17 files changed, 614 insertions, 320 deletions

diff --git a/Documentation/driver-api/pm/devices.rst b/Documentation/driver-api/pm/devices.rst
index 53c1b0b06da5..1128705a5731 100644
--- a/Documentation/driver-api/pm/devices.rst
+++ b/Documentation/driver-api/pm/devices.rst
@@ -777,17 +777,51 @@ The driver can indicate that by setting ``DPM_FLAG_SMART_SUSPEND`` in
 runtime suspend at the beginning of the ``suspend_late`` phase of system-wide
 suspend (or in the ``poweroff_late`` phase of hibernation), when runtime PM
 has been disabled for it, under the assumption that its state should not change
-after that point until the system-wide transition is over.  If that happens, the
-driver's system-wide resume callbacks, if present, may still be invoked during
-the subsequent system-wide resume transition and the device's runtime power
-management status may be set to "active" before enabling runtime PM for it,
-so the driver must be prepared to cope with the invocation of its system-wide
-resume callbacks back-to-back with its ``->runtime_suspend`` one (without the
-intervening ``->runtime_resume`` and so on) and the final state of the device
-must reflect the "active" status for runtime PM in that case.
+after that point until the system-wide transition is over (the PM core itself
+does that for devices whose "noirq", "late" and "early" system-wide PM callbacks
+are executed directly by it).  If that happens, the driver's system-wide resume
+callbacks, if present, may still be invoked during the subsequent system-wide
+resume transition and the device's runtime power management status may be set
+to "active" before enabling runtime PM for it, so the driver must be prepared to
+cope with the invocation of its system-wide resume callbacks back-to-back with
+its ``->runtime_suspend`` one (without the intervening ``->runtime_resume`` and
+so on) and the final state of the device must reflect the "active" runtime PM
+status in that case.
 
 During system-wide resume from a sleep state it's easiest to put devices into
 the full-power state, as explained in :file:`Documentation/power/runtime_pm.txt`.
-Refer to that document for more information regarding this particular issue as
+[Refer to that document for more information regarding this particular issue as
 well as for information on the device runtime power management framework in
-general.
+general.]
+
+However, it often is desirable to leave devices in suspend after system
+transitions to the working state, especially if those devices had been in
+runtime suspend before the preceding system-wide suspend (or analogous)
+transition.  Device drivers can use the ``DPM_FLAG_LEAVE_SUSPENDED`` flag to
+indicate to the PM core (and middle-layer code) that they prefer the specific
+devices handled by them to be left suspended and they have no problems with
+skipping their system-wide resume callbacks for this reason.  Whether or not the
+devices will actually be left in suspend may depend on their state before the
+given system suspend-resume cycle and on the type of the system transition under
+way.  In particular, devices are not left suspended if that transition is a
+restore from hibernation, as device states are not guaranteed to be reflected
+by the information stored in the hibernation image in that case.
+
+The middle-layer code involved in the handling of the device is expected to
+indicate to the PM core if the device may be left in suspend by setting its
+:c:member:`power.may_skip_resume` status bit which is checked by the PM core
+during the "noirq" phase of the preceding system-wide suspend (or analogous)
+transition.  The middle layer is then responsible for handling the device as
+appropriate in its "noirq" resume callback, which is executed regardless of
+whether or not the device is left suspended, but the other resume callbacks
+(except for ``->complete``) will be skipped automatically by the PM core if the
+device really can be left in suspend.
+
+For devices whose "noirq", "late" and "early" driver callbacks are invoked
+directly by the PM core, all of the system-wide resume callbacks are skipped if
+``DPM_FLAG_LEAVE_SUSPENDED`` is set and the device is in runtime suspend during
+the ``suspend_noirq`` (or analogous) phase or the transition under way is a
+proper system suspend (rather than anything related to hibernation) and the
+device's wakeup settings are suitable for runtime PM (that is, it cannot
+generate wakeup signals at all or it is allowed to wake up the system from
+sleep).
diff --git a/Documentation/power/pci.txt b/Documentation/power/pci.txt
index 704cd36079b8..8eaf9ee24d43 100644
--- a/Documentation/power/pci.txt
+++ b/Documentation/power/pci.txt
@@ -994,6 +994,17 @@ into D0 going forward), but if it is in runtime suspend in pci_pm_thaw_noirq(),
 the function will set the power.direct_complete flag for it (to make the PM core
 skip the subsequent "thaw" callbacks for it) and return.
 
