Introduce new top level suspend and hibernation callbacks

Introduce 'struct pm_ops' and 'struct pm_ext_ops' ('ext' meaning
'extended') representing suspend and hibernation operations for bus
types, device classes, device types and device drivers.

Modify the PM core to use 'struct pm_ops' and 'struct pm_ext_ops'
objects, if defined, instead of the ->suspend(), ->resume(),
->suspend_late(), and ->resume_early() callbacks (the old callbacks
will be considered as legacy and gradually phased out).

The main purpose of doing this is to separate suspend (aka S2RAM and
standby) callbacks from hibernation callbacks in such a way that the
new callbacks won't take arguments and the semantics of each of them
will be clearly specified.  This has been requested for multiple
times by many people, including Linus himself, and the reason is that
within the current scheme if ->resume() is called, for example, it's
difficult to say why it's been called (ie. is it a resume from RAM or
from hibernation or a suspend/hibernation failure etc.?).

The second purpose is to make the suspend/hibernation callbacks more
flexible so that device drivers can handle more than they can within
the current scheme.  For example, some drivers may need to prevent
new children of the device from being registered before their
->suspend() callbacks are executed or they may want to carry out some
operations requiring the availability of some other devices, not
directly bound via the parent-child relationship, in order to prepare
for the execution of ->suspend(), etc.

Ultimately, we'd like to stop using the freezing of tasks for suspend
and therefore the drivers' suspend/hibernation code will have to take
care of the handling of the user space during suspend/hibernation.
That, in turn, would be difficult within the current scheme, without
the new ->prepare() and ->complete() callbacks.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>

arch/x86/kernel/apm_32.c

@@ -1211,9 +1211,9 @@ static int suspend(int vetoable)
 	if (err != APM_SUCCESS)
 		apm_error("suspend", err);
 	err = (err == APM_SUCCESS) ? 0 : -EIO;
-	device_power_up();
+	device_power_up(PMSG_RESUME);
 	local_irq_enable();
-	device_resume();
+	device_resume(PMSG_RESUME);
 	queue_event(APM_NORMAL_RESUME, NULL);
 	spin_lock(&user_list_lock);
 	for (as = user_list; as != NULL; as = as->next) {
@@ -1238,7 +1238,7 @@ static void standby(void)
 		apm_error("standby", err);
 
 	local_irq_disable();
-	device_power_up();
+	device_power_up(PMSG_RESUME);
 	local_irq_enable();
 }
 
@@ -1324,7 +1324,7 @@ static void check_events(void)
 			ignore_bounce = 1;
 			if ((event != APM_NORMAL_RESUME)
 			    || (ignore_normal_resume == 0)) {
-				device_resume();
+				device_resume(PMSG_RESUME);
 				queue_event(event, NULL);
 			}
 			ignore_normal_resume = 0;

drivers/base/power/main.c

@@ -12,11 +12,9 @@
  * and add it to the list of power-controlled devices. sysfs entries for
  * controlling device power management will also be added.
  *
- * A different set of lists than the global subsystem list are used to
- * keep track of power info because we use different lists to hold
- * devices based on what stage of the power management process they
- * are in. The power domain dependencies may also differ from the
- * ancestral dependencies that the subsystem list maintains.
+ * A separate list is used for keeping track of power info, because the power
+ * domain dependencies may differ from the ancestral dependencies that the
+ * subsystem list maintains.
  */
 
 #include <linux/device.h>
@@ -30,31 +28,40 @@
 #include "power.h"
 
 /*
- * The entries in the dpm_active list are in a depth first order, simply
+ * 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.
  *
- * All the other lists are kept in the same order, for consistency.
- * However the lists aren't always traversed in the same order.
- * Semaphores must be acquired from the top (i.e., front) down
- * and released in the opposite order.  Devices must be suspended
- * from the bottom (i.e., end) up and resumed in the opposite order.
- * That way no parent will be suspended while it still has an active
- * child.
- *
  * Since device_pm_add() may be called with a device semaphore held,
  * we must never try to acquire a device semaphore while holding
  * dpm_list_mutex.
  */
 
-LIST_HEAD(dpm_active);
-static LIST_HEAD(dpm_off);
-static LIST_HEAD(dpm_off_irq);
+LIST_HEAD(dpm_list);
 
 static DEFINE_MUTEX(dpm_list_mtx);
 
-/* 'true' if all devices have been suspended, protected by dpm_list_mtx */
-static bool all_sleeping;
+/*
+ * Set once the preparation of devices for a PM transition has started, reset
+ * before starting to resume devices.  Protected by dpm_list_mtx.
+ */
+static bool transition_started;
+
+/**
+ *	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 list of active devices
@@ -68,17 +75,25 @@ int device_pm_add(struct device *dev)
 		 dev->bus ? dev->bus->name : "No Bus",
 		 kobject_name(&dev->kobj));
 	mutex_lock(&dpm_list_mtx);
-	if ((dev->parent && dev->parent->power.sleeping) || all_sleeping) {
-		if (dev->parent->power.sleeping)
-			dev_warn(dev, "parent %s is sleeping\n",
+	if (dev->parent) {
+		if (dev->parent->power.status >= DPM_SUSPENDING) {
+			dev_warn(dev, "parent %s is sleeping, will not add\n",
 				dev->parent->bus_id);
-		else
-			dev_warn(dev, "all devices are sleeping\n");
+			WARN_ON(true);
+		}
+	} else if (transition_started) {
+		/*
+		 * We refuse to register parentless devices while a PM
+		 * transition is in progress in order to avoid leaving them
+		 * unhandled down the road
+		 */
 		WARN_ON(true);
 	}
 	error = dpm_sysfs_add(dev);
-	if (!error)
-		list_add_tail(&dev->power.entry, &dpm_active);
+	if (!error) {
+		dev->power.status = DPM_ON;
+		list_add_tail(&dev->power.entry, &dpm_list);
+	}
 	mutex_unlock(&dpm_list_mtx);
 	return error;
 }
@@ -100,73 +115,243 @@ void device_pm_remove(struct device *dev)
 	mutex_unlock(&dpm_list_mtx);
 }
 
