Fixed MTP to work with TWRP

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

drivers/base/power/clock_ops.c

@@ -0,0 +1,516 @@
+/*
+ * 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/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
+ * @clk: The clock being enabled.
+ */
+static inline int __pm_clk_enable(struct device *dev, struct clk *clk)
+{
+	int ret = clk_enable(clk);
+	if (ret)
+		dev_err(dev, "%s: failed to enable clk %p, error %d\n",
+			__func__, 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)
+{
+	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);
+	}
+}
+
+/**
+ * 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)
+{
+	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) {
+		dev_err(dev, "Not enough memory for clock entry.\n");
+		return -ENOMEM;
+	}
+
+	if (con_id) {
+		ce->con_id = kstrdup(con_id, GFP_KERNEL);
+		if (!ce->con_id) {
+			dev_err(dev,
+				"Not enough memory for clock connection ID.\n");
+			kfree(ce);
+			return -ENOMEM;
+		}
+	}
+
+	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_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);
+	}
+}
+
+#endif /* CONFIG_PM */
+
+#ifdef CONFIG_PM_RUNTIME
+
+/**
+ * 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;
+	int ret;
+
+	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) {
+		if (ce->status < PCE_STATUS_ERROR) {
+			ret = __pm_clk_enable(dev, ce->clk);
+			if (!ret)
+				ce->status = PCE_STATUS_ENABLED;
+		}
+	}
+
+	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_RUNTIME */
+
+#ifdef CONFIG_PM
+
+/**
+ * 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 there is no driver, the clocks are already disabled. */
+	if (!psd || !dev->driver)
+		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;
+	int ret;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	/* If there is no driver, the clocks should remain disabled. */
+	if (!psd || !dev->driver)
+		return 0;
+
+	spin_lock_irqsave(&psd->lock, flags);
+
+	list_for_each_entry(ce, &psd->clock_list, node) {
+		if (ce->status < PCE_STATUS_ERROR) {
+			ret = __pm_clk_enable(dev, ce->clk);
+			if (!ret)
+				ce->status = PCE_STATUS_ENABLED;
+		}
+	}
+
+	spin_unlock_irqrestore(&psd->lock, flags);
+
+	return 0;
+}
+
+#endif /* 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_RUNTIME */
+
+/**
+ * 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);
+}

drivers/base/power/common.c

@@ -0,0 +1,136 @@
+/*
+ * 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 1 if a new object has been created, otherwise
+ * return 0 or 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.  Return 1 if that happens or 0
+ * otherwise.
+ */
+int dev_pm_put_subsys_data(struct device *dev)
+{
+	struct pm_subsys_data *psd;
+	int ret = 1;
+
+	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;
+		ret = 0;
+	}
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+	kfree(psd);
+
+	return ret;
+}
+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);

drivers/base/power/domain_governor.c

@@ -0,0 +1,250 @@
+/*
+ * 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>
+
+#ifdef CONFIG_PM_RUNTIME
+
+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;
+}
+
+#else /* !CONFIG_PM_RUNTIME */
+
+static inline bool default_stop_ok(struct device *dev) { return false; }
+
+#define default_power_down_ok	NULL
+#define always_on_power_down_ok	NULL
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+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,
+};

