Merge branch 'pm-sleep'

* pm-sleep:
  PM / Sleep: User space wakeup sources garbage collector Kconfig option
  PM / Sleep: Make the limit of user space wakeup sources configurable
  PM / Documentation: suspend-and-cpuhotplug.txt: Fix typo
  PM / Sleep: Fix a mistake in a conditional in autosleep_store()
  epoll: Add a flag, EPOLLWAKEUP, to prevent suspend while epoll events are ready
  PM / Sleep: Add user space interface for manipulating wakeup sources, v3
  PM / Sleep: Add "prevent autosleep time" statistics to wakeup sources
  PM / Sleep: Implement opportunistic sleep, v2
  PM / Sleep: Add wakeup_source_activate and wakeup_source_deactivate tracepoints
  PM / Sleep: Change wakeup source statistics to follow Android
  PM / Sleep: Use wait queue to signal "no wakeup events in progress"
  PM / Sleep: Look for wakeup events in later stages of device suspend
  PM / Hibernate: Hibernate/thaw fixes/improvements

Documentation/ABI/testing/sysfs-devices-power

@@ -96,16 +96,26 @@ Description:
 		is read-only.  If the device is not enabled to wake up the
 		system from sleep states, this attribute is not present.
 
-What:		/sys/devices/.../power/wakeup_hit_count
-Date:		September 2010
+What:		/sys/devices/.../power/wakeup_abort_count
+Date:		February 2012
 Contact:	Rafael J. Wysocki <rjw@sisk.pl>
 Description:
-		The /sys/devices/.../wakeup_hit_count attribute contains the
+		The /sys/devices/.../wakeup_abort_count attribute contains the
 		number of times the processing of a wakeup event associated with
-		the device might prevent the system from entering a sleep state.
-		This attribute is read-only.  If the device is not enabled to
-		wake up the system from sleep states, this attribute is not
-		present.
+		the device might have aborted system transition into a sleep
+		state in progress.  This attribute is read-only.  If the device
+		is not enabled to wake up the system from sleep states, this
+		attribute is not present.
+
+What:		/sys/devices/.../power/wakeup_expire_count
+Date:		February 2012
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_expire_count attribute contains the
+		number of times a wakeup event associated with the device has
+		been reported with a timeout that expired.  This attribute is
+		read-only.  If the device is not enabled to wake up the system
+		from sleep states, this attribute is not present.
 
 What:		/sys/devices/.../power/wakeup_active
 Date:		September 2010
@@ -148,6 +158,17 @@ Description:
 		not enabled to wake up the system from sleep states, this
 		attribute is not present.
 
+What:		/sys/devices/.../power/wakeup_prevent_sleep_time_ms
+Date:		February 2012
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/devices/.../wakeup_prevent_sleep_time_ms attribute
+		contains the total time the device has been preventing
+		opportunistic transitions to sleep states from occuring.
+		This attribute is read-only.  If the device is not enabled to
+		wake up the system from sleep states, this attribute is not
+		present.
+
 What:		/sys/devices/.../power/autosuspend_delay_ms
 Date:		September 2010
 Contact:	Alan Stern <stern@rowland.harvard.edu>

Documentation/ABI/testing/sysfs-power

@@ -172,3 +172,62 @@ 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 <rjw@sisk.pl>
+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.
+
+What:		/sys/power/wake_lock
+Date:		February 2012
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/wake_lock file allows user space to create
+		wakeup source objects and activate them on demand (if one of
+		those wakeup sources is active, reads from the
+		/sys/power/wakeup_count file block or return false).  When a
+		string without white space is written to /sys/power/wake_lock,
+		it will be assumed to represent a wakeup source name.  If there
+		is a wakeup source object with that name, it will be activated
+		(unless active already).  Otherwise, a new wakeup source object
+		will be registered, assigned the given name and activated.
+		If a string written to /sys/power/wake_lock contains white
+		space, the part of the string preceding the white space will be
+		regarded as a wakeup source name and handled as descrived above.
+		The other part of the string will be regarded as a timeout (in
+		nanoseconds) such that the wakeup source will be automatically
+		deactivated after it has expired.  The timeout, if present, is
+		set regardless of the current state of the wakeup source object
+		in question.
+
+		Reads from this file return a string consisting of the names of
+		wakeup sources created with the help of it that are active at
+		the moment, separated with spaces.
+
+
+What:		/sys/power/wake_unlock
+Date:		February 2012
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/wake_unlock file allows user space to deactivate
+		wakeup sources created with the help of /sys/power/wake_lock.
+		When a string is written to /sys/power/wake_unlock, it will be
+		assumed to represent the name of a wakeup source to deactivate.
+		If a wakeup source object of that name exists and is active at
+		the moment, it will be deactivated.
+
+		Reads from this file return a string consisting of the names of
+		wakeup sources created with the help of /sys/power/wake_lock
+		that are inactive at the moment, separated with spaces.

Documentation/power/suspend-and-cpuhotplug.txt

@@ -29,7 +29,7 @@ More details follow:
 
                                   Write 'mem' to
                                 /sys/power/state
-                                    syfs file
+                                    sysfs file
                                         |
                                         v
                                Acquire pm_mutex lock

drivers/base/power/main.c

@@ -889,6 +889,11 @@ static int dpm_suspend_noirq(pm_message_t state)
 		if (!list_empty(&dev->power.entry))
 			list_move(&dev->power.entry, &dpm_noirq_list);
 		put_device(dev);
+
+		if (pm_wakeup_pending()) {
+			error = -EBUSY;
+			break;
+		}
 	}
 	mutex_unlock(&dpm_list_mtx);
 	if (error)
@@ -962,6 +967,11 @@ static int dpm_suspend_late(pm_message_t state)
 		if (!list_empty(&dev->power.entry))
 			list_move(&dev->power.entry, &dpm_late_early_list);
 		put_device(dev);
+
+		if (pm_wakeup_pending()) {
+			error = -EBUSY;
+			break;
+		}
 	}
 	mutex_unlock(&dpm_list_mtx);
 	if (error)

drivers/base/power/sysfs.c

@@ -314,22 +314,41 @@ static ssize_t wakeup_active_count_show(struct device *dev,
 
 static DEVICE_ATTR(wakeup_active_count, 0444, wakeup_active_count_show, NULL);
 
-static ssize_t wakeup_hit_count_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+static ssize_t wakeup_abort_count_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->wakeup_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_abort_count, 0444, wakeup_abort_count_show, NULL);
+
+static ssize_t wakeup_expire_count_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
 {
 	unsigned long count = 0;
 	bool enabled = false;
 
 	spin_lock_irq(&dev->power.lock);
 	if (dev->power.wakeup) {
-		count = dev->power.wakeup->hit_count;
+		count = dev->power.wakeup->expire_count;
 		enabled = true;
 	}
 	spin_unlock_irq(&dev->power.lock);
 	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
 }
 
