KVM: SEV: Do cache maintenance on the source VM during intra-host migrationgrafted

Manually perform cache maintenance on the source VM during intra-host
migration to ensure no stale data is left in CPU caches after the VM is
destroyed.  Because the source VM is "converted" to a non-SEV VM, KVM's
memory reclaim flows won't trigger cache maintenance, e.g. when all guest
memory is reclaimed in response to detaching from the mmu_notifier.

Note, relying on the destination VM to do cache maintenance isn't an option
as KVM doesn't require identical guest memory configurations, i.e. the
source VM may have access to memory that the destination VM does not.
Enforcing equivalent memory configurations is infeasible, as it would
require a *deep* comparison of memslots, e.g. to verify that not only are
the memslot identical, but what the memslots point at is also identical.

Fixes: b56639318bb2 ("KVM: SEV: Add support for SEV intra host migration")
Cc: stable@vger.kernel.org
Reported-by: Stefan Teodorescu <fane@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20260923163721.1584779-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

15 files changed, 10521 insertions, 0 deletions

diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
new file mode 100644
index 000000000..2989e42d0
--- /dev/null
+++ b/drivers/base/power/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o runtime.o wakeirq.o
+obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o wakeup_stats.o
+obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
+obj-$(CONFIG_HAVE_CLK)	+= clock_ops.o
+obj-$(CONFIG_PM_QOS_KUNIT_TEST) += qos-test.o
+obj-$(CONFIG_PM_RUNTIME_KUNIT_TEST) += runtime-test.o
+
+ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
new file mode 100644
index 000000000..59bb37e82
--- /dev/null
+++ b/drivers/base/power/clock_ops.c
@@ -0,0 +1,732 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * drivers/base/power/clock_ops.c - Generic clock manipulation PM callbacks
+ *
+ * Copyright (c) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/pm.h>
+#include <linux/pm_clock.h>
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/of_clk.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
+
+#ifdef CONFIG_PM_CLK
+
+enum pce_status {
+	PCE_STATUS_NONE = 0,
+	PCE_STATUS_ACQUIRED,
+	PCE_STATUS_PREPARED,
+	PCE_STATUS_ENABLED,
+	PCE_STATUS_ERROR,
+};
+
+struct pm_clock_entry {
+	struct list_head node;
+	char *con_id;
+	struct clk *clk;
+	enum pce_status status;
+	bool enabled_when_prepared;
+};
+
+/**
+ * pm_clk_list_lock - ensure exclusive access for modifying the PM clock
+ *		      entry list.
+ * @psd: pm_subsys_data instance corresponding to the PM clock entry list
+ *	 and clk_op_might_sleep count to be modified.
+ *
+ * Get exclusive access before modifying the PM clock entry list and the
+ * clock_op_might_sleep count to guard against concurrent modifications.
+ * This also protects against a concurrent clock_op_might_sleep and PM clock
+ * entry list usage in pm_clk_suspend()/pm_clk_resume() that may or may not
+ * happen in atomic context, hence both the mutex and the spinlock must be
+ * taken here.
+ */
+static void pm_clk_list_lock(struct pm_subsys_data *psd)
+	__acquires(&psd->lock)
+{
+	mutex_lock(&psd->clock_mutex);
+	spin_lock_irq(&psd->lock);
+}
+
+/**
+ * pm_clk_list_unlock - counterpart to pm_clk_list_lock().
+ * @psd: the same pm_subsys_data instance previously passed to
+ *	 pm_clk_list_lock().
+ */
+static void pm_clk_list_unlock(struct pm_subsys_data *psd)
+	__releases(&psd->lock)
+{
+	spin_unlock_irq(&psd->lock);
+	mutex_unlock(&psd->clock_mutex);
+}
+
+/**
+ * pm_clk_op_lock - ensure exclusive access for performing clock operations.
+ * @psd: pm_subsys_data instance corresponding to the PM clock entry list
+ *	 and clk_op_might_sleep count being used.
+ * @flags: stored irq flags.
+ * @fn: string for the caller function's name.
+ *
+ * This is used by pm_clk_suspend() and pm_clk_resume() to guard
+ * against concurrent modifications to the clock entry list and the
+ * clock_op_might_sleep count. If clock_op_might_sleep is != 0 then
+ * only the mutex can be locked and those functions can only be used in
+ * non atomic context. If clock_op_might_sleep == 0 then these functions
+ * may be used in any context and only the spinlock can be locked.
+ * Returns -EINVAL if called in atomic context when clock ops might sleep.
+ */
+static int pm_clk_op_lock(struct pm_subsys_data *psd, unsigned long *flags,
+			  const char *fn)
+	/* sparse annotations don't work here as exit state isn't static */
+{
+	bool atomic_context = in_atomic() || irqs_disabled();
+
+try_again:
+	spin_lock_irqsave(&psd->lock, *flags);
+	if (!psd->clock_op_might_sleep) {
+		/* the __release is there to work around sparse limitations */
+		__release(&psd->lock);
+		return 0;
+	}
+
+	/* bail out if in atomic context */
+	if (atomic_context) {
+		pr_err("%s: atomic context with clock_ops_might_sleep = %d",
+		       fn, psd->clock_op_might_sleep);
+		spin_unlock_irqrestore(&psd->lock, *flags);
+		might_sleep();
+		return -EPERM;
+	}
+
+	/* we must switch to the mutex */
+	spin_unlock_irqrestore(&psd->lock, *flags);
+	mutex_lock(&psd->clock_mutex);
+
+	/*
+	 * There was a possibility for psd->clock_op_might_sleep
+	 * to become 0 above. Keep the mutex only if not the case.
+	 */
+	if (likely(psd->clock_op_might_sleep))
+		return 0;
+
+	mutex_unlock(&psd->clock_mutex);
+	goto try_again;
+}
+
+/**
+ * pm_clk_op_unlock - counterpart to pm_clk_op_lock().
+ * @psd: the same pm_subsys_data instance previously passed to
+ *	 pm_clk_op_lock().
+ * @flags: irq flags provided by pm_clk_op_lock().
+ */
+static void pm_clk_op_unlock(struct pm_subsys_data *psd, unsigned long *flags)
+	/* sparse annotations don't work here as entry state isn't static */
+{
+	if (psd->clock_op_might_sleep) {
+		mutex_unlock(&psd->clock_mutex);
+	} else {
+		/* the __acquire is there to work around sparse limitations */
+		__acquire(&psd->lock);
+		spin_unlock_irqrestore(&psd->lock, *flags);
+	}
+}
+
+/**
+ * __pm_clk_enable - Enable a clock, reporting any errors
+ * @dev: The device for the given clock
+ * @ce: PM clock entry corresponding to the clock.
+ */
+static inline void __pm_clk_enable(struct device *dev, struct pm_clock_entry *ce)
+{
+	int ret;
+
+	switch (ce->status) {
+	case PCE_STATUS_ACQUIRED:
+		ret = clk_prepare_enable(ce->clk);
+		break;
+	case PCE_STATUS_PREPARED:
+		ret = clk_enable(ce->clk);
+		break;
+	default:
+		return;
+	}
+	if (!ret)
+		ce->status = PCE_STATUS_ENABLED;
+	else
+		dev_err(dev, "%s: failed to enable clk %p, error %d\n",
+			__func__, ce->clk, ret);
+}
+
+/**
+ * pm_clk_acquire - Acquire a device clock.
+ * @dev: Device whose clock is to be acquired.
+ * @ce: PM clock entry corresponding to the clock.
+ */
+static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
+{
+	if (!ce->clk)
+		ce->clk = clk_get(dev, ce->con_id);
+	if (IS_ERR(ce->clk)) {
+		ce->status = PCE_STATUS_ERROR;
+		return;
+	} else if (clk_is_enabled_when_prepared(ce->clk)) {
+		/* we defer preparing the clock in that case */
+		ce->status = PCE_STATUS_ACQUIRED;
+		ce->enabled_when_prepared = true;
+	} else if (clk_prepare(ce->clk)) {
+		ce->status = PCE_STATUS_ERROR;
+		dev_err(dev, "clk_prepare() failed\n");
+		return;
+	} else {
+		ce->status = PCE_STATUS_PREPARED;
+	}
+	dev_dbg(dev, "Clock %pC con_id %s managed by runtime PM.\n",
+		ce->clk, ce->con_id);
+}
+
+static int __pm_clk_add(struct device *dev, const char *con_id,
+			struct clk *clk)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!psd)
+		return -EINVAL;
+
+	ce = kzalloc_obj(*ce);
+	if (!ce)
+		return -ENOMEM;
+
+	if (con_id) {
+		ce->con_id = kstrdup(con_id, GFP_KERNEL);
+		if (!ce->con_id) {
+			kfree(ce);
+			return -ENOMEM;
+		}
+	} else {
+		if (IS_ERR(clk)) {
+			kfree(ce);
+			return -ENOENT;
+		}
+		ce->clk = clk;
+	}
+
+	pm_clk_acquire(dev, ce);
+
+	pm_clk_list_lock(psd);
+	list_add_tail(&ce->node, &psd->clock_list);
+	if (ce->enabled_when_prepared)
+		psd->clock_op_might_sleep++;
+	pm_clk_list_unlock(psd);
+	return 0;
+}
+
+/**
+ * pm_clk_add - Start using a device clock for power management.
+ * @dev: Device whose clock is going to be used for power management.
+ * @con_id: Connection ID of the clock.
+ *
+ * Add the clock represented by @con_id to the list of clocks used for
+ * the power management of @dev.
+ */
+int pm_clk_add(struct device *dev, const char *con_id)
+{
+	return __pm_clk_add(dev, con_id, NULL);
+}
+EXPORT_SYMBOL_GPL(pm_clk_add);
+
+/**
+ * pm_clk_add_clk - Start using a device clock for power management.
+ * @dev: Device whose clock is going to be used for power management.
+ * @clk: Clock pointer
+ *
+ * Add the clock to the list of clocks used for the power management of @dev.
+ * The power-management code will take control of the clock reference, so
+ * callers should not call clk_put() on @clk after this function sucessfully
+ * returned.
+ */
+int pm_clk_add_clk(struct device *dev, struct clk *clk)
+{
+	return __pm_clk_add(dev, NULL, clk);
+}
+EXPORT_SYMBOL_GPL(pm_clk_add_clk);
+
+/**
+ * of_pm_clk_add_clks - Start using device clock(s) for power management.
+ * @dev: Device whose clock(s) is going to be used for power management.
+ *
+ * Add a series of clocks described in the 'clocks' device-tree node for
+ * a device to the list of clocks used for the power management of @dev.
+ * On success, returns the number of clocks added. Returns a negative
+ * error code if there are no clocks in the device node for the device
+ * or if adding a clock fails.
+ */
+int of_pm_clk_add_clks(struct device *dev)
+{
+	struct clk **clks;
+	int i, count;
+	int ret;
+
+	if (!dev || !dev->of_node)
+		return -EINVAL;
+
+	count = of_clk_get_parent_count(dev->of_node);
+	if (count <= 0)
+		return -ENODEV;
+
+	clks = kzalloc_objs(*clks, count);
+	if (!clks)
+		return -ENOMEM;
+
+	for (i = 0; i < count; i++) {
+		clks[i] = of_clk_get(dev->of_node, i);
+		if (IS_ERR(clks[i])) {
+			ret = PTR_ERR(clks[i]);
+			goto error;
+		}
+
+		ret = pm_clk_add_clk(dev, clks[i]);
+		if (ret) {
+			clk_put(clks[i]);
+			goto error;
+		}
+	}
+
+	kfree(clks);
+
+	return i;
+
+error:
+	while (i--)
+		pm_clk_remove_clk(dev, clks[i]);
+
+	kfree(clks);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_pm_clk_add_clks);
+
+/**
+ * __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;
+
+	switch (ce->status) {
+	case PCE_STATUS_ENABLED:
+		clk_disable(ce->clk);
+		fallthrough;
+	case PCE_STATUS_PREPARED:
+		clk_unprepare(ce->clk);
+		fallthrough;
+	case PCE_STATUS_ACQUIRED:
+	case PCE_STATUS_ERROR:
+		if (!IS_ERR(ce->clk))
+			clk_put(ce->clk);
+		break;
+	default:
+		break;
+	}
+
+	kfree(ce->con_id);
+	kfree(ce);
+}
+
+/**
+ * pm_clk_remove_clk - Stop using a device clock for power management.
+ * @dev: Device whose clock should not be used for PM any more.
+ * @clk: Clock pointer
+ *
+ * Remove the clock pointed to by @clk from the list of clocks used for
+ * the power management of @dev.
+ */
+void pm_clk_remove_clk(struct device *dev, struct clk *clk)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!psd || !clk)
+		return;
+
+	pm_clk_list_lock(psd);
+
+	list_for_each_entry(ce, &psd->clock_list, node) {
+		if (clk == ce->clk)
+			goto remove;
+	}
+
+	pm_clk_list_unlock(psd);
+	return;
+
+ remove:
+	list_del(&ce->node);
+	if (ce->enabled_when_prepared)
+		psd->clock_op_might_sleep--;
+	pm_clk_list_unlock(psd);
+
+	__pm_clk_remove(ce);
+}
+EXPORT_SYMBOL_GPL(pm_clk_remove_clk);
+
+/**
+ * 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, set the count of clocks that might sleep to 0.
+ */
+void pm_clk_init(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	if (psd) {
+		INIT_LIST_HEAD(&psd->clock_list);
+		mutex_init(&psd->clock_mutex);
+		psd->clock_op_might_sleep = 0;
+	}
+}
+EXPORT_SYMBOL_GPL(pm_clk_init);
+
+/**
+ * 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);
+}
+EXPORT_SYMBOL_GPL(pm_clk_create);
+
+/**
+ * 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);
+
+	pm_clk_list_lock(psd);
+
+	list_for_each_entry_safe_reverse(ce, c, &psd->clock_list, node)
+		list_move(&ce->node, &list);
+	psd->clock_op_might_sleep = 0;
+
+	pm_clk_list_unlock(psd);
+
+	dev_pm_put_subsys_data(dev);
+
+	list_for_each_entry_safe_reverse(ce, c, &list, node) {
+		list_del(&ce->node);
+		__pm_clk_remove(ce);
+	}
+}
+EXPORT_SYMBOL_GPL(pm_clk_destroy);
+
+static void pm_clk_destroy_action(void *data)
+{
+	pm_clk_destroy(data);
+}
+
+int devm_pm_clk_create(struct device *dev)
+{
+	int ret;
+
+	ret = pm_clk_create(dev);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(dev, pm_clk_destroy_action, dev);
+}
+EXPORT_SYMBOL_GPL(devm_pm_clk_create);
+
+/**
+ * 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;
+	int ret;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (!psd)
+		return 0;
+
+	ret = pm_clk_op_lock(psd, &flags, __func__);
+	if (ret)
+		return ret;
+
+	list_for_each_entry_reverse(ce, &psd->clock_list, node) {
+		if (ce->status == PCE_STATUS_ENABLED) {
+			if (ce->enabled_when_prepared) {
+				clk_disable_unprepare(ce->clk);
+				ce->status = PCE_STATUS_ACQUIRED;
+			} else {
+				clk_disable(ce->clk);
+				ce->status = PCE_STATUS_PREPARED;
+			}
+		}
+	}
+
+	pm_clk_op_unlock(psd, &flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pm_clk_suspend);
+
+/**
+ * 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;
+
+	ret = pm_clk_op_lock(psd, &flags, __func__);
+	if (ret)
+		return ret;
+
+	list_for_each_entry(ce, &psd->clock_list, node)
+		__pm_clk_enable(dev, ce);
+
+	pm_clk_op_unlock(psd, &flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pm_clk_resume);
+
+/**
+ * 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_set(dev, 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_set(dev, NULL);
+		pm_clk_destroy(dev);
+		break;
+	}
+
+	return 0;
+}
+
+int pm_clk_runtime_suspend(struct device *dev)
+{
+	int ret;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	ret = pm_generic_runtime_suspend(dev);
+	if (ret) {
+		dev_err(dev, "failed to suspend device\n");
+		return ret;
+	}
+
+	ret = pm_clk_suspend(dev);
+	if (ret) {
+		dev_err(dev, "failed to suspend clock\n");
+		pm_generic_runtime_resume(dev);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pm_clk_runtime_suspend);
+
+int pm_clk_runtime_resume(struct device *dev)
+{
+	int ret;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	ret = pm_clk_resume(dev);
+	if (ret) {
+		dev_err(dev, "failed to resume clock\n");
+		return ret;
+	}
+
+	return pm_generic_runtime_resume(dev);
+}
+EXPORT_SYMBOL_GPL(pm_clk_runtime_resume);
+
+#else /* !CONFIG_PM_CLK */
+
+/**
+ * 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_DRIVER_NOT_BOUND:
+	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_CLK */
+
+/**
+ * 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(const 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);
+}
+EXPORT_SYMBOL_GPL(pm_clk_add_notifier);
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
new file mode 100644
index 000000000..9bef9248a
--- /dev/null
+++ b/drivers/base/power/common.c
@@ -0,0 +1,457 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * drivers/base/power/common.c - Common device power management code.
+ *
+ * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ */
+#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>
+#include <linux/pm_opp.h>
+
+#include "power.h"
+
+/**
+ * dev_pm_get_subsys_data - Create or refcount power.subsys_data for device.
+ * @dev: Device to handle.
+ *
+ * If power.subsys_data is NULL, point it to a new object, otherwise increment
+ * its reference counter.  Return 0 if new object has been created or refcount
+ * increased, otherwise negative error code.
+ */
+int dev_pm_get_subsys_data(struct device *dev)
+{
+	struct pm_subsys_data *psd;
+
+	psd = kzalloc_obj(*psd);
+	if (!psd)
+		return -ENOMEM;
+
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.subsys_data) {
+		dev->power.subsys_data->refcount++;
+	} else {
+		spin_lock_init(&psd->lock);
+		psd->refcount = 1;
+		dev->power.subsys_data = psd;
+		pm_clk_init(dev);
+		psd = NULL;
+	}
+
+	spin_unlock_irq(&dev->power.lock);
+
+	/* kfree() verifies that its argument is nonzero. */
+	kfree(psd);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_get_subsys_data);
+
+/**
+ * dev_pm_put_subsys_data - Drop reference to power.subsys_data.
+ * @dev: Device to handle.
+ *
+ * If the reference counter of power.subsys_data is zero after dropping the
+ * reference, power.subsys_data is removed.
+ */
+void dev_pm_put_subsys_data(struct device *dev)
+{
+	struct pm_subsys_data *psd;
+
+	spin_lock_irq(&dev->power.lock);
+
+	psd = dev_to_psd(dev);
+	if (!psd)
+		goto out;
+
+	if (--psd->refcount == 0)
+		dev->power.subsys_data = NULL;
+	else
+		psd = NULL;
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+	kfree(psd);
+}
+EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
+
+/**
+ * dev_pm_domain_attach - Attach a device to its PM domain.
+ * @dev: Device to attach.
+ * @flags: indicate whether we should power on/off the device on attach/detach
+ *
+ * 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 when it is found that the
+ * device doesn't need a PM domain, else a negative error code.
+ */
+int dev_pm_domain_attach(struct device *dev, u32 flags)
+{
+	int ret;
+
+	if (dev->pm_domain)
+		return 0;
+
+	ret = acpi_dev_pm_attach(dev, !!(flags & PD_FLAG_ATTACH_POWER_ON));
+	if (!ret)
+		ret = genpd_dev_pm_attach(dev);
+
+	if (dev->pm_domain)
+		dev->power.detach_power_off = !!(flags & PD_FLAG_DETACH_POWER_OFF);
+
+	return ret < 0 ? ret : 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach);
+
+/**
+ * dev_pm_domain_attach_by_id - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @index: The index of the PM domain.
+ *
+ * As @dev may only be attached to a single PM domain, the backend PM domain
+ * provider creates a virtual device to attach instead. If attachment succeeds,
+ * the ->detach() callback in the struct dev_pm_domain are assigned by the
+ * corresponding backend attach function, as to deal with detaching of the
+ * created virtual device.
+ *
+ * This function should typically be invoked by a driver during the probe phase,
+ * in case its device requires power management through multiple PM domains. The
+ * driver may benefit from using the received device, to configure device-links
+ * towards its original device. Depending on the use-case and if needed, the
+ * links may be dynamically changed by the driver, which allows it to control
+ * the power to the PM domains independently from each other.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ *
+ * Returns the virtual created device when successfully attached to its PM
+ * domain, NULL in case @dev don't need a PM domain, else an ERR_PTR().
+ * Note that, to detach the returned virtual device, the driver shall call
+ * dev_pm_domain_detach() on it, typically during the remove phase.
+ */
+struct device *dev_pm_domain_attach_by_id(struct device *dev,
+					  unsigned int index)
+{
+	if (dev->pm_domain)
+		return ERR_PTR(-EEXIST);
+
+	return genpd_dev_pm_attach_by_id(dev, index);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id);
+
+/**
+ * dev_pm_domain_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * For a detailed function description, see dev_pm_domain_attach_by_id().
+ */
+struct device *dev_pm_domain_attach_by_name(struct device *dev,
+					    const char *name)
+{
+	if (dev->pm_domain)
+		return ERR_PTR(-EEXIST);
+
+	return genpd_dev_pm_attach_by_name(dev, name);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_name);
+
+/**
+ * dev_pm_domain_attach_list - Associate a device with its PM domains.
+ * @dev: The device used to lookup the PM domains for.
+ * @data: The data used for attaching to the PM domains.
+ * @list: An out-parameter with an allocated list of attached PM domains.
+ *
+ * This function helps to attach a device to its multiple PM domains. The
+ * caller, which is typically a driver's probe function, may provide a list of
+ * names for the PM domains that we should try to attach the device to, but it
+ * may also provide an empty list, in case the attach should be done for all of
+ * the available PM domains.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ *
+ * Returns the number of attached PM domains or a negative error code in case of
+ * a failure. Note that, to detach the list of PM domains, the driver shall call
+ * dev_pm_domain_detach_list(), typically during the remove phase.
+ */
+int dev_pm_domain_attach_list(struct device *dev,
+			      const struct dev_pm_domain_attach_data *data,
+			      struct dev_pm_domain_list **list)
+{
+	struct device_node *np = dev->of_node;
+	struct dev_pm_domain_list *pds;
+	struct device *pd_dev = NULL;
+	int ret, i, num_pds = 0;
+	bool by_id = true;
+	size_t size;
+	u32 pd_flags = data ? data->pd_flags : 0;
+	u32 link_flags = pd_flags & PD_FLAG_NO_DEV_LINK ? 0 :
+			DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME;
+
+	if (dev->pm_domain)
+		return -EEXIST;
+
+	/* For now this is limited to OF based platforms. */
+	if (!np)
+		return 0;
+
+	if (data && data->pd_names) {
+		num_pds = data->num_pd_names;
+		by_id = false;
+	} else {
+		num_pds = of_count_phandle_with_args(np, "power-domains",
+						     "#power-domain-cells");
+	}
+
+	if (num_pds <= 0)
+		return 0;
+
+	pds = kzalloc_obj(*pds);
+	if (!pds)
+		return -ENOMEM;
+
+	size = sizeof(*pds->pd_devs) + sizeof(*pds->pd_links) +
+	       sizeof(*pds->opp_tokens);
+	pds->pd_devs = kcalloc(num_pds, size, GFP_KERNEL);
+	if (!pds->pd_devs) {
+		ret = -ENOMEM;
+		goto free_pds;
+	}
+	pds->pd_links = (void *)(pds->pd_devs + num_pds);
+	pds->opp_tokens = (void *)(pds->pd_links + num_pds);
+
+	if (link_flags && pd_flags & PD_FLAG_DEV_LINK_ON)
+		link_flags |= DL_FLAG_RPM_ACTIVE;
+
+	for (i = 0; i < num_pds; i++) {
+		if (by_id)
+			pd_dev = dev_pm_domain_attach_by_id(dev, i);
+		else
+			pd_dev = dev_pm_domain_attach_by_name(dev,
+							data->pd_names[i]);
+		if (IS_ERR_OR_NULL(pd_dev)) {
+			ret = pd_dev ? PTR_ERR(pd_dev) : -ENODEV;
+			goto err_attach;
+		}
+
+		if (pd_flags & PD_FLAG_REQUIRED_OPP) {
+			struct dev_pm_opp_config config = {
+				.required_dev = pd_dev,
+				.required_dev_index = i,
+			};
+
+			ret = dev_pm_opp_set_config(dev, &config);
+			if (ret < 0)
+				goto err_link;
+
+			pds->opp_tokens[i] = ret;
+		}
+
+		if (link_flags) {
+			struct device_link *link;
+
+			link = device_link_add(dev, pd_dev, link_flags);
+			if (!link) {
+				ret = -ENODEV;
+				goto err_link;
+			}
+
+			pds->pd_links[i] = link;
+		}
+
+		pds->pd_devs[i] = pd_dev;
+	}
+
+	pds->num_pds = num_pds;
+	*list = pds;
+	return num_pds;
+
+err_link:
+	dev_pm_opp_clear_config(pds->opp_tokens[i]);
+	dev_pm_domain_detach(pd_dev, true);
+err_attach:
+	while (--i >= 0) {
+		dev_pm_opp_clear_config(pds->opp_tokens[i]);
+		if (pds->pd_links[i])
+			device_link_del(pds->pd_links[i]);
+		dev_pm_domain_detach(pds->pd_devs[i], true);
+	}
+	kfree(pds->pd_devs);
+free_pds:
+	kfree(pds);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach_list);
+
+/**
+ * devm_pm_domain_detach_list - devres-enabled version of dev_pm_domain_detach_list.
+ * @_list: The list of PM domains to detach.
+ *
+ * This function reverse the actions from devm_pm_domain_attach_list().
+ * it will be invoked during the remove phase from drivers implicitly if driver
+ * uses devm_pm_domain_attach_list() to attach the PM domains.
+ */
+static void devm_pm_domain_detach_list(void *_list)
+{
+	struct dev_pm_domain_list *list = _list;
+
+	dev_pm_domain_detach_list(list);
+}
+
+/**
+ * devm_pm_domain_attach_list - devres-enabled version of dev_pm_domain_attach_list
+ * @dev: The device used to lookup the PM domains for.
+ * @data: The data used for attaching to the PM domains.
+ * @list: An out-parameter with an allocated list of attached PM domains.
+ *
+ * NOTE: this will also handle calling devm_pm_domain_detach_list() for
+ * you during remove phase.
+ *
+ * Returns the number of attached PM domains or a negative error code in case of
+ * a failure.
+ */
+int devm_pm_domain_attach_list(struct device *dev,
+			       const struct dev_pm_domain_attach_data *data,
+			       struct dev_pm_domain_list **list)
+{
+	int ret, num_pds;
+
+	num_pds = dev_pm_domain_attach_list(dev, data, list);
+	if (num_pds <= 0)
+		return num_pds;
+
+	ret = devm_add_action_or_reset(dev, devm_pm_domain_detach_list, *list);
+	if (ret)
+		return ret;
+
+	return num_pds;
+}
+EXPORT_SYMBOL_GPL(devm_pm_domain_attach_list);
+
+/**
+ * dev_pm_domain_detach - Detach a device from its PM domain.
+ * @dev: Device to detach.
+ * @power_off: Used to indicate whether we should power off the device.
+ *
+ * This functions will reverse the actions from dev_pm_domain_attach(),
+ * dev_pm_domain_attach_by_id() and dev_pm_domain_attach_by_name(), thus it
+ * detaches @dev from its PM domain.  Typically it should be invoked during the
+ * remove phase, either from subsystem level code or from drivers.
+ *
+ * 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);
+
+/**
+ * dev_pm_domain_detach_list - Detach a list of PM domains.
+ * @list: The list of PM domains to detach.
+ *
+ * This function reverse the actions from dev_pm_domain_attach_list().
+ * Typically it should be invoked during the remove phase from drivers.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ */
+void dev_pm_domain_detach_list(struct dev_pm_domain_list *list)
+{
+	int i;
+
+	if (!list)
+		return;
+
+	for (i = 0; i < list->num_pds; i++) {
+		dev_pm_opp_clear_config(list->opp_tokens[i]);
+		if (list->pd_links[i])
+			device_link_del(list->pd_links[i]);
+		dev_pm_domain_detach(list->pd_devs[i], true);
+	}
+
+	kfree(list->pd_devs);
+	kfree(list);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_detach_list);
+
+/**
+ * dev_pm_domain_start - Start the device through its PM domain.
+ * @dev: Device to start.
+ *
+ * This function should typically be called during probe by a subsystem/driver,
+ * when it needs to start its device from the PM domain's perspective. Note
+ * that, it's assumed that the PM domain is already powered on when this
+ * function is called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_domain_start(struct device *dev)
+{
+	if (dev->pm_domain && dev->pm_domain->start)
+		return dev->pm_domain->start(dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_start);
+
+/**
+ * dev_pm_domain_set - Set PM domain of a device.
+ * @dev: Device whose PM domain is to be set.
+ * @pd: PM domain to be set, or NULL.
+ *
+ * Sets the PM domain the device belongs to. The PM domain of a device needs
+ * to be set before its probe finishes (it's bound to a driver).
+ *
+ * This function must be called with the device lock held.
+ */
+void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd)
+{
+	if (dev->pm_domain == pd)
+		return;
+
+	WARN(pd && device_is_bound(dev),
+	     "PM domains can only be changed for unbound devices\n");
+	dev->pm_domain = pd;
+	device_pm_check_callbacks(dev);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_set);
+
+/**
+ * dev_pm_domain_set_performance_state - Request a new performance state.
+ * @dev: The device to make the request for.
+ * @state: Target performance state for the device.
+ *
+ * This function should be called when a new performance state needs to be
+ * requested for a device that is attached to a PM domain. Note that, the
+ * support for performance scaling for PM domains is optional.
+ *
+ * Returns 0 on success and when performance scaling isn't supported, negative
+ * error code on failure.
+ */
+int dev_pm_domain_set_performance_state(struct device *dev, unsigned int state)
+{
+	if (dev->pm_domain && dev->pm_domain->set_performance_state)
+		return dev->pm_domain->set_performance_state(dev, state);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_set_performance_state);
diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c
new file mode 100644
index 000000000..af99bbcf2
--- /dev/null
+++ b/drivers/base/power/generic_ops.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * drivers/base/power/generic_ops.c - Generic PM callbacks for subsystems
+ *
+ * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ */
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/export.h>
+
+#define CALL_PM_OP(dev, op) \
+({ \
+	struct device *_dev = (dev); \
+	const struct dev_pm_ops *pm = _dev->driver ? _dev->driver->pm : NULL; \
+	pm && pm->op ? pm->op(_dev) : 0; \
+})
+
+#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)
+{
+	return CALL_PM_OP(dev, runtime_suspend);
+}
+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)
+{
+	return CALL_PM_OP(dev, runtime_resume);
+}
+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)
+{
+	return CALL_PM_OP(dev, suspend_noirq);
+}
+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)
+{
+	return CALL_PM_OP(dev, suspend_late);
+}
+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)
+{
+	return CALL_PM_OP(dev, suspend);
+}
+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)
+{
+	return CALL_PM_OP(dev, freeze_noirq);
+}
+EXPORT_SYMBOL_GPL(pm_generic_freeze_noirq);
+
+/**
+ * pm_generic_freeze - Generic freeze callback for subsystems.
+ * @dev: Device to freeze.
+ */
+int pm_generic_freeze(struct device *dev)
+{
+	return CALL_PM_OP(dev, freeze);
+}
+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)
+{
+	return CALL_PM_OP(dev, poweroff_noirq);
+}
+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)
+{
+	return CALL_PM_OP(dev, poweroff_late);
+}
+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)
+{
+	return CALL_PM_OP(dev, poweroff);
+}
+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)
+{
+	return CALL_PM_OP(dev, thaw_noirq);
+}
+EXPORT_SYMBOL_GPL(pm_generic_thaw_noirq);
+
+/**
+ * pm_generic_thaw - Generic thaw callback for subsystems.
+ * @dev: Device to thaw.
+ */
+int pm_generic_thaw(struct device *dev)
+{
+	return CALL_PM_OP(dev, thaw);
+}
+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)
+{
+	return CALL_PM_OP(dev, resume_noirq);
+}
+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)
+{
+	return CALL_PM_OP(dev, resume_early);
+}
+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)
+{
+	return CALL_PM_OP(dev, resume);
+}
+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)
+{
+	return CALL_PM_OP(dev, restore_noirq);
+}
+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)
+{
+	return CALL_PM_OP(dev, restore_early);
+}
+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)
+{
+	return CALL_PM_OP(dev, restore);
+}
+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);
+}
+#endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
new file mode 100644
index 000000000..e130da428
--- /dev/null
+++ b/drivers/base/power/main.c
@@ -0,0 +1,2442 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * drivers/base/power/main.c - Where the driver meets power management.
+ *
+ * Copyright (c) 2003 Patrick Mochel
+ * Copyright (c) 2003 Open Source Development Lab
+ *
+ * The driver model core calls device_pm_add() when a device is registered.
+ * This will initialize the embedded device_pm_info object in the device
+ * and add it to the list of power-controlled devices. sysfs entries for
+ * controlling device power management will also be added.
+ *
+ * A separate list is used for keeping track of power info, because the power
+ * domain dependencies may differ from the ancestral dependencies that the
+ * subsystem list maintains.
+ */
+
+#define pr_fmt(fmt) "PM: " fmt
+#define dev_fmt pr_fmt
+
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/mutex.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/pm-trace.h>
+#include <linux/pm_wakeirq.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sysctl.h>
+#include <linux/async.h>
+#include <linux/suspend.h>
+#include <trace/events/power.h>
+#include <linux/cpufreq.h>
+#include <linux/devfreq.h>
+#include <linux/thermal.h>
+#include <linux/timer.h>
+#include <linux/nmi.h>
+
+#include "../base.h"
+#include "power.h"
+
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX "pm."
+
+typedef int (*pm_callback_t)(struct device *);
+
+/*
+ * The entries in the dpm_list list are in a depth first order, simply
+ * because children are guaranteed to be discovered after parents, and
+ * are inserted at the back of the list on discovery.
+ *
+ * Since device_pm_add() may be called with a device lock held,
+ * we must never try to acquire a device lock while holding
+ * dpm_list_mutex.
