Initial import

14 files changed, 10580 insertions, 0 deletions

diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
new file mode 100644
index 000000000..1cb854459
--- /dev/null
+++ b/drivers/base/power/Makefile
@@ -0,0 +1,8 @@
+obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o runtime.o
+obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
+obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
+obj-$(CONFIG_PM_OPP)	+= opp.o
+obj-$(CONFIG_PM_GENERIC_DOMAINS)	+=  domain.o domain_governor.o
+obj-$(CONFIG_HAVE_CLK)	+= clock_ops.o
+
+ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
new file mode 100644
index 000000000..c7b0fcebf
--- /dev/null
+++ b/drivers/base/power/clock_ops.c
@@ -0,0 +1,470 @@
+/*
+ * 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/kernel.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/pm.h>
+#include <linux/pm_clock.h>
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+
+#ifdef CONFIG_PM
+
+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;
+};
+
+/**
+ * pm_clk_enable - Enable a clock, reporting any errors
+ * @dev: The device for the given clock
+ * @ce: PM clock entry corresponding to the clock.
+ */
+static inline int __pm_clk_enable(struct device *dev, struct pm_clock_entry *ce)
+{
+	int ret;
+
+	if (ce->status < PCE_STATUS_ERROR) {
+		ret = clk_enable(ce->clk);
+		if (!ret)
+			ce->status = PCE_STATUS_ENABLED;
+		else
+			dev_err(dev, "%s: failed to enable clk %p, error %d\n",
+				__func__, ce->clk, ret);
+	}
+
+	return ret;
+}
+
+/**
+ * pm_clk_acquire - Acquire a device clock.
+ * @dev: Device whose clock is to be acquired.
+ * @ce: PM clock entry corresponding to the clock.
+ */
+static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
+{
+	if (!ce->clk)
+		ce->clk = clk_get(dev, ce->con_id);
+	if (IS_ERR(ce->clk)) {
+		ce->status = PCE_STATUS_ERROR;
+	} else {
+		clk_prepare(ce->clk);
+		ce->status = PCE_STATUS_ACQUIRED;
+		dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
+	}
+}
+
+static int __pm_clk_add(struct device *dev, const char *con_id,
+			struct clk *clk)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!psd)
+		return -EINVAL;
+
+	ce = kzalloc(sizeof(*ce), GFP_KERNEL);
+	if (!ce)
+		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;
+		}
+	} else {
+		if (IS_ERR(clk) || !__clk_get(clk)) {
+			kfree(ce);
+			return -ENOENT;
+		}
+		ce->clk = clk;
+	}
+
+	pm_clk_acquire(dev, ce);
+
+	spin_lock_irq(&psd->lock);
+	list_add_tail(&ce->node, &psd->clock_list);
+	spin_unlock_irq(&psd->lock);
+	return 0;
+}
+
+/**
+ * pm_clk_add - Start using a device clock for power management.
+ * @dev: Device whose clock is going to be used for power management.
+ * @con_id: Connection ID of the clock.
+ *
+ * Add the clock represented by @con_id to the list of clocks used for
+ * the power management of @dev.
+ */
+int pm_clk_add(struct device *dev, const char *con_id)
+{
+	return __pm_clk_add(dev, con_id, NULL);
+}
+
+/**
+ * pm_clk_add_clk - Start using a device clock for power management.
+ * @dev: Device whose clock is going to be used for power management.
+ * @clk: Clock pointer
+ *
+ * Add the clock to the list of clocks used for the power management of @dev.
+ * It will increment refcount on clock pointer, use clk_put() on it when done.
+ */
+int pm_clk_add_clk(struct device *dev, struct clk *clk)
+{
+	return __pm_clk_add(dev, NULL, clk);
+}
+
+/**
+ * __pm_clk_remove - Destroy PM clock entry.
+ * @ce: PM clock entry to destroy.
+ */
+static void __pm_clk_remove(struct pm_clock_entry *ce)
+{
+	if (!ce)
+		return;
+
+	if (ce->status < PCE_STATUS_ERROR) {
+		if (ce->status == PCE_STATUS_ENABLED)
+			clk_disable(ce->clk);
+
+		if (ce->status >= PCE_STATUS_ACQUIRED) {
+			clk_unprepare(ce->clk);
+			clk_put(ce->clk);
+		}
+	}
+
+	kfree(ce->con_id);
+	kfree(ce);
+}
+
+/**
+ * pm_clk_remove - Stop using a device clock for power management.
+ * @dev: Device whose clock should not be used for 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 power management of @dev.
+ */
+void pm_clk_remove(struct device *dev, const char *con_id)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!psd)
+		return;
+
+	spin_lock_irq(&psd->lock);
+
+	list_for_each_entry(ce, &psd->clock_list, node) {
+		if (!con_id && !ce->con_id)
+			goto remove;
+		else if (!con_id || !ce->con_id)
+			continue;
+		else if (!strcmp(con_id, ce->con_id))
+			goto remove;
+	}
+
+	spin_unlock_irq(&psd->lock);
+	return;
+
+ remove:
+	list_del(&ce->node);
+	spin_unlock_irq(&psd->lock);
+
+	__pm_clk_remove(ce);
+}
+
+/**
+ * pm_clk_init - Initialize a device's list of power management clocks.
+ * @dev: Device to initialize the list of PM clocks for.
+ *
+ * Initialize the lock and clock_list members of the device's pm_subsys_data
+ * object.
+ */
+void pm_clk_init(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	if (psd)
+		INIT_LIST_HEAD(&psd->clock_list);
+}
+
+/**
+ * pm_clk_create - Create and initialize a device's list of PM clocks.
+ * @dev: Device to create and initialize the list of PM clocks for.
+ *
+ * Allocate a struct pm_subsys_data object, initialize its lock and clock_list
+ * members and make the @dev's power.subsys_data field point to it.
+ */
+int pm_clk_create(struct device *dev)
+{
+	return dev_pm_get_subsys_data(dev);
+}
+
+/**
+ * pm_clk_destroy - Destroy a device's list of power management clocks.
+ * @dev: Device to destroy the list of PM clocks for.
+ *
+ * Clear the @dev's power.subsys_data field, remove the list of clock entries
+ * from the struct pm_subsys_data object pointed to by it before and free
+ * that object.
+ */
+void pm_clk_destroy(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce, *c;
+	struct list_head list;
+
+	if (!psd)
+		return;
+
+	INIT_LIST_HEAD(&list);
+
+	spin_lock_irq(&psd->lock);
+
+	list_for_each_entry_safe_reverse(ce, c, &psd->clock_list, node)
+		list_move(&ce->node, &list);
+
+	spin_unlock_irq(&psd->lock);
+
+	dev_pm_put_subsys_data(dev);
+
+	list_for_each_entry_safe_reverse(ce, c, &list, node) {
+		list_del(&ce->node);
+		__pm_clk_remove(ce);
+	}
+}
+
+/**
+ * pm_clk_suspend - Disable clocks in a device's PM clock list.
+ * @dev: Device to disable the clocks for.
+ */
+int pm_clk_suspend(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+	unsigned long flags;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (!psd)
+		return 0;
+
+	spin_lock_irqsave(&psd->lock, flags);
+
+	list_for_each_entry_reverse(ce, &psd->clock_list, node) {
+		if (ce->status < PCE_STATUS_ERROR) {
+			if (ce->status == PCE_STATUS_ENABLED)
+				clk_disable(ce->clk);
+			ce->status = PCE_STATUS_ACQUIRED;
+		}
+	}
+
+	spin_unlock_irqrestore(&psd->lock, flags);
+
+	return 0;
+}
+
+/**
+ * pm_clk_resume - Enable clocks in a device's PM clock list.
+ * @dev: Device to enable the clocks for.
+ */
+int pm_clk_resume(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+	unsigned long flags;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (!psd)
+		return 0;
+
+	spin_lock_irqsave(&psd->lock, flags);
+
+	list_for_each_entry(ce, &psd->clock_list, node)
+		__pm_clk_enable(dev, ce);
+
+	spin_unlock_irqrestore(&psd->lock, flags);
+
+	return 0;
+}
+
+/**
+ * pm_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 pm_domain member of that object is copied to the device's
+ * pm_domain field and its con_ids member is used to populate the device's list
+ * of PM clocks, depending on @action.
+ *
+ * If the device's pm_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_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->pm_domain)
+			break;
+
+		error = pm_clk_create(dev);
+		if (error)
+			break;
+
+		dev->pm_domain = clknb->pm_domain;
+		if (clknb->con_ids[0]) {
+			for (con_id = clknb->con_ids; *con_id; con_id++)
+				pm_clk_add(dev, *con_id);
+		} else {
+			pm_clk_add(dev, NULL);
+		}
+
+		break;
+	case BUS_NOTIFY_DEL_DEVICE:
+		if (dev->pm_domain != clknb->pm_domain)
+			break;
+
+		dev->pm_domain = NULL;
+		pm_clk_destroy(dev);
+		break;
+	}
+
+	return 0;
+}
+
+#else /* !CONFIG_PM */
+
+/**
+ * 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_prepare_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_unprepare(clk);
+		clk_put(clk);
+		dev_info(dev, "Runtime PM disabled, clock forced off.\n");
+	}
+}
+
+/**
+ * pm_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_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 */
+
+/**
+ * pm_clk_add_notifier - Add bus type notifier for power management 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_clk_notify().  However,
+ * the remaining members of @clknb should be populated prior to calling this
+ * routine.
+ */
+void pm_clk_add_notifier(struct bus_type *bus,
+				 struct pm_clk_notifier_block *clknb)
+{
+	if (!bus || !clknb)
+		return;
+
+	clknb->nb.notifier_call = pm_clk_notify;
+	bus_register_notifier(bus, &clknb->nb);
+}
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
new file mode 100644
index 000000000..f32b802b9
--- /dev/null
+++ b/drivers/base/power/common.c
@@ -0,0 +1,130 @@
+/*
+ * drivers/base/power/common.c - Common device power management code.
+ *
+ * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/pm_clock.h>
+#include <linux/acpi.h>
+#include <linux/pm_domain.h>
+
+/**
+ * dev_pm_get_subsys_data - Create or refcount power.subsys_data for device.
+ * @dev: Device to handle.
+ *
+ * If power.subsys_data is NULL, point it to a new object, otherwise increment
+ * its reference counter.  Return 0 if new object has been created or refcount
+ * increased, otherwise negative error code.
+ */
+int dev_pm_get_subsys_data(struct device *dev)
+{
+	struct pm_subsys_data *psd;
+
+	psd = kzalloc(sizeof(*psd), GFP_KERNEL);
+	if (!psd)
+		return -ENOMEM;
+
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.subsys_data) {
+		dev->power.subsys_data->refcount++;
+	} else {
+		spin_lock_init(&psd->lock);
+		psd->refcount = 1;
+		dev->power.subsys_data = psd;
+		pm_clk_init(dev);
+		psd = NULL;
+	}
+
+	spin_unlock_irq(&dev->power.lock);
+
+	/* kfree() verifies that its argument is nonzero. */
+	kfree(psd);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_get_subsys_data);
+
+/**
+ * dev_pm_put_subsys_data - Drop reference to power.subsys_data.
+ * @dev: Device to handle.
+ *
+ * If the reference counter of power.subsys_data is zero after dropping the
+ * reference, power.subsys_data is removed.
+ */
+void dev_pm_put_subsys_data(struct device *dev)
+{
+	struct pm_subsys_data *psd;
+
+	spin_lock_irq(&dev->power.lock);
+
+	psd = dev_to_psd(dev);
+	if (!psd)
+		goto out;
+
+	if (--psd->refcount == 0)
+		dev->power.subsys_data = NULL;
+	else
+		psd = NULL;
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+	kfree(psd);
+}
+EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
+
+/**
+ * dev_pm_domain_attach - Attach a device to its PM domain.
+ * @dev: Device to attach.
+ * @power_on: Used to indicate whether we should power on the device.
+ *
+ * The @dev may only be attached to a single PM domain. By iterating through
+ * the available alternatives we try to find a valid PM domain for the device.
+ * As attachment succeeds, the ->detach() callback in the struct dev_pm_domain
+ * should be assigned by the corresponding attach function.
+ *
+ * This function should typically be invoked from subsystem level code during
+ * the probe phase. Especially for those that holds devices which requires
+ * power management through PM domains.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ *
+ * Returns 0 on successfully attached PM domain or negative error code.
+ */
+int dev_pm_domain_attach(struct device *dev, bool power_on)
+{
+	int ret;
+
+	ret = acpi_dev_pm_attach(dev, power_on);
+	if (ret)
+		ret = genpd_dev_pm_attach(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach);
+
+/**
+ * dev_pm_domain_detach - Detach a device from its PM domain.
+ * @dev: Device to attach.
+ * @power_off: Used to indicate whether we should power off the device.
+ *
+ * This functions will reverse the actions from dev_pm_domain_attach() and thus
+ * try to detach the @dev from its PM domain. Typically it should be invoked
+ * from subsystem level code during the remove phase.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ */
+void dev_pm_domain_detach(struct device *dev, bool power_off)
+{
+	if (dev->pm_domain && dev->pm_domain->detach)
+		dev->pm_domain->detach(dev, power_off);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_detach);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
new file mode 100644
index 000000000..2327613d4
--- /dev/null
+++ b/drivers/base/power/domain.c
@@ -0,0 +1,2381 @@
+/*
+ * drivers/base/power/domain.c - Common code related to device power domains.
+ *
+ * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_qos.h>
+#include <linux/pm_clock.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/suspend.h>
+#include <linux/export.h>
+
+#define GENPD_DEV_CALLBACK(genpd, type, callback, dev)		\
+({								\
+	type (*__routine)(struct device *__d); 			\
+	type __ret = (type)0;					\
+								\
+	__routine = genpd->dev_ops.callback; 			\
+	if (__routine) {					\
+		__ret = __routine(dev); 			\
+	}							\
+	__ret;							\
+})
+
+#define GENPD_DEV_TIMED_CALLBACK(genpd, type, callback, dev, field, name)	\
+({										\
+	ktime_t __start = ktime_get();						\
+	type __retval = GENPD_DEV_CALLBACK(genpd, type, callback, dev);		\
+	s64 __elapsed = ktime_to_ns(ktime_sub(ktime_get(), __start));		\
+	struct gpd_timing_data *__td = &dev_gpd_data(dev)->td;			\
+	if (!__retval && __elapsed > __td->field) {				\
+		__td->field = __elapsed;					\
+		dev_dbg(dev, name " latency exceeded, new value %lld ns\n",	\
+			__elapsed);						\
+		genpd->max_off_time_changed = true;				\
+		__td->constraint_changed = true;				\
+	}									\
+	__retval;								\
+})
+
+static LIST_HEAD(gpd_list);
+static DEFINE_MUTEX(gpd_list_lock);
+
+static struct generic_pm_domain *pm_genpd_lookup_name(const char *domain_name)
+{
+	struct generic_pm_domain *genpd = NULL, *gpd;
+
+	if (IS_ERR_OR_NULL(domain_name))
+		return NULL;
+
+	mutex_lock(&gpd_list_lock);
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+		if (!strcmp(gpd->name, domain_name)) {
+			genpd = gpd;
+			break;
+		}
+	}
+	mutex_unlock(&gpd_list_lock);
+	return genpd;
+}
+
+/*
+ * Get the generic PM domain for a particular struct device.
+ * This validates the struct device pointer, the PM domain pointer,
+ * and checks that the PM domain pointer is a real generic PM domain.
+ * Any failure results in NULL being returned.
+ */
+struct generic_pm_domain *pm_genpd_lookup_dev(struct device *dev)
+{
+	struct generic_pm_domain *genpd = NULL, *gpd;
+
+	if (IS_ERR_OR_NULL(dev) || IS_ERR_OR_NULL(dev->pm_domain))
+		return NULL;
+
+	mutex_lock(&gpd_list_lock);
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+		if (&gpd->domain == dev->pm_domain) {
+			genpd = gpd;
+			break;
+		}
+	}
+	mutex_unlock(&gpd_list_lock);
+
+	return genpd;
+}
+
+/*
+ * This should only be used where we are certain that the pm_domain
+ * attached to the device is a genpd domain.
+ */
+static struct generic_pm_domain *dev_to_genpd(struct device *dev)
+{
+	if (IS_ERR_OR_NULL(dev->pm_domain))
+		return ERR_PTR(-EINVAL);
+
+	return pd_to_genpd(dev->pm_domain);
+}
+
+static int genpd_stop_dev(struct generic_pm_domain *genpd, struct device *dev)
+{
+	return GENPD_DEV_TIMED_CALLBACK(genpd, int, stop, dev,
+					stop_latency_ns, "stop");
+}
+
+static int genpd_start_dev(struct generic_pm_domain *genpd, struct device *dev)
+{
+	return GENPD_DEV_TIMED_CALLBACK(genpd, int, start, dev,
+					start_latency_ns, "start");
+}
+
+static bool genpd_sd_counter_dec(struct generic_pm_domain *genpd)
+{
+	bool ret = false;
+
+	if (!WARN_ON(atomic_read(&genpd->sd_count) == 0))
+		ret = !!atomic_dec_and_test(&genpd->sd_count);
+
+	return ret;
+}
+
+static void genpd_sd_counter_inc(struct generic_pm_domain *genpd)
+{
+	atomic_inc(&genpd->sd_count);
+	smp_mb__after_atomic();
+}
+
+static void genpd_acquire_lock(struct generic_pm_domain *genpd)
+{
+	DEFINE_WAIT(wait);
+
+	mutex_lock(&genpd->lock);
+	/*
+	 * Wait for the domain to transition into either the active,
+	 * or the power off state.
+	 */
+	for (;;) {
+		prepare_to_wait(&genpd->status_wait_queue, &wait,
+				TASK_UNINTERRUPTIBLE);
+		if (genpd->status == GPD_STATE_ACTIVE
+		    || genpd->status == GPD_STATE_POWER_OFF)
+			break;
+		mutex_unlock(&genpd->lock);
+
+		schedule();
+
+		mutex_lock(&genpd->lock);
+	}
+	finish_wait(&genpd->status_wait_queue, &wait);
+}
+
+static void genpd_release_lock(struct generic_pm_domain *genpd)
+{
+	mutex_unlock(&genpd->lock);
+}
+
+static void genpd_set_active(struct generic_pm_domain *genpd)
+{
+	if (genpd->resume_count == 0)
+		genpd->status = GPD_STATE_ACTIVE;
+}
+
+static void genpd_recalc_cpu_exit_latency(struct generic_pm_domain *genpd)
+{
+	s64 usecs64;
+
+	if (!genpd->cpuidle_data)
+		return;
+
+	usecs64 = genpd->power_on_latency_ns;
+	do_div(usecs64, NSEC_PER_USEC);
+	usecs64 += genpd->cpuidle_data->saved_exit_latency;
+	genpd->cpuidle_data->idle_state->exit_latency = usecs64;
+}
+
+static int genpd_power_on(struct generic_pm_domain *genpd)
+{
+	ktime_t time_start;
+	s64 elapsed_ns;
+	int ret;
+
+	if (!genpd->power_on)
+		return 0;
+
+	time_start = ktime_get();
+	ret = genpd->power_on(genpd);
+	if (ret)
+		return ret;
+
+	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
+	if (elapsed_ns <= genpd->power_on_latency_ns)
+		return ret;
+
+	genpd->power_on_latency_ns = elapsed_ns;
+	genpd->max_off_time_changed = true;
+	genpd_recalc_cpu_exit_latency(genpd);
+	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
+		 genpd->name, "on", elapsed_ns);
+
+	return ret;
+}
+
+static int genpd_power_off(struct generic_pm_domain *genpd)
+{
+	ktime_t time_start;
+	s64 elapsed_ns;
+	int ret;
+
+	if (!genpd->power_off)
+		return 0;
+
+	time_start = ktime_get();
+	ret = genpd->power_off(genpd);
+	if (ret == -EBUSY)
+		return ret;
+
+	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
+	if (elapsed_ns <= genpd->power_off_latency_ns)
+		return ret;
+
+	genpd->power_off_latency_ns = elapsed_ns;
+	genpd->max_off_time_changed = true;
+	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
+		 genpd->name, "off", elapsed_ns);
+
+	return ret;
+}
+
+/**
+ * __pm_genpd_poweron - Restore power to a given PM domain and its masters.
+ * @genpd: PM domain to power up.
+ *
+ * Restore power to @genpd and all of its masters so that it is possible to
+ * resume a device belonging to it.
+ */
+static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
+	__releases(&genpd->lock) __acquires(&genpd->lock)
+{
+	struct gpd_link *link;
+	DEFINE_WAIT(wait);
+	int ret = 0;
+
+	/* If the domain's master is being waited for, we have to wait too. */
+	for (;;) {
+		prepare_to_wait(&genpd->status_wait_queue, &wait,
+				TASK_UNINTERRUPTIBLE);
+		if (genpd->status != GPD_STATE_WAIT_MASTER)
+			break;
+		mutex_unlock(&genpd->lock);
+
+		schedule();
+
+		mutex_lock(&genpd->lock);
+	}
+	finish_wait(&genpd->status_wait_queue, &wait);
+
+	if (genpd->status == GPD_STATE_ACTIVE
+	    || (genpd->prepared_count > 0 && genpd->suspend_power_off))
+		return 0;
+
+	if (genpd->status != GPD_STATE_POWER_OFF) {
+		genpd_set_active(genpd);
+		return 0;
+	}
+
+	if (genpd->cpuidle_data) {
+		cpuidle_pause_and_lock();
+		genpd->cpuidle_data->idle_state->disabled = true;
+		cpuidle_resume_and_unlock();
+		goto out;
+	}
+
+	/*
+	 * The list is guaranteed not to change while the loop below is being
+	 * executed, unless one of the masters' .power_on() callbacks fiddles
+	 * with it.
+	 */
+	list_for_each_entry(link, &genpd->slave_links, slave_node) {
+		genpd_sd_counter_inc(link->master);
+		genpd->status = GPD_STATE_WAIT_MASTER;
+
+		mutex_unlock(&genpd->lock);
+
+		ret = pm_genpd_poweron(link->master);
+
+		mutex_lock(&genpd->lock);
+
+		/*
+		 * The "wait for parent" status is guaranteed not to change
+		 * while the master is powering on.
+		 */
+		genpd->status = GPD_STATE_POWER_OFF;
+		wake_up_all(&genpd->status_wait_queue);
+		if (ret) {
+			genpd_sd_counter_dec(link->master);
+			goto err;
+		}
+	}
+
+	ret = genpd_power_on(genpd);
+	if (ret)
+		goto err;
+
+ out:
+	genpd_set_active(genpd);
+
+	return 0;
+
+ err:
+	list_for_each_entry_continue_reverse(link, &genpd->slave_links, slave_node)
+		genpd_sd_counter_dec(link->master);
+
+	return ret;
+}
+
+/**
+ * pm_genpd_poweron - Restore power to a given PM domain and its masters.
+ * @genpd: PM domain to power up.
+ */
+int pm_genpd_poweron(struct generic_pm_domain *genpd)
+{
+	int ret;
+
+	mutex_lock(&genpd->lock);
+	ret = __pm_genpd_poweron(genpd);
+	mutex_unlock(&genpd->lock);
+	return ret;
+}
+
+/**
+ * pm_genpd_name_poweron - Restore power to a given PM domain and its masters.
+ * @domain_name: Name of the PM domain to power up.
+ */
+int pm_genpd_name_poweron(const char *domain_name)
+{
+	struct generic_pm_domain *genpd;
+
+	genpd = pm_genpd_lookup_name(domain_name);
+	return genpd ? pm_genpd_poweron(genpd) : -EINVAL;
+}
+
+static int genpd_start_dev_no_timing(struct generic_pm_domain *genpd,
+				     struct device *dev)
+{
+	return GENPD_DEV_CALLBACK(genpd, int, start, dev);
+}
+
+static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev)
+{
+	return GENPD_DEV_TIMED_CALLBACK(genpd, int, save_state, dev,
+					save_state_latency_ns, "state save");
+}
+
+static int genpd_restore_dev(struct generic_pm_domain *genpd, struct device *dev)
+{
+	return GENPD_DEV_TIMED_CALLBACK(genpd, int, restore_state, dev,
+					restore_state_latency_ns,
+					"state restore");
+}
+
+static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
+				     unsigned long val, void *ptr)
+{
+	struct generic_pm_domain_data *gpd_data;
+	struct device *dev;
+
+	gpd_data = container_of(nb, struct generic_pm_domain_data, nb);
+	dev = gpd_data->base.dev;
+
+	for (;;) {
+		struct generic_pm_domain *genpd;
+		struct pm_domain_data *pdd;
+
+		spin_lock_irq(&dev->power.lock);
+
+		pdd = dev->power.subsys_data ?