+Setting the DPM_FLAG_LEAVE_SUSPENDED flag means that the driver prefers the
+device to be left in suspend after system-wide transitions to the working state.
+This flag is checked by the PM core, but the PCI bus type informs the PM core
+which devices may be left in suspend from its perspective (that happens during
+the "noirq" phase of system-wide suspend and analogous transitions) and next it
+uses the dev_pm_may_skip_resume() helper to decide whether or not to return from
+pci_pm_resume_noirq() early, as the PM core will skip the remaining resume
+callbacks for the device during the transition under way and will set its
+runtime PM status to "suspended" if dev_pm_may_skip_resume() returns "true" for
+it.
+
 3.2. Device Runtime Power Management
 ------------------------------------
 In addition to providing device power management callbacks PCI device drivers
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index a4c8ad98560d..c4d0a1c912f0 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -990,7 +990,7 @@ void acpi_subsys_complete(struct device *dev)
 	 * the sleep state it is going out of and it has never been resumed till
 	 * now, resume it in case the firmware powered it up.
 	 */
-	if (dev->power.direct_complete && pm_resume_via_firmware())
+	if (pm_runtime_suspended(dev) && pm_resume_via_firmware())
 		pm_request_resume(dev);
 }
 EXPORT_SYMBOL_GPL(acpi_subsys_complete);
@@ -1039,10 +1039,28 @@ EXPORT_SYMBOL_GPL(acpi_subsys_suspend_late);
  */
 int acpi_subsys_suspend_noirq(struct device *dev)
 {
-	if (dev_pm_smart_suspend_and_suspended(dev))
+	int ret;
+
+	if (dev_pm_smart_suspend_and_suspended(dev)) {
+		dev->power.may_skip_resume = true;
 		return 0;
+	}
+
+	ret = pm_generic_suspend_noirq(dev);
+	if (ret)
+		return ret;
+
+	/*
+	 * If the target system sleep state is suspend-to-idle, it is sufficient
+	 * to check whether or not the device's wakeup settings are good for
+	 * runtime PM.  Otherwise, the pm_resume_via_firmware() check will cause
+	 * acpi_subsys_complete() to take care of fixing up the device's state
+	 * anyway, if need be.
+	 */
+	dev->power.may_skip_resume = device_may_wakeup(dev) ||
+					!device_can_wakeup(dev);
 
-	return pm_generic_suspend_noirq(dev);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(acpi_subsys_suspend_noirq);
 
@@ -1052,6 +1070,9 @@ EXPORT_SYMBOL_GPL(acpi_subsys_suspend_noirq);
  */
 int acpi_subsys_resume_noirq(struct device *dev)
 {
+	if (dev_pm_may_skip_resume(dev))
+		return 0;
+
 	/*
 	 * Devices with DPM_FLAG_SMART_SUSPEND may be left in runtime suspend
 	 * during system suspend, so update their runtime PM status to "active"
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 08744b572af6..02a497e7c785 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -18,7 +18,6 @@
  */
 
 #include <linux/device.h>
-#include <linux/kallsyms.h>
 #include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/pm.h>
@@ -541,6 +540,73 @@ void dev_pm_skip_next_resume_phases(struct device *dev)
 }
 