+ */
+
+LIST_HEAD(dpm_list);
+static LIST_HEAD(dpm_prepared_list);
+static LIST_HEAD(dpm_suspended_list);
+static LIST_HEAD(dpm_late_early_list);
+static LIST_HEAD(dpm_noirq_list);
+
+static DEFINE_MUTEX(dpm_list_mtx);
+static pm_message_t pm_transition;
+
+static DEFINE_MUTEX(async_wip_mtx);
+static int async_error;
+
+/**
+ * pm_hibernate_is_recovering - if recovering from hibernate due to error.
+ *
+ * Used to query if dev_pm_ops.thaw() is called for normal hibernation case or
+ * recovering from some error.
+ *
+ * Return: true for error case, false for normal case.
+ */
+bool pm_hibernate_is_recovering(void)
+{
+	return pm_transition.event == PM_EVENT_RECOVER;
+}
+EXPORT_SYMBOL_GPL(pm_hibernate_is_recovering);
+
+static const char *pm_verb(int event)
+{
+	switch (event) {
+	case PM_EVENT_SUSPEND:
+		return "suspend";
+	case PM_EVENT_RESUME:
+		return "resume";
+	case PM_EVENT_FREEZE:
+		return "freeze";
+	case PM_EVENT_QUIESCE:
+		return "quiesce";
+	case PM_EVENT_HIBERNATE:
+		return "hibernate";
+	case PM_EVENT_THAW:
+		return "thaw";
+	case PM_EVENT_RESTORE:
+		return "restore";
+	case PM_EVENT_RECOVER:
+		return "recover";
+	case PM_EVENT_POWEROFF:
+		return "poweroff";
+	default:
+		return "(unknown PM event)";
+	}
+}
+
+/**
+ * device_pm_sleep_init - Initialize system suspend-related device fields.
+ * @dev: Device object being initialized.
+ */
+void device_pm_sleep_init(struct device *dev)
+{
+	dev->power.is_prepared = false;
+	dev->power.is_suspended = false;
+	dev->power.is_noirq_suspended = false;
+	dev->power.is_late_suspended = false;
+	init_completion(&dev->power.completion);
+	complete(&dev->power.completion);
+	dev->power.wakeup = NULL;
+	INIT_LIST_HEAD(&dev->power.entry);
+}
+
+/**
+ * device_pm_lock - Lock the list of active devices used by the PM core.
+ */
+void device_pm_lock(void)
+{
+	mutex_lock(&dpm_list_mtx);
+}
+
+/**
+ * device_pm_unlock - Unlock the list of active devices used by the PM core.
+ */
+void device_pm_unlock(void)
+{
+	mutex_unlock(&dpm_list_mtx);
+}
+
+/**
+ * device_pm_add - Add a device to the PM core's list of active devices.
+ * @dev: Device to add to the list.
+ */
+void device_pm_add(struct device *dev)
+{
+	/* Skip PM setup/initialization. */
+	if (device_pm_not_required(dev))
+		return;
+
+	pr_debug("Adding info for %s:%s\n",
+		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
+	device_pm_check_callbacks(dev);
+	mutex_lock(&dpm_list_mtx);
+	if (dev->parent && dev->parent->power.is_prepared)
+		dev_warn(dev, "parent %s should not be sleeping\n",
+			dev_name(dev->parent));
+	list_add_tail(&dev->power.entry, &dpm_list);
+	dev->power.in_dpm_list = true;
+	mutex_unlock(&dpm_list_mtx);
+}
+
+/**
+ * device_pm_remove - Remove a device from the PM core's list of active devices.
+ * @dev: Device to be removed from the list.
+ */
+void device_pm_remove(struct device *dev)
+{
+	if (device_pm_not_required(dev))
+		return;
+
+	pr_debug("Removing info for %s:%s\n",
+		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
+	complete_all(&dev->power.completion);
+	mutex_lock(&dpm_list_mtx);
+	list_del_init(&dev->power.entry);
+	dev->power.in_dpm_list = false;
+	mutex_unlock(&dpm_list_mtx);
+	device_wakeup_disable(dev);
+	pm_runtime_remove(dev);
+	device_pm_check_callbacks(dev);
+}
+
+/**
+ * device_pm_move_before - Move device in the PM core's list of active devices.
+ * @deva: Device to move in dpm_list.
+ * @devb: Device @deva should come before.
+ */
+void device_pm_move_before(struct device *deva, struct device *devb)
+{
+	pr_debug("Moving %s:%s before %s:%s\n",
+		 deva->bus ? deva->bus->name : "No Bus", dev_name(deva),
+		 devb->bus ? devb->bus->name : "No Bus", dev_name(devb));
+	/* Delete deva from dpm_list and reinsert before devb. */
+	list_move_tail(&deva->power.entry, &devb->power.entry);
+}
+
+/**
+ * device_pm_move_after - Move device in the PM core's list of active devices.
+ * @deva: Device to move in dpm_list.
+ * @devb: Device @deva should come after.
+ */
+void device_pm_move_after(struct device *deva, struct device *devb)
+{
+	pr_debug("Moving %s:%s after %s:%s\n",
+		 deva->bus ? deva->bus->name : "No Bus", dev_name(deva),
+		 devb->bus ? devb->bus->name : "No Bus", dev_name(devb));
+	/* Delete deva from dpm_list and reinsert after devb. */
+	list_move(&deva->power.entry, &devb->power.entry);
+}
+
+/**
+ * device_pm_move_last - Move device to end of the PM core's list of devices.
+ * @dev: Device to move in dpm_list.
+ */
+void device_pm_move_last(struct device *dev)
+{
+	pr_debug("Moving %s:%s to end of list\n",
+		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
+	list_move_tail(&dev->power.entry, &dpm_list);
+}
+
+static ktime_t initcall_debug_start(struct device *dev, void *cb)
+{
+	if (!pm_print_times_enabled)
+		return 0;
+
+	dev_info(dev, "calling %ps @ %i, parent: %s\n", cb,
+		 task_pid_nr(current),
+		 dev->parent ? dev_name(dev->parent) : "none");
+	return ktime_get();
+}
+
+static void initcall_debug_report(struct device *dev, ktime_t calltime,
+				  void *cb, int error)
+{
+	ktime_t rettime;
+
+	if (!pm_print_times_enabled)
+		return;
+
+	rettime = ktime_get();
+	dev_info(dev, "%ps returned %d after %Ld usecs\n", cb, error,
+		 (unsigned long long)ktime_us_delta(rettime, calltime));
+}
+
+/**
+ * dpm_wait - Wait for a PM operation to complete.
+ * @dev: Device to wait for.
+ * @async: If unset, wait only if the device's power.async_suspend flag is set.
+ */
+static void dpm_wait(struct device *dev, bool async)
+{
+	if (!dev)
+		return;
+
+	/* Devices with no PM support don't use the completion. */
+	if (dev->power.no_pm)
+		return;
+
+	if (async || (pm_async_enabled && dev->power.async_suspend))
+		wait_for_completion(&dev->power.completion);
+}
+
+static int dpm_wait_fn(struct device *dev, void *async_ptr)
+{
+	dpm_wait(dev, *((bool *)async_ptr));
+	return 0;
+}
+
+static void dpm_wait_for_children(struct device *dev, bool async)
+{
+	device_for_each_child(dev, &async, dpm_wait_fn);
+}
+
+static void dpm_wait_for_suppliers(struct device *dev, bool async)
+{
+	struct device_link *link;
+	int idx;
+
+	idx = device_links_read_lock();
+
+	/*
+	 * If the supplier goes away right after we've checked the link to it,
+	 * we'll wait for its completion to change the state, but that's fine,
+	 * because the only things that will block as a result are the SRCU
+	 * callbacks freeing the link objects for the links in the list we're
+	 * walking.
+	 */
+	dev_for_each_link_to_supplier(link, dev)
+		if (READ_ONCE(link->status) != DL_STATE_DORMANT &&
+		    !device_link_flag_is_sync_state_only(link->flags))
+			dpm_wait(link->supplier, async);
+
+	device_links_read_unlock(idx);
+}
+
+static bool dpm_wait_for_superior(struct device *dev, bool async)
+{
+	struct device *parent;
+
+	/*
+	 * If the device is resumed asynchronously and the parent's callback
+	 * deletes both the device and the parent itself, the parent object may
+	 * be freed while this function is running, so avoid that by reference
+	 * counting the parent once more unless the device has been deleted
+	 * already (in which case return right away).
+	 */
+	mutex_lock(&dpm_list_mtx);
+
+	if (!device_pm_initialized(dev)) {
+		mutex_unlock(&dpm_list_mtx);
+		return false;
+	}
+
+	parent = get_device(dev->parent);
+
+	mutex_unlock(&dpm_list_mtx);
+
+	dpm_wait(parent, async);
+	put_device(parent);
+
+	dpm_wait_for_suppliers(dev, async);
+
+	/*
+	 * If the parent's callback has deleted the device, attempting to resume
+	 * it would be invalid, so avoid doing that then.
+	 */
+	return device_pm_initialized(dev);
+}
+
+static void dpm_wait_for_consumers(struct device *dev, bool async)
+{
+	struct device_link *link;
+	int idx;
+
+	idx = device_links_read_lock();
+
+	/*
+	 * The status of a device link can only be changed from "dormant" by a
+	 * probe, but that cannot happen during system suspend/resume.  In
+	 * theory it can change to "dormant" at that time, but then it is
+	 * reasonable to wait for the target device anyway (eg. if it goes
+	 * away, it's better to wait for it to go away completely and then
+	 * continue instead of trying to continue in parallel with its
+	 * unregistration).
+	 */
+	dev_for_each_link_to_consumer(link, dev)
+		if (READ_ONCE(link->status) != DL_STATE_DORMANT &&
+		    !device_link_flag_is_sync_state_only(link->flags))
+			dpm_wait(link->consumer, async);
+
+	device_links_read_unlock(idx);
+}
+
+static void dpm_wait_for_subordinate(struct device *dev, bool async)
+{
+	dpm_wait_for_children(dev, async);
+	dpm_wait_for_consumers(dev, async);
+}
+
+/**
+ * pm_op - Return the PM operation appropriate for given PM event.
+ * @ops: PM operations to choose from.
+ * @state: PM transition of the system being carried out.
+ */
+static pm_callback_t pm_op(const struct dev_pm_ops *ops, pm_message_t state)
+{
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		return ops->suspend;
+	case PM_EVENT_RESUME:
+		return ops->resume;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		return ops->freeze;
+	case PM_EVENT_POWEROFF:
+	case PM_EVENT_HIBERNATE:
+		return ops->poweroff;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		return ops->thaw;
+	case PM_EVENT_RESTORE:
+		return ops->restore;
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
+	}
+
+	return NULL;
+}
+
+/**
+ * pm_late_early_op - Return the PM operation appropriate for given PM event.
+ * @ops: PM operations to choose from.
+ * @state: PM transition of the system being carried out.
+ *
+ * Runtime PM is disabled for @dev while this function is being executed.
+ */
+static pm_callback_t pm_late_early_op(const struct dev_pm_ops *ops,
+				      pm_message_t state)
+{
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		return ops->suspend_late;
+	case PM_EVENT_RESUME:
+		return ops->resume_early;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		return ops->freeze_late;
+	case PM_EVENT_POWEROFF:
+	case PM_EVENT_HIBERNATE:
+		return ops->poweroff_late;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		return ops->thaw_early;
+	case PM_EVENT_RESTORE:
+		return ops->restore_early;
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
+	}
+
+	return NULL;
+}
+
+/**
+ * pm_noirq_op - Return the PM operation appropriate for given PM event.
+ * @ops: PM operations to choose from.
+ * @state: PM transition of the system being carried out.
+ *
+ * The driver of @dev will not receive interrupts while this function is being
+ * executed.
+ */
+static pm_callback_t pm_noirq_op(const struct dev_pm_ops *ops, pm_message_t state)
+{
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		return ops->suspend_noirq;
+	case PM_EVENT_RESUME:
+		return ops->resume_noirq;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		return ops->freeze_noirq;
+	case PM_EVENT_POWEROFF:
+	case PM_EVENT_HIBERNATE:
+		return ops->poweroff_noirq;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		return ops->thaw_noirq;
+	case PM_EVENT_RESTORE:
+		return ops->restore_noirq;
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
+	}
+
+	return NULL;
+}
+
+static void pm_dev_dbg(struct device *dev, pm_message_t state, const char *info)
+{
+	dev_dbg(dev, "%s%s%s driver flags: %x\n", info, pm_verb(state.event),
+		((state.event & PM_EVENT_SLEEP) && device_may_wakeup(dev)) ?
+		", may wakeup" : "", dev->power.driver_flags);
+}
+
+static void pm_dev_err(struct device *dev, pm_message_t state, const char *info,
+			int error)
+{
+	dev_err(dev, "failed to %s%s: error %d\n", pm_verb(state.event), info,
+		error);
+}
+
+static void dpm_show_time(ktime_t starttime, pm_message_t state, int error,
+			  const char *info)
+{
+	ktime_t calltime;
+	u64 usecs64;
+	int usecs;
+
+	calltime = ktime_get();
+	usecs64 = ktime_to_ns(ktime_sub(calltime, starttime));
+	do_div(usecs64, NSEC_PER_USEC);
+	usecs = usecs64;
+	if (usecs == 0)
+		usecs = 1;
+
+	pm_pr_dbg("%s%s%s of devices %s after %ld.%03ld msecs\n",
+		  info ?: "", info ? " " : "", pm_verb(state.event),
+		  error ? "aborted" : "complete",
+		  usecs / USEC_PER_MSEC, usecs % USEC_PER_MSEC);
+}
+
+static int dpm_run_callback(pm_callback_t cb, struct device *dev,
+			    pm_message_t state, const char *info)
+{
+	ktime_t calltime;
+	int error;
+
+	if (!cb)
+		return 0;
+
+	calltime = initcall_debug_start(dev, cb);
+
+	pm_dev_dbg(dev, state, info);
+	trace_device_pm_callback_start(dev, info, state.event);
+	error = cb(dev);
+	trace_device_pm_callback_end(dev, error);
+	suspend_report_result(dev, cb, error);
+
+	initcall_debug_report(dev, calltime, cb, error);
+
+	return error;
+}
+
+#ifdef CONFIG_DPM_WATCHDOG
+struct dpm_watchdog {
+	struct device		*dev;
+	struct task_struct	*tsk;
+	struct timer_list	timer;
+	bool			fatal;
+};
+
+#define DECLARE_DPM_WATCHDOG_ON_STACK(wd) \
+	struct dpm_watchdog wd
+
+static bool __read_mostly dpm_watchdog_all_cpu_backtrace;
+module_param(dpm_watchdog_all_cpu_backtrace, bool, 0644);
+MODULE_PARM_DESC(dpm_watchdog_all_cpu_backtrace,
+		 "Backtrace all CPUs on DPM watchdog timeout");
+
+static bool __read_mostly dpm_watchdog_enabled =
+				IS_ENABLED(CONFIG_DPM_WATCHDOG_ENABLED);
+module_param(dpm_watchdog_enabled, bool, 0644);
+MODULE_PARM_DESC(dpm_watchdog_enabled, "Enable DPM watchdog");
+
+static unsigned int __read_mostly dpm_watchdog_timeout = CONFIG_DPM_WATCHDOG_TIMEOUT;
+static unsigned int __read_mostly dpm_watchdog_warning_timeout =
+						CONFIG_DPM_WATCHDOG_WARNING_TIMEOUT;
+static const unsigned int dpm_watchdog_timeout_max = CONFIG_DPM_WATCHDOG_TIMEOUT;
+
+static int proc_dodpm_watchdog_timeout_secs(const struct ctl_table *table,
+					    int write, void *buffer,
+					    size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table ctl = *table;
+	unsigned int val = dpm_watchdog_timeout;
+	int ret;
+
+	ctl.data = &val;
+	ret = proc_douintvec_minmax(&ctl, write, buffer, lenp, ppos);
+	if (ret || !write)
+		return ret;
+
+	if (val < dpm_watchdog_warning_timeout)
+		dpm_watchdog_warning_timeout = val;
+	dpm_watchdog_timeout = val;
+
+	return 0;
+}
+
+static const struct ctl_table dpm_watchdog_sysctls[] = {
+	{
+		.procname	= "dpm_watchdog_timeout_secs",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dodpm_watchdog_timeout_secs,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= (void *)&dpm_watchdog_timeout_max,
+	},
+	{
+		.procname	= "dpm_watchdog_warning_timeout_secs",
+		.data		= &dpm_watchdog_warning_timeout,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= (void *)&dpm_watchdog_timeout,
+	},
+};
+
+static int __init dpm_watchdog_sysctl_init(void)
+{
+	register_sysctl_init("kernel", dpm_watchdog_sysctls);
+	return 0;
+}
+subsys_initcall(dpm_watchdog_sysctl_init);
+
+/**
+ * dpm_watchdog_handler - Driver suspend / resume watchdog handler.
+ * @t: The timer that PM watchdog depends on.
+ *
+ * Called when a driver has timed out suspending or resuming.
+ * There's not much we can do here to recover so panic() to
+ * capture a crash-dump in pstore.
+ */
+static void dpm_watchdog_handler(struct timer_list *t)
+{
+	struct dpm_watchdog *wd = timer_container_of(wd, t, timer);
+	struct timer_list *timer = &wd->timer;
+	unsigned int time_left;
+
+	if (wd->fatal) {
+		unsigned int this_cpu = smp_processor_id();
+
+		dev_emerg(wd->dev, "**** DPM device timeout ****\n");
+		show_stack(wd->tsk, NULL, KERN_EMERG);
+		if (dpm_watchdog_all_cpu_backtrace)
+			trigger_allbutcpu_cpu_backtrace(this_cpu);
+		panic("%s %s: unrecoverable failure\n",
+			dev_driver_string(wd->dev), dev_name(wd->dev));
+	}
+
+	time_left = dpm_watchdog_timeout - dpm_watchdog_warning_timeout;
+	dev_warn(wd->dev, "**** DPM device timeout after %u seconds; %u seconds until panic ****\n",
+		 dpm_watchdog_warning_timeout, time_left);
+	show_stack(wd->tsk, NULL, KERN_WARNING);
+
+	wd->fatal = true;
+	mod_timer(timer, jiffies + HZ * time_left);
+}
+
+/**
+ * dpm_watchdog_set - Enable pm watchdog for given device.
+ * @wd: Watchdog. Must be allocated on the stack.
+ * @dev: Device to handle.
+ */
+static void dpm_watchdog_set(struct dpm_watchdog *wd, struct device *dev)
+{
+	struct timer_list *timer = &wd->timer;
+
+	if (!dpm_watchdog_enabled)
+		return;
+
+	wd->dev = dev;
+	wd->tsk = current;
+	wd->fatal = dpm_watchdog_timeout == dpm_watchdog_warning_timeout;
+
+	timer_setup_on_stack(timer, dpm_watchdog_handler, 0);
+	/* use same timeout value for both suspend and resume */
+	timer->expires = jiffies + HZ * dpm_watchdog_warning_timeout;
+	add_timer(timer);
+}
+
+/**
+ * dpm_watchdog_clear - Disable suspend/resume watchdog.
+ * @wd: Watchdog to disable.
+ */
+static void dpm_watchdog_clear(struct dpm_watchdog *wd)
+{
+	struct timer_list *timer = &wd->timer;
+
+	if (!dpm_watchdog_enabled)
+		return;
+
+	timer_delete_sync(timer);
+	timer_destroy_on_stack(timer);
+}
+#else
+#define DECLARE_DPM_WATCHDOG_ON_STACK(wd)
+#define dpm_watchdog_set(x, y)
+#define dpm_watchdog_clear(x)
+#endif
+
+/*------------------------- Resume routines -------------------------*/
+
+/**
+ * dev_pm_skip_resume - System-wide device resume optimization check.
+ * @dev: Target device.
+ *
+ * Return:
+ * - %false if the transition under way is RESTORE.
+ * - Return value of dev_pm_skip_suspend() if the transition under way is THAW.
+ * - The logical negation of %power.must_resume otherwise (that is, when the
+ *   transition under way is RESUME).
+ */
+bool dev_pm_skip_resume(struct device *dev)
+{
+	if (pm_transition.event == PM_EVENT_RESTORE)
+		return false;
+
+	if (pm_transition.event == PM_EVENT_THAW)
+		return dev_pm_skip_suspend(dev);
+
+	return !dev->power.must_resume;
+}
+
+static bool is_async(struct device *dev)
+{
+	return dev->power.async_suspend && pm_async_enabled
+		&& !pm_trace_is_enabled();
+}
+
+static bool __dpm_async(struct device *dev, async_func_t func)
+{
+	if (dev->power.work_in_progress)
+		return true;
+
+	if (!is_async(dev))
+		return false;
+
+	dev->power.work_in_progress = true;
+
+	get_device(dev);
+
+	if (async_schedule_dev_nocall(func, dev))
+		return true;
+
+	put_device(dev);
+
+	return false;
+}
+
+static bool dpm_async_fn(struct device *dev, async_func_t func)
+{
+	guard(mutex)(&async_wip_mtx);
+
+	return __dpm_async(dev, func);
+}
+
+static int dpm_async_with_cleanup(struct device *dev, void *fn)
+{
+	guard(mutex)(&async_wip_mtx);
+
+	if (!__dpm_async(dev, fn))
+		dev->power.work_in_progress = false;
+
+	return 0;
+}
+
+static void dpm_async_resume_children(struct device *dev, async_func_t func)
+{
+	/*
+	 * Prevent racing with dpm_clear_async_state() during initial list
+	 * walks in dpm_noirq_resume_devices(), dpm_resume_early(), and
+	 * dpm_resume().
+	 */
+	guard(mutex)(&dpm_list_mtx);
+
+	/*
+	 * Start processing "async" children of the device unless it's been
+	 * started already for them.
+	 */
+	device_for_each_child(dev, func, dpm_async_with_cleanup);
+}
+
+static void dpm_async_resume_subordinate(struct device *dev, async_func_t func)
+{
+	struct device_link *link;
+	int idx;
+
+	dpm_async_resume_children(dev, func);
+
+	idx = device_links_read_lock();
+
+	/* Start processing the device's "async" consumers. */
+	dev_for_each_link_to_consumer(link, dev)
+		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
+			dpm_async_with_cleanup(link->consumer, func);
+
+	device_links_read_unlock(idx);
+}
+
+static void dpm_clear_async_state(struct device *dev)
+{
+	reinit_completion(&dev->power.completion);
+	dev->power.work_in_progress = false;
+}
+
+static bool dpm_root_device(struct device *dev)
+{
+	lockdep_assert_held(&dpm_list_mtx);
+
+	/*
+	 * Since this function is required to run under dpm_list_mtx, the
+	 * list_empty() below will only return true if the device's list of
+	 * consumers is actually empty before calling it.
+	 */
+	return !dev->parent && list_empty(&dev->links.suppliers);
+}
+
+static void async_resume_noirq(void *data, async_cookie_t cookie);
+
+/**
+ * device_resume_noirq - Execute a "noirq resume" callback for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ * @async: If true, the device is being resumed asynchronously.
+ *
+ * The driver of @dev will not receive interrupts while this function is being
+ * executed.
+ */
+static void device_resume_noirq(struct device *dev, pm_message_t state, bool async)
+{
+	pm_callback_t callback = NULL;
+	const char *info = NULL;
+	bool skip_resume;
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_RESUME(0);
+
+	if (dev->power.syscore || dev->power.direct_complete)
+		goto Out;
+
+	if (!dev->power.is_noirq_suspended) {
+		/*
+		 * This means that system suspend has been aborted in the noirq
+		 * phase before invoking the noirq suspend callback for the
+		 * device, so if device_suspend_late() has left it in suspend,
+		 * device_resume_early() should leave it in suspend either in
+		 * case the early resume of it depends on the noirq resume that
+		 * has not run.
+		 */
+		if (dev_pm_skip_suspend(dev))
+			dev->power.must_resume = false;
+
+		goto Out;
+	}
+
+	if (!dpm_wait_for_superior(dev, async))
+		goto Out;
+
+	skip_resume = dev_pm_skip_resume(dev);
+	/*
+	 * If the driver callback is skipped below or by the middle layer
+	 * callback and device_resume_early() also skips the driver callback for
+	 * this device later, it needs to appear as "suspended" to PM-runtime,
+	 * so change its status accordingly.
+	 *
+	 * Otherwise, the device is going to be resumed, so set its PM-runtime
+	 * status to "active" unless its power.smart_suspend flag is clear, in
+	 * which case it is not necessary to update its PM-runtime status.
+	 */
+	if (skip_resume)
+		pm_runtime_set_suspended(dev);
+	else if (dev_pm_smart_suspend(dev))
+		pm_runtime_set_active(dev);
+
+	if (dev->pm_domain) {
+		info = "noirq power domain ";
+		callback = pm_noirq_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "noirq type ";
+		callback = pm_noirq_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "noirq class ";
+		callback = pm_noirq_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "noirq bus ";
+		callback = pm_noirq_op(dev->bus->pm, state);
+	}
+	if (callback)
+		goto Run;
+
+	if (skip_resume)
+		goto Skip;
+
+	if (dev->driver && dev->driver->pm) {
+		info = "noirq driver ";
+		callback = pm_noirq_op(dev->driver->pm, state);
+	}
+
+Run:
+	error = dpm_run_callback(callback, dev, state, info);
+
+Skip:
+	dev->power.is_noirq_suspended = false;
+
+Out:
+	complete_all(&dev->power.completion);
+	TRACE_RESUME(error);
+
+	if (error) {
+		WRITE_ONCE(async_error, error);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async noirq" : " noirq", error);
+	}
+
+	dpm_async_resume_subordinate(dev, async_resume_noirq);
+}
+
+static void async_resume_noirq(void *data, async_cookie_t cookie)
+{
+	struct device *dev = data;
+
+	device_resume_noirq(dev, pm_transition, true);
+	put_device(dev);
+}
+
+static void dpm_noirq_resume_devices(pm_message_t state)
+{
+	struct device *dev;
+	ktime_t starttime = ktime_get();
+
+	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, true);
+
+	async_error = 0;
+	pm_transition = state;
+
+	mutex_lock(&dpm_list_mtx);
+
+	/*
+	 * Start processing "async" root devices upfront so they don't wait for
+	 * the "sync" devices they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_noirq_list, power.entry) {
+		dpm_clear_async_state(dev);
+		if (dpm_root_device(dev))
+			dpm_async_with_cleanup(dev, async_resume_noirq);
+	}
+
+	while (!list_empty(&dpm_noirq_list)) {
+		dev = to_device(dpm_noirq_list.next);
+		list_move_tail(&dev->power.entry, &dpm_late_early_list);
+
+		if (!dpm_async_fn(dev, async_resume_noirq)) {
+			get_device(dev);
+
+			mutex_unlock(&dpm_list_mtx);
+
+			device_resume_noirq(dev, state, false);
+
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
+	}
+	mutex_unlock(&dpm_list_mtx);
+	async_synchronize_full();
+	dpm_show_time(starttime, state, 0, "noirq");
+	if (READ_ONCE(async_error))
+		dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
+
+	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false);
+}
+
+/**
+ * dpm_resume_noirq - Execute "noirq resume" callbacks for all devices.
+ * @state: PM transition of the system being carried out.
+ *
+ * Invoke the "noirq" resume callbacks for all devices in dpm_noirq_list and
+ * allow device drivers' interrupt handlers to be called.
+ */
+void dpm_resume_noirq(pm_message_t state)
+{
+	dpm_noirq_resume_devices(state);
+
+	resume_device_irqs();
+	device_wakeup_disarm_wake_irqs();
+}
+
+static void async_resume_early(void *data, async_cookie_t cookie);
+
+/**
+ * device_resume_early - Execute an "early resume" callback for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ * @async: If true, the device is being resumed asynchronously.
+ *
+ * Runtime PM is disabled for @dev while this function is being executed.
+ */
+static void device_resume_early(struct device *dev, pm_message_t state, bool async)
+{
+	pm_callback_t callback = NULL;
+	const char *info = NULL;
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_RESUME(0);
+
+	if (dev->power.direct_complete)
+		goto Out;
+
+	if (!dev->power.is_late_suspended)
+		goto Out;
+
+	if (dev->power.syscore)
+		goto Skip;
+
+	if (!dpm_wait_for_superior(dev, async))
+		goto Out;
+
+	if (dev->pm_domain) {
+		info = "early power domain ";
+		callback = pm_late_early_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "early type ";
+		callback = pm_late_early_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "early class ";
+		callback = pm_late_early_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "early bus ";
+		callback = pm_late_early_op(dev->bus->pm, state);
+	}
+	if (callback)
+		goto Run;
+
+	if (dev_pm_skip_resume(dev))
+		goto Skip;
+
+	if (dev->driver && dev->driver->pm) {
+		info = "early driver ";
+		callback = pm_late_early_op(dev->driver->pm, state);
+	}
+
+Run:
+	error = dpm_run_callback(callback, dev, state, info);
+
+Skip:
+	dev->power.is_late_suspended = false;
+	pm_runtime_enable(dev);
+
+Out:
+	TRACE_RESUME(error);
+
+	complete_all(&dev->power.completion);
+
+	if (error) {
+		WRITE_ONCE(async_error, error);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async early" : " early", error);
+	}
+
+	dpm_async_resume_subordinate(dev, async_resume_early);
+}
+
+static void async_resume_early(void *data, async_cookie_t cookie)
+{
+	struct device *dev = data;
+
+	device_resume_early(dev, pm_transition, true);
+	put_device(dev);
+}
+
+/**
+ * dpm_resume_early - Execute "early resume" callbacks for all devices.
+ * @state: PM transition of the system being carried out.
+ */
+void dpm_resume_early(pm_message_t state)
+{
+	struct device *dev;
+	ktime_t starttime = ktime_get();
+
+	trace_suspend_resume(TPS("dpm_resume_early"), state.event, true);
+
+	async_error = 0;
+	pm_transition = state;
+
+	mutex_lock(&dpm_list_mtx);
+
+	/*
+	 * Start processing "async" root devices upfront so they don't wait for
+	 * the "sync" devices they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_late_early_list, power.entry) {
+		dpm_clear_async_state(dev);
+		if (dpm_root_device(dev))
+			dpm_async_with_cleanup(dev, async_resume_early);
+	}
+
+	while (!list_empty(&dpm_late_early_list)) {
+		dev = to_device(dpm_late_early_list.next);
+		list_move_tail(&dev->power.entry, &dpm_suspended_list);
+
+		if (!dpm_async_fn(dev, async_resume_early)) {
+			get_device(dev);
+
+			mutex_unlock(&dpm_list_mtx);
+
+			device_resume_early(dev, state, false);
+
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
+	}
+	mutex_unlock(&dpm_list_mtx);
+	async_synchronize_full();
+	dpm_show_time(starttime, state, 0, "early");
+	if (READ_ONCE(async_error))
+		dpm_save_failed_step(SUSPEND_RESUME_EARLY);
+
+	trace_suspend_resume(TPS("dpm_resume_early"), state.event, false);
+}
+
+/**
+ * dpm_resume_start - Execute "noirq" and "early" device callbacks.
+ * @state: PM transition of the system being carried out.
+ */
+void dpm_resume_start(pm_message_t state)
+{
+	dpm_resume_noirq(state);
+	dpm_resume_early(state);
+}
+EXPORT_SYMBOL_GPL(dpm_resume_start);
+
+static void async_resume(void *data, async_cookie_t cookie);
+
+/**
+ * device_resume - Execute "resume" callbacks for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ * @async: If true, the device is being resumed asynchronously.
+ */
+static void device_resume(struct device *dev, pm_message_t state, bool async)
+{
+	pm_callback_t callback = NULL;
+	const char *info = NULL;
+	int error = 0;
+	DECLARE_DPM_WATCHDOG_ON_STACK(wd);
+
+	TRACE_DEVICE(dev);
+	TRACE_RESUME(0);
+
+	if (dev->power.syscore)
+		goto Complete;
+
+	if (!dev->power.is_suspended)
+		goto Complete;
+
+	dev->power.is_suspended = false;
+
+	if (dev->power.direct_complete) {
+		/*
+		 * Allow new children to be added under the device after this
+		 * point if it has no PM callbacks.
+		 */
+		if (dev->power.no_pm_callbacks)
+			dev->power.is_prepared = false;
+
+		/* Match the pm_runtime_disable() in device_suspend(). */
+		pm_runtime_enable(dev);
+		goto Complete;
+	}
+
+	if (!dpm_wait_for_superior(dev, async))
+		goto Complete;
+
+	dpm_watchdog_set(&wd, dev);
+	device_lock(dev);
+
+	/*
+	 * This is a fib.  But we'll allow new children to be added below
+	 * a resumed device, even if the device hasn't been completed yet.
+	 */
+	dev->power.is_prepared = false;
+
+	if (dev->pm_domain) {
+		info = "power domain ";
+		callback = pm_op(&dev->pm_domain->ops, state);
+		goto Driver;
+	}
+
+	if (dev->type && dev->type->pm) {
+		info = "type ";
+		callback = pm_op(dev->type->pm, state);
+		goto Driver;
+	}
+
+	if (dev->class && dev->class->pm) {
+		info = "class ";
+		callback = pm_op(dev->class->pm, state);
+		goto Driver;
+	}
+
+	if (dev->bus) {
+		if (dev->bus->pm) {
+			info = "bus ";
+			callback = pm_op(dev->bus->pm, state);
+		} else if (dev->bus->resume) {
+			info = "legacy bus ";
+			callback = dev->bus->resume;
+			goto End;
+		}
+	}
+
+ Driver:
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "driver ";
+		callback = pm_op(dev->driver->pm, state);
+	}
+
+ End:
+	error = dpm_run_callback(callback, dev, state, info);
+
+	device_unlock(dev);
+	dpm_watchdog_clear(&wd);
+
+ Complete:
+	complete_all(&dev->power.completion);
+
+	TRACE_RESUME(error);
+
+	if (error) {
+		WRITE_ONCE(async_error, error);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async" : "", error);
+	}
+
+	dpm_async_resume_subordinate(dev, async_resume);
+}
+
+static void async_resume(void *data, async_cookie_t cookie)
+{
+	struct device *dev = data;
+
+	device_resume(dev, pm_transition, true);
+	put_device(dev);
+}
+
+/**
+ * dpm_resume - Execute "resume" callbacks for non-sysdev devices.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute the appropriate "resume" callback for all devices whose status
+ * indicates that they are suspended.