-static DEVICE_ATTR(wakeup_hit_count, 0444, wakeup_hit_count_show, NULL);
+static DEVICE_ATTR(wakeup_expire_count, 0444, wakeup_expire_count_show, NULL);
 
 static ssize_t wakeup_active_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
@@ -398,6 +417,27 @@ static ssize_t wakeup_last_time_show(struct device *dev,
 }
 
 static DEVICE_ATTR(wakeup_last_time_ms, 0444, wakeup_last_time_show, NULL);
+
+#ifdef CONFIG_PM_AUTOSLEEP
+static ssize_t wakeup_prevent_sleep_time_show(struct device *dev,
+					      struct device_attribute *attr,
+					      char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->prevent_sleep_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_prevent_sleep_time_ms, 0444,
+		   wakeup_prevent_sleep_time_show, NULL);
+#endif /* CONFIG_PM_AUTOSLEEP */
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_ADVANCED_DEBUG
@@ -486,11 +526,15 @@ static struct attribute *wakeup_attrs[] = {
 	&dev_attr_wakeup.attr,
 	&dev_attr_wakeup_count.attr,
 	&dev_attr_wakeup_active_count.attr,
-	&dev_attr_wakeup_hit_count.attr,
+	&dev_attr_wakeup_abort_count.attr,
+	&dev_attr_wakeup_expire_count.attr,
 	&dev_attr_wakeup_active.attr,
 	&dev_attr_wakeup_total_time_ms.attr,
 	&dev_attr_wakeup_max_time_ms.attr,
 	&dev_attr_wakeup_last_time_ms.attr,
+#ifdef CONFIG_PM_AUTOSLEEP
+	&dev_attr_wakeup_prevent_sleep_time_ms.attr,
+#endif
 #endif
 	NULL,
 };

drivers/base/power/wakeup.c

@@ -14,16 +14,15 @@
 #include <linux/suspend.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <trace/events/power.h>
 
 #include "power.h"
 
-#define TIMEOUT		100
-
 /*
  * If set, the suspend/hibernate code will abort transitions to a sleep state
  * if wakeup events are registered during or immediately before the transition.
  */
-bool events_check_enabled;
+bool events_check_enabled __read_mostly;
 
 /*
  * Combined counters of registered wakeup events and wakeup events in progress.
@@ -52,6 +51,8 @@ static void pm_wakeup_timer_fn(unsigned long data);
 
 static LIST_HEAD(wakeup_sources);
 
+static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue);
+
 /**
  * wakeup_source_prepare - Prepare a new wakeup source for initialization.
  * @ws: Wakeup source to prepare.
@@ -132,6 +133,7 @@ void wakeup_source_add(struct wakeup_source *ws)
 	spin_lock_init(&ws->lock);
 	setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws);
 	ws->active = false;
+	ws->last_time = ktime_get();
 
 	spin_lock_irq(&events_lock);
 	list_add_rcu(&ws->entry, &wakeup_sources);
@@ -374,12 +376,33 @@ EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
  */
 static void wakeup_source_activate(struct wakeup_source *ws)
 {
+	unsigned int cec;
+
 	ws->active = true;
 	ws->active_count++;
 	ws->last_time = ktime_get();
+	if (ws->autosleep_enabled)
+		ws->start_prevent_time = ws->last_time;
 
 	/* Increment the counter of events in progress. */
-	atomic_inc(&combined_event_count);
+	cec = atomic_inc_return(&combined_event_count);
+
+	trace_wakeup_source_activate(ws->name, cec);
+}
+
+/**
+ * wakeup_source_report_event - Report wakeup event using the given source.
+ * @ws: Wakeup source to report the event for.
+ */
+static void wakeup_source_report_event(struct wakeup_source *ws)
+{
+	ws->event_count++;
+	/* This is racy, but the counter is approximate anyway. */
+	if (events_check_enabled)
+		ws->wakeup_count++;
+
+	if (!ws->active)
+		wakeup_source_activate(ws);
 }
 
 /**
@@ -397,10 +420,7 @@ void __pm_stay_awake(struct wakeup_source *ws)
 
 	spin_lock_irqsave(&ws->lock, flags);
 
-	ws->event_count++;
-	if (!ws->active)
-		wakeup_source_activate(ws);
-
+	wakeup_source_report_event(ws);
 	del_timer(&ws->timer);
 	ws->timer_expires = 0;
 
@@ -432,6 +452,17 @@ void pm_stay_awake(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_stay_awake);
 
+#ifdef CONFIG_PM_AUTOSLEEP
+static void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now)
+{
+	ktime_t delta = ktime_sub(now, ws->start_prevent_time);
+	ws->prevent_sleep_time = ktime_add(ws->prevent_sleep_time, delta);
+}
+#else
+static inline void update_prevent_sleep_time(struct wakeup_source *ws,
+					     ktime_t now) {}
+#endif
+
 /**
  * wakup_source_deactivate - Mark given wakeup source as inactive.
  * @ws: Wakeup source to handle.
@@ -442,6 +473,7 @@ EXPORT_SYMBOL_GPL(pm_stay_awake);
  */
 static void wakeup_source_deactivate(struct wakeup_source *ws)
 {
+	unsigned int cnt, inpr, cec;
 	ktime_t duration;
 	ktime_t now;
 
@@ -468,14 +500,23 @@ static void wakeup_source_deactivate(struct wakeup_source *ws)
 	if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time))
 		ws->max_time = duration;
 
+	ws->last_time = now;
 	del_timer(&ws->timer);
 	ws->timer_expires = 0;
 
+	if (ws->autosleep_enabled)
+		update_prevent_sleep_time(ws, now);
+
 	/*
 	 * Increment the counter of registered wakeup events and decrement the
 	 * couter of wakeup events in progress simultaneously.
 	 */
-	atomic_add(MAX_IN_PROGRESS, &combined_event_count);
+	cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count);
+	trace_wakeup_source_deactivate(ws->name, cec);
+
+	split_counters(&cnt, &inpr);
+	if (!inpr && waitqueue_active(&wakeup_count_wait_queue))
+		wake_up(&wakeup_count_wait_queue);
 }
 
