
+void __suspend_report_result(const char *function, void *fn, int ret)
+{
+	if (ret)
+		printk(KERN_ERR "%s(): %pF returns %d\n", function, fn, ret);
+}
+EXPORT_SYMBOL_GPL(__suspend_report_result);
+
+/**
+ * device_pm_wait_for_dev - Wait for suspend/resume of a device to complete.
+ * @dev: Device to wait for.
+ * @subordinate: Device that needs to wait for @dev.
+ */
+int device_pm_wait_for_dev(struct device *subordinate, struct device *dev)
+{
+	dpm_wait(dev, subordinate->power.async_suspend);
+	return async_error;
+}
+EXPORT_SYMBOL_GPL(device_pm_wait_for_dev);
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
new file mode 100644
index 00000000..56a6899f
--- /dev/null
+++ b/drivers/base/power/opp.c
@@ -0,0 +1,628 @@
+/*
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/cpufreq.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/opp.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 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.
+ * @available:	true/false - marks if this OPP as available or not
+ * @rate:	Frequency in hertz
+ * @u_volt:	Nominal voltage in microvolts corresponding to this OPP
+ * @dev_opp:	points back to the device_opp struct this opp belongs to
+ *
+ * This structure stores the OPP information for a given device.
+ */
+struct opp {
+	struct list_head node;
+
+	bool available;
+	unsigned long rate;
+	unsigned long u_volt;
+
+	struct device_opp *dev_opp;
+};
+
+/**
+ * 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
+ * @dev:	device pointer
+ * @opp_list:	list of opps
+ *
+ * This is an internal data structure maintaining the link to opps attached to
+ * a device. This structure is not meant to be shared to users as it is
+ * meant for book keeping and private to OPP library
+ */
+struct device_opp {
+	struct list_head node;
+
+	struct device *dev;
+	struct list_head opp_list;
+};
+
+/*
+ * The root of the list of all devices. All device_opp structures branch off
+ * from here, with each device_opp containing the list of opp it supports in
+ * various states of availability.
+ */
+static LIST_HEAD(dev_opp_list);
+/* Lock to allow exclusive modification to the device and opp lists */
+static DEFINE_MUTEX(dev_opp_list_lock);
+
+/**
+ * find_device_opp() - find device_opp struct using device pointer
+ * @dev:	device pointer used to lookup device OPPs
+ *
+ * Search list of device OPPs for one containing matching device. Does a RCU
+ * reader operation to grab the pointer needed.
+ *
+ * Returns pointer to 'struct device_opp' if found, otherwise -ENODEV or
+ * -EINVAL based on type of error.
+ *
+ * Locking: This function must be called under rcu_read_lock(). device_opp
+ * 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 *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+
+	if (unlikely(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;
+		}
+	}
+
+	return dev_opp;
+}
+
+/**
+ * opp_get_voltage() - Gets the voltage corresponding to an available opp
+ * @opp:	opp for which voltage has to be returned for
+ *
+ * Return voltage in micro volt corresponding to the opp, else
+ * return 0
+ *
+ * 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.
+ */
+unsigned long opp_get_voltage(struct opp *opp)
+{
+	struct opp *tmp_opp;
+	unsigned long v = 0;
+
+	tmp_opp = rcu_dereference(opp);
+	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+		pr_err("%s: Invalid parameters\n", __func__);
+	else
+		v = tmp_opp->u_volt;
+
+	return v;
+}
+
+/**
+ * opp_get_freq() - Gets the frequency corresponding to an available opp
+ * @opp:	opp for which frequency has to be returned for
+ *
+ * Return frequency in hertz corresponding to the opp, else
+ * return 0
+ *
+ * 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.
+ */
+unsigned long opp_get_freq(struct opp *opp)
+{
+	struct opp *tmp_opp;
+	unsigned long f = 0;
+
+	tmp_opp = rcu_dereference(opp);
+	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+		pr_err("%s: Invalid parameters\n", __func__);
+	else
+		f = tmp_opp->rate;
+
+	return f;
+}
+
+/**
+ * opp_get_opp_count() - Get number of opps available in the opp list
+ * @dev:	device for which we do this operation
+ *
+ * This function returns the number of available opps if there are any,
+ * else returns 0 if none or the corresponding error value.
+ *
+ * Locking: This function must be called under rcu_read_lock(). This function
+ * internally references two RCU protected structures: device_opp and opp which
+ * are safe as long as we are under a common RCU locked section.
+ */
+int opp_get_opp_count(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp;
+	int count = 0;
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int r = PTR_ERR(dev_opp);
+		dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+		return r;
+	}
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available)
+			count++;
+	}
+
+	return count;
+}
+
+/**
+ * opp_find_freq_exact() - search for an exact frequency
+ * @dev:		device for which we do this operation
+ * @freq:		frequency to search for
+ * @available:		true/false - match for available opp
+ *
+ * Searches for exact match in the opp list and returns pointer to the matching
+ * opp if found, else returns ERR_PTR in case of error and should be handled
+ * using IS_ERR.
+ *
+ * Note: available is a modifier for the search. if available=true, then the
+ * match is for exact matching frequency and is available in the stored OPP
+ * table. if false, the match is for exact frequency which is not available.
+ *
+ * This provides a mechanism to enable an opp which is not available currently
+ * or the opposite as well.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_exact(struct device *dev, unsigned long freq,
+				bool available)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int r = PTR_ERR(dev_opp);
+		dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+		return ERR_PTR(r);
+	}
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available == available &&
+				temp_opp->rate == freq) {
+			opp = temp_opp;
+			break;
+		}
+	}
+
+	return opp;
+}
+
+/**
+ * opp_find_freq_ceil() - Search for an rounded ceil freq
+ * @dev:	device for which we do this operation
+ * @freq:	Start frequency
+ *
+ * Search for the matching ceil *available* OPP from a starting freq
+ * for a device.
+ *
+ * Returns matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_ceil(struct device *dev, unsigned long *freq)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+
+	if (!dev || !freq) {
+		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
+		return ERR_PTR(-EINVAL);
+	}
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		return opp;
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available && temp_opp->rate >= *freq) {
+			opp = temp_opp;
+			*freq = opp->rate;
+			break;
+		}
+	}
+
+	return opp;
+}
+
+/**
+ * opp_find_freq_floor() - Search for a rounded floor freq
+ * @dev:	device for which we do this operation
+ * @freq:	Start frequency
+ *
+ * Search for the matching floor *available* OPP from a starting freq
+ * for a device.
+ *
+ * Returns matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_floor(struct device *dev, unsigned long *freq)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+
+	if (!dev || !freq) {
+		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
+		return ERR_PTR(-EINVAL);
+	}
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		return opp;
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available) {
+			/* go to the next node, before choosing prev */
+			if (temp_opp->rate > *freq)
+				break;
+			else
+				opp = temp_opp;
+		}
+	}
+	if (!IS_ERR(opp))
+		*freq = opp->rate;
+
+	return opp;
+}
+
+/**
+ * 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
+ * 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.
+ */
+int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+{
+	struct device_opp *dev_opp = NULL;
+	struct opp *opp, *new_opp;
+	struct list_head *head;
+
+	/* allocate new OPP node */
+	new_opp = kzalloc(sizeof(struct opp), GFP_KERNEL);
+	if (!new_opp) {
+		dev_warn(dev, "%s: Unable to create new OPP node\n", __func__);
+		return -ENOMEM;
+	}
+
+	/* 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)) {
+		/*
+		 * Allocate a new device OPP table. In the infrequent case
+		 * where a new device is needed to be added, we pay this
+		 * penalty.
+		 */
+		dev_opp = kzalloc(sizeof(struct device_opp), GFP_KERNEL);
+		if (!dev_opp) {
+			mutex_unlock(&dev_opp_list_lock);
+			kfree(new_opp);
+			dev_warn(dev,
+				"%s: Unable to create device OPP structure\n",
+				__func__);
+			return -ENOMEM;
+		}
+
+		dev_opp->dev = dev;
+		INIT_LIST_HEAD(&dev_opp->opp_list);
+
+		/* Secure the device list modification */
+		list_add_rcu(&dev_opp->node, &dev_opp_list);
+	}
+
+	/* populate the opp table */
+	new_opp->dev_opp = dev_opp;
+	new_opp->rate = freq;
+	new_opp->u_volt = u_volt;
+	new_opp->available = true;
+
+	/* Insert new OPP in order of increasing frequency */
+	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;
+	}
+
+	list_add_rcu(&new_opp->node, head);
+	mutex_unlock(&dev_opp_list_lock);
+
+	return 0;
+}
+
+/**
+ * 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.
+ *
+ * Returns -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 *tmp_dev_opp, *dev_opp = NULL;
+	struct opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
+	int r = 0;
+
+	/* keep the node allocated */
+	new_opp = kmalloc(sizeof(struct opp), GFP_KERNEL);
+	if (!new_opp) {
+		dev_warn(dev, "%s: Unable to create OPP\n", __func__);
+		return -ENOMEM;
+	}
+
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Find the device_opp */
+	list_for_each_entry(tmp_dev_opp, &dev_opp_list, node) {
+		if (dev == tmp_dev_opp->dev) {
+			dev_opp = tmp_dev_opp;
+			break;
+		}
+	}
+	if (IS_ERR(dev_opp)) {
+		r = PTR_ERR(dev_opp);
+		dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
+		goto unlock;
+	}
+
+	/* Do we have the frequency? */
+	list_for_each_entry(tmp_opp, &dev_opp->opp_list, node) {
+		if (tmp_opp->rate == freq) {
+			opp = tmp_opp;
+			break;
+		}
+	}
+	if (IS_ERR(opp)) {
+		r = PTR_ERR(opp);
+		goto unlock;
+	}
+
+	/* Is update really needed? */
+	if (opp->available == availability_req)
+		goto unlock;
+	/* copy the old data over */
+	*new_opp = *opp;
+
+	/* plug in new node */
+	new_opp->available = availability_req;
+
+	list_replace_rcu(&opp->node, &new_opp->node);
+	mutex_unlock(&dev_opp_list_lock);
+	synchronize_rcu();
+
+	/* clean up old opp */
+	new_opp = opp;
+	goto out;
+
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+out:
+	kfree(new_opp);
+	return r;
+}
+
+/**
+ * opp_enable() - Enable a specific OPP
+ * @dev:	device for which we do this operation
+ * @freq:	OPP frequency to enable
+ *
+ * Enables a provided opp. If the operation is valid, this returns 0, else the
+ * corresponding error value. It is meant to be used for users an OPP available
+ * after being temporarily made unavailable with opp_disable.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function indirectly uses RCU and 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.
+ */
+int opp_enable(struct device *dev, unsigned long freq)
+{
+	return opp_set_availability(dev, freq, true);
+}
+
+/**
+ * opp_disable() - Disable a specific OPP
+ * @dev:	device for which we do this operation
+ * @freq:	OPP frequency to disable
+ *
+ * Disables a provided opp. If the operation is valid, this returns
+ * 0, else the corresponding error value. It is meant to be a temporary
+ * control by users to make this OPP not available until the circumstances are
+ * right to make it available again (with a call to opp_enable).
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function indirectly uses RCU and 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.
+ */
+int opp_disable(struct device *dev, unsigned long freq)
+{
+	return opp_set_availability(dev, freq, false);
+}
+
+#ifdef CONFIG_CPU_FREQ
+/**
+ * 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.
+ * To simplify the logic, we pretend we are updater and hold relevant mutex here
+ * Callers should ensure that this function is *NOT* called under RCU protection
+ * or in contexts where mutex locking cannot be used.