+/**
+ *	pm_op - execute the PM operation appropiate for given PM event
+ *	@dev:	Device.
+ *	@ops:	PM operations to choose from.
+ *	@state:	PM transition of the system being carried out.
+ */
+static int pm_op(struct device *dev, struct pm_ops *ops, pm_message_t state)
+{
+	int error = 0;
+
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		if (ops->suspend) {
+			error = ops->suspend(dev);
+			suspend_report_result(ops->suspend, error);
+		}
+		break;
+	case PM_EVENT_RESUME:
+		if (ops->resume) {
+			error = ops->resume(dev);
+			suspend_report_result(ops->resume, error);
+		}
+		break;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATION
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		if (ops->freeze) {
+			error = ops->freeze(dev);
+			suspend_report_result(ops->freeze, error);
+		}
+		break;
+	case PM_EVENT_HIBERNATE:
+		if (ops->poweroff) {
+			error = ops->poweroff(dev);
+			suspend_report_result(ops->poweroff, error);
+		}
+		break;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		if (ops->thaw) {
+			error = ops->thaw(dev);
+			suspend_report_result(ops->thaw, error);
+		}
+		break;
+	case PM_EVENT_RESTORE:
+		if (ops->restore) {
+			error = ops->restore(dev);
+			suspend_report_result(ops->restore, error);
+		}
+		break;
+#endif /* CONFIG_HIBERNATION */
+	default:
+		error = -EINVAL;
+	}
+	return error;
+}
+
+/**
+ *	pm_noirq_op - execute the PM operation appropiate for given PM event
+ *	@dev:	Device.
+ *	@ops:	PM operations to choose from.
+ *	@state: PM transition of the system being carried out.
+ *
+ *	The operation is executed with interrupts disabled by the only remaining
+ *	functional CPU in the system.
+ */
+static int pm_noirq_op(struct device *dev, struct pm_ext_ops *ops,
+			pm_message_t state)
+{
+	int error = 0;
+
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		if (ops->suspend_noirq) {
+			error = ops->suspend_noirq(dev);
+			suspend_report_result(ops->suspend_noirq, error);
+		}
+		break;
+	case PM_EVENT_RESUME:
+		if (ops->resume_noirq) {
+			error = ops->resume_noirq(dev);
+			suspend_report_result(ops->resume_noirq, error);
+		}
+		break;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATION
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		if (ops->freeze_noirq) {
+			error = ops->freeze_noirq(dev);
+			suspend_report_result(ops->freeze_noirq, error);
+		}
+		break;
+	case PM_EVENT_HIBERNATE:
+		if (ops->poweroff_noirq) {
+			error = ops->poweroff_noirq(dev);
+			suspend_report_result(ops->poweroff_noirq, error);
+		}
+		break;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		if (ops->thaw_noirq) {
+			error = ops->thaw_noirq(dev);
+			suspend_report_result(ops->thaw_noirq, error);
+		}
+		break;
+	case PM_EVENT_RESTORE:
+		if (ops->restore_noirq) {
+			error = ops->restore_noirq(dev);
+			suspend_report_result(ops->restore_noirq, error);
+		}
+		break;
+#endif /* CONFIG_HIBERNATION */
+	default:
+		error = -EINVAL;
+	}
+	return error;
+}
+
+static char *pm_verb(int event)
+{
+	switch (event) {
+	case PM_EVENT_SUSPEND:
+		return "suspend";
+	case PM_EVENT_RESUME:
+		return "resume";
+	case PM_EVENT_FREEZE:
+		return "freeze";
+	case PM_EVENT_QUIESCE:
+		return "quiesce";
+	case PM_EVENT_HIBERNATE:
+		return "hibernate";
+	case PM_EVENT_THAW:
+		return "thaw";
+	case PM_EVENT_RESTORE:
+		return "restore";
+	case PM_EVENT_RECOVER:
+		return "recover";
+	default:
+		return "(unknown PM event)";
+	}
+}
+
+static void pm_dev_dbg(struct device *dev, pm_message_t state, char *info)
+{
+	dev_dbg(dev, "%s%s%s\n", info, pm_verb(state.event),
+		((state.event & PM_EVENT_SLEEP) && device_may_wakeup(dev)) ?
+		", may wakeup" : "");
+}
+
+static void pm_dev_err(struct device *dev, pm_message_t state, char *info,
+			int error)
+{
+	printk(KERN_ERR "PM: Device %s failed to %s%s: error %d\n",
+		kobject_name(&dev->kobj), pm_verb(state.event), info, error);
+}
+
 /*------------------------- Resume routines -------------------------*/
 
 /**
- *	resume_device_early - Power on one device (early resume).
+ *	resume_device_noirq - Power on one device (early resume).
  *	@dev:	Device.
+ *	@state: PM transition of the system being carried out.
  *
  *	Must be called with interrupts disabled.
  */
-static int resume_device_early(struct device *dev)
+static int resume_device_noirq(struct device *dev, pm_message_t state)
 {
 	int error = 0;
 
 	TRACE_DEVICE(dev);
 	TRACE_RESUME(0);
 
-	if (dev->bus && dev->bus->resume_early) {
-		dev_dbg(dev, "EARLY resume\n");
+	if (!dev->bus)
+		goto End;
+
+	if (dev->bus->pm) {
+		pm_dev_dbg(dev, state, "EARLY ");
+		error = pm_noirq_op(dev, dev->bus->pm, state);
+	} else if (dev->bus->resume_early) {
+		pm_dev_dbg(dev, state, "legacy EARLY ");
 		error = dev->bus->resume_early(dev);
 	}
-
+ End:
 	TRACE_RESUME(error);
 	return error;
 }
 
 /**
  *	dpm_power_up - Power on all regular (non-sysdev) devices.
+ *	@state: PM transition of the system being carried out.
  *
- *	Walk the dpm_off_irq list and power each device up. This
- *	is used for devices that required they be powered down with
- *	interrupts disabled. As devices are powered on, they are moved
- *	to the dpm_off list.
+ *	Execute the appropriate "noirq resume" callback for all devices marked
+ *	as DPM_OFF_IRQ.
  *
  *	Must be called with interrupts disabled and only one CPU running.
  */
-static void dpm_power_up(void)
+static void dpm_power_up(pm_message_t state)
 {
+	struct device *dev;
 
-	while (!list_empty(&dpm_off_irq)) {
-		struct list_head *entry = dpm_off_irq.next;
-		struct device *dev = to_device(entry);
+	list_for_each_entry(dev, &dpm_list, power.entry)
+		if (dev->power.status > DPM_OFF) {
+			int error;
 
-		list_move_tail(entry, &dpm_off);
-		resume_device_early(dev);
+			dev->power.status = DPM_OFF;
+			error = resume_device_noirq(dev, state);
+			if (error)
+				pm_dev_err(dev, state, " early", error);
 		}
 }
 