+				dev->power.subsys_data->domain_data : NULL;
+		if (pdd && pdd->dev) {
+			to_gpd_data(pdd)->td.constraint_changed = true;
+			genpd = dev_to_genpd(dev);
+		} else {
+			genpd = ERR_PTR(-ENODATA);
+		}
+
+		spin_unlock_irq(&dev->power.lock);
+
+		if (!IS_ERR(genpd)) {
+			mutex_lock(&genpd->lock);
+			genpd->max_off_time_changed = true;
+			mutex_unlock(&genpd->lock);
+		}
+
+		dev = dev->parent;
+		if (!dev || dev->power.ignore_children)
+			break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+/**
+ * __pm_genpd_save_device - Save the pre-suspend state of a device.
+ * @pdd: Domain data of the device to save the state of.
+ * @genpd: PM domain the device belongs to.
+ */
+static int __pm_genpd_save_device(struct pm_domain_data *pdd,
+				  struct generic_pm_domain *genpd)
+	__releases(&genpd->lock) __acquires(&genpd->lock)
+{
+	struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd);
+	struct device *dev = pdd->dev;
+	int ret = 0;
+
+	if (gpd_data->need_restore > 0)
+		return 0;
+
+	/*
+	 * If the value of the need_restore flag is still unknown at this point,
+	 * we trust that pm_genpd_poweroff() has verified that the device is
+	 * already runtime PM suspended.
+	 */
+	if (gpd_data->need_restore < 0) {
+		gpd_data->need_restore = 1;
+		return 0;
+	}
+
+	mutex_unlock(&genpd->lock);
+
+	genpd_start_dev(genpd, dev);
+	ret = genpd_save_dev(genpd, dev);
+	genpd_stop_dev(genpd, dev);
+
+	mutex_lock(&genpd->lock);
+
+	if (!ret)
+		gpd_data->need_restore = 1;
+
+	return ret;
+}
+
+/**
+ * __pm_genpd_restore_device - Restore the pre-suspend state of a device.
+ * @pdd: Domain data of the device to restore the state of.
+ * @genpd: PM domain the device belongs to.
+ */
+static void __pm_genpd_restore_device(struct pm_domain_data *pdd,
+				      struct generic_pm_domain *genpd)
+	__releases(&genpd->lock) __acquires(&genpd->lock)
+{
+	struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd);
+	struct device *dev = pdd->dev;
+	int need_restore = gpd_data->need_restore;
+
+	gpd_data->need_restore = 0;
+	mutex_unlock(&genpd->lock);
+
+	genpd_start_dev(genpd, dev);
+
+	/*
+	 * Call genpd_restore_dev() for recently added devices too (need_restore
+	 * is negative then).
+	 */
+	if (need_restore)
+		genpd_restore_dev(genpd, dev);
+
+	mutex_lock(&genpd->lock);
+}
+
+/**
+ * genpd_abort_poweroff - Check if a PM domain power off should be aborted.
+ * @genpd: PM domain to check.
+ *
+ * Return true if a PM domain's status changed to GPD_STATE_ACTIVE during
+ * a "power off" operation, which means that a "power on" has occured in the
+ * meantime, or if its resume_count field is different from zero, which means
+ * that one of its devices has been resumed in the meantime.
+ */
+static bool genpd_abort_poweroff(struct generic_pm_domain *genpd)
+{
+	return genpd->status == GPD_STATE_WAIT_MASTER
+		|| genpd->status == GPD_STATE_ACTIVE || genpd->resume_count > 0;
+}
+
+/**
+ * genpd_queue_power_off_work - Queue up the execution of pm_genpd_poweroff().
+ * @genpd: PM domait to power off.
+ *
+ * Queue up the execution of pm_genpd_poweroff() unless it's already been done
+ * before.
+ */
+static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
+{
+	queue_work(pm_wq, &genpd->power_off_work);
+}
+
+/**
+ * pm_genpd_poweroff - Remove power from a given PM domain.
+ * @genpd: PM domain to power down.
+ *
+ * If all of the @genpd's devices have been suspended and all of its subdomains
+ * have been powered down, run the runtime suspend callbacks provided by all of
+ * the @genpd's devices' drivers and remove power from @genpd.
+ */
+static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
+	__releases(&genpd->lock) __acquires(&genpd->lock)
+{
+	struct pm_domain_data *pdd;
+	struct gpd_link *link;
+	unsigned int not_suspended;
+	int ret = 0;
+
+ start:
+	/*
+	 * Do not try to power off the domain in the following situations:
+	 * (1) The domain is already in the "power off" state.
+	 * (2) The domain is waiting for its master to power up.
+	 * (3) One of the domain's devices is being resumed right now.
+	 * (4) System suspend is in progress.
+	 */
+	if (genpd->status == GPD_STATE_POWER_OFF
+	    || genpd->status == GPD_STATE_WAIT_MASTER
+	    || genpd->resume_count > 0 || genpd->prepared_count > 0)
+		return 0;
+
+	if (atomic_read(&genpd->sd_count) > 0)
+		return -EBUSY;
+
+	not_suspended = 0;
+	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
+		enum pm_qos_flags_status stat;
+
+		stat = dev_pm_qos_flags(pdd->dev,
+					PM_QOS_FLAG_NO_POWER_OFF
+						| PM_QOS_FLAG_REMOTE_WAKEUP);
+		if (stat > PM_QOS_FLAGS_NONE)
+			return -EBUSY;
+
+		if (pdd->dev->driver && (!pm_runtime_suspended(pdd->dev)
+		    || pdd->dev->power.irq_safe))
+			not_suspended++;
+	}
+
+	if (not_suspended > genpd->in_progress)
+		return -EBUSY;
+
+	if (genpd->poweroff_task) {
+		/*
+		 * Another instance of pm_genpd_poweroff() is executing
+		 * callbacks, so tell it to start over and return.
+		 */
+		genpd->status = GPD_STATE_REPEAT;
+		return 0;
+	}
+
+	if (genpd->gov && genpd->gov->power_down_ok) {
+		if (!genpd->gov->power_down_ok(&genpd->domain))
+			return -EAGAIN;
+	}
+
+	genpd->status = GPD_STATE_BUSY;
+	genpd->poweroff_task = current;
+
+	list_for_each_entry_reverse(pdd, &genpd->dev_list, list_node) {
+		ret = atomic_read(&genpd->sd_count) == 0 ?
+			__pm_genpd_save_device(pdd, genpd) : -EBUSY;
+
+		if (genpd_abort_poweroff(genpd))
+			goto out;
+
+		if (ret) {
+			genpd_set_active(genpd);
+			goto out;
+		}
+
+		if (genpd->status == GPD_STATE_REPEAT) {
+			genpd->poweroff_task = NULL;
+			goto start;
+		}
+	}
+
+	if (genpd->cpuidle_data) {
+		/*
+		 * If cpuidle_data is set, cpuidle should turn the domain off
+		 * when the CPU in it is idle.  In that case we don't decrement
+		 * the subdomain counts of the master domains, so that power is
+		 * not removed from the current domain prematurely as a result
+		 * of cutting off the masters' power.
+		 */
+		genpd->status = GPD_STATE_POWER_OFF;
+		cpuidle_pause_and_lock();
+		genpd->cpuidle_data->idle_state->disabled = false;
+		cpuidle_resume_and_unlock();
+		goto out;
+	}
+
+	if (genpd->power_off) {
+		if (atomic_read(&genpd->sd_count) > 0) {
+			ret = -EBUSY;
+			goto out;
+		}
+
+		/*
+		 * If sd_count > 0 at this point, one of the subdomains hasn't
+		 * managed to call pm_genpd_poweron() for the master yet after
+		 * incrementing it.  In that case pm_genpd_poweron() will wait
+		 * for us to drop the lock, so we can call .power_off() and let
+		 * the pm_genpd_poweron() restore power for us (this shouldn't
+		 * happen very often).
+		 */
+		ret = genpd_power_off(genpd);
+		if (ret == -EBUSY) {
+			genpd_set_active(genpd);
+			goto out;
+		}
+	}
+
+	genpd->status = GPD_STATE_POWER_OFF;
+
+	list_for_each_entry(link, &genpd->slave_links, slave_node) {
+		genpd_sd_counter_dec(link->master);
+		genpd_queue_power_off_work(link->master);
+	}
+
+ out:
+	genpd->poweroff_task = NULL;
+	wake_up_all(&genpd->status_wait_queue);
+	return ret;
+}
+
+/**
+ * genpd_power_off_work_fn - Power off PM domain whose subdomain count is 0.
+ * @work: Work structure used for scheduling the execution of this function.
+ */
+static void genpd_power_off_work_fn(struct work_struct *work)
+{
+	struct generic_pm_domain *genpd;
+
+	genpd = container_of(work, struct generic_pm_domain, power_off_work);
+
+	genpd_acquire_lock(genpd);
+	pm_genpd_poweroff(genpd);
+	genpd_release_lock(genpd);
+}
+
+/**
+ * pm_genpd_runtime_suspend - Suspend a device belonging to I/O PM domain.
+ * @dev: Device to suspend.
+ *
+ * Carry out a runtime suspend of a device under the assumption that its
+ * pm_domain field points to the domain member of an object of type
+ * struct generic_pm_domain representing a PM domain consisting of I/O devices.
+ */
+static int pm_genpd_runtime_suspend(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+	struct generic_pm_domain_data *gpd_data;
+	bool (*stop_ok)(struct device *__dev);
+	int ret;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	stop_ok = genpd->gov ? genpd->gov->stop_ok : NULL;
+	if (stop_ok && !stop_ok(dev))
+		return -EBUSY;
+
+	ret = genpd_stop_dev(genpd, dev);
+	if (ret)
+		return ret;
+
+	/*
+	 * If power.irq_safe is set, this routine will be run with interrupts
+	 * off, so it can't use mutexes.
+	 */
+	if (dev->power.irq_safe)
+		return 0;
+
+	mutex_lock(&genpd->lock);
+
+	/*
+	 * If we have an unknown state of the need_restore flag, it means none
+	 * of the runtime PM callbacks has been invoked yet. Let's update the
+	 * flag to reflect that the current state is active.
+	 */
+	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
+	if (gpd_data->need_restore < 0)
+		gpd_data->need_restore = 0;
+
+	genpd->in_progress++;
+	pm_genpd_poweroff(genpd);
+	genpd->in_progress--;
+	mutex_unlock(&genpd->lock);
+
+	return 0;
+}
+
+/**
+ * pm_genpd_runtime_resume - Resume a device belonging to I/O PM domain.
+ * @dev: Device to resume.
+ *
+ * Carry out a runtime resume of a device under the assumption that its
+ * pm_domain field points to the domain member of an object of type
+ * struct generic_pm_domain representing a PM domain consisting of I/O devices.
+ */
+static int pm_genpd_runtime_resume(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+	DEFINE_WAIT(wait);
+	int ret;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	/* If power.irq_safe, the PM domain is never powered off. */
+	if (dev->power.irq_safe)
+		return genpd_start_dev_no_timing(genpd, dev);
+
+	mutex_lock(&genpd->lock);
+	ret = __pm_genpd_poweron(genpd);
+	if (ret) {
+		mutex_unlock(&genpd->lock);
+		return ret;
+	}
+	genpd->status = GPD_STATE_BUSY;
+	genpd->resume_count++;
+	for (;;) {
+		prepare_to_wait(&genpd->status_wait_queue, &wait,
+				TASK_UNINTERRUPTIBLE);
+		/*
+		 * If current is the powering off task, we have been called
+		 * reentrantly from one of the device callbacks, so we should
+		 * not wait.
+		 */
+		if (!genpd->poweroff_task || genpd->poweroff_task == current)
+			break;
+		mutex_unlock(&genpd->lock);
+
+		schedule();
+
+		mutex_lock(&genpd->lock);
+	}
+	finish_wait(&genpd->status_wait_queue, &wait);
+	__pm_genpd_restore_device(dev->power.subsys_data->domain_data, genpd);
+	genpd->resume_count--;
+	genpd_set_active(genpd);
+	wake_up_all(&genpd->status_wait_queue);
+	mutex_unlock(&genpd->lock);
+
+	return 0;
+}
+
+static bool pd_ignore_unused;
+static int __init pd_ignore_unused_setup(char *__unused)
+{
+	pd_ignore_unused = true;
+	return 1;
+}
+__setup("pd_ignore_unused", pd_ignore_unused_setup);
+
+/**
+ * pm_genpd_poweroff_unused - Power off all PM domains with no devices in use.
+ */
+void pm_genpd_poweroff_unused(void)
+{
+	struct generic_pm_domain *genpd;
+
+	if (pd_ignore_unused) {
+		pr_warn("genpd: Not disabling unused power domains\n");
+		return;
+	}
+
+	mutex_lock(&gpd_list_lock);
+
+	list_for_each_entry(genpd, &gpd_list, gpd_list_node)
+		genpd_queue_power_off_work(genpd);
+
+	mutex_unlock(&gpd_list_lock);
+}
+
+static int __init genpd_poweroff_unused(void)
+{
+	pm_genpd_poweroff_unused();
+	return 0;
+}
+late_initcall(genpd_poweroff_unused);
+
+#ifdef CONFIG_PM_SLEEP
+
+/**
+ * pm_genpd_present - Check if the given PM domain has been initialized.
+ * @genpd: PM domain to check.
+ */
+static bool pm_genpd_present(const struct generic_pm_domain *genpd)
+{
+	const struct generic_pm_domain *gpd;
+
+	if (IS_ERR_OR_NULL(genpd))
+		return false;
+
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node)
+		if (gpd == genpd)
+			return true;
+
+	return false;
+}
+
+static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd,
+				    struct device *dev)
+{
+	return GENPD_DEV_CALLBACK(genpd, bool, active_wakeup, dev);
+}
+
+/**
+ * pm_genpd_sync_poweroff - Synchronously power off a PM domain and its masters.
+ * @genpd: PM domain to power off, if possible.
+ *
+ * Check if the given PM domain can be powered off (during system suspend or
+ * hibernation) and do that if so.  Also, in that case propagate to its masters.
+ *
+ * This function is only called in "noirq" and "syscore" stages of system power
+ * transitions, so it need not acquire locks (all of the "noirq" callbacks are
+ * executed sequentially, so it is guaranteed that it will never run twice in
+ * parallel).
+ */
+static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd)
+{
+	struct gpd_link *link;
+
+	if (genpd->status == GPD_STATE_POWER_OFF)
+		return;
+
+	if (genpd->suspended_count != genpd->device_count
+	    || atomic_read(&genpd->sd_count) > 0)
+		return;
+
+	genpd_power_off(genpd);
+
+	genpd->status = GPD_STATE_POWER_OFF;
+
+	list_for_each_entry(link, &genpd->slave_links, slave_node) {
+		genpd_sd_counter_dec(link->master);
+		pm_genpd_sync_poweroff(link->master);
+	}
+}
+
+/**
+ * pm_genpd_sync_poweron - Synchronously power on a PM domain and its masters.
+ * @genpd: PM domain to power on.
+ *
+ * This function is only called in "noirq" and "syscore" stages of system power
+ * transitions, so it need not acquire locks (all of the "noirq" callbacks are
+ * executed sequentially, so it is guaranteed that it will never run twice in
+ * parallel).
+ */
+static void pm_genpd_sync_poweron(struct generic_pm_domain *genpd)
+{
+	struct gpd_link *link;
+
+	if (genpd->status != GPD_STATE_POWER_OFF)
+		return;
+
+	list_for_each_entry(link, &genpd->slave_links, slave_node) {
+		pm_genpd_sync_poweron(link->master);
+		genpd_sd_counter_inc(link->master);
+	}
+
+	genpd_power_on(genpd);
+
+	genpd->status = GPD_STATE_ACTIVE;
+}
+
+/**
+ * resume_needed - Check whether to resume a device before system suspend.
+ * @dev: Device to check.
+ * @genpd: PM domain the device belongs to.
+ *
+ * There are two cases in which a device that can wake up the system from sleep
+ * states should be resumed by pm_genpd_prepare(): (1) if the device is enabled
+ * to wake up the system and it has to remain active for this purpose while the
+ * system is in the sleep state and (2) if the device is not enabled to wake up
+ * the system from sleep states and it generally doesn't generate wakeup signals
+ * by itself (those signals are generated on its behalf by other parts of the
+ * system).  In the latter case it may be necessary to reconfigure the device's
+ * wakeup settings during system suspend, because it may have been set up to
+ * signal remote wakeup from the system's working state as needed by runtime PM.
+ * Return 'true' in either of the above cases.
+ */
+static bool resume_needed(struct device *dev, struct generic_pm_domain *genpd)
+{
+	bool active_wakeup;
+
+	if (!device_can_wakeup(dev))
+		return false;
+
+	active_wakeup = genpd_dev_active_wakeup(genpd, dev);
+	return device_may_wakeup(dev) ? active_wakeup : !active_wakeup;
+}
+
+/**
+ * pm_genpd_prepare - Start power transition of a device in a PM domain.
+ * @dev: Device to start the transition of.
+ *
+ * Start a power transition of a device (during a system-wide power transition)
+ * under the assumption that its pm_domain field points to the domain member of
+ * an object of type struct generic_pm_domain representing a PM domain
+ * consisting of I/O devices.
+ */
+static int pm_genpd_prepare(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+	int ret;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	/*
+	 * If a wakeup request is pending for the device, it should be woken up
+	 * at this point and a system wakeup event should be reported if it's
+	 * set up to wake up the system from sleep states.
+	 */
+	pm_runtime_get_noresume(dev);
+	if (pm_runtime_barrier(dev) && device_may_wakeup(dev))
+		pm_wakeup_event(dev, 0);
+
+	if (pm_wakeup_pending()) {
+		pm_runtime_put(dev);
+		return -EBUSY;
+	}
+
+	if (resume_needed(dev, genpd))
+		pm_runtime_resume(dev);
+
+	genpd_acquire_lock(genpd);
+
+	if (genpd->prepared_count++ == 0) {
+		genpd->suspended_count = 0;
+		genpd->suspend_power_off = genpd->status == GPD_STATE_POWER_OFF;
+	}
+
+	genpd_release_lock(genpd);
+
+	if (genpd->suspend_power_off) {
+		pm_runtime_put_noidle(dev);
+		return 0;
+	}
+
+	/*
+	 * The PM domain must be in the GPD_STATE_ACTIVE state at this point,
+	 * so pm_genpd_poweron() will return immediately, but if the device
+	 * is suspended (e.g. it's been stopped by genpd_stop_dev()), we need
+	 * to make it operational.
+	 */
+	pm_runtime_resume(dev);
+	__pm_runtime_disable(dev, false);
+
+	ret = pm_generic_prepare(dev);
+	if (ret) {
+		mutex_lock(&genpd->lock);
+
+		if (--genpd->prepared_count == 0)
+			genpd->suspend_power_off = false;
+
+		mutex_unlock(&genpd->lock);
+		pm_runtime_enable(dev);
+	}
+
+	pm_runtime_put(dev);
+	return ret;
+}
+
+/**
+ * pm_genpd_suspend - Suspend a device belonging to an I/O PM domain.
+ * @dev: Device to suspend.
+ *
+ * Suspend a device under the assumption that its pm_domain field points to the
+ * domain member of an object of type struct generic_pm_domain representing
+ * a PM domain consisting of I/O devices.
+ */
+static int pm_genpd_suspend(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : pm_generic_suspend(dev);
+}
+
+/**
+ * pm_genpd_suspend_late - Late suspend of a device from an I/O PM domain.
+ * @dev: Device to suspend.
+ *
+ * Carry out a late suspend of a device under the assumption that its
+ * pm_domain field points to the domain member of an object of type
+ * struct generic_pm_domain representing a PM domain consisting of I/O devices.
+ */
+static int pm_genpd_suspend_late(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : pm_generic_suspend_late(dev);
+}
+
+/**
+ * pm_genpd_suspend_noirq - Completion of suspend of device in an I/O PM domain.
+ * @dev: Device to suspend.
+ *
+ * Stop the device and remove power from the domain if all devices in it have
+ * been stopped.
+ */
+static int pm_genpd_suspend_noirq(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	if (genpd->suspend_power_off
+	    || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev)))
+		return 0;
+
+	genpd_stop_dev(genpd, dev);
+
+	/*
+	 * Since all of the "noirq" callbacks are executed sequentially, it is
+	 * guaranteed that this function will never run twice in parallel for
+	 * the same PM domain, so it is not necessary to use locking here.
+	 */
+	genpd->suspended_count++;
+	pm_genpd_sync_poweroff(genpd);
+
+	return 0;
+}
+
+/**
+ * pm_genpd_resume_noirq - Start of resume of device in an I/O PM domain.
+ * @dev: Device to resume.
+ *
+ * Restore power to the device's PM domain, if necessary, and start the device.
+ */
+static int pm_genpd_resume_noirq(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	if (genpd->suspend_power_off
+	    || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev)))
+		return 0;
+
+	/*
+	 * Since all of the "noirq" callbacks are executed sequentially, it is
+	 * guaranteed that this function will never run twice in parallel for
+	 * the same PM domain, so it is not necessary to use locking here.
+	 */
+	pm_genpd_sync_poweron(genpd);
+	genpd->suspended_count--;
+
+	return genpd_start_dev(genpd, dev);
+}
+
+/**
+ * pm_genpd_resume_early - Early resume of a device in an I/O PM domain.
+ * @dev: Device to resume.
+ *
+ * Carry out an early resume of a device under the assumption that its
+ * pm_domain field points to the domain member of an object of type
+ * struct generic_pm_domain representing a power domain consisting of I/O
+ * devices.
+ */
+static int pm_genpd_resume_early(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : pm_generic_resume_early(dev);
+}
+
+/**
+ * pm_genpd_resume - Resume of device in an I/O PM domain.
+ * @dev: Device to resume.
+ *
+ * Resume a device under the assumption that its pm_domain field points to the
+ * domain member of an object of type struct generic_pm_domain representing
+ * a power domain consisting of I/O devices.
+ */
+static int pm_genpd_resume(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : pm_generic_resume(dev);
+}
+
+/**
+ * pm_genpd_freeze - Freezing a device in an I/O PM domain.
+ * @dev: Device to freeze.
+ *
+ * Freeze a device under the assumption that its pm_domain field points to the
+ * domain member of an object of type struct generic_pm_domain representing
+ * a power domain consisting of I/O devices.
+ */
+static int pm_genpd_freeze(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : pm_generic_freeze(dev);
+}
+
+/**
+ * pm_genpd_freeze_late - Late freeze of a device in an I/O PM domain.
+ * @dev: Device to freeze.
+ *
+ * Carry out a late freeze of a device under the assumption that its
+ * pm_domain field points to the domain member of an object of type
+ * struct generic_pm_domain representing a power domain consisting of I/O
+ * devices.
+ */
+static int pm_genpd_freeze_late(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : pm_generic_freeze_late(dev);
+}
+
+/**
+ * pm_genpd_freeze_noirq - Completion of freezing a device in an I/O PM domain.
+ * @dev: Device to freeze.
+ *
+ * Carry out a late freeze of a device under the assumption that its
+ * pm_domain field points to the domain member of an object of type
+ * struct generic_pm_domain representing a power domain consisting of I/O
+ * devices.
+ */
+static int pm_genpd_freeze_noirq(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : genpd_stop_dev(genpd, dev);
+}
+
+/**
+ * pm_genpd_thaw_noirq - Early thaw of device in an I/O PM domain.
+ * @dev: Device to thaw.
+ *
+ * Start the device, unless power has been removed from the domain already
+ * before the system transition.
+ */
+static int pm_genpd_thaw_noirq(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : genpd_start_dev(genpd, dev);
+}
+
+/**
+ * pm_genpd_thaw_early - Early thaw of device in an I/O PM domain.
+ * @dev: Device to thaw.
+ *
+ * Carry out an early thaw of a device under the assumption that its
+ * pm_domain field points to the domain member of an object of type
+ * struct generic_pm_domain representing a power domain consisting of I/O
+ * devices.
+ */
+static int pm_genpd_thaw_early(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : pm_generic_thaw_early(dev);
+}
+
+/**
+ * pm_genpd_thaw - Thaw a device belonging to an I/O power domain.
+ * @dev: Device to thaw.
+ *
+ * Thaw a device under the assumption that its pm_domain field points to the
+ * domain member of an object of type struct generic_pm_domain representing
+ * a power domain consisting of I/O devices.
+ */
+static int pm_genpd_thaw(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : pm_generic_thaw(dev);
+}
+
+/**
+ * pm_genpd_restore_noirq - Start of restore of device in an I/O PM domain.
+ * @dev: Device to resume.
+ *
+ * Make sure the domain will be in the same power state as before the
+ * hibernation the system is resuming from and start the device if necessary.
+ */
+static int pm_genpd_restore_noirq(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	/*
+	 * Since all of the "noirq" callbacks are executed sequentially, it is
+	 * guaranteed that this function will never run twice in parallel for
+	 * the same PM domain, so it is not necessary to use locking here.
+	 *
+	 * At this point suspended_count == 0 means we are being run for the
+	 * first time for the given domain in the present cycle.
+	 */
+	if (genpd->suspended_count++ == 0) {
+		/*
+		 * The boot kernel might put the domain into arbitrary state,
+		 * so make it appear as powered off to pm_genpd_sync_poweron(),
+		 * so that it tries to power it on in case it was really off.