+ */
+int opp_init_cpufreq_table(struct device *dev,
+			    struct cpufreq_frequency_table **table)
+{
+	struct device_opp *dev_opp;
+	struct opp *opp;
+	struct cpufreq_frequency_table *freq_table;
+	int i = 0;
+
+	/* Pretend as if I am an updater */
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int r = PTR_ERR(dev_opp);
+		mutex_unlock(&dev_opp_list_lock);
+		dev_err(dev, "%s: Device OPP not found (%d)\n", __func__, r);
+		return r;
+	}
+
+	freq_table = kzalloc(sizeof(struct cpufreq_frequency_table) *
+			     (opp_get_opp_count(dev) + 1), GFP_KERNEL);
+	if (!freq_table) {
+		mutex_unlock(&dev_opp_list_lock);
+		dev_warn(dev, "%s: Unable to allocate frequency table\n",
+			__func__);
+		return -ENOMEM;
+	}
+
+	list_for_each_entry(opp, &dev_opp->opp_list, node) {
+		if (opp->available) {
+			freq_table[i].index = i;
+			freq_table[i].frequency = opp->rate / 1000;
+			i++;
+		}
+	}
+	mutex_unlock(&dev_opp_list_lock);
+
+	freq_table[i].index = i;
+	freq_table[i].frequency = CPUFREQ_TABLE_END;
+
+	*table = &freq_table[0];
+
+	return 0;
+}
+#endif		/* CONFIG_CPU_FREQ */
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
new file mode 100644
index 00000000..51b585a4
--- /dev/null
+++ b/drivers/base/power/power.h
@@ -0,0 +1,79 @@
+#ifdef CONFIG_PM_RUNTIME
+
+extern void pm_runtime_init(struct device *dev);
+extern void pm_runtime_remove(struct device *dev);
+
+#else /* !CONFIG_PM_RUNTIME */
+
+static inline void pm_runtime_init(struct device *dev) {}
+static inline void pm_runtime_remove(struct device *dev) {}
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+#ifdef CONFIG_SUSPEND_DEVICE_TIME_DEBUG
+extern int device_suspend_time_threshold;
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+
+/* kernel/power/main.c */
+extern int pm_async_enabled;
+
+/* drivers/base/power/main.c */
+extern struct list_head dpm_list;	/* The active device list */
+
+static inline struct device *to_device(struct list_head *entry)
+{
+	return container_of(entry, struct device, power.entry);
+}
+
+extern void device_pm_init(struct device *dev);
+extern void device_pm_add(struct device *);
+extern void device_pm_remove(struct device *);
+extern void device_pm_move_before(struct device *, struct device *);
+extern void device_pm_move_after(struct device *, struct device *);
+extern void device_pm_move_last(struct device *);
+
+#else /* !CONFIG_PM_SLEEP */
+
+static inline void device_pm_init(struct device *dev)
+{
+	spin_lock_init(&dev->power.lock);
+	pm_runtime_init(dev);
+}
+
+static inline void device_pm_remove(struct device *dev)
+{
+	pm_runtime_remove(dev);
+}
+
+static inline void device_pm_add(struct device *dev) {}
+static inline void device_pm_move_before(struct device *deva,
+					 struct device *devb) {}
+static inline void device_pm_move_after(struct device *deva,
+					struct device *devb) {}
+static inline void device_pm_move_last(struct device *dev) {}
+
+#endif /* !CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_PM
+
+/*
+ * sysfs.c
+ */
+
+extern int dpm_sysfs_add(struct device *dev);
+extern void dpm_sysfs_remove(struct device *dev);
+extern void rpm_sysfs_remove(struct device *dev);
+extern int wakeup_sysfs_add(struct device *dev);
+extern void wakeup_sysfs_remove(struct device *dev);
+
+#else /* CONFIG_PM */
+
+static inline int dpm_sysfs_add(struct device *dev) { return 0; }
+static inline void dpm_sysfs_remove(struct device *dev) {}
+static inline void rpm_sysfs_remove(struct device *dev) {}
+static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
+static inline void wakeup_sysfs_remove(struct device *dev) {}
+
+#endif
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
new file mode 100644
index 00000000..184cf54f
--- /dev/null
+++ b/drivers/base/power/runtime.c
@@ -0,0 +1,1263 @@
+/*
+ * drivers/base/power/runtime.c - Helper functions for device run-time PM
+ *
+ * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/sched.h>
+#include <linux/pm_runtime.h>
+#include "power.h"
+
+static int rpm_resume(struct device *dev, int rpmflags);
+static int rpm_suspend(struct device *dev, int rpmflags);
+
+/**
+ * update_pm_runtime_accounting - Update the time accounting of power states
+ * @dev: Device to update the accounting for
+ *
+ * In order to be able to have time accounting of the various power states
+ * (as used by programs such as PowerTOP to show the effectiveness of runtime
+ * PM), we need to track the time spent in each state.
+ * update_pm_runtime_accounting must be called each time before the
+ * runtime_status field is updated, to account the time in the old state
+ * correctly.
+ */
+void update_pm_runtime_accounting(struct device *dev)
+{
+	unsigned long now = jiffies;
+	int delta;
+
+	delta = now - dev->power.accounting_timestamp;
+
+	if (delta < 0)
+		delta = 0;
+
+	dev->power.accounting_timestamp = now;
+
+	if (dev->power.disable_depth > 0)
+		return;
+
+	if (dev->power.runtime_status == RPM_SUSPENDED)
+		dev->power.suspended_jiffies += delta;
+	else
+		dev->power.active_jiffies += delta;
+}
+
+static void __update_runtime_status(struct device *dev, enum rpm_status status)
+{
+	update_pm_runtime_accounting(dev);
+	dev->power.runtime_status = status;
+}
+
+/**
+ * pm_runtime_deactivate_timer - Deactivate given device's suspend timer.
+ * @dev: Device to handle.
+ */
+static void pm_runtime_deactivate_timer(struct device *dev)
+{
+	if (dev->power.timer_expires > 0) {
+		del_timer(&dev->power.suspend_timer);
+		dev->power.timer_expires = 0;
+	}
+}
+
+/**
+ * pm_runtime_cancel_pending - Deactivate suspend timer and cancel requests.
+ * @dev: Device to handle.
+ */
+static void pm_runtime_cancel_pending(struct device *dev)
+{
+	pm_runtime_deactivate_timer(dev);
+	/*
+	 * In case there's a request pending, make sure its work function will
+	 * return without doing anything.
+	 */
+	dev->power.request = RPM_REQ_NONE;
+}
+
+/*
+ * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time.
+ * @dev: Device to handle.
+ *
+ * Compute the autosuspend-delay expiration time based on the device's
+ * power.last_busy time.  If the delay has already expired or is disabled
+ * (negative) or the power.use_autosuspend flag isn't set, return 0.
+ * Otherwise return the expiration time in jiffies (adjusted to be nonzero).
+ *
+ * This function may be called either with or without dev->power.lock held.
+ * Either way it can be racy, since power.last_busy may be updated at any time.
+ */
+unsigned long pm_runtime_autosuspend_expiration(struct device *dev)
+{
+	int autosuspend_delay;
+	long elapsed;
+	unsigned long last_busy;
+	unsigned long expires = 0;
+
+	if (!dev->power.use_autosuspend)
+		goto out;
+
+	autosuspend_delay = ACCESS_ONCE(dev->power.autosuspend_delay);
+	if (autosuspend_delay < 0)
+		goto out;
+
+	last_busy = ACCESS_ONCE(dev->power.last_busy);
+	elapsed = jiffies - last_busy;
+	if (elapsed < 0)
+		goto out;	/* jiffies has wrapped around. */
+
+	/*
+	 * If the autosuspend_delay is >= 1 second, align the timer by rounding
+	 * up to the nearest second.
+	 */
+	expires = last_busy + msecs_to_jiffies(autosuspend_delay);
+	if (autosuspend_delay >= 1000)
+		expires = round_jiffies(expires);
+	expires += !expires;
+	if (elapsed >= expires - last_busy)
+		expires = 0;	/* Already expired. */
+
+ out:
+	return expires;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
+
+/**
+ * rpm_check_suspend_allowed - Test whether a device may be suspended.
+ * @dev: Device to test.
+ */
+static int rpm_check_suspend_allowed(struct device *dev)
+{
+	int retval = 0;
+
+	if (dev->power.runtime_error)
+		retval = -EINVAL;
+	else if (atomic_read(&dev->power.usage_count) > 0
+	    || dev->power.disable_depth > 0)
+		retval = -EAGAIN;
+	else if (!pm_children_suspended(dev))
+		retval = -EBUSY;
+
+	/* Pending resume requests take precedence over suspends. */
+	else if ((dev->power.deferred_resume
+			&& dev->power.runtime_status == RPM_SUSPENDING)
+	    || (dev->power.request_pending
+			&& dev->power.request == RPM_REQ_RESUME))
+		retval = -EAGAIN;
+	else if (dev->power.runtime_status == RPM_SUSPENDED)
+		retval = 1;
+
+	return retval;
+}
+
+/**
+ * rpm_idle - Notify device bus type if the device can be suspended.
+ * @dev: Device to notify the bus type about.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's run-time PM status allows it to be suspended.  If
+ * another idle notification has been started earlier, return immediately.  If
+ * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise
+ * run the ->runtime_idle() callback directly.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static int rpm_idle(struct device *dev, int rpmflags)
+{
+	int (*callback)(struct device *);
+	int retval;
+
+	retval = rpm_check_suspend_allowed(dev);
+	if (retval < 0)
+		;	/* Conditions are wrong. */
+
+	/* Idle notifications are allowed only in the RPM_ACTIVE state. */
+	else if (dev->power.runtime_status != RPM_ACTIVE)
+		retval = -EAGAIN;
+
+	/*
+	 * Any pending request other than an idle notification takes
+	 * precedence over us, except that the timer may be running.
+	 */
+	else if (dev->power.request_pending &&
+	    dev->power.request > RPM_REQ_IDLE)
+		retval = -EAGAIN;
+
+	/* Act as though RPM_NOWAIT is always set. */
+	else if (dev->power.idle_notification)
+		retval = -EINPROGRESS;
+	if (retval)
+		goto out;
+
+	/* Pending requests need to be canceled. */
+	dev->power.request = RPM_REQ_NONE;
+
+	if (dev->power.no_callbacks) {
+		/* Assume ->runtime_idle() callback would have suspended. */
+		retval = rpm_suspend(dev, rpmflags);
+		goto out;
+	}
+
+	/* Carry out an asynchronous or a synchronous idle notification. */
+	if (rpmflags & RPM_ASYNC) {
+		dev->power.request = RPM_REQ_IDLE;
+		if (!dev->power.request_pending) {
+			dev->power.request_pending = true;
+			queue_work(pm_wq, &dev->power.work);
+		}
+		goto out;
+	}
+
+	dev->power.idle_notification = true;
+
+	if (dev->pwr_domain)
+		callback = dev->pwr_domain->ops.runtime_idle;
+	else if (dev->type && dev->type->pm)
+		callback = dev->type->pm->runtime_idle;
+	else if (dev->class && dev->class->pm)
+		callback = dev->class->pm->runtime_idle;
+	else if (dev->bus && dev->bus->pm)
+		callback = dev->bus->pm->runtime_idle;
+	else
+		callback = NULL;
+
+	if (callback) {
+		spin_unlock_irq(&dev->power.lock);
+
+		callback(dev);
+
+		spin_lock_irq(&dev->power.lock);
+	}
+
+	dev->power.idle_notification = false;
+	wake_up_all(&dev->power.wait_queue);
+
+ out:
+	return retval;
+}
+
+/**
+ * rpm_callback - Run a given runtime PM callback for a given device.
+ * @cb: Runtime PM callback to run.
+ * @dev: Device to run the callback for.
+ */
+static int rpm_callback(int (*cb)(struct device *), struct device *dev)
+	__releases(&dev->power.lock) __acquires(&dev->power.lock)
+{
+	int retval;
+
+	if (!cb)
+		return -ENOSYS;
+
+	if (dev->power.irq_safe) {
+		retval = cb(dev);
+	} else {
+		spin_unlock_irq(&dev->power.lock);
+
+		retval = cb(dev);
+
+		spin_lock_irq(&dev->power.lock);
+	}
+	dev->power.runtime_error = retval;
+	return retval;
+}
+
+/**
+ * rpm_suspend - Carry out run-time suspend of given device.
+ * @dev: Device to suspend.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's run-time PM status allows it to be suspended.  If
+ * another suspend has been started earlier, either return immediately or wait
+ * for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC flags.  Cancel a
+ * pending idle notification.  If the RPM_ASYNC flag is set then queue a
+ * suspend request; otherwise run the ->runtime_suspend() callback directly.
+ * If a deferred resume was requested while the callback was running then carry
+ * it out; otherwise send an idle notification for the device (if the suspend
+ * failed) or for its parent (if the suspend succeeded).