 /**
  *	device_power_up - Turn on all devices that need special attention.
+ *	@state: PM transition of the system being carried out.
  *
  *	Power on system devices, then devices that required we shut them down
  *	with interrupts disabled.
  *
  *	Must be called with interrupts disabled.
  */
-void device_power_up(void)
+void device_power_up(pm_message_t state)
 {
 	sysdev_resume();
-	dpm_power_up();
+	dpm_power_up(state);
 }
 EXPORT_SYMBOL_GPL(device_power_up);
 
 /**
  *	resume_device - Restore state for one device.
  *	@dev:	Device.
- *
+ *	@state: PM transition of the system being carried out.
  */
-static int resume_device(struct device *dev)
+static int resume_device(struct device *dev, pm_message_t state)
 {
 	int error = 0;
 
@@ -175,21 +360,40 @@ static int resume_device(struct device *dev)
 
 	down(&dev->sem);
 
-	if (dev->bus && dev->bus->resume) {
-		dev_dbg(dev,"resuming\n");
+	if (dev->bus) {
+		if (dev->bus->pm) {
+			pm_dev_dbg(dev, state, "");
+			error = pm_op(dev, &dev->bus->pm->base, state);
+		} else if (dev->bus->resume) {
+			pm_dev_dbg(dev, state, "legacy ");
 			error = dev->bus->resume(dev);
 		}
+		if (error)
+			goto End;
+	}
 
-	if (!error && dev->type && dev->type->resume) {
-		dev_dbg(dev,"resuming\n");
+	if (dev->type) {
+		if (dev->type->pm) {
+			pm_dev_dbg(dev, state, "type ");
+			error = pm_op(dev, dev->type->pm, state);
+		} else if (dev->type->resume) {
+			pm_dev_dbg(dev, state, "legacy type ");
 			error = dev->type->resume(dev);
 		}
+		if (error)
+			goto End;
+	}
 
-	if (!error && dev->class && dev->class->resume) {
-		dev_dbg(dev,"class resume\n");
+	if (dev->class) {
+		if (dev->class->pm) {
+			pm_dev_dbg(dev, state, "class ");
+			error = pm_op(dev, dev->class->pm, state);
+		} else if (dev->class->resume) {
+			pm_dev_dbg(dev, state, "legacy class ");
 			error = dev->class->resume(dev);
 		}
-
+	}
+ End:
 	up(&dev->sem);
 
 	TRACE_RESUME(error);
@@ -198,78 +402,161 @@ static int resume_device(struct device *dev)
 
 /**
  *	dpm_resume - Resume every device.
+ *	@state: PM transition of the system being carried out.
  *
- *	Resume the devices that have either not gone through
- *	the late suspend, or that did go through it but also
- *	went through the early resume.
+ *	Execute the appropriate "resume" callback for all devices the status of
+ *	which indicates that they are inactive.
+ */
+static void dpm_resume(pm_message_t state)
+{
+	struct list_head list;
+
+	INIT_LIST_HEAD(&list);
+	mutex_lock(&dpm_list_mtx);
+	transition_started = false;
+	while (!list_empty(&dpm_list)) {
+		struct device *dev = to_device(dpm_list.next);
+
+		get_device(dev);
+		if (dev->power.status >= DPM_OFF) {
+			int error;
+
+			dev->power.status = DPM_RESUMING;
+			mutex_unlock(&dpm_list_mtx);
+
+			error = resume_device(dev, state);
+
+			mutex_lock(&dpm_list_mtx);
+			if (error)
+				pm_dev_err(dev, state, "", error);
+		} else if (dev->power.status == DPM_SUSPENDING) {
+			/* Allow new children of the device to be registered */
+			dev->power.status = DPM_RESUMING;
+		}
+		if (!list_empty(&dev->power.entry))
+			list_move_tail(&dev->power.entry, &list);
+		put_device(dev);
+	}
+	list_splice(&list, &dpm_list);
+	mutex_unlock(&dpm_list_mtx);
+}
+
+/**
+ *	complete_device - Complete a PM transition for given device
+ *	@dev:	Device.
+ *	@state: PM transition of the system being carried out.
+ */
+static void complete_device(struct device *dev, pm_message_t state)
+{
+	down(&dev->sem);
+
+	if (dev->class && dev->class->pm && dev->class->pm->complete) {
+		pm_dev_dbg(dev, state, "completing class ");
+		dev->class->pm->complete(dev);
+	}
+
+	if (dev->type && dev->type->pm && dev->type->pm->complete) {
+		pm_dev_dbg(dev, state, "completing type ");
+		dev->type->pm->complete(dev);
+	}
+
+	if (dev->bus && dev->bus->pm && dev->bus->pm->base.complete) {
+		pm_dev_dbg(dev, state, "completing ");
+		dev->bus->pm->base.complete(dev);
+	}
+
+	up(&dev->sem);
+}
+
+/**
+ *	dpm_complete - Complete a PM transition for all devices.
+ *	@state: PM transition of the system being carried out.
  *
- *	Take devices from the dpm_off_list, resume them,
- *	and put them on the dpm_locked list.
+ *	Execute the ->complete() callbacks for all devices that are not marked
+ *	as DPM_ON.
  */
-static void dpm_resume(void)
+static void dpm_complete(pm_message_t state)
 {
+	struct list_head list;
+
+	INIT_LIST_HEAD(&list);
 	mutex_lock(&dpm_list_mtx);
-	all_sleeping = false;
-	while(!list_empty(&dpm_off)) {
-		struct list_head *entry = dpm_off.next;
-		struct device *dev = to_device(entry);
+	while (!list_empty(&dpm_list)) {
+		struct device *dev = to_device(dpm_list.prev);
 
-		list_move_tail(entry, &dpm_active);
-		dev->power.sleeping = false;
+		get_device(dev);
+		if (dev->power.status > DPM_ON) {
+			dev->power.status = DPM_ON;
 			mutex_unlock(&dpm_list_mtx);
-		resume_device(dev);
+
+			complete_device(dev, state);
+
 			mutex_lock(&dpm_list_mtx);
 		}
+		if (!list_empty(&dev->power.entry))
+			list_move(&dev->power.entry, &list);
+		put_device(dev);
+	}
+	list_splice(&list, &dpm_list);
 	mutex_unlock(&dpm_list_mtx);
 }
 
 /**
  *	device_resume - Restore state of each device in system.
+ *	@state: PM transition of the system being carried out.
  *
  *	Resume all the devices, unlock them all, and allow new
  *	devices to be registered once again.
  */
-void device_resume(void)
+void device_resume(pm_message_t state)
 {
 	might_sleep();
-	dpm_resume();
+	dpm_resume(state);
+	dpm_complete(state);
 }
 EXPORT_SYMBOL_GPL(device_resume);
 