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 */

drivers/base/power/opp.c

@@ -0,0 +1,678 @@
+/*
+ * 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.
+ * @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
+ * @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;
+	unsigned long rate;
+	unsigned long u_volt;
+
+	struct device_opp *dev_opp;
+	struct rcu_head 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
+ * @head:	notifier head to notify the OPP availability changes.
+ * @opp_list:	list of opps
+ *
+ * This is an internal data structure maintaining the link to opps attached to
+ * a device. This structure is not meant to be shared to users as it is
+ * meant for book keeping and private to OPP library
+ */
+struct device_opp {
+	struct list_head node;
+
+	struct device *dev;
+	struct srcu_notifier_head 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);
+
+/**
+ * find_device_opp() - find device_opp struct using device pointer
+ * @dev:	device pointer used to lookup device OPPs
+ *
+ * Search list of device OPPs for one containing matching device. Does a RCU
+ * reader operation to grab the pointer needed.
+ *
+ * Returns pointer to 'struct device_opp' if found, otherwise -ENODEV or
+ * -EINVAL based on type of error.
+ *
+ * Locking: This function must be called under rcu_read_lock(). device_opp
+ * is a RCU protected pointer. This means that device_opp is valid as long
+ * as we are under RCU lock.
+ */
+static struct device_opp *find_device_opp(struct device *dev)
+{
+	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+
+	if (unlikely(IS_ERR_OR_NULL(dev))) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+
+	list_for_each_entry_rcu(tmp_dev_opp, &dev_opp_list, node) {
+		if (tmp_dev_opp->dev == dev) {
+			dev_opp = tmp_dev_opp;
+			break;
+		}
+	}
+
+	return dev_opp;
+}
+
+/**
+ * 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;
+
+	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;
+
+	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
+ *
+ * This function returns the number of available opps if there are any,
+ * else returns 0 if none or the corresponding error value.
+ *
+ * Locking: This function must be called under rcu_read_lock(). This function
+ * internally references two RCU protected structures: device_opp and opp which
+ * are safe as long as we are under a common RCU locked section.
+ */
+int dev_pm_opp_get_opp_count(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *temp_opp;
+	int count = 0;
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int r = PTR_ERR(dev_opp);
+		dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+		return r;
+	}
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available)
+			count++;
+	}
+
+	return count;
+}
+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
+ *
+ * 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);
+
+	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.
+ *
+ * Returns 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);
+
+	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.
+ *
+ * Returns 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);
+
+	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);
+
+/**
+ * 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)
+{
+	struct device_opp *dev_opp = NULL;
+	struct dev_pm_opp *opp, *new_opp;
+	struct list_head *head;
+
+	/* allocate new OPP node */
+	new_opp = kzalloc(sizeof(*new_opp), GFP_KERNEL);
+	if (!new_opp) {
+		dev_warn(dev, "%s: Unable to create new OPP node\n", __func__);
+		return -ENOMEM;
+	}
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Check for existing list for 'dev' */
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		/*
+		 * Allocate a new device OPP table. In the infrequent case
+		 * where a new device is needed to be added, we pay this
+		 * penalty.
+		 */
+		dev_opp = kzalloc(sizeof(struct device_opp), GFP_KERNEL);
+		if (!dev_opp) {
+			mutex_unlock(&dev_opp_list_lock);
+			kfree(new_opp);
+			dev_warn(dev,
+				"%s: Unable to create device OPP structure\n",
+				__func__);
+			return -ENOMEM;
+		}
+
+		dev_opp->dev = dev;
+		srcu_init_notifier_head(&dev_opp->head);
+		INIT_LIST_HEAD(&dev_opp->opp_list);
+
+		/* Secure the device list modification */
+		list_add_rcu(&dev_opp->node, &dev_opp_list);
+	}
+
+	/* populate the opp table */
+	new_opp->dev_opp = dev_opp;
+	new_opp->rate = freq;
+	new_opp->u_volt = u_volt;
+	new_opp->available = true;
+
+	/*
+	 * Insert new OPP in order of increasing frequency
+	 * 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) {
+		int 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);
+		mutex_unlock(&dev_opp_list_lock);
+		kfree(new_opp);
+		return ret;
+	}
+
+	list_add_rcu(&new_opp->node, head);
+	mutex_unlock(&dev_opp_list_lock);
+
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_ADD, new_opp);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_add);
+
+/**
+ * opp_set_availability() - helper to set the availability of an opp
+ * @dev:		device for which we do this operation
+ * @freq:		OPP frequency to modify availability
+ * @availability_req:	availability status requested for this opp
+ *
+ * Set the availability of an OPP with an RCU operation, opp_{enable,disable}
+ * share a common logic which is isolated here.
+ *
+ * Returns -EINVAL for bad pointers, -ENOMEM if no memory available for the
+ * copy operation, returns 0 if no modifcation was done OR modification was
+ * successful.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks to
+ * keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+static int opp_set_availability(struct device *dev, unsigned long freq,
+		bool availability_req)
+{
+	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+	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) {
+		dev_warn(dev, "%s: Unable to create OPP\n", __func__);
+		return -ENOMEM;
+	}
+
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Find the device_opp */
+	list_for_each_entry(tmp_dev_opp, &dev_opp_list, node) {
+		if (dev == tmp_dev_opp->dev) {
+			dev_opp = tmp_dev_opp;
+			break;
+		}
+	}
+	if (IS_ERR(dev_opp)) {
+		r = PTR_ERR(dev_opp);
+		dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
+		goto unlock;
+	}
+
+	/* Do we have the frequency? */
+	list_for_each_entry(tmp_opp, &dev_opp->opp_list, node) {
+		if (tmp_opp->rate == freq) {
+			opp = tmp_opp;
+			break;
+		}
+	}
+	if (IS_ERR(opp)) {
+		r = PTR_ERR(opp);
+		goto unlock;
+	}
+
+	/* Is update really needed? */
+	if (opp->available == availability_req)
+		goto unlock;
+	/* copy the old data over */
+	*new_opp = *opp;
+
+	/* plug in new node */
+	new_opp->available = availability_req;
+
+	list_replace_rcu(&opp->node, &new_opp->node);
+	mutex_unlock(&dev_opp_list_lock);
+	kfree_rcu(opp, head);
+
+	/* Notify the change of the OPP availability */
+	if (availability_req)
+		srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_ENABLE,
+					 new_opp);
+	else
+		srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_DISABLE,
+					 new_opp);
+
+	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.
+ */
+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.
+ */
+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.
+ */
+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->head;
+}
+
+#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.
+ */
+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 (dev_pm_opp_add(dev, freq, volt))
+			dev_warn(dev, "%s: Failed to add OPP %ld\n",
+				 __func__, freq);
+		nr -= 2;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_init_opp_table);
+#endif