+		 */
+		genpd->status = GPD_STATE_POWER_OFF;
+		if (genpd->suspend_power_off) {
+			/*
+			 * If the domain was off before the hibernation, make
+			 * sure it will be off going forward.
+			 */
+			genpd_power_off(genpd);
+
+			return 0;
+		}
+	}
+
+	if (genpd->suspend_power_off)
+		return 0;
+
+	pm_genpd_sync_poweron(genpd);
+
+	return genpd_start_dev(genpd, dev);
+}
+
+/**
+ * pm_genpd_complete - Complete power transition of a device in a power domain.
+ * @dev: Device to complete the transition of.
+ *
+ * Complete a power transition of a device (during a system-wide power
+ * transition) under the assumption that its pm_domain field points to the
+ * domain member of an object of type struct generic_pm_domain representing
+ * a power domain consisting of I/O devices.
+ */
+static void pm_genpd_complete(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+	bool run_complete;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return;
+
+	mutex_lock(&genpd->lock);
+
+	run_complete = !genpd->suspend_power_off;
+	if (--genpd->prepared_count == 0)
+		genpd->suspend_power_off = false;
+
+	mutex_unlock(&genpd->lock);
+
+	if (run_complete) {
+		pm_generic_complete(dev);
+		pm_runtime_set_active(dev);
+		pm_runtime_enable(dev);
+		pm_request_idle(dev);
+	}
+}
+
+/**
+ * genpd_syscore_switch - Switch power during system core suspend or resume.
+ * @dev: Device that normally is marked as "always on" to switch power for.
+ *
+ * This routine may only be called during the system core (syscore) suspend or
+ * resume phase for devices whose "always on" flags are set.
+ */
+static void genpd_syscore_switch(struct device *dev, bool suspend)
+{
+	struct generic_pm_domain *genpd;
+
+	genpd = dev_to_genpd(dev);
+	if (!pm_genpd_present(genpd))
+		return;
+
+	if (suspend) {
+		genpd->suspended_count++;
+		pm_genpd_sync_poweroff(genpd);
+	} else {
+		pm_genpd_sync_poweron(genpd);
+		genpd->suspended_count--;
+	}
+}
+
+void pm_genpd_syscore_poweroff(struct device *dev)
+{
+	genpd_syscore_switch(dev, true);
+}
+EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweroff);
+
+void pm_genpd_syscore_poweron(struct device *dev)
+{
+	genpd_syscore_switch(dev, false);
+}
+EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
+
+#else /* !CONFIG_PM_SLEEP */
+
+#define pm_genpd_prepare		NULL
+#define pm_genpd_suspend		NULL
+#define pm_genpd_suspend_late		NULL
+#define pm_genpd_suspend_noirq		NULL
+#define pm_genpd_resume_early		NULL
+#define pm_genpd_resume_noirq		NULL
+#define pm_genpd_resume			NULL
+#define pm_genpd_freeze			NULL
+#define pm_genpd_freeze_late		NULL
+#define pm_genpd_freeze_noirq		NULL
+#define pm_genpd_thaw_early		NULL
+#define pm_genpd_thaw_noirq		NULL
+#define pm_genpd_thaw			NULL
+#define pm_genpd_restore_noirq		NULL
+#define pm_genpd_complete		NULL
+
+#endif /* CONFIG_PM_SLEEP */
+
+static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
+					struct generic_pm_domain *genpd,
+					struct gpd_timing_data *td)
+{
+	struct generic_pm_domain_data *gpd_data;
+	int ret;
+
+	ret = dev_pm_get_subsys_data(dev);
+	if (ret)
+		return ERR_PTR(ret);
+
+	gpd_data = kzalloc(sizeof(*gpd_data), GFP_KERNEL);
+	if (!gpd_data) {
+		ret = -ENOMEM;
+		goto err_put;
+	}
+
+	if (td)
+		gpd_data->td = *td;
+
+	gpd_data->base.dev = dev;
+	gpd_data->need_restore = -1;
+	gpd_data->td.constraint_changed = true;
+	gpd_data->td.effective_constraint_ns = -1;
+	gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier;
+
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.subsys_data->domain_data) {
+		ret = -EINVAL;
+		goto err_free;
+	}
+
+	dev->power.subsys_data->domain_data = &gpd_data->base;
+	dev->pm_domain = &genpd->domain;
+
+	spin_unlock_irq(&dev->power.lock);
+
+	return gpd_data;
+
+ err_free:
+	spin_unlock_irq(&dev->power.lock);
+	kfree(gpd_data);
+ err_put:
+	dev_pm_put_subsys_data(dev);
+	return ERR_PTR(ret);
+}
+
+static void genpd_free_dev_data(struct device *dev,
+				struct generic_pm_domain_data *gpd_data)
+{
+	spin_lock_irq(&dev->power.lock);
+
+	dev->pm_domain = NULL;
+	dev->power.subsys_data->domain_data = NULL;
+
+	spin_unlock_irq(&dev->power.lock);
+
+	kfree(gpd_data);
+	dev_pm_put_subsys_data(dev);
+}
+
+/**
+ * __pm_genpd_add_device - Add a device to an I/O PM domain.
+ * @genpd: PM domain to add the device to.
+ * @dev: Device to be added.
+ * @td: Set of PM QoS timing parameters to attach to the device.
+ */
+int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
+			  struct gpd_timing_data *td)
+{
+	struct generic_pm_domain_data *gpd_data;
+	int ret = 0;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
+		return -EINVAL;
+
+	gpd_data = genpd_alloc_dev_data(dev, genpd, td);
+	if (IS_ERR(gpd_data))
+		return PTR_ERR(gpd_data);
+
+	genpd_acquire_lock(genpd);
+
+	if (genpd->prepared_count > 0) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
+	ret = genpd->attach_dev ? genpd->attach_dev(genpd, dev) : 0;
+	if (ret)
+		goto out;
+
+	genpd->device_count++;
+	genpd->max_off_time_changed = true;
+
+	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
+
+ out:
+	genpd_release_lock(genpd);
+
+	if (ret)
+		genpd_free_dev_data(dev, gpd_data);
+	else
+		dev_pm_qos_add_notifier(dev, &gpd_data->nb);
+
+	return ret;
+}
+
+/**
+ * __pm_genpd_name_add_device - Find I/O PM domain and add a device to it.
+ * @domain_name: Name of the PM domain to add the device to.
+ * @dev: Device to be added.
+ * @td: Set of PM QoS timing parameters to attach to the device.
+ */
+int __pm_genpd_name_add_device(const char *domain_name, struct device *dev,
+			       struct gpd_timing_data *td)
+{
+	return __pm_genpd_add_device(pm_genpd_lookup_name(domain_name), dev, td);
+}
+
+/**
+ * pm_genpd_remove_device - Remove a device from an I/O PM domain.
+ * @genpd: PM domain to remove the device from.
+ * @dev: Device to be removed.
+ */
+int pm_genpd_remove_device(struct generic_pm_domain *genpd,
+			   struct device *dev)
+{
+	struct generic_pm_domain_data *gpd_data;
+	struct pm_domain_data *pdd;
+	int ret = 0;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (!genpd || genpd != pm_genpd_lookup_dev(dev))
+		return -EINVAL;
+
+	/* The above validation also means we have existing domain_data. */
+	pdd = dev->power.subsys_data->domain_data;
+	gpd_data = to_gpd_data(pdd);
+	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
+
+	genpd_acquire_lock(genpd);
+
+	if (genpd->prepared_count > 0) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
+	genpd->device_count--;
+	genpd->max_off_time_changed = true;
+
+	if (genpd->detach_dev)
+		genpd->detach_dev(genpd, dev);
+
+	list_del_init(&pdd->list_node);
+
+	genpd_release_lock(genpd);
+
+	genpd_free_dev_data(dev, gpd_data);
+
+	return 0;
+
+ out:
+	genpd_release_lock(genpd);
+	dev_pm_qos_add_notifier(dev, &gpd_data->nb);
+
+	return ret;
+}
+
+/**
+ * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain.
+ * @genpd: Master PM domain to add the subdomain to.
+ * @subdomain: Subdomain to be added.
+ */
+int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
+			   struct generic_pm_domain *subdomain)
+{
+	struct gpd_link *link;
+	int ret = 0;
+
+	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain)
+	    || genpd == subdomain)
+		return -EINVAL;
+
+ start:
+	genpd_acquire_lock(genpd);
+	mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
+
+	if (subdomain->status != GPD_STATE_POWER_OFF
+	    && subdomain->status != GPD_STATE_ACTIVE) {
+		mutex_unlock(&subdomain->lock);
+		genpd_release_lock(genpd);
+		goto start;
+	}
+
+	if (genpd->status == GPD_STATE_POWER_OFF
+	    &&  subdomain->status != GPD_STATE_POWER_OFF) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	list_for_each_entry(link, &genpd->master_links, master_node) {
+		if (link->slave == subdomain && link->master == genpd) {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	link = kzalloc(sizeof(*link), GFP_KERNEL);
+	if (!link) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	link->master = genpd;
+	list_add_tail(&link->master_node, &genpd->master_links);
+	link->slave = subdomain;
+	list_add_tail(&link->slave_node, &subdomain->slave_links);
+	if (subdomain->status != GPD_STATE_POWER_OFF)
+		genpd_sd_counter_inc(genpd);
+
+ out:
+	mutex_unlock(&subdomain->lock);
+	genpd_release_lock(genpd);
+
+	return ret;
+}
+
+/**
+ * pm_genpd_add_subdomain_names - Add a subdomain to an I/O PM domain.
+ * @master_name: Name of the master PM domain to add the subdomain to.
+ * @subdomain_name: Name of the subdomain to be added.
+ */
+int pm_genpd_add_subdomain_names(const char *master_name,
+				 const char *subdomain_name)
+{
+	struct generic_pm_domain *master = NULL, *subdomain = NULL, *gpd;
+
+	if (IS_ERR_OR_NULL(master_name) || IS_ERR_OR_NULL(subdomain_name))
+		return -EINVAL;
+
+	mutex_lock(&gpd_list_lock);
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+		if (!master && !strcmp(gpd->name, master_name))
+			master = gpd;
+
+		if (!subdomain && !strcmp(gpd->name, subdomain_name))
+			subdomain = gpd;
+
+		if (master && subdomain)
+			break;
+	}
+	mutex_unlock(&gpd_list_lock);
+
+	return pm_genpd_add_subdomain(master, subdomain);
+}
+
+/**
+ * pm_genpd_remove_subdomain - Remove a subdomain from an I/O PM domain.
+ * @genpd: Master PM domain to remove the subdomain from.
+ * @subdomain: Subdomain to be removed.
+ */
+int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
+			      struct generic_pm_domain *subdomain)
+{
+	struct gpd_link *link;
+	int ret = -EINVAL;
+
+	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain))
+		return -EINVAL;
+
+ start:
+	genpd_acquire_lock(genpd);
+
+	list_for_each_entry(link, &genpd->master_links, master_node) {
+		if (link->slave != subdomain)
+			continue;
+
+		mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
+
+		if (subdomain->status != GPD_STATE_POWER_OFF
+		    && subdomain->status != GPD_STATE_ACTIVE) {
+			mutex_unlock(&subdomain->lock);
+			genpd_release_lock(genpd);
+			goto start;
+		}
+
+		list_del(&link->master_node);
+		list_del(&link->slave_node);
+		kfree(link);
+		if (subdomain->status != GPD_STATE_POWER_OFF)
+			genpd_sd_counter_dec(genpd);
+
+		mutex_unlock(&subdomain->lock);
+
+		ret = 0;
+		break;
+	}
+
+	genpd_release_lock(genpd);
+
+	return ret;
+}
+
+/**
+ * pm_genpd_attach_cpuidle - Connect the given PM domain with cpuidle.
+ * @genpd: PM domain to be connected with cpuidle.
+ * @state: cpuidle state this domain can disable/enable.
+ *
+ * Make a PM domain behave as though it contained a CPU core, that is, instead
+ * of calling its power down routine it will enable the given cpuidle state so
+ * that the cpuidle subsystem can power it down (if possible and desirable).
+ */
+int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
+{
+	struct cpuidle_driver *cpuidle_drv;
+	struct gpd_cpuidle_data *cpuidle_data;
+	struct cpuidle_state *idle_state;
+	int ret = 0;
+
+	if (IS_ERR_OR_NULL(genpd) || state < 0)
+		return -EINVAL;
+
+	genpd_acquire_lock(genpd);
+
+	if (genpd->cpuidle_data) {
+		ret = -EEXIST;
+		goto out;
+	}
+	cpuidle_data = kzalloc(sizeof(*cpuidle_data), GFP_KERNEL);
+	if (!cpuidle_data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	cpuidle_drv = cpuidle_driver_ref();
+	if (!cpuidle_drv) {
+		ret = -ENODEV;
+		goto err_drv;
+	}
+	if (cpuidle_drv->state_count <= state) {
+		ret = -EINVAL;
+		goto err;
+	}
+	idle_state = &cpuidle_drv->states[state];
+	if (!idle_state->disabled) {
+		ret = -EAGAIN;
+		goto err;
+	}
+	cpuidle_data->idle_state = idle_state;
+	cpuidle_data->saved_exit_latency = idle_state->exit_latency;
+	genpd->cpuidle_data = cpuidle_data;
+	genpd_recalc_cpu_exit_latency(genpd);
+
+ out:
+	genpd_release_lock(genpd);
+	return ret;
+
+ err:
+	cpuidle_driver_unref();
+
+ err_drv:
+	kfree(cpuidle_data);
+	goto out;
+}
+
+/**
+ * pm_genpd_name_attach_cpuidle - Find PM domain and connect cpuidle to it.
+ * @name: Name of the domain to connect to cpuidle.
+ * @state: cpuidle state this domain can manipulate.
+ */
+int pm_genpd_name_attach_cpuidle(const char *name, int state)
+{
+	return pm_genpd_attach_cpuidle(pm_genpd_lookup_name(name), state);
+}
+
+/**
+ * pm_genpd_detach_cpuidle - Remove the cpuidle connection from a PM domain.
+ * @genpd: PM domain to remove the cpuidle connection from.
+ *
+ * Remove the cpuidle connection set up by pm_genpd_attach_cpuidle() from the
+ * given PM domain.
+ */
+int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd)
+{
+	struct gpd_cpuidle_data *cpuidle_data;
+	struct cpuidle_state *idle_state;
+	int ret = 0;
+
+	if (IS_ERR_OR_NULL(genpd))
+		return -EINVAL;
+
+	genpd_acquire_lock(genpd);
+
+	cpuidle_data = genpd->cpuidle_data;
+	if (!cpuidle_data) {
+		ret = -ENODEV;
+		goto out;
+	}
+	idle_state = cpuidle_data->idle_state;
+	if (!idle_state->disabled) {
+		ret = -EAGAIN;
+		goto out;
+	}
+	idle_state->exit_latency = cpuidle_data->saved_exit_latency;
+	cpuidle_driver_unref();
+	genpd->cpuidle_data = NULL;
+	kfree(cpuidle_data);
+
+ out:
+	genpd_release_lock(genpd);
+	return ret;
+}
+
+/**
+ * pm_genpd_name_detach_cpuidle - Find PM domain and disconnect cpuidle from it.
+ * @name: Name of the domain to disconnect cpuidle from.
+ */
+int pm_genpd_name_detach_cpuidle(const char *name)
+{
+	return pm_genpd_detach_cpuidle(pm_genpd_lookup_name(name));
+}
+
+/* Default device callbacks for generic PM domains. */
+
+/**
+ * pm_genpd_default_save_state - Default "save device state" for PM domains.
+ * @dev: Device to handle.
+ */
+static int pm_genpd_default_save_state(struct device *dev)
+{
+	int (*cb)(struct device *__dev);
+
+	if (dev->type && dev->type->pm)
+		cb = dev->type->pm->runtime_suspend;
+	else if (dev->class && dev->class->pm)
+		cb = dev->class->pm->runtime_suspend;
+	else if (dev->bus && dev->bus->pm)
+		cb = dev->bus->pm->runtime_suspend;
+	else
+		cb = NULL;
+
+	if (!cb && dev->driver && dev->driver->pm)
+		cb = dev->driver->pm->runtime_suspend;
+
+	return cb ? cb(dev) : 0;
+}
+
+/**
+ * pm_genpd_default_restore_state - Default PM domains "restore device state".
+ * @dev: Device to handle.
+ */
+static int pm_genpd_default_restore_state(struct device *dev)
+{
+	int (*cb)(struct device *__dev);
+
+	if (dev->type && dev->type->pm)
+		cb = dev->type->pm->runtime_resume;
+	else if (dev->class && dev->class->pm)
+		cb = dev->class->pm->runtime_resume;
+	else if (dev->bus && dev->bus->pm)
+		cb = dev->bus->pm->runtime_resume;
+	else
+		cb = NULL;
+
+	if (!cb && dev->driver && dev->driver->pm)
+		cb = dev->driver->pm->runtime_resume;
+
+	return cb ? cb(dev) : 0;
+}
+
+/**
+ * pm_genpd_init - Initialize a generic I/O PM domain object.
+ * @genpd: PM domain object to initialize.
+ * @gov: PM domain governor to associate with the domain (may be NULL).
+ * @is_off: Initial value of the domain's power_is_off field.
+ */
+void pm_genpd_init(struct generic_pm_domain *genpd,
+		   struct dev_power_governor *gov, bool is_off)
+{
+	if (IS_ERR_OR_NULL(genpd))
+		return;
+
+	INIT_LIST_HEAD(&genpd->master_links);
+	INIT_LIST_HEAD(&genpd->slave_links);
+	INIT_LIST_HEAD(&genpd->dev_list);
+	mutex_init(&genpd->lock);
+	genpd->gov = gov;
+	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
+	genpd->in_progress = 0;
+	atomic_set(&genpd->sd_count, 0);
+	genpd->status = is_off ? GPD_STATE_POWER_OFF : GPD_STATE_ACTIVE;
+	init_waitqueue_head(&genpd->status_wait_queue);
+	genpd->poweroff_task = NULL;
+	genpd->resume_count = 0;
+	genpd->device_count = 0;
+	genpd->max_off_time_ns = -1;
+	genpd->max_off_time_changed = true;
+	genpd->domain.ops.runtime_suspend = pm_genpd_runtime_suspend;
+	genpd->domain.ops.runtime_resume = pm_genpd_runtime_resume;
+	genpd->domain.ops.prepare = pm_genpd_prepare;
+	genpd->domain.ops.suspend = pm_genpd_suspend;
+	genpd->domain.ops.suspend_late = pm_genpd_suspend_late;
+	genpd->domain.ops.suspend_noirq = pm_genpd_suspend_noirq;
+	genpd->domain.ops.resume_noirq = pm_genpd_resume_noirq;
+	genpd->domain.ops.resume_early = pm_genpd_resume_early;
+	genpd->domain.ops.resume = pm_genpd_resume;
+	genpd->domain.ops.freeze = pm_genpd_freeze;
+	genpd->domain.ops.freeze_late = pm_genpd_freeze_late;
+	genpd->domain.ops.freeze_noirq = pm_genpd_freeze_noirq;
+	genpd->domain.ops.thaw_noirq = pm_genpd_thaw_noirq;
+	genpd->domain.ops.thaw_early = pm_genpd_thaw_early;
+	genpd->domain.ops.thaw = pm_genpd_thaw;
+	genpd->domain.ops.poweroff = pm_genpd_suspend;
+	genpd->domain.ops.poweroff_late = pm_genpd_suspend_late;
+	genpd->domain.ops.poweroff_noirq = pm_genpd_suspend_noirq;
+	genpd->domain.ops.restore_noirq = pm_genpd_restore_noirq;
+	genpd->domain.ops.restore_early = pm_genpd_resume_early;
+	genpd->domain.ops.restore = pm_genpd_resume;
+	genpd->domain.ops.complete = pm_genpd_complete;
+	genpd->dev_ops.save_state = pm_genpd_default_save_state;
+	genpd->dev_ops.restore_state = pm_genpd_default_restore_state;
+
+	if (genpd->flags & GENPD_FLAG_PM_CLK) {
+		genpd->dev_ops.stop = pm_clk_suspend;
+		genpd->dev_ops.start = pm_clk_resume;
+	}
+
+	mutex_lock(&gpd_list_lock);
+	list_add(&genpd->gpd_list_node, &gpd_list);
+	mutex_unlock(&gpd_list_lock);
+}
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+/*
+ * Device Tree based PM domain providers.
+ *
+ * The code below implements generic device tree based PM domain providers that
+ * bind device tree nodes with generic PM domains registered in the system.
+ *
+ * Any driver that registers generic PM domains and needs to support binding of
+ * devices to these domains is supposed to register a PM domain provider, which
+ * maps a PM domain specifier retrieved from the device tree to a PM domain.
+ *
+ * Two simple mapping functions have been provided for convenience:
+ *  - __of_genpd_xlate_simple() for 1:1 device tree node to PM domain mapping.
+ *  - __of_genpd_xlate_onecell() for mapping of multiple PM domains per node by
+ *    index.
+ */
+
+/**
+ * struct of_genpd_provider - PM domain provider registration structure
+ * @link: Entry in global list of PM domain providers
+ * @node: Pointer to device tree node of PM domain provider
+ * @xlate: Provider-specific xlate callback mapping a set of specifier cells
+ *         into a PM domain.
+ * @data: context pointer to be passed into @xlate callback
+ */
+struct of_genpd_provider {
+	struct list_head link;
+	struct device_node *node;
+	genpd_xlate_t xlate;
+	void *data;
+};
+
+/* List of registered PM domain providers. */
+static LIST_HEAD(of_genpd_providers);
+/* Mutex to protect the list above. */
+static DEFINE_MUTEX(of_genpd_mutex);
+
+/**
+ * __of_genpd_xlate_simple() - Xlate function for direct node-domain mapping
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct generic_pm_domain
+ *
+ * This is a generic xlate function that can be used to model PM domains that
+ * have their own device tree nodes. The private data of xlate function needs
+ * to be a valid pointer to struct generic_pm_domain.
+ */
+struct generic_pm_domain *__of_genpd_xlate_simple(
+					struct of_phandle_args *genpdspec,
+					void *data)
+{
+	if (genpdspec->args_count != 0)
+		return ERR_PTR(-EINVAL);
+	return data;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_simple);
+
+/**
+ * __of_genpd_xlate_onecell() - Xlate function using a single index.
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct genpd_onecell_data
+ *
+ * This is a generic xlate function that can be used to model simple PM domain
+ * controllers that have one device tree node and provide multiple PM domains.
+ * A single cell is used as an index into an array of PM domains specified in
+ * the genpd_onecell_data struct when registering the provider.
+ */
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+					struct of_phandle_args *genpdspec,
+					void *data)
+{
+	struct genpd_onecell_data *genpd_data = data;
+	unsigned int idx = genpdspec->args[0];
+
+	if (genpdspec->args_count != 1)
+		return ERR_PTR(-EINVAL);
+
+	if (idx >= genpd_data->num_domains) {
+		pr_err("%s: invalid domain index %u\n", __func__, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!genpd_data->domains[idx])
+		return ERR_PTR(-ENOENT);
+
+	return genpd_data->domains[idx];
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_onecell);
+
+/**
+ * __of_genpd_add_provider() - Register a PM domain provider for a node
+ * @np: Device node pointer associated with the PM domain provider.
+ * @xlate: Callback for decoding PM domain from phandle arguments.
+ * @data: Context pointer for @xlate callback.
+ */
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+			void *data)
+{
+	struct of_genpd_provider *cp;
+
+	cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+	if (!cp)
+		return -ENOMEM;
+
+	cp->node = of_node_get(np);
+	cp->data = data;
+	cp->xlate = xlate;
+
+	mutex_lock(&of_genpd_mutex);
+	list_add(&cp->link, &of_genpd_providers);
+	mutex_unlock(&of_genpd_mutex);
+	pr_debug("Added domain provider from %s\n", np->full_name);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_add_provider);
+
+/**
+ * of_genpd_del_provider() - Remove a previously registered PM domain provider
+ * @np: Device node pointer associated with the PM domain provider
+ */
+void of_genpd_del_provider(struct device_node *np)
+{
+	struct of_genpd_provider *cp;
+
+	mutex_lock(&of_genpd_mutex);
+	list_for_each_entry(cp, &of_genpd_providers, link) {
+		if (cp->node == np) {
+			list_del(&cp->link);
+			of_node_put(cp->node);
+			kfree(cp);
+			break;
+		}
+	}
+	mutex_unlock(&of_genpd_mutex);
+}
+EXPORT_SYMBOL_GPL(of_genpd_del_provider);
+
+/**
+ * of_genpd_get_from_provider() - Look-up PM domain
+ * @genpdspec: OF phandle args to use for look-up
+ *
+ * Looks for a PM domain provider under the node specified by @genpdspec and if
+ * found, uses xlate function of the provider to map phandle args to a PM
+ * domain.
+ *
+ * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR()
+ * on failure.