 
 /*------------------------- Suspend routines -------------------------*/
 
-static inline char *suspend_verb(u32 event)
+/**
+ *	resume_event - return a PM message representing the resume event
+ *	               corresponding to given sleep state.
+ *	@sleep_state: PM message representing a sleep state.
+ */
+static pm_message_t resume_event(pm_message_t sleep_state)
 {
-	switch (event) {
-	case PM_EVENT_SUSPEND:	return "suspend";
-	case PM_EVENT_FREEZE:	return "freeze";
-	case PM_EVENT_PRETHAW:	return "prethaw";
-	default:		return "(unknown suspend event)";
+	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;
 	}
-}
-
-static void
-suspend_device_dbg(struct device *dev, pm_message_t state, char *info)
-{
-	dev_dbg(dev, "%s%s%s\n", info, suspend_verb(state.event),
-		((state.event == PM_EVENT_SUSPEND) && device_may_wakeup(dev)) ?
-		", may wakeup" : "");
+	return PMSG_ON;
 }
 
 /**
- *	suspend_device_late - Shut down one device (late suspend).
+ *	suspend_device_noirq - Shut down one device (late suspend).
  *	@dev:	Device.
- *	@state:	Power state device is entering.
+ *	@state: PM transition of the system being carried out.
  *
  *	This is called with interrupts off and only a single CPU running.
  */
-static int suspend_device_late(struct device *dev, pm_message_t state)
+static int suspend_device_noirq(struct device *dev, pm_message_t state)
 {
 	int error = 0;
 
-	if (dev->bus && dev->bus->suspend_late) {
-		suspend_device_dbg(dev, state, "LATE ");
+	if (!dev->bus)
+		return 0;
+
+	if (dev->bus->pm) {
+		pm_dev_dbg(dev, state, "LATE ");
+		error = pm_noirq_op(dev, dev->bus->pm, state);
+	} else if (dev->bus->suspend_late) {
+		pm_dev_dbg(dev, state, "legacy LATE ");
 		error = dev->bus->suspend_late(dev, state);
 		suspend_report_result(dev->bus->suspend_late, error);
 	}
@@ -278,37 +565,30 @@ static int suspend_device_late(struct device *dev, pm_message_t state)
 
 /**
  *	device_power_down - Shut down special devices.
- *	@state:		Power state to enter.
+ *	@state: PM transition of the system being carried out.
  *
- *	Power down devices that require interrupts to be disabled
- *	and move them from the dpm_off list to the dpm_off_irq list.
+ *	Power down devices that require interrupts to be disabled.
  *	Then power down system devices.
  *
  *	Must be called with interrupts disabled and only one CPU running.
  */
 int device_power_down(pm_message_t state)
 {
+	struct device *dev;
 	int error = 0;
 
-	while (!list_empty(&dpm_off)) {
-		struct list_head *entry = dpm_off.prev;
-		struct device *dev = to_device(entry);
-
-		error = suspend_device_late(dev, state);
+	list_for_each_entry_reverse(dev, &dpm_list, power.entry) {
+		error = suspend_device_noirq(dev, state);
 		if (error) {
-			printk(KERN_ERR "Could not power down device %s: "
-					"error %d\n",
-					kobject_name(&dev->kobj), error);
+			pm_dev_err(dev, state, " late", error);
 			break;
 		}
-		if (!list_empty(&dev->power.entry))
-			list_move(&dev->power.entry, &dpm_off_irq);
+		dev->power.status = DPM_OFF_IRQ;
 	}
-
 	if (!error)
 		error = sysdev_suspend(state);
 	if (error)
-		dpm_power_up();
+		dpm_power_up(resume_event(state));
 	return error;
 }
 EXPORT_SYMBOL_GPL(device_power_down);
@@ -316,7 +596,7 @@ EXPORT_SYMBOL_GPL(device_power_down);
 /**
  *	suspend_device - Save state of one device.
  *	@dev:	Device.
- *	@state:	Power state device is entering.
+ *	@state: PM transition of the system being carried out.
  */
 static int suspend_device(struct device *dev, pm_message_t state)
 {
@@ -324,24 +604,43 @@ static int suspend_device(struct device *dev, pm_message_t state)
 
 	down(&dev->sem);
 
-	if (dev->class && dev->class->suspend) {
-		suspend_device_dbg(dev, state, "class ");
+	if (dev->class) {
+		if (dev->class->pm) {
+			pm_dev_dbg(dev, state, "class ");
+			error = pm_op(dev, dev->class->pm, state);
+		} else if (dev->class->suspend) {
+			pm_dev_dbg(dev, state, "legacy class ");
 			error = dev->class->suspend(dev, state);
 			suspend_report_result(dev->class->suspend, error);
 		}
+		if (error)
+			goto End;
+	}
 
-	if (!error && dev->type && dev->type->suspend) {
-		suspend_device_dbg(dev, state, "type ");
+	if (dev->type) {
+		if (dev->type->pm) {
+			pm_dev_dbg(dev, state, "type ");
+			error = pm_op(dev, dev->type->pm, state);
+		} else if (dev->type->suspend) {
+			pm_dev_dbg(dev, state, "legacy type ");
 			error = dev->type->suspend(dev, state);
 			suspend_report_result(dev->type->suspend, error);
 		}
+		if (error)
+			goto End;
+	}
 
-	if (!error && dev->bus && dev->bus->suspend) {
-		suspend_device_dbg(dev, state, "");
+	if (dev->bus) {
+		if (dev->bus->pm) {
+			pm_dev_dbg(dev, state, "");
+			error = pm_op(dev, &dev->bus->pm->base, state);
+		} else if (dev->bus->suspend) {
+			pm_dev_dbg(dev, state, "legacy ");
 			error = dev->bus->suspend(dev, state);
 			suspend_report_result(dev->bus->suspend, error);
 		}
-
+	}
+ End:
 	up(&dev->sem);
 
 	return error;
@@ -349,67 +648,141 @@ static int suspend_device(struct device *dev, pm_message_t state)
 
 /**
  *	dpm_suspend - Suspend every device.
- *	@state:	Power state to put each device in.
+ *	@state: PM transition of the system being carried out.
  *
- *	Walk the dpm_locked list.  Suspend each device and move it
- *	to the dpm_off list.
- *
- *	(For historical reasons, if it returns -EAGAIN, that used to mean
- *	that the device would be called again with interrupts disabled.
- *	These days, we use the "suspend_late()" callback for that, so we
- *	print a warning and consider it an error).
+ *	Execute the appropriate "suspend" callbacks for all devices.
  */
 static int dpm_suspend(pm_message_t state)
 {
+	struct list_head list;
 	int error = 0;
 