 /**
@@ -536,8 +577,10 @@ static void pm_wakeup_timer_fn(unsigned long data)
 	spin_lock_irqsave(&ws->lock, flags);
 
 	if (ws->active && ws->timer_expires
-	    && time_after_eq(jiffies, ws->timer_expires))
+	    && time_after_eq(jiffies, ws->timer_expires)) {
 		wakeup_source_deactivate(ws);
+		ws->expire_count++;
+	}
 
 	spin_unlock_irqrestore(&ws->lock, flags);
 }
@@ -564,9 +607,7 @@ void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec)
 
 	spin_lock_irqsave(&ws->lock, flags);
 
-	ws->event_count++;
-	if (!ws->active)
-		wakeup_source_activate(ws);
+	wakeup_source_report_event(ws);
 
 	if (!msec) {
 		wakeup_source_deactivate(ws);
@@ -608,24 +649,6 @@ void pm_wakeup_event(struct device *dev, unsigned int msec)
 }
 EXPORT_SYMBOL_GPL(pm_wakeup_event);
 
-/**
- * pm_wakeup_update_hit_counts - Update hit counts of all active wakeup sources.
- */
-static void pm_wakeup_update_hit_counts(void)
-{
-	unsigned long flags;
-	struct wakeup_source *ws;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
-		spin_lock_irqsave(&ws->lock, flags);
-		if (ws->active)
-			ws->hit_count++;
-		spin_unlock_irqrestore(&ws->lock, flags);
-	}
-	rcu_read_unlock();
-}
-
 /**
  * pm_wakeup_pending - Check if power transition in progress should be aborted.
  *
@@ -648,32 +671,38 @@ bool pm_wakeup_pending(void)
 		events_check_enabled = !ret;
 	}
 	spin_unlock_irqrestore(&events_lock, flags);
-	if (ret)
-		pm_wakeup_update_hit_counts();
 	return ret;
 }
 
 /**
  * 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;
 
-	for (;;) {
-		split_counters(&cnt, &inpr);
-		if (inpr == 0 || signal_pending(current))
-			break;
-		pm_wakeup_update_hit_counts();
-		schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT));
+	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();
+		}
+		finish_wait(&wakeup_count_wait_queue, &wait);
 	}
 
 	split_counters(&cnt, &inpr);
@@ -703,11 +732,37 @@ bool pm_save_wakeup_count(unsigned int count)
 		events_check_enabled = true;
 	}
 	spin_unlock_irq(&events_lock);
-	if (!events_check_enabled)
-		pm_wakeup_update_hit_counts();
 	return events_check_enabled;
 }
 
+#ifdef CONFIG_PM_AUTOSLEEP
+/**
+ * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources.
+ * @enabled: Whether to set or to clear the autosleep_enabled flags.
+ */
+void pm_wakep_autosleep_enabled(bool set)
+{
+	struct wakeup_source *ws;
+	ktime_t now = ktime_get();
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		spin_lock_irq(&ws->lock);
+		if (ws->autosleep_enabled != set) {
+			ws->autosleep_enabled = set;
+			if (ws->active) {
+				if (set)
+					ws->start_prevent_time = now;
+				else
+					update_prevent_sleep_time(ws, now);
+			}
+		}
+		spin_unlock_irq(&ws->lock);
+	}
+	rcu_read_unlock();
+}
+#endif /* CONFIG_PM_AUTOSLEEP */
+
 static struct dentry *wakeup_sources_stats_dentry;
 
 /**
@@ -723,27 +778,37 @@ static int print_wakeup_source_stats(struct seq_file *m,
 	ktime_t max_time;
 	unsigned long active_count;
 	ktime_t active_time;
+	ktime_t prevent_sleep_time;
 	int ret;
 
 	spin_lock_irqsave(&ws->lock, flags);
 
 	total_time = ws->total_time;
 	max_time = ws->max_time;
+	prevent_sleep_time = ws->prevent_sleep_time;
 	active_count = ws->active_count;
 	if (ws->active) {
-		active_time = ktime_sub(ktime_get(), ws->last_time);
+		ktime_t now = ktime_get();
+
+		active_time = ktime_sub(now, ws->last_time);
 		total_time = ktime_add(total_time, active_time);
 		if (active_time.tv64 > max_time.tv64)
 			max_time = active_time;
+
+		if (ws->autosleep_enabled)
+			prevent_sleep_time = ktime_add(prevent_sleep_time,
+				ktime_sub(now, ws->start_prevent_time));
 	} else {
 		active_time = ktime_set(0, 0);
 	}
 
-	ret = seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t"
-			"%lld\t\t%lld\t\t%lld\t\t%lld\n",
-			ws->name, active_count, ws->event_count, ws->hit_count,
+	ret = seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t"
+			"%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n",
+			ws->name, active_count, ws->event_count,
+			ws->wakeup_count, ws->expire_count,
 			ktime_to_ms(active_time), ktime_to_ms(total_time),
-			ktime_to_ms(max_time), ktime_to_ms(ws->last_time));
+			ktime_to_ms(max_time), ktime_to_ms(ws->last_time),
+			ktime_to_ms(prevent_sleep_time));
 
 	spin_unlock_irqrestore(&ws->lock, flags);
 
@@ -758,8 +823,9 @@ static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
 {
 	struct wakeup_source *ws;
 
-	seq_puts(m, "name\t\tactive_count\tevent_count\thit_count\t"
-		"active_since\ttotal_time\tmax_time\tlast_change\n");
+	seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
+		"expire_count\tactive_since\ttotal_time\tmax_time\t"
+		"last_change\tprevent_suspend_time\n");
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry)

fs/eventpoll.c

@@ -33,6 +33,7 @@
 #include <linux/bitops.h>
 #include <linux/mutex.h>
 #include <linux/anon_inodes.h>
+#include <linux/device.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/mman.h>
@@ -87,7 +88,7 @@
  */
 
 /* Epoll private bits inside the event mask */
-#define EP_PRIVATE_BITS (EPOLLONESHOT | EPOLLET)
+#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET)
 
 /* Maximum number of nesting allowed inside epoll sets */
 #define EP_MAX_NESTS 4
@@ -154,6 +155,9 @@ struct epitem {
 	/* List header used to link this item to the "struct file" items list */
 	struct list_head fllink;
 
+	/* wakeup_source used when EPOLLWAKEUP is set */
+	struct wakeup_source *ws;
+
 	/* The structure that describe the interested events and the source fd */
 	struct epoll_event event;
 };
@@ -194,6 +198,9 @@ struct eventpoll {
 	 */
 	struct epitem *ovflist;
 
+	/* wakeup_source used when ep_scan_ready_list is running */
+	struct wakeup_source *ws;
+
 	/* The user that created the eventpoll descriptor */
 	struct user_struct *user;
 