+ */
+void dpm_resume(pm_message_t state)
+{
+	struct device *dev;
+	ktime_t starttime = ktime_get();
+
+	trace_suspend_resume(TPS("dpm_resume"), state.event, true);
+
+	pm_transition = state;
+	async_error = 0;
+
+	mutex_lock(&dpm_list_mtx);
+
+	/*
+	 * Start processing "async" root devices upfront so they don't wait for
+	 * the "sync" devices they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_suspended_list, power.entry) {
+		dpm_clear_async_state(dev);
+		if (dpm_root_device(dev))
+			dpm_async_with_cleanup(dev, async_resume);
+	}
+
+	while (!list_empty(&dpm_suspended_list)) {
+		dev = to_device(dpm_suspended_list.next);
+		list_move_tail(&dev->power.entry, &dpm_prepared_list);
+
+		if (!dpm_async_fn(dev, async_resume)) {
+			get_device(dev);
+
+			mutex_unlock(&dpm_list_mtx);
+
+			device_resume(dev, state, false);
+
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
+	}
+	mutex_unlock(&dpm_list_mtx);
+	async_synchronize_full();
+	dpm_show_time(starttime, state, 0, NULL);
+	if (READ_ONCE(async_error))
+		dpm_save_failed_step(SUSPEND_RESUME);
+
+	cpufreq_resume();
+	devfreq_resume();
+	trace_suspend_resume(TPS("dpm_resume"), state.event, false);
+}
+
+/**
+ * device_complete - Complete a PM transition for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ */
+static void device_complete(struct device *dev, pm_message_t state)
+{
+	void (*callback)(struct device *) = NULL;
+	const char *info = NULL;
+
+	if (dev->power.syscore)
+		goto out;
+
+	device_lock(dev);
+
+	if (dev->pm_domain) {
+		info = "completing power domain ";
+		callback = dev->pm_domain->ops.complete;
+	} else if (dev->type && dev->type->pm) {
+		info = "completing type ";
+		callback = dev->type->pm->complete;
+	} else if (dev->class && dev->class->pm) {
+		info = "completing class ";
+		callback = dev->class->pm->complete;
+	} else if (dev->bus && dev->bus->pm) {
+		info = "completing bus ";
+		callback = dev->bus->pm->complete;
+	}
+
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "completing driver ";
+		callback = dev->driver->pm->complete;
+	}
+
+	if (callback) {
+		pm_dev_dbg(dev, state, info);
+		callback(dev);
+	}
+
+	device_unlock(dev);
+
+out:
+	/* If enabling runtime PM for the device is blocked, unblock it. */
+	pm_runtime_unblock(dev);
+	pm_runtime_put(dev);
+}
+
+/**
+ * dpm_complete - Complete a PM transition for all non-sysdev devices.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute the ->complete() callbacks for all devices whose PM status is not
+ * DPM_ON (this allows new devices to be registered).
+ */
+void dpm_complete(pm_message_t state)
+{
+	struct list_head list;
+
+	trace_suspend_resume(TPS("dpm_complete"), state.event, true);
+
+	INIT_LIST_HEAD(&list);
+	mutex_lock(&dpm_list_mtx);
+	while (!list_empty(&dpm_prepared_list)) {
+		struct device *dev = to_device(dpm_prepared_list.prev);
+
+		get_device(dev);
+		dev->power.is_prepared = false;
+		list_move(&dev->power.entry, &list);
+
+		mutex_unlock(&dpm_list_mtx);
+
+		trace_device_pm_callback_start(dev, "", state.event);
+		device_complete(dev, state);
+		trace_device_pm_callback_end(dev, 0);
+
+		put_device(dev);
+
+		mutex_lock(&dpm_list_mtx);
+	}
+	list_splice(&list, &dpm_list);
+	mutex_unlock(&dpm_list_mtx);
+
+	/* Start resuming thermal control */
+	thermal_pm_complete();
+	/* Allow device probing and trigger re-probing of deferred devices */
+	device_unblock_probing();
+	trace_suspend_resume(TPS("dpm_complete"), state.event, false);
+}
+
+/**
+ * dpm_resume_end - Execute "resume" callbacks and complete system transition.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute "resume" callbacks for all devices and complete the PM transition of
+ * the system.
+ */
+void dpm_resume_end(pm_message_t state)
+{
+	dpm_resume(state);
+	pm_restore_gfp_mask();
+	dpm_complete(state);
+}
+EXPORT_SYMBOL_GPL(dpm_resume_end);
+
+
+/*------------------------- Suspend routines -------------------------*/
+
+static bool dpm_leaf_device(struct device *dev)
+{
+	struct device *child;
+
+	lockdep_assert_held(&dpm_list_mtx);
+
+	child = device_find_any_child(dev);
+	if (child) {
+		put_device(child);
+
+		return false;
+	}
+
+	/*
+	 * Since this function is required to run under dpm_list_mtx, the
+	 * list_empty() below will only return true if the device's list of
+	 * consumers is actually empty before calling it.
+	 */
+	return list_empty(&dev->links.consumers);
+}
+
+static bool dpm_async_suspend_parent(struct device *dev, async_func_t func)
+{
+	guard(mutex)(&dpm_list_mtx);
+
+	/*
+	 * If the device is suspended asynchronously and the parent's callback
+	 * deletes both the device and the parent itself, the parent object may
+	 * be freed while this function is running, so avoid that by checking
+	 * if the device has been deleted already as the parent cannot be
+	 * deleted before it.
+	 */
+	if (!device_pm_initialized(dev))
+		return false;
+
+	/* Start processing the device's parent if it is "async". */
+	if (dev->parent)
+		dpm_async_with_cleanup(dev->parent, func);
+
+	return true;
+}
+
+static void dpm_async_suspend_superior(struct device *dev, async_func_t func)
+{
+	struct device_link *link;
+	int idx;
+
+	if (!dpm_async_suspend_parent(dev, func))
+		return;
+
+	idx = device_links_read_lock();
+
+	/* Start processing the device's "async" suppliers. */
+	dev_for_each_link_to_supplier(link, dev)
+		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
+			dpm_async_with_cleanup(link->supplier, func);
+
+	device_links_read_unlock(idx);
+}
+
+static void dpm_async_suspend_complete_all(struct list_head *device_list)
+{
+	struct device *dev;
+
+	guard(mutex)(&async_wip_mtx);
+
+	list_for_each_entry_reverse(dev, device_list, power.entry) {
+		/*
+		 * In case the device is being waited for and async processing
+		 * has not started for it yet, let the waiters make progress.
+		 */
+		if (!dev->power.work_in_progress)
+			complete_all(&dev->power.completion);
+	}
+}
+
+/**
+ * resume_event - Return a "resume" message for given "suspend" sleep state.
+ * @sleep_state: PM message representing a sleep state.
+ *
+ * Return a PM message representing the resume event corresponding to given
+ * sleep state.
+ */
+static pm_message_t resume_event(pm_message_t sleep_state)
+{
+	switch (sleep_state.event) {
+	case PM_EVENT_SUSPEND:
+		return PMSG_RESUME;
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		return PMSG_RECOVER;
+	case PM_EVENT_HIBERNATE:
+		return PMSG_RESTORE;
+	}
+	return PMSG_ON;
+}
+
+static void dpm_superior_set_must_resume(struct device *dev)
+{
+	struct device_link *link;
+	int idx;
+
+	if (dev->parent)
+		dev->parent->power.must_resume = true;
+
+	idx = device_links_read_lock();
+
+	dev_for_each_link_to_supplier(link, dev)
+		link->supplier->power.must_resume = true;
+
+	device_links_read_unlock(idx);
+}
+
+static void async_suspend_noirq(void *data, async_cookie_t cookie);
+
+/**
+ * device_suspend_noirq - Execute a "noirq suspend" callback for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ * @async: If true, the device is being suspended asynchronously.
+ *
+ * The driver of @dev will not receive interrupts while this function is being
+ * executed.
+ */
+static void device_suspend_noirq(struct device *dev, pm_message_t state, bool async)
+{
+	pm_callback_t callback = NULL;
+	const char *info = NULL;
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_SUSPEND(0);
+
+	dpm_wait_for_subordinate(dev, async);
+
+	if (READ_ONCE(async_error))
+		goto Complete;
+
+	if (dev->power.syscore || dev->power.direct_complete)
+		goto Complete;
+
+	if (dev->pm_domain) {
+		info = "noirq power domain ";
+		callback = pm_noirq_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "noirq type ";
+		callback = pm_noirq_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "noirq class ";
+		callback = pm_noirq_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "noirq bus ";
+		callback = pm_noirq_op(dev->bus->pm, state);
+	}
+	if (callback)
+		goto Run;
+
+	if (dev_pm_skip_suspend(dev))
+		goto Skip;
+
+	if (dev->driver && dev->driver->pm) {
+		info = "noirq driver ";
+		callback = pm_noirq_op(dev->driver->pm, state);
+	}
+
+Run:
+	error = dpm_run_callback(callback, dev, state, info);
+	if (error) {
+		WRITE_ONCE(async_error, error);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async noirq" : " noirq", error);
+		goto Complete;
+	}
+
+Skip:
+	dev->power.is_noirq_suspended = true;
+
+	/*
+	 * Devices must be resumed unless they are explicitly allowed to be left
+	 * in suspend, but even in that case skipping the resume of devices that
+	 * were in use right before the system suspend (as indicated by their
+	 * runtime PM usage counters and child counters) would be suboptimal.
+	 */
+	if (!(dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME) &&
+	      dev->power.may_skip_resume) || !pm_runtime_need_not_resume(dev))
+		dev->power.must_resume = true;
+
+	if (dev->power.must_resume)
+		dpm_superior_set_must_resume(dev);
+
+Complete:
+	complete_all(&dev->power.completion);
+	TRACE_SUSPEND(error);
+
+	if (error || READ_ONCE(async_error))
+		return;
+
+	dpm_async_suspend_superior(dev, async_suspend_noirq);
+}
+
+static void async_suspend_noirq(void *data, async_cookie_t cookie)
+{
+	struct device *dev = data;
+
+	device_suspend_noirq(dev, pm_transition, true);
+	put_device(dev);
+}
+
+static int dpm_noirq_suspend_devices(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+	struct device *dev;
+	int error;
+
+	trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true);
+
+	pm_transition = state;
+	async_error = 0;
+
+	mutex_lock(&dpm_list_mtx);
+
+	/*
+	 * Start processing "async" leaf devices upfront so they don't need to
+	 * wait for the "sync" devices they don't depend on.
+	 */
+	list_for_each_entry_reverse(dev, &dpm_late_early_list, power.entry) {
+		dpm_clear_async_state(dev);
+		if (dpm_leaf_device(dev))
+			dpm_async_with_cleanup(dev, async_suspend_noirq);
+	}
+
+	while (!list_empty(&dpm_late_early_list)) {
+		dev = to_device(dpm_late_early_list.prev);
+
+		list_move(&dev->power.entry, &dpm_noirq_list);
+
+		if (dpm_async_fn(dev, async_suspend_noirq))
+			continue;
+
+		get_device(dev);
+
+		mutex_unlock(&dpm_list_mtx);
+
+		device_suspend_noirq(dev, state, false);
+
+		put_device(dev);
+
+		mutex_lock(&dpm_list_mtx);
+
+		if (READ_ONCE(async_error)) {
+			dpm_async_suspend_complete_all(&dpm_late_early_list);
+			/*
+			 * Move all devices to the target list to resume them
+			 * properly.
+			 */
+			list_splice_init(&dpm_late_early_list, &dpm_noirq_list);
+			break;
+		}
+	}
+
+	mutex_unlock(&dpm_list_mtx);
+
+	async_synchronize_full();
+
+	error = READ_ONCE(async_error);
+	if (error)
+		dpm_save_failed_step(SUSPEND_SUSPEND_NOIRQ);
+
+	dpm_show_time(starttime, state, error, "noirq");
+	trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, false);
+	return error;
+}
+
+/**
+ * dpm_suspend_noirq - Execute "noirq suspend" callbacks for all devices.
+ * @state: PM transition of the system being carried out.
+ *
+ * Prevent device drivers' interrupt handlers from being called and invoke
+ * "noirq" suspend callbacks for all non-sysdev devices.
+ */
+int dpm_suspend_noirq(pm_message_t state)
+{
+	int ret;
+
+	device_wakeup_arm_wake_irqs();
+	suspend_device_irqs();
+
+	ret = dpm_noirq_suspend_devices(state);
+	if (ret)
+		dpm_resume_noirq(resume_event(state));
+
+	return ret;
+}
+
+static void dpm_propagate_wakeup_to_parent(struct device *dev)
+{
+	struct device *parent = dev->parent;
+
+	if (!parent)
+		return;
+
+	spin_lock_irq(&parent->power.lock);
+
+	if (device_wakeup_path(dev) && !parent->power.ignore_children)
+		parent->power.wakeup_path = true;
+
+	spin_unlock_irq(&parent->power.lock);
+}
+
+static void async_suspend_late(void *data, async_cookie_t cookie);
+
+/**
+ * device_suspend_late - Execute a "late suspend" callback for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ * @async: If true, the device is being suspended asynchronously.
+ *
+ * Runtime PM is disabled for @dev while this function is being executed.
+ */
+static void device_suspend_late(struct device *dev, pm_message_t state, bool async)
+{
+	pm_callback_t callback = NULL;
+	const char *info = NULL;
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_SUSPEND(0);
+
+	dpm_wait_for_subordinate(dev, async);
+
+	if (READ_ONCE(async_error))
+		goto Complete;
+
+	if (pm_wakeup_pending()) {
+		WRITE_ONCE(async_error, -EBUSY);
+		goto Complete;
+	}
+
+	if (dev->power.direct_complete)
+		goto Complete;
+
+	/*
+	 * After this point, any runtime PM operations targeting the device
+	 * will fail until the corresponding pm_runtime_enable() call in
+	 * device_resume_early().
+	 */
+	pm_runtime_disable(dev);
+
+	if (dev->power.syscore)
+		goto Skip;
+
+	if (dev->pm_domain) {
+		info = "late power domain ";
+		callback = pm_late_early_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "late type ";
+		callback = pm_late_early_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "late class ";
+		callback = pm_late_early_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "late bus ";
+		callback = pm_late_early_op(dev->bus->pm, state);
+	}
+	if (callback)
+		goto Run;
+
+	if (dev_pm_skip_suspend(dev))
+		goto Skip;
+
+	if (dev->driver && dev->driver->pm) {
+		info = "late driver ";
+		callback = pm_late_early_op(dev->driver->pm, state);
+	}
+
+Run:
+	error = dpm_run_callback(callback, dev, state, info);
+	if (error) {
+		WRITE_ONCE(async_error, error);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async late" : " late", error);
+		pm_runtime_enable(dev);
+		goto Complete;
+	}
+	dpm_propagate_wakeup_to_parent(dev);
+
+Skip:
+	dev->power.is_late_suspended = true;
+
+Complete:
+	TRACE_SUSPEND(error);
+	complete_all(&dev->power.completion);
+
+	if (error || READ_ONCE(async_error))
+		return;
+
+	dpm_async_suspend_superior(dev, async_suspend_late);
+}
+
+static void async_suspend_late(void *data, async_cookie_t cookie)
+{
+	struct device *dev = data;
+
+	device_suspend_late(dev, pm_transition, true);
+	put_device(dev);
+}
+
+/**
+ * dpm_suspend_late - Execute "late suspend" callbacks for all devices.
+ * @state: PM transition of the system being carried out.
+ */
+int dpm_suspend_late(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+	struct device *dev;
+	int error;
+
+	trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true);
+
+	pm_transition = state;
+	async_error = 0;
+
+	wake_up_all_idle_cpus();
+
+	mutex_lock(&dpm_list_mtx);
+
+	/*
+	 * Start processing "async" leaf devices upfront so they don't need to
+	 * wait for the "sync" devices they don't depend on.
+	 */
+	list_for_each_entry_reverse(dev, &dpm_suspended_list, power.entry) {
+		dpm_clear_async_state(dev);
+		if (dpm_leaf_device(dev))
+			dpm_async_with_cleanup(dev, async_suspend_late);
+	}
+
+	while (!list_empty(&dpm_suspended_list)) {
+		dev = to_device(dpm_suspended_list.prev);
+
+		list_move(&dev->power.entry, &dpm_late_early_list);
+
+		if (dpm_async_fn(dev, async_suspend_late))
+			continue;
+
+		get_device(dev);
+
+		mutex_unlock(&dpm_list_mtx);
+
+		device_suspend_late(dev, state, false);
+
+		put_device(dev);
+
+		mutex_lock(&dpm_list_mtx);
+
+		if (READ_ONCE(async_error)) {
+			dpm_async_suspend_complete_all(&dpm_suspended_list);
+			/*
+			 * Move all devices to the target list to resume them
+			 * properly.
+			 */
+			list_splice_init(&dpm_suspended_list, &dpm_late_early_list);
+			break;
+		}
+	}
+
+	mutex_unlock(&dpm_list_mtx);
+
+	async_synchronize_full();
+
+	error = READ_ONCE(async_error);
+	if (error) {
+		dpm_save_failed_step(SUSPEND_SUSPEND_LATE);
+		dpm_resume_early(resume_event(state));
+	}
+	dpm_show_time(starttime, state, error, "late");
+	trace_suspend_resume(TPS("dpm_suspend_late"), state.event, false);
+	return error;
+}
+
+/**
+ * dpm_suspend_end - Execute "late" and "noirq" device suspend callbacks.
+ * @state: PM transition of the system being carried out.
+ */
+int dpm_suspend_end(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+	int error;
+
+	error = dpm_suspend_late(state);
+	if (error)
+		goto out;
+
+	error = dpm_suspend_noirq(state);
+	if (error)
+		dpm_resume_early(resume_event(state));
+
+out:
+	dpm_show_time(starttime, state, error, "end");
+	return error;
+}
+EXPORT_SYMBOL_GPL(dpm_suspend_end);
+
+/**
+ * legacy_suspend - Execute a legacy (bus or class) suspend callback for device.
+ * @dev: Device to suspend.
+ * @state: PM transition of the system being carried out.
+ * @cb: Suspend callback to execute.
+ * @info: string description of caller.
+ */
+static int legacy_suspend(struct device *dev, pm_message_t state,
+			  int (*cb)(struct device *dev, pm_message_t state),
+			  const char *info)
+{
+	int error;
+	ktime_t calltime;
+
+	calltime = initcall_debug_start(dev, cb);
+
+	trace_device_pm_callback_start(dev, info, state.event);
+	error = cb(dev, state);
+	trace_device_pm_callback_end(dev, error);
+	suspend_report_result(dev, cb, error);
+
+	initcall_debug_report(dev, calltime, cb, error);
+
+	return error;
+}
+
+static void dpm_clear_superiors_direct_complete(struct device *dev)
+{
+	struct device_link *link;
+	int idx;
+
+	if (dev->parent) {
+		spin_lock_irq(&dev->parent->power.lock);
+		dev->parent->power.direct_complete = false;
+		spin_unlock_irq(&dev->parent->power.lock);
+	}
+
+	idx = device_links_read_lock();
+
+	dev_for_each_link_to_supplier(link, dev) {
+		spin_lock_irq(&link->supplier->power.lock);
+		link->supplier->power.direct_complete = false;
+		spin_unlock_irq(&link->supplier->power.lock);
+	}
+
+	device_links_read_unlock(idx);
+}
+
+static void async_suspend(void *data, async_cookie_t cookie);
+
+/**
+ * device_suspend - Execute "suspend" callbacks for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ * @async: If true, the device is being suspended asynchronously.
+ */
+static void device_suspend(struct device *dev, pm_message_t state, bool async)
+{
+	pm_callback_t callback = NULL;
+	const char *info = NULL;
+	int error = 0;
+	DECLARE_DPM_WATCHDOG_ON_STACK(wd);
+
+	TRACE_DEVICE(dev);
+	TRACE_SUSPEND(0);
+
+	dpm_wait_for_subordinate(dev, async);
+
+	if (READ_ONCE(async_error)) {
+		dev->power.direct_complete = false;
+		goto Complete;
+	}
+
+	/*
+	 * Wait for possible runtime PM transitions of the device in progress
+	 * to complete and if there's a runtime resume request pending for it,
+	 * resume it before proceeding with invoking the system-wide suspend
+	 * callbacks for it.
+	 *
+	 * If the system-wide suspend callbacks below change the configuration
+	 * of the device, they must disable runtime PM for it or otherwise
+	 * ensure that its runtime-resume callbacks will not be confused by that
+	 * change in case they are invoked going forward.
+	 */
+	pm_runtime_barrier(dev);
+
+	if (pm_wakeup_pending()) {
+		dev->power.direct_complete = false;
+		WRITE_ONCE(async_error, -EBUSY);
+		goto Complete;
+	}
+
+	if (dev->power.syscore)
+		goto Complete;
+
+	/* Avoid direct_complete to let wakeup_path propagate. */
+	if (device_may_wakeup(dev) || device_wakeup_path(dev))
+		dev->power.direct_complete = false;
+
+	if (dev->power.direct_complete) {
+		if (pm_runtime_status_suspended(dev)) {
+			pm_runtime_disable(dev);
+			if (pm_runtime_status_suspended(dev)) {
+				pm_dev_dbg(dev, state, "direct-complete ");
+				dev->power.is_suspended = true;
+				goto Complete;
+			}
+
+			pm_runtime_enable(dev);
+		}
+		dev->power.direct_complete = false;
+	}
+
+	dev->power.may_skip_resume = true;
+	dev->power.must_resume = !dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME);
+
+	dpm_watchdog_set(&wd, dev);
+	device_lock(dev);
+
+	if (dev->pm_domain) {
+		info = "power domain ";
+		callback = pm_op(&dev->pm_domain->ops, state);
+		goto Run;
+	}
+
+	if (dev->type && dev->type->pm) {
+		info = "type ";
+		callback = pm_op(dev->type->pm, state);
+		goto Run;
+	}
+
+	if (dev->class && dev->class->pm) {
+		info = "class ";
+		callback = pm_op(dev->class->pm, state);
+		goto Run;
+	}
+
+	if (dev->bus) {
+		if (dev->bus->pm) {
+			info = "bus ";
+			callback = pm_op(dev->bus->pm, state);
+		} else if (dev->bus->suspend) {
+			pm_dev_dbg(dev, state, "legacy bus ");
+			error = legacy_suspend(dev, state, dev->bus->suspend,
+						"legacy bus ");
+			goto End;
+		}
+	}
+
+ Run:
+	if (!callback && dev->driver && dev->driver->pm) {
+		info = "driver ";
+		callback = pm_op(dev->driver->pm, state);
+	}
+
+	error = dpm_run_callback(callback, dev, state, info);
+
+ End:
+	if (!error) {
+		dev->power.is_suspended = true;
+		if (device_may_wakeup(dev))
+			dev->power.wakeup_path = true;
+
+		dpm_propagate_wakeup_to_parent(dev);
+		dpm_clear_superiors_direct_complete(dev);
+	}
+
+	device_unlock(dev);
+	dpm_watchdog_clear(&wd);
+
+ Complete:
+	if (error) {
+		WRITE_ONCE(async_error, error);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async" : "", error);
+	}
+
+	complete_all(&dev->power.completion);
+	TRACE_SUSPEND(error);
+
+	if (error || READ_ONCE(async_error))
+		return;
+
+	dpm_async_suspend_superior(dev, async_suspend);
+}
+
+static void async_suspend(void *data, async_cookie_t cookie)
+{
+	struct device *dev = data;
+
+	device_suspend(dev, pm_transition, true);
+	put_device(dev);
+}
+
+/**
+ * dpm_suspend - Execute "suspend" callbacks for all non-sysdev devices.
+ * @state: PM transition of the system being carried out.
+ */
+int dpm_suspend(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+	struct device *dev;
+	int error;
+
+	trace_suspend_resume(TPS("dpm_suspend"), state.event, true);
+	might_sleep();
+
+	devfreq_suspend();
+	cpufreq_suspend();
+
+	pm_transition = state;
+	async_error = 0;
+
+	mutex_lock(&dpm_list_mtx);
+
+	/*
+	 * Start processing "async" leaf devices upfront so they don't need to
+	 * wait for the "sync" devices they don't depend on.
+	 */
+	list_for_each_entry_reverse(dev, &dpm_prepared_list, power.entry) {
+		dpm_clear_async_state(dev);
+		if (dpm_leaf_device(dev))
+			dpm_async_with_cleanup(dev, async_suspend);
+	}
+
+	while (!list_empty(&dpm_prepared_list)) {
+		dev = to_device(dpm_prepared_list.prev);
+
+		list_move(&dev->power.entry, &dpm_suspended_list);
+
+		if (dpm_async_fn(dev, async_suspend))
+			continue;
+
+		get_device(dev);
+
+		mutex_unlock(&dpm_list_mtx);
+
+		device_suspend(dev, state, false);
+
+		put_device(dev);
+
+		mutex_lock(&dpm_list_mtx);
+
+		if (READ_ONCE(async_error)) {
+			dpm_async_suspend_complete_all(&dpm_prepared_list);
+			/*
+			 * Move all devices to the target list to resume them
+			 * properly.
+			 */
+			list_splice_init(&dpm_prepared_list, &dpm_suspended_list);
+			break;
+		}
+	}
+
+	mutex_unlock(&dpm_list_mtx);
+
+	async_synchronize_full();
+
+	error = READ_ONCE(async_error);
+	if (error)
+		dpm_save_failed_step(SUSPEND_SUSPEND);
+
+	dpm_show_time(starttime, state, error, NULL);
+	trace_suspend_resume(TPS("dpm_suspend"), state.event, false);
+	return error;
+}
+
+static bool device_prepare_smart_suspend(struct device *dev)
+{
+	struct device_link *link;
+	bool ret = true;
+	int idx;
+
+	/*
+	 * The "smart suspend" feature is enabled for devices whose drivers ask
+	 * for it and for devices without PM callbacks.
+	 *
+	 * However, if "smart suspend" is not enabled for the device's parent
+	 * or any of its suppliers that take runtime PM into account, it cannot
+	 * be enabled for the device either.
+	 */
+	if (!dev->power.no_pm_callbacks &&
+	    !dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND))
+		return false;
+
+	if (dev->parent && !dev_pm_smart_suspend(dev->parent) &&
+	    !dev->parent->power.ignore_children && !pm_runtime_blocked(dev->parent))
+		return false;
+
+	idx = device_links_read_lock();
+
+	dev_for_each_link_to_supplier(link, dev) {
+		if (!device_link_test(link, DL_FLAG_PM_RUNTIME))
+			continue;
+
+		if (!dev_pm_smart_suspend(link->supplier) &&
+		    !pm_runtime_blocked(link->supplier)) {
+			ret = false;
+			break;
+		}
+	}
+
+	device_links_read_unlock(idx);
+
+	return ret;
+}
+
+/**
+ * device_prepare - Prepare a device for system power transition.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute the ->prepare() callback(s) for given device.  No new children of the
+ * device may be registered after this function has returned.
+ */
+static int device_prepare(struct device *dev, pm_message_t state)
+{
+	int (*callback)(struct device *) = NULL;
+	bool smart_suspend;
+	int ret = 0;
+
+	/*
+	 * If a device's parent goes into runtime suspend at the wrong time,
+	 * it won't be possible to resume the device.  To prevent this we
+	 * block runtime suspend here, during the prepare phase, and allow
+	 * it again during the complete phase.
+	 */
+	pm_runtime_get_noresume(dev);
+	/*
+	 * If runtime PM is disabled for the device at this point and it has
+	 * never been enabled so far, it should not be enabled until this system
+	 * suspend-resume cycle is complete, so prepare to trigger a warning on
+	 * subsequent attempts to enable it.
+	 */
+	smart_suspend = !pm_runtime_block_if_disabled(dev);
+
+	if (dev->power.syscore)
+		return 0;
+
+	device_lock(dev);
+
+	dev->power.wakeup_path = false;
+	dev->power.out_band_wakeup = false;
+
+	if (dev->power.no_pm_callbacks)
+		goto unlock;
+
+	if (dev->pm_domain)
+		callback = dev->pm_domain->ops.prepare;
+	else if (dev->type && dev->type->pm)
+		callback = dev->type->pm->prepare;
+	else if (dev->class && dev->class->pm)
+		callback = dev->class->pm->prepare;
+	else if (dev->bus && dev->bus->pm)
+		callback = dev->bus->pm->prepare;
+
+	if (!callback && dev->driver && dev->driver->pm)
+		callback = dev->driver->pm->prepare;
+
+	if (callback)
+		ret = callback(dev);
+
+unlock:
+	device_unlock(dev);
+
+	if (ret < 0) {
+		suspend_report_result(dev, callback, ret);
+		pm_runtime_unblock(dev);
+		pm_runtime_put(dev);
+		return ret;
+	}
+	/* Do not enable "smart suspend" for devices with disabled runtime PM. */
+	if (smart_suspend)
+		smart_suspend = device_prepare_smart_suspend(dev);
+
+	spin_lock_irq(&dev->power.lock);
+
+	dev->power.smart_suspend = smart_suspend;
+	/*
+	 * A positive return value from ->prepare() means "this device appears
+	 * to be runtime-suspended and its state is fine, so if it really is
+	 * runtime-suspended, you can leave it in that state provided that you
+	 * will do the same thing with all of its descendants".  This only
+	 * applies to suspend transitions, however.
+	 */
+	dev->power.direct_complete = state.event == PM_EVENT_SUSPEND &&
+		(ret > 0 || dev->power.no_pm_callbacks) &&
+		!dev_pm_test_driver_flags(dev, DPM_FLAG_NO_DIRECT_COMPLETE);
+
+	spin_unlock_irq(&dev->power.lock);
+
+	return 0;
+}
+
+/**
+ * dpm_prepare - Prepare all non-sysdev devices for a system PM transition.
+ * @state: PM transition of the system being carried out.
+ *
+ * Execute the ->prepare() callback(s) for all devices.
+ */
+int dpm_prepare(pm_message_t state)
+{
+	int error = 0;
+
+	trace_suspend_resume(TPS("dpm_prepare"), state.event, true);
+
+	/*
+	 * Give a chance for the known devices to complete their probes, before
+	 * disable probing of devices. This sync point is important at least
+	 * at boot time + hibernation restore.
+	 */
+	wait_for_device_probe();
+	/*
+	 * It is unsafe if probing of devices will happen during suspend or
+	 * hibernation and system behavior will be unpredictable in this case.
+	 * So, let's prohibit device's probing here and defer their probes
+	 * instead. The normal behavior will be restored in dpm_complete().
+	 */
+	device_block_probing();
+	/* Suspend thermal control. */
+	thermal_pm_prepare();
+
+	mutex_lock(&dpm_list_mtx);
+	while (!list_empty(&dpm_list) && !error) {
+		struct device *dev = to_device(dpm_list.next);
+
+		get_device(dev);
+
+		mutex_unlock(&dpm_list_mtx);
+
+		trace_device_pm_callback_start(dev, "", state.event);
+		error = device_prepare(dev, state);
+		trace_device_pm_callback_end(dev, error);
+
+		mutex_lock(&dpm_list_mtx);
+
+		if (!error) {
+			dev->power.is_prepared = true;
+			if (!list_empty(&dev->power.entry))
+				list_move_tail(&dev->power.entry, &dpm_prepared_list);
+		} else if (error == -EAGAIN) {
+			error = 0;
+		} else {
+			dev_info(dev, "not prepared for power transition: code %d\n",
+				 error);
+		}
+
+		mutex_unlock(&dpm_list_mtx);
+
+		put_device(dev);
+
+		mutex_lock(&dpm_list_mtx);
+	}
+	mutex_unlock(&dpm_list_mtx);
+	trace_suspend_resume(TPS("dpm_prepare"), state.event, false);
+	return error;
+}
+
+/**
+ * dpm_suspend_start - Prepare devices for PM transition and suspend them.
+ * @state: PM transition of the system being carried out.
+ *
+ * Prepare all non-sysdev devices for system PM transition and execute "suspend"
+ * callbacks for them.
+ */
+int dpm_suspend_start(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+	int error;
+
+	error = dpm_prepare(state);
+	if (error)
+		dpm_save_failed_step(SUSPEND_PREPARE);
+	else {
+		pm_restrict_gfp_mask();
+		error = dpm_suspend(state);
+	}
+
+	dpm_show_time(starttime, state, error, "start");
+	return error;
+}
+EXPORT_SYMBOL_GPL(dpm_suspend_start);
+
+void __suspend_report_result(const char *function, struct device *dev, void *fn, int ret)
+{
+	if (ret)
+		dev_err(dev, "%s(): %ps returns %d\n", function, fn, ret);
+}
+EXPORT_SYMBOL_GPL(__suspend_report_result);
+
+/**
+ * device_pm_wait_for_dev - Wait for suspend/resume of a device to complete.
+ * @subordinate: Device that needs to wait for @dev.
+ * @dev: Device to wait for.
+ */
+int device_pm_wait_for_dev(struct device *subordinate, struct device *dev)
+{
+	dpm_wait(dev, subordinate->power.async_suspend);
+	return async_error;
+}
+EXPORT_SYMBOL_GPL(device_pm_wait_for_dev);
+
+/**
+ * dpm_for_each_dev - device iterator.
+ * @data: data for the callback.
+ * @fn: function to be called for each device.
+ *
+ * Iterate over devices in dpm_list, and call @fn for each device,
+ * passing it @data.