+	INIT_LIST_HEAD(&list);
 	mutex_lock(&dpm_list_mtx);
-	while (!list_empty(&dpm_active)) {
-		struct list_head *entry = dpm_active.prev;
-		struct device *dev = to_device(entry);
-
-		WARN_ON(dev->parent && dev->parent->power.sleeping);
+	while (!list_empty(&dpm_list)) {
+		struct device *dev = to_device(dpm_list.prev);
 
-		dev->power.sleeping = true;
+		get_device(dev);
 		mutex_unlock(&dpm_list_mtx);
+
 		error = suspend_device(dev, state);
+
 		mutex_lock(&dpm_list_mtx);
 		if (error) {
-			printk(KERN_ERR "Could not suspend device %s: "
-					"error %d%s\n",
-					kobject_name(&dev->kobj),
-					error,
-					(error == -EAGAIN ?
-					" (please convert to suspend_late)" :
-					""));
-			dev->power.sleeping = false;
+			pm_dev_err(dev, state, "", error);
+			put_device(dev);
 			break;
 		}
+		dev->power.status = DPM_OFF;
 		if (!list_empty(&dev->power.entry))
-			list_move(&dev->power.entry, &dpm_off);
+			list_move(&dev->power.entry, &list);
+		put_device(dev);
 	}
-	if (!error)
-		all_sleeping = true;
+	list_splice(&list, dpm_list.prev);
+	mutex_unlock(&dpm_list_mtx);
+	return error;
+}
+
+/**
+ *	prepare_device - Execute the ->prepare() callback(s) for given device.
+ *	@dev:	Device.
+ *	@state: PM transition of the system being carried out.
+ */
+static int prepare_device(struct device *dev, pm_message_t state)
+{
+	int error = 0;
+
+	down(&dev->sem);
+
+	if (dev->bus && dev->bus->pm && dev->bus->pm->base.prepare) {
+		pm_dev_dbg(dev, state, "preparing ");
+		error = dev->bus->pm->base.prepare(dev);
+		suspend_report_result(dev->bus->pm->base.prepare, error);
+		if (error)
+			goto End;
+	}
+
+	if (dev->type && dev->type->pm && dev->type->pm->prepare) {
+		pm_dev_dbg(dev, state, "preparing type ");
+		error = dev->type->pm->prepare(dev);
+		suspend_report_result(dev->type->pm->prepare, error);
+		if (error)
+			goto End;
+	}
+
+	if (dev->class && dev->class->pm && dev->class->pm->prepare) {
+		pm_dev_dbg(dev, state, "preparing class ");
+		error = dev->class->pm->prepare(dev);
+		suspend_report_result(dev->class->pm->prepare, error);
+	}
+ End:
+	up(&dev->sem);
+
+	return error;
+}
+
+/**
+ *	dpm_prepare - Prepare all devices for a PM transition.
+ *	@state: PM transition of the system being carried out.
+ *
+ *	Execute the ->prepare() callback for all devices.
+ */
+static int dpm_prepare(pm_message_t state)
+{
+	struct list_head list;
+	int error = 0;
+
+	INIT_LIST_HEAD(&list);
+	mutex_lock(&dpm_list_mtx);
+	transition_started = true;
+	while (!list_empty(&dpm_list)) {
+		struct device *dev = to_device(dpm_list.next);
+
+		get_device(dev);
+		dev->power.status = DPM_PREPARING;
 		mutex_unlock(&dpm_list_mtx);
 
+		error = prepare_device(dev, state);
+
+		mutex_lock(&dpm_list_mtx);
+		if (error) {
+			dev->power.status = DPM_ON;
+			if (error == -EAGAIN) {
+				put_device(dev);
+				continue;
+			}
+			printk(KERN_ERR "PM: Failed to prepare device %s "
+				"for power transition: error %d\n",
+				kobject_name(&dev->kobj), error);
+			put_device(dev);
+			break;
+		}
+		dev->power.status = DPM_SUSPENDING;
+		if (!list_empty(&dev->power.entry))
+			list_move_tail(&dev->power.entry, &list);
+		put_device(dev);
+	}
+	list_splice(&list, &dpm_list);
+	mutex_unlock(&dpm_list_mtx);
 	return error;
 }
 
 /**
  *	device_suspend - Save state and stop all devices in system.
- *	@state: new power management state
+ *	@state: PM transition of the system being carried out.
  *
- *	Prevent new devices from being registered, then lock all devices
- *	and suspend them.
+ *	Prepare and suspend all devices.
  */
 int device_suspend(pm_message_t state)
 {
 	int error;
 
 	might_sleep();
+	error = dpm_prepare(state);
+	if (!error)
 		error = dpm_suspend(state);
 	if (error)
-		device_resume();
+		device_resume(resume_event(state));
 	return error;
 }
 EXPORT_SYMBOL_GPL(device_suspend);

drivers/base/power/power.h

@@ -4,7 +4,7 @@
  * main.c
  */
 
-extern struct list_head dpm_active;	/* The active device list */
+extern struct list_head dpm_list;	/* The active device list */
 
 static inline struct device *to_device(struct list_head *entry)
 {

drivers/base/power/trace.c

@@ -188,9 +188,9 @@ static int show_file_hash(unsigned int value)
 static int show_dev_hash(unsigned int value)
 {
 	int match = 0;
-	struct list_head * entry = dpm_active.prev;
+	struct list_head *entry = dpm_list.prev;
 
-	while (entry != &dpm_active) {
+	while (entry != &dpm_list) {
 		struct device * dev = to_device(entry);
 		unsigned int hash = hash_string(DEVSEED, dev->bus_id, DEVHASH);
 		if (hash == value) {

include/linux/device.h

@@ -68,6 +68,8 @@ struct bus_type {
 	int (*resume_early)(struct device *dev);
 	int (*resume)(struct device *dev);
 
+	struct pm_ext_ops *pm;
+
 	struct bus_type_private *p;
 };
 
@@ -131,6 +133,8 @@ struct device_driver {
 	int (*resume) (struct device *dev);
 	struct attribute_group **groups;
 
+	struct pm_ops *pm;
+
 	struct driver_private *p;
 };
 
@@ -197,6 +201,8 @@ struct class {
 
 	int (*suspend)(struct device *dev, pm_message_t state);
 	int (*resume)(struct device *dev);
+
+	struct pm_ops *pm;
 };
 
 extern int __must_check class_register(struct class *class);
@@ -248,8 +254,11 @@ struct device_type {
 	struct attribute_group **groups;
 	int (*uevent)(struct device *dev, struct kobj_uevent_env *env);
 	void (*release)(struct device *dev);
+
 	int (*suspend)(struct device *dev, pm_message_t state);
 	int (*resume)(struct device *dev);
+
+	struct pm_ops *pm;
 };
 