@@ -588,8 +595,10 @@ static int ep_scan_ready_list(struct eventpoll *ep,
 		 * queued into ->ovflist but the "txlist" might already
 		 * contain them, and the list_splice() below takes care of them.
 		 */
-		if (!ep_is_linked(&epi->rdllink))
+		if (!ep_is_linked(&epi->rdllink)) {
 			list_add_tail(&epi->rdllink, &ep->rdllist);
+			__pm_stay_awake(epi->ws);
+		}
 	}
 	/*
 	 * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
@@ -602,6 +611,7 @@ static int ep_scan_ready_list(struct eventpoll *ep,
 	 * Quickly re-inject items left on "txlist".
 	 */
 	list_splice(&txlist, &ep->rdllist);
+	__pm_relax(ep->ws);
 
 	if (!list_empty(&ep->rdllist)) {
 		/*
@@ -656,6 +666,8 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
 		list_del_init(&epi->rdllink);
 	spin_unlock_irqrestore(&ep->lock, flags);
 
+	wakeup_source_unregister(epi->ws);
+
 	/* At this point it is safe to free the eventpoll item */
 	kmem_cache_free(epi_cache, epi);
 
@@ -706,6 +718,7 @@ static void ep_free(struct eventpoll *ep)
 	mutex_unlock(&epmutex);
 	mutex_destroy(&ep->mtx);
 	free_uid(ep->user);
+	wakeup_source_unregister(ep->ws);
 	kfree(ep);
 }
 
@@ -737,6 +750,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
 			 * callback, but it's not actually ready, as far as
 			 * caller requested events goes. We can remove it here.
 			 */
+			__pm_relax(epi->ws);
 			list_del_init(&epi->rdllink);
 		}
 	}
@@ -927,13 +941,23 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 		if (epi->next == EP_UNACTIVE_PTR) {
 			epi->next = ep->ovflist;
 			ep->ovflist = epi;
+			if (epi->ws) {
+				/*
+				 * Activate ep->ws since epi->ws may get
+				 * deactivated at any time.
+				 */
+				__pm_stay_awake(ep->ws);
+			}
+
 		}
 		goto out_unlock;
 	}
 
 	/* If this file is already in the ready list we exit soon */
-	if (!ep_is_linked(&epi->rdllink))
+	if (!ep_is_linked(&epi->rdllink)) {
 		list_add_tail(&epi->rdllink, &ep->rdllist);
+		__pm_stay_awake(epi->ws);
+	}
 
 	/*
 	 * Wake up ( if active ) both the eventpoll wait list and the ->poll()
@@ -1091,6 +1115,30 @@ static int reverse_path_check(void)
 	return error;
 }
 
+static int ep_create_wakeup_source(struct epitem *epi)
+{
+	const char *name;
+
+	if (!epi->ep->ws) {
+		epi->ep->ws = wakeup_source_register("eventpoll");
+		if (!epi->ep->ws)
+			return -ENOMEM;
+	}
+
+	name = epi->ffd.file->f_path.dentry->d_name.name;
+	epi->ws = wakeup_source_register(name);
+	if (!epi->ws)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void ep_destroy_wakeup_source(struct epitem *epi)
+{
+	wakeup_source_unregister(epi->ws);
+	epi->ws = NULL;
+}
+
 /*
  * Must be called with "mtx" held.
  */
@@ -1118,6 +1166,13 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	epi->event = *event;
 	epi->nwait = 0;
 	epi->next = EP_UNACTIVE_PTR;
+	if (epi->event.events & EPOLLWAKEUP) {
+		error = ep_create_wakeup_source(epi);
+		if (error)
+			goto error_create_wakeup_source;
+	} else {
+		epi->ws = NULL;
+	}
 
 	/* Initialize the poll table using the queue callback */
 	epq.epi = epi;
@@ -1164,6 +1219,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	/* If the file is already "ready" we drop it inside the ready list */
 	if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
 		list_add_tail(&epi->rdllink, &ep->rdllist);
+		__pm_stay_awake(epi->ws);
 
 		/* Notify waiting tasks that events are available */
 		if (waitqueue_active(&ep->wq))
@@ -1204,6 +1260,9 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 		list_del_init(&epi->rdllink);
 	spin_unlock_irqrestore(&ep->lock, flags);
 
+	wakeup_source_unregister(epi->ws);
+
+error_create_wakeup_source:
 	kmem_cache_free(epi_cache, epi);
 
 	return error;
@@ -1229,6 +1288,12 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
 	epi->event.events = event->events;
 	pt._key = event->events;
 	epi->event.data = event->data; /* protected by mtx */
+	if (epi->event.events & EPOLLWAKEUP) {
+		if (!epi->ws)
+			ep_create_wakeup_source(epi);
+	} else if (epi->ws) {
+		ep_destroy_wakeup_source(epi);
+	}
 
 	/*
 	 * Get current event bits. We can safely use the file* here because
@@ -1244,6 +1309,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
 		spin_lock_irq(&ep->lock);
 		if (!ep_is_linked(&epi->rdllink)) {
 			list_add_tail(&epi->rdllink, &ep->rdllist);
+			__pm_stay_awake(epi->ws);
 
 			/* Notify waiting tasks that events are available */
 			if (waitqueue_active(&ep->wq))
@@ -1282,6 +1348,18 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
 	     !list_empty(head) && eventcnt < esed->maxevents;) {
 		epi = list_first_entry(head, struct epitem, rdllink);
 
+		/*
+		 * Activate ep->ws before deactivating epi->ws to prevent
+		 * triggering auto-suspend here (in case we reactive epi->ws
+		 * below).
+		 *
+		 * This could be rearranged to delay the deactivation of epi->ws
+		 * instead, but then epi->ws would temporarily be out of sync
+		 * with ep_is_linked().
+		 */
+		if (epi->ws && epi->ws->active)
+			__pm_stay_awake(ep->ws);
+		__pm_relax(epi->ws);
 		list_del_init(&epi->rdllink);
 
 		pt._key = epi->event.events;
@@ -1298,6 +1376,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
 			if (__put_user(revents, &uevent->events) ||
 			    __put_user(epi->event.data, &uevent->data)) {
 				list_add(&epi->rdllink, head);
+				__pm_stay_awake(epi->ws);
 				return eventcnt ? eventcnt : -EFAULT;
 			}
 			eventcnt++;
@@ -1317,6 +1396,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
 				 * poll callback will queue them in ep->ovflist.
 				 */
 				list_add_tail(&epi->rdllink, &ep->rdllist);
+				__pm_stay_awake(epi->ws);
 			}
 		}
 	}
@@ -1629,6 +1709,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	if (!tfile->f_op || !tfile->f_op->poll)
 		goto error_tgt_fput;
 
