PM: Handle device registrations during suspend/resume

Modify the PM core to protect its data structures, specifically the
dpm_active list, from being corrupted if a child of the currently
suspending device is registered concurrently with its ->suspend()
callback.  In that case, since the new device (the child) is added
to dpm_active after its parent, the PM core will attempt to
suspend it after the parent, which is wrong.

Introduce a new member of struct dev_pm_info, called 'sleeping',
and use it to check if the parent of the device being added to
dpm_active has been suspended, in which case the device registration
fails.  Also, use 'sleeping' for checking if the ordering of devices
on dpm_active is correct.

Introduce variable 'all_sleeping' that will be set to 'true' once all
devices have been suspended and make new device registrations fail
until 'all_sleeping' is reset to 'false', in order to avoid having
unsuspended devices around while the system is going into a sleep state.

Remove pm_sleep_rwsem which is not necessary any more.

Special thanks to Alan Stern for discussions and suggestions that
lead to the creation of this patch.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

5 files changed, 40 insertions, 52 deletions

diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 461e4f1dbec4..421e7d00ffd0 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -196,6 +196,11 @@ its parent; and can't be removed or suspended after that parent.
 
 The policy is that the device tree should match hardware bus topology.
 (Or at least the control bus, for devices which use multiple busses.)
+In particular, this means that a device registration may fail if the parent of
+the device is suspending (ie. has been chosen by the PM core as the next
+device to suspend) or has already suspended, as well as after all of the other
+devices have been suspended.  Device drivers must be prepared to cope with such
+situations.
 
 
 Suspending Devices
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 24198ad01976..79848e6c5db5 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -820,7 +820,11 @@ int device_add(struct device *dev)
 	error = dpm_sysfs_add(dev);
 	if (error)
 		goto PMError;
-	device_pm_add(dev);
+	error = device_pm_add(dev);
+	if (error) {
+		dpm_sysfs_remove(dev);
+		goto PMError;
+	}
 	error = bus_add_device(dev);
 	if (error)
 		goto BusError;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 26de2c0fda80..0e3991a437c6 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -54,7 +54,8 @@ static LIST_HEAD(dpm_destroy);
 
 static DEFINE_MUTEX(dpm_list_mtx);
 
-static DECLARE_RWSEM(pm_sleep_rwsem);
+/* 'true' if all devices have been suspended, protected by dpm_list_mtx */
+static bool all_sleeping;
 
 int (*platform_enable_wakeup)(struct device *dev, int is_on);
 
@@ -62,14 +63,28 @@ int (*platform_enable_wakeup)(struct device *dev, int is_on);
  *	device_pm_add - add a device to the list of active devices
  *	@dev:	Device to be added to the list
  */
-void device_pm_add(struct device *dev)
+int device_pm_add(struct device *dev)
 {
+	int error = 0;
+
 	pr_debug("PM: Adding info for %s:%s\n",
 		 dev->bus ? dev->bus->name : "No Bus",
 		 kobject_name(&dev->kobj));
 	mutex_lock(&dpm_list_mtx);
-	list_add_tail(&dev->power.entry, &dpm_active);
+	if ((dev->parent && dev->parent->power.sleeping) || all_sleeping) {
+		if (dev->parent->power.sleeping)
+			dev_warn(dev,
+				"parent %s is sleeping, will not add\n",
+				dev->parent->bus_id);
+		else
+			dev_warn(dev, "devices are sleeping, will not add\n");
+		WARN_ON(true);
+		error = -EBUSY;
+	} else {
+		list_add_tail(&dev->power.entry, &dpm_active);
+	}
 	mutex_unlock(&dpm_list_mtx);
+	return error;
 }
 
 /**
@@ -107,32 +122,6 @@ void device_pm_schedule_removal(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(device_pm_schedule_removal);
 
-/**
- *	pm_sleep_lock - mutual exclusion for registration and suspend
- *
- *	Returns 0 if no suspend is underway and device registration
- *	may proceed, otherwise -EBUSY.
- */
-int pm_sleep_lock(void)
-{
-	if (down_read_trylock(&pm_sleep_rwsem))
-		return 0;
-
-	return -EBUSY;
-}
-
-/**
- *	pm_sleep_unlock - mutual exclusion for registration and suspend
- *
- *	This routine undoes the effect of device_pm_add_lock
- *	when a device's registration is complete.
- */
-void pm_sleep_unlock(void)
-{
-	up_read(&pm_sleep_rwsem);
-}
-
-
 /*------------------------- Resume routines -------------------------*/
 
 /**
@@ -242,11 +231,13 @@ static int resume_device(struct device *dev)
 static void dpm_resume(void)
 {
 	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);
 
 		list_move_tail(entry, &dpm_active);
+		dev->power.sleeping = false;
 		mutex_unlock(&dpm_list_mtx);
 		resume_device(dev);
 		mutex_lock(&dpm_list_mtx);
@@ -285,7 +276,6 @@ void device_resume(void)
 	might_sleep();
 	dpm_resume();
 	unregister_dropped_devices();
-	up_write(&pm_sleep_rwsem);
 }
 EXPORT_SYMBOL_GPL(device_resume);
 
@@ -421,6 +411,9 @@ static int dpm_suspend(pm_message_t state)
 		struct list_head *entry = dpm_active.prev;
 		struct device *dev = to_device(entry);
 
+		WARN_ON(dev->parent && dev->parent->power.sleeping);
+
+		dev->power.sleeping = true;
 		mutex_unlock(&dpm_list_mtx);
 		error = suspend_device(dev, state);
 		mutex_lock(&dpm_list_mtx);
@@ -432,11 +425,14 @@ static int dpm_suspend(pm_message_t state)
 					(error == -EAGAIN ?
 					" (please convert to suspend_late)" :
 					""));
+			dev->power.sleeping = false;
 			break;
 		}
 		if (!list_empty(&dev->power.entry))
 			list_move(&dev->power.entry, &dpm_off);
 	}
+	if (!error)
+		all_sleeping = true;
 	mutex_unlock(&dpm_list_mtx);
 
 	return error;
@@ -454,7 +450,6 @@ int device_suspend(pm_message_t state)
 	int error;
 
 	might_sleep();
-	down_write(&pm_sleep_rwsem);
 	error = dpm_suspend(state);
 	if (error)
 		device_resume();
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index e32d3bdb92c1..a6894f2a4b99 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -11,30 +11,13 @@ static inline struct device *to_device(struct list_head *entry)
 	return container_of(entry, struct device, power.entry);
 }
 
-extern void device_pm_add(struct device *);
+extern int device_pm_add(struct device *);
 extern void device_pm_remove(struct device *);
-extern int pm_sleep_lock(void);
-extern void pm_sleep_unlock(void);
 
 #else /* CONFIG_PM_SLEEP */
 
-
-static inline void device_pm_add(struct device *dev)
-{
-}
-
-static inline void device_pm_remove(struct device *dev)
-{
-}
-
-static inline int pm_sleep_lock(void)
-{
-	return 0;
-}
-
-static inline void pm_sleep_unlock(void)
-{
-}
+static inline int device_pm_add(struct device *dev) { return 0; }
+static inline void device_pm_remove(struct device *dev) {}
 
 #endif
 
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 015b735811b4..e6b9f29e27d7 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -183,6 +183,7 @@ typedef struct pm_message {
 struct dev_pm_info {
 	pm_message_t		power_state;
 	unsigned		can_wakeup:1;
+	bool			sleeping:1;	/* Owned by the PM core */
 #ifdef	CONFIG_PM_SLEEP
 	unsigned		should_wakeup:1;
 	struct list_head	entry;