PM / Sleep: Implement opportunistic sleep, v2

Introduce a mechanism by which the kernel can trigger global
transitions to a sleep state chosen by user space if there are no
active wakeup sources.

It consists of a new sysfs attribute, /sys/power/autosleep, that
can be written one of the strings returned by reads from
/sys/power/state, an ordered workqueue and a work item carrying out
the "suspend" operations.  If a string representing the system's
sleep state is written to /sys/power/autosleep, the work item
triggering transitions to that state is queued up and it requeues
itself after every execution until user space writes "off" to
/sys/power/autosleep.

That work item enables the detection of wakeup events using the
functions already defined in drivers/base/power/wakeup.c (with one
small modification) and calls either pm_suspend(), or hibernate() to
put the system into a sleep state.  If a wakeup event is reported
while the transition is in progress, it will abort the transition and
the "system suspend" work item will be queued up again.

Signed-off-by: Rafael J. Wysocki <[email protected]>
Acked-by: Greg Kroah-Hartman <[email protected]>
Reviewed-by: NeilBrown <[email protected]>

Documentation/ABI/testing/sysfs-power

@@ -172,3 +172,20 @@ Description:
 
 		Reading from this file will display the current value, which is
 		set to 1 MB by default.
+
+What:		/sys/power/autosleep
+Date:		April 2012
+Contact:	Rafael J. Wysocki <[email protected]>
+Description:
+		The /sys/power/autosleep file can be written one of the strings
+		returned by reads from /sys/power/state.  If that happens, a
+		work item attempting to trigger a transition of the system to
+		the sleep state represented by that string is queued up.  This
+		attempt will only succeed if there are no active wakeup sources
+		in the system at that time.  After every execution, regardless
+		of whether or not the attempt to put the system to sleep has
+		succeeded, the work item requeues itself until user space
+		writes "off" to /sys/power/autosleep.
+
+		Reading from this file causes the last string successfully
+		written to it to be returned.

drivers/base/power/wakeup.c

@@ -660,29 +660,33 @@ bool pm_wakeup_pending(void)
 /**
  * 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.  Block
- * if the current number of wakeup events being processed is nonzero.
+ * 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 wait for the number of wakeup events being processed to
- * drop down to zero has been interrupted by a signal (and the current number
- * of wakeup events being processed is still nonzero).  Otherwise return 'true'.
+ * 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 pm_get_wakeup_count(unsigned int *count, bool block)
 {
 	unsigned int cnt, inpr;
-	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;
+	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;
 
-		schedule();
+			schedule();
+		}
+		finish_wait(&wakeup_count_wait_queue, &wait);
 	}
-	finish_wait(&wakeup_count_wait_queue, &wait);
 
 	split_counters(&cnt, &inpr);
 	*count = cnt;

include/linux/suspend.h

@@ -356,7 +356,7 @@ extern int unregister_pm_notifier(struct notifier_block *nb);
 extern bool events_check_enabled;
 
 extern bool pm_wakeup_pending(void);
-extern bool pm_get_wakeup_count(unsigned int *count);
+extern bool pm_get_wakeup_count(unsigned int *count, bool block);
 extern bool pm_save_wakeup_count(unsigned int count);
 
 static inline void lock_system_sleep(void)
@@ -407,6 +407,17 @@ static inline void unlock_system_sleep(void) {}
 
 #endif /* !CONFIG_PM_SLEEP */
 
+#ifdef CONFIG_PM_AUTOSLEEP
+
+/* kernel/power/autosleep.c */
+void queue_up_suspend_work(void);
+
+#else /* !CONFIG_PM_AUTOSLEEP */
+
+static inline void queue_up_suspend_work(void) {}
+
+#endif /* !CONFIG_PM_AUTOSLEEP */
+
 #ifdef CONFIG_ARCH_SAVE_PAGE_KEYS
 /*
  * The ARCH_SAVE_PAGE_KEYS functions can be used by an architecture