+ */
+void dpm_for_each_dev(void *data, void (*fn)(struct device *, void *))
+{
+	struct device *dev;
+
+	if (!fn)
+		return;
+
+	device_pm_lock();
+	list_for_each_entry(dev, &dpm_list, power.entry)
+		fn(dev, data);
+	device_pm_unlock();
+}
+EXPORT_SYMBOL_GPL(dpm_for_each_dev);
+
+static bool pm_ops_is_empty(const struct dev_pm_ops *ops)
+{
+	if (!ops)
+		return true;
+
+	return !ops->prepare &&
+	       !ops->suspend &&
+	       !ops->suspend_late &&
+	       !ops->suspend_noirq &&
+	       !ops->resume_noirq &&
+	       !ops->resume_early &&
+	       !ops->resume &&
+	       !ops->complete;
+}
+
+void device_pm_check_callbacks(struct device *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	dev->power.no_pm_callbacks =
+		(!dev->bus || (pm_ops_is_empty(dev->bus->pm) &&
+		 !dev->bus->suspend && !dev->bus->resume)) &&
+		(!dev->class || pm_ops_is_empty(dev->class->pm)) &&
+		(!dev->type || pm_ops_is_empty(dev->type->pm)) &&
+		(!dev->pm_domain || pm_ops_is_empty(&dev->pm_domain->ops)) &&
+		(!dev->driver || (pm_ops_is_empty(dev->driver->pm) &&
+		 !dev->driver->suspend && !dev->driver->resume));
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+
+bool dev_pm_skip_suspend(struct device *dev)
+{
+	return dev_pm_smart_suspend(dev) && pm_runtime_status_suspended(dev);
+}
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
new file mode 100644
index 000000000..8823aceea
--- /dev/null
+++ b/drivers/base/power/power.h
@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/pm_qos.h>
+
+static inline void device_pm_init_common(struct device *dev)
+{
+	if (!dev->power.early_init) {
+		spin_lock_init(&dev->power.lock);
+		dev->power.qos = NULL;
+		dev->power.early_init = true;
+	}
+}
+
+#ifdef CONFIG_PM
+
+static inline void pm_runtime_early_init(struct device *dev)
+{
+	dev->power.disable_depth = 1;
+	device_pm_init_common(dev);
+}
+
+extern void pm_runtime_init(struct device *dev);
+extern void pm_runtime_reinit(struct device *dev);
+extern void pm_runtime_remove(struct device *dev);
+extern u64 pm_runtime_active_time(struct device *dev);
+
+#define WAKE_IRQ_DEDICATED_ALLOCATED	BIT(0)
+#define WAKE_IRQ_DEDICATED_MANAGED	BIT(1)
+#define WAKE_IRQ_DEDICATED_REVERSE	BIT(2)
+#define WAKE_IRQ_DEDICATED_MASK		(WAKE_IRQ_DEDICATED_ALLOCATED | \
+					 WAKE_IRQ_DEDICATED_MANAGED | \
+					 WAKE_IRQ_DEDICATED_REVERSE)
+#define WAKE_IRQ_DEDICATED_ENABLED	BIT(3)
+
+struct wake_irq {
+	struct device *dev;
+	unsigned int status;
+	int irq;
+	const char *name;
+};
+
+extern void dev_pm_arm_wake_irq(struct wake_irq *wirq);
+extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq);
+extern void dev_pm_enable_wake_irq_check(struct device *dev,
+					 bool can_change_status);
+extern void dev_pm_disable_wake_irq_check(struct device *dev, bool cond_disable);
+extern void dev_pm_enable_wake_irq_complete(struct device *dev);
+
+#ifdef CONFIG_PM_SLEEP
+
+extern void device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq);
+extern void device_wakeup_detach_irq(struct device *dev);
+extern void device_wakeup_arm_wake_irqs(void);
+extern void device_wakeup_disarm_wake_irqs(void);
+
+#else
+
+static inline void device_wakeup_attach_irq(struct device *dev,
+					    struct wake_irq *wakeirq) {}
+
+static inline void device_wakeup_detach_irq(struct device *dev)
+{
+}
+
+#endif /* CONFIG_PM_SLEEP */
+
+/*
+ * 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);
+extern int pm_qos_sysfs_add_latency_tolerance(struct device *dev);
+extern void pm_qos_sysfs_remove_latency_tolerance(struct device *dev);
+extern int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid);
+
+#else /* CONFIG_PM */
+
+static inline void pm_runtime_early_init(struct device *dev)
+{
+	device_pm_init_common(dev);
+}
+
+static inline void pm_runtime_init(struct device *dev) {}
+static inline void pm_runtime_reinit(struct device *dev) {}
+static inline void pm_runtime_remove(struct device *dev) {}
+
+static inline int dpm_sysfs_add(struct device *dev) { return 0; }
+static inline void dpm_sysfs_remove(struct device *dev) {}
+static inline int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid,
+					 kgid_t kgid) { return 0; }
+
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+
+/* kernel/power/main.c */
+extern int pm_async_enabled;
+
+/* drivers/base/power/main.c */
+extern struct list_head dpm_list;	/* The active device list */
+
+static inline struct device *to_device(struct list_head *entry)
+{
+	return container_of(entry, struct device, power.entry);
+}
+
+extern void device_pm_sleep_init(struct device *dev);
+extern void device_pm_add(struct device *);
+extern void device_pm_remove(struct device *);
+extern void device_pm_move_before(struct device *, struct device *);
+extern void device_pm_move_after(struct device *, struct device *);
+extern void device_pm_move_last(struct device *);
+extern void device_pm_check_callbacks(struct device *dev);
+
+static inline bool device_pm_initialized(struct device *dev)
+{
+	return dev->power.in_dpm_list;
+}
+
+/* drivers/base/power/wakeup_stats.c */
+extern int wakeup_source_sysfs_add(struct device *parent,
+				   struct wakeup_source *ws);
+extern void wakeup_source_sysfs_remove(struct wakeup_source *ws);
+
+extern int pm_wakeup_source_sysfs_add(struct device *parent);
+
+#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_check_callbacks(struct device *dev) {}
+
+static inline bool device_pm_initialized(struct device *dev)
+{
+	return device_is_registered(dev);
+}
+
+static inline int pm_wakeup_source_sysfs_add(struct device *parent)
+{
+	return 0;
+}
+
+#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_BPF_SYSCALL
+struct bpf_ws_lock { };
+struct bpf_ws_lock *bpf_wakeup_sources_read_lock(void);
+void bpf_wakeup_sources_read_unlock(struct bpf_ws_lock *lock);
+void *bpf_wakeup_sources_get_head(void);
+#endif
diff --git a/drivers/base/power/qos-test.c b/drivers/base/power/qos-test.c
new file mode 100644
index 000000000..79fc6c441
--- /dev/null
+++ b/drivers/base/power/qos-test.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 NXP
+ */
+#include <kunit/test.h>
+#include <linux/pm_qos.h>
+
+/* Basic test for aggregating two "min" requests */
+static void freq_qos_test_min(struct kunit *test)
+{
+	struct freq_constraints	qos;
+	struct freq_qos_request	req1, req2;
+	int ret;
+
+	freq_constraints_init(&qos);
+	memset(&req1, 0, sizeof(req1));
+	memset(&req2, 0, sizeof(req2));
+
+	ret = freq_qos_add_request(&qos, &req1, FREQ_QOS_MIN, 1000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	ret = freq_qos_add_request(&qos, &req2, FREQ_QOS_MIN, 2000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 2000);
+
+	ret = freq_qos_remove_request(&req2);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 1000);
+
+	ret = freq_qos_remove_request(&req1);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN),
+			FREQ_QOS_MIN_DEFAULT_VALUE);
+}
+
+/* Test that requests for MAX_DEFAULT_VALUE have no effect */
+static void freq_qos_test_maxdef(struct kunit *test)
+{
+	struct freq_constraints	qos;
+	struct freq_qos_request	req1, req2;
+	int ret;
+
+	freq_constraints_init(&qos);
+	memset(&req1, 0, sizeof(req1));
+	memset(&req2, 0, sizeof(req2));
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX),
+			FREQ_QOS_MAX_DEFAULT_VALUE);
+
+	ret = freq_qos_add_request(&qos, &req1, FREQ_QOS_MAX,
+			FREQ_QOS_MAX_DEFAULT_VALUE);
+	KUNIT_EXPECT_EQ(test, ret, 0);
+	ret = freq_qos_add_request(&qos, &req2, FREQ_QOS_MAX,
+			FREQ_QOS_MAX_DEFAULT_VALUE);
+	KUNIT_EXPECT_EQ(test, ret, 0);
+
+	/* Add max 1000 */
+	ret = freq_qos_update_request(&req1, 1000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 1000);
+
+	/* Add max 2000, no impact */
+	ret = freq_qos_update_request(&req2, 2000);
+	KUNIT_EXPECT_EQ(test, ret, 0);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 1000);
+
+	/* Remove max 1000, new max 2000 */
+	ret = freq_qos_remove_request(&req1);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 2000);
+}
+
+/*
+ * Test that a freq_qos_request can be added again after removal
+ *
+ * This issue was solved by commit 05ff1ba412fd ("PM: QoS: Invalidate frequency
+ * QoS requests after removal")
+ */
+static void freq_qos_test_readd(struct kunit *test)
+{
+	struct freq_constraints	qos;
+	struct freq_qos_request	req;
+	int ret;
+
+	freq_constraints_init(&qos);
+	memset(&req, 0, sizeof(req));
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN),
+			FREQ_QOS_MIN_DEFAULT_VALUE);
+
+	/* Add */
+	ret = freq_qos_add_request(&qos, &req, FREQ_QOS_MIN, 1000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 1000);
+
+	/* Remove */
+	ret = freq_qos_remove_request(&req);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN),
+			FREQ_QOS_MIN_DEFAULT_VALUE);
+
+	/* Add again */
+	ret = freq_qos_add_request(&qos, &req, FREQ_QOS_MIN, 2000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 2000);
+}
+
+static struct kunit_case pm_qos_test_cases[] = {
+	KUNIT_CASE(freq_qos_test_min),
+	KUNIT_CASE(freq_qos_test_maxdef),
+	KUNIT_CASE(freq_qos_test_readd),
+	{},
+};
+
+static struct kunit_suite pm_qos_test_module = {
+	.name = "qos-kunit-test",
+	.test_cases = pm_qos_test_cases,
+};
+kunit_test_suites(&pm_qos_test_module);
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
new file mode 100644
index 000000000..9b69827cb
--- /dev/null
+++ b/drivers/base/power/qos.c
@@ -0,0 +1,983 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Devices PM QoS constraints management
+ *
+ * Copyright (C) 2011 Texas Instruments, Inc.
+ *
+ * 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 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.
+ *
+ * Note about the per-device constraint data struct allocation:
+ * . The per-device constraints data struct ptr is stored 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);
+
+/**
+ * __dev_pm_qos_flags - Check PM QoS flags for a given device.
+ * @dev: Device to check the PM QoS flags for.
+ * @mask: Flags to check against.
+ *
+ * This routine must be called with dev->power.lock held.
+ */
+enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask)
+{
+	struct dev_pm_qos *qos = dev->power.qos;
+	struct pm_qos_flags *pqf;
+	s32 val;
+
+	lockdep_assert_held(&dev->power.lock);
+
+	if (IS_ERR_OR_NULL(qos))
+		return PM_QOS_FLAGS_UNDEFINED;
+
+	pqf = &qos->flags;
+	if (list_empty(&pqf->list))
+		return PM_QOS_FLAGS_UNDEFINED;
+
+	val = pqf->effective_flags & mask;
+	if (val)
+		return (val == mask) ? PM_QOS_FLAGS_ALL : PM_QOS_FLAGS_SOME;
+
+	return PM_QOS_FLAGS_NONE;
+}
+
+/**
+ * dev_pm_qos_flags - Check PM QoS flags for a given device (locked).
+ * @dev: Device to check the PM QoS flags for.
+ * @mask: Flags to check against.
+ */
+enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask)
+{
+	unsigned long irqflags;
+	enum pm_qos_flags_status ret;
+
+	spin_lock_irqsave(&dev->power.lock, irqflags);
+	ret = __dev_pm_qos_flags(dev, mask);
+	spin_unlock_irqrestore(&dev->power.lock, irqflags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_flags);
+
+/**
+ * __dev_pm_qos_resume_latency - Get resume latency 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_resume_latency(struct device *dev)
+{
+	lockdep_assert_held(&dev->power.lock);
+
+	return dev_pm_qos_raw_resume_latency(dev);
+}
+
+/**
+ * dev_pm_qos_read_value - Get PM QoS constraint for a given device (locked).
+ * @dev: Device to get the PM QoS constraint value for.
+ * @type: QoS request type.
+ */
+s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type)
+{
+	struct dev_pm_qos *qos = dev->power.qos;
+	unsigned long flags;
+	s32 ret;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT
+			: pm_qos_read_value(&qos->resume_latency);
+		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE
+			: freq_qos_read_value(&qos->freq, FREQ_QOS_MIN);
+		break;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE
+			: freq_qos_read_value(&qos->freq, FREQ_QOS_MAX);
+		break;
+	default:
+		WARN_ON(1);
+		ret = 0;
+	}
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_read_value);
+
+/**
+ * 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 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:
+		if (WARN_ON(action != PM_QOS_REMOVE_REQ && value < 0))
+			value = 0;
+
+		ret = pm_qos_update_target(&qos->resume_latency,
+					   &req->data.pnode, action, value);
+		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_MIN_FREQUENCY:
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = freq_qos_apply(&req->data.freq, action, 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_obj(*qos);
+	if (!qos)
+		return -ENOMEM;
+
+	n = kzalloc_objs(*n, 3);
+	if (!n) {
+		kfree(qos);
+		return -ENOMEM;
+	}
+
+	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_NO_CONSTRAINT;
+	c->type = PM_QOS_MIN;
+	c->notifiers = n;
+	BLOCKING_INIT_NOTIFIER_HEAD(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;
+
+	freq_constraints_init(&qos->freq);
+
+	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));
+	}
+
+	c = &qos->freq.min_freq;
+	plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) {
+		apply_constraint(req, PM_QOS_REMOVE_REQ,
+				 PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
+
+	c = &qos->freq.max_freq;
+	plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) {
+		apply_constraint(req, PM_QOS_REMOVE_REQ,
+				 PM_QOS_MAX_FREQUENCY_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(qos->resume_latency.notifiers);
+	kfree(qos);
+
+ out:
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+}
+
+static bool dev_pm_qos_invalid_req_type(struct device *dev,
+					enum dev_pm_qos_req_type type)
+{
+	return 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 || !req || dev_pm_qos_invalid_req_type(dev, type))
+		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)
+		return ret;
+
+	req->dev = dev;
+	req->type = type;
+	if (req->type == DEV_PM_QOS_MIN_FREQUENCY)
+		ret = freq_qos_add_request(&dev->power.qos->freq,
+					   &req->data.freq,
+					   FREQ_QOS_MIN, value);
+	else if (req->type == DEV_PM_QOS_MAX_FREQUENCY)
+		ret = freq_qos_add_request(&dev->power.qos->freq,
+					   &req->data.freq,
+					   FREQ_QOS_MAX, value);
+	else
+		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_MIN_FREQUENCY:
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		curr_value = req->data.freq.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.
+ * @type: request type.
+ *
+ * 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,
+			    enum dev_pm_qos_req_type type)
+{
+	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)
+		goto unlock;
+
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers,
+						       notifier);
+		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		ret = freq_qos_add_notifier(&dev->power.qos->freq,
+					    FREQ_QOS_MIN, notifier);
+		break;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = freq_qos_add_notifier(&dev->power.qos->freq,
+					    FREQ_QOS_MAX, notifier);
+		break;
+	default:
+		WARN_ON(1);
+		ret = -EINVAL;
+	}
+
+unlock:
+	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.
+ * @type: request type.
+ *
+ * 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,
+			       enum dev_pm_qos_req_type type)
+{
+	int ret = 0;
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	/* Silently return if the constraints object is not present. */
+	if (IS_ERR_OR_NULL(dev->power.qos))
+		goto unlock;
+
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers,
+							 notifier);
+		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		ret = freq_qos_remove_notifier(&dev->power.qos->freq,
+					       FREQ_QOS_MIN, notifier);
+		break;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = freq_qos_remove_notifier(&dev->power.qos->freq,
+					       FREQ_QOS_MAX, notifier);
+		break;
+	default:
+		WARN_ON(1);
+		ret = -EINVAL;
+	}
+
+unlock:
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier);
+
+/**
+ * dev_pm_qos_add_ancestor_request - Add PM QoS request for device's ancestor.
+ * @dev: Device whose ancestor to add the request for.
+ * @req: Pointer to the preallocated handle.
+ * @type: Type of the request.
+ * @value: Constraint latency value.
+ */
+int dev_pm_qos_add_ancestor_request(struct device *dev,
+				    struct dev_pm_qos_request *req,
+				    enum dev_pm_qos_req_type type, s32 value)
+{
+	struct device *ancestor = dev->parent;
+	int ret = -ENODEV;
+
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		while (ancestor && !ancestor->power.ignore_children)
+			ancestor = ancestor->parent;
+
+		break;
+	case DEV_PM_QOS_LATENCY_TOLERANCE:
+		while (ancestor && !ancestor->power.set_latency_tolerance)
+			ancestor = ancestor->parent;
+
+		break;
+	default:
+		ancestor = NULL;
+	}
+	if (ancestor)
+		ret = dev_pm_qos_add_request(ancestor, req, type, value);
+
+	if (ret < 0)
+		req->dev = NULL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_ancestor_request);
+
+static void __dev_pm_qos_drop_user_request(struct device *dev,
+					   enum dev_pm_qos_req_type type)
+{
+	struct dev_pm_qos_request *req = NULL;
+
+	switch(type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		req = dev->power.qos->resume_latency_req;
+		dev->power.qos->resume_latency_req = NULL;
+		break;
+	case DEV_PM_QOS_LATENCY_TOLERANCE:
+		req = dev->power.qos->latency_tolerance_req;
+		dev->power.qos->latency_tolerance_req = NULL;
+		break;
+	case DEV_PM_QOS_FLAGS:
+		req = dev->power.qos->flags_req;
+		dev->power.qos->flags_req = NULL;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+	__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_obj(*req);
+	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_obj(*req);
+	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) {
+			if (val == PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT)
+				ret = 0;
+			else
+				ret = -EINVAL;
+			goto out;
+		}
+		req = kzalloc_obj(*req);
+		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;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_update_user_latency_tolerance);
+
+/**
+ * dev_pm_qos_expose_latency_tolerance - Expose latency tolerance to userspace
+ * @dev: Device whose latency tolerance to expose
+ */
+int dev_pm_qos_expose_latency_tolerance(struct device *dev)
+{
+	int ret;
+
+	if (!dev->power.set_latency_tolerance)
+		return -EINVAL;
+
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+	ret = pm_qos_sysfs_add_latency_tolerance(dev);
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_tolerance);
+
+/**
+ * dev_pm_qos_hide_latency_tolerance - Hide latency tolerance from userspace
+ * @dev: Device whose latency tolerance to hide
+ */
+void dev_pm_qos_hide_latency_tolerance(struct device *dev)
+{
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+	pm_qos_sysfs_remove_latency_tolerance(dev);
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+
+	/* Remove the request from user space now */
+	pm_runtime_get_sync(dev);
+	dev_pm_qos_update_user_latency_tolerance(dev,
+		PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT);
+	pm_runtime_put(dev);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_tolerance);
diff --git a/drivers/base/power/runtime-test.c b/drivers/base/power/runtime-test.c
new file mode 100644
index 000000000..1535ad2b0
--- /dev/null
+++ b/drivers/base/power/runtime-test.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2025 Google, Inc.
+ */
+
+#include <linux/cleanup.h>
+#include <linux/pm_runtime.h>
+#include <kunit/device.h>
+#include <kunit/test.h>
+
+#define DEVICE_NAME "pm_runtime_test_device"
+
+static void pm_runtime_depth_test(struct kunit *test)
+{
+	struct device *dev = kunit_device_register(test, DEVICE_NAME);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	pm_runtime_enable(dev);
+
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_get_sync(dev));
+	KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev));
+	KUNIT_EXPECT_EQ(test, 1, pm_runtime_get_sync(dev)); /* "already active" */
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_put_sync(dev));
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_put_sync(dev));
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+}
+
+/* Test pm_runtime_put() and friends when already suspended. */
+static void pm_runtime_already_suspended_test(struct kunit *test)
+{
+	struct device *dev = kunit_device_register(test, DEVICE_NAME);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	pm_runtime_enable(dev);
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+
+	pm_runtime_get_noresume(dev);
+	KUNIT_EXPECT_EQ(test, 1, pm_runtime_put_sync(dev));
+
+	KUNIT_EXPECT_EQ(test, 1, pm_runtime_suspend(dev));
+	KUNIT_EXPECT_EQ(test, 1, pm_runtime_autosuspend(dev));
+	KUNIT_EXPECT_EQ(test, 1, pm_request_autosuspend(dev));
+
+	pm_runtime_get_noresume(dev);
+	KUNIT_EXPECT_EQ(test, 1, pm_runtime_put_sync_autosuspend(dev));
+
+	pm_runtime_get_noresume(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	/* Grab 2 refcounts */
+	pm_runtime_get_noresume(dev);
+	pm_runtime_get_noresume(dev);
+	/* The first put() sees usage_count 1 */
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_put_sync_autosuspend(dev));
+	/* The second put() sees usage_count 0 but tells us "already suspended". */
+	KUNIT_EXPECT_EQ(test, 1, pm_runtime_put_sync_autosuspend(dev));
+
+	/* Should have remained suspended the whole time. */
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+}
+
+static void pm_runtime_idle_test(struct kunit *test)
+{
+	struct device *dev = kunit_device_register(test, DEVICE_NAME);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	pm_runtime_enable(dev);
+
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_get_sync(dev));
+	KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev));
+	KUNIT_EXPECT_EQ(test, -EAGAIN, pm_runtime_idle(dev));
+	KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev));
+	pm_runtime_put_noidle(dev);
+	KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev));
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_idle(dev));
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+	KUNIT_EXPECT_EQ(test, -EAGAIN, pm_runtime_idle(dev));
+	KUNIT_EXPECT_EQ(test, -EAGAIN, pm_request_idle(dev));
+}
+
+static void pm_runtime_disabled_test(struct kunit *test)
+{
+	struct device *dev = kunit_device_register(test, DEVICE_NAME);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	/* Never called pm_runtime_enable() */
+	KUNIT_EXPECT_FALSE(test, pm_runtime_enabled(dev));
+
+	/* "disabled" is treated as "active" */
+	KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev));
+	KUNIT_EXPECT_FALSE(test, pm_runtime_suspended(dev));
+
+	/*
+	 * Note: these "fail", but they still acquire/release refcounts, so
+	 * keep them balanced.
+	 */
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_get(dev));
+	pm_runtime_put(dev);
+
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_get_sync(dev));
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_put_sync(dev));
+
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_get(dev));
+	pm_runtime_put_autosuspend(dev);
+
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_resume_and_get(dev));
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_idle(dev));
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_request_idle(dev));
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_request_resume(dev));
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_request_autosuspend(dev));
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_suspend(dev));
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_resume(dev));
+	KUNIT_EXPECT_EQ(test, -EACCES, pm_runtime_autosuspend(dev));
+
+	/* Still disabled */
+	KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev));
+	KUNIT_EXPECT_FALSE(test, pm_runtime_enabled(dev));
+}
+
+static void pm_runtime_error_test(struct kunit *test)
+{
+	struct device *dev = kunit_device_register(test, DEVICE_NAME);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	pm_runtime_enable(dev);
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+
+	/* Fake a .runtime_resume() error */
+	dev->power.runtime_error = -EIO;
+
+	/*
+	 * Note: these "fail", but they still acquire/release refcounts, so
+	 * keep them balanced.
+	 */
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_get(dev));
+	pm_runtime_put(dev);
+
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_get_sync(dev));
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_put_sync(dev));
+
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_get(dev));
+	pm_runtime_put_autosuspend(dev);
+
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_get(dev));
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_put_sync_autosuspend(dev));
+
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_resume_and_get(dev));
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_idle(dev));
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_request_idle(dev));
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_request_resume(dev));
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_request_autosuspend(dev));
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_suspend(dev));
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_resume(dev));
+	KUNIT_EXPECT_EQ(test, -EINVAL, pm_runtime_autosuspend(dev));
+
+	/* Error is still pending */
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+	KUNIT_EXPECT_EQ(test, -EIO, dev->power.runtime_error);
+	/* Clear error */
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_set_suspended(dev));
+	KUNIT_EXPECT_EQ(test, 0, dev->power.runtime_error);
+	/* Still suspended */
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_get(dev));
+	pm_runtime_barrier(dev);
+	pm_runtime_put(dev);
+	pm_runtime_suspend(dev); /* flush the put(), to suspend */
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_get_sync(dev));
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_put_sync(dev));
+
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_get_sync(dev));
+	pm_runtime_put_autosuspend(dev);
+
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_resume_and_get(dev));
+
+	/*
+	 * The following should all return -EAGAIN (usage is non-zero) or 1
+	 * (already resumed).
+	 */
+	KUNIT_EXPECT_EQ(test, -EAGAIN, pm_runtime_idle(dev));
+	KUNIT_EXPECT_EQ(test, -EAGAIN, pm_request_idle(dev));
+	KUNIT_EXPECT_EQ(test, 1, pm_request_resume(dev));
+	KUNIT_EXPECT_EQ(test, -EAGAIN, pm_request_autosuspend(dev));
+	KUNIT_EXPECT_EQ(test, -EAGAIN, pm_runtime_suspend(dev));
+	KUNIT_EXPECT_EQ(test, 1, pm_runtime_resume(dev));
+	KUNIT_EXPECT_EQ(test, -EAGAIN, pm_runtime_autosuspend(dev));
+
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_put_sync(dev));
+
+	/* Suspended again */
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+}
+
+/*
+ * Explore a typical probe() sequence in which a device marks itself powered,
+ * but doesn't hold any runtime PM reference, so it suspends as soon as it goes
+ * idle.
+ */
+static void pm_runtime_probe_active_test(struct kunit *test)
+{
+	struct device *dev = kunit_device_register(test, DEVICE_NAME);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	KUNIT_EXPECT_TRUE(test, pm_runtime_status_suspended(dev));
+
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_set_active(dev));
+	KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev));
+
+	pm_runtime_enable(dev);
+	KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev));
+
+	/* Nothing to flush. We stay active. */
+	pm_runtime_barrier(dev);
+	KUNIT_EXPECT_TRUE(test, pm_runtime_active(dev));
+
+	/* Ask for idle? Now we suspend. */
+	KUNIT_EXPECT_EQ(test, 0, pm_runtime_idle(dev));
+	KUNIT_EXPECT_TRUE(test, pm_runtime_suspended(dev));
+}
+
+static struct kunit_case pm_runtime_test_cases[] = {
+	KUNIT_CASE(pm_runtime_depth_test),
+	KUNIT_CASE(pm_runtime_already_suspended_test),
+	KUNIT_CASE(pm_runtime_idle_test),
+	KUNIT_CASE(pm_runtime_disabled_test),
+	KUNIT_CASE(pm_runtime_error_test),
+	KUNIT_CASE(pm_runtime_probe_active_test),
+	{}
+};
+
+static struct kunit_suite pm_runtime_test_suite = {
+	.name = "pm_runtime_test_cases",
+	.test_cases = pm_runtime_test_cases,
+};
+
+kunit_test_suite(pm_runtime_test_suite);
+MODULE_DESCRIPTION("Runtime power management unit test suite");
+MODULE_LICENSE("GPL");
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
new file mode 100644
index 000000000..fab38bc98
--- /dev/null
+++ b/drivers/base/power/runtime.c
@@ -0,0 +1,2118 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * drivers/base/power/runtime.c - Helper functions for device runtime PM
+ *
+ * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu>
+ */
+#include <linux/sched/mm.h>
+#include <linux/ktime.h>
+#include <linux/hrtimer.h>
+#include <linux/export.h>
+#include <linux/pm_runtime.h>
+#include <linux/pm_wakeirq.h>
+#include <linux/rculist.h>
+#include <trace/events/rpm.h>
+
+#include "../base.h"
+#include "power.h"
+
+typedef int (*pm_callback_t)(struct device *);
+
+static inline pm_callback_t get_callback_ptr(const void *start, size_t offset)
+{
+	return *(pm_callback_t *)(start + offset);
+}
+
+static pm_callback_t __rpm_get_driver_callback(struct device *dev,
+					       size_t cb_offset)
+{
+	if (dev->driver && dev->driver->pm)
+		return get_callback_ptr(dev->driver->pm, cb_offset);
+
+	return NULL;
+}
+
+static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset)
+{
+	const struct dev_pm_ops *ops;
+	pm_callback_t cb = NULL;
+
+	if (dev->pm_domain)
+		ops = &dev->pm_domain->ops;
+	else if (dev->type && dev->type->pm)
+		ops = dev->type->pm;
+	else if (dev->class && dev->class->pm)
+		ops = dev->class->pm;
+	else if (dev->bus && dev->bus->pm)
+		ops = dev->bus->pm;
+	else
+		ops = NULL;
+
+	if (ops)
+		cb = get_callback_ptr(ops, cb_offset);
+
+	if (!cb)
+		cb = __rpm_get_driver_callback(dev, cb_offset);
+
+	return cb;
+}
+
+#define RPM_GET_CALLBACK(dev, callback) \
+		__rpm_get_callback(dev, offsetof(struct dev_pm_ops, callback))
+
+static int rpm_resume(struct device *dev, int rpmflags);
+static int rpm_suspend(struct device *dev, int rpmflags);
+
+/**
+ * update_pm_runtime_accounting - Update the time accounting of power states
+ * @dev: Device to update the accounting for
+ *
+ * In order to be able to have time accounting of the various power states
+ * (as used by programs such as PowerTOP to show the effectiveness of runtime
+ * PM), we need to track the time spent in each state.
+ * update_pm_runtime_accounting must be called each time before the
+ * runtime_status field is updated, to account the time in the old state
+ * correctly.
+ */
+static void update_pm_runtime_accounting(struct device *dev)
+{
+	u64 now, last, delta;
+
+	if (dev->power.disable_depth > 0)
+		return;
+
+	last = dev->power.accounting_timestamp;
+
+	now = ktime_get_mono_fast_ns();
+	dev->power.accounting_timestamp = now;
+
+	/*
+	 * Because ktime_get_mono_fast_ns() is not monotonic during
+	 * timekeeping updates, ensure that 'now' is after the last saved
+	 * timestamp.
+	 */
+	if (now < last)
+		return;
+
+	delta = now - last;
+
+	if (dev->power.runtime_status == RPM_SUSPENDED)
+		dev->power.suspended_time += delta;
+	else
+		dev->power.active_time += delta;
+}
+
+static void __update_runtime_status(struct device *dev, enum rpm_status status)
+{
+	update_pm_runtime_accounting(dev);
+	trace_rpm_status(dev, status);
+	dev->power.runtime_status = status;
+}
+
+static u64 rpm_get_accounted_time(struct device *dev, bool suspended)
+{
+	u64 time;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	update_pm_runtime_accounting(dev);
+	time = suspended ? dev->power.suspended_time : dev->power.active_time;
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return time;
+}
+
+u64 pm_runtime_active_time(struct device *dev)
+{
+	return rpm_get_accounted_time(dev, false);
+}
+
+u64 pm_runtime_suspended_time(struct device *dev)
+{
+	return rpm_get_accounted_time(dev, true);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_suspended_time);
+
+/**
+ * pm_runtime_deactivate_timer - Deactivate given device's suspend timer.
+ * @dev: Device to handle.
+ */
+static void pm_runtime_deactivate_timer(struct device *dev)
+{
+	if (dev->power.timer_expires > 0) {
+		hrtimer_try_to_cancel(&dev->power.suspend_timer);
+		dev->power.timer_expires = 0;
+	}
+}
+
+/**
+ * pm_runtime_cancel_pending - Deactivate suspend timer and cancel requests.
+ * @dev: Device to handle.
+ */
+static void pm_runtime_cancel_pending(struct device *dev)
+{
+	pm_runtime_deactivate_timer(dev);
+	/*
+	 * In case there's a request pending, make sure its work function will
+	 * return without doing anything.
+	 */
+	dev->power.request = RPM_REQ_NONE;
+}
+
+/*
+ * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time.
+ * @dev: Device to handle.
+ *
+ * Compute the autosuspend-delay expiration time based on the device's
+ * power.last_busy time.  If the delay has already expired or is disabled
+ * (negative) or the power.use_autosuspend flag isn't set, return 0.
+ * Otherwise return the expiration time in nanoseconds (adjusted to be nonzero).
+ *
+ * This function may be called either with or without dev->power.lock held.
+ * Either way it can be racy, since power.last_busy may be updated at any time.
+ */
+u64 pm_runtime_autosuspend_expiration(struct device *dev)
+{
+	int autosuspend_delay;
+	u64 expires;
+
+	if (!dev->power.use_autosuspend)
+		return 0;
+
+	autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay);
+	if (autosuspend_delay < 0)
+		return 0;
+
+	expires  = READ_ONCE(dev->power.last_busy);
+	expires += (u64)autosuspend_delay * NSEC_PER_MSEC;
+	if (expires > ktime_get_mono_fast_ns())
+		return expires;	/* Expires in the future */
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
+
+static int dev_memalloc_noio(struct device *dev, void *data)
+{
+	return dev->power.memalloc_noio;
+}
+
+/*
+ * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag.
+ * @dev: Device to handle.
+ * @enable: True for setting the flag and False for clearing the flag.
+ *
+ * Set the flag for all devices in the path from the device to the
+ * root device in the device tree if @enable is true, otherwise clear
+ * the flag for devices in the path whose siblings don't set the flag.
+ *
+ * The function should only be called by block device, or network
+ * device driver for solving the deadlock problem during runtime
+ * resume/suspend:
+ *
+ *     If memory allocation with GFP_KERNEL is called inside runtime
+ *     resume/suspend callback of any one of its ancestors(or the
+ *     block device itself), the deadlock may be triggered inside the
+ *     memory allocation since it might not complete until the block
+ *     device becomes active and the involved page I/O finishes. The
+ *     situation is pointed out first by Alan Stern. Network device
+ *     are involved in iSCSI kind of situation.
+ *
+ * The lock of dev_hotplug_mutex is held in the function for handling
+ * hotplug race because pm_runtime_set_memalloc_noio() may be called
+ * in async probe().
+ *
+ * The function should be called between device_add() and device_del()
+ * on the affected device(block/network device).
+ */
+void pm_runtime_set_memalloc_noio(struct device *dev, bool enable)
+{
+	static DEFINE_MUTEX(dev_hotplug_mutex);
+
+	mutex_lock(&dev_hotplug_mutex);
+	for (;;) {
+		bool enabled;
+
+		/* hold power lock since bitfield is not SMP-safe. */
+		spin_lock_irq(&dev->power.lock);
+		enabled = dev->power.memalloc_noio;
+		dev->power.memalloc_noio = enable;
+		spin_unlock_irq(&dev->power.lock);
+
+		/*
+		 * not need to enable ancestors any more if the device
+		 * has been enabled.
+		 */
+		if (enabled && enable)
+			break;
+
+		dev = dev->parent;
+
+		/*
+		 * clear flag of the parent device only if all the
+		 * children don't set the flag because ancestor's
+		 * flag was set by any one of the descendants.