+ */
+struct generic_pm_domain *of_genpd_get_from_provider(
+					struct of_phandle_args *genpdspec)
+{
+	struct generic_pm_domain *genpd = ERR_PTR(-ENOENT);
+	struct of_genpd_provider *provider;
+
+	mutex_lock(&of_genpd_mutex);
+
+	/* Check if we have such a provider in our array */
+	list_for_each_entry(provider, &of_genpd_providers, link) {
+		if (provider->node == genpdspec->np)
+			genpd = provider->xlate(genpdspec, provider->data);
+		if (!IS_ERR(genpd))
+			break;
+	}
+
+	mutex_unlock(&of_genpd_mutex);
+
+	return genpd;
+}
+EXPORT_SYMBOL_GPL(of_genpd_get_from_provider);
+
+/**
+ * genpd_dev_pm_detach - Detach a device from its PM domain.
+ * @dev: Device to attach.
+ * @power_off: Currently not used
+ *
+ * Try to locate a corresponding generic PM domain, which the device was
+ * attached to previously. If such is found, the device is detached from it.
+ */
+static void genpd_dev_pm_detach(struct device *dev, bool power_off)
+{
+	struct generic_pm_domain *pd;
+	int ret = 0;
+
+	pd = pm_genpd_lookup_dev(dev);
+	if (!pd)
+		return;
+
+	dev_dbg(dev, "removing from PM domain %s\n", pd->name);
+
+	while (1) {
+		ret = pm_genpd_remove_device(pd, dev);
+		if (ret != -EAGAIN)
+			break;
+		cond_resched();
+	}
+
+	if (ret < 0) {
+		dev_err(dev, "failed to remove from PM domain %s: %d",
+			pd->name, ret);
+		return;
+	}
+
+	/* Check if PM domain can be powered off after removing this device. */
+	genpd_queue_power_off_work(pd);
+}
+
+static void genpd_dev_pm_sync(struct device *dev)
+{
+	struct generic_pm_domain *pd;
+
+	pd = dev_to_genpd(dev);
+	if (IS_ERR(pd))
+		return;
+
+	genpd_queue_power_off_work(pd);
+}
+
+/**
+ * genpd_dev_pm_attach - Attach a device to its PM domain using DT.
+ * @dev: Device to attach.
+ *
+ * Parse device's OF node to find a PM domain specifier. If such is found,
+ * attaches the device to retrieved pm_domain ops.
+ *
+ * Both generic and legacy Samsung-specific DT bindings are supported to keep
+ * backwards compatibility with existing DTBs.
+ *
+ * Returns 0 on successfully attached PM domain or negative error code.
+ */
+int genpd_dev_pm_attach(struct device *dev)
+{
+	struct of_phandle_args pd_args;
+	struct generic_pm_domain *pd;
+	int ret;
+
+	if (!dev->of_node)
+		return -ENODEV;
+
+	if (dev->pm_domain)
+		return -EEXIST;
+
+	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
+					"#power-domain-cells", 0, &pd_args);
+	if (ret < 0) {
+		if (ret != -ENOENT)
+			return ret;
+
+		/*
+		 * Try legacy Samsung-specific bindings
+		 * (for backwards compatibility of DT ABI)
+		 */
+		pd_args.args_count = 0;
+		pd_args.np = of_parse_phandle(dev->of_node,
+						"samsung,power-domain", 0);
+		if (!pd_args.np)
+			return -ENOENT;
+	}
+
+	pd = of_genpd_get_from_provider(&pd_args);
+	if (IS_ERR(pd)) {
+		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
+			__func__, PTR_ERR(pd));
+		of_node_put(dev->of_node);
+		return PTR_ERR(pd);
+	}
+
+	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
+
+	while (1) {
+		ret = pm_genpd_add_device(pd, dev);
+		if (ret != -EAGAIN)
+			break;
+		cond_resched();
+	}
+
+	if (ret < 0) {
+		dev_err(dev, "failed to add to PM domain %s: %d",
+			pd->name, ret);
+		of_node_put(dev->of_node);
+		return ret;
+	}
+
+	dev->pm_domain->detach = genpd_dev_pm_detach;
+	dev->pm_domain->sync = genpd_dev_pm_sync;
+	pm_genpd_poweron(pd);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
+#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
+
+
+/***        debugfs support        ***/
+
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+#include <linux/pm.h>
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/kobject.h>
+static struct dentry *pm_genpd_debugfs_dir;
+
+/*
+ * TODO: This function is a slightly modified version of rtpm_status_show
+ * from sysfs.c, so generalize it.
+ */
+static void rtpm_status_str(struct seq_file *s, struct device *dev)
+{
+	static const char * const status_lookup[] = {
+		[RPM_ACTIVE] = "active",
+		[RPM_RESUMING] = "resuming",
+		[RPM_SUSPENDED] = "suspended",
+		[RPM_SUSPENDING] = "suspending"
+	};
+	const char *p = "";
+
+	if (dev->power.runtime_error)
+		p = "error";
+	else if (dev->power.disable_depth)
+		p = "unsupported";
+	else if (dev->power.runtime_status < ARRAY_SIZE(status_lookup))
+		p = status_lookup[dev->power.runtime_status];
+	else
+		WARN_ON(1);
+
+	seq_puts(s, p);
+}
+
+static int pm_genpd_summary_one(struct seq_file *s,
+				struct generic_pm_domain *genpd)
+{
+	static const char * const status_lookup[] = {
+		[GPD_STATE_ACTIVE] = "on",
+		[GPD_STATE_WAIT_MASTER] = "wait-master",
+		[GPD_STATE_BUSY] = "busy",
+		[GPD_STATE_REPEAT] = "off-in-progress",
+		[GPD_STATE_POWER_OFF] = "off"
+	};
+	struct pm_domain_data *pm_data;
+	const char *kobj_path;
+	struct gpd_link *link;
+	int ret;
+
+	ret = mutex_lock_interruptible(&genpd->lock);
+	if (ret)
+		return -ERESTARTSYS;
+
+	if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup)))
+		goto exit;
+	seq_printf(s, "%-30s  %-15s  ", genpd->name, status_lookup[genpd->status]);
+
+	/*
+	 * Modifications on the list require holding locks on both
+	 * master and slave, so we are safe.
+	 * Also genpd->name is immutable.
+	 */
+	list_for_each_entry(link, &genpd->master_links, master_node) {
+		seq_printf(s, "%s", link->slave->name);
+		if (!list_is_last(&link->master_node, &genpd->master_links))
+			seq_puts(s, ", ");
+	}
+
+	list_for_each_entry(pm_data, &genpd->dev_list, list_node) {
+		kobj_path = kobject_get_path(&pm_data->dev->kobj, GFP_KERNEL);
+		if (kobj_path == NULL)
+			continue;
+
+		seq_printf(s, "\n    %-50s  ", kobj_path);
+		rtpm_status_str(s, pm_data->dev);
+		kfree(kobj_path);
+	}
+
+	seq_puts(s, "\n");
+exit:
+	mutex_unlock(&genpd->lock);
+
+	return 0;
+}
+
+static int pm_genpd_summary_show(struct seq_file *s, void *data)
+{
+	struct generic_pm_domain *genpd;
+	int ret = 0;
+
+	seq_puts(s, "    domain                      status         slaves\n");
+	seq_puts(s, "           /device                                      runtime status\n");
+	seq_puts(s, "----------------------------------------------------------------------\n");
+
+	ret = mutex_lock_interruptible(&gpd_list_lock);
+	if (ret)
+		return -ERESTARTSYS;
+
+	list_for_each_entry(genpd, &gpd_list, gpd_list_node) {
+		ret = pm_genpd_summary_one(s, genpd);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&gpd_list_lock);
+
+	return ret;
+}
+
+static int pm_genpd_summary_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, pm_genpd_summary_show, NULL);
+}
+
+static const struct file_operations pm_genpd_summary_fops = {
+	.open = pm_genpd_summary_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init pm_genpd_debug_init(void)
+{
+	struct dentry *d;
+
+	pm_genpd_debugfs_dir = debugfs_create_dir("pm_genpd", NULL);
+
+	if (!pm_genpd_debugfs_dir)
+		return -ENOMEM;
+
+	d = debugfs_create_file("pm_genpd_summary", S_IRUGO,
+			pm_genpd_debugfs_dir, NULL, &pm_genpd_summary_fops);
+	if (!d)
+		return -ENOMEM;
+
+	return 0;
+}
+late_initcall(pm_genpd_debug_init);
+
+static void __exit pm_genpd_debug_exit(void)
+{
+	debugfs_remove_recursive(pm_genpd_debugfs_dir);
+}
+__exitcall(pm_genpd_debug_exit);
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
new file mode 100644
index 000000000..2a4154a09
--- /dev/null
+++ b/drivers/base/power/domain_governor.c
@@ -0,0 +1,239 @@
+/*
+ * drivers/base/power/domain_governor.c - Governors for device PM domains.
+ *
+ * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_qos.h>
+#include <linux/hrtimer.h>
+
+static int dev_update_qos_constraint(struct device *dev, void *data)
+{
+	s64 *constraint_ns_p = data;
+	s32 constraint_ns = -1;
+
+	if (dev->power.subsys_data && dev->power.subsys_data->domain_data)
+		constraint_ns = dev_gpd_data(dev)->td.effective_constraint_ns;
+
+	if (constraint_ns < 0) {
+		constraint_ns = dev_pm_qos_read_value(dev);
+		constraint_ns *= NSEC_PER_USEC;
+	}
+	if (constraint_ns == 0)
+		return 0;
+
+	/*
+	 * constraint_ns cannot be negative here, because the device has been
+	 * suspended.
+	 */
+	if (constraint_ns < *constraint_ns_p || *constraint_ns_p == 0)
+		*constraint_ns_p = constraint_ns;
+
+	return 0;
+}
+
+/**
+ * default_stop_ok - Default PM domain governor routine for stopping devices.
+ * @dev: Device to check.
+ */
+static bool default_stop_ok(struct device *dev)
+{
+	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
+	unsigned long flags;
+	s64 constraint_ns;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	if (!td->constraint_changed) {
+		bool ret = td->cached_stop_ok;
+
+		spin_unlock_irqrestore(&dev->power.lock, flags);
+		return ret;
+	}
+	td->constraint_changed = false;
+	td->cached_stop_ok = false;
+	td->effective_constraint_ns = -1;
+	constraint_ns = __dev_pm_qos_read_value(dev);
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	if (constraint_ns < 0)
+		return false;
+
+	constraint_ns *= NSEC_PER_USEC;
+	/*
+	 * We can walk the children without any additional locking, because
+	 * they all have been suspended at this point and their
+	 * effective_constraint_ns fields won't be modified in parallel with us.
+	 */
+	if (!dev->power.ignore_children)
+		device_for_each_child(dev, &constraint_ns,
+				      dev_update_qos_constraint);
+
+	if (constraint_ns > 0) {
+		constraint_ns -= td->start_latency_ns;
+		if (constraint_ns == 0)
+			return false;
+	}
+	td->effective_constraint_ns = constraint_ns;
+	td->cached_stop_ok = constraint_ns > td->stop_latency_ns ||
+				constraint_ns == 0;
+	/*
+	 * The children have been suspended already, so we don't need to take
+	 * their stop latencies into account here.
+	 */
+	return td->cached_stop_ok;
+}
+
+/**
+ * default_power_down_ok - Default generic PM domain power off governor routine.
+ * @pd: PM domain to check.
+ *
+ * This routine must be executed under the PM domain's lock.
+ */
+static bool default_power_down_ok(struct dev_pm_domain *pd)
+{
+	struct generic_pm_domain *genpd = pd_to_genpd(pd);
+	struct gpd_link *link;
+	struct pm_domain_data *pdd;
+	s64 min_off_time_ns;
+	s64 off_on_time_ns;
+
+	if (genpd->max_off_time_changed) {
+		struct gpd_link *link;
+
+		/*
+		 * We have to invalidate the cached results for the masters, so
+		 * use the observation that default_power_down_ok() is not
+		 * going to be called for any master until this instance
+		 * returns.
+		 */
+		list_for_each_entry(link, &genpd->slave_links, slave_node)
+			link->master->max_off_time_changed = true;
+
+		genpd->max_off_time_changed = false;
+		genpd->cached_power_down_ok = false;
+		genpd->max_off_time_ns = -1;
+	} else {
+		return genpd->cached_power_down_ok;
+	}
+
+	off_on_time_ns = genpd->power_off_latency_ns +
+				genpd->power_on_latency_ns;
+	/*
+	 * It doesn't make sense to remove power from the domain if saving
+	 * the state of all devices in it and the power off/power on operations
+	 * take too much time.
+	 *
+	 * All devices in this domain have been stopped already at this point.
+	 */
+	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
+		if (pdd->dev->driver)
+			off_on_time_ns +=
+				to_gpd_data(pdd)->td.save_state_latency_ns;
+	}
+
+	min_off_time_ns = -1;
+	/*
+	 * Check if subdomains can be off for enough time.
+	 *
+	 * All subdomains have been powered off already at this point.
+	 */
+	list_for_each_entry(link, &genpd->master_links, master_node) {
+		struct generic_pm_domain *sd = link->slave;
+		s64 sd_max_off_ns = sd->max_off_time_ns;
+
+		if (sd_max_off_ns < 0)
+			continue;
+
+		/*
+		 * Check if the subdomain is allowed to be off long enough for
+		 * the current domain to turn off and on (that's how much time
+		 * it will have to wait worst case).
+		 */
+		if (sd_max_off_ns <= off_on_time_ns)
+			return false;
+
+		if (min_off_time_ns > sd_max_off_ns || min_off_time_ns < 0)
+			min_off_time_ns = sd_max_off_ns;
+	}
+
+	/*
+	 * Check if the devices in the domain can be off enough time.
+	 */
+	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
+		struct gpd_timing_data *td;
+		s64 constraint_ns;
+
+		if (!pdd->dev->driver)
+			continue;
+
+		/*
+		 * Check if the device is allowed to be off long enough for the
+		 * domain to turn off and on (that's how much time it will
+		 * have to wait worst case).
+		 */
+		td = &to_gpd_data(pdd)->td;
+		constraint_ns = td->effective_constraint_ns;
+		/* default_stop_ok() need not be called before us. */
+		if (constraint_ns < 0) {
+			constraint_ns = dev_pm_qos_read_value(pdd->dev);
+			constraint_ns *= NSEC_PER_USEC;
+		}
+		if (constraint_ns == 0)
+			continue;
+
+		/*
+		 * constraint_ns cannot be negative here, because the device has
+		 * been suspended.
+		 */
+		constraint_ns -= td->restore_state_latency_ns;
+		if (constraint_ns <= off_on_time_ns)
+			return false;
+
+		if (min_off_time_ns > constraint_ns || min_off_time_ns < 0)
+			min_off_time_ns = constraint_ns;
+	}
+
+	genpd->cached_power_down_ok = true;
+
+	/*
+	 * If the computed minimum device off time is negative, there are no
+	 * latency constraints, so the domain can spend arbitrary time in the
+	 * "off" state.
+	 */
+	if (min_off_time_ns < 0)
+		return true;
+
+	/*
+	 * The difference between the computed minimum subdomain or device off
+	 * time and the time needed to turn the domain on is the maximum
+	 * theoretical time this domain can spend in the "off" state.
+	 */
+	genpd->max_off_time_ns = min_off_time_ns - genpd->power_on_latency_ns;
+	return true;
+}
+
+static bool always_on_power_down_ok(struct dev_pm_domain *domain)
+{
+	return false;
+}
+
+struct dev_power_governor simple_qos_governor = {
+	.stop_ok = default_stop_ok,
+	.power_down_ok = default_power_down_ok,
+};
+
+/**
+ * pm_genpd_gov_always_on - A governor implementing an always-on policy
+ */
+struct dev_power_governor pm_domain_always_on_gov = {
+	.power_down_ok = always_on_power_down_ok,
+	.stop_ok = default_stop_ok,
+};
diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c
new file mode 100644
index 000000000..96a92db83
--- /dev/null
+++ b/drivers/base/power/generic_ops.c
@@ -0,0 +1,306 @@
+/*
+ * 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>
+#include <linux/export.h>
+
+#ifdef CONFIG_PM
+/**
+ * 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 */
+
+#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_suspend_noirq - Generic suspend_noirq callback for subsystems.
+ * @dev: Device to suspend.
+ */
+int pm_generic_suspend_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->suspend_noirq ? pm->suspend_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_suspend_noirq);
+
+/**
+ * pm_generic_suspend_late - Generic suspend_late callback for subsystems.
+ * @dev: Device to suspend.
+ */
+int pm_generic_suspend_late(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->suspend_late ? pm->suspend_late(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_suspend_late);
+
+/**
+ * pm_generic_suspend - Generic suspend callback for subsystems.
+ * @dev: Device to suspend.
+ */
+int pm_generic_suspend(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->suspend ? pm->suspend(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_suspend);
+
+/**
+ * pm_generic_freeze_noirq - Generic freeze_noirq callback for subsystems.
+ * @dev: Device to freeze.
+ */
+int pm_generic_freeze_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->freeze_noirq ? pm->freeze_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_freeze_noirq);
+
+/**
+ * pm_generic_freeze_late - Generic freeze_late callback for subsystems.
+ * @dev: Device to freeze.
+ */
+int pm_generic_freeze_late(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->freeze_late ? pm->freeze_late(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_freeze_late);
+
+/**
+ * pm_generic_freeze - Generic freeze callback for subsystems.
+ * @dev: Device to freeze.
+ */
+int pm_generic_freeze(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->freeze ? pm->freeze(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_freeze);
+
+/**
+ * pm_generic_poweroff_noirq - Generic poweroff_noirq callback for subsystems.
+ * @dev: Device to handle.
+ */
+int pm_generic_poweroff_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->poweroff_noirq ? pm->poweroff_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_poweroff_noirq);
+
+/**
+ * pm_generic_poweroff_late - Generic poweroff_late callback for subsystems.
+ * @dev: Device to handle.
+ */
+int pm_generic_poweroff_late(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->poweroff_late ? pm->poweroff_late(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_poweroff_late);
+
+/**
+ * pm_generic_poweroff - Generic poweroff callback for subsystems.
+ * @dev: Device to handle.
+ */
+int pm_generic_poweroff(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->poweroff ? pm->poweroff(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_poweroff);
+
+/**
+ * pm_generic_thaw_noirq - Generic thaw_noirq callback for subsystems.
+ * @dev: Device to thaw.
+ */
+int pm_generic_thaw_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->thaw_noirq ? pm->thaw_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_thaw_noirq);
+
+/**
+ * pm_generic_thaw_early - Generic thaw_early callback for subsystems.
+ * @dev: Device to thaw.
+ */
+int pm_generic_thaw_early(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->thaw_early ? pm->thaw_early(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_thaw_early);
+
+/**
+ * pm_generic_thaw - Generic thaw callback for subsystems.
+ * @dev: Device to thaw.
+ */
+int pm_generic_thaw(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->thaw ? pm->thaw(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_thaw);
+
+/**
+ * pm_generic_resume_noirq - Generic resume_noirq callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_resume_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->resume_noirq ? pm->resume_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_resume_noirq);
+
+/**
+ * pm_generic_resume_early - Generic resume_early callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_resume_early(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->resume_early ? pm->resume_early(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_resume_early);
+
+/**
+ * pm_generic_resume - Generic resume callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_resume(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->resume ? pm->resume(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_resume);
+
+/**
+ * pm_generic_restore_noirq - Generic restore_noirq callback for subsystems.
+ * @dev: Device to restore.
+ */
+int pm_generic_restore_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->restore_noirq ? pm->restore_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_restore_noirq);
+
+/**
+ * pm_generic_restore_early - Generic restore_early callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_restore_early(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->restore_early ? pm->restore_early(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_restore_early);
+
+/**
+ * pm_generic_restore - Generic restore callback for subsystems.
+ * @dev: Device to restore.
+ */
+int pm_generic_restore(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->restore ? pm->restore(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_restore);
+
+/**
+ * pm_generic_complete - Generic routine completing 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_request_idle(dev);
+}
+#endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
new file mode 100644
index 000000000..3d874eca7
--- /dev/null
+++ b/drivers/base/power/main.c
@@ -0,0 +1,1719 @@
+/*
+ * 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/export.h>
+#include <linux/mutex.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/pm-trace.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/async.h>
+#include <linux/suspend.h>
+#include <trace/events/power.h>
+#include <linux/cpufreq.h>
+#include <linux/cpuidle.h>
+#include <linux/timer.h>
+
+#include "../base.h"
+#include "power.h"
+
+typedef int (*pm_callback_t)(struct device *);
+
+/*
+ * 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);
+static LIST_HEAD(dpm_prepared_list);
+static LIST_HEAD(dpm_suspended_list);
+static LIST_HEAD(dpm_late_early_list);
+static LIST_HEAD(dpm_noirq_list);
+
+struct suspend_stats suspend_stats;
+static DEFINE_MUTEX(dpm_list_mtx);
+static pm_message_t pm_transition;
+
+static int async_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)";
+	}
+}
+
+/**
+ * device_pm_sleep_init - Initialize system suspend-related device fields.
+ * @dev: Device object being initialized.
+ */
+void device_pm_sleep_init(struct device *dev)
+{
+	dev->power.is_prepared = false;
+	dev->power.is_suspended = false;
+	dev->power.is_noirq_suspended = false;
+	dev->power.is_late_suspended = false;
+	init_completion(&dev->power.completion);
+	complete_all(&dev->power.completion);
+	dev->power.wakeup = NULL;
+	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 (pm_print_times_enabled) {
+		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();
+	}
+
+	return calltime;
+}
+
+static void initcall_debug_report(struct device *dev, ktime_t calltime,
+				  int error, pm_message_t state, char *info)
+{
+	ktime_t rettime;
+	s64 nsecs;
+
+	rettime = ktime_get();
+	nsecs = (s64) ktime_to_ns(ktime_sub(rettime, calltime));
+
+	if (pm_print_times_enabled) {
+		pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev),
+			error, (unsigned long long)nsecs >> 10);
+	}
+}
+
+/**
+ * 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 - Return the PM operation appropriate for given PM event.
+ * @ops: PM operations to choose from.
+ * @state: PM transition of the system being carried out.
+ */
+static pm_callback_t pm_op(const struct dev_pm_ops *ops, pm_message_t state)
+{
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		return ops->suspend;
+	case PM_EVENT_RESUME:
+		return ops->resume;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		return ops->freeze;
+	case PM_EVENT_HIBERNATE:
+		return ops->poweroff;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		return ops->thaw;
+		break;
+	case PM_EVENT_RESTORE:
+		return ops->restore;
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
+	}
+
+	return NULL;
+}
+
+/**
+ * pm_late_early_op - Return the PM operation appropriate for given PM event.
+ * @ops: PM operations to choose from.
+ * @state: PM transition of the system being carried out.
+ *
+ * Runtime PM is disabled for @dev while this function is being executed.
+ */
+static pm_callback_t pm_late_early_op(const struct dev_pm_ops *ops,
+				      pm_message_t state)
+{
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		return ops->suspend_late;
+	case PM_EVENT_RESUME:
+		return ops->resume_early;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		return ops->freeze_late;
+	case PM_EVENT_HIBERNATE:
+		return ops->poweroff_late;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		return ops->thaw_early;
+	case PM_EVENT_RESTORE:
+		return ops->restore_early;
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
+	}
+
+	return NULL;
+}
+
+/**
+ * pm_noirq_op - Return the PM operation appropriate for given PM event.
+ * @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 pm_callback_t pm_noirq_op(const struct dev_pm_ops *ops, pm_message_t state)
+{
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		return ops->suspend_noirq;
+	case PM_EVENT_RESUME:
+		return ops->resume_noirq;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		return ops->freeze_noirq;
+	case PM_EVENT_HIBERNATE:
+		return ops->poweroff_noirq;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		return ops->thaw_noirq;
+	case PM_EVENT_RESTORE:
+		return ops->restore_noirq;
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
+	}
+
+	return NULL;
+}
+
+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);
+}
+
+static int dpm_run_callback(pm_callback_t cb, struct device *dev,
+			    pm_message_t state, char *info)
+{
+	ktime_t calltime;
+	int error;
+
+	if (!cb)
+		return 0;
+
+	calltime = initcall_debug_start(dev);
+
+	pm_dev_dbg(dev, state, info);
+	trace_device_pm_callback_start(dev, info, state.event);
+	error = cb(dev);
+	trace_device_pm_callback_end(dev, error);
+	suspend_report_result(cb, error);
+
+	initcall_debug_report(dev, calltime, error, state, info);
+
+	return error;
+}
+
+#ifdef CONFIG_DPM_WATCHDOG
+struct dpm_watchdog {
+	struct device		*dev;
+	struct task_struct	*tsk;
+	struct timer_list	timer;
+};
+
+#define DECLARE_DPM_WATCHDOG_ON_STACK(wd) \
+	struct dpm_watchdog wd
+
+/**
+ * dpm_watchdog_handler - Driver suspend / resume watchdog handler.
+ * @data: Watchdog object address.