+	/* Check if EPOLLWAKEUP is allowed */
+	if ((epds.events & EPOLLWAKEUP) && !capable(CAP_EPOLLWAKEUP))
+		goto error_tgt_fput;
+
 	/*
 	 * We have to check that the file structure underneath the file descriptor
 	 * the user passed to us _is_ an eventpoll file. And also we do not permit

include/linux/capability.h

@@ -360,8 +360,11 @@ struct cpu_vfs_cap_data {
 
 #define CAP_WAKE_ALARM            35
 
+/* Allow preventing system suspends while epoll events are pending */
 
-#define CAP_LAST_CAP         CAP_WAKE_ALARM
+#define CAP_EPOLLWAKEUP      36
+
+#define CAP_LAST_CAP         CAP_EPOLLWAKEUP
 
 #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
 

include/linux/eventpoll.h

@@ -26,6 +26,18 @@
 #define EPOLL_CTL_DEL 2
 #define EPOLL_CTL_MOD 3
 
+/*
+ * Request the handling of system wakeup events so as to prevent system suspends
+ * from happening while those events are being processed.
+ *
+ * Assuming neither EPOLLET nor EPOLLONESHOT is set, system suspends will not be
+ * re-allowed until epoll_wait is called again after consuming the wakeup
+ * event(s).
+ *
+ * Requires CAP_EPOLLWAKEUP
+ */
+#define EPOLLWAKEUP (1 << 29)
+
 /* Set the One Shot behaviour for the target file descriptor */
 #define EPOLLONESHOT (1 << 30)
 

include/linux/pm_wakeup.h

@@ -33,12 +33,15 @@
  *
  * @total_time: Total time this wakeup source has been active.
  * @max_time: Maximum time this wakeup source has been continuously active.
- * @last_time: Monotonic clock when the wakeup source's was activated last time.
+ * @last_time: Monotonic clock when the wakeup source's was touched last time.
+ * @prevent_sleep_time: Total time this source has been preventing autosleep.
  * @event_count: Number of signaled wakeup events.
  * @active_count: Number of times the wakeup sorce was activated.
  * @relax_count: Number of times the wakeup sorce was deactivated.
- * @hit_count: Number of times the wakeup sorce might abort system suspend.
+ * @expire_count: Number of times the wakeup source's timeout has expired.
+ * @wakeup_count: Number of times the wakeup source might abort suspend.
  * @active: Status of the wakeup source.
+ * @has_timeout: The wakeup source has been activated with a timeout.
  */
 struct wakeup_source {
 	const char 		*name;
@@ -49,11 +52,15 @@ struct wakeup_source {
 	ktime_t total_time;
 	ktime_t max_time;
 	ktime_t last_time;
+	ktime_t start_prevent_time;
+	ktime_t prevent_sleep_time;
 	unsigned long		event_count;
 	unsigned long		active_count;
 	unsigned long		relax_count;
-	unsigned long		hit_count;
-	unsigned int		active:1;
+	unsigned long		expire_count;
+	unsigned long		wakeup_count;
+	bool			active:1;
+	bool			autosleep_enabled:1;
 };
 
 #ifdef CONFIG_PM_SLEEP

include/linux/suspend.h

@@ -356,8 +356,9 @@ 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);
+extern void pm_wakep_autosleep_enabled(bool set);
 
 static inline void lock_system_sleep(void)
 {
@@ -407,6 +408,17 @@ 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

include/trace/events/power.h

@@ -65,6 +65,40 @@ TRACE_EVENT(machine_suspend,
 	TP_printk("state=%lu", (unsigned long)__entry->state)
 );
 
+DECLARE_EVENT_CLASS(wakeup_source,
+
+	TP_PROTO(const char *name, unsigned int state),
+
+	TP_ARGS(name, state),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+	),
+
+	TP_printk("%s state=0x%lx", __get_str(name),
+		(unsigned long)__entry->state)
+);
+
+DEFINE_EVENT(wakeup_source, wakeup_source_activate,
+
+	TP_PROTO(const char *name, unsigned int state),
+
+	TP_ARGS(name, state)
+);
+
+DEFINE_EVENT(wakeup_source, wakeup_source_deactivate,
+
+	TP_PROTO(const char *name, unsigned int state),
+
+	TP_ARGS(name, state)
+);
+
 #ifdef CONFIG_EVENT_POWER_TRACING_DEPRECATED
 
 /*

kernel/power/Kconfig

@@ -103,6 +103,33 @@ 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_WAKELOCKS
+	bool "User space wakeup sources interface"
+	depends on PM_SLEEP
+	default n
+	---help---
+	Allow user space to create, activate and deactivate wakeup source
+	objects with the help of a sysfs-based interface.
+
+config PM_WAKELOCKS_LIMIT
+	int "Maximum number of user space wakeup sources (0 = no limit)"
+	range 0 100000
+	default 100
+	depends on PM_WAKELOCKS
+
+config PM_WAKELOCKS_GC
+	bool "Garbage collector for user space wakeup sources"
+	depends on PM_WAKELOCKS
+	default y
+
 config PM_RUNTIME
 	bool "Run-time PM core functionality"
 	depends on !IA64_HP_SIM

kernel/power/Makefile

@@ -9,5 +9,7 @@ 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_PM_WAKELOCKS)	+= wakelock.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o

kernel/power/autosleep.c

+/*
+ * kernel/power/autosleep.c
+ *
+ * Opportunistic sleep support.
+ *
+ * Copyright (C) 2012 Rafael J. Wysocki <rjw@sisk.pl>
+ */
+
+#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) {
+		pm_wakep_autosleep_enabled(true);
+		queue_up_suspend_work();
+	} else {
+		pm_wakep_autosleep_enabled(false);
+	}
+
+	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;
+}

kernel/power/main.c

@@ -269,8 +269,7 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
 	return (s - buf);
 }
 
-static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
-			   const char *buf, size_t n)
+static suspend_state_t decode_state(const char *buf, size_t n)
 {
 #ifdef CONFIG_SUSPEND
 	suspend_state_t state = PM_SUSPEND_STANDBY;
@@ -278,27 +277,48 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
 #endif
 	char *p;
 	int len;
-	int error = -EINVAL;
 
 	p = memchr(buf, '\n', n);
 	len = p ? p - buf : n;
 
-	/* First, check if we are requested to hibernate */
-	if (len == 4 && !strncmp(buf, "disk", len)) {
-		error = hibernate();
-		goto Exit;
-	}
+	/* Check hibernation first. */
+	if (len == 4 && !strncmp(buf, "disk", len))
+		return PM_SUSPEND_MAX;
 