 /* interface for exporting device attributes */

include/linux/pm.h

@@ -112,7 +112,9 @@ typedef struct pm_message {
 	int event;
 } pm_message_t;
 
-/*
+/**
+ * struct pm_ops - device PM callbacks
+ *
  * Several driver power state transitions are externally visible, affecting
  * the state of pending I/O queues and (for drivers that touch hardware)
  * interrupts, wakeups, DMA, and other hardware state.  There may also be
@@ -120,6 +122,284 @@ typedef struct pm_message {
  * to the rest of the driver stack (such as a driver that's ON gating off
  * clocks which are not in active use).
  *
+ * The externally visible transitions are handled with the help of the following
+ * callbacks included in this structure:
+ *
+ * @prepare: Prepare the device for the upcoming transition, but do NOT change
+ *	its hardware state.  Prevent new children of the device from being
+ *	registered after @prepare() returns (the driver's subsystem and
+ *	generally the rest of the kernel is supposed to prevent new calls to the
+ *	probe method from being made too once @prepare() has succeeded).  If
+ *	@prepare() detects a situation it cannot handle (e.g. registration of a
+ *	child already in progress), it may return -EAGAIN, so that the PM core
+ *	can execute it once again (e.g. after the new child has been registered)
+ *	to recover from the race condition.  This method is executed for all
+ *	kinds of suspend transitions and is followed by one of the suspend
+ *	callbacks: @suspend(), @freeze(), or @poweroff().
+ *	The PM core executes @prepare() for all devices before starting to
+ *	execute suspend callbacks for any of them, so drivers may assume all of
+ *	the other devices to be present and functional while @prepare() is being
+ *	executed.  In particular, it is safe to make GFP_KERNEL memory
+ *	allocations from within @prepare().  However, drivers may NOT assume
+ *	anything about the availability of the user space at that time and it
+ *	is not correct to request firmware from within @prepare() (it's too
+ *	late to do that).  [To work around this limitation, drivers may
+ *	register suspend and hibernation notifiers that are executed before the
+ *	freezing of tasks.]
+ *
+ * @complete: Undo the changes made by @prepare().  This method is executed for
+ *	all kinds of resume transitions, following one of the resume callbacks:
+ *	@resume(), @thaw(), @restore().  Also called if the state transition
+ *	fails before the driver's suspend callback (@suspend(), @freeze(),
+ *	@poweroff()) can be executed (e.g. if the suspend callback fails for one
+ *	of the other devices that the PM core has unsuccessfully attempted to
+ *	suspend earlier).
+ *	The PM core executes @complete() after it has executed the appropriate
+ *	resume callback for all devices.
+ *
+ * @suspend: Executed before putting the system into a sleep state in which the
+ *	contents of main memory are preserved.  Quiesce the device, put it into
+ *	a low power state appropriate for the upcoming system state (such as
+ *	PCI_D3hot), and enable wakeup events as appropriate.
+ *
+ * @resume: Executed after waking the system up from a sleep state in which the
+ *	contents of main memory were preserved.  Put the device into the
+ *	appropriate state, according to the information saved in memory by the
+ *	preceding @suspend().  The driver starts working again, responding to
+ *	hardware events and software requests.  The hardware may have gone
+ *	through a power-off reset, or it may have maintained state from the
+ *	previous suspend() which the driver may rely on while resuming.  On most
+ *	platforms, there are no restrictions on availability of resources like
+ *	clocks during @resume().
+ *
+ * @freeze: Hibernation-specific, executed before creating a hibernation image.
+ *	Quiesce operations so that a consistent image can be created, but do NOT
+ *	otherwise put the device into a low power device state and do NOT emit
+ *	system wakeup events.  Save in main memory the device settings to be
+ *	used by @restore() during the subsequent resume from hibernation or by
+ *	the subsequent @thaw(), if the creation of the image or the restoration
+ *	of main memory contents from it fails.
+ *
+ * @thaw: Hibernation-specific, executed after creating a hibernation image OR
+ *	if the creation of the image fails.  Also executed after a failing
+ *	attempt to restore the contents of main memory from such an image.
+ *	Undo the changes made by the preceding @freeze(), so the device can be
+ *	operated in the same way as immediately before the call to @freeze().
+ *
+ * @poweroff: Hibernation-specific, executed after saving a hibernation image.
+ *	Quiesce the device, put it into a low power state appropriate for the
+ *	upcoming system state (such as PCI_D3hot), and enable wakeup events as
+ *	appropriate.
+ *
+ * @restore: Hibernation-specific, executed after restoring the contents of main
+ *	memory from a hibernation image.  Driver starts working again,
+ *	responding to hardware events and software requests.  Drivers may NOT
+ *	make ANY assumptions about the hardware state right prior to @restore().
+ *	On most platforms, there are no restrictions on availability of
+ *	resources like clocks during @restore().
+ *
+ * All of the above callbacks, except for @complete(), return error codes.
+ * However, the error codes returned by the resume operations, @resume(),
+ * @thaw(), and @restore(), do not cause the PM core to abort the resume
+ * transition during which they are returned.  The error codes returned in
+ * that cases are only printed by the PM core to the system logs for debugging
+ * purposes.  Still, it is recommended that drivers only return error codes
+ * from their resume methods in case of an unrecoverable failure (i.e. when the
+ * device being handled refuses to resume and becomes unusable) to allow us to
+ * modify the PM core in the future, so that it can avoid attempting to handle
+ * devices that failed to resume and their children.
+ *
+ * It is allowed to unregister devices while the above callbacks are being
+ * executed.  However, it is not allowed to unregister a device from within any
+ * of its own callbacks.
+ */
+
+struct pm_ops {
+	int (*prepare)(struct device *dev);
+	void (*complete)(struct device *dev);
+	int (*suspend)(struct device *dev);
+	int (*resume)(struct device *dev);
+	int (*freeze)(struct device *dev);
+	int (*thaw)(struct device *dev);
+	int (*poweroff)(struct device *dev);
+	int (*restore)(struct device *dev);
+};
+
+/**
+ * struct pm_ext_ops - extended device PM callbacks
+ *
+ * Some devices require certain operations related to suspend and hibernation
+ * to be carried out with interrupts disabled.  Thus, 'struct pm_ext_ops' below