+ *
+ * Called when a driver has timed out suspending or resuming.
+ * There's not much we can do here to recover so panic() to
+ * capture a crash-dump in pstore.
+ */
+static void dpm_watchdog_handler(unsigned long data)
+{
+	struct dpm_watchdog *wd = (void *)data;
+
+	dev_emerg(wd->dev, "**** DPM device timeout ****\n");
+	show_stack(wd->tsk, NULL);
+	panic("%s %s: unrecoverable failure\n",
+		dev_driver_string(wd->dev), dev_name(wd->dev));
+}
+
+/**
+ * dpm_watchdog_set - Enable pm watchdog for given device.
+ * @wd: Watchdog. Must be allocated on the stack.
+ * @dev: Device to handle.
+ */
+static void dpm_watchdog_set(struct dpm_watchdog *wd, struct device *dev)
+{
+	struct timer_list *timer = &wd->timer;
+
+	wd->dev = dev;
+	wd->tsk = current;
+
+	init_timer_on_stack(timer);
+	/* use same timeout value for both suspend and resume */
+	timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_TIMEOUT;
+	timer->function = dpm_watchdog_handler;
+	timer->data = (unsigned long)wd;
+	add_timer(timer);
+}
+
+/**
+ * dpm_watchdog_clear - Disable suspend/resume watchdog.
+ * @wd: Watchdog to disable.
+ */
+static void dpm_watchdog_clear(struct dpm_watchdog *wd)
+{
+	struct timer_list *timer = &wd->timer;
+
+	del_timer_sync(timer);
+	destroy_timer_on_stack(timer);
+}
+#else
+#define DECLARE_DPM_WATCHDOG_ON_STACK(wd)
+#define dpm_watchdog_set(x, y)
+#define dpm_watchdog_clear(x)
+#endif
+
+/*------------------------- 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.
+ * @async: If true, the device is being resumed asynchronously.
+ *
+ * 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, bool async)
+{
+	pm_callback_t callback = NULL;
+	char *info = NULL;
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_RESUME(0);
+
+	if (dev->power.syscore || dev->power.direct_complete)
+		goto Out;
+
+	if (!dev->power.is_noirq_suspended)
+		goto Out;
+
+	dpm_wait(dev->parent, async);
+
+	if (dev->pm_domain) {
+		info = "noirq power domain ";
+		callback = pm_noirq_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "noirq type ";
+		callback = pm_noirq_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "noirq class ";
+		callback = pm_noirq_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "noirq bus ";
+		callback = pm_noirq_op(dev->bus->pm, state);
+	}
+
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "noirq driver ";
+		callback = pm_noirq_op(dev->driver->pm, state);
+	}
+
+	error = dpm_run_callback(callback, dev, state, info);
+	dev->power.is_noirq_suspended = false;
+
+ Out:
+	complete_all(&dev->power.completion);
+	TRACE_RESUME(error);
+	return error;
+}
+
+static bool is_async(struct device *dev)
+{
+	return dev->power.async_suspend && pm_async_enabled
+		&& !pm_trace_is_enabled();
+}
+
+static void async_resume_noirq(void *data, async_cookie_t cookie)
+{
+	struct device *dev = (struct device *)data;
+	int error;
+
+	error = device_resume_noirq(dev, pm_transition, true);
+	if (error)
+		pm_dev_err(dev, pm_transition, " async", error);
+
+	put_device(dev);
+}
+
+/**
+ * dpm_resume_noirq - Execute "noirq resume" callbacks for all devices.
+ * @state: PM transition of the system being carried out.
+ *
+ * Call the "noirq" resume handlers for all devices in dpm_noirq_list and
+ * enable device drivers to receive interrupts.
+ */
+void dpm_resume_noirq(pm_message_t state)
+{
+	struct device *dev;
+	ktime_t starttime = ktime_get();
+
+	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, true);
+	mutex_lock(&dpm_list_mtx);
+	pm_transition = state;
+
+	/*
+	 * Advanced the async threads upfront,
+	 * in case the starting of async threads is
+	 * delayed by non-async resuming devices.
+	 */
+	list_for_each_entry(dev, &dpm_noirq_list, power.entry) {
+		reinit_completion(&dev->power.completion);
+		if (is_async(dev)) {
+			get_device(dev);
+			async_schedule(async_resume_noirq, dev);
+		}
+	}
+
+	while (!list_empty(&dpm_noirq_list)) {
+		dev = to_device(dpm_noirq_list.next);
+		get_device(dev);
+		list_move_tail(&dev->power.entry, &dpm_late_early_list);
+		mutex_unlock(&dpm_list_mtx);
+
+		if (!is_async(dev)) {
+			int error;
+
+			error = device_resume_noirq(dev, state, false);
+			if (error) {
+				suspend_stats.failed_resume_noirq++;
+				dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
+				dpm_save_failed_dev(dev_name(dev));
+				pm_dev_err(dev, state, " noirq", error);
+			}
+		}
+
+		mutex_lock(&dpm_list_mtx);
+		put_device(dev);
+	}
+	mutex_unlock(&dpm_list_mtx);
+	async_synchronize_full();
+	dpm_show_time(starttime, state, "noirq");
+	resume_device_irqs();
+	cpuidle_resume();
+	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false);
+}
+
+/**
+ * device_resume_early - Execute an "early resume" callback 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.
+ *
+ * Runtime PM is disabled for @dev while this function is being executed.
+ */
+static int device_resume_early(struct device *dev, pm_message_t state, bool async)
+{
+	pm_callback_t callback = NULL;
+	char *info = NULL;
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_RESUME(0);
+
+	if (dev->power.syscore || dev->power.direct_complete)
+		goto Out;
+
+	if (!dev->power.is_late_suspended)
+		goto Out;
+
+	dpm_wait(dev->parent, async);
+
+	if (dev->pm_domain) {
+		info = "early power domain ";
+		callback = pm_late_early_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "early type ";
+		callback = pm_late_early_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "early class ";
+		callback = pm_late_early_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "early bus ";
+		callback = pm_late_early_op(dev->bus->pm, state);
+	}
+
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "early driver ";
+		callback = pm_late_early_op(dev->driver->pm, state);
+	}
+
+	error = dpm_run_callback(callback, dev, state, info);
+	dev->power.is_late_suspended = false;
+
+ Out:
+	TRACE_RESUME(error);
+
+	pm_runtime_enable(dev);
+	complete_all(&dev->power.completion);
+	return error;
+}
+
+static void async_resume_early(void *data, async_cookie_t cookie)
+{
+	struct device *dev = (struct device *)data;
+	int error;
+
+	error = device_resume_early(dev, pm_transition, true);
+	if (error)
+		pm_dev_err(dev, pm_transition, " async", error);
+
+	put_device(dev);
+}
+
+/**
+ * dpm_resume_early - Execute "early resume" callbacks for all devices.
+ * @state: PM transition of the system being carried out.
+ */
+void dpm_resume_early(pm_message_t state)
+{
+	struct device *dev;
+	ktime_t starttime = ktime_get();
+
+	trace_suspend_resume(TPS("dpm_resume_early"), state.event, true);
+	mutex_lock(&dpm_list_mtx);
+	pm_transition = state;
+
+	/*
+	 * Advanced the async threads upfront,
+	 * in case the starting of async threads is
+	 * delayed by non-async resuming devices.
+	 */
+	list_for_each_entry(dev, &dpm_late_early_list, power.entry) {
+		reinit_completion(&dev->power.completion);
+		if (is_async(dev)) {
+			get_device(dev);
+			async_schedule(async_resume_early, dev);
+		}
+	}
+
+	while (!list_empty(&dpm_late_early_list)) {
+		dev = to_device(dpm_late_early_list.next);
+		get_device(dev);
+		list_move_tail(&dev->power.entry, &dpm_suspended_list);
+		mutex_unlock(&dpm_list_mtx);
+
+		if (!is_async(dev)) {
+			int error;
+
+			error = device_resume_early(dev, state, false);
+			if (error) {
+				suspend_stats.failed_resume_early++;
+				dpm_save_failed_step(SUSPEND_RESUME_EARLY);
+				dpm_save_failed_dev(dev_name(dev));
+				pm_dev_err(dev, state, " early", error);
+			}
+		}
+		mutex_lock(&dpm_list_mtx);
+		put_device(dev);
+	}
+	mutex_unlock(&dpm_list_mtx);
+	async_synchronize_full();
+	dpm_show_time(starttime, state, "early");
+	trace_suspend_resume(TPS("dpm_resume_early"), state.event, false);
+}
+
+/**
+ * dpm_resume_start - Execute "noirq" and "early" device callbacks.
+ * @state: PM transition of the system being carried out.
+ */
+void dpm_resume_start(pm_message_t state)
+{
+	dpm_resume_noirq(state);
+	dpm_resume_early(state);
+}
+EXPORT_SYMBOL_GPL(dpm_resume_start);
+
+/**
+ * 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)
+{
+	pm_callback_t callback = NULL;
+	char *info = NULL;
+	int error = 0;
+	DECLARE_DPM_WATCHDOG_ON_STACK(wd);
+
+	TRACE_DEVICE(dev);
+	TRACE_RESUME(0);
+
+	if (dev->power.syscore)
+		goto Complete;
+
+	if (dev->power.direct_complete) {
+		/* Match the pm_runtime_disable() in __device_suspend(). */
+		pm_runtime_enable(dev);
+		goto Complete;
+	}
+
+	dpm_wait(dev->parent, async);
+	dpm_watchdog_set(&wd, dev);
+	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->pm_domain) {
+		info = "power domain ";
+		callback = pm_op(&dev->pm_domain->ops, state);
+		goto Driver;
+	}
+
+	if (dev->type && dev->type->pm) {
+		info = "type ";
+		callback = pm_op(dev->type->pm, state);
+		goto Driver;
+	}
+
+	if (dev->class) {
+		if (dev->class->pm) {
+			info = "class ";
+			callback = pm_op(dev->class->pm, state);
+			goto Driver;
+		} else if (dev->class->resume) {
+			info = "legacy class ";
+			callback = dev->class->resume;
+			goto End;
+		}
+	}
+
+	if (dev->bus) {
+		if (dev->bus->pm) {
+			info = "bus ";
+			callback = pm_op(dev->bus->pm, state);
+		} else if (dev->bus->resume) {
+			info = "legacy bus ";
+			callback = dev->bus->resume;
+			goto End;
+		}
+	}
+
+ Driver:
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "driver ";
+		callback = pm_op(dev->driver->pm, state);
+	}
+
+ End:
+	error = dpm_run_callback(callback, dev, state, info);
+	dev->power.is_suspended = false;
+
+ Unlock:
+	device_unlock(dev);
+	dpm_watchdog_clear(&wd);
+
+ Complete:
+	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);
+}
+
+/**
+ * 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();
+
+	trace_suspend_resume(TPS("dpm_resume"), state.event, true);
+	might_sleep();
+
+	mutex_lock(&dpm_list_mtx);
+	pm_transition = state;
+	async_error = 0;
+
+	list_for_each_entry(dev, &dpm_suspended_list, power.entry) {
+		reinit_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) {
+				suspend_stats.failed_resume++;
+				dpm_save_failed_step(SUSPEND_RESUME);
+				dpm_save_failed_dev(dev_name(dev));
+				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);
+
+	cpufreq_resume();
+	trace_suspend_resume(TPS("dpm_resume"), state.event, false);
+}
+
+/**
+ * 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)
+{
+	void (*callback)(struct device *) = NULL;
+	char *info = NULL;
+
+	if (dev->power.syscore)
+		return;
+
+	device_lock(dev);
+
+	if (dev->pm_domain) {
+		info = "completing power domain ";
+		callback = dev->pm_domain->ops.complete;
+	} else if (dev->type && dev->type->pm) {
+		info = "completing type ";
+		callback = dev->type->pm->complete;
+	} else if (dev->class && dev->class->pm) {
+		info = "completing class ";
+		callback = dev->class->pm->complete;
+	} else if (dev->bus && dev->bus->pm) {
+		info = "completing bus ";
+		callback = dev->bus->pm->complete;
+	}
+
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "completing driver ";
+		callback = dev->driver->pm->complete;
+	}
+
+	if (callback) {
+		pm_dev_dbg(dev, state, info);
+		trace_device_pm_callback_start(dev, info, state.event);
+		callback(dev);
+		trace_device_pm_callback_end(dev, 0);
+	}
+
+	device_unlock(dev);
+
+	pm_runtime_put(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;
+
+	trace_suspend_resume(TPS("dpm_complete"), state.event, true);
+	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);
+	trace_suspend_resume(TPS("dpm_complete"), state.event, false);
+}
+
+/**
+ * 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.
+ * @async: If true, the device is being suspended asynchronously.
+ *
+ * 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, bool async)
+{
+	pm_callback_t callback = NULL;
+	char *info = NULL;
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_SUSPEND(0);
+
+	if (async_error)
+		goto Complete;
+
+	if (pm_wakeup_pending()) {
+		async_error = -EBUSY;
+		goto Complete;
+	}
+
+	if (dev->power.syscore || dev->power.direct_complete)
+		goto Complete;
+
+	dpm_wait_for_children(dev, async);
+
+	if (dev->pm_domain) {
+		info = "noirq power domain ";
+		callback = pm_noirq_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "noirq type ";
+		callback = pm_noirq_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "noirq class ";
+		callback = pm_noirq_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "noirq bus ";
+		callback = pm_noirq_op(dev->bus->pm, state);
+	}
+
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "noirq driver ";
+		callback = pm_noirq_op(dev->driver->pm, state);
+	}
+
+	error = dpm_run_callback(callback, dev, state, info);
+	if (!error)
+		dev->power.is_noirq_suspended = true;
+	else
+		async_error = error;
+
+Complete:
+	complete_all(&dev->power.completion);
+	TRACE_SUSPEND(error);
+	return error;
+}
+
+static void async_suspend_noirq(void *data, async_cookie_t cookie)
+{
+	struct device *dev = (struct device *)data;
+	int error;
+
+	error = __device_suspend_noirq(dev, pm_transition, true);
+	if (error) {
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, pm_transition, " async", error);
+	}
+
+	put_device(dev);
+}
+
+static int device_suspend_noirq(struct device *dev)
+{
+	reinit_completion(&dev->power.completion);
+
+	if (is_async(dev)) {
+		get_device(dev);
+		async_schedule(async_suspend_noirq, dev);
+		return 0;
+	}
+	return __device_suspend_noirq(dev, pm_transition, false);
+}
+
+/**
+ * dpm_suspend_noirq - Execute "noirq suspend" callbacks for all 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;
+
+	trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true);
+	cpuidle_pause();
+	suspend_device_irqs();
+	mutex_lock(&dpm_list_mtx);
+	pm_transition = state;
+	async_error = 0;
+
+	while (!list_empty(&dpm_late_early_list)) {
+		struct device *dev = to_device(dpm_late_early_list.prev);
+
+		get_device(dev);
+		mutex_unlock(&dpm_list_mtx);
+
+		error = device_suspend_noirq(dev);
+
+		mutex_lock(&dpm_list_mtx);
+		if (error) {
+			pm_dev_err(dev, state, " noirq", error);
+			dpm_save_failed_dev(dev_name(dev));
+			put_device(dev);
+			break;
+		}
+		if (!list_empty(&dev->power.entry))
+			list_move(&dev->power.entry, &dpm_noirq_list);
+		put_device(dev);
+
+		if (async_error)
+			break;
+	}
+	mutex_unlock(&dpm_list_mtx);
+	async_synchronize_full();
+	if (!error)
+		error = async_error;
+
+	if (error) {
+		suspend_stats.failed_suspend_noirq++;
+		dpm_save_failed_step(SUSPEND_SUSPEND_NOIRQ);
+		dpm_resume_noirq(resume_event(state));
+	} else {
+		dpm_show_time(starttime, state, "noirq");
+	}
+	trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, false);
+	return error;
+}
+
+/**
+ * device_suspend_late - Execute a "late suspend" callback 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.
+ *
+ * Runtime PM is disabled for @dev while this function is being executed.
+ */
+static int __device_suspend_late(struct device *dev, pm_message_t state, bool async)
+{
+	pm_callback_t callback = NULL;
+	char *info = NULL;
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_SUSPEND(0);
+
+	__pm_runtime_disable(dev, false);
+
+	if (async_error)
+		goto Complete;
+
+	if (pm_wakeup_pending()) {
+		async_error = -EBUSY;
+		goto Complete;
+	}
+
+	if (dev->power.syscore || dev->power.direct_complete)
+		goto Complete;
+
+	dpm_wait_for_children(dev, async);
+
+	if (dev->pm_domain) {
+		info = "late power domain ";
+		callback = pm_late_early_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "late type ";
+		callback = pm_late_early_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "late class ";
+		callback = pm_late_early_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "late bus ";
+		callback = pm_late_early_op(dev->bus->pm, state);
+	}
+
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "late driver ";
+		callback = pm_late_early_op(dev->driver->pm, state);
+	}
+
+	error = dpm_run_callback(callback, dev, state, info);
+	if (!error)
+		dev->power.is_late_suspended = true;
+	else
+		async_error = error;
+
+Complete:
+	TRACE_SUSPEND(error);
+	complete_all(&dev->power.completion);
+	return error;
+}
+
+static void async_suspend_late(void *data, async_cookie_t cookie)
+{
+	struct device *dev = (struct device *)data;
+	int error;
+
+	error = __device_suspend_late(dev, pm_transition, true);
+	if (error) {
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, pm_transition, " async", error);
+	}
+	put_device(dev);
+}
+
+static int device_suspend_late(struct device *dev)
+{
+	reinit_completion(&dev->power.completion);
+
+	if (is_async(dev)) {
+		get_device(dev);
+		async_schedule(async_suspend_late, dev);
+		return 0;
+	}
+
+	return __device_suspend_late(dev, pm_transition, false);
+}
+
+/**
+ * dpm_suspend_late - Execute "late suspend" callbacks for all devices.
+ * @state: PM transition of the system being carried out.
+ */
+int dpm_suspend_late(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+	int error = 0;
+
+	trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true);
+	mutex_lock(&dpm_list_mtx);
+	pm_transition = state;
+	async_error = 0;
+
+	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_late(dev);
+
+		mutex_lock(&dpm_list_mtx);
+		if (error) {
+			pm_dev_err(dev, state, " late", error);
+			dpm_save_failed_dev(dev_name(dev));
+			put_device(dev);
+			break;
+		}
+		if (!list_empty(&dev->power.entry))
+			list_move(&dev->power.entry, &dpm_late_early_list);
+		put_device(dev);
+
+		if (async_error)
+			break;
+	}
+	mutex_unlock(&dpm_list_mtx);
+	async_synchronize_full();
+	if (!error)
+		error = async_error;
+	if (error) {
+		suspend_stats.failed_suspend_late++;
+		dpm_save_failed_step(SUSPEND_SUSPEND_LATE);
+		dpm_resume_early(resume_event(state));
+	} else {
+		dpm_show_time(starttime, state, "late");
+	}
+	trace_suspend_resume(TPS("dpm_suspend_late"), state.event, false);
+	return error;
+}
+
+/**
+ * dpm_suspend_end - Execute "late" and "noirq" device suspend callbacks.
+ * @state: PM transition of the system being carried out.
+ */
+int dpm_suspend_end(pm_message_t state)
+{
+	int error = dpm_suspend_late(state);
+	if (error)
+		return error;
+
+	error = dpm_suspend_noirq(state);
+	if (error) {
+		dpm_resume_early(resume_event(state));
+		return error;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dpm_suspend_end);
+
+/**
+ * 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.
+ * @info: string description of caller.
+ */
+static int legacy_suspend(struct device *dev, pm_message_t state,
+			  int (*cb)(struct device *dev, pm_message_t state),
+			  char *info)
+{
+	int error;
+	ktime_t calltime;
+
+	calltime = initcall_debug_start(dev);
+
+	trace_device_pm_callback_start(dev, info, state.event);
+	error = cb(dev, state);
+	trace_device_pm_callback_end(dev, error);
+	suspend_report_result(cb, error);
+
+	initcall_debug_report(dev, calltime, error, state, info);
+
+	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)
+{
+	pm_callback_t callback = NULL;
+	char *info = NULL;
+	int error = 0;
+	DECLARE_DPM_WATCHDOG_ON_STACK(wd);
+
+	TRACE_DEVICE(dev);
+	TRACE_SUSPEND(0);
+
+	dpm_wait_for_children(dev, async);
+
+	if (async_error)
+		goto Complete;
+
+	/*
+	 * If a device configured to wake up the system from sleep states
+	 * has been suspended at run time and there's a resume request pending
+	 * for it, this is equivalent to the device signaling wakeup, so the
+	 * system suspend operation should be aborted.
+	 */
+	if (pm_runtime_barrier(dev) && device_may_wakeup(dev))
+		pm_wakeup_event(dev, 0);
+
+	if (pm_wakeup_pending()) {
+		async_error = -EBUSY;
+		goto Complete;
+	}
+
+	if (dev->power.syscore)
+		goto Complete;
+
+	if (dev->power.direct_complete) {
+		if (pm_runtime_status_suspended(dev)) {
+			pm_runtime_disable(dev);
+			if (pm_runtime_suspended_if_enabled(dev))
+				goto Complete;
+
+			pm_runtime_enable(dev);
+		}
+		dev->power.direct_complete = false;
+	}
+
+	dpm_watchdog_set(&wd, dev);
+	device_lock(dev);
+
+	if (dev->pm_domain) {
+		info = "power domain ";
+		callback = pm_op(&dev->pm_domain->ops, state);
+		goto Run;
+	}
+
+	if (dev->type && dev->type->pm) {
+		info = "type ";
+		callback = pm_op(dev->type->pm, state);
+		goto Run;
+	}
+
+	if (dev->class) {
+		if (dev->class->pm) {
+			info = "class ";
+			callback = pm_op(dev->class->pm, state);
+			goto Run;
+		} else if (dev->class->suspend) {
+			pm_dev_dbg(dev, state, "legacy class ");
+			error = legacy_suspend(dev, state, dev->class->suspend,
+						"legacy class ");
+			goto End;
+		}
+	}
+
+	if (dev->bus) {
+		if (dev->bus->pm) {
+			info = "bus ";
+			callback = pm_op(dev->bus->pm, state);
+		} else if (dev->bus->suspend) {
+			pm_dev_dbg(dev, state, "legacy bus ");
+			error = legacy_suspend(dev, state, dev->bus->suspend,
+						"legacy bus ");
+			goto End;
+		}
+	}
+
+ Run:
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "driver ";
+		callback = pm_op(dev->driver->pm, state);
+	}
+
+	error = dpm_run_callback(callback, dev, state, info);
+
+ End:
+	if (!error) {
+		struct device *parent = dev->parent;
+
+		dev->power.is_suspended = true;
+		if (parent) {
+			spin_lock_irq(&parent->power.lock);
+
+			dev->parent->power.direct_complete = false;
+			if (dev->power.wakeup_path
+			    && !dev->parent->power.ignore_children)
+				dev->parent->power.wakeup_path = true;
+
+			spin_unlock_irq(&parent->power.lock);
+		}
+	}
+
+	device_unlock(dev);
+	dpm_watchdog_clear(&wd);
+
+ Complete:
+	complete_all(&dev->power.completion);
+	if (error)
+		async_error = error;
+
+	TRACE_SUSPEND(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) {
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, pm_transition, " async", error);
+	}
+
+	put_device(dev);
+}
+
+static int device_suspend(struct device *dev)
+{
+	reinit_completion(&dev->power.completion);
+
+	if (is_async(dev)) {
+		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;
+
+	trace_suspend_resume(TPS("dpm_suspend"), state.event, true);
+	might_sleep();
+
+	cpufreq_suspend();
+
+	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);
+			dpm_save_failed_dev(dev_name(dev));
+			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) {
+		suspend_stats.failed_suspend++;
+		dpm_save_failed_step(SUSPEND_SUSPEND);
+	} else
+		dpm_show_time(starttime, state, NULL);
+	trace_suspend_resume(TPS("dpm_suspend"), state.event, false);
+	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 (*callback)(struct device *) = NULL;
+	char *info = NULL;
+	int ret = 0;
+
+	if (dev->power.syscore)
+		return 0;
+
+	/*
+	 * If a device's parent goes into runtime suspend at the wrong time,
+	 * it won't be possible to resume the device.  To prevent this we
+	 * block runtime suspend here, during the prepare phase, and allow
+	 * it again during the complete phase.