+ * If ->runtime_suspend failed with -EAGAIN or -EBUSY, and if the RPM_AUTO
+ * flag is set and the next autosuspend-delay expiration time is in the
+ * future, schedule another autosuspend attempt.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static int rpm_suspend(struct device *dev, int rpmflags)
+	__releases(&dev->power.lock) __acquires(&dev->power.lock)
+{
+	int (*callback)(struct device *);
+	struct device *parent = NULL;
+	int retval;
+
+	dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags);
+
+ repeat:
+	retval = rpm_check_suspend_allowed(dev);
+
+	if (retval < 0)
+		;	/* Conditions are wrong. */
+
+	/* Synchronous suspends are not allowed in the RPM_RESUMING state. */
+	else if (dev->power.runtime_status == RPM_RESUMING &&
+	    !(rpmflags & RPM_ASYNC))
+		retval = -EAGAIN;
+	if (retval)
+		goto out;
+
+	/* If the autosuspend_delay time hasn't expired yet, reschedule. */
+	if ((rpmflags & RPM_AUTO)
+	    && dev->power.runtime_status != RPM_SUSPENDING) {
+		unsigned long expires = pm_runtime_autosuspend_expiration(dev);
+
+		if (expires != 0) {
+			/* Pending requests need to be canceled. */
+			dev->power.request = RPM_REQ_NONE;
+
+			/*
+			 * Optimization: If the timer is already running and is
+			 * set to expire at or before the autosuspend delay,
+			 * avoid the overhead of resetting it.  Just let it
+			 * expire; pm_suspend_timer_fn() will take care of the
+			 * rest.
+			 */
+			if (!(dev->power.timer_expires && time_before_eq(
+			    dev->power.timer_expires, expires))) {
+				dev->power.timer_expires = expires;
+				mod_timer(&dev->power.suspend_timer, expires);
+			}
+			dev->power.timer_autosuspends = 1;
+			goto out;
+		}
+	}
+
+	/* Other scheduled or pending requests need to be canceled. */
+	pm_runtime_cancel_pending(dev);
+
+	if (dev->power.runtime_status == RPM_SUSPENDING) {
+		DEFINE_WAIT(wait);
+
+		if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
+			retval = -EINPROGRESS;
+			goto out;
+		}
+
+		/* Wait for the other suspend running in parallel with us. */
+		for (;;) {
+			prepare_to_wait(&dev->power.wait_queue, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (dev->power.runtime_status != RPM_SUSPENDING)
+				break;
+
+			spin_unlock_irq(&dev->power.lock);
+
+			schedule();
+
+			spin_lock_irq(&dev->power.lock);
+		}
+		finish_wait(&dev->power.wait_queue, &wait);
+		goto repeat;
+	}
+
+	dev->power.deferred_resume = false;
+	if (dev->power.no_callbacks)
+		goto no_callback;	/* Assume success. */
+
+	/* Carry out an asynchronous or a synchronous suspend. */
+	if (rpmflags & RPM_ASYNC) {
+		dev->power.request = (rpmflags & RPM_AUTO) ?
+		    RPM_REQ_AUTOSUSPEND : RPM_REQ_SUSPEND;
+		if (!dev->power.request_pending) {
+			dev->power.request_pending = true;
+			queue_work(pm_wq, &dev->power.work);
+		}
+		goto out;
+	}
+
+	__update_runtime_status(dev, RPM_SUSPENDING);
+
+	if (dev->pwr_domain)
+		callback = dev->pwr_domain->ops.runtime_suspend;
+	else if (dev->type && dev->type->pm)
+		callback = dev->type->pm->runtime_suspend;
+	else if (dev->class && dev->class->pm)
+		callback = dev->class->pm->runtime_suspend;
+	else if (dev->bus && dev->bus->pm)
+		callback = dev->bus->pm->runtime_suspend;
+	else
+		callback = NULL;
+
+	retval = rpm_callback(callback, dev);
+	if (retval) {
+		__update_runtime_status(dev, RPM_ACTIVE);
+		dev->power.deferred_resume = 0;
+		if (retval == -EAGAIN || retval == -EBUSY) {
+			dev->power.runtime_error = 0;
+
+			/*
+			 * If the callback routine failed an autosuspend, and
+			 * if the last_busy time has been updated so that there
+			 * is a new autosuspend expiration time, automatically
+			 * reschedule another autosuspend.
+			 */
+			if ((rpmflags & RPM_AUTO) &&
+			    pm_runtime_autosuspend_expiration(dev) != 0)
+				goto repeat;
+		} else {
+			pm_runtime_cancel_pending(dev);
+		}
+	} else {
+ no_callback:
+		__update_runtime_status(dev, RPM_SUSPENDED);
+		pm_runtime_deactivate_timer(dev);
+
+		if (dev->parent) {
+			parent = dev->parent;
+			atomic_add_unless(&parent->power.child_count, -1, 0);
+		}
+	}
+	wake_up_all(&dev->power.wait_queue);
+
+	if (dev->power.deferred_resume) {
+		rpm_resume(dev, 0);
+		retval = -EAGAIN;
+		goto out;
+	}
+
+	/* Maybe the parent is now able to suspend. */
+	if (parent && !parent->power.ignore_children && !dev->power.irq_safe) {
+		spin_unlock(&dev->power.lock);
+
+		spin_lock(&parent->power.lock);
+		rpm_idle(parent, RPM_ASYNC);
+		spin_unlock(&parent->power.lock);
+
+		spin_lock(&dev->power.lock);
+	}
+
+ out:
+	dev_dbg(dev, "%s returns %d\n", __func__, retval);
+
+	return retval;
+}
+
+/**
+ * rpm_resume - Carry out run-time resume of given device.
+ * @dev: Device to resume.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's run-time PM status allows it to be resumed.  Cancel
+ * any scheduled or pending requests.  If another resume has been started
+ * earlier, either return immediately or wait for it to finish, depending on the
+ * RPM_NOWAIT and RPM_ASYNC flags.  Similarly, if there's a suspend running in
+ * parallel with this function, either tell the other process to resume after
+ * suspending (deferred_resume) or wait for it to finish.  If the RPM_ASYNC
+ * flag is set then queue a resume request; otherwise run the
+ * ->runtime_resume() callback directly.  Queue an idle notification for the
+ * device if the resume succeeded.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static int rpm_resume(struct device *dev, int rpmflags)
+	__releases(&dev->power.lock) __acquires(&dev->power.lock)
+{
+	int (*callback)(struct device *);
+	struct device *parent = NULL;
+	int retval = 0;
+
+	dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags);
+
+ repeat:
+	if (dev->power.runtime_error)
+		retval = -EINVAL;
+	else if (dev->power.disable_depth > 0)
+		retval = -EAGAIN;
+	if (retval)
+		goto out;
+
+	/*
+	 * Other scheduled or pending requests need to be canceled.  Small
+	 * optimization: If an autosuspend timer is running, leave it running
+	 * rather than cancelling it now only to restart it again in the near
+	 * future.
+	 */
+	dev->power.request = RPM_REQ_NONE;
+	if (!dev->power.timer_autosuspends)
+		pm_runtime_deactivate_timer(dev);
+
+	if (dev->power.runtime_status == RPM_ACTIVE) {
+		retval = 1;
+		goto out;
+	}
+
+	if (dev->power.runtime_status == RPM_RESUMING
+	    || dev->power.runtime_status == RPM_SUSPENDING) {
+		DEFINE_WAIT(wait);
+
+		if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
+			if (dev->power.runtime_status == RPM_SUSPENDING)
+				dev->power.deferred_resume = true;
+			else
+				retval = -EINPROGRESS;
+			goto out;
+		}
+
+		/* Wait for the operation carried out in parallel with us. */
+		for (;;) {
+			prepare_to_wait(&dev->power.wait_queue, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (dev->power.runtime_status != RPM_RESUMING
+			    && dev->power.runtime_status != RPM_SUSPENDING)
+				break;
+
+			spin_unlock_irq(&dev->power.lock);
+
+			schedule();
+
+			spin_lock_irq(&dev->power.lock);
+		}
+		finish_wait(&dev->power.wait_queue, &wait);
+		goto repeat;
+	}
+
+	/*
+	 * See if we can skip waking up the parent.  This is safe only if
+	 * power.no_callbacks is set, because otherwise we don't know whether
+	 * the resume will actually succeed.
+	 */
+	if (dev->power.no_callbacks && !parent && dev->parent) {
+		spin_lock_nested(&dev->parent->power.lock, SINGLE_DEPTH_NESTING);
+		if (dev->parent->power.disable_depth > 0
+		    || dev->parent->power.ignore_children
+		    || dev->parent->power.runtime_status == RPM_ACTIVE) {
+			atomic_inc(&dev->parent->power.child_count);
+			spin_unlock(&dev->parent->power.lock);
+			goto no_callback;	/* Assume success. */
+		}
+		spin_unlock(&dev->parent->power.lock);
+	}
+
+	/* Carry out an asynchronous or a synchronous resume. */
+	if (rpmflags & RPM_ASYNC) {
+		dev->power.request = RPM_REQ_RESUME;
+		if (!dev->power.request_pending) {
+			dev->power.request_pending = true;
+			queue_work(pm_wq, &dev->power.work);
+		}
+		retval = 0;
+		goto out;
+	}
+
+	if (!parent && dev->parent) {
+		/*
+		 * Increment the parent's usage counter and resume it if
+		 * necessary.  Not needed if dev is irq-safe; then the
+		 * parent is permanently resumed.
+		 */
+		parent = dev->parent;
+		if (dev->power.irq_safe)
+			goto skip_parent;
+		spin_unlock(&dev->power.lock);
+
+		pm_runtime_get_noresume(parent);
+
+		spin_lock(&parent->power.lock);
+		/*
+		 * We can resume if the parent's run-time PM is disabled or it
+		 * is set to ignore children.
+		 */
+		if (!parent->power.disable_depth
+		    && !parent->power.ignore_children) {
+			rpm_resume(parent, 0);
+			if (parent->power.runtime_status != RPM_ACTIVE)
+				retval = -EBUSY;
+		}
+		spin_unlock(&parent->power.lock);
+
+		spin_lock(&dev->power.lock);
+		if (retval)
+			goto out;
+		goto repeat;
+	}
+ skip_parent:
+
+	if (dev->power.no_callbacks)
+		goto no_callback;	/* Assume success. */
+
+	__update_runtime_status(dev, RPM_RESUMING);
+
+	if (dev->pwr_domain)
+		callback = dev->pwr_domain->ops.runtime_resume;
+	else if (dev->type && dev->type->pm)
+		callback = dev->type->pm->runtime_resume;
+	else if (dev->class && dev->class->pm)
+		callback = dev->class->pm->runtime_resume;
+	else if (dev->bus && dev->bus->pm)
+		callback = dev->bus->pm->runtime_resume;
+	else
+		callback = NULL;
+
+	retval = rpm_callback(callback, dev);
+	if (retval) {
+		__update_runtime_status(dev, RPM_SUSPENDED);
+		pm_runtime_cancel_pending(dev);
+	} else {
+ no_callback:
+		__update_runtime_status(dev, RPM_ACTIVE);
+		if (parent)
+			atomic_inc(&parent->power.child_count);
+	}
+	wake_up_all(&dev->power.wait_queue);
+
+	if (!retval)
+		rpm_idle(dev, RPM_ASYNC);
+
+ out:
+	if (parent && !dev->power.irq_safe) {
+		spin_unlock_irq(&dev->power.lock);
+
+		pm_runtime_put(parent);
+
+		spin_lock_irq(&dev->power.lock);
+	}
+
+	dev_dbg(dev, "%s returns %d\n", __func__, retval);
+
+	return retval;
+}
+
+/**
+ * pm_runtime_work - Universal run-time PM work function.
+ * @work: Work structure used for scheduling the execution of this function.
+ *
+ * Use @work to get the device object the work is to be done for, determine what
+ * is to be done and execute the appropriate run-time PM function.
+ */
+static void pm_runtime_work(struct work_struct *work)
+{
+	struct device *dev = container_of(work, struct device, power.work);
+	enum rpm_request req;
+
+	spin_lock_irq(&dev->power.lock);
+
+	if (!dev->power.request_pending)
+		goto out;
+
+	req = dev->power.request;
+	dev->power.request = RPM_REQ_NONE;
+	dev->power.request_pending = false;
+
+	switch (req) {
+	case RPM_REQ_NONE:
+		break;
+	case RPM_REQ_IDLE:
+		rpm_idle(dev, RPM_NOWAIT);
+		break;
+	case RPM_REQ_SUSPEND:
+		rpm_suspend(dev, RPM_NOWAIT);
+		break;
+	case RPM_REQ_AUTOSUSPEND:
+		rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO);
+		break;
+	case RPM_REQ_RESUME:
+		rpm_resume(dev, RPM_NOWAIT);
+		break;
+	}
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+}
+
+/**
+ * pm_suspend_timer_fn - Timer function for pm_schedule_suspend().