+		 */
+		if (!dev || (!enable &&
+		    device_for_each_child(dev, NULL, dev_memalloc_noio)))
+			break;
+	}
+	mutex_unlock(&dev_hotplug_mutex);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio);
+
+/**
+ * rpm_check_suspend_allowed - Test whether a device may be suspended.
+ * @dev: Device to test.
+ */
+static int rpm_check_suspend_allowed(struct device *dev)
+{
+	int retval = 0;
+
+	if (dev->power.runtime_error)
+		retval = -EINVAL;
+	else if (dev->power.disable_depth > 0)
+		retval = -EACCES;
+	else if (atomic_read(&dev->power.usage_count))
+		retval = -EAGAIN;
+	else if (!dev->power.ignore_children && atomic_read(&dev->power.child_count))
+		retval = -EBUSY;
+
+	/* Pending resume requests take precedence over suspends. */
+	else if ((dev->power.deferred_resume &&
+	    dev->power.runtime_status == RPM_SUSPENDING) ||
+	    (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME))
+		retval = -EAGAIN;
+	else if (__dev_pm_qos_resume_latency(dev) == 0)
+		retval = -EPERM;
+	else if (dev->power.runtime_status == RPM_SUSPENDED)
+		retval = 1;
+
+	return retval;
+}
+
+static int rpm_get_suppliers(struct device *dev)
+{
+	struct device_link *link;
+
+	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
+				device_links_read_lock_held()) {
+		int retval;
+
+		if (!device_link_test(link, DL_FLAG_PM_RUNTIME))
+			continue;
+
+		retval = pm_runtime_get_sync(link->supplier);
+		/* Ignore suppliers with disabled runtime PM. */
+		if (retval < 0 && retval != -EACCES) {
+			pm_runtime_put_noidle(link->supplier);
+			return retval;
+		}
+		refcount_inc(&link->rpm_active);
+	}
+	return 0;
+}
+
+/**
+ * pm_runtime_release_supplier - Drop references to device link's supplier.
+ * @link: Target device link.
+ *
+ * Drop all runtime PM references associated with @link to its supplier device.
+ */
+void pm_runtime_release_supplier(struct device_link *link)
+{
+	struct device *supplier = link->supplier;
+
+	/*
+	 * The additional power.usage_count check is a safety net in case
+	 * the rpm_active refcount becomes saturated, in which case
+	 * refcount_dec_not_one() would return true forever, but it is not
+	 * strictly necessary.
+	 */
+	while (refcount_dec_not_one(&link->rpm_active) &&
+	       atomic_read(&supplier->power.usage_count) > 0)
+		pm_runtime_put_noidle(supplier);
+}
+
+static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend)
+{
+	struct device_link *link;
+
+	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
+				device_links_read_lock_held()) {
+		pm_runtime_release_supplier(link);
+		if (try_to_suspend)
+			pm_request_idle(link->supplier);
+	}
+}
+
+static void rpm_put_suppliers(struct device *dev)
+{
+	__rpm_put_suppliers(dev, true);
+}
+
+static void rpm_suspend_suppliers(struct device *dev)
+{
+	struct device_link *link;
+	int idx = device_links_read_lock();
+
+	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
+				device_links_read_lock_held())
+		pm_request_idle(link->supplier);
+
+	device_links_read_unlock(idx);
+}
+
+/**
+ * __rpm_callback - Run a given runtime PM callback for a given device.
+ * @cb: Runtime PM callback to run.
+ * @dev: Device to run the callback for.
+ */
+static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
+	__releases(&dev->power.lock) __acquires(&dev->power.lock)
+{
+	int retval = 0, idx;
+	bool use_links = dev->power.links_count > 0;
+
+	if (dev->power.irq_safe) {
+		spin_unlock(&dev->power.lock);
+	} else {
+		spin_unlock_irq(&dev->power.lock);
+
+		/*
+		 * Resume suppliers if necessary.
+		 *
+		 * The device's runtime PM status cannot change until this
+		 * routine returns, so it is safe to read the status outside of
+		 * the lock.
+		 */
+		if (use_links && dev->power.runtime_status == RPM_RESUMING) {
+			idx = device_links_read_lock();
+
+			retval = rpm_get_suppliers(dev);
+			if (retval) {
+				rpm_put_suppliers(dev);
+				goto fail;
+			}
+
+			device_links_read_unlock(idx);
+		}
+	}
+
+	if (cb)
+		retval = cb(dev);
+
+	if (dev->power.irq_safe) {
+		spin_lock(&dev->power.lock);
+	} else {
+		/*
+		 * If the device is suspending and the callback has returned
+		 * success, drop the usage counters of the suppliers that have
+		 * been reference counted on its resume.
+		 *
+		 * Do that if resume fails too.
+		 */
+		if (use_links &&
+		    ((dev->power.runtime_status == RPM_SUSPENDING && !retval) ||
+		    (dev->power.runtime_status == RPM_RESUMING && retval))) {
+			idx = device_links_read_lock();
+
+			__rpm_put_suppliers(dev, false);
+
+fail:
+			device_links_read_unlock(idx);
+		}
+
+		spin_lock_irq(&dev->power.lock);
+	}
+
+	return retval;
+}
+
+/**
+ * rpm_callback - Run a given runtime PM callback for a given device.
+ * @cb: Runtime PM callback to run.
+ * @dev: Device to run the callback for.
+ */
+static int rpm_callback(int (*cb)(struct device *), struct device *dev)
+{
+	int retval;
+
+	if (dev->power.memalloc_noio) {
+		unsigned int noio_flag;
+
+		/*
+		 * Deadlock might be caused if memory allocation with
+		 * GFP_KERNEL happens inside runtime_suspend and
+		 * runtime_resume callbacks of one block device's
+		 * ancestor or the block device itself. Network
+		 * device might be thought as part of iSCSI block
+		 * device, so network device and its ancestor should
+		 * be marked as memalloc_noio too.
+		 */
+		noio_flag = memalloc_noio_save();
+		retval = __rpm_callback(cb, dev);
+		memalloc_noio_restore(noio_flag);
+	} else {
+		retval = __rpm_callback(cb, dev);
+	}
+
+	/*
+	 * Since -EACCES means that runtime PM is disabled for the given device,
+	 * it should not be returned by runtime PM callbacks.  If it is returned
+	 * nevertheless, assume it to be a transient error and convert it to
+	 * -EAGAIN.
+	 */
+	if (retval == -EACCES)
+		retval = -EAGAIN;
+
+	return retval;
+}
+
+/**
+ * rpm_idle - Notify device bus type if the device can be suspended.
+ * @dev: Device to notify the bus type about.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's runtime PM status allows it to be suspended.  If
+ * another idle notification has been started earlier, return immediately.  If
+ * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise
+ * run the ->runtime_idle() callback directly. If the ->runtime_idle callback
+ * doesn't exist or if it returns 0, call rpm_suspend with the RPM_AUTO flag.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static int rpm_idle(struct device *dev, int rpmflags)
+{
+	int (*callback)(struct device *);
+	int retval;
+
+	trace_rpm_idle(dev, rpmflags);
+	retval = rpm_check_suspend_allowed(dev);
+	if (retval < 0)
+		;	/* Conditions are wrong. */
+
+	else if ((rpmflags & RPM_GET_PUT) && retval == 1)
+		;	/* put() is allowed in RPM_SUSPENDED */
+
+	/* Idle notifications are allowed only in the RPM_ACTIVE state. */
+	else if (dev->power.runtime_status != RPM_ACTIVE)
+		retval = -EAGAIN;
+
+	/*
+	 * Any pending request other than an idle notification takes
+	 * precedence over us, except that the timer may be running.
+	 */
+	else if (dev->power.request_pending &&
+	    dev->power.request > RPM_REQ_IDLE)
+		retval = -EAGAIN;
+
+	/* Act as though RPM_NOWAIT is always set. */
+	else if (dev->power.idle_notification)
+		retval = -EINPROGRESS;
+
+	if (retval)
+		goto out;
+
+	/* Pending requests need to be canceled. */
+	dev->power.request = RPM_REQ_NONE;
+
+	callback = RPM_GET_CALLBACK(dev, runtime_idle);
+
+	/* If no callback assume success. */
+	if (!callback || dev->power.no_callbacks)
+		goto out;
+
+	/* Carry out an asynchronous or a synchronous idle notification. */
+	if (rpmflags & RPM_ASYNC) {
+		dev->power.request = RPM_REQ_IDLE;
+		if (!dev->power.request_pending) {
+			dev->power.request_pending = true;
+			queue_work(pm_wq, &dev->power.work);
+		}
+		trace_rpm_return_int(dev, _THIS_IP_, 0);
+		return 0;
+	}
+
+	dev->power.idle_notification = true;
+
+	if (dev->power.irq_safe)
+		spin_unlock(&dev->power.lock);
+	else
+		spin_unlock_irq(&dev->power.lock);
+
+	retval = callback(dev);
+
+	if (dev->power.irq_safe)
+		spin_lock(&dev->power.lock);
+	else
+		spin_lock_irq(&dev->power.lock);
+
+	dev->power.idle_notification = false;
+	wake_up_all(&dev->power.wait_queue);
+
+ out:
+	trace_rpm_return_int(dev, _THIS_IP_, retval);
+	return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO);
+}
+
+/**
+ * rpm_suspend - Carry out runtime suspend of given device.
+ * @dev: Device to suspend.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's runtime PM status allows it to be suspended.
+ * Cancel a pending idle notification, autosuspend or suspend. If
+ * another suspend has been started earlier, either return immediately
+ * or wait for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC
+ * flags. If the RPM_ASYNC flag is set then queue a suspend request;
+ * otherwise run the ->runtime_suspend() callback directly. When
+ * ->runtime_suspend succeeded, if a deferred resume was requested while
+ * the callback was running then carry it out, otherwise send an idle
+ * notification for its parent (if the suspend succeeded and both
+ * ignore_children of parent->power and irq_safe of dev->power are not set).
+ * If ->runtime_suspend failed with -EAGAIN or -EBUSY, and if the RPM_AUTO
+ * flag is set and the next autosuspend-delay expiration time is in the
+ * future, schedule another autosuspend attempt.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static int rpm_suspend(struct device *dev, int rpmflags)
+	__releases(&dev->power.lock) __acquires(&dev->power.lock)
+{
+	int (*callback)(struct device *);
+	struct device *parent = NULL;
+	int retval;
+
+	trace_rpm_suspend(dev, rpmflags);
+
+ repeat:
+	retval = rpm_check_suspend_allowed(dev);
+	if (retval < 0)
+		goto out;	/* Conditions are wrong. */
+
+	/* Synchronous suspends are not allowed in the RPM_RESUMING state. */
+	if (dev->power.runtime_status == RPM_RESUMING && !(rpmflags & RPM_ASYNC))
+		retval = -EAGAIN;
+
+	if (retval)
+		goto out;
+
+	/* If the autosuspend_delay time hasn't expired yet, reschedule. */
+	if ((rpmflags & RPM_AUTO) && dev->power.runtime_status != RPM_SUSPENDING) {
+		u64 expires = pm_runtime_autosuspend_expiration(dev);
+
+		if (expires != 0) {
+			/* Pending requests need to be canceled. */
+			dev->power.request = RPM_REQ_NONE;
+
+			/*
+			 * Optimization: If the timer is already running and is
+			 * set to expire at or before the autosuspend delay,
+			 * avoid the overhead of resetting it.  Just let it
+			 * expire; pm_suspend_timer_fn() will take care of the
+			 * rest.
+			 */
+			if (!(dev->power.timer_expires &&
+			    dev->power.timer_expires <= expires)) {
+				/*
+				 * We add a slack of 25% to gather wakeups
+				 * without sacrificing the granularity.
+				 */
+				u64 slack = (u64)READ_ONCE(dev->power.autosuspend_delay) *
+						    (NSEC_PER_MSEC >> 2);
+
+				dev->power.timer_expires = expires;
+				hrtimer_start_range_ns(&dev->power.suspend_timer,
+						       ns_to_ktime(expires),
+						       slack,
+						       HRTIMER_MODE_ABS);
+			}
+			dev->power.timer_autosuspends = 1;
+			goto out;
+		}
+	}
+
+	/* Other scheduled or pending requests need to be canceled. */
+	pm_runtime_cancel_pending(dev);
+
+	if (dev->power.runtime_status == RPM_SUSPENDING) {
+		DEFINE_WAIT(wait);
+
+		if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
+			retval = -EINPROGRESS;
+			goto out;
+		}
+
+		if (dev->power.irq_safe) {
+			spin_unlock(&dev->power.lock);
+
+			cpu_relax();
+
+			spin_lock(&dev->power.lock);
+			goto repeat;
+		}
+
+		/* Wait for the other suspend running in parallel with us. */
+		for (;;) {
+			prepare_to_wait(&dev->power.wait_queue, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (dev->power.runtime_status != RPM_SUSPENDING)
+				break;
+
+			spin_unlock_irq(&dev->power.lock);
+
+			schedule();
+
+			spin_lock_irq(&dev->power.lock);
+		}
+		finish_wait(&dev->power.wait_queue, &wait);
+		goto repeat;
+	}
+
+	if (dev->power.no_callbacks)
+		goto no_callback;	/* Assume success. */
+
+	/* Carry out an asynchronous or a synchronous suspend. */
+	if (rpmflags & RPM_ASYNC) {
+		dev->power.request = (rpmflags & RPM_AUTO) ?
+		    RPM_REQ_AUTOSUSPEND : RPM_REQ_SUSPEND;
+		if (!dev->power.request_pending) {
+			dev->power.request_pending = true;
+			queue_work(pm_wq, &dev->power.work);
+		}
+		goto out;
+	}
+
+	__update_runtime_status(dev, RPM_SUSPENDING);
+
+	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
+
+	dev_pm_enable_wake_irq_check(dev, true);
+	retval = rpm_callback(callback, dev);
+	if (retval)
+		goto fail;
+
+	dev_pm_enable_wake_irq_complete(dev);
+
+ no_callback:
+	__update_runtime_status(dev, RPM_SUSPENDED);
+	pm_runtime_deactivate_timer(dev);
+
+	if (dev->parent) {
+		parent = dev->parent;
+		atomic_add_unless(&parent->power.child_count, -1, 0);
+	}
+	wake_up_all(&dev->power.wait_queue);
+
+	if (dev->power.deferred_resume) {
+		dev->power.deferred_resume = false;
+		rpm_resume(dev, 0);
+		retval = -EAGAIN;
+		goto out;
+	}
+
+	if (dev->power.irq_safe)
+		goto out;
+
+	/* Maybe the parent is now able to suspend. */
+	if (parent && !parent->power.ignore_children) {
+		spin_unlock(&dev->power.lock);
+
+		spin_lock(&parent->power.lock);
+		rpm_idle(parent, RPM_ASYNC);
+		spin_unlock(&parent->power.lock);
+
+		spin_lock(&dev->power.lock);
+	}
+	/* Maybe the suppliers are now able to suspend. */
+	if (dev->power.links_count > 0) {
+		spin_unlock_irq(&dev->power.lock);
+
+		rpm_suspend_suppliers(dev);
+
+		spin_lock_irq(&dev->power.lock);
+	}
+
+ out:
+	trace_rpm_return_int(dev, _THIS_IP_, retval);
+
+	return retval;
+
+ fail:
+	dev_pm_disable_wake_irq_check(dev, true);
+	__update_runtime_status(dev, RPM_ACTIVE);
+	dev->power.deferred_resume = false;
+	wake_up_all(&dev->power.wait_queue);
+
+	if (retval != -EAGAIN && retval != -EBUSY)
+		dev->power.runtime_error = retval;
+
+	/*
+	 * On transient errors, if the callback routine failed an autosuspend,
+	 * and if the last_busy time has been updated so that there is a new
+	 * autosuspend expiration time, automatically reschedule another
+	 * autosuspend.
+	 */
+	if (!dev->power.runtime_error && (rpmflags & RPM_AUTO) &&
+	    pm_runtime_autosuspend_expiration(dev) != 0)
+		goto repeat;
+
+	pm_runtime_cancel_pending(dev);
+
+	goto out;
+}
+
+/**
+ * rpm_resume - Carry out runtime resume of given device.
+ * @dev: Device to resume.
+ * @rpmflags: Flag bits.
+ *
+ * Check if the device's runtime PM status allows it to be resumed.  Cancel
+ * any scheduled or pending requests.  If another resume has been started
+ * earlier, either return immediately or wait for it to finish, depending on the
+ * RPM_NOWAIT and RPM_ASYNC flags.  Similarly, if there's a suspend running in
+ * parallel with this function, either tell the other process to resume after
+ * suspending (deferred_resume) or wait for it to finish.  If the RPM_ASYNC
+ * flag is set then queue a resume request; otherwise run the
+ * ->runtime_resume() callback directly.  Queue an idle notification for the
+ * device if the resume succeeded.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static int rpm_resume(struct device *dev, int rpmflags)
+	__releases(&dev->power.lock) __acquires(&dev->power.lock)
+{
+	int (*callback)(struct device *);
+	struct device *parent = NULL;
+	int retval = 0;
+
+	trace_rpm_resume(dev, rpmflags);
+
+ repeat:
+	if (dev->power.runtime_error) {
+		retval = -EINVAL;
+	} else if (dev->power.disable_depth > 0) {
+		if (dev->power.runtime_status == RPM_ACTIVE &&
+		    dev->power.last_status == RPM_ACTIVE)
+			retval = 1;
+		else if (rpmflags & RPM_TRANSPARENT)
+			goto out;
+		else
+			retval = -EACCES;
+	}
+	if (retval)
+		goto out;
+
+	/*
+	 * Other scheduled or pending requests need to be canceled.  Small
+	 * optimization: If an autosuspend timer is running, leave it running
+	 * rather than cancelling it now only to restart it again in the near
+	 * future.
+	 */
+	dev->power.request = RPM_REQ_NONE;
+	if (!dev->power.timer_autosuspends)
+		pm_runtime_deactivate_timer(dev);
+
+	if (dev->power.runtime_status == RPM_ACTIVE) {
+		retval = 1;
+		goto out;
+	}
+
+	if (dev->power.runtime_status == RPM_RESUMING ||
+	    dev->power.runtime_status == RPM_SUSPENDING) {
+		DEFINE_WAIT(wait);
+
+		if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) {
+			if (dev->power.runtime_status == RPM_SUSPENDING) {
+				dev->power.deferred_resume = true;
+				if (rpmflags & RPM_NOWAIT)
+					retval = -EINPROGRESS;
+			} else {
+				retval = -EINPROGRESS;
+			}
+			goto out;
+		}
+
+		if (dev->power.irq_safe) {
+			spin_unlock(&dev->power.lock);
+
+			cpu_relax();
+
+			spin_lock(&dev->power.lock);
+			goto repeat;
+		}
+
+		/* Wait for the operation carried out in parallel with us. */
+		for (;;) {
+			prepare_to_wait(&dev->power.wait_queue, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (dev->power.runtime_status != RPM_RESUMING &&
+			    dev->power.runtime_status != RPM_SUSPENDING)
+				break;
+
+			spin_unlock_irq(&dev->power.lock);
+
+			schedule();
+
+			spin_lock_irq(&dev->power.lock);
+		}
+		finish_wait(&dev->power.wait_queue, &wait);
+		goto repeat;
+	}
+
+	/*
+	 * See if we can skip waking up the parent.  This is safe only if
+	 * power.no_callbacks is set, because otherwise we don't know whether
+	 * the resume will actually succeed.
+	 */
+	if (dev->power.no_callbacks && !parent && dev->parent) {
+		spin_lock_nested(&dev->parent->power.lock, SINGLE_DEPTH_NESTING);
+		if (dev->parent->power.disable_depth > 0 ||
+		    dev->parent->power.ignore_children ||
+		    dev->parent->power.runtime_status == RPM_ACTIVE) {
+			atomic_inc(&dev->parent->power.child_count);
+			spin_unlock(&dev->parent->power.lock);
+			retval = 1;
+			goto no_callback;	/* Assume success. */
+		}
+		spin_unlock(&dev->parent->power.lock);
+	}
+
+	/* Carry out an asynchronous or a synchronous resume. */
+	if (rpmflags & RPM_ASYNC) {
+		dev->power.request = RPM_REQ_RESUME;
+		if (!dev->power.request_pending) {
+			dev->power.request_pending = true;
+			queue_work(pm_wq, &dev->power.work);
+		}
+		retval = 0;
+		goto out;
+	}
+
+	if (!parent && dev->parent) {
+		/*
+		 * Increment the parent's usage counter and resume it if
+		 * necessary.  Not needed if dev is irq-safe; then the
+		 * parent is permanently resumed.
+		 */
+		parent = dev->parent;
+		if (dev->power.irq_safe)
+			goto skip_parent;
+
+		spin_unlock(&dev->power.lock);
+
+		pm_runtime_get_noresume(parent);
+
+		spin_lock(&parent->power.lock);
+		/*
+		 * Resume the parent if it has runtime PM enabled and not been
+		 * set to ignore its children.
+		 */
+		if (!parent->power.disable_depth &&
+		    !parent->power.ignore_children) {
+			rpm_resume(parent, 0);
+			if (parent->power.runtime_status != RPM_ACTIVE)
+				retval = -EBUSY;
+		}
+		spin_unlock(&parent->power.lock);
+
+		spin_lock(&dev->power.lock);
+		if (retval)
+			goto out;
+
+		goto repeat;
+	}
+ skip_parent:
+
+	if (dev->power.no_callbacks)
+		goto no_callback;	/* Assume success. */
+
+	__update_runtime_status(dev, RPM_RESUMING);
+
+	callback = RPM_GET_CALLBACK(dev, runtime_resume);
+
+	dev_pm_disable_wake_irq_check(dev, false);
+	retval = rpm_callback(callback, dev);
+	if (retval) {
+		__update_runtime_status(dev, RPM_SUSPENDED);
+		pm_runtime_cancel_pending(dev);
+		dev_pm_enable_wake_irq_check(dev, false);
+	} else {
+ no_callback:
+		__update_runtime_status(dev, RPM_ACTIVE);
+		pm_runtime_mark_last_busy(dev);
+		if (parent)
+			atomic_inc(&parent->power.child_count);
+	}
+	wake_up_all(&dev->power.wait_queue);
+
+	if (retval >= 0)
+		rpm_idle(dev, RPM_ASYNC);
+
+ out:
+	if (parent && !dev->power.irq_safe) {
+		spin_unlock_irq(&dev->power.lock);
+
+		pm_runtime_put(parent);
+
+		spin_lock_irq(&dev->power.lock);
+	}
+
+	trace_rpm_return_int(dev, _THIS_IP_, retval);
+
+	return retval;
+}
+
+/**
+ * pm_runtime_work - Universal runtime PM work function.
+ * @work: Work structure used for scheduling the execution of this function.
+ *
+ * Use @work to get the device object the work is to be done for, determine what
+ * is to be done and execute the appropriate runtime PM function.
+ */
+static void pm_runtime_work(struct work_struct *work)
+{
+	struct device *dev = container_of(work, struct device, power.work);
+	enum rpm_request req;
+
+	spin_lock_irq(&dev->power.lock);
+
+	if (!dev->power.request_pending)
+		goto out;
+
+	req = dev->power.request;
+	dev->power.request = RPM_REQ_NONE;
+	dev->power.request_pending = false;
+
+	switch (req) {
+	case RPM_REQ_NONE:
+		break;
+	case RPM_REQ_IDLE:
+		rpm_idle(dev, RPM_NOWAIT);
+		break;
+	case RPM_REQ_SUSPEND:
+		rpm_suspend(dev, RPM_NOWAIT);
+		break;
+	case RPM_REQ_AUTOSUSPEND:
+		rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO);
+		break;
+	case RPM_REQ_RESUME:
+		rpm_resume(dev, RPM_NOWAIT);
+		break;
+	}
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+}
+
+/**
+ * pm_suspend_timer_fn - Timer function for pm_schedule_suspend().
+ * @timer: hrtimer used by pm_schedule_suspend().
+ *
+ * Check if the time is right and queue a suspend request.
+ */
+static enum hrtimer_restart  pm_suspend_timer_fn(struct hrtimer *timer)
+{
+	struct device *dev = container_of(timer, struct device, power.suspend_timer);
+	unsigned long flags;
+	u64 expires;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	expires = dev->power.timer_expires;
+	/*
+	 * If 'expires' is after the current time, we've been called
+	 * too early.
+	 */
+	if (expires > 0 && expires <= ktime_get_mono_fast_ns()) {
+		dev->power.timer_expires = 0;
+		rpm_suspend(dev, dev->power.timer_autosuspends ?
+		    (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC);
+	}
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return HRTIMER_NORESTART;
+}
+
+/**
+ * pm_schedule_suspend - Set up a timer to submit a suspend request in future.
+ * @dev: Device to suspend.
+ * @delay: Time to wait before submitting a suspend request, in milliseconds.
+ */
+int pm_schedule_suspend(struct device *dev, unsigned int delay)
+{
+	unsigned long flags;
+	u64 expires;
+	int retval;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	if (!delay) {
+		retval = rpm_suspend(dev, RPM_ASYNC);
+		goto out;
+	}
+
+	retval = rpm_check_suspend_allowed(dev);
+	if (retval)
+		goto out;
+
+	/* Other scheduled or pending requests need to be canceled. */
+	pm_runtime_cancel_pending(dev);
+
+	expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC;
+	dev->power.timer_expires = expires;
+	dev->power.timer_autosuspends = 0;
+	hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS);
+
+ out:
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(pm_schedule_suspend);
+
+static int rpm_drop_usage_count(struct device *dev)
+{
+	int ret;
+
+	ret = atomic_sub_return(1, &dev->power.usage_count);
+	if (ret >= 0)
+		return ret;
+
+	/*
+	 * Because rpm_resume() does not check the usage counter, it will resume
+	 * the device even if the usage counter is 0 or negative, so it is
+	 * sufficient to increment the usage counter here to reverse the change
+	 * made above.
+	 */
+	atomic_inc(&dev->power.usage_count);
+	dev_warn(dev, "Runtime PM usage count underflow!\n");
+	return -EINVAL;
+}
+
+/**
+ * __pm_runtime_idle - Entry point for runtime idle operations.
+ * @dev: Device to send idle notification for.
+ * @rpmflags: Flag bits.
+ *
+ * If the RPM_GET_PUT flag is set, decrement the device's usage count and
+ * return immediately if it is larger than zero (if it becomes negative, log a
+ * warning, increment it, and return an error).  Then carry out an idle
+ * notification, either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set,
+ * or if pm_runtime_irq_safe() has been called.
+ */
+int __pm_runtime_idle(struct device *dev, int rpmflags)
+{
+	unsigned long flags;
+	int retval;
+
+	if (rpmflags & RPM_GET_PUT) {
+		retval = rpm_drop_usage_count(dev);
+		if (retval < 0) {
+			return retval;
+		} else if (retval > 0) {
+			trace_rpm_usage(dev, rpmflags);
+			return 0;
+		}
+	}
+
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	retval = rpm_idle(dev, rpmflags);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_idle);
+
+/**
+ * __pm_runtime_suspend - Entry point for runtime put/suspend operations.
+ * @dev: Device to suspend.
+ * @rpmflags: Flag bits.
+ *
+ * If the RPM_GET_PUT flag is set, decrement the device's usage count and
+ * return immediately if it is larger than zero (if it becomes negative, log a
+ * warning, increment it, and return an error).  Then carry out a suspend,
+ * either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set,
+ * or if pm_runtime_irq_safe() has been called.
+ */
+int __pm_runtime_suspend(struct device *dev, int rpmflags)
+{
+	unsigned long flags;
+	int retval;
+
+	if (rpmflags & RPM_GET_PUT) {
+		retval = rpm_drop_usage_count(dev);
+		if (retval < 0) {
+			return retval;
+		} else if (retval > 0) {
+			trace_rpm_usage(dev, rpmflags);
+			return 0;
+		}
+	}
+
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	retval = rpm_suspend(dev, rpmflags);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_suspend);
+
+/**
+ * __pm_runtime_resume - Entry point for runtime resume operations.
+ * @dev: Device to resume.
+ * @rpmflags: Flag bits.
+ *
+ * If the RPM_GET_PUT flag is set, increment the device's usage count.  Then
+ * carry out a resume, either synchronous or asynchronous.
+ *
+ * This routine may be called in atomic context if the RPM_ASYNC flag is set,
+ * or if pm_runtime_irq_safe() has been called.
+ */
+int __pm_runtime_resume(struct device *dev, int rpmflags)
+{
+	unsigned long flags;
+	int retval;
+
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe &&
+			dev->power.runtime_status != RPM_ACTIVE);
+
+	if (rpmflags & RPM_GET_PUT)
+		atomic_inc(&dev->power.usage_count);
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	retval = rpm_resume(dev, rpmflags);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_resume);
+
+/**
+ * pm_runtime_get_conditional - Conditionally bump up device usage counter.
+ * @dev: Device to handle.
+ * @ign_usage_count: Whether or not to look at the current usage counter value.
+ *
+ * Return -EINVAL if runtime PM is disabled for @dev.
+ *
+ * Otherwise, if its runtime PM status is %RPM_ACTIVE and (1) @ign_usage_count
+ * is set, or (2) @dev is not ignoring children and its active child count is
+ * nonzero, or (3) the runtime PM usage counter of @dev is not zero, increment
+ * the usage counter of @dev and return 1.
+ *
+ * Otherwise, return 0 without changing the usage counter.
+ *
+ * If @ign_usage_count is %true, this function can be used to prevent suspending
+ * the device when its runtime PM status is %RPM_ACTIVE.
+ *
+ * If @ign_usage_count is %false, this function can be used to prevent
+ * suspending the device when both its runtime PM status is %RPM_ACTIVE and its
+ * runtime PM usage counter is not zero.
+ *
+ * The caller is responsible for decrementing the runtime PM usage counter of
+ * @dev after this function has returned a positive value for it.
+ */
+static int pm_runtime_get_conditional(struct device *dev, bool ign_usage_count)
+{
+	unsigned long flags;
+	int retval;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	if (dev->power.disable_depth > 0) {
+		retval = -EINVAL;
+	} else if (dev->power.runtime_status != RPM_ACTIVE) {
+		retval = 0;
+	} else if (ign_usage_count || (!dev->power.ignore_children &&
+		   atomic_read(&dev->power.child_count) > 0)) {
+		retval = 1;
+		atomic_inc(&dev->power.usage_count);
+	} else {
+		retval = atomic_inc_not_zero(&dev->power.usage_count);
+	}
+	trace_rpm_usage(dev, 0);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return retval;
+}
+
+/**
+ * pm_runtime_get_if_active - Bump up runtime PM usage counter if the device is
+ *			      in active state
+ * @dev: Target device.
+ *
+ * Increment the runtime PM usage counter of @dev if its runtime PM status is
+ * %RPM_ACTIVE, in which case it returns 1. If the device is in a different
+ * state, 0 is returned. -EINVAL is returned if runtime PM is disabled for the
+ * device, in which case also the usage_count will remain unmodified.
+ */
+int pm_runtime_get_if_active(struct device *dev)
+{
+	return pm_runtime_get_conditional(dev, true);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_get_if_active);
+
+/**
+ * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter.
+ * @dev: Target device.
+ *
+ * Increment the runtime PM usage counter of @dev if its runtime PM status is
+ * %RPM_ACTIVE and its runtime PM usage counter is greater than 0 or it is not
+ * ignoring children and its active child count is nonzero.  1 is returned in
+ * this case.
+ *
+ * If @dev is in a different state or it is not in use (that is, its usage
+ * counter is 0, or it is ignoring children, or its active child count is 0),
+ * 0 is returned.
+ *
+ * -EINVAL is returned if runtime PM is disabled for the device, in which case
+ * also the usage counter of @dev is not updated.
+ */
+int pm_runtime_get_if_in_use(struct device *dev)
+{
+	return pm_runtime_get_conditional(dev, false);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use);
+
+/**
+ * __pm_runtime_set_status - Set runtime PM status of a device.
+ * @dev: Device to handle.
+ * @status: New runtime PM status of the device.
+ *
+ * If runtime PM of the device is disabled or its power.runtime_error field is
+ * different from zero, the status may be changed either to RPM_ACTIVE, or to
+ * RPM_SUSPENDED, as long as that reflects the actual state of the device.
+ * However, if the device has a parent and the parent is not active, and the
+ * parent's power.ignore_children flag is unset, the device's status cannot be
+ * set to RPM_ACTIVE, so -EBUSY is returned in that case.
+ *
+ * If successful, __pm_runtime_set_status() clears the power.runtime_error field
+ * and the device parent's counter of unsuspended children is modified to
+ * reflect the new status.  If the new status is RPM_SUSPENDED, an idle
+ * notification request for the parent is submitted.
+ *
+ * If @dev has any suppliers (as reflected by device links to them), and @status
+ * is RPM_ACTIVE, they will be activated upfront and if the activation of one
+ * of them fails, the status of @dev will be changed to RPM_SUSPENDED (instead
+ * of the @status value) and the suppliers will be deacticated on exit.  The
+ * error returned by the failing supplier activation will be returned in that
+ * case.
+ */
+int __pm_runtime_set_status(struct device *dev, unsigned int status)
+{
+	struct device *parent = dev->parent;
+	bool notify_parent = false;
+	unsigned long flags;
+	int error = 0;
+
+	if (status != RPM_ACTIVE && status != RPM_SUSPENDED)
+		return -EINVAL;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	/*
+	 * Prevent PM-runtime from being enabled for the device or return an
+	 * error if it is enabled already and working.
+	 */
+	if (dev->power.runtime_error || dev->power.disable_depth)
+		dev->power.disable_depth++;
+	else
+		error = -EAGAIN;
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	if (error)
+		return error;
+
+	/*
+	 * If the new status is RPM_ACTIVE, the suppliers can be activated
+	 * upfront regardless of the current status, because next time
+	 * rpm_put_suppliers() runs, the rpm_active refcounts of the links
+	 * involved will be dropped down to one anyway.
+	 */
+	if (status == RPM_ACTIVE) {
+		int idx = device_links_read_lock();
+
+		error = rpm_get_suppliers(dev);
+		if (error)
+			status = RPM_SUSPENDED;
+
+		device_links_read_unlock(idx);
+	}
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	if (dev->power.runtime_status == status || !parent)
+		goto out_set;
+
+	if (status == RPM_SUSPENDED) {
+		atomic_add_unless(&parent->power.child_count, -1, 0);
+		notify_parent = !parent->power.ignore_children;
+	} else {
+		spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING);
+
+		/*
+		 * It is invalid to put an active child under a parent that is
+		 * not active, has runtime PM enabled and the
+		 * 'power.ignore_children' flag unset.
+		 */
+		if (!parent->power.disable_depth &&
+		    !parent->power.ignore_children &&
+		    parent->power.runtime_status != RPM_ACTIVE) {
+			dev_err(dev, "runtime PM trying to activate child device %s but parent (%s) is not active\n",
+				dev_name(dev),
+				dev_name(parent));
+			error = -EBUSY;
+		} else if (dev->power.runtime_status == RPM_SUSPENDED) {
+			atomic_inc(&parent->power.child_count);
+		}
+
+		spin_unlock(&parent->power.lock);
+
+		if (error) {
+			status = RPM_SUSPENDED;
+			goto out;
+		}
+	}
+
+ out_set:
+	__update_runtime_status(dev, status);
+	if (!error)
+		dev->power.runtime_error = 0;
+
+ out:
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	if (notify_parent)
+		pm_request_idle(parent);
+
+	if (status == RPM_SUSPENDED) {
+		int idx = device_links_read_lock();
+
+		rpm_put_suppliers(dev);
+
+		device_links_read_unlock(idx);
+	}
+
+	pm_runtime_enable(dev);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_set_status);
+
+/**
+ * __pm_runtime_barrier - Cancel pending requests and wait for completions.
+ * @dev: Device to handle.
+ *
+ * Flush all pending requests for the device from pm_wq and wait for all
+ * runtime PM operations involving the device in progress to complete.
+ *
+ * Should be called under dev->power.lock with interrupts disabled.
+ */
+static void __pm_runtime_barrier(struct device *dev)
+{
+	pm_runtime_deactivate_timer(dev);
+
+	if (dev->power.request_pending) {
+		dev->power.request = RPM_REQ_NONE;
+		spin_unlock_irq(&dev->power.lock);
+
+		cancel_work_sync(&dev->power.work);
+
+		spin_lock_irq(&dev->power.lock);
+		dev->power.request_pending = false;
+	}
+
+	if (dev->power.runtime_status == RPM_SUSPENDING ||
+	    dev->power.runtime_status == RPM_RESUMING ||
+	    dev->power.idle_notification) {
+		DEFINE_WAIT(wait);
+
+		/* Suspend, wake-up or idle notification in progress. */
+		for (;;) {
+			prepare_to_wait(&dev->power.wait_queue, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (dev->power.runtime_status != RPM_SUSPENDING
+			    && dev->power.runtime_status != RPM_RESUMING
+			    && !dev->power.idle_notification)
+				break;
+			spin_unlock_irq(&dev->power.lock);
+
+			schedule();
+
+			spin_lock_irq(&dev->power.lock);
+		}
+		finish_wait(&dev->power.wait_queue, &wait);
+	}
+}
+
+/**
+ * pm_runtime_barrier - Flush pending requests and wait for completions.
+ * @dev: Device to handle.
+ *
+ * Prevent the device from being suspended by incrementing its usage counter and
+ * if there's a pending resume request for the device, wake the device up.
+ * Next, make sure that all pending requests for the device have been flushed
+ * from pm_wq and wait for all runtime PM operations involving the device in
+ * progress to complete.
+ */
+void pm_runtime_barrier(struct device *dev)
+{
+	pm_runtime_get_noresume(dev);
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.request_pending
+	    && dev->power.request == RPM_REQ_RESUME)
+		rpm_resume(dev, 0);
+
+	__pm_runtime_barrier(dev);
+
+	spin_unlock_irq(&dev->power.lock);
+	pm_runtime_put_noidle(dev);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_barrier);
+
+bool pm_runtime_block_if_disabled(struct device *dev)
+{
+	bool ret;
+
+	spin_lock_irq(&dev->power.lock);
+
+	ret = !pm_runtime_enabled(dev);
+	if (ret && dev->power.last_status == RPM_INVALID)
+		dev->power.last_status = RPM_BLOCKED;
+
+	spin_unlock_irq(&dev->power.lock);
+
+	return ret;
+}
+
+void pm_runtime_unblock(struct device *dev)
+{
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.last_status == RPM_BLOCKED)
+		dev->power.last_status = RPM_INVALID;
+
+	spin_unlock_irq(&dev->power.lock);
+}
+
+void __pm_runtime_disable(struct device *dev, bool check_resume)
+{
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.disable_depth > 0) {
+		dev->power.disable_depth++;
+		goto out;
+	}
+
+	/*
+	 * Wake up the device if there's a resume request pending, because that
+	 * means there probably is some I/O to process and disabling runtime PM
+	 * shouldn't prevent the device from processing the I/O.
+	 */
+	if (check_resume && dev->power.request_pending &&
+	    dev->power.request == RPM_REQ_RESUME) {
+		/*
+		 * Prevent suspends and idle notifications from being carried
+		 * out after we have woken up the device.
+		 */
+		pm_runtime_get_noresume(dev);
+
+		rpm_resume(dev, 0);
+
+		pm_runtime_put_noidle(dev);
+	}
+
+	/* Update time accounting before disabling PM-runtime. */
+	update_pm_runtime_accounting(dev);
+
+	if (!dev->power.disable_depth++) {
+		__pm_runtime_barrier(dev);
+		dev->power.last_status = dev->power.runtime_status;
+	}
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_disable);
+
+/**
+ * pm_runtime_enable - Enable runtime PM of a device.
+ * @dev: Device to handle.
+ */
+void pm_runtime_enable(struct device *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	if (!dev->power.disable_depth) {
+		dev_warn(dev, "Unbalanced %s!\n", __func__);
+		goto out;
+	}
+
+	if (--dev->power.disable_depth > 0)
+		goto out;
+
+	if (dev->power.last_status == RPM_BLOCKED) {
+		dev_warn(dev, "Attempt to enable runtime PM when it is blocked\n");
+		dump_stack();
+	}
+	dev->power.last_status = RPM_INVALID;
+	dev->power.accounting_timestamp = ktime_get_mono_fast_ns();
+
+	if (dev->power.runtime_status == RPM_SUSPENDED &&
+	    !dev->power.ignore_children &&
+	    atomic_read(&dev->power.child_count) > 0)
+		dev_warn(dev, "Enabling runtime PM for inactive device with active children\n");
+
+out:
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_enable);
+
+static void pm_runtime_set_suspended_action(void *data)
+{
+	pm_runtime_set_suspended(data);
+}
+
+/**
+ * devm_pm_runtime_set_active_enabled - set_active version of devm_pm_runtime_enable.
+ *
+ * @dev: Device to handle.
+ */
+int devm_pm_runtime_set_active_enabled(struct device *dev)
+{
+	int err;
+
+	err = pm_runtime_set_active(dev);
+	if (err)
+		return err;
+
+	err = devm_add_action_or_reset(dev, pm_runtime_set_suspended_action, dev);
+	if (err)
+		return err;
+
+	return devm_pm_runtime_enable(dev);
+}
+EXPORT_SYMBOL_GPL(devm_pm_runtime_set_active_enabled);
+
+static void pm_runtime_disable_action(void *data)
+{
+	pm_runtime_dont_use_autosuspend(data);
+	pm_runtime_disable(data);
+}
+
+/**
+ * devm_pm_runtime_enable - devres-enabled version of pm_runtime_enable.
+ *
+ * NOTE: this will also handle calling pm_runtime_dont_use_autosuspend() for
+ * you at driver exit time if needed.
+ *
+ * @dev: Device to handle.
+ */
+int devm_pm_runtime_enable(struct device *dev)
+{
+	pm_runtime_enable(dev);
+
+	return devm_add_action_or_reset(dev, pm_runtime_disable_action, dev);
+}
+EXPORT_SYMBOL_GPL(devm_pm_runtime_enable);
+
+static void pm_runtime_put_noidle_action(void *data)
+{
+	pm_runtime_put_noidle(data);
+}
+
+/**
+ * devm_pm_runtime_get_noresume - devres-enabled version of pm_runtime_get_noresume.
+ *
+ * @dev: Device to handle.
+ */
+int devm_pm_runtime_get_noresume(struct device *dev)
+{
+	pm_runtime_get_noresume(dev);
+
+	return devm_add_action_or_reset(dev, pm_runtime_put_noidle_action, dev);
+}
+EXPORT_SYMBOL_GPL(devm_pm_runtime_get_noresume);
+
+/**
+ * pm_runtime_forbid - Block runtime PM of a device.
+ * @dev: Device to handle.
+ *
+ * Resume @dev if already suspended and block runtime suspend of @dev in such
+ * a way that it can be unblocked via the /sys/devices/.../power/control
+ * interface, or otherwise by calling pm_runtime_allow().
+ *
+ * Calling this function many times in a row has the same effect as calling it
+ * once.
+ */
+void pm_runtime_forbid(struct device *dev)
+{
+	spin_lock_irq(&dev->power.lock);
+	if (!dev->power.runtime_auto)
+		goto out;
+
+	dev->power.runtime_auto = false;
+	atomic_inc(&dev->power.usage_count);
+	rpm_resume(dev, 0);
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_forbid);
+
+/**
+ * pm_runtime_allow - Unblock runtime PM of a device.
+ * @dev: Device to handle.
+ *
+ * Unblock runtime suspend of @dev after it has been blocked by
+ * pm_runtime_forbid() (for instance, if it has been blocked via the
+ * /sys/devices/.../power/control interface), check if @dev can be
+ * suspended and suspend it in that case.
+ *
+ * Calling this function many times in a row has the same effect as calling it
+ * once.
+ */
+void pm_runtime_allow(struct device *dev)
+{
+	int ret;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.runtime_auto)
+		goto out;
+
+	dev->power.runtime_auto = true;
+	ret = rpm_drop_usage_count(dev);
+	if (ret == 0)
+		rpm_idle(dev, RPM_AUTO | RPM_ASYNC);
+	else if (ret > 0)
+		trace_rpm_usage(dev, RPM_AUTO | RPM_ASYNC);
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_allow);
+
+/**
+ * pm_runtime_no_callbacks - Ignore runtime PM callbacks for a device.
+ * @dev: Device to handle.
+ *
+ * Set the power.no_callbacks flag, which tells the PM core that this
+ * device is power-managed through its parent and has no runtime PM
+ * callbacks of its own.  The runtime sysfs attributes will be removed.
+ */
+void pm_runtime_no_callbacks(struct device *dev)
+{
+	spin_lock_irq(&dev->power.lock);
+	dev->power.no_callbacks = 1;
+	spin_unlock_irq(&dev->power.lock);
+	if (device_is_registered(dev))
+		rpm_sysfs_remove(dev);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_no_callbacks);
+
+/**
+ * pm_runtime_irq_safe - Leave interrupts disabled during callbacks.
+ * @dev: Device to handle
+ *
+ * Set the power.irq_safe flag, which tells the PM core that the
+ * ->runtime_suspend() and ->runtime_resume() callbacks for this device should
+ * always be invoked with the spinlock held and interrupts disabled.  It also
+ * causes the parent's usage counter to be permanently incremented, preventing
+ * the parent from runtime suspending -- otherwise an irq-safe child might have
+ * to wait for a non-irq-safe parent.
+ */
+void pm_runtime_irq_safe(struct device *dev)
+{
+	if (dev->parent)
+		pm_runtime_get_sync(dev->parent);
+
+	spin_lock_irq(&dev->power.lock);
+	dev->power.irq_safe = 1;
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_irq_safe);
+
+/**
+ * update_autosuspend - Handle a change to a device's autosuspend settings.
+ * @dev: Device to handle.
+ * @old_delay: The former autosuspend_delay value.
+ * @old_use: The former use_autosuspend value.
+ *
+ * Prevent runtime suspend if the new delay is negative and use_autosuspend is
+ * set; otherwise allow it.  Send an idle notification if suspends are allowed.
+ *
+ * This function must be called under dev->power.lock with interrupts disabled.
+ */
+static void update_autosuspend(struct device *dev, int old_delay, int old_use)
+{
+	int delay = dev->power.autosuspend_delay;
+
+	/* Should runtime suspend be prevented now? */
+	if (dev->power.use_autosuspend && delay < 0) {
+
+		/* If it used to be allowed then prevent it. */
+		if (!old_use || old_delay >= 0) {
+			atomic_inc(&dev->power.usage_count);
+			rpm_resume(dev, 0);
+		} else {
+			trace_rpm_usage(dev, 0);
+		}
+	}
+
+	/* Runtime suspend should be allowed now. */
+	else {
+
+		/* If it used to be prevented then allow it. */
+		if (old_use && old_delay < 0)
+			atomic_dec(&dev->power.usage_count);
+
+		/* Maybe we can autosuspend now. */
+		rpm_idle(dev, RPM_AUTO);
+	}
+}
+
+/**
+ * pm_runtime_set_autosuspend_delay - Set a device's autosuspend_delay value.
+ * @dev: Device to handle.
+ * @delay: Value of the new delay in milliseconds.
+ *
+ * Set the device's power.autosuspend_delay value.  If it changes to negative
+ * and the power.use_autosuspend flag is set, prevent runtime suspends.  If it
+ * changes the other way, allow runtime suspends.
+ */
+void pm_runtime_set_autosuspend_delay(struct device *dev, int delay)
+{
+	int old_delay, old_use;
+
+	spin_lock_irq(&dev->power.lock);
+	old_delay = dev->power.autosuspend_delay;
+	old_use = dev->power.use_autosuspend;
+	dev->power.autosuspend_delay = delay;
+	update_autosuspend(dev, old_delay, old_use);
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_autosuspend_delay);
+
+/**
+ * __pm_runtime_use_autosuspend - Set a device's use_autosuspend flag.
+ * @dev: Device to handle.
+ * @use: New value for use_autosuspend.
+ *
+ * Set the device's power.use_autosuspend flag, and allow or prevent runtime
+ * suspends as needed.
+ */
+void __pm_runtime_use_autosuspend(struct device *dev, bool use)
+{
+	int old_delay, old_use;
+
+	spin_lock_irq(&dev->power.lock);
+	old_delay = dev->power.autosuspend_delay;
+	old_use = dev->power.use_autosuspend;
+	dev->power.use_autosuspend = use;
+	update_autosuspend(dev, old_delay, old_use);
+	spin_unlock_irq(&dev->power.lock);
+}
+EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend);
+
+/**
+ * pm_runtime_init - Initialize runtime PM fields in given device object.
+ * @dev: Device object to initialize.
+ */
+void pm_runtime_init(struct device *dev)
+{
+	dev->power.runtime_status = RPM_SUSPENDED;
+	dev->power.last_status = RPM_INVALID;
+	dev->power.idle_notification = false;
+
+	dev->power.disable_depth = 1;
+	atomic_set(&dev->power.usage_count, 0);
+
+	dev->power.runtime_error = 0;
+
+	atomic_set(&dev->power.child_count, 0);
+	pm_suspend_ignore_children(dev, false);
+	dev->power.runtime_auto = true;
+
+	dev->power.request_pending = false;
+	dev->power.request = RPM_REQ_NONE;
+	dev->power.deferred_resume = false;
+	dev->power.needs_force_resume = false;
+	INIT_WORK(&dev->power.work, pm_runtime_work);
+
+	dev->power.timer_expires = 0;
+	hrtimer_setup(&dev->power.suspend_timer, pm_suspend_timer_fn, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS);
+
+	init_waitqueue_head(&dev->power.wait_queue);
+}
+
+/**
+ * pm_runtime_reinit - Re-initialize runtime PM fields in given device object.
+ * @dev: Device object to re-initialize.
+ */
+void pm_runtime_reinit(struct device *dev)
+{
+	if (pm_runtime_enabled(dev))
+		return;
+
+	if (dev->power.runtime_status == RPM_ACTIVE)
+		pm_runtime_set_suspended(dev);
+
+	if (dev->power.irq_safe) {
+		spin_lock_irq(&dev->power.lock);
+		dev->power.irq_safe = 0;
+		spin_unlock_irq(&dev->power.lock);
+		if (dev->parent)
+			pm_runtime_put(dev->parent);
+	}
+	/*
+	 * Clear power.needs_force_resume in case it has been set by
+	 * pm_runtime_force_suspend() invoked from a driver remove callback.
+	 */
+	dev->power.needs_force_resume = false;
+}
+
+/**
+ * pm_runtime_remove - Prepare for removing a device from device hierarchy.
+ * @dev: Device object being removed from device hierarchy.
+ */
+void pm_runtime_remove(struct device *dev)
+{
+	__pm_runtime_disable(dev, false);
+	flush_work(&dev->power.work);
+	pm_runtime_reinit(dev);
+}
+
+/**
+ * pm_runtime_get_suppliers - Resume and reference-count supplier devices.
+ * @dev: Consumer device.
+ */
+void pm_runtime_get_suppliers(struct device *dev)
+{
+	struct device_link *link;
+	int idx;
+
+	idx = device_links_read_lock();
+
+	dev_for_each_link_to_supplier(link, dev)
+		if (device_link_test(link, DL_FLAG_PM_RUNTIME)) {
+			link->supplier_preactivated = true;
+			pm_runtime_get_sync(link->supplier);
+		}
+
+	device_links_read_unlock(idx);
+}
+
+/**
+ * pm_runtime_put_suppliers - Drop references to supplier devices.
+ * @dev: Consumer device.
+ */
+void pm_runtime_put_suppliers(struct device *dev)
+{
+	struct device_link *link;
+	int idx;
+
+	idx = device_links_read_lock();
+
+	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
+				device_links_read_lock_held())
+		if (link->supplier_preactivated) {
+			link->supplier_preactivated = false;
+			pm_runtime_put(link->supplier);
+		}
+
+	device_links_read_unlock(idx);
+}
+
+void pm_runtime_new_link(struct device *dev)
+{
+	spin_lock_irq(&dev->power.lock);
+	dev->power.links_count++;
+	spin_unlock_irq(&dev->power.lock);
+}
+
+static void pm_runtime_drop_link_count(struct device *dev)
+{
+	spin_lock_irq(&dev->power.lock);
+	WARN_ON(dev->power.links_count == 0);
+	dev->power.links_count--;
+	spin_unlock_irq(&dev->power.lock);
+}
+
+/**
+ * pm_runtime_drop_link - Prepare for device link removal.
+ * @link: Device link going away.
+ *
+ * Drop the link count of the consumer end of @link and decrement the supplier
+ * device's runtime PM usage counter as many times as needed to drop all of the
+ * PM runtime reference to it from the consumer.
+ */
+void pm_runtime_drop_link(struct device_link *link)
+{
+	if (!device_link_test(link, DL_FLAG_PM_RUNTIME))
+		return;
+
+	pm_runtime_drop_link_count(link->consumer);
+	pm_runtime_release_supplier(link);
+	pm_request_idle(link->supplier);
+}
+
+static pm_callback_t get_callback(struct device *dev, size_t cb_offset)
+{
+	/*
+	 * Setting power.strict_midlayer means that the middle layer
+	 * code does not want its runtime PM callbacks to be invoked via
+	 * pm_runtime_force_suspend() and pm_runtime_force_resume(), so
+	 * return a direct pointer to the driver callback in that case.
+	 */
+	if (dev_pm_strict_midlayer_is_set(dev))
+		return __rpm_get_driver_callback(dev, cb_offset);
+
+	return __rpm_get_callback(dev, cb_offset);
+}
+
+#define GET_CALLBACK(dev, callback) \
+		get_callback(dev, offsetof(struct dev_pm_ops, callback))
+
+/**
+ * pm_runtime_force_suspend - Force a device into suspend state if needed.
+ * @dev: Device to suspend.
+ *
+ * Disable runtime PM so we safely can check the device's runtime PM status and
+ * if it is active, invoke its ->runtime_suspend callback to suspend it and
+ * change its runtime PM status field to RPM_SUSPENDED.  Also, if the device's
+ * usage and children counters don't indicate that the device was in use before
+ * the system-wide transition under way, decrement its parent's children counter
+ * (if there is a parent).  Keep runtime PM disabled to preserve the state
+ * unless we encounter errors.
+ *
+ * Typically this function may be invoked from a system suspend callback to make
+ * sure the device is put into low power state and it should only be used during
+ * system-wide PM transitions to sleep states.  It assumes that the analogous
+ * pm_runtime_force_resume() will be used to resume the device.
+ */
+int pm_runtime_force_suspend(struct device *dev)
+{
+	int (*callback)(struct device *);
+	int ret;
+
+	pm_runtime_disable(dev);
+	if (pm_runtime_status_suspended(dev) || dev->power.needs_force_resume)
+		return 0;
+
+	callback = GET_CALLBACK(dev, runtime_suspend);
+
+	dev_pm_enable_wake_irq_check(dev, true);
+	ret = callback ? callback(dev) : 0;
+	if (ret)
+		goto err;
+
+	dev_pm_enable_wake_irq_complete(dev);
+
+	/*
+	 * If the device can stay in suspend after the system-wide transition
+	 * to the working state that will follow, drop the children counter of
+	 * its parent and the usage counters of its suppliers.  Otherwise, set
+	 * power.needs_force_resume to let pm_runtime_force_resume() know that
+	 * the device needs to be taken care of and to prevent this function
+	 * from handling the device again in case the device is passed to it
+	 * once more subsequently.
+	 */
+	if (pm_runtime_need_not_resume(dev))
+		pm_runtime_set_suspended(dev);
+	else
+		dev->power.needs_force_resume = true;
+
+	return 0;
+
+err:
+	dev_pm_disable_wake_irq_check(dev, true);
+	pm_runtime_enable(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_force_suspend);
+
+#ifdef CONFIG_PM_SLEEP
+
+/**
+ * pm_runtime_force_resume - Force a device into resume state if needed.
+ * @dev: Device to resume.
+ *
+ * This function expects that either pm_runtime_force_suspend() has put the
+ * device into a low-power state prior to calling it, or the device had been
+ * runtime-suspended before the preceding system-wide suspend transition and it
+ * was left in suspend during that transition.
+ *
+ * The actions carried out by pm_runtime_force_suspend(), or by a runtime
+ * suspend in general, are reversed and the device is brought back into full
+ * power if it is expected to be used on system resume, which is the case when
+ * its needs_force_resume flag is set or when its smart_suspend flag is set and
+ * its runtime PM status is "active".
+ *
+ * In other cases, the resume is deferred to be managed via runtime PM.
+ *
+ * Typically, this function may be invoked from a system resume callback.
+ */
+int pm_runtime_force_resume(struct device *dev)
+{
+	int (*callback)(struct device *);
+	int ret = 0;
+
+	if (!dev->power.needs_force_resume && (!dev_pm_smart_suspend(dev) ||
+	    pm_runtime_status_suspended(dev)))
+		goto out;
+
+	callback = GET_CALLBACK(dev, runtime_resume);
+
+	dev_pm_disable_wake_irq_check(dev, false);
+	ret = callback ? callback(dev) : 0;
+	if (ret) {
+		pm_runtime_set_suspended(dev);
+		dev_pm_enable_wake_irq_check(dev, false);
+		goto out;
+	}
+
+	pm_runtime_mark_last_busy(dev);
+
+out:
+	/*
+	 * The smart_suspend flag can be cleared here because it is not going
+	 * to be necessary until the next system-wide suspend transition that
+	 * will update it again.
+	 */
+	dev->power.smart_suspend = false;
+	/*
+	 * Also clear needs_force_resume to make this function skip devices that
+	 * have been seen by it once.
+	 */
+	dev->power.needs_force_resume = false;
+
+	pm_runtime_enable(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_force_resume);
+
+bool pm_runtime_need_not_resume(struct device *dev)
+{
+	return atomic_read(&dev->power.usage_count) <= 1 &&
+		(atomic_read(&dev->power.child_count) == 0 ||
+		 dev->power.ignore_children);
+}
+
+#endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
new file mode 100644
index 000000000..13b31a3ad
--- /dev/null
+++ b/drivers/base/power/sysfs.c
@@ -0,0 +1,835 @@
+// SPDX-License-Identifier: GPL-2.0
+/* sysfs entries for device PM */
+#include <linux/device.h>
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/export.h>
+#include <linux/pm_qos.h>
+#include <linux/pm_runtime.h>
+#include <linux/atomic.h>
+#include <linux/jiffies.h>
+#include "power.h"
+
+/*
+ *	control - Report/change current runtime PM setting of the device
+ *
+ *	Runtime power management of a device can be blocked with the help of
+ *	this attribute.  All devices have one of the following two values for
+ *	the power/control file:
+ *
+ *	 + "auto\n" to allow the device to be power managed at run time;
+ *	 + "on\n" to prevent the device from being power managed at run time;
+ *
+ *	The default for all devices is "auto", which means that devices may be
+ *	subject to automatic power management, depending on their drivers.
+ *	Changing this attribute to "on" prevents the driver from power managing
+ *	the device at run time.  Doing that while the device is suspended causes
+ *	it to be woken up.
+ *
+ *	wakeup - Report/change current wakeup option for device
+ *
+ *	Some devices support "wakeup" events, which are hardware signals
+ *	used to activate devices from suspended or low power states.  Such
+ *	devices have one of three values for the sysfs power/wakeup file:
+ *
+ *	 + "enabled\n" to issue the events;
+ *	 + "disabled\n" not to do so; or
+ *	 + "\n" for temporary or permanent inability to issue wakeup.
+ *
+ *	(For example, unconfigured USB devices can't issue wakeups.)
+ *
+ *	Familiar examples of devices that can issue wakeup events include
+ *	keyboards and mice (both PS2 and USB styles), power buttons, modems,
+ *	"Wake-On-LAN" Ethernet links, GPIO lines, and more.  Some events
+ *	will wake the entire system from a suspend state; others may just
+ *	wake up the device (if the system as a whole is already active).
+ *	Some wakeup events use normal IRQ lines; other use special out
+ *	of band signaling.
+ *
+ *	It is the responsibility of device drivers to enable (or disable)
+ *	wakeup signaling as part of changing device power states, respecting
+ *	the policy choices provided through the driver model.
+ *
+ *	Devices may not be able to generate wakeup events from all power
+ *	states.  Also, the events may be ignored in some configurations;
+ *	for example, they might need help from other devices that aren't
+ *	active, or which may have wakeup disabled.  Some drivers rely on
+ *	wakeup events internally (unless they are disabled), keeping
+ *	their hardware in low power modes whenever they're unused.  This
+ *	saves runtime power, without requiring system-wide sleep states.
+ *
+ *	async - Report/change current async suspend setting for the device
+ *
+ *	Asynchronous suspend and resume of the device during system-wide power
+ *	state transitions can be enabled by writing "enabled" to this file.
+ *	Analogously, if "disabled" is written to this file, the device will be
+ *	suspended and resumed synchronously.
+ *
+ *	All devices have one of the following two values for power/async:
+ *
+ *	 + "enabled\n" to permit the asynchronous suspend/resume of the device;
+ *	 + "disabled\n" to forbid it;
+ *
+ *	NOTE: It generally is unsafe to permit the asynchronous suspend/resume
+ *	of a device unless it is certain that all of the PM dependencies of the
+ *	device are known to the PM core.  However, for some devices this
+ *	attribute is set to "enabled" by bus type code or device drivers and in
+ *	that cases it should be safe to leave the default value.
+ *
+ *	autosuspend_delay_ms - Report/change a device's autosuspend_delay value
+ *
+ *	Some drivers don't want to carry out a runtime suspend as soon as a
+ *	device becomes idle; they want it always to remain idle for some period
+ *	of time before suspending it.  This period is the autosuspend_delay
+ *	value (expressed in milliseconds) and it can be controlled by the user.
+ *	If the value is negative then the device will never be runtime
+ *	suspended.
+ *
+ *	NOTE: The autosuspend_delay_ms attribute and the autosuspend_delay
+ *	value are used only if the driver calls pm_runtime_use_autosuspend().
+ *
+ *	wakeup_count - Report the number of wakeup events related to the device
+ */
+
+const char power_group_name[] = "power";
+EXPORT_SYMBOL_GPL(power_group_name);
+
+static const char ctrl_auto[] = "auto";
+static const char ctrl_on[] = "on";
+
+static ssize_t control_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sysfs_emit(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)
+{
+	device_lock(dev);
+	if (sysfs_streq(buf, ctrl_auto))
+		pm_runtime_allow(dev);
+	else if (sysfs_streq(buf, ctrl_on))
+		pm_runtime_forbid(dev);
+	else
+		n = -EINVAL;
+	device_unlock(dev);
+	return n;
+}
+
+static DEVICE_ATTR_RW(control);
+
+static ssize_t runtime_active_time_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	u64 tmp = pm_runtime_active_time(dev);
+
+	do_div(tmp, NSEC_PER_MSEC);
+
+	return sysfs_emit(buf, "%llu\n", tmp);
+}
+
+static DEVICE_ATTR_RO(runtime_active_time);
+
+static ssize_t runtime_suspended_time_show(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	u64 tmp = pm_runtime_suspended_time(dev);
+
+	do_div(tmp, NSEC_PER_MSEC);
+
+	return sysfs_emit(buf, "%llu\n", tmp);
+}
+
+static DEVICE_ATTR_RO(runtime_suspended_time);
+
+static ssize_t runtime_status_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	const char *output;
+
+	if (dev->power.runtime_error) {
+		output = "error";
+	} else if (dev->power.disable_depth) {
+		output = "unsupported";
+	} else {
+		switch (dev->power.runtime_status) {
+		case RPM_SUSPENDED:
+			output = "suspended";
+			break;
+		case RPM_SUSPENDING:
+			output = "suspending";
+			break;
+		case RPM_RESUMING:
+			output = "resuming";
+			break;
+		case RPM_ACTIVE:
+			output = "active";
+			break;
+		default:
+			return -EIO;
+		}
+	}
+	return sysfs_emit(buf, "%s\n", output);
+}
+
+static DEVICE_ATTR_RO(runtime_status);
+
+static ssize_t autosuspend_delay_ms_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	if (!dev->power.use_autosuspend)
+		return -EIO;
+
+	return sysfs_emit(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_RW(autosuspend_delay_ms);
+
+static ssize_t pm_qos_resume_latency_us_show(struct device *dev,
+					     struct device_attribute *attr,
+					     char *buf)
+{
+	s32 value = dev_pm_qos_requested_resume_latency(dev);
+
+	if (value == 0)
+		return sysfs_emit(buf, "n/a\n");
+	if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+		value = 0;
+
+	return sysfs_emit(buf, "%d\n", value);
+}
+
+static ssize_t pm_qos_resume_latency_us_store(struct device *dev,
+					      struct device_attribute *attr,
+					      const char *buf, size_t n)
+{
+	s32 value;
+	int ret;
+
+	if (!kstrtos32(buf, 0, &value)) {
+		/*
+		 * Prevent users from writing negative or "no constraint" values
+		 * directly.
+		 */
+		if (value < 0 || value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+			return -EINVAL;
+
+		if (value == 0)
+			value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
+	} else if (sysfs_streq(buf, "n/a")) {
+		value = 0;
+	} else {
+		return -EINVAL;
+	}
+
+	ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req,
+					value);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR_RW(pm_qos_resume_latency_us);
+
+static ssize_t pm_qos_latency_tolerance_us_show(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	s32 value = dev_pm_qos_get_user_latency_tolerance(dev);
+
+	if (value < 0)
+		return sysfs_emit(buf, "%s\n", "auto");
+	if (value == PM_QOS_LATENCY_ANY)
+		return sysfs_emit(buf, "%s\n", "any");
+
+	return sysfs_emit(buf, "%d\n", value);
+}
+
+static ssize_t pm_qos_latency_tolerance_us_store(struct device *dev,
+						 struct device_attribute *attr,
+						 const char *buf, size_t n)
+{
+	s32 value;
+	int ret;
+
+	if (kstrtos32(buf, 0, &value) == 0) {
+		/* Users can't write negative values directly */
+		if (value < 0)
+			return -EINVAL;
+	} else {
+		if (sysfs_streq(buf, "auto"))
+			value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
+		else if (sysfs_streq(buf, "any"))
+			value = PM_QOS_LATENCY_ANY;
+		else
+			return -EINVAL;
+	}
+	ret = dev_pm_qos_update_user_latency_tolerance(dev, value);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR_RW(pm_qos_latency_tolerance_us);
+
+static ssize_t pm_qos_no_power_off_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return sysfs_emit(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_RW(pm_qos_no_power_off);
+
+#ifdef CONFIG_PM_SLEEP
+static const char _enabled[] = "enabled";
+static const char _disabled[] = "disabled";
+
+static ssize_t wakeup_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	return sysfs_emit(buf, "%s\n", device_can_wakeup(dev)
+			  ? (device_may_wakeup(dev) ? _enabled : _disabled)
+			  : "");
+}
+
+static ssize_t wakeup_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t n)
+{
+	if (!device_can_wakeup(dev))
+		return -EINVAL;
+
+	if (sysfs_streq(buf, _enabled))
+		device_set_wakeup_enable(dev, 1);
+	else if (sysfs_streq(buf, _disabled))
+		device_set_wakeup_enable(dev, 0);
+	else
+		return -EINVAL;
+	return n;
+}
+
+static DEVICE_ATTR_RW(wakeup);
+
+static ssize_t wakeup_count_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long count;
+	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);
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lu\n", count);
+}
+
+static DEVICE_ATTR_RO(wakeup_count);
+
+static ssize_t wakeup_active_count_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	unsigned long count;
+	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);
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lu\n", count);
+}
+
+static DEVICE_ATTR_RO(wakeup_active_count);
+
+static ssize_t wakeup_abort_count_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	unsigned long count;
+	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);
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lu\n", count);
+}
+
+static DEVICE_ATTR_RO(wakeup_abort_count);
+
+static ssize_t wakeup_expire_count_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	unsigned long count;
+	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);
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lu\n", count);
+}
+
+static DEVICE_ATTR_RO(wakeup_expire_count);
+
+static ssize_t wakeup_active_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	unsigned int active;
+	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);
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%u\n", active);
+}
+
+static DEVICE_ATTR_RO(wakeup_active);
+
+static ssize_t wakeup_total_time_ms_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	s64 msec;
+	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);
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lld\n", msec);
+}
+
+static DEVICE_ATTR_RO(wakeup_total_time_ms);
+
+static ssize_t wakeup_max_time_ms_show(struct device *dev,
+				       struct device_attribute *attr, char *buf)
+{
+	s64 msec;
+	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);
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lld\n", msec);
+}
+
+static DEVICE_ATTR_RO(wakeup_max_time_ms);
+
+static ssize_t wakeup_last_time_ms_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	s64 msec;
+	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);
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lld\n", msec);
+}
+
+static DEVICE_ATTR_RO(wakeup_last_time_ms);
+
+#ifdef CONFIG_PM_AUTOSLEEP
+static ssize_t wakeup_prevent_sleep_time_ms_show(struct device *dev,
+						 struct device_attribute *attr,
+						 char *buf)
+{
+	s64 msec;
+	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);
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lld\n", msec);
+}
+
+static DEVICE_ATTR_RO(wakeup_prevent_sleep_time_ms);
+#endif /* CONFIG_PM_AUTOSLEEP */
+
+static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid,
+						kgid_t kgid)
+{
+	if (dev->power.wakeup && dev->power.wakeup->dev)
+		return device_change_owner(dev->power.wakeup->dev, kuid, kgid);
+	return 0;
+}
+
+#else /* CONFIG_PM_SLEEP */
+static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid,
+						kgid_t kgid)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+static ssize_t runtime_usage_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", atomic_read(&dev->power.usage_count));
+}
+static DEVICE_ATTR_RO(runtime_usage);
+
+static ssize_t runtime_active_kids_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return sysfs_emit(buf, "%d\n", dev->power.ignore_children ?