+	 */
+	pm_runtime_get_noresume(dev);
+
+	device_lock(dev);
+
+	dev->power.wakeup_path = device_may_wakeup(dev);
+
+	if (dev->pm_domain) {
+		info = "preparing power domain ";
+		callback = dev->pm_domain->ops.prepare;
+	} else if (dev->type && dev->type->pm) {
+		info = "preparing type ";
+		callback = dev->type->pm->prepare;
+	} else if (dev->class && dev->class->pm) {
+		info = "preparing class ";
+		callback = dev->class->pm->prepare;
+	} else if (dev->bus && dev->bus->pm) {
+		info = "preparing bus ";
+		callback = dev->bus->pm->prepare;
+	}
+
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "preparing driver ";
+		callback = dev->driver->pm->prepare;
+	}
+
+	if (callback) {
+		trace_device_pm_callback_start(dev, info, state.event);
+		ret = callback(dev);
+		trace_device_pm_callback_end(dev, ret);
+	}
+
+	device_unlock(dev);
+
+	if (ret < 0) {
+		suspend_report_result(callback, ret);
+		pm_runtime_put(dev);
+		return ret;
+	}
+	/*
+	 * A positive return value from ->prepare() means "this device appears
+	 * to be runtime-suspended and its state is fine, so if it really is
+	 * runtime-suspended, you can leave it in that state provided that you
+	 * will do the same thing with all of its descendants".  This only
+	 * applies to suspend transitions, however.
+	 */
+	spin_lock_irq(&dev->power.lock);
+	dev->power.direct_complete = ret > 0 && state.event == PM_EVENT_SUSPEND;
+	spin_unlock_irq(&dev->power.lock);
+	return 0;
+}
+
+/**
+ * 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;
+
+	trace_suspend_resume(TPS("dpm_prepare"), state.event, true);
+	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);
+
+		error = 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);
+	trace_suspend_resume(TPS("dpm_prepare"), state.event, false);
+	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) {
+		suspend_stats.failed_prepare++;
+		dpm_save_failed_step(SUSPEND_PREPARE);
+	} else
+		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);
+
+/**
+ * dpm_for_each_dev - device iterator.
+ * @data: data for the callback.
+ * @fn: function to be called for each device.
+ *
+ * Iterate over devices in dpm_list, and call @fn for each device,
+ * passing it @data.
+ */
+void dpm_for_each_dev(void *data, void (*fn)(struct device *, void *))
+{
+	struct device *dev;
+
+	if (!fn)
+		return;
+
+	device_pm_lock();
+	list_for_each_entry(dev, &dpm_list, power.entry)
+		fn(dev, data);
+	device_pm_unlock();
+}
+EXPORT_SYMBOL_GPL(dpm_for_each_dev);
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
new file mode 100644
index 000000000..677fb2843
--- /dev/null
+++ b/drivers/base/power/opp.c
@@ -0,0 +1,927 @@
+/*
+ * 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/slab.h>
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/pm_opp.h>
+#include <linux/of.h>
+#include <linux/export.h>
+
+/*
+ * Internal data structure organization with the OPP layer library is as
+ * follows:
+ * dev_opp_list (root)
+ *	|- device 1 (represents voltage domain 1)
+ *	|	|- opp 1 (availability, freq, voltage)
+ *	|	|- opp 2 ..
+ *	...	...
+ *	|	`- opp n ..
+ *	|- device 2 (represents the next voltage domain)
+ *	...
+ *	`- device m (represents mth voltage domain)
+ * device 1, 2.. are represented by dev_opp structure while each opp
+ * is represented by the opp structure.
+ */
+
+/**
+ * struct dev_pm_opp - Generic OPP description structure
+ * @node:	opp list node. The nodes are maintained throughout the lifetime
+ *		of boot. It is expected only an optimal set of OPPs are
+ *		added to the library by the SoC framework.
+ *		RCU usage: opp list is traversed with RCU locks. node
+ *		modification is possible realtime, hence the modifications
+ *		are protected by the dev_opp_list_lock for integrity.
+ *		IMPORTANT: the opp nodes should be maintained in increasing
+ *		order.
+ * @dynamic:	not-created from static DT entries.
+ * @available:	true/false - marks if this OPP as available or not
+ * @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
+ * @rcu_head:	RCU callback head used for deferred freeing
+ *
+ * This structure stores the OPP information for a given device.
+ */
+struct dev_pm_opp {
+	struct list_head node;
+
+	bool available;
+	bool dynamic;
+	unsigned long rate;
+	unsigned long u_volt;
+
+	struct device_opp *dev_opp;
+	struct rcu_head rcu_head;
+};
+
+/**
+ * struct device_opp - Device opp structure
+ * @node:	list node - contains the devices with OPPs that
+ *		have been registered. Nodes once added are not modified in this
+ *		list.
+ *		RCU usage: nodes are not modified in the list of device_opp,
+ *		however addition is possible and is secured by dev_opp_list_lock
+ * @dev:	device pointer
+ * @srcu_head:	notifier head to notify the OPP availability changes.
+ * @rcu_head:	RCU callback head used for deferred freeing
+ * @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.
+ *
+ * Because the opp structures can be used from both rcu and srcu readers, we
+ * need to wait for the grace period of both of them before freeing any
+ * resources. And so we have used kfree_rcu() from within call_srcu() handlers.
+ */
+struct device_opp {
+	struct list_head node;
+
+	struct device *dev;
+	struct srcu_notifier_head srcu_head;
+	struct rcu_head rcu_head;
+	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);
+
+#define opp_rcu_lockdep_assert()					\
+do {									\
+	rcu_lockdep_assert(rcu_read_lock_held() ||			\
+				lockdep_is_held(&dev_opp_list_lock),	\
+			   "Missing rcu_read_lock() or "		\
+			   "dev_opp_list_lock protection");		\
+} while (0)
+
+/**
+ * _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.
+ *
+ * Return: 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;
+}
+
+/**
+ * dev_pm_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 dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
+{
+	struct dev_pm_opp *tmp_opp;
+	unsigned long v = 0;
+
+	opp_rcu_lockdep_assert();
+
+	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;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
+
+/**
+ * dev_pm_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 dev_pm_opp_get_freq(struct dev_pm_opp *opp)
+{
+	struct dev_pm_opp *tmp_opp;
+	unsigned long f = 0;
+
+	opp_rcu_lockdep_assert();
+
+	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;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
+
+/**
+ * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list
+ * @dev:	device for which we do this operation
+ *
+ * Return: 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 takes rcu_read_lock().
+ */
+int dev_pm_opp_get_opp_count(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *temp_opp;
+	int count = 0;
+
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		count = PTR_ERR(dev_opp);
+		dev_err(dev, "%s: device OPP not found (%d)\n",
+			__func__, count);
+		goto out_unlock;
+	}
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available)
+			count++;
+	}
+
+out_unlock:
+	rcu_read_unlock();
+	return count;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
+
+/**
+ * dev_pm_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
+ *
+ * Return: 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. Error return values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * 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 dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
+					      unsigned long freq,
+					      bool available)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	opp_rcu_lockdep_assert();
+
+	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;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
+
+/**
+ * dev_pm_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.
+ *
+ * Return: matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR. Error return
+ * values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * 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 dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
+					     unsigned long *freq)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	opp_rcu_lockdep_assert();
+
+	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 ERR_CAST(dev_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;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
+
+/**
+ * dev_pm_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.
+ *
+ * Return: matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR. Error return
+ * values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * 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 dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
+					      unsigned long *freq)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	opp_rcu_lockdep_assert();
+
+	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 ERR_CAST(dev_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;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
+
+/**
+ * _add_device_opp() - Allocate a new device OPP table
+ * @dev:	device for which we do this operation
+ *
+ * New device node which uses OPPs - used when multiple devices with OPP tables
+ * are maintained.
+ *
+ * Return: valid device_opp pointer if success, else NULL.
+ */
+static struct device_opp *_add_device_opp(struct device *dev)
+{
+	struct device_opp *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(*dev_opp), GFP_KERNEL);
+	if (!dev_opp)
+		return NULL;
+
+	dev_opp->dev = dev;
+	srcu_init_notifier_head(&dev_opp->srcu_head);
+	INIT_LIST_HEAD(&dev_opp->opp_list);
+
+	/* Secure the device list modification */
+	list_add_rcu(&dev_opp->node, &dev_opp_list);
+	return dev_opp;
+}
+
+/**
+ * _opp_add_dynamic() - Allocate a dynamic OPP.
+ * @dev:	device for which we do this operation
+ * @freq:	Frequency in Hz for this OPP
+ * @u_volt:	Voltage in uVolts for this OPP
+ * @dynamic:	Dynamically added OPPs.
+ *
+ * This function adds an opp definition to the opp list and returns status.
+ * The opp is made available by default and it can be controlled using
+ * dev_pm_opp_enable/disable functions and may be removed by dev_pm_opp_remove.
+ *
+ * NOTE: "dynamic" parameter impacts OPPs added by the of_init_opp_table and
+ * freed by of_free_opp_table.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ */
+static int _opp_add_dynamic(struct device *dev, unsigned long freq,
+			    long u_volt, bool dynamic)
+{
+	struct device_opp *dev_opp = NULL;
+	struct dev_pm_opp *opp, *new_opp;
+	struct list_head *head;
+	int ret;
+
+	/* allocate new OPP node */
+	new_opp = kzalloc(sizeof(*new_opp), GFP_KERNEL);
+	if (!new_opp)
+		return -ENOMEM;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* populate the opp table */
+	new_opp->rate = freq;
+	new_opp->u_volt = u_volt;
+	new_opp->available = true;
+	new_opp->dynamic = dynamic;
+
+	/* Check for existing list for 'dev' */
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		dev_opp = _add_device_opp(dev);
+		if (!dev_opp) {
+			ret = -ENOMEM;
+			goto free_opp;
+		}
+
+		head = &dev_opp->opp_list;
+		goto list_add;
+	}
+
+	/*
+	 * Insert new OPP in order of increasing frequency
+	 * and discard if already present
+	 */
+	head = &dev_opp->opp_list;
+	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
+		if (new_opp->rate <= opp->rate)
+			break;
+		else
+			head = &opp->node;
+	}
+
+	/* Duplicate OPPs ? */
+	if (new_opp->rate == opp->rate) {
+		ret = opp->available && new_opp->u_volt == opp->u_volt ?
+			0 : -EEXIST;
+
+		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
+			 __func__, opp->rate, opp->u_volt, opp->available,
+			 new_opp->rate, new_opp->u_volt, new_opp->available);
+		goto free_opp;
+	}
+
+list_add:
+	new_opp->dev_opp = dev_opp;
+	list_add_rcu(&new_opp->node, head);
+	mutex_unlock(&dev_opp_list_lock);
+
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
+	return 0;
+
+free_opp:
+	mutex_unlock(&dev_opp_list_lock);
+	kfree(new_opp);
+	return ret;
+}
+
+/**
+ * dev_pm_opp_add()  - Add an OPP table from a table definitions
+ * @dev:	device for which we do this operation
+ * @freq:	Frequency in Hz for this OPP
+ * @u_volt:	Voltage in uVolts for this OPP
+ *
+ * This function adds an opp definition to the opp list and returns status.
+ * The opp is made available by default and it can be controlled using
+ * dev_pm_opp_enable/disable functions.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ */
+int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+{
+	return _opp_add_dynamic(dev, freq, u_volt, true);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_add);
+
+/**
+ * _kfree_opp_rcu() - Free OPP RCU handler
+ * @head:	RCU head
+ */
+static void _kfree_opp_rcu(struct rcu_head *head)
+{
+	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
+
+	kfree_rcu(opp, rcu_head);
+}
+
+/**
+ * _kfree_device_rcu() - Free device_opp RCU handler
+ * @head:	RCU head
+ */
+static void _kfree_device_rcu(struct rcu_head *head)
+{
+	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+
+	kfree_rcu(device_opp, rcu_head);
+}
+
+/**
+ * _opp_remove()  - Remove an OPP from a table definition
+ * @dev_opp:	points back to the device_opp struct this opp belongs to
+ * @opp:	pointer to the OPP to remove
+ *
+ * This function removes an opp definition from the opp list.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * It is assumed that the caller holds required mutex for an RCU updater
+ * strategy.
+ */
+static void _opp_remove(struct device_opp *dev_opp,
+			struct dev_pm_opp *opp)
+{
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
+	list_del_rcu(&opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+
+	if (list_empty(&dev_opp->opp_list)) {
+		list_del_rcu(&dev_opp->node);
+		call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
+			  _kfree_device_rcu);
+	}
+}
+
+/**
+ * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * @dev:	device for which we do this operation
+ * @freq:	OPP to remove with matching 'freq'
+ *
+ * This function removes an opp from the opp list.
+ *
+ * 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.
+ */
+void dev_pm_opp_remove(struct device *dev, unsigned long freq)
+{
+	struct dev_pm_opp *opp;
+	struct device_opp *dev_opp;
+	bool found = false;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		goto unlock;
+
+	list_for_each_entry(opp, &dev_opp->opp_list, node) {
+		if (opp->rate == freq) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
+			 __func__, freq);
+		goto unlock;
+	}
+
+	_opp_remove(dev_opp, opp);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
+
+/**
+ * _opp_set_availability() - helper to set the availability of an opp
+ * @dev:		device for which we do this operation
+ * @freq:		OPP frequency to modify availability
+ * @availability_req:	availability status requested for this opp
+ *
+ * Set the availability of an OPP with an RCU operation, opp_{enable,disable}
+ * share a common logic which is isolated here.
+ *
+ * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
+ * copy operation, returns 0 if no modifcation was done OR modification was
+ * successful.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks to
+ * keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+static int _opp_set_availability(struct device *dev, unsigned long freq,
+				 bool availability_req)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
+	int r = 0;
+
+	/* keep the node allocated */
+	new_opp = kmalloc(sizeof(*new_opp), GFP_KERNEL);
+	if (!new_opp)
+		return -ENOMEM;
+
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Find the device_opp */
+	dev_opp = _find_device_opp(dev);
+	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);
+	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+
+	/* Notify the change of the OPP availability */
+	if (availability_req)
+		srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ENABLE,
+					 new_opp);
+	else
+		srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_DISABLE,
+					 new_opp);
+
+	return 0;
+
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+	kfree(new_opp);
+	return r;
+}
+
+/**
+ * dev_pm_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 dev_pm_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.
+ *
+ * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
+ * copy operation, returns 0 if no modifcation was done OR modification was
+ * successful.
+ */
+int dev_pm_opp_enable(struct device *dev, unsigned long freq)
+{
+	return _opp_set_availability(dev, freq, true);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_enable);
+
+/**
+ * dev_pm_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 dev_pm_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.
+ *
+ * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
+ * copy operation, returns 0 if no modifcation was done OR modification was
+ * successful.
+ */
+int dev_pm_opp_disable(struct device *dev, unsigned long freq)
+{
+	return _opp_set_availability(dev, freq, false);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_disable);
+
+/**
+ * dev_pm_opp_get_notifier() - find notifier_head of the device with opp
+ * @dev:	device pointer used to lookup device OPPs.
+ *
+ * Return: pointer to  notifier head if found, otherwise -ENODEV or
+ * -EINVAL based on type of error casted as pointer. value must be checked
+ *  with IS_ERR to determine valid pointer or error result.
+ *
+ * Locking: This function must be called under rcu_read_lock(). dev_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 srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev)
+{
+	struct device_opp *dev_opp = _find_device_opp(dev);
+
+	if (IS_ERR(dev_opp))
+		return ERR_CAST(dev_opp); /* matching type */
+
+	return &dev_opp->srcu_head;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
+
+#ifdef CONFIG_OF
+/**
+ * of_init_opp_table() - Initialize opp table from device tree
+ * @dev:	device pointer used to lookup device OPPs.
+ *
+ * Register the initial OPP table with the OPP library for given device.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function indirectly uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -ENODEV	when 'operating-points' property is not found or is invalid data
+ *		in device node.
+ * -ENODATA	when empty 'operating-points' property is found
+ */
+int of_init_opp_table(struct device *dev)
+{
+	const struct property *prop;
+	const __be32 *val;
+	int nr;
+
+	prop = of_find_property(dev->of_node, "operating-points", NULL);
+	if (!prop)
+		return -ENODEV;
+	if (!prop->value)
+		return -ENODATA;
+
+	/*
+	 * Each OPP is a set of tuples consisting of frequency and
+	 * voltage like <freq-kHz vol-uV>.
+	 */
+	nr = prop->length / sizeof(u32);
+	if (nr % 2) {
+		dev_err(dev, "%s: Invalid OPP list\n", __func__);
+		return -EINVAL;
+	}
+
+	val = prop->value;
+	while (nr) {
+		unsigned long freq = be32_to_cpup(val++) * 1000;
+		unsigned long volt = be32_to_cpup(val++);
+
+		if (_opp_add_dynamic(dev, freq, volt, false))
+			dev_warn(dev, "%s: Failed to add OPP %ld\n",
+				 __func__, freq);
+		nr -= 2;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_init_opp_table);
+
+/**
+ * of_free_opp_table() - Free OPP table entries created from static DT entries
+ * @dev:	device pointer used to lookup device OPPs.
+ *
+ * Free OPPs created using static entries present in DT.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function indirectly uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+void of_free_opp_table(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *opp, *tmp;
+
+	/* Check for existing list for 'dev' */
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int error = PTR_ERR(dev_opp);
+		if (error != -ENODEV)
+			WARN(1, "%s: dev_opp: %d\n",
+			     IS_ERR_OR_NULL(dev) ?
+					"Invalid device" : dev_name(dev),
+			     error);
+		return;
+	}
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Free static OPPs */
+	list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
+		if (!opp->dynamic)
+			_opp_remove(dev_opp, opp);
+	}
+
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(of_free_opp_table);
+#endif
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
new file mode 100644
index 000000000..b6b8a273c
--- /dev/null
+++ b/drivers/base/power/power.h
@@ -0,0 +1,101 @@
+#include <linux/pm_qos.h>
+
+static inline void device_pm_init_common(struct device *dev)
+{
+	if (!dev->power.early_init) {
+		spin_lock_init(&dev->power.lock);
+		dev->power.qos = NULL;
+		dev->power.early_init = true;
+	}
+}
+
+#ifdef CONFIG_PM
+
+static inline void pm_runtime_early_init(struct device *dev)
+{
+	dev->power.disable_depth = 1;
+	device_pm_init_common(dev);
+}
+
+extern void pm_runtime_init(struct device *dev);
+extern void pm_runtime_remove(struct device *dev);
+
+/*
+ * 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);
+extern int pm_qos_sysfs_add_resume_latency(struct device *dev);
+extern void pm_qos_sysfs_remove_resume_latency(struct device *dev);
+extern int pm_qos_sysfs_add_flags(struct device *dev);
+extern void pm_qos_sysfs_remove_flags(struct device *dev);
+
+#else /* CONFIG_PM */
+
+static inline void pm_runtime_early_init(struct device *dev)
+{
+	device_pm_init_common(dev);
+}
+
+static inline void pm_runtime_init(struct device *dev) {}
+static inline void pm_runtime_remove(struct device *dev) {}
+
+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) {}
+static inline int pm_qos_sysfs_add(struct device *dev) { return 0; }
+static inline void pm_qos_sysfs_remove(struct device *dev) {}
+
+#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_sleep_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_sleep_init(struct device *dev) {}
+
+static inline void device_pm_add(struct device *dev) {}
+
+static inline void device_pm_remove(struct device *dev)
+{
+	pm_runtime_remove(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 */
+
+static inline void device_pm_init(struct device *dev)
+{
+	device_pm_init_common(dev);
+	device_pm_sleep_init(dev);
+	pm_runtime_init(dev);
+}
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
new file mode 100644
index 000000000..e56d538d0
--- /dev/null
+++ b/drivers/base/power/qos.c
@@ -0,0 +1,885 @@
+/*
+ * Devices PM QoS constraints management
+ *
+ * Copyright (C) 2011 Texas Instruments, Inc.
+ *
+ * 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.
+ *
+ *
+ * This module exposes the interface to kernel space for specifying
+ * per-device PM QoS dependencies. It provides infrastructure for registration
+ * of:
+ *
+ * Dependents on a QoS value : register requests
+ * Watchers of QoS value : get notified when target QoS value changes
+ *
+ * This QoS design is best effort based. Dependents register their QoS needs.
+ * Watchers register to keep track of the current QoS needs of the system.
+ * Watchers can register different types of notification callbacks:
+ *  . a per-device notification callback using the dev_pm_qos_*_notifier API.
+ *    The notification chain data is stored in the per-device constraint
+ *    data struct.
+ *  . a system-wide notification callback using the dev_pm_qos_*_global_notifier
+ *    API. The notification chain data is stored in a static variable.
+ *
+ * Note about the per-device constraint data struct allocation:
+ * . The per-device constraints data struct ptr is tored into the device
+ *    dev_pm_info.
+ * . To minimize the data usage by the per-device constraints, the data struct
+ *   is only allocated at the first call to dev_pm_qos_add_request.
+ * . The data is later free'd when the device is removed from the system.
+ *  . A global mutex protects the constraints users from the data being
+ *     allocated and free'd.
+ */
+
+#include <linux/pm_qos.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/export.h>
+#include <linux/pm_runtime.h>
+#include <linux/err.h>
+#include <trace/events/power.h>
+
+#include "power.h"
+
+static DEFINE_MUTEX(dev_pm_qos_mtx);
+static DEFINE_MUTEX(dev_pm_qos_sysfs_mtx);
+
+static BLOCKING_NOTIFIER_HEAD(dev_pm_notifiers);
+
+/**
+ * __dev_pm_qos_flags - Check PM QoS flags for a given device.
+ * @dev: Device to check the PM QoS flags for.
+ * @mask: Flags to check against.
+ *
+ * This routine must be called with dev->power.lock held.
+ */
+enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask)
+{
+	struct dev_pm_qos *qos = dev->power.qos;
+	struct pm_qos_flags *pqf;
+	s32 val;
+
+	lockdep_assert_held(&dev->power.lock);
+
+	if (IS_ERR_OR_NULL(qos))
+		return PM_QOS_FLAGS_UNDEFINED;
+
+	pqf = &qos->flags;
+	if (list_empty(&pqf->list))
+		return PM_QOS_FLAGS_UNDEFINED;
+
+	val = pqf->effective_flags & mask;
+	if (val)
+		return (val == mask) ? PM_QOS_FLAGS_ALL : PM_QOS_FLAGS_SOME;
+
+	return PM_QOS_FLAGS_NONE;
+}
+
+/**
+ * dev_pm_qos_flags - Check PM QoS flags for a given device (locked).
+ * @dev: Device to check the PM QoS flags for.
+ * @mask: Flags to check against.
+ */
+enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask)
+{
+	unsigned long irqflags;
+	enum pm_qos_flags_status ret;
+
+	spin_lock_irqsave(&dev->power.lock, irqflags);
+	ret = __dev_pm_qos_flags(dev, mask);
+	spin_unlock_irqrestore(&dev->power.lock, irqflags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_flags);
+
+/**
+ * __dev_pm_qos_read_value - Get PM QoS constraint for a given device.
+ * @dev: Device to get the PM QoS constraint value for.
+ *
+ * This routine must be called with dev->power.lock held.
+ */
+s32 __dev_pm_qos_read_value(struct device *dev)
+{
+	lockdep_assert_held(&dev->power.lock);
+
+	return IS_ERR_OR_NULL(dev->power.qos) ?
+		0 : pm_qos_read_value(&dev->power.qos->resume_latency);
+}
+
+/**
+ * dev_pm_qos_read_value - Get PM QoS constraint for a given device (locked).
+ * @dev: Device to get the PM QoS constraint value for.
+ */
+s32 dev_pm_qos_read_value(struct device *dev)
+{
+	unsigned long flags;
+	s32 ret;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	ret = __dev_pm_qos_read_value(dev);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return ret;
+}
+
+/**
+ * apply_constraint - Add/modify/remove device PM QoS request.
+ * @req: Constraint request to apply
+ * @action: Action to perform (add/update/remove).
+ * @value: Value to assign to the QoS request.
+ *
+ * Internal function to update the constraints list using the PM QoS core
+ * code and if needed call the per-device and the global notification
+ * callbacks
+ */
+static int apply_constraint(struct dev_pm_qos_request *req,
+			    enum pm_qos_req_action action, s32 value)
+{
+	struct dev_pm_qos *qos = req->dev->power.qos;
+	int ret;
+
+	switch(req->type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		ret = pm_qos_update_target(&qos->resume_latency,
+					   &req->data.pnode, action, value);
+		if (ret) {
+			value = pm_qos_read_value(&qos->resume_latency);
+			blocking_notifier_call_chain(&dev_pm_notifiers,
+						     (unsigned long)value,
+						     req);
+		}
+		break;
+	case DEV_PM_QOS_LATENCY_TOLERANCE:
+		ret = pm_qos_update_target(&qos->latency_tolerance,
+					   &req->data.pnode, action, value);
+		if (ret) {
+			value = pm_qos_read_value(&qos->latency_tolerance);
+			req->dev->power.set_latency_tolerance(req->dev, value);
+		}
+		break;
+	case DEV_PM_QOS_FLAGS:
+		ret = pm_qos_update_flags(&qos->flags, &req->data.flr,
+					  action, value);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+/*
+ * dev_pm_qos_constraints_allocate
+ * @dev: device to allocate data for
+ *
+ * Called at the first call to add_request, for constraint data allocation
+ * Must be called with the dev_pm_qos_mtx mutex held
+ */
+static int dev_pm_qos_constraints_allocate(struct device *dev)
+{
+	struct dev_pm_qos *qos;
+	struct pm_qos_constraints *c;
+	struct blocking_notifier_head *n;
+
+	qos = kzalloc(sizeof(*qos), GFP_KERNEL);
+	if (!qos)
+		return -ENOMEM;
+
+	n = kzalloc(sizeof(*n), GFP_KERNEL);
+	if (!n) {
+		kfree(qos);
+		return -ENOMEM;
+	}
+	BLOCKING_INIT_NOTIFIER_HEAD(n);
+
+	c = &qos->resume_latency;
+	plist_head_init(&c->list);
+	c->target_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
+	c->default_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
+	c->no_constraint_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
+	c->type = PM_QOS_MIN;
+	c->notifiers = n;
+
+	c = &qos->latency_tolerance;
+	plist_head_init(&c->list);
+	c->target_value = PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE;
+	c->default_value = PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE;
+	c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
+	c->type = PM_QOS_MIN;
+
+	INIT_LIST_HEAD(&qos->flags.list);
+
+	spin_lock_irq(&dev->power.lock);
+	dev->power.qos = qos;
+	spin_unlock_irq(&dev->power.lock);
+
+	return 0;
+}
+
+static void __dev_pm_qos_hide_latency_limit(struct device *dev);
+static void __dev_pm_qos_hide_flags(struct device *dev);
+
+/**
+ * dev_pm_qos_constraints_destroy
+ * @dev: target device
+ *
+ * Called from the device PM subsystem on device removal under device_pm_lock().