+ * @data: Device pointer passed by pm_schedule_suspend().
+ *
+ * Check if the time is right and queue a suspend request.
+ */
+static void pm_suspend_timer_fn(unsigned long data)
+{
+	struct device *dev = (struct device *)data;
+	unsigned long flags;
+	unsigned long expires;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	expires = dev->power.timer_expires;
+	/* If 'expire' is after 'jiffies' we've been called too early. */
+	if (expires > 0 && !time_after(expires, jiffies)) {
+		dev->power.timer_expires = 0;
+		rpm_suspend(dev, dev->power.timer_autosuspends ?
+		    (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC);
+	}
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+
+/**
+ * pm_schedule_suspend - Set up a timer to submit a suspend request in future.
+ * @dev: Device to suspend.
+ * @delay: Time to wait before submitting a suspend request, in milliseconds.
+ */
+int pm_schedule_suspend(struct device *dev, unsigned int delay)
+{
+	unsigned long flags;
+	int retval;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	if (!delay) {
+		retval = rpm_suspend(dev, RPM_ASYNC);
+		goto out;
+	}
+
+	retval = rpm_check_suspend_allowed(dev);
+	if (retval)
+		goto out;
+
+	/* Other scheduled or pending requests need to be canceled. */
+	pm_runtime_cancel_pending(dev);
+
+	dev->power.timer_expires = jiffies + msecs_to_jiffies(delay);
+	dev->power.timer_expires += !dev->power.timer_expires;
+	dev->power.timer_autosuspends = 0;
+	mod_timer(&dev->power.suspend_timer, dev->power.timer_expires);
+
+ out:
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(pm_schedule_suspend);
+
+/**
+ * __pm_runtime_idle - Entry point for run-time idle operations.
+ * @dev: Device to send idle notification for.
+ * @rpmflags: Flag bits.
+ *
+ * If the RPM_GET_PUT flag is set, decrement the device's usage count and
+ * return immediately if it is larger than zero.  Then carry out an idle
+ * notification, either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set.
+ */
+int __pm_runtime_idle(struct device *dev, int rpmflags)
+{
+	unsigned long flags;
+	int retval;
+
+	might_sleep_if(!(rpmflags & RPM_ASYNC));
+
+	if (rpmflags & RPM_GET_PUT) {
+		if (!atomic_dec_and_test(&dev->power.usage_count))
+			return 0;
+	}
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	retval = rpm_idle(dev, rpmflags);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_idle);
+
+/**
+ * __pm_runtime_suspend - Entry point for run-time put/suspend operations.
+ * @dev: Device to suspend.
+ * @rpmflags: Flag bits.
+ *
+ * If the RPM_GET_PUT flag is set, decrement the device's usage count and
+ * return immediately if it is larger than zero.  Then carry out a suspend,
+ * either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set.
+ */
+int __pm_runtime_suspend(struct device *dev, int rpmflags)
+{
+	unsigned long flags;
+	int retval;
+
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
+	if (rpmflags & RPM_GET_PUT) {
+		if (!atomic_dec_and_test(&dev->power.usage_count))
+			return 0;
+	}
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	retval = rpm_suspend(dev, rpmflags);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_suspend);
+
+/**
+ * __pm_runtime_resume - Entry point for run-time resume operations.
+ * @dev: Device to resume.
+ * @rpmflags: Flag bits.
+ *
+ * If the RPM_GET_PUT flag is set, increment the device's usage count.  Then
+ * carry out a resume, either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set.
+ */
+int __pm_runtime_resume(struct device *dev, int rpmflags)
+{
+	unsigned long flags;
+	int retval;
+
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
+	if (rpmflags & RPM_GET_PUT)
+		atomic_inc(&dev->power.usage_count);
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	retval = rpm_resume(dev, rpmflags);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_resume);
+
+/**
+ * __pm_runtime_set_status - Set run-time PM status of a device.
+ * @dev: Device to handle.
+ * @status: New run-time PM status of the device.
+ *
+ * If run-time PM of the device is disabled or its power.runtime_error field is
+ * different from zero, the status may be changed either to RPM_ACTIVE, or to
+ * RPM_SUSPENDED, as long as that reflects the actual state of the device.
+ * However, if the device has a parent and the parent is not active, and the
+ * parent's power.ignore_children flag is unset, the device's status cannot be
+ * set to RPM_ACTIVE, so -EBUSY is returned in that case.
+ *
+ * If successful, __pm_runtime_set_status() clears the power.runtime_error field
+ * and the device parent's counter of unsuspended children is modified to
+ * reflect the new status.  If the new status is RPM_SUSPENDED, an idle
+ * notification request for the parent is submitted.
+ */
+int __pm_runtime_set_status(struct device *dev, unsigned int status)
+{
+	struct device *parent = dev->parent;
+	unsigned long flags;
+	bool notify_parent = false;
+	int error = 0;
+
+	if (status != RPM_ACTIVE && status != RPM_SUSPENDED)
+		return -EINVAL;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	if (!dev->power.runtime_error && !dev->power.disable_depth) {
+		error = -EAGAIN;
+		goto out;
+	}
+
+	if (dev->power.runtime_status == status)
+		goto out_set;
+
+	if (status == RPM_SUSPENDED) {
+		/* It always is possible to set the status to 'suspended'. */
+		if (parent) {
+			atomic_add_unless(&parent->power.child_count, -1, 0);
+			notify_parent = !parent->power.ignore_children;
+		}
+		goto out_set;
+	}
+
+	if (parent) {
+		spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING);
+
+		/*
+		 * It is invalid to put an active child under a parent that is
+		 * not active, has run-time PM enabled and the
+		 * 'power.ignore_children' flag unset.
+		 */
+		if (!parent->power.disable_depth
+		    && !parent->power.ignore_children
+		    && parent->power.runtime_status != RPM_ACTIVE)
+			error = -EBUSY;
+		else if (dev->power.runtime_status == RPM_SUSPENDED)
+			atomic_inc(&parent->power.child_count);
+
+		spin_unlock(&parent->power.lock);
+
+		if (error)
+			goto out;
+	}
+
+ out_set:
+	__update_runtime_status(dev, status);
+	dev->power.runtime_error = 0;
+ out:
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	if (notify_parent)
+		pm_request_idle(parent);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_set_status);
+
+/**
+ * __pm_runtime_barrier - Cancel pending requests and wait for completions.
+ * @dev: Device to handle.
+ *
+ * Flush all pending requests for the device from pm_wq and wait for all
+ * run-time PM operations involving the device in progress to complete.
+ *
+ * Should be called under dev->power.lock with interrupts disabled.
+ */
+static void __pm_runtime_barrier(struct device *dev)
+{
+	pm_runtime_deactivate_timer(dev);
+
+	if (dev->power.request_pending) {
+		dev->power.request = RPM_REQ_NONE;
+		spin_unlock_irq(&dev->power.lock);
+
+		cancel_work_sync(&dev->power.work);
+
+		spin_lock_irq(&dev->power.lock);
+		dev->power.request_pending = false;
+	}
+
+	if (dev->power.runtime_status == RPM_SUSPENDING
+	    || dev->power.runtime_status == RPM_RESUMING
+	    || dev->power.idle_notification) {
+		DEFINE_WAIT(wait);
+
+		/* Suspend, wake-up or idle notification in progress. */
+		for (;;) {
+			prepare_to_wait(&dev->power.wait_queue, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (dev->power.runtime_status != RPM_SUSPENDING
+			    && dev->power.runtime_status != RPM_RESUMING
+			    && !dev->power.idle_notification)
+				break;
+			spin_unlock_irq(&dev->power.lock);
+
+			schedule();
+
+			spin_lock_irq(&dev->power.lock);
+		}
+		finish_wait(&dev->power.wait_queue, &wait);
+	}
+}
+
+/**
+ * pm_runtime_barrier - Flush pending requests and wait for completions.
+ * @dev: Device to handle.
+ *
+ * Prevent the device from being suspended by incrementing its usage counter and
+ * if there's a pending resume request for the device, wake the device up.
+ * Next, make sure that all pending requests for the device have been flushed
+ * from pm_wq and wait for all run-time PM operations involving the device in
+ * progress to complete.
+ *
+ * Return value:
+ * 1, if there was a resume request pending and the device had to be woken up,
+ * 0, otherwise
+ */
+int pm_runtime_barrier(struct device *dev)
+{
+	int retval = 0;
+
+	pm_runtime_get_noresume(dev);
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.request_pending
+	    && dev->power.request == RPM_REQ_RESUME) {
+		rpm_resume(dev, 0);
+		retval = 1;
+	}
+
+	__pm_runtime_barrier(dev);
+
+	spin_unlock_irq(&dev->power.lock);
+	pm_runtime_put_noidle(dev);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_barrier);
+
+/**
+ * __pm_runtime_disable - Disable run-time PM of a device.
+ * @dev: Device to handle.
+ * @check_resume: If set, check if there's a resume request for the device.
+ *
+ * Increment power.disable_depth for the device and if was zero previously,
+ * cancel all pending run-time PM requests for the device and wait for all
+ * operations in progress to complete.  The device can be either active or
+ * suspended after its run-time PM has been disabled.
+ *
+ * If @check_resume is set and there's a resume request pending when
+ * __pm_runtime_disable() is called and power.disable_depth is zero, the
+ * function will wake up the device before disabling its run-time PM.
+ */
+void __pm_runtime_disable(struct device *dev, bool check_resume)
+{
+	might_sleep();
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.disable_depth > 0) {
+		dev->power.disable_depth++;
+		goto out;
+	}
+
+	/*
+	 * Wake up the device if there's a resume request pending, because that
+	 * means there probably is some I/O to process and disabling run-time PM
+	 * shouldn't prevent the device from processing the I/O.
+	 */
+	if (check_resume && dev->power.request_pending
+	    && dev->power.request == RPM_REQ_RESUME) {
+		/*
+		 * Prevent suspends and idle notifications from being carried
+		 * out after we have woken up the device.
+		 */
+		pm_runtime_get_noresume(dev);
+
+		rpm_resume(dev, 0);
+
+		pm_runtime_put_noidle(dev);
+	}
+
+	if (!dev->power.disable_depth++)
+		__pm_runtime_barrier(dev);
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_disable);
+
+/**
+ * pm_runtime_enable - Enable run-time PM of a device.
+ * @dev: Device to handle.
+ */
+void pm_runtime_enable(struct device *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	if (dev->power.disable_depth > 0)
+		dev->power.disable_depth--;
+	else
+		dev_warn(dev, "Unbalanced %s!\n", __func__);
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_enable);
+
+/**
+ * pm_runtime_forbid - Block run-time PM of a device.
+ * @dev: Device to handle.
+ *
+ * Increase the device's usage count and clear its power.runtime_auto flag,
+ * so that it cannot be suspended at run time until pm_runtime_allow() is called
+ * for it.
+ */
+void pm_runtime_forbid(struct device *dev)
+{
+	spin_lock_irq(&dev->power.lock);
+	if (!dev->power.runtime_auto)
+		goto out;
+
+	dev->power.runtime_auto = false;
+	atomic_inc(&dev->power.usage_count);
+	rpm_resume(dev, 0);
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_forbid);
+
+/**
+ * pm_runtime_allow - Unblock run-time PM of a device.
+ * @dev: Device to handle.
+ *
+ * Decrease the device's usage count and set its power.runtime_auto flag.
+ */
+void pm_runtime_allow(struct device *dev)
+{
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.runtime_auto)
+		goto out;
+
+	dev->power.runtime_auto = true;
+	if (atomic_dec_and_test(&dev->power.usage_count))
+		rpm_idle(dev, RPM_AUTO);
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_allow);
+
+/**
+ * pm_runtime_no_callbacks - Ignore run-time PM callbacks for a device.
+ * @dev: Device to handle.
+ *
+ * Set the power.no_callbacks flag, which tells the PM core that this
+ * device is power-managed through its parent and has no run-time PM
+ * callbacks of its own.  The run-time sysfs attributes will be removed.