 #ifdef CONFIG_SUSPEND
-	for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) {
-		if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) {
-			error = pm_suspend(state);
-			break;
-		}
-	}
+	for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++)
+		if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
+			return state;
 #endif
 
- Exit:
+	return PM_SUSPEND_ON;
+}
+
+static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
+			   const char *buf, size_t n)
+{
+	suspend_state_t state;
+	int error;
+
+	error = pm_autosleep_lock();
+	if (error)
+		return error;
+
+	if (pm_autosleep_state() > PM_SUSPEND_ON) {
+		error = -EBUSY;
+		goto out;
+	}
+
+	state = decode_state(buf, n);
+	if (state < PM_SUSPEND_MAX)
+		error = pm_suspend(state);
+	else if (state == PM_SUSPEND_MAX)
+		error = hibernate();
+	else
+		error = -EINVAL;
+
+ out:
+	pm_autosleep_unlock();
 	return error ? error : n;
 }
 
@@ -339,7 +359,8 @@ static ssize_t wakeup_count_show(struct kobject *kobj,
 {
 	unsigned int val;
 
-	return pm_get_wakeup_count(&val) ? sprintf(buf, "%u\n", val) : -EINTR;
+	return pm_get_wakeup_count(&val, true) ?
+		sprintf(buf, "%u\n", val) : -EINTR;
 }
 
 static ssize_t wakeup_count_store(struct kobject *kobj,
@@ -347,15 +368,106 @@ static ssize_t wakeup_count_store(struct kobject *kobj,
 				const char *buf, size_t n)
 {
 	unsigned int val;
+	int error;
+
+	error = pm_autosleep_lock();
+	if (error)
+		return error;
+
+	if (pm_autosleep_state() > PM_SUSPEND_ON) {
+		error = -EBUSY;
+		goto out;
+	}
 
+	error = -EINVAL;
 	if (sscanf(buf, "%u", &val) == 1) {
 		if (pm_save_wakeup_count(val))
-			return n;
+			error = n;
 	}
-	return -EINVAL;
+
+ out:
+	pm_autosleep_unlock();
+	return error;
 }
 
 power_attr(wakeup_count);
+
+#ifdef CONFIG_PM_AUTOSLEEP
+static ssize_t autosleep_show(struct kobject *kobj,
+			      struct kobj_attribute *attr,
+			      char *buf)
+{
+	suspend_state_t state = pm_autosleep_state();
+
+	if (state == PM_SUSPEND_ON)
+		return sprintf(buf, "off\n");
+
+#ifdef CONFIG_SUSPEND
+	if (state < PM_SUSPEND_MAX)
+		return sprintf(buf, "%s\n", valid_state(state) ?
+						pm_states[state] : "error");
+#endif
+#ifdef CONFIG_HIBERNATION
+	return sprintf(buf, "disk\n");
+#else
+	return sprintf(buf, "error");
+#endif
+}
+
+static ssize_t autosleep_store(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       const char *buf, size_t n)
+{
+	suspend_state_t state = decode_state(buf, n);
+	int error;
+
+	if (state == PM_SUSPEND_ON
+	    && strcmp(buf, "off") && strcmp(buf, "off\n"))
+		return -EINVAL;
+
+	error = pm_autosleep_set_state(state);
+	return error ? error : n;
+}
+
+power_attr(autosleep);
+#endif /* CONFIG_PM_AUTOSLEEP */
+
+#ifdef CONFIG_PM_WAKELOCKS
+static ssize_t wake_lock_show(struct kobject *kobj,
+			      struct kobj_attribute *attr,
+			      char *buf)
+{
+	return pm_show_wakelocks(buf, true);
+}
+
+static ssize_t wake_lock_store(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       const char *buf, size_t n)
+{
+	int error = pm_wake_lock(buf);
+	return error ? error : n;
+}
+
+power_attr(wake_lock);
+
+static ssize_t wake_unlock_show(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				char *buf)
+{
+	return pm_show_wakelocks(buf, false);
+}
+
+static ssize_t wake_unlock_store(struct kobject *kobj,
+				 struct kobj_attribute *attr,
+				 const char *buf, size_t n)
+{
+	int error = pm_wake_unlock(buf);
+	return error ? error : n;
+}
+
+power_attr(wake_unlock);
+
+#endif /* CONFIG_PM_WAKELOCKS */
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_TRACE
@@ -409,6 +521,13 @@ static struct attribute * g[] = {
 #ifdef CONFIG_PM_SLEEP
 	&pm_async_attr.attr,
 	&wakeup_count_attr.attr,
+#ifdef CONFIG_PM_AUTOSLEEP
+	&autosleep_attr.attr,
+#endif
+#ifdef CONFIG_PM_WAKELOCKS
+	&wake_lock_attr.attr,
+	&wake_unlock_attr.attr,
+#endif
 #ifdef CONFIG_PM_DEBUG
 	&pm_test_attr.attr,
 #endif
@@ -444,7 +563,10 @@ static int __init pm_init(void)
 	power_kobj = kobject_create_and_add("power", NULL);
 	if (!power_kobj)
 		return -ENOMEM;
-	return sysfs_create_group(power_kobj, &attr_group);
+	error = sysfs_create_group(power_kobj, &attr_group);
+	if (error)
+		return error;
+	return pm_autosleep_init();
 }
 
 core_initcall(pm_init);

kernel/power/power.h

@@ -264,3 +264,30 @@ static inline void suspend_thaw_processes(void)
 {
 }
 #endif
+
+#ifdef CONFIG_PM_AUTOSLEEP
+
+/* kernel/power/autosleep.c */
+extern int pm_autosleep_init(void);
+extern int pm_autosleep_lock(void);
+extern void pm_autosleep_unlock(void);
+extern suspend_state_t pm_autosleep_state(void);
+extern int pm_autosleep_set_state(suspend_state_t state);
+
+#else /* !CONFIG_PM_AUTOSLEEP */
+
+static inline int pm_autosleep_init(void) { return 0; }
+static inline int pm_autosleep_lock(void) { return 0; }
+static inline void pm_autosleep_unlock(void) {}
+static inline suspend_state_t pm_autosleep_state(void) { return PM_SUSPEND_ON; }
+
+#endif /* !CONFIG_PM_AUTOSLEEP */
+
+#ifdef CONFIG_PM_WAKELOCKS
+
+/* kernel/power/wakelock.c */
+extern ssize_t pm_show_wakelocks(char *buf, bool show_active);
+extern int pm_wake_lock(const char *buf);
+extern int pm_wake_unlock(const char *buf);
+
+#endif /* !CONFIG_PM_WAKELOCKS */