+ * is defined, adding callbacks to be executed with interrupts disabled to
+ * 'struct pm_ops'.
+ *
+ * The following callbacks included in 'struct pm_ext_ops' are executed with
+ * the nonboot CPUs switched off and with interrupts disabled on the only
+ * functional CPU.  They also are executed with the PM core list of devices
+ * locked, so they must NOT unregister any devices.
+ *
+ * @suspend_noirq: Complete the operations of ->suspend() by carrying out any
+ *	actions required for suspending the device that need interrupts to be
+ *	disabled
+ *
+ * @resume_noirq: Prepare for the execution of ->resume() by carrying out any
+ *	actions required for resuming the device that need interrupts to be
+ *	disabled
+ *
+ * @freeze_noirq: Complete the operations of ->freeze() by carrying out any
+ *	actions required for freezing the device that need interrupts to be
+ *	disabled
+ *
+ * @thaw_noirq: Prepare for the execution of ->thaw() by carrying out any
+ *	actions required for thawing the device that need interrupts to be
+ *	disabled
+ *
+ * @poweroff_noirq: Complete the operations of ->poweroff() by carrying out any
+ *	actions required for handling the device that need interrupts to be
+ *	disabled
+ *
+ * @restore_noirq: Prepare for the execution of ->restore() by carrying out any
+ *	actions required for restoring the operations of the device that need
+ *	interrupts to be disabled
+ *
+ * All of the above callbacks return error codes, but the error codes returned
+ * by the resume operations, @resume_noirq(), @thaw_noirq(), and
+ * @restore_noirq(), do not cause the PM core to abort the resume transition
+ * during which they are returned.  The error codes returned in that cases are
+ * only printed by the PM core to the system logs for debugging purposes.
+ * Still, as stated above, it is recommended that drivers only return error
+ * codes from their resume methods if the device being handled fails to resume
+ * and is not usable any more.
+ */
+
+struct pm_ext_ops {
+	struct pm_ops base;
+	int (*suspend_noirq)(struct device *dev);
+	int (*resume_noirq)(struct device *dev);
+	int (*freeze_noirq)(struct device *dev);
+	int (*thaw_noirq)(struct device *dev);
+	int (*poweroff_noirq)(struct device *dev);
+	int (*restore_noirq)(struct device *dev);
+};
+
+/**
+ * PM_EVENT_ messages
+ *
+ * The following PM_EVENT_ messages are defined for the internal use of the PM
+ * core, in order to provide a mechanism allowing the high level suspend and
+ * hibernation code to convey the necessary information to the device PM core
+ * code:
+ *
+ * ON		No transition.
+ *
+ * FREEZE 	System is going to hibernate, call ->prepare() and ->freeze()
+ *		for all devices.
+ *
+ * SUSPEND	System is going to suspend, call ->prepare() and ->suspend()
+ *		for all devices.
+ *
+ * HIBERNATE	Hibernation image has been saved, call ->prepare() and
+ *		->poweroff() for all devices.
+ *
+ * QUIESCE	Contents of main memory are going to be restored from a (loaded)
+ *		hibernation image, call ->prepare() and ->freeze() for all
+ *		devices.
+ *
+ * RESUME	System is resuming, call ->resume() and ->complete() for all
+ *		devices.
+ *
+ * THAW		Hibernation image has been created, call ->thaw() and
+ *		->complete() for all devices.
+ *
+ * RESTORE	Contents of main memory have been restored from a hibernation
+ *		image, call ->restore() and ->complete() for all devices.
+ *
+ * RECOVER	Creation of a hibernation image or restoration of the main
+ *		memory contents from a hibernation image has failed, call
+ *		->thaw() and ->complete() for all devices.
+ */
+
+#define PM_EVENT_ON		0x0000
+#define PM_EVENT_FREEZE 	0x0001
+#define PM_EVENT_SUSPEND	0x0002
+#define PM_EVENT_HIBERNATE	0x0004
+#define PM_EVENT_QUIESCE	0x0008
+#define PM_EVENT_RESUME		0x0010
+#define PM_EVENT_THAW		0x0020
+#define PM_EVENT_RESTORE	0x0040
+#define PM_EVENT_RECOVER	0x0080
+
+#define PM_EVENT_SLEEP	(PM_EVENT_SUSPEND | PM_EVENT_HIBERNATE)
+
+#define PMSG_FREEZE	((struct pm_message){ .event = PM_EVENT_FREEZE, })
+#define PMSG_QUIESCE	((struct pm_message){ .event = PM_EVENT_QUIESCE, })
+#define PMSG_SUSPEND	((struct pm_message){ .event = PM_EVENT_SUSPEND, })
+#define PMSG_HIBERNATE	((struct pm_message){ .event = PM_EVENT_HIBERNATE, })
+#define PMSG_RESUME	((struct pm_message){ .event = PM_EVENT_RESUME, })
+#define PMSG_THAW	((struct pm_message){ .event = PM_EVENT_THAW, })
+#define PMSG_RESTORE	((struct pm_message){ .event = PM_EVENT_RESTORE, })
+#define PMSG_RECOVER	((struct pm_message){ .event = PM_EVENT_RECOVER, })
+#define PMSG_ON		((struct pm_message){ .event = PM_EVENT_ON, })
+
+/**
+ * Device power management states
+ *
+ * These state labels are used internally by the PM core to indicate the current
+ * status of a device with respect to the PM core operations.
+ *
+ * DPM_ON		Device is regarded as operational.  Set this way
+ *			initially and when ->complete() is about to be called.
+ *			Also set when ->prepare() fails.
+ *
+ * DPM_PREPARING	Device is going to be prepared for a PM transition.  Set
+ *			when ->prepare() is about to be called.
+ *
+ * DPM_RESUMING		Device is going to be resumed.  Set when ->resume(),
+ *			->thaw(), or ->restore() is about to be called.
+ *
+ * DPM_SUSPENDING	Device has been prepared for a power transition.  Set
+ *			when ->prepare() has just succeeded.
+ *
+ * DPM_OFF		Device is regarded as inactive.  Set immediately after
+ *			->suspend(), ->freeze(), or ->poweroff() has succeeded.
+ *			Also set when ->resume()_noirq, ->thaw_noirq(), or
+ *			->restore_noirq() is about to be called.
+ *
+ * DPM_OFF_IRQ		Device is in a "deep sleep".  Set immediately after
+ *			->suspend_noirq(), ->freeze_noirq(), or
+ *			->poweroff_noirq() has just succeeded.
+ */
+
+enum dpm_state {
+	DPM_INVALID,
+	DPM_ON,
+	DPM_PREPARING,
+	DPM_RESUMING,
+	DPM_SUSPENDING,
+	DPM_OFF,
+	DPM_OFF_IRQ,
+};
+
+struct dev_pm_info {
+	pm_message_t		power_state;
+	unsigned		can_wakeup:1;
+	unsigned		should_wakeup:1;
+	enum dpm_state		status;		/* Owned by the PM core */
+#ifdef	CONFIG_PM_SLEEP
+	struct list_head	entry;
+#endif
+};
+
+/*
+ * The PM_EVENT_ messages are also used by drivers implementing the legacy
+ * suspend framework, based on the ->suspend() and ->resume() callbacks common
+ * for suspend and hibernation transitions, according to the rules below.
+ */
+
+/* Necessary, because several drivers use PM_EVENT_PRETHAW */
+#define PM_EVENT_PRETHAW PM_EVENT_QUIESCE
+
+/*
  * One transition is triggered by resume(), after a suspend() call; the
  * message is implicit:
  *
@@ -164,35 +444,13 @@ typedef struct pm_message {
  * or from system low-power states such as standby or suspend-to-RAM.
  */
 