+ */
+void pm_runtime_no_callbacks(struct device *dev)
+{
+	spin_lock_irq(&dev->power.lock);
+	dev->power.no_callbacks = 1;
+	spin_unlock_irq(&dev->power.lock);
+	if (device_is_registered(dev))
+		rpm_sysfs_remove(dev);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_no_callbacks);
+
+/**
+ * pm_runtime_irq_safe - Leave interrupts disabled during callbacks.
+ * @dev: Device to handle
+ *
+ * Set the power.irq_safe flag, which tells the PM core that the
+ * ->runtime_suspend() and ->runtime_resume() callbacks for this device should
+ * always be invoked with the spinlock held and interrupts disabled.  It also
+ * causes the parent's usage counter to be permanently incremented, preventing
+ * the parent from runtime suspending -- otherwise an irq-safe child might have
+ * to wait for a non-irq-safe parent.
+ */
+void pm_runtime_irq_safe(struct device *dev)
+{
+	if (dev->parent)
+		pm_runtime_get_sync(dev->parent);
+	spin_lock_irq(&dev->power.lock);
+	dev->power.irq_safe = 1;
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_irq_safe);
+
+/**
+ * update_autosuspend - Handle a change to a device's autosuspend settings.
+ * @dev: Device to handle.
+ * @old_delay: The former autosuspend_delay value.
+ * @old_use: The former use_autosuspend value.
+ *
+ * Prevent runtime suspend if the new delay is negative and use_autosuspend is
+ * set; otherwise allow it.  Send an idle notification if suspends are allowed.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static void update_autosuspend(struct device *dev, int old_delay, int old_use)
+{
+	int delay = dev->power.autosuspend_delay;
+
+	/* Should runtime suspend be prevented now? */
+	if (dev->power.use_autosuspend && delay < 0) {
+
+		/* If it used to be allowed then prevent it. */
+		if (!old_use || old_delay >= 0) {
+			atomic_inc(&dev->power.usage_count);
+			rpm_resume(dev, 0);
+		}
+	}
+
+	/* Runtime suspend should be allowed now. */
+	else {
+
+		/* If it used to be prevented then allow it. */
+		if (old_use && old_delay < 0)
+			atomic_dec(&dev->power.usage_count);
+
+		/* Maybe we can autosuspend now. */
+		rpm_idle(dev, RPM_AUTO);
+	}
+}
+
+/**
+ * pm_runtime_set_autosuspend_delay - Set a device's autosuspend_delay value.
+ * @dev: Device to handle.
+ * @delay: Value of the new delay in milliseconds.
+ *
+ * Set the device's power.autosuspend_delay value.  If it changes to negative
+ * and the power.use_autosuspend flag is set, prevent run-time suspends.  If it
+ * changes the other way, allow run-time suspends.
+ */
+void pm_runtime_set_autosuspend_delay(struct device *dev, int delay)
+{
+	int old_delay, old_use;
+
+	spin_lock_irq(&dev->power.lock);
+	old_delay = dev->power.autosuspend_delay;
+	old_use = dev->power.use_autosuspend;
+	dev->power.autosuspend_delay = delay;
+	update_autosuspend(dev, old_delay, old_use);
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_autosuspend_delay);
+
+/**
+ * __pm_runtime_use_autosuspend - Set a device's use_autosuspend flag.
+ * @dev: Device to handle.
+ * @use: New value for use_autosuspend.
+ *
+ * Set the device's power.use_autosuspend flag, and allow or prevent run-time
+ * suspends as needed.
+ */
+void __pm_runtime_use_autosuspend(struct device *dev, bool use)
+{
+	int old_delay, old_use;
+
+	might_sleep();
+
+	spin_lock_irq(&dev->power.lock);
+	old_delay = dev->power.autosuspend_delay;
+	old_use = dev->power.use_autosuspend;
+	dev->power.use_autosuspend = use;
+	update_autosuspend(dev, old_delay, old_use);
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend);
+
+/**
+ * pm_runtime_init - Initialize run-time PM fields in given device object.
+ * @dev: Device object to initialize.
+ */
+void pm_runtime_init(struct device *dev)
+{
+	dev->power.runtime_status = RPM_SUSPENDED;
+	dev->power.idle_notification = false;
+
+	dev->power.disable_depth = 1;
+	atomic_set(&dev->power.usage_count, 0);
+
+	dev->power.runtime_error = 0;
+
+	atomic_set(&dev->power.child_count, 0);
+	pm_suspend_ignore_children(dev, false);
+	dev->power.runtime_auto = true;
+
+	dev->power.request_pending = false;
+	dev->power.request = RPM_REQ_NONE;
+	dev->power.deferred_resume = false;
+	dev->power.accounting_timestamp = jiffies;
+	INIT_WORK(&dev->power.work, pm_runtime_work);
+
+	dev->power.timer_expires = 0;
+	setup_timer(&dev->power.suspend_timer, pm_suspend_timer_fn,
+			(unsigned long)dev);
+
+	init_waitqueue_head(&dev->power.wait_queue);
+}
+
+/**
+ * pm_runtime_remove - Prepare for removing a device from device hierarchy.
+ * @dev: Device object being removed from device hierarchy.
+ */
+void pm_runtime_remove(struct device *dev)
+{
+	__pm_runtime_disable(dev, false);
+
+	/* Change the status back to 'suspended' to match the initial status. */
+	if (dev->power.runtime_status == RPM_ACTIVE)
+		pm_runtime_set_suspended(dev);
+	if (dev->power.irq_safe && dev->parent)
+		pm_runtime_put_sync(dev->parent);
+}
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
new file mode 100644
index 00000000..a9f5b897
--- /dev/null
+++ b/drivers/base/power/sysfs.c
@@ -0,0 +1,538 @@
+/*
+ * drivers/base/power/sysfs.c - sysfs entries for device PM
+ */
+
+#include <linux/device.h>
+#include <linux/string.h>
+#include <linux/pm_runtime.h>
+#include <asm/atomic.h>
+#include <linux/jiffies.h>
+#include "power.h"
+
+/*
+ *	control - Report/change current runtime PM setting of the device
+ *
+ *	Runtime power management of a device can be blocked with the help of
+ *	this attribute.  All devices have one of the following two values for
+ *	the power/control file:
+ *
+ *	 + "auto\n" to allow the device to be power managed at run time;
+ *	 + "on\n" to prevent the device from being power managed at run time;
+ *
+ *	The default for all devices is "auto", which means that devices may be
+ *	subject to automatic power management, depending on their drivers.
+ *	Changing this attribute to "on" prevents the driver from power managing
+ *	the device at run time.  Doing that while the device is suspended causes
+ *	it to be woken up.
+ *
+ *	wakeup - Report/change current wakeup option for device
+ *
+ *	Some devices support "wakeup" events, which are hardware signals
+ *	used to activate devices from suspended or low power states.  Such
+ *	devices have one of three values for the sysfs power/wakeup file:
+ *
+ *	 + "enabled\n" to issue the events;
+ *	 + "disabled\n" not to do so; or
+ *	 + "\n" for temporary or permanent inability to issue wakeup.
+ *
+ *	(For example, unconfigured USB devices can't issue wakeups.)
+ *
+ *	Familiar examples of devices that can issue wakeup events include
+ *	keyboards and mice (both PS2 and USB styles), power buttons, modems,
+ *	"Wake-On-LAN" Ethernet links, GPIO lines, and more.  Some events
+ *	will wake the entire system from a suspend state; others may just
+ *	wake up the device (if the system as a whole is already active).
+ *	Some wakeup events use normal IRQ lines; other use special out
+ *	of band signaling.
+ *
+ *	It is the responsibility of device drivers to enable (or disable)
+ *	wakeup signaling as part of changing device power states, respecting
+ *	the policy choices provided through the driver model.
+ *
+ *	Devices may not be able to generate wakeup events from all power
+ *	states.  Also, the events may be ignored in some configurations;
+ *	for example, they might need help from other devices that aren't
+ *	active, or which may have wakeup disabled.  Some drivers rely on
+ *	wakeup events internally (unless they are disabled), keeping
+ *	their hardware in low power modes whenever they're unused.  This
+ *	saves runtime power, without requiring system-wide sleep states.
+ *
+ *	async - Report/change current async suspend setting for the device
+ *
+ *	Asynchronous suspend and resume of the device during system-wide power
+ *	state transitions can be enabled by writing "enabled" to this file.
+ *	Analogously, if "disabled" is written to this file, the device will be
+ *	suspended and resumed synchronously.
+ *
+ *	All devices have one of the following two values for power/async:
+ *
+ *	 + "enabled\n" to permit the asynchronous suspend/resume of the device;
+ *	 + "disabled\n" to forbid it;
+ *
+ *	NOTE: It generally is unsafe to permit the asynchronous suspend/resume
+ *	of a device unless it is certain that all of the PM dependencies of the
+ *	device are known to the PM core.  However, for some devices this
+ *	attribute is set to "enabled" by bus type code or device drivers and in
+ *	that cases it should be safe to leave the default value.
+ *
+ *	autosuspend_delay_ms - Report/change a device's autosuspend_delay value
+ *
+ *	Some drivers don't want to carry out a runtime suspend as soon as a
+ *	device becomes idle; they want it always to remain idle for some period
+ *	of time before suspending it.  This period is the autosuspend_delay
+ *	value (expressed in milliseconds) and it can be controlled by the user.
+ *	If the value is negative then the device will never be runtime
+ *	suspended.
+ *
+ *	NOTE: The autosuspend_delay_ms attribute and the autosuspend_delay
+ *	value are used only if the driver calls pm_runtime_use_autosuspend().
+ *
+ *	wakeup_count - Report the number of wakeup events related to the device
+ */
+
+static const char enabled[] = "enabled";
+static const char disabled[] = "disabled";
+
+const char power_group_name[] = "power";
+EXPORT_SYMBOL_GPL(power_group_name);
+
+#ifdef CONFIG_PM_RUNTIME
+static const char ctrl_auto[] = "auto";
+static const char ctrl_on[] = "on";
+
+static ssize_t control_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "%s\n",
+				dev->power.runtime_auto ? ctrl_auto : ctrl_on);
+}
+
+static ssize_t control_store(struct device * dev, struct device_attribute *attr,
+			     const char * buf, size_t n)
+{
+	char *cp;
+	int len = n;
+
+	cp = memchr(buf, '\n', n);
+	if (cp)
+		len = cp - buf;
+	if (len == sizeof ctrl_auto - 1 && strncmp(buf, ctrl_auto, len) == 0)
+		pm_runtime_allow(dev);
+	else if (len == sizeof ctrl_on - 1 && strncmp(buf, ctrl_on, len) == 0)
+		pm_runtime_forbid(dev);
+	else
+		return -EINVAL;
+	return n;
+}
+
+static DEVICE_ATTR(control, 0644, control_show, control_store);
+
+static ssize_t rtpm_active_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int ret;
+	spin_lock_irq(&dev->power.lock);
+	update_pm_runtime_accounting(dev);
+	ret = sprintf(buf, "%i\n", jiffies_to_msecs(dev->power.active_jiffies));
+	spin_unlock_irq(&dev->power.lock);
+	return ret;
+}
+
+static DEVICE_ATTR(runtime_active_time, 0444, rtpm_active_time_show, NULL);
+
+static ssize_t rtpm_suspended_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int ret;
+	spin_lock_irq(&dev->power.lock);
+	update_pm_runtime_accounting(dev);
+	ret = sprintf(buf, "%i\n",
+		jiffies_to_msecs(dev->power.suspended_jiffies));
+	spin_unlock_irq(&dev->power.lock);
+	return ret;
+}
+
+static DEVICE_ATTR(runtime_suspended_time, 0444, rtpm_suspended_time_show, NULL);
+
+static ssize_t rtpm_status_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	const char *p;
+
+	if (dev->power.runtime_error) {
+		p = "error\n";
+	} else if (dev->power.disable_depth) {
+		p = "unsupported\n";
+	} else {
+		switch (dev->power.runtime_status) {
+		case RPM_SUSPENDED:
+			p = "suspended\n";
+			break;
+		case RPM_SUSPENDING:
+			p = "suspending\n";
+			break;
+		case RPM_RESUMING:
+			p = "resuming\n";
+			break;
+		case RPM_ACTIVE:
+			p = "active\n";
+			break;
+		default:
+			return -EIO;
+		}
+	}
+	return sprintf(buf, p);
+}
+
+static DEVICE_ATTR(runtime_status, 0444, rtpm_status_show, NULL);
+
+static ssize_t autosuspend_delay_ms_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	if (!dev->power.use_autosuspend)
+		return -EIO;
+	return sprintf(buf, "%d\n", dev->power.autosuspend_delay);
+}
+
+static ssize_t autosuspend_delay_ms_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t n)
+{
+	long delay;
+
+	if (!dev->power.use_autosuspend)
+		return -EIO;
+
+	if (strict_strtol(buf, 10, &delay) != 0 || delay != (int) delay)
+		return -EINVAL;
+
+	pm_runtime_set_autosuspend_delay(dev, delay);
+	return n;
+}
+
+static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
+		autosuspend_delay_ms_store);
+
+#endif /* CONFIG_PM_RUNTIME */
+
+#ifdef CONFIG_PM_SLEEP
+static ssize_t
+wake_show(struct device * dev, struct device_attribute *attr, char * buf)
+{
+	return sprintf(buf, "%s\n", device_can_wakeup(dev)
+		? (device_may_wakeup(dev) ? enabled : disabled)
+		: "");
+}
+
+static ssize_t
+wake_store(struct device * dev, struct device_attribute *attr,
+	const char * buf, size_t n)
+{
+	char *cp;
+	int len = n;
+
+	if (!device_can_wakeup(dev))
+		return -EINVAL;
+
+	cp = memchr(buf, '\n', n);
+	if (cp)
+		len = cp - buf;
+	if (len == sizeof enabled - 1
+			&& strncmp(buf, enabled, sizeof enabled - 1) == 0)
+		device_set_wakeup_enable(dev, 1);
+	else if (len == sizeof disabled - 1
+			&& strncmp(buf, disabled, sizeof disabled - 1) == 0)
+		device_set_wakeup_enable(dev, 0);
+	else
+		return -EINVAL;
+	return n;
+}
+
+static DEVICE_ATTR(wakeup, 0644, wake_show, wake_store);
+
+static ssize_t wakeup_count_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->event_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_count, 0444, wakeup_count_show, NULL);
+
+static ssize_t wakeup_active_count_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->active_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_active_count, 0444, wakeup_active_count_show, NULL);
+
+static ssize_t wakeup_hit_count_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->hit_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_hit_count, 0444, wakeup_hit_count_show, NULL);
+
+static ssize_t wakeup_active_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned int active = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		active = dev->power.wakeup->active;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%u\n", active) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_active, 0444, wakeup_active_show, NULL);
+
+static ssize_t wakeup_total_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->total_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_total_time_ms, 0444, wakeup_total_time_show, NULL);
+
+static ssize_t wakeup_max_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->max_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_max_time_ms, 0444, wakeup_max_time_show, NULL);
+
+static ssize_t wakeup_last_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->last_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_last_time_ms, 0444, wakeup_last_time_show, NULL);
+#endif /* CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+#ifdef CONFIG_PM_RUNTIME
+
+static ssize_t rtpm_usagecount_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", atomic_read(&dev->power.usage_count));
+}
+
+static ssize_t rtpm_children_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", dev->power.ignore_children ?