+			  0 : atomic_read(&dev->power.child_count));
+}
+static DEVICE_ATTR_RO(runtime_active_kids);
+
+static ssize_t runtime_enabled_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	const char *output;
+
+	if (dev->power.disable_depth && !dev->power.runtime_auto)
+		output = "disabled & forbidden";
+	else if (dev->power.disable_depth)
+		output = "disabled";
+	else if (!dev->power.runtime_auto)
+		output = "forbidden";
+	else
+		output = "enabled";
+
+	return sysfs_emit(buf, "%s\n", output);
+}
+static DEVICE_ATTR_RO(runtime_enabled);
+
+#ifdef CONFIG_PM_SLEEP
+static ssize_t async_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	return sysfs_emit(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)
+{
+	if (sysfs_streq(buf, _enabled))
+		device_enable_async_suspend(dev);
+	else if (sysfs_streq(buf, _disabled))
+		device_disable_async_suspend(dev);
+	else
+		return -EINVAL;
+	return n;
+}
+
+static DEVICE_ATTR_RW(async);
+
+#endif /* CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
+
+static struct attribute *power_attrs[] = {
+#if defined(CONFIG_PM_ADVANCED_DEBUG) && defined(CONFIG_PM_SLEEP)
+	&dev_attr_async.attr,
+#endif
+	NULL,
+};
+static const 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 const struct attribute_group pm_wakeup_attr_group = {
+	.name	= power_group_name,
+	.attrs	= wakeup_attrs,
+};
+
+static struct attribute *runtime_attrs[] = {
+	&dev_attr_runtime_status.attr,
+	&dev_attr_control.attr,
+	&dev_attr_runtime_suspended_time.attr,
+	&dev_attr_runtime_active_time.attr,
+	&dev_attr_autosuspend_delay_ms.attr,
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+	&dev_attr_runtime_usage.attr,
+	&dev_attr_runtime_active_kids.attr,
+	&dev_attr_runtime_enabled.attr,
+#endif
+	NULL,
+};
+static const struct attribute_group pm_runtime_attr_group = {
+	.name	= power_group_name,
+	.attrs	= runtime_attrs,
+};
+
+static struct attribute *pm_qos_resume_latency_attrs[] = {
+	&dev_attr_pm_qos_resume_latency_us.attr,
+	NULL,
+};
+static const struct attribute_group pm_qos_resume_latency_attr_group = {
+	.name	= power_group_name,
+	.attrs	= pm_qos_resume_latency_attrs,
+};
+
+static struct attribute *pm_qos_latency_tolerance_attrs[] = {
+	&dev_attr_pm_qos_latency_tolerance_us.attr,
+	NULL,
+};
+static const struct attribute_group pm_qos_latency_tolerance_attr_group = {
+	.name	= power_group_name,
+	.attrs	= pm_qos_latency_tolerance_attrs,
+};
+
+static struct attribute *pm_qos_flags_attrs[] = {
+	&dev_attr_pm_qos_no_power_off.attr,
+	NULL,
+};
+static const 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;
+
+	/* No need to create PM sysfs if explicitly disabled. */
+	if (device_pm_not_required(dev))
+		return 0;
+
+	rc = sysfs_create_group(&dev->kobj, &pm_attr_group);
+	if (rc)
+		return rc;
+
+	if (!pm_runtime_has_no_callbacks(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;
+	}
+	rc = pm_wakeup_source_sysfs_add(dev);
+	if (rc)
+		goto err_latency;
+	return 0;
+
+ err_latency:
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group);
+ 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 dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid)
+{
+	int rc;
+
+	if (device_pm_not_required(dev))
+		return 0;
+
+	rc = sysfs_group_change_owner(&dev->kobj, &pm_attr_group, kuid, kgid);
+	if (rc)
+		return rc;
+
+	if (!pm_runtime_has_no_callbacks(dev)) {
+		rc = sysfs_group_change_owner(
+			&dev->kobj, &pm_runtime_attr_group, kuid, kgid);
+		if (rc)
+			return rc;
+	}
+
+	if (device_can_wakeup(dev)) {
+		rc = sysfs_group_change_owner(&dev->kobj, &pm_wakeup_attr_group,
+					      kuid, kgid);
+		if (rc)
+			return rc;
+
+		rc = dpm_sysfs_wakeup_change_owner(dev, kuid, kgid);
+		if (rc)
+			return rc;
+	}
+
+	if (dev->power.set_latency_tolerance) {
+		rc = sysfs_group_change_owner(
+			&dev->kobj, &pm_qos_latency_tolerance_attr_group, kuid,
+			kgid);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+int wakeup_sysfs_add(struct device *dev)
+{
+	int ret = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+
+	if (!ret)
+		kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+
+	return ret;
+}
+
+void wakeup_sysfs_remove(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
+	kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+}
+
+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);
+}
+
+int pm_qos_sysfs_add_latency_tolerance(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj,
+				 &pm_qos_latency_tolerance_attr_group);
+}
+
+void pm_qos_sysfs_remove_latency_tolerance(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_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)
+{
+	if (device_pm_not_required(dev))
+		return;
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group);
+	dev_pm_qos_constraints_destroy(dev);
+	rpm_sysfs_remove(dev);
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
+	sysfs_remove_group(&dev->kobj, &pm_attr_group);
+}
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
new file mode 100644
index 000000000..d8da7195b
--- /dev/null
+++ b/drivers/base/power/trace.c
@@ -0,0 +1,305 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * drivers/base/power/trace.c
+ *
+ * Copyright (C) 2006 Linus Torvalds
+ *
+ * Trace facility for suspend/resume problems, when none of the
+ * devices may be working.
+ */
+#define pr_fmt(fmt) "PM: " fmt
+
+#include <linux/pm-trace.h>
+#include <linux/export.h>
+#include <linux/rtc.h>
+#include <linux/suspend.h>
+#include <linux/init.h>
+
+#include <linux/mc146818rtc.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)
+
+bool pm_trace_rtc_abused __read_mostly;
+EXPORT_SYMBOL_GPL(pm_trace_rtc_abused);
+
+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;
+	mc146818_set_time(&time);
+	pm_trace_rtc_abused = true;
+	return n ? -1 : 0;
+}
+
+static unsigned int read_magic_time(void)
+{
+	struct rtc_time time;
+	unsigned int val;
+
+	if (mc146818_get_time(&time, 1000) < 0) {
+		pr_err("Unable to read current time from RTC\n");
+		return 0;
+	}
+
+	pr_info("RTC time: %ptRt, date: %ptRd\n", &time, &time);
+	val = time.tm_year;				/* 100 years */
+	if (val > 100)
+		val -= 100;
+	val += time.tm_mon * 100;			/* 12 months */
+	val += (time.tm_mday-1) * 100 * 12;		/* 28 month-days */
+	val += time.tm_hour * 100 * 12 * 28;		/* 24 hours */
+	val += (time.tm_min / 3) * 100 * 12 * 28 * 24;	/* 20 3-minute intervals */
+	return val;
+}
+
+/*
+ * This is just the sdbm hash function with a user-supplied
+ * seed and final size parameter.
+ */
+static unsigned int hash_string(unsigned int seed, const char *data, unsigned int mod)
+{
+	unsigned char c;
+	while ((c = *data++) != 0) {
+		seed = (seed << 16) + (seed << 6) - seed + c;
+	}
+	return seed % mod;
+}
+
+void set_trace_device(struct device *dev)
+{
+	dev_hash_value = hash_string(DEVSEED, dev_name(dev), DEVHASH);
+}
+EXPORT_SYMBOL(set_trace_device);
+
+/*
+ * We could just take the "tracedata" index into the .tracedata
+ * section instead. Generating a hash of the data gives us a
+ * chance to work across kernel versions, and perhaps more
+ * importantly it also gives us valid/invalid check (ie we will
+ * likely not give totally bogus reports - if the hash matches,
+ * it's not any guarantee, but it's a high _likelihood_ that
+ * the match is valid).
+ */
+void generate_pm_trace(const void *tracedata, unsigned int user)
+{
+	unsigned short lineno = *(unsigned short *)tracedata;
+	const char *file = *(const char **)(tracedata + 2);
+	unsigned int user_hash_value, file_hash_value;
+
+	if (!x86_platform.legacy.rtc)
+		return;
+
+	user_hash_value = user % USERHASH;
+	file_hash_value = hash_string(lineno, file, FILEHASH);
+	set_magic_time(user_hash_value, file_hash_value, dev_hash_value);
+}
+EXPORT_SYMBOL(generate_pm_trace);
+
+extern char __tracedata_start[], __tracedata_end[];
+static int show_file_hash(unsigned int value)
+{
+	int match;
+	char *tracedata;
+
+	match = 0;
+	for (tracedata = __tracedata_start ; tracedata < __tracedata_end ;
+			tracedata += 2 + sizeof(unsigned long)) {
+		unsigned short lineno = *(unsigned short *)tracedata;
+		const char *file = *(const char **)(tracedata + 2);
+		unsigned int hash = hash_string(lineno, file, FILEHASH);
+		if (hash != value)
+			continue;
+		pr_info("  hash matches %s:%u\n", file, lineno);
+		match++;
+	}
+	return match;
+}
+
+static int show_dev_hash(unsigned int value)
+{
+	int match = 0;
+	struct list_head *entry;
+
+	device_pm_lock();
+	entry = dpm_list.prev;
+	while (entry != &dpm_list) {
+		struct device * dev = to_device(entry);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH);
+		if (hash == value) {
+			dev_info(dev, "hash matches\n");
+			match++;
+		}
+		entry = entry->prev;
+	}
+	device_pm_unlock();
+	return match;
+}
+
+static unsigned int hash_value_early_read;
+
+int show_trace_dev_match(char *buf, size_t size)
+{
+	unsigned int value = hash_value_early_read / (USERHASH * FILEHASH);
+	int ret = 0;
+	struct list_head *entry;
+
+	/*
+	 * It's possible that multiple devices will match the hash and we can't
+	 * tell which is the culprit, so it's best to output them all.
+	 */
+	device_pm_lock();
+	entry = dpm_list.prev;
+	while (size && entry != &dpm_list) {
+		struct device *dev = to_device(entry);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev),
+						DEVHASH);
+		if (hash == value) {
+			int len = scnprintf(buf, size, "%s\n",
+					    dev_driver_string(dev));
+			buf += len;
+			ret += len;
+			size -= len;
+		}
+		entry = entry->prev;
+	}
+	device_pm_unlock();
+	return ret;
+}
+
+static int
+pm_trace_notify(struct notifier_block *nb, unsigned long mode, void *_unused)
+{
+	switch (mode) {
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		if (pm_trace_rtc_abused) {
+			pm_trace_rtc_abused = false;
+			pr_warn("Possible incorrect RTC due to pm_trace, please use 'ntpdate' or 'rdate' to reset it.\n");
+		}
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static struct notifier_block pm_trace_nb = {
+	.notifier_call = pm_trace_notify,
+};
+
+static int __init early_resume_init(void)
+{
+	if (!x86_platform.legacy.rtc)
+		return 0;
+
+	hash_value_early_read = read_magic_time();
+	register_pm_notifier(&pm_trace_nb);
+	return 0;
+}
+
+static int __init late_resume_init(void)
+{
+	unsigned int val = hash_value_early_read;
+	unsigned int user, file, dev;
+
+	if (!x86_platform.legacy.rtc)
+		return 0;
+
+	user = val % USERHASH;
+	val = val / USERHASH;
+	file = val % FILEHASH;
+	val = val / FILEHASH;
+	dev = val /* % DEVHASH */;
+
+	pr_info("  Magic number: %d:%d:%d\n", user, file, dev);
+	show_file_hash(file);
+	show_dev_hash(dev);
+	return 0;
+}
+
+core_initcall(early_resume_init);
+late_initcall(late_resume_init);
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
new file mode 100644
index 000000000..ad23f0fa5
--- /dev/null
+++ b/drivers/base/power/wakeirq.c
@@ -0,0 +1,394 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Device wakeirq helper functions */
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/pm_runtime.h>
+#include <linux/pm_wakeirq.h>
+
+#include "power.h"
+
+/**
+ * dev_pm_attach_wake_irq - Attach device interrupt as a wake IRQ
+ * @dev: Device entry
+ * @wirq: Wake irq specific data
+ *
+ * Internal function to attach a dedicated wake-up interrupt as a wake IRQ.
+ */
+static int dev_pm_attach_wake_irq(struct device *dev, struct wake_irq *wirq)
+{
+	unsigned long flags;
+
+	if (!dev || !wirq)
+		return -EINVAL;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	if (dev_WARN_ONCE(dev, dev->power.wakeirq,
+			  "wake irq already initialized\n")) {
+		spin_unlock_irqrestore(&dev->power.lock, flags);
+		return -EEXIST;
+	}
+
+	dev->power.wakeirq = wirq;
+	device_wakeup_attach_irq(dev, wirq);
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+	return 0;
+}
+
+/**
+ * dev_pm_set_wake_irq - Attach device IO interrupt as wake IRQ
+ * @dev: Device entry
+ * @irq: Device IO interrupt
+ *
+ * Attach a device IO interrupt as a wake IRQ. The wake IRQ gets
+ * automatically configured for wake-up from suspend  based
+ * on the device specific sysfs wakeup entry. Typically called
+ * during driver probe after calling device_init_wakeup().
+ */
+int dev_pm_set_wake_irq(struct device *dev, int irq)
+{
+	struct wake_irq *wirq;
+	int err;
+
+	if (irq < 0)
+		return -EINVAL;
+
+	wirq = kzalloc_obj(*wirq);
+	if (!wirq)
+		return -ENOMEM;
+
+	wirq->dev = dev;
+	wirq->irq = irq;
+
+	err = dev_pm_attach_wake_irq(dev, wirq);
+	if (err)
+		kfree(wirq);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(dev_pm_set_wake_irq);
+
+/**
+ * dev_pm_clear_wake_irq - Detach a device IO interrupt wake IRQ
+ * @dev: Device entry
+ *
+ * Detach a device wake IRQ and free resources.
+ *
+ * Note that it's OK for drivers to call this without calling
+ * dev_pm_set_wake_irq() as all the driver instances may not have
+ * a wake IRQ configured. This avoid adding wake IRQ specific
+ * checks into the drivers.
+ */
+void dev_pm_clear_wake_irq(struct device *dev)
+{
+	struct wake_irq *wirq;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	wirq = dev->power.wakeirq;
+	if (!wirq) {
+		spin_unlock_irqrestore(&dev->power.lock, flags);
+		return;
+	}
+
+	device_wakeup_detach_irq(dev);
+	dev->power.wakeirq = NULL;
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) {
+		free_irq(wirq->irq, wirq);
+		wirq->status &= ~WAKE_IRQ_DEDICATED_MASK;
+	}
+	kfree(wirq->name);
+	kfree(wirq);
+}
+EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq);
+
+static void devm_pm_clear_wake_irq(void *dev)
+{
+	dev_pm_clear_wake_irq(dev);
+}
+
+/**
+ * devm_pm_set_wake_irq - device-managed variant of dev_pm_set_wake_irq
+ * @dev: Device entry
+ * @irq: Device IO interrupt
+ *
+ *
+ * Attach a device IO interrupt as a wake IRQ, same with dev_pm_set_wake_irq,
+ * but the device will be auto clear wake capability on driver detach.
+ */
+int devm_pm_set_wake_irq(struct device *dev, int irq)
+{
+	int ret;
+
+	ret = dev_pm_set_wake_irq(dev, irq);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(dev, devm_pm_clear_wake_irq, dev);
+}
+EXPORT_SYMBOL_GPL(devm_pm_set_wake_irq);
+
+/**
+ * handle_threaded_wake_irq - Handler for dedicated wake-up interrupts
+ * @irq: Device specific dedicated wake-up interrupt
+ * @_wirq: Wake IRQ data
+ *
+ * Some devices have a separate wake-up interrupt in addition to the
+ * device IO interrupt. The wake-up interrupt signals that a device
+ * should be woken up from it's idle state. This handler uses device
+ * specific pm_runtime functions to wake the device, and then it's
+ * up to the device to do whatever it needs to. Note that as the
+ * device may need to restore context and start up regulators, we
+ * use a threaded IRQ.
+ *
+ * Also note that we are not resending the lost device interrupts.
+ * We assume that the wake-up interrupt just needs to wake-up the
+ * device, and then device's pm_runtime_resume() can deal with the
+ * situation.
+ */
+static irqreturn_t handle_threaded_wake_irq(int irq, void *_wirq)
+{
+	struct wake_irq *wirq = _wirq;
+	int res;
+
+	/* Maybe abort suspend? */
+	if (irqd_is_wakeup_set(irq_get_irq_data(irq))) {
+		pm_wakeup_event(wirq->dev, 0);
+
+		return IRQ_HANDLED;
+	}
+
+	/* We don't want RPM_ASYNC or RPM_NOWAIT here */
+	res = pm_runtime_resume(wirq->dev);
+	if (res < 0)
+		dev_warn(wirq->dev,
+			 "wake IRQ with no resume: %i\n", res);
+
+	return IRQ_HANDLED;
+}
+
+static int __dev_pm_set_dedicated_wake_irq(struct device *dev, int irq, unsigned int flag)
+{
+	struct wake_irq *wirq;
+	int err;
+
+	if (irq < 0)
+		return -EINVAL;
+
+	wirq = kzalloc_obj(*wirq);
+	if (!wirq)
+		return -ENOMEM;
+
+	wirq->name = kasprintf(GFP_KERNEL, "%s:wakeup", dev_name(dev));
+	if (!wirq->name) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	wirq->dev = dev;
+	wirq->irq = irq;
+
+	/* Prevent deferred spurious wakeirqs with disable_irq_nosync() */
+	irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY);
+
+	/*
+	 * Consumer device may need to power up and restore state
+	 * so we use a threaded irq.
+	 */
+	err = request_threaded_irq(irq, NULL, handle_threaded_wake_irq,
+				   IRQF_ONESHOT | IRQF_NO_AUTOEN,
+				   wirq->name, wirq);
+	if (err)
+		goto err_free_name;
+
+	err = dev_pm_attach_wake_irq(dev, wirq);
+	if (err)
+		goto err_free_irq;
+
+	wirq->status = WAKE_IRQ_DEDICATED_ALLOCATED | flag;
+
+	return err;
+
+err_free_irq:
+	free_irq(irq, wirq);
+err_free_name:
+	kfree(wirq->name);
+err_free:
+	kfree(wirq);
+
+	return err;
+}
+
+/**
+ * dev_pm_set_dedicated_wake_irq - Request a dedicated wake-up interrupt
+ * @dev: Device entry
+ * @irq: Device wake-up interrupt
+ *
+ * Unless your hardware has separate wake-up interrupts in addition
+ * to the device IO interrupts, you don't need this.
+ *
+ * Sets up a threaded interrupt handler for a device that has
+ * a dedicated wake-up interrupt in addition to the device IO
+ * interrupt.
+ */
+int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
+{
+	return __dev_pm_set_dedicated_wake_irq(dev, irq, 0);
+}
+EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq);
+
+/**
+ * dev_pm_set_dedicated_wake_irq_reverse - Request a dedicated wake-up interrupt
+ *                                         with reverse enable ordering
+ * @dev: Device entry
+ * @irq: Device wake-up interrupt
+ *
+ * Unless your hardware has separate wake-up interrupts in addition
+ * to the device IO interrupts, you don't need this.
+ *
+ * Sets up a threaded interrupt handler for a device that has a dedicated
+ * wake-up interrupt in addition to the device IO interrupt. It sets
+ * the status of WAKE_IRQ_DEDICATED_REVERSE to tell rpm_suspend()
+ * to enable dedicated wake-up interrupt after running the runtime suspend
+ * callback for @dev.
+ */
+int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq)
+{
+	return __dev_pm_set_dedicated_wake_irq(dev, irq, WAKE_IRQ_DEDICATED_REVERSE);
+}
+EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq_reverse);
+
+/**
+ * dev_pm_enable_wake_irq_check - Checks and enables wake-up interrupt
+ * @dev: Device
+ * @can_change_status: Can change wake-up interrupt status
+ *
+ * Enables wakeirq conditionally. We need to enable wake-up interrupt
+ * lazily on the first rpm_suspend(). This is needed as the consumer device
+ * starts in RPM_SUSPENDED state, and the first pm_runtime_get() would
+ * otherwise try to disable already disabled wakeirq. The wake-up interrupt
+ * starts disabled with IRQ_NOAUTOEN set.
+ *
+ * Should be called from rpm_suspend(), rpm_resume(),
+ * pm_runtime_force_suspend() or pm_runtime_force_resume().
+ * Caller must hold &dev->power.lock or disable runtime PM to change
+ * wirq->status.
+ */
+void dev_pm_enable_wake_irq_check(struct device *dev,
+				  bool can_change_status)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK))
+		return;
+
+	if (likely(wirq->status & WAKE_IRQ_DEDICATED_MANAGED)) {
+		goto enable;
+	} else if (can_change_status) {
+		wirq->status |= WAKE_IRQ_DEDICATED_MANAGED;
+		goto enable;
+	}
+
+	return;
+
+enable:
+	if (!can_change_status || !(wirq->status & WAKE_IRQ_DEDICATED_REVERSE)) {
+		enable_irq(wirq->irq);
+		wirq->status |= WAKE_IRQ_DEDICATED_ENABLED;
+	}
+}
+
+/**
+ * dev_pm_disable_wake_irq_check - Checks and disables wake-up interrupt
+ * @dev: Device
+ * @cond_disable: if set, also check WAKE_IRQ_DEDICATED_REVERSE
+ *
+ * Disables wake-up interrupt conditionally based on status.
+ * Should be called from rpm_suspend(), rpm_resume(),
+ * pm_runtime_force_suspend() or pm_runtime_force_resume().
+ */
+void dev_pm_disable_wake_irq_check(struct device *dev, bool cond_disable)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK))
+		return;
+
+	if (cond_disable && (wirq->status & WAKE_IRQ_DEDICATED_REVERSE))
+		return;
+
+	if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED) {
+		wirq->status &= ~WAKE_IRQ_DEDICATED_ENABLED;
+		disable_irq_nosync(wirq->irq);
+	}
+}
+
+/**
+ * dev_pm_enable_wake_irq_complete - enable wake IRQ not enabled before
+ * @dev: Device using the wake IRQ
+ *
+ * Enable wake IRQ conditionally based on status, mainly used if want to
+ * enable wake IRQ after running ->runtime_suspend() which depends on
+ * WAKE_IRQ_DEDICATED_REVERSE.
+ *
+ * Should be called from rpm_suspend() or pm_runtime_force_suspend().
+ */
+void dev_pm_enable_wake_irq_complete(struct device *dev)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK))
+		return;
+
+	if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED &&
+	    wirq->status & WAKE_IRQ_DEDICATED_REVERSE) {
+		enable_irq(wirq->irq);
+		wirq->status |= WAKE_IRQ_DEDICATED_ENABLED;
+	}
+}
+
+/**
+ * dev_pm_arm_wake_irq - Arm device wake-up
+ * @wirq: Device wake-up interrupt
+ *
+ * Sets up the wake-up event conditionally based on the
+ * device_may_wake().
+ */
+void dev_pm_arm_wake_irq(struct wake_irq *wirq)
+{
+	if (!wirq)
+		return;
+
+	if (device_may_wakeup(wirq->dev)) {
+		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED &&
+		    !(wirq->status & WAKE_IRQ_DEDICATED_ENABLED))
+			enable_irq(wirq->irq);
+
+		enable_irq_wake(wirq->irq);
+	}
+}
+
+/**
+ * dev_pm_disarm_wake_irq - Disarm device wake-up
+ * @wirq: Device wake-up interrupt
+ *
+ * Clears up the wake-up event conditionally based on the
+ * device_may_wake().
+ */
+void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
+{
+	if (!wirq)
+		return;
+
+	if (device_may_wakeup(wirq->dev)) {
+		disable_irq_wake(wirq->irq);
+
+		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED &&
+		    !(wirq->status & WAKE_IRQ_DEDICATED_ENABLED))
+			disable_irq_nosync(wirq->irq);
+	}
+}
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
new file mode 100644
index 000000000..80b497de2
--- /dev/null
+++ b/drivers/base/power/wakeup.c
@@ -0,0 +1,1245 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * drivers/base/power/wakeup.c - System wakeup events framework
+ *
+ * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ */
+#define pr_fmt(fmt) "PM: " fmt
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/sched/signal.h>
+#include <linux/capability.h>
+#include <linux/export.h>
+#include <linux/suspend.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/pm_wakeirq.h>
+#include <trace/events/power.h>
+
+#include "power.h"
+
+#define list_for_each_entry_rcu_locked(pos, head, member) \
+	list_for_each_entry_rcu(pos, head, member, \
+		srcu_read_lock_held(&wakeup_srcu))
+/*
+ * If set, the suspend/hibernate code will abort transitions to a sleep state
+ * if wakeup events are registered during or immediately before the transition.
+ */
+bool events_check_enabled __read_mostly;
+
+/* First wakeup IRQ seen by the kernel in the last cycle. */
+static unsigned int wakeup_irq[2] __read_mostly;
+static DEFINE_RAW_SPINLOCK(wakeup_irq_lock);
+
+/* If greater than 0 and the system is suspending, terminate the suspend. */
+static atomic_t pm_abort_suspend __read_mostly;
+
+/*
+ * Combined counters of registered wakeup events and wakeup events in progress.
+ * They need to be modified together atomically, so it's better to use one
+ * atomic variable to hold them both.
+ */
+static atomic_t combined_event_count = ATOMIC_INIT(0);
+
+#define IN_PROGRESS_BITS	(sizeof(int) * 4)
+#define MAX_IN_PROGRESS		((1 << IN_PROGRESS_BITS) - 1)
+
+static void split_counters(unsigned int *cnt, unsigned int *inpr)
+{
+	unsigned int comb = atomic_read(&combined_event_count);
+
+	*cnt = (comb >> IN_PROGRESS_BITS);
+	*inpr = comb & MAX_IN_PROGRESS;
+}
+
+/* A preserved old value of the events counter. */
+static unsigned int saved_count;
+
+static DEFINE_RAW_SPINLOCK(events_lock);
+
+static void pm_wakeup_timer_fn(struct timer_list *t);
+
+static LIST_HEAD(wakeup_sources);
+
+static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue);
+
+DEFINE_STATIC_SRCU(wakeup_srcu);
+
+static struct wakeup_source deleted_ws = {
+	.name = "deleted",
+	.lock =  __SPIN_LOCK_UNLOCKED(deleted_ws.lock),
+};
+
+static DEFINE_IDA(wakeup_ida);
+
+/**
+ * wakeup_source_create - Create a struct wakeup_source object.
+ * @name: Name of the new wakeup source.
+ */
+static struct wakeup_source *wakeup_source_create(const char *name)
+{
+	struct wakeup_source *ws;
+	const char *ws_name;
+	int id;
+
+	ws = kzalloc_obj(*ws);
+	if (!ws)
+		goto err_ws;
+
+	ws_name = kstrdup_const(name, GFP_KERNEL);
+	if (!ws_name)
+		goto err_name;
+	ws->name = ws_name;
+
+	id = ida_alloc(&wakeup_ida, GFP_KERNEL);
+	if (id < 0)
+		goto err_id;
+	ws->id = id;
+
+	return ws;
+
+err_id:
+	kfree_const(ws->name);
+err_name:
+	kfree(ws);
+err_ws:
+	return NULL;
+}
+
+/*
+ * Record wakeup_source statistics being deleted into a dummy wakeup_source.
+ */
+static void wakeup_source_record(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&deleted_ws.lock, flags);
+
+	if (ws->event_count) {
+		deleted_ws.total_time =
+			ktime_add(deleted_ws.total_time, ws->total_time);
+		deleted_ws.prevent_sleep_time =
+			ktime_add(deleted_ws.prevent_sleep_time,
+				  ws->prevent_sleep_time);
+		deleted_ws.max_time =
+			ktime_compare(deleted_ws.max_time, ws->max_time) > 0 ?
+				deleted_ws.max_time : ws->max_time;
+		deleted_ws.event_count += ws->event_count;
+		deleted_ws.active_count += ws->active_count;
+		deleted_ws.relax_count += ws->relax_count;
+		deleted_ws.expire_count += ws->expire_count;
+		deleted_ws.wakeup_count += ws->wakeup_count;
+	}
+
+	spin_unlock_irqrestore(&deleted_ws.lock, flags);
+}
+
+static void wakeup_source_free(struct wakeup_source *ws)
+{
+	ida_free(&wakeup_ida, ws->id);
+	kfree_const(ws->name);
+	kfree(ws);
+}
+
+/**
+ * wakeup_source_destroy - Destroy a struct wakeup_source object.
+ * @ws: Wakeup source to destroy.
+ *
+ * Use only for wakeup source objects created with wakeup_source_create().
+ */
+static void wakeup_source_destroy(struct wakeup_source *ws)
+{
+	if (!ws)
+		return;
+
+	__pm_relax(ws);
+	wakeup_source_record(ws);
+	wakeup_source_free(ws);
+}
+
+/**
+ * wakeup_source_add - Add given object to the list of wakeup sources.
+ * @ws: Wakeup source object to add to the list.
+ */
+static void wakeup_source_add(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (WARN_ON(!ws))
+		return;
+
+	spin_lock_init(&ws->lock);
+	timer_setup(&ws->timer, pm_wakeup_timer_fn, 0);
+	ws->active = false;
+
+	raw_spin_lock_irqsave(&events_lock, flags);
+	list_add_rcu(&ws->entry, &wakeup_sources);
+	raw_spin_unlock_irqrestore(&events_lock, flags);
+}
+
+/**
+ * wakeup_source_remove - Remove given object from the wakeup sources list.
+ * @ws: Wakeup source object to remove from the list.
+ */
+static void wakeup_source_remove(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (WARN_ON(!ws))
+		return;
+
+	/*
+	 * After shutting down the timer, wakeup_source_activate() will warn if
+	 * the given wakeup source is passed to it.
+	 */
+	timer_shutdown_sync(&ws->timer);
+
+	raw_spin_lock_irqsave(&events_lock, flags);
+	list_del_rcu(&ws->entry);
+	raw_spin_unlock_irqrestore(&events_lock, flags);
+	synchronize_srcu(&wakeup_srcu);
+}
+
+/**
+ * wakeup_source_register - Create wakeup source and add it to the list.
+ * @dev: Device this wakeup source is associated with (or NULL if virtual).
+ * @name: Name of the wakeup source to register.
+ */
+struct wakeup_source *wakeup_source_register(struct device *dev,
+					     const char *name)
+{
+	struct wakeup_source *ws;
+	int ret;
+
+	ws = wakeup_source_create(name);
+	if (ws) {
+		if (!dev || device_is_registered(dev)) {
+			ret = wakeup_source_sysfs_add(dev, ws);
+			if (ret) {
+				wakeup_source_free(ws);
+				return NULL;
+			}
+		}
+		wakeup_source_add(ws);
+	}
+	return ws;
+}
+EXPORT_SYMBOL_GPL(wakeup_source_register);
+
+/**
+ * wakeup_source_unregister - Remove wakeup source from the list and remove it.
+ * @ws: Wakeup source object to unregister.
+ */
+void wakeup_source_unregister(struct wakeup_source *ws)
+{
+	if (ws) {
+		wakeup_source_remove(ws);
+		if (ws->dev)
+			wakeup_source_sysfs_remove(ws);
+
+		wakeup_source_destroy(ws);
+	}
+}
+EXPORT_SYMBOL_GPL(wakeup_source_unregister);
+
+/**
+ * wakeup_sources_read_lock - Lock wakeup source list for read.
+ *
+ * Returns an index of srcu lock for struct wakeup_srcu.
+ * This index must be passed to the matching wakeup_sources_read_unlock().
+ */
+int wakeup_sources_read_lock(void)
+{
+	return srcu_read_lock(&wakeup_srcu);
+}
+EXPORT_SYMBOL_GPL(wakeup_sources_read_lock);
+
+/**
+ * wakeup_sources_read_unlock - Unlock wakeup source list.
+ * @idx: return value from corresponding wakeup_sources_read_lock()
+ */
+void wakeup_sources_read_unlock(int idx)
+{
+	srcu_read_unlock(&wakeup_srcu, idx);
+}
+EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock);
+
+/**
+ * wakeup_sources_walk_start - Begin a walk on wakeup source list
+ *
+ * Returns first object of the list of wakeup sources.
+ *
+ * Note that to be safe, wakeup sources list needs to be locked by calling
+ * wakeup_source_read_lock() for this.
+ */
+struct wakeup_source *wakeup_sources_walk_start(void)
+{
+	return list_first_or_null_rcu(&wakeup_sources, struct wakeup_source, entry);
+}
+EXPORT_SYMBOL_GPL(wakeup_sources_walk_start);
+
+/**
+ * wakeup_sources_walk_next - Get next wakeup source from the list
+ * @ws: Previous wakeup source object
+ *
+ * Note that to be safe, wakeup sources list needs to be locked by calling
+ * wakeup_source_read_lock() for this.
+ */
+struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws)
+{
+	struct list_head *ws_head = &wakeup_sources;
+
+	return list_next_or_null_rcu(ws_head, &ws->entry,
+				struct wakeup_source, entry);
+}
+EXPORT_SYMBOL_GPL(wakeup_sources_walk_next);
+
+/**
+ * device_wakeup_attach - Attach a wakeup source object to a device object.