 /**
+ * suspend_event - Return a "suspend" message for given "resume" one.
+ * @resume_msg: PM message representing a system-wide resume transition.
+ */
+static pm_message_t suspend_event(pm_message_t resume_msg)
+{
+	switch (resume_msg.event) {
+	case PM_EVENT_RESUME:
+		return PMSG_SUSPEND;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RESTORE:
+		return PMSG_FREEZE;
+	case PM_EVENT_RECOVER:
+		return PMSG_HIBERNATE;
+	}
+	return PMSG_ON;
+}
+
+/**
+ * dev_pm_may_skip_resume - System-wide device resume optimization check.
+ * @dev: Target device.
+ *
+ * Checks whether or not the device may be left in suspend after a system-wide
+ * transition to the working state.
+ */
+bool dev_pm_may_skip_resume(struct device *dev)
+{
+	return !dev->power.must_resume && pm_transition.event != PM_EVENT_RESTORE;
+}
+
+static pm_callback_t dpm_subsys_resume_noirq_cb(struct device *dev,
+						pm_message_t state,
+						const char **info_p)
+{
+	pm_callback_t callback;
+	const char *info;
+
+	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);
+	} else {
+		return NULL;
+	}
+
+	if (info_p)
+		*info_p = info;
+
+	return callback;
+}
+
+static pm_callback_t dpm_subsys_suspend_noirq_cb(struct device *dev,
+						 pm_message_t state,
+						 const char **info_p);
+
+static pm_callback_t dpm_subsys_suspend_late_cb(struct device *dev,
+						pm_message_t state,
+						const char **info_p);
+
+/**
  * device_resume_noirq - Execute a "noirq resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
@@ -551,8 +617,9 @@ void dev_pm_skip_next_resume_phases(struct device *dev)
  */
 static int device_resume_noirq(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback = NULL;
-	const char *info = NULL;
+	pm_callback_t callback;
+	const char *info;
+	bool skip_resume;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -566,29 +633,61 @@ static int device_resume_noirq(struct device *dev, pm_message_t state, bool asyn
 
 	dpm_wait_for_superior(dev, async);
 
-	if (dev->pm_domain) {
-		info = "noirq power domain ";
-		callback = pm_noirq_op(&dev->pm_domain->ops, state);
-	} else if (dev->type && dev->type->pm) {
-		info = "noirq type ";
-		callback = pm_noirq_op(dev->type->pm, state);
-	} else if (dev->class && dev->class->pm) {
-		info = "noirq class ";
-		callback = pm_noirq_op(dev->class->pm, state);
-	} else if (dev->bus && dev->bus->pm) {
-		info = "noirq bus ";
-		callback = pm_noirq_op(dev->bus->pm, state);
+	skip_resume = dev_pm_may_skip_resume(dev);
+
+	callback = dpm_subsys_resume_noirq_cb(dev, state, &info);
+	if (callback)
+		goto Run;
+
+	if (skip_resume)
+		goto Skip;
+
+	if (dev_pm_smart_suspend_and_suspended(dev)) {
+		pm_message_t suspend_msg = suspend_event(state);
+
+		/*
+		 * If "freeze" callbacks have been skipped during a transition
+		 * related to hibernation, the subsequent "thaw" callbacks must
+		 * be skipped too or bad things may happen.  Otherwise, resume
+		 * callbacks are going to be run for the device, so its runtime
+		 * PM status must be changed to reflect the new state after the
+		 * transition under way.
+		 */
+		if (!dpm_subsys_suspend_late_cb(dev, suspend_msg, NULL) &&
+		    !dpm_subsys_suspend_noirq_cb(dev, suspend_msg, NULL)) {
+			if (state.event == PM_EVENT_THAW) {
+				skip_resume = true;
+				goto Skip;
+			} else {
+				pm_runtime_set_active(dev);
+			}
+		}
 	}
 
-	if (!callback && dev->driver && dev->driver->pm) {
+	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:
+	if (skip_resume) {
+		/*
+		 * The device is going to be left in suspend, but it might not
+		 * have been in runtime suspend before the system suspended, so
+		 * its runtime PM status needs to be updated to avoid confusing
+		 * the runtime PM framework when runtime PM is enabled for the
+		 * device again.
+		 */
+		pm_runtime_set_suspended(dev);
+		dev_pm_skip_next_resume_phases(dev);
+	}
+
+Out:
 	complete_all(&dev->power.completion);
 	TRACE_RESUME(error);
 	return error;
@@ -681,6 +780,35 @@ void dpm_resume_noirq(pm_message_t state)
 	dpm_noirq_end();
 }
 
+static pm_callback_t dpm_subsys_resume_early_cb(struct device *dev,
+						pm_message_t state,
+						const char **info_p)
+{
+	pm_callback_t callback;
+	const char *info;
+
+	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);
+	} else {
+		return NULL;
+	}
+
+	if (info_p)
+		*info_p = info;
+
+	return callback;
+}
+
 /**
  * device_resume_early - Execute an "early resume" callback for given device.
  * @dev: Device to handle.
@@ -691,8 +819,8 @@ void dpm_resume_noirq(pm_message_t state)
  */
 static int device_resume_early(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback = NULL;
-	const char *info = NULL;
+	pm_callback_t callback;
+	const char *info;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -706,19 +834,7 @@ static int device_resume_early(struct device *dev, pm_message_t state, bool asyn
 
 	dpm_wait_for_superior(dev, async);
 
-	if (dev->pm_domain) {
-		info = "early power domain ";
-		callback = pm_late_early_op(&dev->pm_domain->ops, state);
-	} else if (dev->type && dev->type->pm) {
-		info = "early type ";
-		callback = pm_late_early_op(dev->type->pm, state);
-	} else if (dev->class && dev->class->pm) {
-		info = "early class ";
-		callback = pm_late_early_op(dev->class->pm, state);
-	} else if (dev->bus && dev->bus->pm) {
-		info = "early bus ";
-		callback = pm_late_early_op(dev->bus->pm, state);
-	}
+	callback = dpm_subsys_resume_early_cb(dev, state, &info);
 
 	if (!callback && dev->driver && dev->driver->pm) {
 		info = "early driver ";
@@ -1089,6 +1205,77 @@ static pm_message_t resume_event(pm_message_t sleep_state)
 	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();
+
+	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+		link->supplier->power.must_resume = true;
+
+	device_links_read_unlock(idx);
+}
+
+static pm_callback_t dpm_subsys_suspend_noirq_cb(struct device *dev,
+						 pm_message_t state,
+						 const char **info_p)
+{
+	pm_callback_t callback;
+	const char *info;
+
+	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);
+	} else {
+		return NULL;
+	}
+
+	if (info_p)
+		*info_p = info;
+
+	return callback;
+}
+
+static bool device_must_resume(struct device *dev, pm_message_t state,
+			       bool no_subsys_suspend_noirq)
+{
+	pm_message_t resume_msg = resume_event(state);
+
+	/*
+	 * If all of the device driver's "noirq", "late" and "early" callbacks
+	 * are invoked directly by the core, the decision to allow the device to
+	 * stay in suspend can be based on its current runtime PM status and its
+	 * wakeup settings.
+	 */
+	if (no_subsys_suspend_noirq &&
+	    !dpm_subsys_suspend_late_cb(dev, state, NULL) &&
+	    !dpm_subsys_resume_early_cb(dev, resume_msg, NULL) &&
+	    !dpm_subsys_resume_noirq_cb(dev, resume_msg, NULL))
+		return !pm_runtime_status_suspended(dev) &&
+			(resume_msg.event != PM_EVENT_RESUME ||
+			 (device_can_wakeup(dev) && !device_may_wakeup(dev)));
+
+	/*
+	 * The only safe strategy here is to require that if the device may not
+	 * be left in suspend, resume callbacks must be invoked for it.
+	 */
+	return !dev->power.may_skip_resume;
+}
+
 /**
  * __device_suspend_noirq - Execute a "noirq suspend" callback for given device.
  * @dev: Device to handle.
@@ -1100,8 +1287,9 @@ static pm_message_t resume_event(pm_message_t sleep_state)
  */
 static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback = NULL;
-	const char *info = NULL;
+	pm_callback_t callback;
+	const char *info;
+	bool no_subsys_cb = false;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -1120,30 +1308,40 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a
 	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);
-	}
+	callback = dpm_subsys_suspend_noirq_cb(dev, state, &info);
+	if (callback)
+		goto Run;
 
-	if (!callback && dev->driver && dev->driver->pm) {
+	no_subsys_cb = !dpm_subsys_suspend_late_cb(dev, state, NULL);
+
+	if (dev_pm_smart_suspend_and_suspended(dev) && no_subsys_cb)
+		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)
-		dev->power.is_noirq_suspended = true;
-	else
+	if (error) {
 		async_error = error;
+		goto Complete;
+	}
+
+Skip:
+	dev->power.is_noirq_suspended = true;
+
+	if (dev_pm_test_driver_flags(dev, DPM_FLAG_LEAVE_SUSPENDED)) {
+		dev->power.must_resume = dev->power.must_resume ||
+				atomic_read(&dev->power.usage_count) > 1 ||
+				device_must_resume(dev, state, no_subsys_cb);
+	} else {
+		dev->power.must_resume = true;
+	}
+
+	if (dev->power.must_resume)
+		dpm_superior_set_must_resume(dev);
 
 Complete:
 	complete_all(&dev->power.completion);
@@ -1249,6 +1447,50 @@ int dpm_suspend_noirq(pm_message_t 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 (dev->power.wakeup_path && !parent->power.ignore_children)
+		parent->power.wakeup_path = true;
+
+	spin_unlock_irq(&parent->power.lock);
+}
+
+static pm_callback_t dpm_subsys_suspend_late_cb(struct device *dev,
+						pm_message_t state,
+						const char **info_p)
+{
+	pm_callback_t callback;
+	const char *info;
+
+	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);
+	} else {
+		return NULL;
+	}
+
+	if (info_p)
+		*info_p = info;
+
+	return callback;
+}
+
 /**
  * __device_suspend_late - Execute a "late suspend" callback for given device.
  * @dev: Device to handle.
@@ -1259,8 +1501,8 @@ int dpm_suspend_noirq(pm_message_t state)
  */
 static int __device_suspend_late(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback = NULL;
-	const char *info = NULL;
+	pm_callback_t callback;
+	const char *info;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -1281,30 +1523,29 @@ static int __device_suspend_late(struct device *dev, pm_message_t state, bool as
 	if (dev->power.syscore || dev->power.direct_complete)
 		goto Complete;
 
-	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);
-	}
+	callback = dpm_subsys_suspend_late_cb(dev, state, &info);
+	if (callback)
+		goto Run;
 
-	if (!callback && dev->driver && dev->driver->pm) {
+	if (dev_pm_smart_suspend_and_suspended(dev) &&
+	    !dpm_subsys_suspend_noirq_cb(dev, state, NULL))
+		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)
-		dev->power.is_late_suspended = true;
-	else
+	if (error) {
 		async_error = error;
+		goto Complete;
+	}
+	dpm_propagate_wakeup_to_parent(dev);
+
+Skip:
+	dev->power.is_late_suspended = true;
 
 Complete:
 	TRACE_SUSPEND(error);
@@ -1435,11 +1676,17 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
 	return error;
 }
 
-static void dpm_clear_suppliers_direct_complete(struct device *dev)
+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();
 
 	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) {
@@ -1500,6 +1747,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 		dev->power.direct_complete = false;
 	}
 
+	dev->power.may_skip_resume = false;
+	dev->power.must_resume = false;
+
 	dpm_watchdog_set(&wd, dev);
 	device_lock(dev);
 
@@ -1543,20 +1793,12 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 
  End:
 	if (!error) {
-		struct device *parent = dev->parent;
-
 		dev->power.is_suspended = true;
-		if (parent) {
-			spin_lock_irq(&parent->power.lock);
-
-			dev->parent->power.direct_complete = false;
-			if (dev->power.wakeup_path
-			    && !dev->parent->power.ignore_children)
-				dev->parent->power.wakeup_path = true;
+		if (device_may_wakeup(dev))
+			dev->power.wakeup_path = true;
 
-			spin_unlock_irq(&parent->power.lock);
-		}
-		dpm_clear_suppliers_direct_complete(dev);
+		dpm_propagate_wakeup_to_parent(dev);
+		dpm_clear_superiors_direct_complete(dev);
 	}
 
 	device_unlock(dev);
@@ -1665,8 +1907,9 @@ static int device_prepare(struct device *dev, pm_message_t state)
 	if (dev->power.syscore)
 		return 0;
 
-	WARN_ON(dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) &&
-		!pm_runtime_enabled(dev));
+	WARN_ON(!pm_runtime_enabled(dev) &&
+		dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND |
+					      DPM_FLAG_LEAVE_SUSPENDED));
 
 	/*
 	 * If a device's parent goes into runtime suspend at the wrong time,
@@ -1678,7 +1921,7 @@ static int device_prepare(struct device *dev, pm_message_t state)
 
 	device_lock(dev);
 
-	dev->power.wakeup_path = device_may_wakeup(dev);
+	dev->power.wakeup_path = false;
 
 	if (dev->power.no_pm_callbacks) {
 		ret = 1;	/* Let device go direct_complete */
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 7beee75399d4..21244c53e377 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -41,20 +41,15 @@ extern void dev_pm_disable_wake_irq_check(struct device *dev);
 
 #ifdef CONFIG_PM_SLEEP
 
-extern int device_wakeup_attach_irq(struct device *dev,
-				    struct wake_irq *wakeirq);
+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 int
-device_wakeup_attach_irq(struct device *dev,
-			 struct wake_irq *wakeirq)
-{
-	return 0;
-}
+static inline void device_wakeup_attach_irq(struct device *dev,
+					    struct wake_irq *wakeirq) {}
 
 static inline void device_wakeup_detach_irq(struct device *dev)
 {
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 6e89b51ea3d9..8bef3cb2424d 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1613,22 +1613,34 @@ void pm_runtime_drop_link(struct device *dev)
 	spin_unlock_irq(&dev->power.lock);
 }
 
+static 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);
+}
+
 /**
  * pm_runtime_force_suspend - Force a device into suspend state if needed.
  * @dev: Device to suspend.
  *
  * Disable runtime PM so we safely can check the device's runtime PM status and
- * if it is active, invoke it's .runtime_suspend callback to bring it into
- * suspend state. Keep runtime PM disabled to preserve the state unless we
- * encounter errors.
+ * 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.
+ * 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 = 0;
+	int ret;
 
 	pm_runtime_disable(dev);
 	if (pm_runtime_status_suspended(dev))
@@ -1636,27 +1648,23 @@ int pm_runtime_force_suspend(struct device *dev)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
 
-	if (!callback) {
-		ret = -ENOSYS;
-		goto err;
-	}
-
-	ret = callback(dev);
+	ret = callback ? callback(dev) : 0;
 	if (ret)
 		goto err;
 
 	/*
-	 * Increase the runtime PM usage count for the device's parent, in case
-	 * when we find the device being used when system suspend was invoked.
-	 * This informs pm_runtime_force_resume() to resume the parent
-	 * immediately, which is needed to be able to resume its children,
-	 * when not deferring the resume to be managed via runtime PM.
+	 * 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, but set its status to RPM_SUSPENDED anyway in case this
+	 * function will be called again for it in the meantime.
 	 */
-	if (dev->parent && atomic_read(&dev->power.usage_count) > 1)
-		pm_runtime_get_noresume(dev->parent);
+	if (pm_runtime_need_not_resume(dev))
+		pm_runtime_set_suspended(dev);
+	else
+		__update_runtime_status(dev, RPM_SUSPENDED);
 
-	pm_runtime_set_suspended(dev);
 	return 0;
+
 err:
 	pm_runtime_enable(dev);
 	return ret;
@@ -1669,13 +1677,9 @@ EXPORT_SYMBOL_GPL(pm_runtime_force_suspend);
  *
  * Prior invoking this function we expect the user to have brought the device
  * into low power state by a call to pm_runtime_force_suspend(). Here we reverse
- * those actions and brings the device into full power, if it is expected to be
- * used on system resume. To distinguish that, we check whether the runtime PM
- * usage count is greater than 1 (the PM core increases the usage count in the
- * system PM prepare phase), as that indicates a real user (such as a subsystem,
- * driver, userspace, etc.) is using it. If that is the case, the device is
- * expected to be used on system resume as well, so then we resume it. In the
- * other case, we defer the resume to be managed via runtime PM.
+ * those actions and bring the device into full power, if it is expected to be
+ * used on system resume.  In the other case, we defer the resume to be managed
+ * via runtime PM.
  *
  * Typically this function may be invoked from a system resume callback.
  */
@@ -1684,32 +1688,18 @@ int pm_runtime_force_resume(struct device *dev)
 	int (*callback)(struct device *);
 	int ret = 0;
 
-	callback = RPM_GET_CALLBACK(dev, runtime_resume);
-
-	if (!callback) {
-		ret = -ENOSYS;
-		goto out;
-	}
-
-	if (!pm_runtime_status_suspended(dev))
+	if (!pm_runtime_status_suspended(dev) || pm_runtime_need_not_resume(dev))
 		goto out;
 
 	/*
-	 * Decrease the parent's runtime PM usage count, if we increased it
-	 * during system suspend in pm_runtime_force_suspend().
-	*/
-	if (atomic_read(&dev->power.usage_count) > 1) {
-		if (dev->parent)
-			pm_runtime_put_noidle(dev->parent);
-	} else {
-		goto out;
-	}
+	 * The value of the parent's children counter is correct already, so
+	 * just update the status of the device.
+	 */
+	__update_runtime_status(dev, RPM_ACTIVE);
 
-	ret = pm_runtime_set_active(dev);
-	if (ret)
-		goto out;
+	callback = RPM_GET_CALLBACK(dev, runtime_resume);
 
-	ret = callback(dev);
+	ret = callback ? callback(dev) : 0;
 	if (ret) {
 		pm_runtime_set_suspended(dev);
 		goto out;
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index e153e28b1857..0f651efc58a1 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -108,16 +108,10 @@ static ssize_t control_show(struct device *dev, struct device_attribute *attr,
 static ssize_t control_store(struct device * dev, struct device_attribute *attr,
 			     const char * buf, size_t n)
 {
-	char *cp;
-	int len = n;
-
-	cp = memchr(buf, '\n', n);
-	if (cp)
-		len = cp - buf;
 	device_lock(dev);
-	if (len == sizeof ctrl_auto - 1 && strncmp(buf, ctrl_auto, len) == 0)
+	if (sysfs_streq(buf, ctrl_auto))
 		pm_runtime_allow(dev);
-	else if (len == sizeof ctrl_on - 1 && strncmp(buf, ctrl_on, len) == 0)
+	else if (sysfs_streq(buf, ctrl_on))
 		pm_runtime_forbid(dev);
 	else
 		n = -EINVAL;
@@ -125,9 +119,9 @@ static ssize_t control_store(struct device * dev, struct device_attribute *attr,
 	return n;
 }
 
-static DEVICE_ATTR(control, 0644, control_show, control_store);
+static DEVICE_ATTR_RW(control);
 
-static ssize_t rtpm_active_time_show(struct device *dev,
+static ssize_t runtime_active_time_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	int ret;
@@ -138,9 +132,9 @@ static ssize_t rtpm_active_time_show(struct device *dev,
 	return ret;
 }
 
-static DEVICE_ATTR(runtime_active_time, 0444, rtpm_active_time_show, NULL);
+st