+		0 : atomic_read(&dev->power.child_count));
+}
+
+static ssize_t rtpm_enabled_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	if ((dev->power.disable_depth) && (dev->power.runtime_auto == false))
+		return sprintf(buf, "disabled & forbidden\n");
+	else if (dev->power.disable_depth)
+		return sprintf(buf, "disabled\n");
+	else if (dev->power.runtime_auto == false)
+		return sprintf(buf, "forbidden\n");
+	return sprintf(buf, "enabled\n");
+}
+
+static DEVICE_ATTR(runtime_usage, 0444, rtpm_usagecount_show, NULL);
+static DEVICE_ATTR(runtime_active_kids, 0444, rtpm_children_show, NULL);
+static DEVICE_ATTR(runtime_enabled, 0444, rtpm_enabled_show, NULL);
+
+#endif
+
+static ssize_t async_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	return sprintf(buf, "%s\n",
+			device_async_suspend_enabled(dev) ? enabled : disabled);
+}
+
+static ssize_t async_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t n)
+{
+	char *cp;
+	int len = n;
+
+	cp = memchr(buf, '\n', n);
+	if (cp)
+		len = cp - buf;
+	if (len == sizeof enabled - 1 && strncmp(buf, enabled, len) == 0)
+		device_enable_async_suspend(dev);
+	else if (len == sizeof disabled - 1 && strncmp(buf, disabled, len) == 0)
+		device_disable_async_suspend(dev);
+	else
+		return -EINVAL;
+	return n;
+}
+
+static DEVICE_ATTR(async, 0644, async_show, async_store);
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
+
+static struct attribute *power_attrs[] = {
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+#ifdef CONFIG_PM_SLEEP
+	&dev_attr_async.attr,
+#endif
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_runtime_status.attr,
+	&dev_attr_runtime_usage.attr,
+	&dev_attr_runtime_active_kids.attr,
+	&dev_attr_runtime_enabled.attr,
+#endif
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
+	NULL,
+};
+static struct attribute_group pm_attr_group = {
+	.name	= power_group_name,
+	.attrs	= power_attrs,
+};
+
+static struct attribute *wakeup_attrs[] = {
+#ifdef CONFIG_PM_SLEEP
+	&dev_attr_wakeup.attr,
+	&dev_attr_wakeup_count.attr,
+	&dev_attr_wakeup_active_count.attr,
+	&dev_attr_wakeup_hit_count.attr,
+	&dev_attr_wakeup_active.attr,
+	&dev_attr_wakeup_total_time_ms.attr,
+	&dev_attr_wakeup_max_time_ms.attr,
+	&dev_attr_wakeup_last_time_ms.attr,
+#endif
+	NULL,
+};
+static struct attribute_group pm_wakeup_attr_group = {
+	.name	= power_group_name,
+	.attrs	= wakeup_attrs,
+};
+
+static struct attribute *runtime_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
+#ifndef CONFIG_PM_ADVANCED_DEBUG
+	&dev_attr_runtime_status.attr,
+#endif
+	&dev_attr_control.attr,
+	&dev_attr_runtime_suspended_time.attr,
+	&dev_attr_runtime_active_time.attr,
+	&dev_attr_autosuspend_delay_ms.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	NULL,
+};
+static struct attribute_group pm_runtime_attr_group = {
+	.name	= power_group_name,
+	.attrs	= runtime_attrs,
+};
+
+int dpm_sysfs_add(struct device *dev)
+{
+	int rc;
+
+	rc = sysfs_create_group(&dev->kobj, &pm_attr_group);
+	if (rc)
+		return rc;
+
+	if (pm_runtime_callbacks_present(dev)) {
+		rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group);
+		if (rc)
+			goto err_out;
+	}
+
+	if (device_can_wakeup(dev)) {
+		rc = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+		if (rc) {
+			if (pm_runtime_callbacks_present(dev))
+				sysfs_unmerge_group(&dev->kobj,
+						    &pm_runtime_attr_group);
+			goto err_out;
+		}
+	}
+	return 0;
+
+ err_out:
+	sysfs_remove_group(&dev->kobj, &pm_attr_group);
+	return rc;
+}
+
+int wakeup_sysfs_add(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+}
+
+void wakeup_sysfs_remove(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
+}
+
+void rpm_sysfs_remove(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
+}
+
+void dpm_sysfs_remove(struct device *dev)
+{
+	rpm_sysfs_remove(dev);
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
+	sysfs_remove_group(&dev->kobj, &pm_attr_group);
+}
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
new file mode 100644
index 00000000..c80e138b
--- /dev/null
+++ b/drivers/base/power/trace.c
@@ -0,0 +1,265 @@
+/*
+ * drivers/base/power/trace.c
+ *
+ * Copyright (C) 2006 Linus Torvalds
+ *
+ * Trace facility for suspend/resume problems, when none of the
+ * devices may be working.
+ */
+
+#include <linux/resume-trace.h>
+#include <linux/rtc.h>
+
+#include <asm/rtc.h>
+
+#include "power.h"
+
+/*
+ * Horrid, horrid, horrid.
+ *
+ * It turns out that the _only_ piece of hardware that actually
+ * keeps its value across a hard boot (and, more importantly, the
+ * POST init sequence) is literally the realtime clock.
+ *
+ * Never mind that an RTC chip has 114 bytes (and often a whole
+ * other bank of an additional 128 bytes) of nice SRAM that is
+ * _designed_ to keep data - the POST will clear it. So we literally
+ * can just use the few bytes of actual time data, which means that
+ * we're really limited.
+ *
+ * It means, for example, that we can't use the seconds at all
+ * (since the time between the hang and the boot might be more
+ * than a minute), and we'd better not depend on the low bits of
+ * the minutes either.
+ *
+ * There are the wday fields etc, but I wouldn't guarantee those
+ * are dependable either. And if the date isn't valid, either the
+ * hw or POST will do strange things.
+ *
+ * So we're left with:
+ *  - year: 0-99
+ *  - month: 0-11
+ *  - day-of-month: 1-28
+ *  - hour: 0-23
+ *  - min: (0-30)*2
+ *
+ * Giving us a total range of 0-16128000 (0xf61800), ie less
+ * than 24 bits of actual data we can save across reboots.
+ *
+ * And if your box can't boot in less than three minutes,
+ * you're screwed.
+ *
+ * Now, almost 24 bits of data is pitifully small, so we need
+ * to be pretty dense if we want to use it for anything nice.
+ * What we do is that instead of saving off nice readable info,
+ * we save off _hashes_ of information that we can hopefully
+ * regenerate after the reboot.
+ *
+ * In particular, this means that we might be unlucky, and hit
+ * a case where we have a hash collision, and we end up not
+ * being able to tell for certain exactly which case happened.
+ * But that's hopefully unlikely.
+ *
+ * What we do is to take the bits we can fit, and split them
+ * into three parts (16*997*1009 = 16095568), and use the values
+ * for:
+ *  - 0-15: user-settable
+ *  - 0-996: file + line number
+ *  - 0-1008: device
+ */
+#define USERHASH (16)
+#define FILEHASH (997)
+#define DEVHASH (1009)
+
+#define DEVSEED (7919)
+
+static unsigned int dev_hash_value;
+
+static int set_magic_time(unsigned int user, unsigned int file, unsigned int device)
+{
+	unsigned int n = user + USERHASH*(file + FILEHASH*device);
+
+	// June 7th, 2006
+	static struct rtc_time time = {
+		.tm_sec = 0,
+		.tm_min = 0,
+		.tm_hour = 0,
+		.tm_mday = 7,
+		.tm_mon = 5,	// June - counting from zero
+		.tm_year = 106,
+		.tm_wday = 3,
+		.tm_yday = 160,
+		.tm_isdst = 1
+	};
+
+	time.tm_year = (n % 100);
+	n /= 100;
+	time.tm_mon = (n % 12);
+	n /= 12;
+	time.tm_mday = (n % 28) + 1;
+	n /= 28;
+	time.tm_hour = (n % 24);
+	n /= 24;
+	time.tm_min = (n % 20) * 3;
+	n /= 20;
+	set_rtc_time(&time);
+	return n ? -1 : 0;
+}
+
+static unsigned int read_magic_time(void)
+{
+	struct rtc_time time;
+	unsigned int val;
+
+	get_rtc_time(&time);
+	pr_info("Time: %2d:%02d:%02d  Date: %02d/%02d/%02d\n",
+		time.tm_hour, time.tm_min, time.tm_sec,
+		time.tm_mon + 1, time.tm_mday, time.tm_year % 100);
+	val = time.tm_year;				/* 100 years */
+	if (val > 100)
+		val -= 100;
+	val += time.tm_mon * 100;			/* 12 months */
+	val += (time.tm_mday-1) * 100 * 12;		/* 28 month-days */
+	val += time.tm_hour * 100 * 12 * 28;		/* 24 hours */
+	val += (time.tm_min / 3) * 100 * 12 * 28 * 24;	/* 20 3-minute intervals */
+	return val;
+}
+
+/*
+ * This is just the sdbm hash function with a user-supplied
+ * seed and final size parameter.
+ */
+static unsigned int hash_string(unsigned int seed, const char *data, unsigned int mod)
+{
+	unsigned char c;
+	while ((c = *data++) != 0) {
+		seed = (seed << 16) + (seed << 6) - seed + c;
+	}
+	return seed % mod;
+}
+
+void set_trace_device(struct device *dev)
+{
+	dev_hash_value = hash_string(DEVSEED, dev_name(dev), DEVHASH);
+}
+EXPORT_SYMBOL(set_trace_device);
+
+/*
+ * We could just take the "tracedata" index into the .tracedata
+ * section instead. Generating a hash of the data gives us a
+ * chance to work across kernel versions, and perhaps more
+ * importantly it also gives us valid/invalid check (ie we will
+ * likely not give totally bogus reports - if the hash matches,
+ * it's not any guarantee, but it's a high _likelihood_ that
+ * the match is valid).