+ * @dev: Device to handle.
+ * @ws: Wakeup source object to attach to @dev.
+ *
+ * This causes @dev to be treated as a wakeup device.
+ */
+static int device_wakeup_attach(struct device *dev, struct wakeup_source *ws)
+{
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		spin_unlock_irq(&dev->power.lock);
+		return -EEXIST;
+	}
+	dev->power.wakeup = ws;
+	if (dev->power.wakeirq)
+		device_wakeup_attach_irq(dev, dev->power.wakeirq);
+	spin_unlock_irq(&dev->power.lock);
+	return 0;
+}
+
+/**
+ * device_wakeup_enable - Enable given device to be a wakeup source.
+ * @dev: Device to handle.
+ *
+ * Create a wakeup source object, register it and attach it to @dev.
+ */
+int device_wakeup_enable(struct device *dev)
+{
+	struct wakeup_source *ws;
+	int ret;
+
+	if (!dev || !dev->power.can_wakeup)
+		return -EINVAL;
+
+	if (pm_sleep_transition_in_progress())
+		dev_dbg(dev, "Suspicious %s() during system transition!\n", __func__);
+
+	ws = wakeup_source_register(dev, dev_name(dev));
+	if (!ws)
+		return -ENOMEM;
+
+	ret = device_wakeup_attach(dev, ws);
+	if (ret)
+		wakeup_source_unregister(ws);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(device_wakeup_enable);
+
+/**
+ * device_wakeup_attach_irq - Attach a wakeirq to a wakeup source
+ * @dev: Device to handle
+ * @wakeirq: Device specific wakeirq entry
+ *
+ * Attach a device wakeirq to the wakeup source so the device
+ * wake IRQ can be configured automatically for suspend and
+ * resume.
+ *
+ * Call under the device's power.lock lock.
+ */
+void device_wakeup_attach_irq(struct device *dev,
+			     struct wake_irq *wakeirq)
+{
+	struct wakeup_source *ws;
+
+	ws = dev->power.wakeup;
+	if (!ws)
+		return;
+
+	if (ws->wakeirq)
+		dev_err(dev, "Leftover wakeup IRQ found, overriding\n");
+
+	ws->wakeirq = wakeirq;
+}
+
+/**
+ * device_wakeup_detach_irq - Detach a wakeirq from a wakeup source
+ * @dev: Device to handle
+ *
+ * Removes a device wakeirq from the wakeup source.
+ *
+ * Call under the device's power.lock lock.
+ */
+void device_wakeup_detach_irq(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	ws = dev->power.wakeup;
+	if (ws)
+		ws->wakeirq = NULL;
+}
+
+/**
+ * device_wakeup_arm_wake_irqs -
+ *
+ * Iterates over the list of device wakeirqs to arm them.
+ */
+void device_wakeup_arm_wake_irqs(void)
+{
+	struct wakeup_source *ws;
+	int srcuidx;
+
+	srcuidx = srcu_read_lock(&wakeup_srcu);
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry)
+		dev_pm_arm_wake_irq(ws->wakeirq);
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
+}
+
+/**
+ * device_wakeup_disarm_wake_irqs -
+ *
+ * Iterates over the list of device wakeirqs to disarm them.
+ */
+void device_wakeup_disarm_wake_irqs(void)
+{
+	struct wakeup_source *ws;
+	int srcuidx;
+
+	srcuidx = srcu_read_lock(&wakeup_srcu);
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry)
+		dev_pm_disarm_wake_irq(ws->wakeirq);
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
+}
+
+/**
+ * device_wakeup_detach - Detach a device's wakeup source object from it.
+ * @dev: Device to detach the wakeup source object from.
+ *
+ * After it returns, @dev will not be treated as a wakeup device any more.
+ */
+static struct wakeup_source *device_wakeup_detach(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	spin_lock_irq(&dev->power.lock);
+	ws = dev->power.wakeup;
+	dev->power.wakeup = NULL;
+	spin_unlock_irq(&dev->power.lock);
+	return ws;
+}
+
+/**
+ * device_wakeup_disable - Do not regard a device as a wakeup source any more.
+ * @dev: Device to handle.
+ *
+ * Detach the @dev's wakeup source object from it, unregister this wakeup source
+ * object and destroy it.
+ */
+void device_wakeup_disable(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	if (!dev || !dev->power.can_wakeup)
+		return;
+
+	ws = device_wakeup_detach(dev);
+	wakeup_source_unregister(ws);
+}
+EXPORT_SYMBOL_GPL(device_wakeup_disable);
+
+/**
+ * device_set_wakeup_capable - Set/reset device wakeup capability flag.
+ * @dev: Device to handle.
+ * @capable: Whether or not @dev is capable of waking up the system from sleep.
+ *
+ * If @capable is set, set the @dev's power.can_wakeup flag and add its
+ * wakeup-related attributes to sysfs.  Otherwise, unset the @dev's
+ * power.can_wakeup flag and remove its wakeup-related attributes from sysfs.
+ *
+ * This function may sleep and it can't be called from any context where
+ * sleeping is not allowed.
+ */
+void device_set_wakeup_capable(struct device *dev, bool capable)
+{
+	if (!!dev->power.can_wakeup == !!capable)
+		return;
+
+	dev->power.can_wakeup = capable;
+	if (device_is_registered(dev) && !list_empty(&dev->power.entry)) {
+		if (capable) {
+			int ret = wakeup_sysfs_add(dev);
+
+			if (ret)
+				dev_info(dev, "Wakeup sysfs attributes not added\n");
+		} else {
+			wakeup_sysfs_remove(dev);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_capable);
+
+/**
+ * device_set_wakeup_enable - Enable or disable a device to wake up the system.
+ * @dev: Device to handle.
+ * @enable: enable/disable flag
+ */
+int device_set_wakeup_enable(struct device *dev, bool enable)
+{
+	if (enable)
+		return device_wakeup_enable(dev);
+
+	device_wakeup_disable(dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
+
+/**
+ * wakeup_source_not_usable - validate the given wakeup source.
+ * @ws: Wakeup source to be validated.
+ */
+static bool wakeup_source_not_usable(struct wakeup_source *ws)
+{
+	/*
+	 * Use the timer struct to check if the given wakeup source has been
+	 * initialized by wakeup_source_add() and it is not going away.
+	 */
+	return ws->timer.function != pm_wakeup_timer_fn;
+}
+
+/*
+ * The functions below use the observation that each wakeup event starts a
+ * period in which the system should not be suspended.  The moment this period
+ * will end depends on how the wakeup event is going to be processed after being
+ * detected and all of the possible cases can be divided into two distinct
+ * groups.
+ *
+ * First, a wakeup event may be detected by the same functional unit that will
+ * carry out the entire processing of it and possibly will pass it to user space
+ * for further processing.  In that case the functional unit that has detected
+ * the event may later "close" the "no suspend" period associated with it
+ * directly as soon as it has been dealt with.  The pair of pm_stay_awake() and
+ * pm_relax(), balanced with each other, is supposed to be used in such
+ * situations.
+ *
+ * Second, a wakeup event may be detected by one functional unit and processed
+ * by another one.  In that case the unit that has detected it cannot really
+ * "close" the "no suspend" period associated with it, unless it knows in
+ * advance what's going to happen to the event during processing.  This
+ * knowledge, however, may not be available to it, so it can simply specify time
+ * to wait before the system can be suspended and pass it as the second
+ * argument of pm_wakeup_event().
+ *
+ * It is valid to call pm_relax() after pm_wakeup_event(), in which case the
+ * "no suspend" period will be ended either by the pm_relax(), or by the timer
+ * function executed when the timer expires, whichever comes first.
+ */
+
+/**
+ * wakeup_source_activate - Mark given wakeup source as active.
+ * @ws: Wakeup source to handle.
+ *
+ * Update the @ws' statistics and, if @ws has just been activated, notify the PM
+ * core of the event by incrementing the counter of the wakeup events being
+ * processed.
+ */
+static void wakeup_source_activate(struct wakeup_source *ws)
+{
+	unsigned int cec;
+
+	if (WARN_ONCE(wakeup_source_not_usable(ws), "unusable wakeup source\n"))
+		return;
+
+	ws->active = true;
+	ws->active_count++;
+	ws->last_time = ktime_get();
+	if (ws->autosleep_enabled)
+		ws->start_prevent_time = ws->last_time;
+
+	/* Increment the counter of events in progress. */
+	cec = atomic_inc_return(&combined_event_count);
+
+	trace_wakeup_source_activate(ws->name, cec);
+}
+
+/**
+ * wakeup_source_report_event - Report wakeup event using the given source.
+ * @ws: Wakeup source to report the event for.
+ * @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
+ */
+static void wakeup_source_report_event(struct wakeup_source *ws, bool hard)
+{
+	ws->event_count++;
+	/* This is racy, but the counter is approximate anyway. */
+	if (events_check_enabled)
+		ws->wakeup_count++;
+
+	if (!ws->active)
+		wakeup_source_activate(ws);
+
+	if (hard)
+		pm_system_wakeup();
+}
+
+/**
+ * __pm_stay_awake - Notify the PM core of a wakeup event.
+ * @ws: Wakeup source object associated with the source of the event.
+ *
+ * It is safe to call this function from interrupt context.
+ */
+void __pm_stay_awake(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	wakeup_source_report_event(ws, false);
+	timer_delete(&ws->timer);
+	ws->timer_expires = 0;
+
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_stay_awake);
+
+/**
+ * pm_stay_awake - Notify the PM core that a wakeup event is being processed.
+ * @dev: Device the wakeup event is related to.
+ *
+ * Notify the PM core of a wakeup event (signaled by @dev) by calling
+ * __pm_stay_awake for the @dev's wakeup source object.
+ *
+ * Call this function after detecting of a wakeup event if pm_relax() is going
+ * to be called directly after processing the event (and possibly passing it to
+ * user space for further processing).
+ */
+void pm_stay_awake(struct device *dev)
+{
+	unsigned long flags;
+
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_stay_awake(dev->power.wakeup);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_stay_awake);
+
+#ifdef CONFIG_PM_AUTOSLEEP
+static void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now)
+{
+	ktime_t delta = ktime_sub(now, ws->start_prevent_time);
+	ws->prevent_sleep_time = ktime_add(ws->prevent_sleep_time, delta);
+}
+#else
+static inline void update_prevent_sleep_time(struct wakeup_source *ws,
+					     ktime_t now) {}
+#endif
+
+/**
+ * wakeup_source_deactivate - Mark given wakeup source as inactive.
+ * @ws: Wakeup source to handle.
+ *
+ * Update the @ws' statistics and notify the PM core that the wakeup source has
+ * become inactive by decrementing the counter of wakeup events being processed
+ * and incrementing the counter of registered wakeup events.
+ */
+static void wakeup_source_deactivate(struct wakeup_source *ws)
+{
+	unsigned int cnt, inpr, cec;
+	ktime_t duration;
+	ktime_t now;
+
+	ws->relax_count++;
+	/*
+	 * __pm_relax() may be called directly or from a timer function.
+	 * If it is called directly right after the timer function has been
+	 * started, but before the timer function calls __pm_relax(), it is
+	 * possible that __pm_stay_awake() will be called in the meantime and
+	 * will set ws->active.  Then, ws->active may be cleared immediately
+	 * by the __pm_relax() called from the timer function, but in such a
+	 * case ws->relax_count will be different from ws->active_count.
+	 */
+	if (ws->relax_count != ws->active_count) {
+		ws->relax_count--;
+		return;
+	}
+
+	ws->active = false;
+
+	now = ktime_get();
+	duration = ktime_sub(now, ws->last_time);
+	ws->total_time = ktime_add(ws->total_time, duration);
+	if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time))
+		ws->max_time = duration;
+
+	ws->last_time = now;
+	timer_delete(&ws->timer);
+	ws->timer_expires = 0;
+
+	if (ws->autosleep_enabled)
+		update_prevent_sleep_time(ws, now);
+
+	/*
+	 * Increment the counter of registered wakeup events and decrement the
+	 * counter of wakeup events in progress simultaneously.
+	 */
+	cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count);
+	trace_wakeup_source_deactivate(ws->name, cec);
+
+	split_counters(&cnt, &inpr);
+	if (!inpr && waitqueue_active(&wakeup_count_wait_queue))
+		wake_up(&wakeup_count_wait_queue);
+}
+
+/**
+ * __pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * @ws: Wakeup source object associated with the source of the event.
+ *
+ * Call this function for wakeup events whose processing started with calling
+ * __pm_stay_awake().
+ *
+ * It is safe to call it from interrupt context.
+ */
+void __pm_relax(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+	if (ws->active)
+		wakeup_source_deactivate(ws);
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_relax);
+
+/**
+ * pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * @dev: Device that signaled the event.
+ *
+ * Execute __pm_relax() for the @dev's wakeup source object.
+ */
+void pm_relax(struct device *dev)
+{
+	unsigned long flags;
+
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_relax(dev->power.wakeup);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_relax);
+
+/**
+ * pm_wakeup_timer_fn - Delayed finalization of a wakeup event.
+ * @t: timer list
+ *
+ * Call wakeup_source_deactivate() for the wakeup source whose address is stored
+ * in @data if it is currently active and its timer has not been canceled and
+ * the expiration time of the timer is not in future.
+ */
+static void pm_wakeup_timer_fn(struct timer_list *t)
+{
+	struct wakeup_source *ws = timer_container_of(ws, t, timer);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	if (ws->active && ws->timer_expires
+	    && time_after_eq(jiffies, ws->timer_expires)) {
+		wakeup_source_deactivate(ws);
+		ws->expire_count++;
+	}
+
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+
+/**
+ * pm_wakeup_ws_event - Notify the PM core of a wakeup event.
+ * @ws: Wakeup source object associated with the event source.
+ * @msec: Anticipated event processing time (in milliseconds).
+ * @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
+ *
+ * Notify the PM core of a wakeup event whose source is @ws that will take
+ * approximately @msec milliseconds to be processed by the kernel.  If @ws is
+ * not active, activate it.  If @msec is nonzero, set up the @ws' timer to
+ * execute pm_wakeup_timer_fn() in future.
+ *
+ * It is safe to call this function from interrupt context.
+ */
+void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard)
+{
+	unsigned long flags;
+	unsigned long expires;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	wakeup_source_report_event(ws, hard);
+
+	if (!msec) {
+		wakeup_source_deactivate(ws);
+		goto unlock;
+	}
+
+	expires = jiffies + msecs_to_jiffies(msec);
+	if (!expires)
+		expires = 1;
+
+	if (!ws->timer_expires || time_after(expires, ws->timer_expires)) {
+		mod_timer(&ws->timer, expires);
+		ws->timer_expires = expires;
+	}
+
+ unlock:
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_wakeup_ws_event);
+
+/**
+ * pm_wakeup_dev_event - Notify the PM core of a wakeup event.
+ * @dev: Device the wakeup event is related to.
+ * @msec: Anticipated event processing time (in milliseconds).
+ * @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
+ *
+ * Call pm_wakeup_ws_event() for the @dev's wakeup source object.
+ */
+void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard)
+{
+	unsigned long flags;
+
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	pm_wakeup_ws_event(dev->power.wakeup, msec, hard);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_wakeup_dev_event);
+
+void pm_print_active_wakeup_sources(void)
+{
+	struct wakeup_source *ws;
+	int srcuidx, active = 0;
+	struct wakeup_source *last_activity_ws = NULL;
+
+	srcuidx = srcu_read_lock(&wakeup_srcu);
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
+		if (ws->active) {
+			pm_pr_dbg("active wakeup source: %s\n", ws->name);
+			active = 1;
+		} else if (!active &&
+			   (!last_activity_ws ||
+			    ktime_to_ns(ws->last_time) >
+			    ktime_to_ns(last_activity_ws->last_time))) {
+			last_activity_ws = ws;
+		}
+	}
+
+	if (!active && last_activity_ws)
+		pm_pr_dbg("last active wakeup source: %s\n",
+			last_activity_ws->name);
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
+}
+EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources);
+
+/**
+ * pm_wakeup_pending - Check if power transition in progress should be aborted.
+ *
+ * Compare the current number of registered wakeup events with its preserved
+ * value from the past and return true if new wakeup events have been registered
+ * since the old value was stored.  Also return true if the current number of
+ * wakeup events being processed is different from zero.
+ */
+bool pm_wakeup_pending(void)
+{
+	unsigned long flags;
+	bool ret = false;
+
+	raw_spin_lock_irqsave(&events_lock, flags);
+	if (events_check_enabled) {
+		unsigned int cnt, inpr;
+
+		split_counters(&cnt, &inpr);
+		ret = (cnt != saved_count || inpr > 0);
+		events_check_enabled = !ret;
+	}
+	raw_spin_unlock_irqrestore(&events_lock, flags);
+
+	if (ret) {
+		pm_pr_dbg("Wakeup pending, aborting suspend\n");
+		pm_print_active_wakeup_sources();
+	}
+
+	return ret || atomic_read(&pm_abort_suspend) > 0;
+}
+EXPORT_SYMBOL_GPL(pm_wakeup_pending);
+
+void pm_system_wakeup(void)
+{
+	atomic_inc(&pm_abort_suspend);
+	s2idle_wake();
+}
+EXPORT_SYMBOL_GPL(pm_system_wakeup);
+
+void pm_system_cancel_wakeup(void)
+{
+	atomic_dec_if_positive(&pm_abort_suspend);
+}
+
+void pm_wakeup_clear(unsigned int irq_number)
+{
+	raw_spin_lock_irq(&wakeup_irq_lock);
+
+	if (irq_number && wakeup_irq[0] == irq_number)
+		wakeup_irq[0] = wakeup_irq[1];
+	else
+		wakeup_irq[0] = 0;
+
+	wakeup_irq[1] = 0;
+
+	raw_spin_unlock_irq(&wakeup_irq_lock);
+
+	if (!irq_number)
+		atomic_set(&pm_abort_suspend, 0);
+}
+
+void pm_system_irq_wakeup(unsigned int irq_number)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&wakeup_irq_lock, flags);
+
+	if (wakeup_irq[0] == 0)
+		wakeup_irq[0] = irq_number;
+	else if (wakeup_irq[1] == 0)
+		wakeup_irq[1] = irq_number;
+	else
+		irq_number = 0;
+
+	pm_pr_dbg("Triggering wakeup from IRQ %d\n", irq_number);
+
+	raw_spin_unlock_irqrestore(&wakeup_irq_lock, flags);
+
+	if (irq_number)
+		pm_system_wakeup();
+}
+
+unsigned int pm_wakeup_irq(void)
+{
+	return wakeup_irq[0];
+}
+
+/**
+ * pm_get_wakeup_count - Read the number of registered wakeup events.
+ * @count: Address to store the value at.
+ * @block: Whether or not to block.
+ *
+ * Store the number of registered wakeup events at the address in @count.  If
+ * @block is set, block until the current number of wakeup events being
+ * processed is zero.
+ *
+ * Return 'false' if the current number of wakeup events being processed is
+ * nonzero.  Otherwise return 'true'.
+ */
+bool pm_get_wakeup_count(unsigned int *count, bool block)
+{
+	unsigned int cnt, inpr;
+
+	if (block) {
+		DEFINE_WAIT(wait);
+
+		for (;;) {
+			prepare_to_wait(&wakeup_count_wait_queue, &wait,
+					TASK_INTERRUPTIBLE);
+			split_counters(&cnt, &inpr);
+			if (inpr == 0 || signal_pending(current))
+				break;
+			pm_print_active_wakeup_sources();
+			schedule();
+		}
+		finish_wait(&wakeup_count_wait_queue, &wait);
+	}
+
+	split_counters(&cnt, &inpr);
+	*count = cnt;
+	return !inpr;
+}
+
+/**
+ * pm_save_wakeup_count - Save the current number of registered wakeup events.
+ * @count: Value to compare with the current number of registered wakeup events.
+ *
+ * If @count is equal to the current number of registered wakeup events and the
+ * current number of wakeup events being processed is zero, store @count as the
+ * old number of registered wakeup events for pm_check_wakeup_events(), enable
+ * wakeup events detection and return 'true'.  Otherwise disable wakeup events
+ * detection and return 'false'.
+ */
+bool pm_save_wakeup_count(unsigned int count)
+{
+	unsigned int cnt, inpr;
+	unsigned long flags;
+
+	events_check_enabled = false;
+	raw_spin_lock_irqsave(&events_lock, flags);
+	split_counters(&cnt, &inpr);
+	if (cnt == count && inpr == 0) {
+		saved_count = count;
+		events_check_enabled = true;
+	}
+	raw_spin_unlock_irqrestore(&events_lock, flags);
+	return events_check_enabled;
+}
+
+#ifdef CONFIG_PM_AUTOSLEEP
+/**
+ * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources.
+ * @set: Whether to set or to clear the autosleep_enabled flags.
+ */
+void pm_wakep_autosleep_enabled(bool set)
+{
+	struct wakeup_source *ws;
+	ktime_t now = ktime_get();
+	int srcuidx;
+
+	srcuidx = srcu_read_lock(&wakeup_srcu);
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
+		spin_lock_irq(&ws->lock);
+		if (ws->autosleep_enabled != set) {
+			ws->autosleep_enabled = set;
+			if (ws->active) {
+				if (set)
+					ws->start_prevent_time = now;
+				else
+					update_prevent_sleep_time(ws, now);
+			}
+		}
+		spin_unlock_irq(&ws->lock);
+	}
+	srcu_read_unlock(&wakeup_srcu, srcuidx);
+}
+#endif /* CONFIG_PM_AUTOSLEEP */
+
+/**
+ * print_wakeup_source_stats - Print wakeup source statistics information.
+ * @m: seq_file to print the statistics into.
+ * @ws: Wakeup source object to print the statistics for.
+ */
+static int print_wakeup_source_stats(struct seq_file *m,
+				     struct wakeup_source *ws)
+{
+	unsigned long flags;
+	ktime_t total_time;
+	ktime_t max_time;
+	unsigned long active_count;
+	ktime_t active_time;
+	ktime_t prevent_sleep_time;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	total_time = ws->total_time;
+	max_time = ws->max_time;
+	prevent_sleep_time = ws->prevent_sleep_time;
+	active_count = ws->active_count;
+	if (ws->active) {
+		ktime_t now = ktime_get();
+
+		active_time = ktime_sub(now, ws->last_time);
+		total_time = ktime_add(total_time, active_time);
+		if (active_time > max_time)
+			max_time = active_time;
+
+		if (ws->autosleep_enabled)
+			prevent_sleep_time = ktime_add(prevent_sleep_time,
+				ktime_sub(now, ws->start_prevent_time));
+	} else {
+		active_time = 0;
+	}
+
+	seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n",
+		   ws->name, active_count, ws->event_count,
+		   ws->wakeup_count, ws->expire_count,
+		   ktime_to_ms(active_time), ktime_to_ms(total_time),
+		   ktime_to_ms(max_time), ktime_to_ms(ws->last_time),
+		   ktime_to_ms(prevent_sleep_time));
+
+	spin_unlock_irqrestore(&ws->lock, flags);
+
+	return 0;
+}
+
+static void *wakeup_sources_stats_seq_start(struct seq_file *m,
+					loff_t *pos)
+{
+	struct wakeup_source *ws;
+	loff_t n = *pos;
+	int *srcuidx = m->private;
+
+	if (n == 0) {
+		seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
+			"expire_count\tactive_since\ttotal_time\tmax_time\t"
+			"last_change\tprevent_suspend_time\n");
+	}
+
+	*srcuidx = srcu_read_lock(&wakeup_srcu);
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
+		if (n-- <= 0)
+			return ws;
+	}
+
+	return NULL;
+}
+
+static void *wakeup_sources_stats_seq_next(struct seq_file *m,
+					void *v, loff_t *pos)
+{
+	struct wakeup_source *ws = v;
+	struct wakeup_source *next_ws = NULL;
+
+	++(*pos);
+
+	list_for_each_entry_continue_rcu(ws, &wakeup_sources, entry) {
+		next_ws = ws;
+		break;
+	}
+
+	if (!next_ws)
+		print_wakeup_source_stats(m, &deleted_ws);
+
+	return next_ws;
+}
+
+static void wakeup_sources_stats_seq_stop(struct seq_file *m, void *v)
+{
+	int *srcuidx = m->private;
+
+	srcu_read_unlock(&wakeup_srcu, *srcuidx);
+}
+
+/**
+ * wakeup_sources_stats_seq_show - Print wakeup sources statistics information.
+ * @m: seq_file to print the statistics into.
+ * @v: wakeup_source of each iteration
+ */
+static int wakeup_sources_stats_seq_show(struct seq_file *m, void *v)
+{
+	struct wakeup_source *ws = v;
+
+	print_wakeup_source_stats(m, ws);
+
+	return 0;
+}
+
+static const struct seq_operations wakeup_sources_stats_seq_ops = {
+	.start = wakeup_sources_stats_seq_start,
+	.next  = wakeup_sources_stats_seq_next,
+	.stop  = wakeup_sources_stats_seq_stop,
+	.show  = wakeup_sources_stats_seq_show,
+};
+
+static int wakeup_sources_stats_open(struct inode *inode, struct file *file)
+{
+	return seq_open_private(file, &wakeup_sources_stats_seq_ops, sizeof(int));
+}
+
+static const struct file_operations wakeup_sources_stats_fops = {
+	.owner = THIS_MODULE,
+	.open = wakeup_sources_stats_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release_private,
+};
+
+#ifdef CONFIG_BPF_SYSCALL
+#include <linux/btf.h>
+
+__bpf_kfunc_start_defs();
+
+/**
+ * bpf_wakeup_sources_read_lock - Acquire the SRCU lock for wakeup sources
+ *
+ * The underlying SRCU lock returns an integer index. However, the BPF verifier
+ * requires a pointer (PTR_TO_BTF_ID) to strictly track the state of acquired
+ * resources using KF_ACQUIRE and KF_RELEASE semantics. We use an opaque
+ * structure pointer (struct bpf_ws_lock *) to satisfy the verifier while
+ * safely encoding the integer index within the pointer address itself.
+ *
+ * Return: An opaque pointer encoding the SRCU lock index + 1 (to avoid NULL).
+ */
+__bpf_kfunc struct bpf_ws_lock *bpf_wakeup_sources_read_lock(void)
+{
+	return (struct bpf_ws_lock *)(long)(wakeup_sources_read_lock() + 1);
+}
+
+/**
+ * bpf_wakeup_sources_read_unlock - Release the SRCU lock for wakeup sources
+ * @lock: The opaque pointer returned by bpf_wakeup_sources_read_lock()
+ *
+ * The BPF verifier guarantees that @lock is a valid, unreleased pointer from
+ * the acquire function. We decode the pointer back into the integer SRCU index
+ * by subtracting 1 and release the lock.
+ */
+__bpf_kfunc void bpf_wakeup_sources_read_unlock(struct bpf_ws_lock *lock)
+{
+	wakeup_sources_read_unlock((int)(long)lock - 1);
+}
+
+/**
+ * bpf_wakeup_sources_get_head - Get the head of the wakeup sources list
+ *
+ * Return: The head of the wakeup sources list.
+ */
+__bpf_kfunc void *bpf_wakeup_sources_get_head(void)
+{
+	return &wakeup_sources;
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(wakeup_source_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_wakeup_sources_read_lock, KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_wakeup_sources_read_unlock, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_wakeup_sources_get_head)
+BTF_KFUNCS_END(wakeup_source_kfunc_ids)
+
+static const struct btf_kfunc_id_set wakeup_source_kfunc_set = {
+	.set   = &wakeup_source_kfunc_ids,
+};
+
+static void __init wakeup_sources_bpf_init(void)
+{
+	if (register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &wakeup_source_kfunc_set))
+		pm_pr_dbg("Wakeup: failed to register BTF kfuncs\n");
+}
+#else
+static inline void wakeup_sources_bpf_init(void) {}
+#endif /* CONFIG_BPF_SYSCALL */
+
+static int __init wakeup_sources_init(void)
+{
+	debugfs_create_file("wakeup_sources", 0444, NULL, NULL,
+			    &wakeup_sources_stats_fops);
+	wakeup_sources_bpf_init();
+
+	return 0;
+}
+
+postcore_initcall(wakeup_sources_init);
diff --git a/drivers/base/power/wakeup_stats.c b/drivers/base/power/wakeup_stats.c
new file mode 100644
index 000000000..308f8bde9
--- /dev/null
+++ b/drivers/base/power/wakeup_stats.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Wakeup statistics in sysfs
+ *
+ * Copyright (c) 2019 Linux Foundation
+ * Copyright (c) 2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+ * Copyright (c) 2019 Google Inc.
+ */
+
+#include <linux/device.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/kdev_t.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/slab.h>
+#include <linux/timekeeping.h>
+
+#include "power.h"
+
+static struct class *wakeup_class;
+
+#define wakeup_attr(_name)						\
+static ssize_t _name##_show(struct device *dev,				\
+			    struct device_attribute *attr, char *buf)	\
+{									\
+	struct wakeup_source *ws = dev_get_drvdata(dev);		\
+									\
+	return sysfs_emit(buf, "%lu\n", ws->_name);			\
+}									\
+static DEVICE_ATTR_RO(_name)
+
+wakeup_attr(active_count);
+wakeup_attr(event_count);
+wakeup_attr(wakeup_count);
+wakeup_attr(expire_count);
+wakeup_attr(relax_count);
+
+static ssize_t active_time_ms_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+	ktime_t active_time =
+		ws->active ? ktime_sub(ktime_get(), ws->last_time) : 0;
+
+	return sysfs_emit(buf, "%lld\n", ktime_to_ms(active_time));
+}
+static DEVICE_ATTR_RO(active_time_ms);
+
+static ssize_t total_time_ms_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+	ktime_t active_time;
+	ktime_t total_time = ws->total_time;
+
+	if (ws->active) {
+		active_time = ktime_sub(ktime_get(), ws->last_time);
+		total_time = ktime_add(total_time, active_time);
+	}
+
+	return sysfs_emit(buf, "%lld\n", ktime_to_ms(total_time));
+}
+static DEVICE_ATTR_RO(total_time_ms);
+
+static ssize_t max_time_ms_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+	ktime_t active_time;
+	ktime_t max_time = ws->max_time;
+
+	if (ws->active) {
+		active_time = ktime_sub(ktime_get(), ws->last_time);
+		if (active_time > max_time)
+			max_time = active_time;
+	}
+
+	return sysfs_emit(buf, "%lld\n", ktime_to_ms(max_time));
+}
+static DEVICE_ATTR_RO(max_time_ms);
+
+static ssize_t last_change_ms_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%lld\n", ktime_to_ms(ws->last_time));
+}
+static DEVICE_ATTR_RO(last_change_ms);
+
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", ws->name);
+}
+static DEVICE_ATTR_RO(name);
+
+static ssize_t prevent_suspend_time_ms_show(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+	ktime_t prevent_sleep_time = ws->prevent_sleep_time;
+
+	if (ws->active && ws->autosleep_enabled) {
+		prevent_sleep_time = ktime_add(prevent_sleep_time,
+			ktime_sub(ktime_get(), ws->start_prevent_time));
+	}
+
+	return sysfs_emit(buf, "%lld\n", ktime_to_ms(prevent_sleep_time));
+}
+static DEVICE_ATTR_RO(prevent_suspend_time_ms);
+
+static struct attribute *wakeup_source_attrs[] = {
+	&dev_attr_name.attr,
+	&dev_attr_active_count.attr,
+	&dev_attr_event_count.attr,
+	&dev_attr_wakeup_count.attr,
+	&dev_attr_expire_count.attr,
+	&dev_attr_relax_count.attr,
+	&dev_attr_active_time_ms.attr,
+	&dev_attr_total_time_ms.attr,
+	&dev_attr_max_time_ms.attr,
+	&dev_attr_last_change_ms.attr,
+	&dev_attr_prevent_suspend_time_ms.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(wakeup_source);
+
+static void device_create_release(struct device *dev)
+{
+	kfree(dev);
+}
+
+static struct device *wakeup_source_device_create(struct device *parent,
+						  struct wakeup_source *ws)
+{
+	struct device *dev = NULL;
+	int retval;
+
+	dev = kzalloc_obj(*dev);
+	if (!dev) {
+		retval = -ENOMEM;
+		goto error;
+	}
+
+	device_initialize(dev);
+	dev->devt = MKDEV(0, 0);
+	dev->class = wakeup_class;
+	dev->parent = parent;
+	dev->groups = wakeup_source_groups;
+	dev->release = device_create_release;
+	dev_set_drvdata(dev, ws);
+	device_set_pm_not_required(dev);
+
+	retval = dev_set_name(dev, "wakeup%d", ws->id);
+	if (retval)
+		goto error;
+
+	retval = device_add(dev);
+	if (retval)
+		goto error;
+
+	return dev;
+
+error:
+	put_device(dev);
+	return ERR_PTR(retval);
+}
+
+/**
+ * wakeup_source_sysfs_add - Add wakeup_source attributes to sysfs.
+ * @parent: Device given wakeup source is associated with (or NULL if virtual).
+ * @ws: Wakeup source to be added in sysfs.
+ */
+int wakeup_source_sysfs_add(struct device *parent, struct wakeup_source *ws)
+{
+	struct device *dev;
+
+	dev = wakeup_source_device_create(parent, ws);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+	ws->dev = dev;
+
+	return 0;
+}
+
+/**
+ * pm_wakeup_source_sysfs_add - Add wakeup_source attributes to sysfs
+ * for a device if they're missing.
+ * @parent: Device given wakeup source is associated with
+ */
+int pm_wakeup_source_sysfs_add(struct device *parent)
+{
+	if (!parent->power.wakeup || parent->power.wakeup->dev)
+		return 0;
+
+	return wakeup_source_sysfs_add(parent, parent->power.wakeup);
+}
+
+/**
+ * wakeup_source_sysfs_remove - Remove wakeup_source attributes from sysfs.
+ * @ws: Wakeup source to be removed from sysfs.
+ */
+void wakeup_source_sysfs_remove(struct wakeup_source *ws)
+{
+	device_unregister(ws->dev);
+}
+
+static int __init wakeup_sources_sysfs_init(void)
+{
+	wakeup_class = class_create("wakeup");
+
+	return PTR_ERR_OR_ZERO(wakeup_class);
+}
+postcore_initcall(wakeup_sources_sysfs_init);