kernel/power/swap.c

@@ -6,7 +6,7 @@
  *
  * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
  * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
- * Copyright (C) 2010 Bojan Smojver <bojan@rexursive.com>
+ * Copyright (C) 2010-2012 Bojan Smojver <bojan@rexursive.com>
  *
  * This file is released under the GPLv2.
  *
@@ -282,14 +282,17 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
 		return -ENOSPC;
 
 	if (bio_chain) {
-		src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+		src = (void *)__get_free_page(__GFP_WAIT | __GFP_NOWARN |
+		                              __GFP_NORETRY);
 		if (src) {
 			copy_page(src, buf);
 		} else {
 			ret = hib_wait_on_bio_chain(bio_chain); /* Free pages */
 			if (ret)
 				return ret;
-			src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+			src = (void *)__get_free_page(__GFP_WAIT |
+			                              __GFP_NOWARN |
+			                              __GFP_NORETRY);
 			if (src) {
 				copy_page(src, buf);
 			} else {
@@ -367,12 +370,17 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		clear_page(handle->cur);
 		handle->cur_swap = offset;
 		handle->k = 0;
-	}
-	if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
-		error = hib_wait_on_bio_chain(bio_chain);
-		if (error)
-			goto out;
-		handle->reqd_free_pages = reqd_free_pages();
+
+		if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
+			error = hib_wait_on_bio_chain(bio_chain);
+			if (error)
+				goto out;
+			/*
+			 * Recalculate the number of required free pages, to
+			 * make sure we never take more than half.
+			 */
+			handle->reqd_free_pages = reqd_free_pages();
+		}
 	}
  out:
 	return error;
@@ -419,8 +427,9 @@ static int swap_writer_finish(struct swap_map_handle *handle,
 /* Maximum number of threads for compression/decompression. */
 #define LZO_THREADS	3
 
-/* Maximum number of pages for read buffering. */
-#define LZO_READ_PAGES	(MAP_PAGE_ENTRIES * 8)
+/* Minimum/maximum number of pages for read buffering. */
+#define LZO_MIN_RD_PAGES	1024
+#define LZO_MAX_RD_PAGES	8192
 
 
 /**
@@ -630,12 +639,6 @@ static int save_image_lzo(struct swap_map_handle *handle,
 		}
 	}
 
-	/*
-	 * Adjust number of free pages after all allocations have been done.
-	 * We don't want to run out of pages when writing.
-	 */
-	handle->reqd_free_pages = reqd_free_pages();
-
 	/*
 	 * Start the CRC32 thread.
 	 */
@@ -657,6 +660,12 @@ static int save_image_lzo(struct swap_map_handle *handle,
 		goto out_clean;
 	}
 
+	/*
+	 * Adjust the number of required free pages after all allocations have
+	 * been done. We don't want to run out of pages when writing.
+	 */
+	handle->reqd_free_pages = reqd_free_pages();
+
 	printk(KERN_INFO
 		"PM: Using %u thread(s) for compression.\n"
 		"PM: Compressing and saving image data (%u pages) ...     ",
@@ -1067,7 +1076,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	unsigned i, thr, run_threads, nr_threads;
 	unsigned ring = 0, pg = 0, ring_size = 0,
 	         have = 0, want, need, asked = 0;
-	unsigned long read_pages;
+	unsigned long read_pages = 0;
 	unsigned char **page = NULL;
 	struct dec_data *data = NULL;
 	struct crc_data *crc = NULL;
@@ -1079,7 +1088,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	nr_threads = num_online_cpus() - 1;
 	nr_threads = clamp_val(nr_threads, 1, LZO_THREADS);
 
-	page = vmalloc(sizeof(*page) * LZO_READ_PAGES);
+	page = vmalloc(sizeof(*page) * LZO_MAX_RD_PAGES);
 	if (!page) {
 		printk(KERN_ERR "PM: Failed to allocate LZO page\n");
 		ret = -ENOMEM;
@@ -1144,15 +1153,22 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	}
 
 	/*
-	 * Adjust number of pages for read buffering, in case we are short.
+	 * Set the number of pages for read buffering.
+	 * This is complete guesswork, because we'll only know the real
+	 * picture once prepare_image() is called, which is much later on
+	 * during the image load phase. We'll assume the worst case and
+	 * say that none of the image pages are from high memory.
 	 */
-	read_pages = (nr_free_pages() - snapshot_get_image_size()) >> 1;
-	read_pages = clamp_val(read_pages, LZO_CMP_PAGES, LZO_READ_PAGES);
+	if (low_free_pages() > snapshot_get_image_size())
+		read_pages = (low_free_pages() - snapshot_get_image_size()) / 2;
+	read_pages = clamp_val(read_pages, LZO_MIN_RD_PAGES, LZO_MAX_RD_PAGES);
 
 	for (i = 0; i < read_pages; i++) {
 		page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ?
 		                                  __GFP_WAIT | __GFP_HIGH :
-		                                  __GFP_WAIT);
+		                                  __GFP_WAIT | __GFP_NOWARN |
+		                                  __GFP_NORETRY);
+
 		if (!page[i]) {
 			if (i < LZO_CMP_PAGES) {
 				ring_size = i;