+ */
+void generate_resume_trace(const void *tracedata, unsigned int user)
+{
+	unsigned short lineno = *(unsigned short *)tracedata;
+	const char *file = *(const char **)(tracedata + 2);
+	unsigned int user_hash_value, file_hash_value;
+
+	user_hash_value = user % USERHASH;
+	file_hash_value = hash_string(lineno, file, FILEHASH);
+	set_magic_time(user_hash_value, file_hash_value, dev_hash_value);
+}
+EXPORT_SYMBOL(generate_resume_trace);
+
+extern char __tracedata_start, __tracedata_end;
+static int show_file_hash(unsigned int value)
+{
+	int match;
+	char *tracedata;
+
+	match = 0;
+	for (tracedata = &__tracedata_start ; tracedata < &__tracedata_end ;
+			tracedata += 2 + sizeof(unsigned long)) {
+		unsigned short lineno = *(unsigned short *)tracedata;
+		const char *file = *(const char **)(tracedata + 2);
+		unsigned int hash = hash_string(lineno, file, FILEHASH);
+		if (hash != value)
+			continue;
+		pr_info("  hash matches %s:%u\n", file, lineno);
+		match++;
+	}
+	return match;
+}
+
+static int show_dev_hash(unsigned int value)
+{
+	int match = 0;
+	struct list_head *entry;
+
+	device_pm_lock();
+	entry = dpm_list.prev;
+	while (entry != &dpm_list) {
+		struct device * dev = to_device(entry);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH);
+		if (hash == value) {
+			dev_info(dev, "hash matches\n");
+			match++;
+		}
+		entry = entry->prev;
+	}
+	device_pm_unlock();
+	return match;
+}
+
+static unsigned int hash_value_early_read;
+
+int show_trace_dev_match(char *buf, size_t size)
+{
+	unsigned int value = hash_value_early_read / (USERHASH * FILEHASH);
+	int ret = 0;
+	struct list_head *entry;
+
+	/*
+	 * It's possible that multiple devices will match the hash and we can't
+	 * tell which is the culprit, so it's best to output them all.
+	 */
+	device_pm_lock();
+	entry = dpm_list.prev;
+	while (size && entry != &dpm_list) {
+		struct device *dev = to_device(entry);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev),
+						DEVHASH);
+		if (hash == value) {
+			int len = snprintf(buf, size, "%s\n",
+					    dev_driver_string(dev));
+			if (len > size)
+				len = size;
+			buf += len;
+			ret += len;
+			size -= len;
+		}
+		entry = entry->prev;
+	}
+	device_pm_unlock();
+	return ret;
+}
+
+static int early_resume_init(void)
+{
+	hash_value_early_read = read_magic_time();
+	return 0;
+}
+
+static int late_resume_init(void)
+{
+	unsigned int val = hash_value_early_read;
+	unsigned int user, file, dev;
+
+	user = val % USERHASH;
+	val = val / USERHASH;
+	file = val % FILEHASH;
+	val = val / FILEHASH;
+	dev = val /* % DEVHASH */;
+
+	pr_info("  Magic number: %d:%d:%d\n", user, file, dev);
+	show_file_hash(file);
+	show_dev_hash(dev);
+	return 0;
+}
+
+core_initcall(early_resume_init);
+late_initcall(late_resume_init);
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
new file mode 100644
index 00000000..84f7c7d5
--- /dev/null
+++ b/drivers/base/power/wakeup.c
@@ -0,0 +1,746 @@
+/*
+ * drivers/base/power/wakeup.c - System wakeup events framework
+ *
+ * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/capability.h>
+#include <linux/suspend.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+
+#include "power.h"
+
+#define TIMEOUT		100
+
+/*
+ * If set, the suspend/hibernate code will abort transitions to a sleep state
+ * if wakeup events are registered during or immediately before the transition.
+ */
+bool events_check_enabled;
+
+/*
+ * Combined counters of registered wakeup events and wakeup events in progress.
+ * They need to be modified together atomically, so it's better to use one
+ * atomic variable to hold them both.
+ */
+static atomic_t combined_event_count = ATOMIC_INIT(0);
+
+#define IN_PROGRESS_BITS	(sizeof(int) * 4)
+#define MAX_IN_PROGRESS		((1 << IN_PROGRESS_BITS) - 1)
+
+static void split_counters(unsigned int *cnt, unsigned int *inpr)
+{
+	unsigned int comb = atomic_read(&combined_event_count);
+
+	*cnt = (comb >> IN_PROGRESS_BITS);
+	*inpr = comb & MAX_IN_PROGRESS;
+}
+
+/* A preserved old value of the events counter. */
+static unsigned int saved_count;
+
+static DEFINE_SPINLOCK(events_lock);
+
+static void pm_wakeup_timer_fn(unsigned long data);
+
+static LIST_HEAD(wakeup_sources);
+
+/**
+ * wakeup_source_create - Create a struct wakeup_source object.
+ * @name: Name of the new wakeup source.
+ */
+struct wakeup_source *wakeup_source_create(const char *name)
+{
+	struct wakeup_source *ws;
+
+	ws = kzalloc(sizeof(*ws), GFP_KERNEL);
+	if (!ws)
+		return NULL;
+
+	spin_lock_init(&ws->lock);
+	if (name)
+		ws->name = kstrdup(name, GFP_KERNEL);
+
+	return ws;
+}
+EXPORT_SYMBOL_GPL(wakeup_source_create);
+
+/**
+ * wakeup_source_destroy - Destroy a struct wakeup_source object.
+ * @ws: Wakeup source to destroy.
+ */
+void wakeup_source_destroy(struct wakeup_source *ws)
+{
+	if (!ws)
+		return;
+
+	spin_lock_irq(&ws->lock);
+	while (ws->active) {
+		spin_unlock_irq(&ws->lock);
+
+		schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT));
+
+		spin_lock_irq(&ws->lock);
+	}
+	spin_unlock_irq(&ws->lock);
+
+	kfree(ws->name);
+	kfree(ws);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_destroy);
+
+/**
+ * wakeup_source_add - Add given object to the list of wakeup sources.
+ * @ws: Wakeup source object to add to the list.
+ */
+void wakeup_source_add(struct wakeup_source *ws)
+{
+	if (WARN_ON(!ws))
+		return;
+
+	setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws);
+	ws->active = false;
+
+	spin_lock_irq(&events_lock);
+	list_add_rcu(&ws->entry, &wakeup_sources);
+	spin_unlock_irq(&events_lock);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_add);
+
+/**
+ * wakeup_source_remove - Remove given object from the wakeup sources list.
+ * @ws: Wakeup source object to remove from the list.
+ */
+void wakeup_source_remove(struct wakeup_source *ws)
+{
+	if (WARN_ON(!ws))
+		return;
+
+	spin_lock_irq(&events_lock);
+	list_del_rcu(&ws->entry);
+	spin_unlock_irq(&events_lock);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(wakeup_source_remove);
+
+/**
+ * wakeup_source_register - Create wakeup source and add it to the list.
+ * @name: Name of the wakeup source to register.
+ */
+struct wakeup_source *wakeup_source_register(const char *name)
+{
+	struct wakeup_source *ws;
+
+	ws = wakeup_source_create(name);
+	if (ws)
+		wakeup_source_add(ws);
+
+	return ws;
+}
+EXPORT_SYMBOL_GPL(wakeup_source_register);
+
+/**
+ * wakeup_source_unregister - Remove wakeup source from the list and remove it.
+ * @ws: Wakeup source object to unregister.
+ */
+void wakeup_source_unregister(struct wakeup_source *ws)
+{
+	wakeup_source_remove(ws);
+	wakeup_source_destroy(ws);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_unregister);
+
+/**
+ * device_wakeup_attach - Attach a wakeup source object to a device object.
+ * @dev: Device to handle.
+ * @ws: Wakeup source object to attach to @dev.
+ *
+ * This causes @dev to be treated as a wakeup device.
+ */
+static int device_wakeup_attach(struct device *dev, struct wakeup_source *ws)
+{
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		spin_unlock_irq(&dev->power.lock);
+		return -EEXIST;
+	}
+	dev->power.wakeup = ws;
+	spin_unlock_irq(&dev->power.lock);
+	return 0;
+}
+
+/**
+ * device_wakeup_enable - Enable given device to be a wakeup source.
+ * @dev: Device to handle.
+ *
+ * Create a wakeup source object, register it and attach it to @dev.
+ */
+int device_wakeup_enable(struct device *dev)
+{
+	struct wakeup_source *ws;
+	int ret;
+
+	if (!dev || !dev->power.can_wakeup)
+		return -EINVAL;
+
+	ws = wakeup_source_register(dev_name(dev));
+	if (!ws)
+		return -ENOMEM;
+
+	ret = device_wakeup_attach(dev, ws);
+	if (ret)
+		wakeup_source_unregister(ws);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(device_wakeup_enable);
+
+/**
+ * device_wakeup_detach - Detach a device's wakeup source object from it.
+ * @dev: Device to detach the wakeup source object from.
+ *
+ * After it returns, @dev will not be treated as a wakeup device any more.
+ */
+static struct wakeup_source *device_wakeup_detach(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	spin_lock_irq(&dev->power.lock);
+	ws = dev->power.wakeup;
+	dev->power.wakeup = NULL;
+	spin_unlock_irq(&dev->power.lock);
+	return ws;
+}
+
+/**
+ * device_wakeup_disable - Do not regard a device as a wakeup source any more.
+ * @dev: Device to handle.
+ *
+ * Detach the @dev's wakeup source object from it, unregister this wakeup source
+ * object and destroy it.
+ */
+int device_wakeup_disable(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	if (!dev || !dev->power.can_wakeup)
+		return -EINVAL;
+
+	ws = device_wakeup_detach(dev);
+	if (ws)
+		wakeup_source_unregister(ws);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(device_wakeup_disable);
+
+/**
+ * device_set_wakeup_capable - Set/reset device wakeup capability flag.
+ * @dev: Device to handle.
+ * @capable: Whether or not @dev is capable of waking up the system from sleep.
+ *
+ * If @capable is set, set the @dev's power.can_wakeup flag and add its
+ * wakeup-related attributes to sysfs.  Otherwise, unset the @dev's
+ * power.can_wakeup flag and remove its wakeup-related attributes from sysfs.
+ *
+ * This function may sleep and it can't be called from any context where
+ * sleeping is not allowed.
+ */
+void device_set_wakeup_capable(struct device *dev, bool capable)
+{
+	if (!!dev->power.can_wakeup == !!capable)
+		return;
+
+	if (device_is_registered(dev) && !list_empty(&dev->power.entry)) {
+		if (capable) {
+			if (wakeup_sysfs_add(dev))
+				return;
+		} else {
+			wakeup_sysfs_remove(dev);
+		}
+	}
+	dev->power.can_wakeup = capable;
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_capable);
+
+/**
+ * device_init_wakeup - Device wakeup initialization.
+ * @dev: Device to handle.
+ * @enable: Whether or not to enable @dev as a wakeup device.
+ *
+ * By default, most devices should leave wakeup disabled.  The exceptions are
+ * devices that everyone expects to be wakeup sources: keyboards, power buttons,
+ * possibly network interfaces, etc.
+ */
+int device_init_wakeup(struct device *dev, bool enable)
+{
+	int ret = 0;
+
+	if (enable) {
+		device_set_wakeup_capable(dev, true);
+		ret = device_wakeup_enable(dev);
+	} else {
+		device_set_wakeup_capable(dev, false);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(device_init_wakeup);
+
+/**
+ * device_set_wakeup_enable - Enable or disable a device to wake up the system.
+ * @dev: Device to handle.
+ */
+int device_set_wakeup_enable(struct device *dev, bool enable)
+{
+	if (!dev || !dev->power.can_wakeup)
+		return -EINVAL;
+
+	return enable ? device_wakeup_enable(dev) : device_wakeup_disable(dev);
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
+
+/*
+ * The functions below use the observation that each wakeup event starts a
+ * period in which the system should not be suspended.  The moment this period
+ * will end depends on how the wakeup event is going to be processed after being
+ * detected and all of the possible cases can be divided into two distinct
+ * groups.