+ */
+void dev_pm_qos_constraints_destroy(struct device *dev)
+{
+	struct dev_pm_qos *qos;
+	struct dev_pm_qos_request *req, *tmp;
+	struct pm_qos_constraints *c;
+	struct pm_qos_flags *f;
+
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+
+	/*
+	 * If the device's PM QoS resume latency limit or PM QoS flags have been
+	 * exposed to user space, they have to be hidden at this point.
+	 */
+	pm_qos_sysfs_remove_resume_latency(dev);
+	pm_qos_sysfs_remove_flags(dev);
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	__dev_pm_qos_hide_latency_limit(dev);
+	__dev_pm_qos_hide_flags(dev);
+
+	qos = dev->power.qos;
+	if (!qos)
+		goto out;
+
+	/* Flush the constraints lists for the device. */
+	c = &qos->resume_latency;
+	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
+		/*
+		 * Update constraints list and call the notification
+		 * callbacks if needed
+		 */
+		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
+	c = &qos->latency_tolerance;
+	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
+		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
+	f = &qos->flags;
+	list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) {
+		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
+
+	spin_lock_irq(&dev->power.lock);
+	dev->power.qos = ERR_PTR(-ENODEV);
+	spin_unlock_irq(&dev->power.lock);
+
+	kfree(c->notifiers);
+	kfree(qos);
+
+ out:
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+}
+
+static bool dev_pm_qos_invalid_request(struct device *dev,
+				       struct dev_pm_qos_request *req)
+{
+	return !req || (req->type == DEV_PM_QOS_LATENCY_TOLERANCE
+			&& !dev->power.set_latency_tolerance);
+}
+
+static int __dev_pm_qos_add_request(struct device *dev,
+				    struct dev_pm_qos_request *req,
+				    enum dev_pm_qos_req_type type, s32 value)
+{
+	int ret = 0;
+
+	if (!dev || dev_pm_qos_invalid_request(dev, req))
+		return -EINVAL;
+
+	if (WARN(dev_pm_qos_request_active(req),
+		 "%s() called for already added request\n", __func__))
+		return -EINVAL;
+
+	if (IS_ERR(dev->power.qos))
+		ret = -ENODEV;
+	else if (!dev->power.qos)
+		ret = dev_pm_qos_constraints_allocate(dev);
+
+	trace_dev_pm_qos_add_request(dev_name(dev), type, value);
+	if (!ret) {
+		req->dev = dev;
+		req->type = type;
+		ret = apply_constraint(req, PM_QOS_ADD_REQ, value);
+	}
+	return ret;
+}
+
+/**
+ * dev_pm_qos_add_request - inserts new qos request into the list
+ * @dev: target device for the constraint
+ * @req: pointer to a preallocated handle
+ * @type: type of the request
+ * @value: defines the qos request
+ *
+ * This function inserts a new entry in the device constraints list of
+ * requested qos performance characteristics. It recomputes the aggregate
+ * QoS expectations of parameters and initializes the dev_pm_qos_request
+ * handle.  Caller needs to save this handle for later use in updates and
+ * removal.
+ *
+ * Returns 1 if the aggregated constraint value has changed,
+ * 0 if the aggregated constraint value has not changed,
+ * -EINVAL in case of wrong parameters, -ENOMEM if there's not enough memory
+ * to allocate for data structures, -ENODEV if the device has just been removed
+ * from the system.
+ *
+ * Callers should ensure that the target device is not RPM_SUSPENDED before
+ * using this function for requests of type DEV_PM_QOS_FLAGS.
+ */
+int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
+			   enum dev_pm_qos_req_type type, s32 value)
+{
+	int ret;
+
+	mutex_lock(&dev_pm_qos_mtx);
+	ret = __dev_pm_qos_add_request(dev, req, type, value);
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_request);
+
+/**
+ * __dev_pm_qos_update_request - Modify an existing device PM QoS request.
+ * @req : PM QoS request to modify.
+ * @new_value: New value to request.
+ */
+static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req,
+				       s32 new_value)
+{
+	s32 curr_value;
+	int ret = 0;
+
+	if (!req) /*guard against callers passing in null */
+		return -EINVAL;
+
+	if (WARN(!dev_pm_qos_request_active(req),
+		 "%s() called for unknown object\n", __func__))
+		return -EINVAL;
+
+	if (IS_ERR_OR_NULL(req->dev->power.qos))
+		return -ENODEV;
+
+	switch(req->type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+	case DEV_PM_QOS_LATENCY_TOLERANCE:
+		curr_value = req->data.pnode.prio;
+		break;
+	case DEV_PM_QOS_FLAGS:
+		curr_value = req->data.flr.flags;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	trace_dev_pm_qos_update_request(dev_name(req->dev), req->type,
+					new_value);
+	if (curr_value != new_value)
+		ret = apply_constraint(req, PM_QOS_UPDATE_REQ, new_value);
+
+	return ret;
+}
+
+/**
+ * dev_pm_qos_update_request - modifies an existing qos request
+ * @req : handle to list element holding a dev_pm_qos request to use
+ * @new_value: defines the qos request
+ *
+ * Updates an existing dev PM qos request along with updating the
+ * target value.
+ *
+ * Attempts are made to make this code callable on hot code paths.
+ *
+ * Returns 1 if the aggregated constraint value has changed,
+ * 0 if the aggregated constraint value has not changed,
+ * -EINVAL in case of wrong parameters, -ENODEV if the device has been
+ * removed from the system
+ *
+ * Callers should ensure that the target device is not RPM_SUSPENDED before
+ * using this function for requests of type DEV_PM_QOS_FLAGS.
+ */
+int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value)
+{
+	int ret;
+
+	mutex_lock(&dev_pm_qos_mtx);
+	ret = __dev_pm_qos_update_request(req, new_value);
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_update_request);
+
+static int __dev_pm_qos_remove_request(struct dev_pm_qos_request *req)
+{
+	int ret;
+
+	if (!req) /*guard against callers passing in null */
+		return -EINVAL;
+
+	if (WARN(!dev_pm_qos_request_active(req),
+		 "%s() called for unknown object\n", __func__))
+		return -EINVAL;
+
+	if (IS_ERR_OR_NULL(req->dev->power.qos))
+		return -ENODEV;
+
+	trace_dev_pm_qos_remove_request(dev_name(req->dev), req->type,
+					PM_QOS_DEFAULT_VALUE);
+	ret = apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+	memset(req, 0, sizeof(*req));
+	return ret;
+}
+
+/**
+ * dev_pm_qos_remove_request - modifies an existing qos request
+ * @req: handle to request list element
+ *
+ * Will remove pm qos request from the list of constraints and
+ * recompute the current target value. Call this on slow code paths.
+ *
+ * Returns 1 if the aggregated constraint value has changed,
+ * 0 if the aggregated constraint value has not changed,
+ * -EINVAL in case of wrong parameters, -ENODEV if the device has been
+ * removed from the system
+ *
+ * Callers should ensure that the target device is not RPM_SUSPENDED before
+ * using this function for requests of type DEV_PM_QOS_FLAGS.
+ */
+int dev_pm_qos_remove_request(struct dev_pm_qos_request *req)
+{
+	int ret;
+
+	mutex_lock(&dev_pm_qos_mtx);
+	ret = __dev_pm_qos_remove_request(req);
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request);
+
+/**
+ * dev_pm_qos_add_notifier - sets notification entry for changes to target value
+ * of per-device PM QoS constraints
+ *
+ * @dev: target device for the constraint
+ * @notifier: notifier block managed by caller.
+ *
+ * Will register the notifier into a notification chain that gets called
+ * upon changes to the target value for the device.
+ *
+ * If the device's constraints object doesn't exist when this routine is called,
+ * it will be created (or error code will be returned if that fails).
+ */
+int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier)
+{
+	int ret = 0;
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR(dev->power.qos))
+		ret = -ENODEV;
+	else if (!dev->power.qos)
+		ret = dev_pm_qos_constraints_allocate(dev);
+
+	if (!ret)
+		ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers,
+						       notifier);
+
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_notifier);
+
+/**
+ * dev_pm_qos_remove_notifier - deletes notification for changes to target value
+ * of per-device PM QoS constraints
+ *
+ * @dev: target device for the constraint
+ * @notifier: notifier block to be removed.
+ *
+ * Will remove the notifier from the notification chain that gets called
+ * upon changes to the target value.
+ */
+int dev_pm_qos_remove_notifier(struct device *dev,
+			       struct notifier_block *notifier)
+{
+	int retval = 0;
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	/* Silently return if the constraints object is not present. */
+	if (!IS_ERR_OR_NULL(dev->power.qos))
+		retval = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers,
+							    notifier);
+
+	mutex_unlock(&dev_pm_qos_mtx);
+	return retval;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier);
+
+/**
+ * dev_pm_qos_add_global_notifier - sets notification entry for changes to
+ * target value of the PM QoS constraints for any device
+ *
+ * @notifier: notifier block managed by caller.
+ *
+ * Will register the notifier into a notification chain that gets called
+ * upon changes to the target value for any device.
+ */
+int dev_pm_qos_add_global_notifier(struct notifier_block *notifier)
+{
+	return blocking_notifier_chain_register(&dev_pm_notifiers, notifier);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_global_notifier);
+
+/**
+ * dev_pm_qos_remove_global_notifier - deletes notification for changes to
+ * target value of PM QoS constraints for any device
+ *
+ * @notifier: notifier block to be removed.
+ *
+ * Will remove the notifier from the notification chain that gets called
+ * upon changes to the target value for any device.
+ */
+int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier)
+{
+	return blocking_notifier_chain_unregister(&dev_pm_notifiers, notifier);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_remove_global_notifier);
+
+/**
+ * dev_pm_qos_add_ancestor_request - Add PM QoS request for device's ancestor.
+ * @dev: Device whose ancestor to add the request for.
+ * @req: Pointer to the preallocated handle.
+ * @type: Type of the request.
+ * @value: Constraint latency value.
+ */
+int dev_pm_qos_add_ancestor_request(struct device *dev,
+				    struct dev_pm_qos_request *req,
+				    enum dev_pm_qos_req_type type, s32 value)
+{
+	struct device *ancestor = dev->parent;
+	int ret = -ENODEV;
+
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		while (ancestor && !ancestor->power.ignore_children)
+			ancestor = ancestor->parent;
+
+		break;
+	case DEV_PM_QOS_LATENCY_TOLERANCE:
+		while (ancestor && !ancestor->power.set_latency_tolerance)
+			ancestor = ancestor->parent;
+
+		break;
+	default:
+		ancestor = NULL;
+	}
+	if (ancestor)
+		ret = dev_pm_qos_add_request(ancestor, req, type, value);
+
+	if (ret < 0)
+		req->dev = NULL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_ancestor_request);
+
+static void __dev_pm_qos_drop_user_request(struct device *dev,
+					   enum dev_pm_qos_req_type type)
+{
+	struct dev_pm_qos_request *req = NULL;
+
+	switch(type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		req = dev->power.qos->resume_latency_req;
+		dev->power.qos->resume_latency_req = NULL;
+		break;
+	case DEV_PM_QOS_LATENCY_TOLERANCE:
+		req = dev->power.qos->latency_tolerance_req;
+		dev->power.qos->latency_tolerance_req = NULL;
+		break;
+	case DEV_PM_QOS_FLAGS:
+		req = dev->power.qos->flags_req;
+		dev->power.qos->flags_req = NULL;
+		break;
+	}
+	__dev_pm_qos_remove_request(req);
+	kfree(req);
+}
+
+static void dev_pm_qos_drop_user_request(struct device *dev,
+					 enum dev_pm_qos_req_type type)
+{
+	mutex_lock(&dev_pm_qos_mtx);
+	__dev_pm_qos_drop_user_request(dev, type);
+	mutex_unlock(&dev_pm_qos_mtx);
+}
+
+/**
+ * dev_pm_qos_expose_latency_limit - Expose PM QoS latency limit to user space.
+ * @dev: Device whose PM QoS latency limit is to be exposed to user space.
+ * @value: Initial value of the latency limit.
+ */
+int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
+{
+	struct dev_pm_qos_request *req;
+	int ret;
+
+	if (!device_is_registered(dev) || value < 0)
+		return -EINVAL;
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_RESUME_LATENCY, value);
+	if (ret < 0) {
+		kfree(req);
+		return ret;
+	}
+
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR_OR_NULL(dev->power.qos))
+		ret = -ENODEV;
+	else if (dev->power.qos->resume_latency_req)
+		ret = -EEXIST;
+
+	if (ret < 0) {
+		__dev_pm_qos_remove_request(req);
+		kfree(req);
+		mutex_unlock(&dev_pm_qos_mtx);
+		goto out;
+	}
+	dev->power.qos->resume_latency_req = req;
+
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	ret = pm_qos_sysfs_add_resume_latency(dev);
+	if (ret)
+		dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_RESUME_LATENCY);
+
+ out:
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_limit);
+
+static void __dev_pm_qos_hide_latency_limit(struct device *dev)
+{
+	if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->resume_latency_req)
+		__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_RESUME_LATENCY);
+}
+
+/**
+ * dev_pm_qos_hide_latency_limit - Hide PM QoS latency limit from user space.
+ * @dev: Device whose PM QoS latency limit is to be hidden from user space.
+ */
+void dev_pm_qos_hide_latency_limit(struct device *dev)
+{
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+
+	pm_qos_sysfs_remove_resume_latency(dev);
+
+	mutex_lock(&dev_pm_qos_mtx);
+	__dev_pm_qos_hide_latency_limit(dev);
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_limit);
+
+/**
+ * dev_pm_qos_expose_flags - Expose PM QoS flags of a device to user space.
+ * @dev: Device whose PM QoS flags are to be exposed to user space.
+ * @val: Initial values of the flags.
+ */
+int dev_pm_qos_expose_flags(struct device *dev, s32 val)
+{
+	struct dev_pm_qos_request *req;
+	int ret;
+
+	if (!device_is_registered(dev))
+		return -EINVAL;
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_FLAGS, val);
+	if (ret < 0) {
+		kfree(req);
+		return ret;
+	}
+
+	pm_runtime_get_sync(dev);
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR_OR_NULL(dev->power.qos))
+		ret = -ENODEV;
+	else if (dev->power.qos->flags_req)
+		ret = -EEXIST;
+
+	if (ret < 0) {
+		__dev_pm_qos_remove_request(req);
+		kfree(req);
+		mutex_unlock(&dev_pm_qos_mtx);
+		goto out;
+	}
+	dev->power.qos->flags_req = req;
+
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	ret = pm_qos_sysfs_add_flags(dev);
+	if (ret)
+		dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS);
+
+ out:
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+	pm_runtime_put(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_expose_flags);
+
+static void __dev_pm_qos_hide_flags(struct device *dev)
+{
+	if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->flags_req)
+		__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS);
+}
+
+/**
+ * dev_pm_qos_hide_flags - Hide PM QoS flags of a device from user space.
+ * @dev: Device whose PM QoS flags are to be hidden from user space.
+ */
+void dev_pm_qos_hide_flags(struct device *dev)
+{
+	pm_runtime_get_sync(dev);
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+
+	pm_qos_sysfs_remove_flags(dev);
+
+	mutex_lock(&dev_pm_qos_mtx);
+	__dev_pm_qos_hide_flags(dev);
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+	pm_runtime_put(dev);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_hide_flags);
+
+/**
+ * dev_pm_qos_update_flags - Update PM QoS flags request owned by user space.
+ * @dev: Device to update the PM QoS flags request for.
+ * @mask: Flags to set/clear.
+ * @set: Whether to set or clear the flags (true means set).
+ */
+int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set)
+{
+	s32 value;
+	int ret;
+
+	pm_runtime_get_sync(dev);
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->flags_req) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	value = dev_pm_qos_requested_flags(dev);
+	if (set)
+		value |= mask;
+	else
+		value &= ~mask;
+
+	ret = __dev_pm_qos_update_request(dev->power.qos->flags_req, value);
+
+ out:
+	mutex_unlock(&dev_pm_qos_mtx);
+	pm_runtime_put(dev);
+	return ret;
+}
+
+/**
+ * dev_pm_qos_get_user_latency_tolerance - Get user space latency tolerance.
+ * @dev: Device to obtain the user space latency tolerance for.
+ */
+s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev)
+{
+	s32 ret;
+
+	mutex_lock(&dev_pm_qos_mtx);
+	ret = IS_ERR_OR_NULL(dev->power.qos)
+		|| !dev->power.qos->latency_tolerance_req ?
+			PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT :
+			dev->power.qos->latency_tolerance_req->data.pnode.prio;
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
+
+/**
+ * dev_pm_qos_update_user_latency_tolerance - Update user space latency tolerance.
+ * @dev: Device to update the user space latency tolerance for.
+ * @val: New user space latency tolerance for @dev (negative values disable).
+ */
+int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
+{
+	int ret;
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR_OR_NULL(dev->power.qos)
+	    || !dev->power.qos->latency_tolerance_req) {
+		struct dev_pm_qos_request *req;
+
+		if (val < 0) {
+			ret = -EINVAL;
+			goto out;
+		}
+		req = kzalloc(sizeof(*req), GFP_KERNEL);
+		if (!req) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		ret = __dev_pm_qos_add_request(dev, req, DEV_PM_QOS_LATENCY_TOLERANCE, val);
+		if (ret < 0) {
+			kfree(req);
+			goto out;
+		}
+		dev->power.qos->latency_tolerance_req = req;
+	} else {
+		if (val < 0) {
+			__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY_TOLERANCE);
+			ret = 0;
+		} else {
+			ret = __dev_pm_qos_update_request(dev->power.qos->latency_tolerance_req, val);
+		}
+	}
+
+ out:
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
new file mode 100644
index 000000000..5070c4fe8
--- /dev/null
+++ b/drivers/base/power/runtime.c
@@ -0,0 +1,1475 @@
+/*
+ * drivers/base/power/runtime.c - Helper functions for device runtime 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/export.h>
+#include <linux/pm_runtime.h>
+#include <trace/events/rpm.h>
+#include "power.h"
+
+typedef int (*pm_callback_t)(struct device *);
+
+static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset)
+{
+	pm_callback_t cb;
+	const struct dev_pm_ops *ops;
+
+	if (dev->pm_domain)
+		ops = &dev->pm_domain->ops;
+	else if (dev->type && dev->type->pm)
+		ops = dev->type->pm;
+	else if (dev->class && dev->class->pm)
+		ops = dev->class->pm;
+	else if (dev->bus && dev->bus->pm)
+		ops = dev->bus->pm;
+	else
+		ops = NULL;
+
+	if (ops)
+		cb = *(pm_callback_t *)((void *)ops + cb_offset);
+	else
+		cb = NULL;
+
+	if (!cb && dev->driver && dev->driver->pm)
+		cb = *(pm_callback_t *)((void *)dev->driver->pm + cb_offset);
+
+	return cb;
+}
+
+#define RPM_GET_CALLBACK(dev, callback) \
+		__rpm_get_callback(dev, offsetof(struct dev_pm_ops, callback))
+
+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;
+	unsigned long delta;
+
+	delta = now - dev->power.accounting_timestamp;
+
+	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);
+
+static int dev_memalloc_noio(struct device *dev, void *data)
+{
+	return dev->power.memalloc_noio;
+}
+
+/*
+ * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag.
+ * @dev: Device to handle.
+ * @enable: True for setting the flag and False for clearing the flag.
+ *
+ * Set the flag for all devices in the path from the device to the
+ * root device in the device tree if @enable is true, otherwise clear
+ * the flag for devices in the path whose siblings don't set the flag.
+ *
+ * The function should only be called by block device, or network
+ * device driver for solving the deadlock problem during runtime
+ * resume/suspend:
+ *
+ *     If memory allocation with GFP_KERNEL is called inside runtime
+ *     resume/suspend callback of any one of its ancestors(or the
+ *     block device itself), the deadlock may be triggered inside the
+ *     memory allocation since it might not complete until the block
+ *     device becomes active and the involed page I/O finishes. The
+ *     situation is pointed out first by Alan Stern. Network device
+ *     are involved in iSCSI kind of situation.
+ *
+ * The lock of dev_hotplug_mutex is held in the function for handling
+ * hotplug race because pm_runtime_set_memalloc_noio() may be called
+ * in async probe().
+ *
+ * The function should be called between device_add() and device_del()
+ * on the affected device(block/network device).
+ */
+void pm_runtime_set_memalloc_noio(struct device *dev, bool enable)
+{
+	static DEFINE_MUTEX(dev_hotplug_mutex);
+
+	mutex_lock(&dev_hotplug_mutex);
+	for (;;) {
+		bool enabled;
+
+		/* hold power lock since bitfield is not SMP-safe. */
+		spin_lock_irq(&dev->power.lock);
+		enabled = dev->power.memalloc_noio;
+		dev->power.memalloc_noio = enable;
+		spin_unlock_irq(&dev->power.lock);
+
+		/*
+		 * not need to enable ancestors any more if the device
+		 * has been enabled.
+		 */
+		if (enabled && enable)
+			break;
+
+		dev = dev->parent;
+
+		/*
+		 * clear flag of the parent device only if all the
+		 * children don't set the flag because ancestor's
+		 * flag was set by any one of the descendants.
+		 */
+		if (!dev || (!enable &&
+			     device_for_each_child(dev, NULL,
+						   dev_memalloc_noio)))
+			break;
+	}
+	mutex_unlock(&dev_hotplug_mutex);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio);
+
+/**
+ * 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 (dev->power.disable_depth > 0)
+		retval = -EACCES;
+	else if (atomic_read(&dev->power.usage_count) > 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_pm_qos_read_value(dev) < 0)
+		retval = -EPERM;
+	else if (dev->power.runtime_status == RPM_SUSPENDED)
+		retval = 1;
+
+	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 (dev->power.irq_safe)
+		spin_unlock(&dev->power.lock);
+	else
+		spin_unlock_irq(&dev->power.lock);
+
+	retval = cb(dev);
+
+	if (dev->power.irq_safe)
+		spin_lock(&dev->power.lock);
+	else
+		spin_lock_irq(&dev->power.lock);
+
+	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 runtime 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. If the ->runtime_idle callback
+ * doesn't exist or if it returns 0, call rpm_suspend with the RPM_AUTO flag.
+ *
+ * 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;
+
+	trace_rpm_idle(dev, rpmflags);
+	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)
+		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);
+		}
+		trace_rpm_return_int(dev, _THIS_IP_, 0);
+		return 0;
+	}
+
+	dev->power.idle_notification = true;
+
+	callback = RPM_GET_CALLBACK(dev, runtime_idle);
+
+	if (callback)
+		retval = __rpm_callback(callback, dev);
+
+	dev->power.idle_notification = false;
+	wake_up_all(&dev->power.wait_queue);
+
+ out:
+	trace_rpm_return_int(dev, _THIS_IP_, retval);
+	return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO);
+}
+
+/**
+ * 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)
+{
+	int retval;
+
+	if (!cb)
+		return -ENOSYS;
+
+	if (dev->power.memalloc_noio) {
+		unsigned int noio_flag;
+
+		/*
+		 * Deadlock might be caused if memory allocation with
+		 * GFP_KERNEL happens inside runtime_suspend and
+		 * runtime_resume callbacks of one block device's
+		 * ancestor or the block device itself. Network
+		 * device might be thought as part of iSCSI block
+		 * device, so network device and its ancestor should
+		 * be marked as memalloc_noio too.
+		 */
+		noio_flag = memalloc_noio_save();
+		retval = __rpm_callback(cb, dev);
+		memalloc_noio_restore(noio_flag);
+	} else {
+		retval = __rpm_callback(cb, dev);
+	}
+
+	dev->power.runtime_error = retval;
+	return retval != -EACCES ? retval : -EIO;
+}
+
+/**
+ * rpm_suspend - Carry out runtime suspend of given device.