kernel/power/wakelock.c

+/*
+ * kernel/power/wakelock.c
+ *
+ * User space wakeup sources support.
+ *
+ * Copyright (C) 2012 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * This code is based on the analogous interface allowing user space to
+ * manipulate wakelocks on Android.
+ */
+
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+
+static DEFINE_MUTEX(wakelocks_lock);
+
+struct wakelock {
+	char			*name;
+	struct rb_node		node;
+	struct wakeup_source	ws;
+#ifdef CONFIG_PM_WAKELOCKS_GC
+	struct list_head	lru;
+#endif
+};
+
+static struct rb_root wakelocks_tree = RB_ROOT;
+
+ssize_t pm_show_wakelocks(char *buf, bool show_active)
+{
+	struct rb_node *node;
+	struct wakelock *wl;
+	char *str = buf;
+	char *end = buf + PAGE_SIZE;
+
+	mutex_lock(&wakelocks_lock);
+
+	for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) {
+		wl = rb_entry(node, struct wakelock, node);
+		if (wl->ws.active == show_active)
+			str += scnprintf(str, end - str, "%s ", wl->name);
+	}
+	if (str > buf)
+		str--;
+
+	str += scnprintf(str, end - str, "\n");
+
+	mutex_unlock(&wakelocks_lock);
+	return (str - buf);
+}
+
+#if CONFIG_PM_WAKELOCKS_LIMIT > 0
+static unsigned int number_of_wakelocks;
+
+static inline bool wakelocks_limit_exceeded(void)
+{
+	return number_of_wakelocks > CONFIG_PM_WAKELOCKS_LIMIT;
+}
+
+static inline void increment_wakelocks_number(void)
+{
+	number_of_wakelocks++;
+}
+
+static inline void decrement_wakelocks_number(void)
+{
+	number_of_wakelocks--;
+}
+#else /* CONFIG_PM_WAKELOCKS_LIMIT = 0 */
+static inline bool wakelocks_limit_exceeded(void) { return false; }
+static inline void increment_wakelocks_number(void) {}
+static inline void decrement_wakelocks_number(void) {}
+#endif /* CONFIG_PM_WAKELOCKS_LIMIT */
+
+#ifdef CONFIG_PM_WAKELOCKS_GC
+#define WL_GC_COUNT_MAX	100
+#define WL_GC_TIME_SEC	300
+
+static LIST_HEAD(wakelocks_lru_list);
+static unsigned int wakelocks_gc_count;
+
+static inline void wakelocks_lru_add(struct wakelock *wl)
+{
+	list_add(&wl->lru, &wakelocks_lru_list);
+}
+
+static inline void wakelocks_lru_most_recent(struct wakelock *wl)
+{
+	list_move(&wl->lru, &wakelocks_lru_list);
+}
+
+static void wakelocks_gc(void)
+{
+	struct wakelock *wl, *aux;
+	ktime_t now;
+
+	if (++wakelocks_gc_count <= WL_GC_COUNT_MAX)
+		return;
+
+	now = ktime_get();
+	list_for_each_entry_safe_reverse(wl, aux, &wakelocks_lru_list, lru) {
+		u64 idle_time_ns;
+		bool active;
+
+		spin_lock_irq(&wl->ws.lock);
+		idle_time_ns = ktime_to_ns(ktime_sub(now, wl->ws.last_time));
+		active = wl->ws.active;
+		spin_unlock_irq(&wl->ws.lock);
+
+		if (idle_time_ns < ((u64)WL_GC_TIME_SEC * NSEC_PER_SEC))
+			break;
+
+		if (!active) {
+			wakeup_source_remove(&wl->ws);
+			rb_erase(&wl->node, &wakelocks_tree);
+			list_del(&wl->lru);
+			kfree(wl->name);
+			kfree(wl);
+			decrement_wakelocks_number();
+		}
+	}
+	wakelocks_gc_count = 0;
+}
+#else /* !CONFIG_PM_WAKELOCKS_GC */
+static inline void wakelocks_lru_add(struct wakelock *wl) {}
+static inline void wakelocks_lru_most_recent(struct wakelock *wl) {}
+static inline void wakelocks_gc(void) {}
+#endif /* !CONFIG_PM_WAKELOCKS_GC */
+
+static struct wakelock *wakelock_lookup_add(const char *name, size_t len,
+					    bool add_if_not_found)
+{
+	struct rb_node **node = &wakelocks_tree.rb_node;
+	struct rb_node *parent = *node;
+	struct wakelock *wl;
+
+	while (*node) {
+		int diff;
+
+		parent = *node;
+		wl = rb_entry(*node, struct wakelock, node);
+		diff = strncmp(name, wl->name, len);
+		if (diff == 0) {
+			if (wl->name[len])
+				diff = -1;
+			else
+				return wl;
+		}
+		if (diff < 0)
+			node = &(*node)->rb_left;
+		else
+			node = &(*node)->rb_right;
+	}
+	if (!add_if_not_found)
+		return ERR_PTR(-EINVAL);
+
+	if (wakelocks_limit_exceeded())
+		return ERR_PTR(-ENOSPC);
+
+	/* Not found, we have to add a new one. */
+	wl = kzalloc(sizeof(*wl), GFP_KERNEL);
+	if (!wl)
+		return ERR_PTR(-ENOMEM);
+
+	wl->name = kstrndup(name, len, GFP_KERNEL);
+	if (!wl->name) {
+		kfree(wl);
+		return ERR_PTR(-ENOMEM);
+	}
+	wl->ws.name = wl->name;
+	wakeup_source_add(&wl->ws);
+	rb_link_node(&wl->node, parent, node);
+	rb_insert_color(&wl->node, &wakelocks_tree);
+	wakelocks_lru_add(wl);
+	increment_wakelocks_number();
+	return wl;
+}
+
+int pm_wake_lock(const char *buf)
+{
+	const char *str = buf;
+	struct wakelock *wl;
+	u64 timeout_ns = 0;
+	size_t len;
+	int ret = 0;
+
+	while (*str && !isspace(*str))
+		str++;
+
+	len = str - buf;
+	if (!len)
+		return -EINVAL;
+
+	if (*str && *str != '\n') {
+		/* Find out if there's a valid timeout string appended. */
+		ret = kstrtou64(skip_spaces(str), 10, &timeout_ns);
+		if (ret)
+			return -EINVAL;
+	}
+
+	mutex_lock(&wakelocks_lock);
+
+	wl = wakelock_lookup_add(buf, len, true);
+	if (IS_ERR(wl)) {
+		ret = PTR_ERR(wl);
+		goto out;
+	}
+	if (timeout_ns) {
+		u64 timeout_ms = timeout_ns + NSEC_PER_MSEC - 1;
+
+		do_div(timeout_ms, NSEC_PER_MSEC);
+		__pm_wakeup_event(&wl->ws, timeout_ms);
+	} else {
+		__pm_stay_awake(&wl->ws);
+	}
+
+	wakelocks_lru_most_recent(wl);
+
+ out:
+	mutex_unlock(&wakelocks_lock);
+	return ret;
+}
+
+int pm_wake_unlock(const char *buf)
+{
+	struct wakelock *wl;
+	size_t len;
+	int ret = 0;
+
+	len = strlen(buf);
+	if (!len)
+		return -EINVAL;
+
+	if (buf[len-1] == '\n')
+		len--;
+
+	if (!len)
+		return -EINVAL;
+
+	mutex_lock(&wakelocks_lock);
+
+	wl = wakelock_lookup_add(buf, len, false);
+	if (IS_ERR(wl)) {
+		ret = PTR_ERR(wl);
+		goto out;
+	}
+	__pm_relax(&wl->ws);
+
+	wakelocks_lru_most_recent(wl);
+	wakelocks_gc();
+
+ out:
+	mutex_unlock(&wakelocks_lock);
+	return ret;
+}