drivers/base/power/power.h

@@ -0,0 +1,109 @@
+#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_RUNTIME
+
+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);
+
+#else /* !CONFIG_PM_RUNTIME */
+
+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) {}
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+#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 *);
+extern void device_pm_move_first(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) {}
+static inline void device_pm_move_first(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);
+}
+
+#ifdef CONFIG_PM
+
+/*
+ * sysfs.c
+ */
+
+extern int dpm_sysfs_add(struct device *dev);
+extern void dpm_sysfs_remove(struct device *dev);
+extern void rpm_sysfs_remove(struct device *dev);
+extern int wakeup_sysfs_add(struct device *dev);
+extern void wakeup_sysfs_remove(struct device *dev);
+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 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

drivers/base/power/qos.c

@@ -0,0 +1,886 @@
+/*
+ * 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;
+
+	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)
+{
+	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);
+
+#ifdef CONFIG_PM_RUNTIME
+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;
+}
+#else /* !CONFIG_PM_RUNTIME */
+static void __dev_pm_qos_hide_latency_limit(struct device *dev) {}
+static void __dev_pm_qos_hide_flags(struct device *dev) {}
+#endif /* CONFIG_PM_RUNTIME */

drivers/base/power/sysfs.c

@@ -0,0 +1,770 @@
+/*
+ * 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);
+
+#ifdef CONFIG_PM_RUNTIME
+static const char ctrl_auto[] = "auto";
+static const char ctrl_on[] = "on";
+
+static ssize_t control_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "%s\n",
+				dev->power.runtime_auto ? ctrl_auto : ctrl_on);
+}
+
+static ssize_t control_store(struct device * dev, struct device_attribute *attr,
+			     const char * buf, size_t n)
+{
+	char *cp;
+	int len = n;
+
+	cp = memchr(buf, '\n', n);
+	if (cp)
+		len = cp - buf;
+	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);
+#endif /* CONFIG_PM_RUNTIME */
+
+#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
+#ifdef CONFIG_PM_RUNTIME
+
+static ssize_t rtpm_usagecount_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", atomic_read(&dev->power.usage_count));
+}
+
+static ssize_t rtpm_children_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", dev->power.ignore_children ?
+		0 : atomic_read(&dev->power.child_count));
+}
+
+static ssize_t rtpm_enabled_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	if ((dev->power.disable_depth) && (dev->power.runtime_auto == false))
+		return sprintf(buf, "disabled & forbidden\n");
+	else if (dev->power.disable_depth)
+		return sprintf(buf, "disabled\n");
+	else if (dev->power.runtime_auto == false)
+		return sprintf(buf, "forbidden\n");
+	return sprintf(buf, "enabled\n");
+}
+
+static DEVICE_ATTR(runtime_usage, 0444, rtpm_usagecount_show, NULL);
+static DEVICE_ATTR(runtime_active_kids, 0444, rtpm_children_show, NULL);
+static DEVICE_ATTR(runtime_enabled, 0444, rtpm_enabled_show, NULL);
+
+#endif
+
+#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
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
+
+static struct attribute *power_attrs[] = {
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+#ifdef CONFIG_PM_SLEEP
+	&dev_attr_async.attr,
+#endif
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_runtime_status.attr,
+	&dev_attr_runtime_usage.attr,
+	&dev_attr_runtime_active_kids.attr,
+	&dev_attr_runtime_enabled.attr,
+#endif
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
+	NULL,
+};
+static struct attribute_group pm_attr_group = {
+	.name	= power_group_name,
+	.attrs	= power_attrs,
+};
+
+static struct attribute *wakeup_attrs[] = {
+#ifdef CONFIG_PM_SLEEP
+	&dev_attr_wakeup.attr,
+	&dev_attr_wakeup_count.attr,
+	&dev_attr_wakeup_active_count.attr,
+	&dev_attr_wakeup_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[] = {
+#ifdef CONFIG_PM_RUNTIME
+#ifndef CONFIG_PM_ADVANCED_DEBUG
+	&dev_attr_runtime_status.attr,
+#endif
+	&dev_attr_control.attr,
+	&dev_attr_runtime_suspended_time.attr,
+	&dev_attr_runtime_active_time.attr,
+	&dev_attr_autosuspend_delay_ms.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	NULL,
+};
+static struct attribute_group pm_runtime_attr_group = {
+	.name	= power_group_name,
+	.attrs	= runtime_attrs,
+};
+
+static struct attribute *pm_qos_resume_latency_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_pm_qos_resume_latency_us.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	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[] = {
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_pm_qos_latency_tolerance_us.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	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[] = {
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_pm_qos_no_power_off.attr,
+	&dev_attr_pm_qos_remote_wakeup.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	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);
+}