+ * @dev: Device to suspend.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's runtime PM status allows it to be suspended.
+ * Cancel a pending idle notification, autosuspend or suspend. 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. If the RPM_ASYNC flag is set then queue a suspend request;
+ * otherwise run the ->runtime_suspend() callback directly. When
+ * ->runtime_suspend succeeded, if a deferred resume was requested while
+ * the callback was running then carry it out, otherwise send an idle
+ * notification for its parent (if the suspend succeeded and both
+ * ignore_children of parent->power and irq_safe of dev->power are not set).
+ * 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;
+
+	trace_rpm_suspend(dev, 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;
+		}
+
+		if (dev->power.irq_safe) {
+			spin_unlock(&dev->power.lock);
+
+			cpu_relax();
+
+			spin_lock(&dev->power.lock);
+			goto repeat;
+		}
+
+		/* 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;
+	}
+
+	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);
+
+	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
+
+	retval = rpm_callback(callback, dev);
+	if (retval)
+		goto fail;
+
+ 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) {
+		dev->power.deferred_resume = false;
+		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:
+	trace_rpm_return_int(dev, _THIS_IP_, retval);
+
+	return retval;
+
+ fail:
+	__update_runtime_status(dev, RPM_ACTIVE);
+	dev->power.deferred_resume = false;
+	wake_up_all(&dev->power.wait_queue);
+
+	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);
+	}
+	goto out;
+}
+
+/**
+ * rpm_resume - Carry out runtime resume of given device.
+ * @dev: Device to resume.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's runtime 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;
+
+	trace_rpm_resume(dev, rpmflags);
+
+ repeat:
+	if (dev->power.runtime_error)
+		retval = -EINVAL;
+	else if (dev->power.disable_depth == 1 && dev->power.is_suspended
+	    && dev->power.runtime_status == RPM_ACTIVE)
+		retval = 1;
+	else if (dev->power.disable_depth > 0)
+		retval = -EACCES;
+	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;
+		}
+
+		if (dev->power.irq_safe) {
+			spin_unlock(&dev->power.lock);
+
+			cpu_relax();
+
+			spin_lock(&dev->power.lock);
+			goto repeat;
+		}
+
+		/* 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);
+			retval = 1;
+			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 runtime 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);
+
+	callback = RPM_GET_CALLBACK(dev, runtime_resume);
+
+	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 >= 0)
+		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);
+	}
+
+	trace_rpm_return_int(dev, _THIS_IP_, retval);
+
+	return retval;
+}
+
+/**
+ * pm_runtime_work - Universal runtime 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 runtime 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 runtime 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,
+ * or if pm_runtime_irq_safe() has been called.
+ */
+int __pm_runtime_idle(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_idle(dev, rpmflags);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_idle);
+
+/**
+ * __pm_runtime_suspend - Entry point for runtime 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,
+ * or if pm_runtime_irq_safe() has been called.
+ */
+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 runtime 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,
+ * or if pm_runtime_irq_safe() has been called.
+ */
+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 runtime PM status of a device.
+ * @dev: Device to handle.
+ * @status: New runtime PM status of the device.
+ *
+ * If runtime 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 runtime 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
+ * runtime 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 runtime 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 runtime 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 it was zero previously,
+ * cancel all pending runtime PM requests for the device and wait for all
+ * operations in progress to complete.  The device can be either active or
+ * suspended after its runtime 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 runtime PM.
+ */
+void __pm_runtime_disable(struct device *dev, bool check_resume)
+{
+	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 runtime 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 runtime 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 runtime 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 runtime 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 runtime 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 runtime PM
+ * callbacks of its own.  The runtime 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 runtime suspends.  If it
+ * changes the other way, allow runtime 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 runtime
+ * suspends as needed.
+ */
+void __pm_runtime_use_autosuspend(struct device *dev, bool use)
+{
+	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.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 runtime 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(dev->parent);
+}
+
+/**
+ * pm_runtime_force_suspend - Force a device into suspend state if needed.
+ * @dev: Device to suspend.
+ *
+ * Disable runtime PM so we safely can check the device's runtime PM status and
+ * if it is active, invoke it's .runtime_suspend callback to bring it into
+ * suspend state. Keep runtime PM disabled to preserve the state unless we
+ * encounter errors.
+ *
+ * Typically this function may be invoked from a system suspend callback to make
+ * sure the device is put into low power state.
+ */
+int pm_runtime_force_suspend(struct device *dev)
+{
+	int (*callback)(struct device *);
+	int ret = 0;
+
+	pm_runtime_disable(dev);
+	if (pm_runtime_status_suspended(dev))
+		return 0;
+
+	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
+
+	if (!callback) {
+		ret = -ENOSYS;
+		goto err;
+	}
+
+	ret = callback(dev);
+	if (ret)
+		goto err;
+
+	pm_runtime_set_suspended(dev);
+	return 0;
+err:
+	pm_runtime_enable(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_force_suspend);
+
+/**
+ * pm_runtime_force_resume - Force a device into resume state.
+ * @dev: Device to resume.
+ *
+ * Prior invoking this function we expect the user to have brought the device
+ * into low power state by a call to pm_runtime_force_suspend(). Here we reverse
+ * those actions and brings the device into full power. We update the runtime PM
+ * status and re-enables runtime PM.
+ *
+ * Typically this function may be invoked from a system resume callback to make
+ * sure the device is put into full power state.
+ */
+int pm_runtime_force_resume(struct device *dev)
+{
+	int (*callback)(struct device *);
+	int ret = 0;
+
+	callback = RPM_GET_CALLBACK(dev, runtime_resume);
+
+	if (!callback) {
+		ret = -ENOSYS;
+		goto out;
+	}
+
+	ret = callback(dev);
+	if (ret)
+		goto out;
+
+	pm_runtime_set_active(dev);
+	pm_runtime_mark_last_busy(dev);
+out:
+	pm_runtime_enable(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_force_resume);
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
new file mode 100644
index 000000000..d2be3f9c2
--- /dev/null
+++ b/drivers/base/power/sysfs.c
@@ -0,0 +1,753 @@
+/*
+ * drivers/base/power/sysfs.c - sysfs entries for device PM
+ */
+
+#include <linux/device.h>
+#include <linux/string.h>
+#include <linux/export.h>
+#include <linux/pm_qos.h>
+#include <linux/pm_runtime.h>
+#include <linux/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
+ */
+
+const char power_group_name[] = "power";
+EXPORT_SYMBOL_GPL(power_group_name);
+
+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;
+	device_lock(dev);
+	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
+		n = -EINVAL;
+	device_unlock(dev);
+	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 (kstrtol(buf, 10, &delay) != 0 || delay != (int) delay)
+		return -EINVAL;
+
+	device_lock(dev);
+	pm_runtime_set_autosuspend_delay(dev, delay);
+	device_unlock(dev);
+	return n;
+}
+
+static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
+		autosuspend_delay_ms_store);
+
+static ssize_t pm_qos_resume_latency_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	return sprintf(buf, "%d\n", dev_pm_qos_requested_resume_latency(dev));
+}
+
+static ssize_t pm_qos_resume_latency_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t n)
+{
+	s32 value;
+	int ret;
+
+	if (kstrtos32(buf, 0, &value))
+		return -EINVAL;
+
+	if (value < 0)
+		return -EINVAL;
+
+	ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req,
+					value);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_resume_latency_us, 0644,
+		   pm_qos_resume_latency_show, pm_qos_resume_latency_store);
+
+static ssize_t pm_qos_latency_tolerance_show(struct device *dev,
+					     struct device_attribute *attr,
+					     char *buf)
+{
+	s32 value = dev_pm_qos_get_user_latency_tolerance(dev);
+
+	if (value < 0)
+		return sprintf(buf, "auto\n");
+	else if (value == PM_QOS_LATENCY_ANY)
+		return sprintf(buf, "any\n");
+
+	return sprintf(buf, "%d\n", value);
+}
+
+static ssize_t pm_qos_latency_tolerance_store(struct device *dev,
+					      struct device_attribute *attr,
+					      const char *buf, size_t n)
+{
+	s32 value;
+	int ret;
+
+	if (kstrtos32(buf, 0, &value)) {
+		if (!strcmp(buf, "auto") || !strcmp(buf, "auto\n"))
+			value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
+		else if (!strcmp(buf, "any") || !strcmp(buf, "any\n"))
+			value = PM_QOS_LATENCY_ANY;
+	}
+	ret = dev_pm_qos_update_user_latency_tolerance(dev, value);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_latency_tolerance_us, 0644,
+		   pm_qos_latency_tolerance_show, pm_qos_latency_tolerance_store);
+
+static ssize_t pm_qos_no_power_off_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return sprintf(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev)
+					& PM_QOS_FLAG_NO_POWER_OFF));
+}
+
+static ssize_t pm_qos_no_power_off_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t n)
+{
+	int ret;
+
+	if (kstrtoint(buf, 0, &ret))
+		return -EINVAL;
+
+	if (ret != 0 && ret != 1)
+		return -EINVAL;
+
+	ret = dev_pm_qos_update_flags(dev, PM_QOS_FLAG_NO_POWER_OFF, ret);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_no_power_off, 0644,
+		   pm_qos_no_power_off_show, pm_qos_no_power_off_store);
+
+static ssize_t pm_qos_remote_wakeup_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	return sprintf(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev)
+					& PM_QOS_FLAG_REMOTE_WAKEUP));
+}
+
+static ssize_t pm_qos_remote_wakeup_store(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *buf, size_t n)
+{
+	int ret;
+
+	if (kstrtoint(buf, 0, &ret))
+		return -EINVAL;
+
+	if (ret != 0 && ret != 1)
+		return -EINVAL;
+
+	ret = dev_pm_qos_update_flags(dev, PM_QOS_FLAG_REMOTE_WAKEUP, ret);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_remote_wakeup, 0644,
+		   pm_qos_remote_wakeup_show, pm_qos_remote_wakeup_store);
+
+#ifdef CONFIG_PM_SLEEP
+static const char _enabled[] = "enabled";
+static const char _disabled[] = "disabled";
+
+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_abort_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->wakeup_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_abort_count, 0444, wakeup_abort_count_show, NULL);
+
+static ssize_t wakeup_expire_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->expire_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_expire_count, 0444, wakeup_expire_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);
+
+#ifdef CONFIG_PM_AUTOSLEEP
+static ssize_t wakeup_prevent_sleep_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->prevent_sleep_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_prevent_sleep_time_ms, 0444,
+		   wakeup_prevent_sleep_time_show, NULL);
+#endif /* CONFIG_PM_AUTOSLEEP */
+#endif /* CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+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);
+
+#ifdef CONFIG_PM_SLEEP
+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_SLEEP */
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
+
+static struct attribute *power_attrs[] = {
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+#ifdef CONFIG_PM_SLEEP
+	&dev_attr_async.attr,
+#endif
+	&dev_attr_runtime_status.attr,
+	&dev_attr_runtime_usage.attr,
+	&dev_attr_runtime_active_kids.attr,
+	&dev_attr_runtime_enabled.attr,
+#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_abort_count.attr,
+	&dev_attr_wakeup_expire_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,
+#ifdef CONFIG_PM_AUTOSLEEP
+	&dev_attr_wakeup_prevent_sleep_time_ms.attr,
+#endif
+#endif
+	NULL,
+};
+static struct attribute_group pm_wakeup_attr_group = {
+	.name	= power_group_name,
+	.attrs	= wakeup_attrs,
+};
+
+static struct attribute *runtime_attrs[] = {
+#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,
+	NULL,
+};
+static struct attribute_group pm_runtime_attr_group = {
+	.name	= power_group_name,
+	.attrs	= runtime_attrs,
+};
+
+static struct attribute *pm_qos_resume_latency_attrs[] = {
+	&dev_attr_pm_qos_resume_latency_us.attr,
+	NULL,
+};
+static struct attribute_group pm_qos_resume_latency_attr_group = {
+	.name	= power_group_name,
+	.attrs	= pm_qos_resume_latency_attrs,
+};
+
+static struct attribute *pm_qos_latency_tolerance_attrs[] = {
+	&dev_attr_pm_qos_latency_tolerance_us.attr,
+	NULL,
+};
+static struct attribute_group pm_qos_latency_tolerance_attr_group = {
+	.name	= power_group_name,
+	.attrs	= pm_qos_latency_tolerance_attrs,
+};
+
+static struct attribute *pm_qos_flags_attrs[] = {
+	&dev_attr_pm_qos_no_power_off.attr,
+	&dev_attr_pm_qos_remote_wakeup.attr,
+	NULL,
+};
+static struct attribute_group pm_qos_flags_attr_group = {
+	.name	= power_group_name,
+	.attrs	= pm_qos_flags_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)
+			goto err_runtime;
+	}
+	if (dev->power.set_latency_tolerance) {
+		rc = sysfs_merge_group(&dev->kobj,
+				       &pm_qos_latency_tolerance_attr_group);
+		if (rc)
+			goto err_wakeup;
+	}
+	return 0;
+
+ err_wakeup:
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
+ err_runtime:
+	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
+ 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);
+}
+
+int pm_qos_sysfs_add_resume_latency(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj, &pm_qos_resume_latency_attr_group);
+}
+
+void pm_qos_sysfs_remove_resume_latency(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_resume_latency_attr_group);
+}
+
+int pm_qos_sysfs_add_flags(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj, &pm_qos_flags_attr_group);
+}
+
+void pm_qos_sysfs_remove_flags(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_flags_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)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group);
+	dev_pm_qos_constraints_destroy(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 000000000..a311cfa4c
--- /dev/null
+++ b/drivers/base/power/trace.c
@@ -0,0 +1,266 @@
+/*
+ * 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/pm-trace.h>
+#include <linux/export.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("RTC 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_pm_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_pm_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 000000000..77262009f
--- /dev/null
+++ b/drivers/base/power/wakeup.c
@@ -0,0 +1,920 @@
+/*
+ * 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/export.h>
+#include <linux/suspend.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <trace/events/power.h>
+
+#include "power.h"
+
+/*
+ * 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 __read_mostly;
+
+/* If set and the system is suspending, terminate the suspend. */
+static bool pm_abort_suspend __read_mostly;
+
+/*
+ * 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);
+
+static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue);
+
+/**
+ * wakeup_source_prepare - Prepare a new wakeup source for initialization.
+ * @ws: Wakeup source to prepare.
+ * @name: Pointer to the name of the new wakeup source.
+ *
+ * Callers must ensure that the @name string won't be freed when @ws is still in
+ * use.
+ */
+void wakeup_source_prepare(struct wakeup_source *ws, const char *name)
+{
+	if (ws) {
+		memset(ws, 0, sizeof(*ws));
+		ws->name = name;
+	}
+}
+EXPORT_SYMBOL_GPL(wakeup_source_prepare);
+
+/**
+ * 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 = kmalloc(sizeof(*ws), GFP_KERNEL);
+	if (!ws)
+		return NULL;
+
+	wakeup_source_prepare(ws, name ? kstrdup(name, GFP_KERNEL) : NULL);
+	return ws;
+}
+EXPORT_SYMBOL_GPL(wakeup_source_create);
+
+/**
+ * wakeup_source_drop - Prepare a struct wakeup_source object for destruction.
+ * @ws: Wakeup source to prepare for destruction.
+ *
+ * Callers must ensure that __pm_stay_awake() or __pm_wakeup_event() will never
+ * be run in parallel with this function for the same wakeup source object.
+ */
+void wakeup_source_drop(struct wakeup_source *ws)
+{
+	if (!ws)
+		return;
+
+	del_timer_sync(&ws->timer);
+	__pm_relax(ws);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_drop);
+
+/**
+ * wakeup_source_destroy - Destroy a struct wakeup_source object.
+ * @ws: Wakeup source to destroy.
+ *
+ * Use only for wakeup source objects created with wakeup_source_create().
+ */
+void wakeup_source_destroy(struct wakeup_source *ws)
+{
+	if (!ws)
+		return;
+
+	wakeup_source_drop(ws);
+	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)
+{
+	unsigned long flags;
+
+	if (WARN_ON(!ws))
+		return;
+
+	spin_lock_init(&ws->lock);
+	setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws);
+	ws->active = false;
+	ws->last_time = ktime_get();
+
+	spin_lock_irqsave(&events_lock, flags);
+	list_add_rcu(&ws->entry, &wakeup_sources);
+	spin_unlock_irqrestore(&events_lock, flags);
+}
+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)
+{
+	unsigned long flags;
+
+	if (WARN_ON(!ws))
+		return;
+
+	spin_lock_irqsave(&events_lock, flags);
+	list_del_rcu(&ws->entry);
+	spin_unlock_irqrestore(&events_lock, flags);
+	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)
+{
+	if (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.  Also, devices that don't generate their
+ * own wakeup requests but merely forward requests from one bus to another
+ * (like PCI bridges) should have wakeup enabled by default.
+ */
+int device_init_wakeup(struct device *dev, bool enable)
+{
+	int ret = 0;
+
+	if (!dev)
+		return -EINVAL;
+
+	if (enable) {
+		device_set_wakeup_capable(dev, true);
+		ret = device_wakeup_enable(dev);
+	} else {
+		if (dev->power.can_wakeup)
+			device_wakeup_disable(dev);
+
+		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)
+{
+	unsigned int cec;
+
+	/*
+	 * active wakeup source should bring the system
+	 * out of PM_SUSPEND_FREEZE state
+	 */
+	freeze_wake();
+
+	ws->active = true;
+	ws->active_count++;
+	ws->last_time = ktime_get();
+	if (ws->autosleep_enabled)
+		ws->start_prevent_time = ws->last_time;
+
+	/* Increment the counter of events in progress. */
+	cec = atomic_inc_return(&combined_event_count);
+
+	trace_wakeup_source_activate(ws->name, cec);
+}
+
+/**
+ * wakeup_source_report_event - Report wakeup event using the given source.
+ * @ws: Wakeup source to report the event for.
+ */
+static void wakeup_source_report_event(struct wakeup_source *ws)
+{
+	ws->event_count++;
+	/* This is racy, but the counter is approximate anyway. */
+	if (events_check_enabled)
+		ws->wakeup_count++;
+
+	if (!ws->active)
+		wakeup_source_activate(ws);
+}
+
+/**
+ * __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);
+
+	wakeup_source_report_event(ws);
+	del_timer(&ws->timer);
+	ws->timer_expires = 0;
+
+	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);
+
+#ifdef CONFIG_PM_AUTOSLEEP
+static void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now)
+{
+	ktime_t delta = ktime_sub(now, ws->start_prevent_time);
+	ws->prevent_sleep_time = ktime_add(ws->prevent_sleep_time, delta);
+}
+#else
+static inline void update_prevent_sleep_time(struct wakeup_source *ws,
+					     ktime_t now) {}
+#endif
+
+/**
+ * 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)
+{
+	unsigned int cnt, inpr, cec;
+	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;
+
+	ws->last_time = now;
+	del_timer(&ws->timer);
+	ws->timer_expires = 0;
+
+	if (ws->autosleep_enabled)
+		update_prevent_sleep_time(ws, now);
+
+	/*
+	 * Increment the counter of registered wakeup events and decrement the
+	 * couter of wakeup events in progress simultaneously.
+	 */
+	cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count);
+	trace_wakeup_source_deactivate(ws->name, cec);
+
+	split_counters(&cnt, &inpr);
+	if (!inpr && waitqueue_active(&wakeup_count_wait_queue))
+		wake_up(&wakeup_count_wait_queue);
+}
+
+/**
+ * __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 wakeup_source_deactivate() for the wakeup source whose address is stored
+ * in @data if it is currently active and its timer has not been canceled and
+ * the expiration time of the timer is not in future.
+ */
+static void pm_wakeup_timer_fn(unsigned long data)
+{
+	struct wakeup_source *ws = (struct wakeup_source *)data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	if (ws->active && ws->timer_expires
+	    && time_after_eq(jiffies, ws->timer_expires)) {
+		wakeup_source_deactivate(ws);
+		ws->expire_count++;
+	}
+
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+
+/**
+ * __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);
+
+	wakeup_source_report_event(ws);
+
+	if (!msec) {
+		wakeup_source_deactivate(ws);
+		goto unlock;
+	}
+
+	expires = jiffies + msecs_to_jiffies(msec);
+	if (!expires)
+		expires = 1;
+
+	if (!ws->timer_expires || 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);
+
+void pm_print_active_wakeup_sources(void)
+{
+	struct wakeup_source *ws;
+	int active = 0;
+	struct wakeup_source *last_activity_ws = NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		if (ws->active) {
+			pr_info("active wakeup source: %s\n", ws->name);
+			active = 1;
+		} else if (!active &&
+			   (!last_activity_ws ||
+			    ktime_to_ns(ws->last_time) >
+			    ktime_to_ns(last_activity_ws->last_time))) {
+			last_activity_ws = ws;
+		}
+	}
+
+	if (!active && last_activity_ws)
+		pr_info("last active wakeup source: %s\n",
+			last_activity_ws->name);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources);
+
+/**
+ * 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) {
+		pr_info("PM: Wakeup pending, aborting suspend\n");
+		pm_print_active_wakeup_sources();
+	}
+
+	return ret || pm_abort_suspend;
+}
+
+void pm_system_wakeup(void)
+{
+	pm_abort_suspend = true;
+	freeze_wake();
+}
+EXPORT_SYMBOL_GPL(pm_system_wakeup);
+
+void pm_wakeup_clear(void)
+{
+	pm_abort_suspend = false;
+}
+
+/**
+ * pm_get_wakeup_count - Read the number of registered wakeup events.
+ * @count: Address to store the value at.
+ * @block: Whether or not to block.
+ *
+ * Store the number of registered wakeup events at the address in @count.  If
+ * @block is set, block until the current number of wakeup events being
+ * processed is zero.
+ *
+ * Return 'false' if the current number of wakeup events being processed is
+ * nonzero.  Otherwise return 'true'.
+ */
+bool pm_get_wakeup_count(unsigned int *count, bool block)
+{
+	unsigned int cnt, inpr;
+
+	if (block) {
+		DEFINE_WAIT(wait);
+
+		for (;;) {
+			prepare_to_wait(&wakeup_count_wait_queue, &wait,
+					TASK_INTERRUPTIBLE);
+			split_counters(&cnt, &inpr);
+			if (inpr == 0 || signal_pending(current))
+				break;
+
+			schedule();
+		}
+		finish_wait(&wakeup_count_wait_queue, &wait);
+	}
+
+	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;
+	unsigned long flags;
+
+	events_check_enabled = false;
+	spin_lock_irqsave(&events_lock, flags);
+	split_counters(&cnt, &inpr);
+	if (cnt == count && inpr == 0) {
+		saved_count = count;
+		events_check_enabled = true;
+	}
+	spin_unlock_irqrestore(&events_lock, flags);
+	return events_check_enabled;
+}
+
+#ifdef CONFIG_PM_AUTOSLEEP
+/**
+ * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources.
+ * @enabled: Whether to set or to clear the autosleep_enabled flags.
+ */
+void pm_wakep_autosleep_enabled(bool set)
+{
+	struct wakeup_source *ws;
+	ktime_t now = ktime_get();
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		spin_lock_irq(&ws->lock);
+		if (ws->autosleep_enabled != set) {
+			ws->autosleep_enabled = set;
+			if (ws->active) {
+				if (set)
+					ws->start_prevent_time = now;
+				else
+					update_prevent_sleep_time(ws, now);
+			}
+		}
+		spin_unlock_irq(&ws->lock);
+	}
+	rcu_read_unlock();
+}
+#endif /* CONFIG_PM_AUTOSLEEP */
+
+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;
+	ktime_t prevent_sleep_time;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	total_time = ws->total_time;
+	max_time = ws->max_time;
+	prevent_sleep_time = ws->prevent_sleep_time;
+	active_count = ws->active_count;
+	if (ws->active) {
+		ktime_t now = ktime_get();
+
+		active_time = ktime_sub(now, ws->last_time);
+		total_time = ktime_add(total_time, active_time);
+		if (active_time.tv64 > max_time.tv64)
+			max_time = active_time;
+
+		if (ws->autosleep_enabled)
+			prevent_sleep_time = ktime_add(prevent_sleep_time,
+				ktime_sub(now, ws->start_prevent_time));
+	} else {
+		active_time = ktime_set(0, 0);
+	}
+
+	seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n",
+		   ws->name, active_count, ws->event_count,
+		   ws->wakeup_count, ws->expire_count,
+		   ktime_to_ms(active_time), ktime_to_ms(total_time),
+		   ktime_to_ms(max_time), ktime_to_ms(ws->last_time),
+		   ktime_to_ms(prevent_sleep_time));
+
+	spin_unlock_irqrestore(&ws->lock, flags);
+
+	return 0;
+}
+
+/**
+ * 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\twakeup_count\t"
+		"expire_count\tactive_since\ttotal_time\tmax_time\t"
+		"last_change\tprevent_suspend_time\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);