+ *
+ * First, a wakeup event may be detected by the same functional unit that will
+ * carry out the entire processing of it and possibly will pass it to user space
+ * for further processing.  In that case the functional unit that has detected
+ * the event may later "close" the "no suspend" period associated with it
+ * directly as soon as it has been dealt with.  The pair of pm_stay_awake() and
+ * pm_relax(), balanced with each other, is supposed to be used in such
+ * situations.
+ *
+ * Second, a wakeup event may be detected by one functional unit and processed
+ * by another one.  In that case the unit that has detected it cannot really
+ * "close" the "no suspend" period associated with it, unless it knows in
+ * advance what's going to happen to the event during processing.  This
+ * knowledge, however, may not be available to it, so it can simply specify time
+ * to wait before the system can be suspended and pass it as the second
+ * argument of pm_wakeup_event().
+ *
+ * It is valid to call pm_relax() after pm_wakeup_event(), in which case the
+ * "no suspend" period will be ended either by the pm_relax(), or by the timer
+ * function executed when the timer expires, whichever comes first.
+ */
+
+/**
+ * wakup_source_activate - Mark given wakeup source as active.
+ * @ws: Wakeup source to handle.
+ *
+ * Update the @ws' statistics and, if @ws has just been activated, notify the PM
+ * core of the event by incrementing the counter of of wakeup events being
+ * processed.
+ */
+static void wakeup_source_activate(struct wakeup_source *ws)
+{
+	ws->active = true;
+	ws->active_count++;
+	ws->timer_expires = jiffies;
+	ws->last_time = ktime_get();
+
+	/* Increment the counter of events in progress. */
+	atomic_inc(&combined_event_count);
+}
+
+/**
+ * __pm_stay_awake - Notify the PM core of a wakeup event.
+ * @ws: Wakeup source object associated with the source of the event.
+ *
+ * It is safe to call this function from interrupt context.
+ */
+void __pm_stay_awake(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+	ws->event_count++;
+	if (!ws->active)
+		wakeup_source_activate(ws);
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_stay_awake);
+
+/**
+ * pm_stay_awake - Notify the PM core that a wakeup event is being processed.
+ * @dev: Device the wakeup event is related to.
+ *
+ * Notify the PM core of a wakeup event (signaled by @dev) by calling
+ * __pm_stay_awake for the @dev's wakeup source object.
+ *
+ * Call this function after detecting of a wakeup event if pm_relax() is going
+ * to be called directly after processing the event (and possibly passing it to
+ * user space for further processing).
+ */
+void pm_stay_awake(struct device *dev)
+{
+	unsigned long flags;
+
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_stay_awake(dev->power.wakeup);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_stay_awake);
+
+/**
+ * wakup_source_deactivate - Mark given wakeup source as inactive.
+ * @ws: Wakeup source to handle.
+ *
+ * Update the @ws' statistics and notify the PM core that the wakeup source has
+ * become inactive by decrementing the counter of wakeup events being processed
+ * and incrementing the counter of registered wakeup events.
+ */
+static void wakeup_source_deactivate(struct wakeup_source *ws)
+{
+	ktime_t duration;
+	ktime_t now;
+
+	ws->relax_count++;
+	/*
+	 * __pm_relax() may be called directly or from a timer function.
+	 * If it is called directly right after the timer function has been
+	 * started, but before the timer function calls __pm_relax(), it is
+	 * possible that __pm_stay_awake() will be called in the meantime and
+	 * will set ws->active.  Then, ws->active may be cleared immediately
+	 * by the __pm_relax() called from the timer function, but in such a
+	 * case ws->relax_count will be different from ws->active_count.
+	 */
+	if (ws->relax_count != ws->active_count) {
+		ws->relax_count--;
+		return;
+	}
+
+	ws->active = false;
+
+	now = ktime_get();
+	duration = ktime_sub(now, ws->last_time);
+	ws->total_time = ktime_add(ws->total_time, duration);
+	if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time))
+		ws->max_time = duration;
+
+	del_timer(&ws->timer);
+
+	/*
+	 * Increment the counter of registered wakeup events and decrement the
+	 * couter of wakeup events in progress simultaneously.
+	 */
+	atomic_add(MAX_IN_PROGRESS, &combined_event_count);
+}
+
+/**
+ * __pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * @ws: Wakeup source object associated with the source of the event.
+ *
+ * Call this function for wakeup events whose processing started with calling
+ * __pm_stay_awake().
+ *
+ * It is safe to call it from interrupt context.
+ */
+void __pm_relax(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+	if (ws->active)
+		wakeup_source_deactivate(ws);
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_relax);
+
+/**
+ * pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * @dev: Device that signaled the event.
+ *
+ * Execute __pm_relax() for the @dev's wakeup source object.
+ */
+void pm_relax(struct device *dev)
+{
+	unsigned long flags;
+
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_relax(dev->power.wakeup);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_relax);
+
+/**
+ * pm_wakeup_timer_fn - Delayed finalization of a wakeup event.
+ * @data: Address of the wakeup source object associated with the event source.
+ *
+ * Call __pm_relax() for the wakeup source whose address is stored in @data.
+ */
+static void pm_wakeup_timer_fn(unsigned long data)
+{
+	__pm_relax((struct wakeup_source *)data);
+}
+
+/**
+ * __pm_wakeup_event - Notify the PM core of a wakeup event.
+ * @ws: Wakeup source object associated with the event source.
+ * @msec: Anticipated event processing time (in milliseconds).
+ *
+ * Notify the PM core of a wakeup event whose source is @ws that will take
+ * approximately @msec milliseconds to be processed by the kernel.  If @ws is
+ * not active, activate it.  If @msec is nonzero, set up the @ws' timer to
+ * execute pm_wakeup_timer_fn() in future.
+ *
+ * It is safe to call this function from interrupt context.
+ */
+void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec)
+{
+	unsigned long flags;
+	unsigned long expires;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	ws->event_count++;
+	if (!ws->active)
+		wakeup_source_activate(ws);
+
+	if (!msec) {
+		wakeup_source_deactivate(ws);
+		goto unlock;
+	}
+
+	expires = jiffies + msecs_to_jiffies(msec);
+	if (!expires)
+		expires = 1;
+
+	if (time_after(expires, ws->timer_expires)) {
+		mod_timer(&ws->timer, expires);
+		ws->timer_expires = expires;
+	}
+
+ unlock:
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_wakeup_event);
+
+
+/**
+ * pm_wakeup_event - Notify the PM core of a wakeup event.
+ * @dev: Device the wakeup event is related to.
+ * @msec: Anticipated event processing time (in milliseconds).
+ *
+ * Call __pm_wakeup_event() for the @dev's wakeup source object.
+ */
+void pm_wakeup_event(struct device *dev, unsigned int msec)
+{
+	unsigned long flags;
+
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_wakeup_event(dev->power.wakeup, msec);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_wakeup_event);
+
+/**
+ * pm_wakeup_update_hit_counts - Update hit counts of all active wakeup sources.
+ */
+static void pm_wakeup_update_hit_counts(void)
+{
+	unsigned long flags;
+	struct wakeup_source *ws;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		spin_lock_irqsave(&ws->lock, flags);
+		if (ws->active)
+			ws->hit_count++;
+		spin_unlock_irqrestore(&ws->lock, flags);
+	}
+	rcu_read_unlock();
+}
+
+/**
+ * pm_wakeup_pending - Check if power transition in progress should be aborted.
+ *
+ * Compare the current number of registered wakeup events with its preserved
+ * value from the past and return true if new wakeup events have been registered
+ * since the old value was stored.  Also return true if the current number of
+ * wakeup events being processed is different from zero.
+ */
+bool pm_wakeup_pending(void)
+{
+	unsigned long flags;
+	bool ret = false;
+
+	spin_lock_irqsave(&events_lock, flags);
+	if (events_check_enabled) {
+		unsigned int cnt, inpr;
+
+		split_counters(&cnt, &inpr);
+		ret = (cnt != saved_count || inpr > 0);
+		events_check_enabled = !ret;
+	}
+	spin_unlock_irqrestore(&events_lock, flags);
+	if (ret)
+		pm_wakeup_update_hit_counts();
+	return ret;
+}
+
+/**
+ * pm_get_wakeup_count - Read the number of registered wakeup events.
+ * @count: Address to store the value at.
+ *
+ * Store the number of registered wakeup events at the address in @count.  Block
+ * if the current number of wakeup events being processed is nonzero.
+ *
+ * Return 'false' if the wait for the number of wakeup events being processed to
+ * drop down to zero has been interrupted by a signal (and the current number
+ * of wakeup events being processed is still nonzero).  Otherwise return 'true'.
+ */
+bool pm_get_wakeup_count(unsigned int *count)
+{
+	unsigned int cnt, inpr;
+
+	for (;;) {
+		split_counters(&cnt, &inpr);
+		if (inpr == 0 || signal_pending(current))
+			break;
+		pm_wakeup_update_hit_counts();
+		schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT));
+	}
+
+	split_counters(&cnt, &inpr);
+	*count = cnt;
+	return !inpr;
+}
+
+/**
+ * pm_save_wakeup_count - Save the current number of registered wakeup events.
+ * @count: Value to compare with the current number of registered wakeup events.
+ *
+ * If @count is equal to the current number of registered wakeup events and the
+ * current number of wakeup events being processed is zero, store @count as the
+ * old number of registered wakeup events for pm_check_wakeup_events(), enable
+ * wakeup events detection and return 'true'.  Otherwise disable wakeup events
+ * detection and return 'false'.
+ */
+bool pm_save_wakeup_count(unsigned int count)
+{
+	unsigned int cnt, inpr;
+
+	events_check_enabled = false;
+	spin_lock_irq(&events_lock);
+	split_counters(&cnt, &inpr);
+	if (cnt == count && inpr == 0) {
+		saved_count = count;
+		events_check_enabled = true;
+	}
+	spin_unlock_irq(&events_lock);
+	if (!events_check_enabled)
+		pm_wakeup_update_hit_counts();
+	return events_check_enabled;
+}
+
+static struct dentry *wakeup_sources_stats_dentry;
+
+/**
+ * print_wakeup_source_stats - Print wakeup source statistics information.
+ * @m: seq_file to print the statistics into.
+ * @ws: Wakeup source object to print the statistics for.
+ */
+static int print_wakeup_source_stats(struct seq_file *m,
+				     struct wakeup_source *ws)
+{
+	unsigned long flags;
+	ktime_t total_time;
+	ktime_t max_time;
+	unsigned long active_count;
+	ktime_t active_time;
+	int ret;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	total_time = ws->total_time;
+	max_time = ws->max_time;
+	active_count = ws->active_count;
+	if (ws->active) {
+		active_time = ktime_sub(ktime_get(), ws->last_time);
+		total_time = ktime_add(total_time, active_time);
+		if (active_time.tv64 > max_time.tv64)
+			max_time = active_time;
+	} else {
+		active_time = ktime_set(0, 0);
+	}
+
+	ret = seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t"
+			"%lld\t\t%lld\t\t%lld\t\t%lld\n",
+			ws->name, active_count, ws->event_count, ws->hit_count,
+			ktime_to_ms(active_time), ktime_to_ms(total_time),
+			ktime_to_ms(max_time), ktime_to_ms(ws->last_time));
+
+	spin_unlock_irqrestore(&ws->lock, flags);
+
+	return ret;
+}
+
+/**
+ * wakeup_sources_stats_show - Print wakeup sources statistics information.
+ * @m: seq_file to print the statistics into.
+ */
+static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
+{
+	struct wakeup_source *ws;
+
+	seq_puts(m, "name\t\tactive_count\tevent_count\thit_count\t"
+		"active_since\ttotal_time\tmax_time\tlast_change\n");
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
+		print_wakeup_source_stats(m, ws);
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int wakeup_sources_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wakeup_sources_stats_show, NULL);
+}
+
+static const struct file_operations wakeup_sources_stats_fops = {
+	.owner = THIS_MODULE,
+	.open = wakeup_sources_stats_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init wakeup_sources_debugfs_init(void)
+{
+	wakeup_sources_stats_dentry = debugfs_create_file("wakeup_sources",
+			S_IRUGO, NULL, NULL, &wakeup_sources_stats_fops);
+	return 0;
+}
+
+postcore_initcall(wakeup_sources_debugfs_init);