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/resume-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_resume_trace(const void *tracedata, unsigned int user)
+{
+	unsigned short lineno = *(unsigned short *)tracedata;
+	const char *file = *(const char **)(tracedata + 2);
+	unsigned int user_hash_value, file_hash_value;
+
+	user_hash_value = user % USERHASH;
+	file_hash_value = hash_string(lineno, file, FILEHASH);
+	set_magic_time(user_hash_value, file_hash_value, dev_hash_value);
+}
+EXPORT_SYMBOL(generate_resume_trace);
+
+extern char __tracedata_start, __tracedata_end;
+static int show_file_hash(unsigned int value)
+{
+	int match;
+	char *tracedata;
+
+	match = 0;
+	for (tracedata = &__tracedata_start ; tracedata < &__tracedata_end ;
+			tracedata += 2 + sizeof(unsigned long)) {
+		unsigned short lineno = *(unsigned short *)tracedata;
+		const char *file = *(const char **)(tracedata + 2);
+		unsigned int hash = hash_string(lineno, file, FILEHASH);
+		if (hash != value)
+			continue;
+		pr_info("  hash matches %s:%u\n", file, lineno);
+		match++;
+	}
+	return match;
+}
+
+static int show_dev_hash(unsigned int value)
+{
+	int match = 0;
+	struct list_head *entry;
+
+	device_pm_lock();
+	entry = dpm_list.prev;
+	while (entry != &dpm_list) {
+		struct device * dev = to_device(entry);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH);
+		if (hash == value) {
+			dev_info(dev, "hash matches\n");
+			match++;
+		}
+		entry = entry->prev;
+	}
+	device_pm_unlock();
+	return match;
+}
+
+static unsigned int hash_value_early_read;
+
+int show_trace_dev_match(char *buf, size_t size)
+{
+	unsigned int value = hash_value_early_read / (USERHASH * FILEHASH);
+	int ret = 0;
+	struct list_head *entry;
+
+	/*
+	 * It's possible that multiple devices will match the hash and we can't
+	 * tell which is the culprit, so it's best to output them all.
+	 */
+	device_pm_lock();
+	entry = dpm_list.prev;
+	while (size && entry != &dpm_list) {
+		struct device *dev = to_device(entry);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev),
+						DEVHASH);
+		if (hash == value) {
+			int len = snprintf(buf, size, "%s\n",
+					    dev_driver_string(dev));
+			if (len > size)
+				len = size;
+			buf += len;
+			ret += len;
+			size -= len;
+		}
+		entry = entry->prev;
+	}
+	device_pm_unlock();
+	return ret;
+}
+
+static int early_resume_init(void)
+{
+	hash_value_early_read = read_magic_time();
+	return 0;
+}
+
+static int late_resume_init(void)
+{
+	unsigned int val = hash_value_early_read;
+	unsigned int user, file, dev;
+
+	user = val % USERHASH;
+	val = val / USERHASH;
+	file = val % FILEHASH;
+	val = val / FILEHASH;
+	dev = val /* % DEVHASH */;
+
+	pr_info("  Magic number: %d:%d:%d\n", user, file, dev);
+	show_file_hash(file);
+	show_dev_hash(dev);
+	return 0;
+}
+
+core_initcall(early_resume_init);
+late_initcall(late_resume_init);