kernel/power/Kconfig

@@ -103,6 +103,14 @@ config PM_SLEEP_SMP
 	select HOTPLUG
 	select HOTPLUG_CPU
 
+config PM_AUTOSLEEP
+	bool "Opportunistic sleep"
+	depends on PM_SLEEP
+	default n
+	---help---
+	Allow the kernel to trigger a system transition into a global sleep
+	state automatically whenever there are no active wakeup sources.
+
 config PM_RUNTIME
 	bool "Run-time PM core functionality"
 	depends on !IA64_HP_SIM

kernel/power/Makefile

@@ -9,5 +9,6 @@ obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
 obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o \
 				   block_io.o
+obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o

kernel/power/autosleep.c

@@ -0,0 +1,123 @@
+/*
+ * kernel/power/autosleep.c
+ *
+ * Opportunistic sleep support.
+ *
+ * Copyright (C) 2012 Rafael J. Wysocki <[email protected]>
+ */
+
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/pm_wakeup.h>
+
+#include "power.h"
+
+static suspend_state_t autosleep_state;
+static struct workqueue_struct *autosleep_wq;
+/*
+ * Note: it is only safe to mutex_lock(&autosleep_lock) if a wakeup_source
+ * is active, otherwise a deadlock with try_to_suspend() is possible.
+ * Alternatively mutex_lock_interruptible() can be used.  This will then fail
+ * if an auto_sleep cycle tries to freeze processes.
+ */
+static DEFINE_MUTEX(autosleep_lock);
+static struct wakeup_source *autosleep_ws;
+
+static void try_to_suspend(struct work_struct *work)
+{
+	unsigned int initial_count, final_count;
+
+	if (!pm_get_wakeup_count(&initial_count, true))
+		goto out;
+
+	mutex_lock(&autosleep_lock);
+
+	if (!pm_save_wakeup_count(initial_count)) {
+		mutex_unlock(&autosleep_lock);
+		goto out;
+	}
+
+	if (autosleep_state == PM_SUSPEND_ON) {
+		mutex_unlock(&autosleep_lock);
+		return;
+	}
+	if (autosleep_state >= PM_SUSPEND_MAX)
+		hibernate();
+	else
+		pm_suspend(autosleep_state);
+
+	mutex_unlock(&autosleep_lock);
+
+	if (!pm_get_wakeup_count(&final_count, false))
+		goto out;
+
+	/*
+	 * If the wakeup occured for an unknown reason, wait to prevent the
+	 * system from trying to suspend and waking up in a tight loop.
+	 */
+	if (final_count == initial_count)
+		schedule_timeout_uninterruptible(HZ / 2);
+
+ out:
+	queue_up_suspend_work();
+}
+
+static DECLARE_WORK(suspend_work, try_to_suspend);
+
+void queue_up_suspend_work(void)
+{
+	if (!work_pending(&suspend_work) && autosleep_state > PM_SUSPEND_ON)
+		queue_work(autosleep_wq, &suspend_work);
+}
+
+suspend_state_t pm_autosleep_state(void)
+{
+	return autosleep_state;
+}
+
+int pm_autosleep_lock(void)
+{
+	return mutex_lock_interruptible(&autosleep_lock);
+}
+
+void pm_autosleep_unlock(void)
+{
+	mutex_unlock(&autosleep_lock);
+}
+
+int pm_autosleep_set_state(suspend_state_t state)
+{
+
+#ifndef CONFIG_HIBERNATION
+	if (state >= PM_SUSPEND_MAX)
+		return -EINVAL;
+#endif
+
+	__pm_stay_awake(autosleep_ws);
+
+	mutex_lock(&autosleep_lock);
+
+	autosleep_state = state;
+
+	__pm_relax(autosleep_ws);
+
+	if (state > PM_SUSPEND_ON)
+		queue_up_suspend_work();
+
+	mutex_unlock(&autosleep_lock);
+	return 0;
+}
+
+int __init pm_autosleep_init(void)
+{
+	autosleep_ws = wakeup_source_register("autosleep");
+	if (!autosleep_ws)
+		return -ENOMEM;
+
+	autosleep_wq = alloc_ordered_workqueue("autosleep", 0);
+	if (autosleep_wq)
+		return 0;
+
+	wakeup_source_unregister(autosleep_ws);
+	return -ENOMEM;
+}