-#define PM_EVENT_ON 0
-#define PM_EVENT_FREEZE 1
-#define PM_EVENT_SUSPEND 2
-#define PM_EVENT_HIBERNATE 4
-#define PM_EVENT_PRETHAW 8
-
-#define PM_EVENT_SLEEP	(PM_EVENT_SUSPEND | PM_EVENT_HIBERNATE)
-
-#define PMSG_FREEZE	((struct pm_message){ .event = PM_EVENT_FREEZE, })
-#define PMSG_PRETHAW	((struct pm_message){ .event = PM_EVENT_PRETHAW, })
-#define PMSG_SUSPEND	((struct pm_message){ .event = PM_EVENT_SUSPEND, })
-#define PMSG_HIBERNATE	((struct pm_message){ .event = PM_EVENT_HIBERNATE, })
-#define PMSG_ON		((struct pm_message){ .event = PM_EVENT_ON, })
-
-struct dev_pm_info {
-	pm_message_t		power_state;
-	unsigned		can_wakeup:1;
-	unsigned		should_wakeup:1;
-	bool			sleeping:1;	/* Owned by the PM core */
 #ifdef CONFIG_PM_SLEEP
-	struct list_head	entry;
-#endif
-};
+extern void device_pm_lock(void);
+extern void device_power_up(pm_message_t state);
+extern void device_resume(pm_message_t state);
 
+extern void device_pm_unlock(void);
 extern int device_power_down(pm_message_t state);
-extern void device_power_up(void);
-extern void device_resume(void);
-
-#ifdef CONFIG_PM_SLEEP
 extern int device_suspend(pm_message_t state);
 extern int device_prepare_suspend(pm_message_t state);
 

kernel/power/disk.c

@@ -193,6 +193,7 @@ static int create_image(int platform_mode)
 	if (error)
 		return error;
 
+	device_pm_lock();
 	local_irq_disable();
 	/* At this point, device_suspend() has been called, but *not*
 	 * device_power_down(). We *must* call device_power_down() now.
@@ -224,9 +225,11 @@ static int create_image(int platform_mode)
 	/* NOTE:  device_power_up() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
-	device_power_up();
+	device_power_up(in_suspend ?
+		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
  Enable_irqs:
 	local_irq_enable();
+	device_pm_unlock();
 	return error;
 }
 
@@ -280,7 +283,8 @@ int hibernation_snapshot(int platform_mode)
  Finish:
 	platform_finish(platform_mode);
  Resume_devices:
-	device_resume();
+	device_resume(in_suspend ?
+		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
  Resume_console:
 	resume_console();
  Close:
@@ -300,8 +304,9 @@ static int resume_target_kernel(void)
 {
 	int error;
 
+	device_pm_lock();
 	local_irq_disable();
-	error = device_power_down(PMSG_PRETHAW);
+	error = device_power_down(PMSG_QUIESCE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting resume\n");
@@ -329,9 +334,10 @@ static int resume_target_kernel(void)
 	swsusp_free();
 	restore_processor_state();
 	touch_softlockup_watchdog();
-	device_power_up();
+	device_power_up(PMSG_RECOVER);
  Enable_irqs:
 	local_irq_enable();
+	device_pm_unlock();
 	return error;
 }
 
@@ -350,7 +356,7 @@ int hibernation_restore(int platform_mode)
 
 	pm_prepare_console();
 	suspend_console();
-	error = device_suspend(PMSG_PRETHAW);
+	error = device_suspend(PMSG_QUIESCE);
 	if (error)
 		goto Finish;
 
@@ -362,7 +368,7 @@ int hibernation_restore(int platform_mode)
 		enable_nonboot_cpus();
 	}
 	platform_restore_cleanup(platform_mode);
-	device_resume();
+	device_resume(PMSG_RECOVER);
  Finish:
 	resume_console();
 	pm_restore_console();
@@ -403,6 +409,7 @@ int hibernation_platform_enter(void)
 	if (error)
 		goto Finish;
 
+	device_pm_lock();
 	local_irq_disable();
 	error = device_power_down(PMSG_HIBERNATE);
 	if (!error) {
@@ -411,6 +418,7 @@ int hibernation_platform_enter(void)
 		while (1);
 	}
 	local_irq_enable();
+	device_pm_unlock();
 
 	/*
 	 * We don't need to reenable the nonboot CPUs or resume consoles, since
@@ -419,7 +427,7 @@ int hibernation_platform_enter(void)
  Finish:
 	hibernation_ops->finish();
  Resume_devices:
-	device_resume();
+	device_resume(PMSG_RESTORE);
  Resume_console:
 	resume_console();
  Close:

kernel/power/main.c

@@ -228,6 +228,7 @@ static int suspend_enter(suspend_state_t state)
 {
 	int error = 0;
 
+	device_pm_lock();
 	arch_suspend_disable_irqs();
 	BUG_ON(!irqs_disabled());
 
@@ -239,10 +240,11 @@ static int suspend_enter(suspend_state_t state)
 	if (!suspend_test(TEST_CORE))
 		error = suspend_ops->enter(state);
 
-	device_power_up();
+	device_power_up(PMSG_RESUME);
  Done:
 	arch_suspend_enable_irqs();
 	BUG_ON(irqs_disabled());
+	device_pm_unlock();
 	return error;
 }
 
@@ -291,7 +293,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	if (suspend_ops->finish)
 		suspend_ops->finish();
  Resume_devices:
-	device_resume();
+	device_resume(PMSG_RESUME);
  Resume_console:
 	resume_console();
  Close: