Merge tag 'pm-for-3.5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:

 - Implementation of opportunistic suspend (autosleep) and user space
   interface for manipulating wakeup sources.

 - Hibernate updates from Bojan Smojver and Minho Ban.

 - Updates of the runtime PM core and generic PM domains framework
   related to PM QoS.

 - Assorted fixes.

* tag 'pm-for-3.5' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (25 commits)
  epoll: Fix user space breakage related to EPOLLWAKEUP
  PM / Domains: Make it possible to add devices to inactive domains
  PM / Hibernate: Use get_gendisk to verify partition if resume_file is integer format
  PM / Domains: Fix computation of maximum domain off time
  PM / Domains: Fix link checking when add subdomain
  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 / Domains: Cache device stop and domain power off governor results, v3
  PM / Domains: Make device removal more straightforward
  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 / QoS: Create device constraints objects on notifier registration
  PM / Runtime: Remove device fields related to suspend time, v2
  PM / Domains: Rework default domain power off governor function, v2
  PM / Domains: Rework default device stop governor function, v2
  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
  ...

7 files changed, 449 insertions, 253 deletions

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 73ce9fbe9839..83aa694a8efe 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -11,6 +11,7 @@
 #include <linux/io.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_domain.h>
+#include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/sched.h>
@@ -38,11 +39,13 @@
 	ktime_t __start = ktime_get();						\
 	type __retval = GENPD_DEV_CALLBACK(genpd, type, callback, dev);		\
 	s64 __elapsed = ktime_to_ns(ktime_sub(ktime_get(), __start));		\
-	struct generic_pm_domain_data *__gpd_data = dev_gpd_data(dev);		\
-	if (__elapsed > __gpd_data->td.field) {					\
-		__gpd_data->td.field = __elapsed;				\
+	struct gpd_timing_data *__td = &dev_gpd_data(dev)->td;			\
+	if (!__retval && __elapsed > __td->field) {				\
+		__td->field = __elapsed;					\
 		dev_warn(dev, name " latency exceeded, new value %lld ns\n",	\
 			__elapsed);						\
+		genpd->max_off_time_changed = true;				\
+		__td->constraint_changed = true;				\
 	}									\
 	__retval;								\
 })
@@ -211,6 +214,7 @@ int __pm_genpd_poweron(struct generic_pm_domain *genpd)
 		elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
 		if (elapsed_ns > genpd->power_on_latency_ns) {
 			genpd->power_on_latency_ns = elapsed_ns;
+			genpd->max_off_time_changed = true;
 			if (genpd->name)
 				pr_warning("%s: Power-on latency exceeded, "
 					"new value %lld ns\n", genpd->name,
@@ -247,6 +251,53 @@ int pm_genpd_poweron(struct generic_pm_domain *genpd)
 
 #ifdef CONFIG_PM_RUNTIME
 
+static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
+				     unsigned long val, void *ptr)
+{
+	struct generic_pm_domain_data *gpd_data;
+	struct device *dev;
+
+	gpd_data = container_of(nb, struct generic_pm_domain_data, nb);
+
+	mutex_lock(&gpd_data->lock);
+	dev = gpd_data->base.dev;
+	if (!dev) {
+		mutex_unlock(&gpd_data->lock);
+		return NOTIFY_DONE;
+	}
+	mutex_unlock(&gpd_data->lock);
+
+	for (;;) {
+		struct generic_pm_domain *genpd;
+		struct pm_domain_data *pdd;
+
+		spin_lock_irq(&dev->power.lock);
+
+		pdd = dev->power.subsys_data ?
+				dev->power.subsys_data->domain_data : NULL;
+		if (pdd) {
+			to_gpd_data(pdd)->td.constraint_changed = true;
+			genpd = dev_to_genpd(dev);
+		} else {
+			genpd = ERR_PTR(-ENODATA);
+		}
+
+		spin_unlock_irq(&dev->power.lock);
+
+		if (!IS_ERR(genpd)) {
+			mutex_lock(&genpd->lock);
+			genpd->max_off_time_changed = true;
+			mutex_unlock(&genpd->lock);
+		}
+
+		dev = dev->parent;
+		if (!dev || dev->power.ignore_children)
+			break;
+	}
+
+	return NOTIFY_DONE;
+}
+
 /**
  * __pm_genpd_save_device - Save the pre-suspend state of a device.
  * @pdd: Domain data of the device to save the state of.
@@ -435,6 +486,7 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
 		if (elapsed_ns > genpd->power_off_latency_ns) {
 			genpd->power_off_latency_ns = elapsed_ns;
+			genpd->max_off_time_changed = true;
 			if (genpd->name)
 				pr_warning("%s: Power-off latency exceeded, "
 					"new value %lld ns\n", genpd->name,
@@ -443,17 +495,6 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 	}
 
 	genpd->status = GPD_STATE_POWER_OFF;
-	genpd->power_off_time = ktime_get();
-
-	/* Update PM QoS information for devices in the domain. */
-	list_for_each_entry_reverse(pdd, &genpd->dev_list, list_node) {
-		struct gpd_timing_data *td = &to_gpd_data(pdd)->td;
-
-		pm_runtime_update_max_time_suspended(pdd->dev,
-					td->start_latency_ns +
-					td->restore_state_latency_ns +
-					genpd->power_on_latency_ns);
-	}
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
 		genpd_sd_counter_dec(link->master);
@@ -514,9 +555,6 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
-	pm_runtime_update_max_time_suspended(dev,
-				dev_gpd_data(dev)->td.start_latency_ns);
-
 	/*
 	 * If power.irq_safe is set, this routine will be run with interrupts
 	 * off, so it can't use mutexes.
@@ -613,6 +651,12 @@ void pm_genpd_poweroff_unused(void)
 
 #else
 
+static inline int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
+					    unsigned long val, void *ptr)
+{
+	return NOTIFY_DONE;
+}
+
 static inline void genpd_power_off_work_fn(struct work_struct *work) {}
 
 #define pm_genpd_runtime_suspend	NULL
@@ -1209,12 +1253,15 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
 		return -EINVAL;
 
-	genpd_acquire_lock(genpd);
+	gpd_data = kzalloc(sizeof(*gpd_data), GFP_KERNEL);
+	if (!gpd_data)
+		return -ENOMEM;
 
-	if (genpd->status == GPD_STATE_POWER_OFF) {
-		ret = -EINVAL;
-		goto out;
-	}
+	mutex_init(&gpd_data->lock);
+	gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier;
+	dev_pm_qos_add_notifier(dev, &gpd_data->nb);
+
+	genpd_acquire_lock(genpd);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1227,26 +1274,35 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 			goto out;
 		}
 
-	gpd_data = kzalloc(sizeof(*gpd_data), GFP_KERNEL);
-	if (!gpd_data) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
 	genpd->device_count++;
+	genpd->max_off_time_changed = true;
 
-	dev->pm_domain = &genpd->domain;
 	dev_pm_get_subsys_data(dev);
+
+	mutex_lock(&gpd_data->lock);
+	spin_lock_irq(&dev->power.lock);
+	dev->pm_domain = &genpd->domain;
 	dev->power.subsys_data->domain_data = &gpd_data->base;
 	gpd_data->base.dev = dev;
-	gpd_data->need_restore = false;
 	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
+	gpd_data->need_restore = genpd->status == GPD_STATE_POWER_OFF;
 	if (td)
 		gpd_data->td = *td;
 
+	gpd_data->td.constraint_changed = true;
+	gpd_data->td.effective_constraint_ns = -1;
+	spin_unlock_irq(&dev->power.lock);
+	mutex_unlock(&gpd_data->lock);
+
+	genpd_release_lock(genpd);
+
+	return 0;
+
  out:
 	genpd_release_lock(genpd);
 
+	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
+	kfree(gpd_data);
 	return ret;
 }
 
@@ -1290,12 +1346,15 @@ int __pm_genpd_of_add_device(struct device_node *genpd_node, struct device *dev,
 int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 			   struct device *dev)
 {
+	struct generic_pm_domain_data *gpd_data;
 	struct pm_domain_data *pdd;
-	int ret = -EINVAL;
+	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
-	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
+	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev)
+	    ||  IS_ERR_OR_NULL(dev->pm_domain)
+	    ||  pd_to_genpd(dev->pm_domain) != genpd)
 		return -EINVAL;
 
 	genpd_acquire_lock(genpd);
@@ -1305,21 +1364,27 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 		goto out;
 	}
 
-	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
-		if (pdd->dev != dev)
-			continue;
+	genpd->device_count--;
+	genpd->max_off_time_changed = true;
 
-		list_del_init(&pdd->list_node);
-		pdd->dev = NULL;
-		dev_pm_put_subsys_data(dev);
-		dev->pm_domain = NULL;
-		kfree(to_gpd_data(pdd));
+	spin_lock_irq(&dev->power.lock);
+	dev->pm_domain = NULL;
+	pdd = dev->power.subsys_data->domain_data;
+	list_del_init(&pdd->list_node);
+	dev->power.subsys_data->domain_data = NULL;
+	spin_unlock_irq(&dev->power.lock);
 
-		genpd->device_count--;
+	gpd_data = to_gpd_data(pdd);
+	mutex_lock(&gpd_data->lock);
+	pdd->dev = NULL;
+	mutex_unlock(&gpd_data->lock);
 
-		ret = 0;
-		break;
-	}
+	genpd_release_lock(genpd);
+
+	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
+	kfree(gpd_data);
+	dev_pm_put_subsys_data(dev);
+	return 0;
 
  out:
 	genpd_release_lock(genpd);
@@ -1348,6 +1413,26 @@ void pm_genpd_dev_always_on(struct device *dev, bool val)
 EXPORT_SYMBOL_GPL(pm_genpd_dev_always_on);
 
 /**
+ * pm_genpd_dev_need_restore - Set/unset the device's "need restore" flag.
+ * @dev: Device to set/unset the flag for.
+ * @val: The new value of the device's "need restore" flag.
+ */
+void pm_genpd_dev_need_restore(struct device *dev, bool val)
+{
+	struct pm_subsys_data *psd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	psd = dev_to_psd(dev);
+	if (psd && psd->domain_data)
+		to_gpd_data(psd->domain_data)->need_restore = val;
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_genpd_dev_need_restore);
+
+/**
  * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain.
  * @genpd: Master PM domain to add the subdomain to.
  * @subdomain: Subdomain to be added.
@@ -1378,7 +1463,7 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 		goto out;
 	}
 
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
+	list_for_each_entry(link, &genpd->master_links, master_node) {
 		if (link->slave == subdomain && link->master == genpd) {
 			ret = -EINVAL;
 			goto out;
@@ -1690,6 +1775,7 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->resume_count = 0;
 	genpd->device_count = 0;
 	genpd->max_off_time_ns = -1;
+	genpd->max_off_time_changed = true;
 	genpd->domain.ops.runtime_suspend = pm_genpd_runtime_suspend;
 	genpd->domain.ops.runtime_resume = pm_genpd_runtime_resume;
 	genpd->domain.ops.runtime_idle = pm_generic_runtime_idle;
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 66a265bf5867..28dee3053f1f 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -14,6 +14,31 @@
 
 #ifdef CONFIG_PM_RUNTIME
 
+static int dev_update_qos_constraint(struct device *dev, void *data)
+{
+	s64 *constraint_ns_p = data;
+	s32 constraint_ns = -1;
+
+	if (dev->power.subsys_data && dev->power.subsys_data->domain_data)
+		constraint_ns = dev_gpd_data(dev)->td.effective_constraint_ns;
+
+	if (constraint_ns < 0) {
+		constraint_ns = dev_pm_qos_read_value(dev);
+		constraint_ns *= NSEC_PER_USEC;
+	}
+	if (constraint_ns == 0)
+		return 0;
+
+	/*
+	 * constraint_ns cannot be negative here, because the device has been
+	 * suspended.
+	 */
+	if (constraint_ns < *constraint_ns_p || *constraint_ns_p == 0)
+		*constraint_ns_p = constraint_ns;
+
+	return 0;
+}
+
 /**
  * default_stop_ok - Default PM domain governor routine for stopping devices.
  * @dev: Device to check.
@@ -21,14 +46,52 @@
 bool default_stop_ok(struct device *dev)
 {
 	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
+	unsigned long flags;
+	s64 constraint_ns;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
-	if (dev->power.max_time_suspended_ns < 0 || td->break_even_ns == 0)
-		return true;
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	if (!td->constraint_changed) {
+		bool ret = td->cached_stop_ok;
 
-	return td->stop_latency_ns + td->start_latency_ns < td->break_even_ns
-		&& td->break_even_ns < dev->power.max_time_suspended_ns;
+		spin_unlock_irqrestore(&dev->power.lock, flags);
+		return ret;
+	}
+	td->constraint_changed = false;
+	td->cached_stop_ok = false;
+	td->effective_constraint_ns = -1;
+	constraint_ns = __dev_pm_qos_read_value(dev);
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	if (constraint_ns < 0)
+		return false;
+
+	constraint_ns *= NSEC_PER_USEC;
+	/*
+	 * We can walk the children without any additional locking, because
+	 * they all have been suspended at this point and their
+	 * effective_constraint_ns fields won't be modified in parallel with us.
+	 */
+	if (!dev->power.ignore_children)
+		device_for_each_child(dev, &constraint_ns,
+				      dev_update_qos_constraint);
+
+	if (constraint_ns > 0) {
+		constraint_ns -= td->start_latency_ns;
+		if (constraint_ns == 0)
+			return false;
+	}
+	td->effective_constraint_ns = constraint_ns;
+	td->cached_stop_ok = constraint_ns > td->stop_latency_ns ||
+				constraint_ns == 0;
+	/*
+	 * The children have been suspended already, so we don't need to take
+	 * their stop latencies into account here.
+	 */
+	return td->cached_stop_ok;
 }
 
 /**
@@ -42,9 +105,27 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 	struct generic_pm_domain *genpd = pd_to_genpd(pd);
 	struct gpd_link *link;
 	struct pm_domain_data *pdd;
-	s64 min_dev_off_time_ns;
+	s64 min_off_time_ns;
 	s64 off_on_time_ns;
-	ktime_t time_now = ktime_get();
+
+	if (genpd->max_off_time_changed) {
+		struct gpd_link *link;
+
+		/*
+		 * We have to invalidate the cached results for the masters, so
+		 * use the observation that default_power_down_ok() is not
+		 * going to be called for any master until this instance
+		 * returns.
+		 */
+		list_for_each_entry(link, &genpd->slave_links, slave_node)
+			link->master->max_off_time_changed = true;
+
+		genpd->max_off_time_changed = false;
+		genpd->cached_power_down_ok = false;
+		genpd->max_off_time_ns = -1;
+	} else {
+		return genpd->cached_power_down_ok;
+	}
 
 	off_on_time_ns = genpd->power_off_latency_ns +
 				genpd->power_on_latency_ns;
@@ -61,6 +142,7 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 				to_gpd_data(pdd)->td.save_state_latency_ns;
 	}
 
+	min_off_time_ns = -1;
 	/*
 	 * Check if subdomains can be off for enough time.
 	 *
@@ -73,8 +155,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 		if (sd_max_off_ns < 0)
 			continue;
 
-		sd_max_off_ns -= ktime_to_ns(ktime_sub(time_now,
-						       sd->power_off_time));
 		/*
 		 * Check if the subdomain is allowed to be off long enough for
 		 * the current domain to turn off and on (that's how much time
@@ -82,60 +162,64 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 		 */
 		if (sd_max_off_ns <= off_on_time_ns)
 			return false;
+
+		if (min_off_time_ns > sd_max_off_ns || min_off_time_ns < 0)
+			min_off_time_ns = sd_max_off_ns;
 	}
 
 	/*
 	 * Check if the devices in the domain can be off enough time.
 	 */
-	min_dev_off_time_ns = -1;
 	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
 		struct gpd_timing_data *td;
-		struct device *dev = pdd->dev;
-		s64 dev_off_time_ns;
+		s64 constraint_ns;
 
-		if (!dev->driver || dev->power.max_time_suspended_ns < 0)
+		if (!pdd->dev->driver)
 			continue;
 
+		/*
+		 * Check if the device is allowed to be off long enough for the
+		 * domain to turn off and on (that's how much time it will
+		 * have to wait worst case).
+		 */
 		td = &to_gpd_data(pdd)->td;
-		dev_off_time_ns = dev->power.max_time_suspended_ns -
-			(td->start_latency_ns + td->restore_state_latency_ns +
-				ktime_to_ns(ktime_sub(time_now,
-						dev->power.suspend_time)));
-		if (dev_off_time_ns <= off_on_time_ns)
-			return false;
-
-		if (min_dev_off_time_ns > dev_off_time_ns
-		    || min_dev_off_time_ns < 0)
-			min_dev_off_time_ns = dev_off_time_ns;
-	}
+		constraint_ns = td->effective_constraint_ns;
+		/* default_stop_ok() need not be called before us. */
+		if (constraint_ns < 0) {
+			constraint_ns = dev_pm_qos_read_value(pdd->dev);
+			constraint_ns *= NSEC_PER_USEC;
+		}
+		if (constraint_ns == 0)
+			continue;
 
-	if (min_dev_off_time_ns < 0) {
 		/*
-		 * There are no latency constraints, so the domain can spend
-		 * arbitrary time in the "off" state.
+		 * constraint_ns cannot be negative here, because the device has
+		 * been suspended.
 		 */
-		genpd->max_off_time_ns = -1;
-		return true;
+		constraint_ns -= td->restore_state_latency_ns;
+		if (constraint_ns <= off_on_time_ns)
+			return false;
+
+		if (min_off_time_ns > constraint_ns || min_off_time_ns < 0)
+			min_off_time_ns = constraint_ns;
 	}
 
+	genpd->cached_power_down_ok = true;
+
 	/*
-	 * The difference between the computed minimum delta and the time needed
-	 * to turn the domain on is the maximum theoretical time this domain can
-	 * spend in the "off" state.
+	 * If the computed minimum device off time is negative, there are no
+	 * latency constraints, so the domain can spend arbitrary time in the
+	 * "off" state.
 	 */
-	min_dev_off_time_ns -= genpd->power_on_latency_ns;
+	if (min_off_time_ns < 0)
+		return true;
 
 	/*
-	 * If the difference between the computed minimum delta and the time
-	 * needed to turn the domain off and back on on is smaller than the
-	 * domain's power break even time, removing power from the domain is not
-	 * worth it.
+	 * The difference between the computed minimum subdomain or device off
+	 * time and the time needed to turn the domain on is the maximum
+	 * theoretical time this domain can spend in the "off" state.
 	 */
-	if (genpd->break_even_ns >
-	    min_dev_off_time_ns - genpd->power_off_latency_ns)
-		return false;
-
-	genpd->max_off_time_ns = min_dev_off_time_ns;
+	genpd->max_off_time_ns = min_off_time_ns - genpd->power_on_latency_ns;
 	return true;
 }
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index b462c0e341cb..e0fb5b0435a3 100644
--- a/drivers/base/power/main.c
+++ b/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)
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 71855570922d..fd849a2c4fa8 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -352,21 +352,26 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request);
  *
  * Will register the notifier into a notification chain that gets called
  * upon changes to the target value for the device.
+ *
+ * If the device's constraints object doesn't exist when this routine is called,
+ * it will be created (or error code will be returned if that fails).
  */
 int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier)
 {
-	int retval = 0;
+	int ret = 0;
 
 	mutex_lock(&dev_pm_qos_mtx);
 
-	/* Silently return if the constraints object is not present. */
-	if (dev->power.constraints)
-		retval = blocking_notifier_chain_register(
-				dev->power.constraints->notifiers,
-				notifier);
+	if (!dev->power.constraints)
+		ret = dev->power.power_state.event != PM_EVENT_INVALID ?
+			dev_pm_qos_constraints_allocate(dev) : -ENODEV;
+
+	if (!ret)
+		ret = blocking_notifier_chain_register(
+				dev->power.constraints->notifiers, notifier);
 
 	mutex_unlock(&dev_pm_qos_mtx);
-	return retval;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_qos_add_notifier);
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index bd0f3949bcf9..59894873a3b3 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -282,47 +282,6 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev)
 	return retval != -EACCES ? retval : -EIO;
 }
 
-struct rpm_qos_data {
-	ktime_t time_now;
-	s64 constraint_ns;
-};
-
-/**
- * rpm_update_qos_constraint - Update a given PM QoS constraint data.
- * @dev: Device whose timing data to use.
- * @data: PM QoS constraint data to update.
- *
- * Use the suspend timing data of @dev to update PM QoS constraint data pointed
- * to by @data.
- */
-static int rpm_update_qos_constraint(struct device *dev, void *data)
-{
-	struct rpm_qos_data *qos = data;
-	unsigned long flags;
-	s64 delta_ns;
-	int ret = 0;
-
-	spin_lock_irqsave(&dev->power.lock, flags);
-
-	if (dev->power.max_time_suspended_ns < 0)
-		goto out;
-
-	delta_ns = dev->power.max_time_suspended_ns -
-		ktime_to_ns(ktime_sub(qos->time_now, dev->power.suspend_time));
-	if (delta_ns <= 0) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	if (qos->constraint_ns > delta_ns || qos->constraint_ns == 0)
-		qos->constraint_ns = delta_ns;
-
- out:
-	spin_unlock_irqrestore(&dev->power.lock, flags);
-
-	return ret;
-}
-
 /**
  * rpm_suspend - Carry out runtime suspend of given device.
  * @dev: Device to suspend.
@@ -349,7 +308,6 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 {
 	int (*callback)(struct device *);
 	struct device *parent = NULL;
-	struct rpm_qos_data qos;
 	int retval;
 
 	trace_rpm_suspend(dev, rpmflags);
@@ -445,38 +403,14 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 		goto out;
 	}
 
-	qos.constraint_ns = __dev_pm_qos_read_value(dev);
-	if (qos.constraint_ns < 0) {
-		/* Negative constraint means "never suspend". */
+	if (__dev_pm_qos_read_value(dev) < 0) {
+		/* Negative PM QoS constraint means "never suspend". */
 		retval = -EPERM;
 		goto out;
 	}
-	qos.constraint_ns *= NSEC_PER_USEC;
-	qos.time_now = ktime_get();
 
 	__update_runtime_status(dev, RPM_SUSPENDING);
 
-	if (!dev->power.ignore_children) {
-		if (dev->power.irq_safe)
-			spin_unlock(&dev->power.lock);
-		else
-			spin_unlock_irq(&dev->power.lock);
-
-		retval = device_for_each_child(dev, &qos,
-					       rpm_update_qos_constraint);
-
-		if (dev->power.irq_safe)
-			spin_lock(&dev->power.lock);
-		else
-			spin_lock_irq(&dev->power.lock);
-
-		if (retval)
-			goto fail;
-	}
-
-	dev->power.suspend_time = qos.time_now;
-	dev->power.max_time_suspended_ns = qos.constraint_ns ? : -1;
-
 	if (dev->pm_domain)
 		callback = dev->pm_domain->ops.runtime_suspend;
 	else if (dev->type && dev->type->pm)
@@ -529,8 +463,6 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
  fail:
 	__update_runtime_status(dev, RPM_ACTIVE);
-	dev->power.suspend_time = ktime_set(0, 0);
-	dev->power.max_time_suspended_ns = -1;
 	dev->power.deferred_resume = false;
 	wake_up_all(&dev->power.wait_queue);
 
@@ -704,9 +636,6 @@ static int rpm_resume(struct device *dev, int rpmflags)
 	if (dev->power.no_callbacks)
 		goto no_callback;	/* Assume success. */
 
-	dev->power.suspend_time = ktime_set(0, 0);
-	dev->power.max_time_suspended_ns = -1;
-
 	__update_runtime_status(dev, RPM_RESUMING);
 
 	if (dev->pm_domain)
@@ -1369,9 +1298,6 @@ void pm_runtime_init(struct device *dev)
 	setup_timer(&dev->power.suspend_timer, pm_suspend_timer_fn,
 			(unsigned long)dev);
 
-	dev->power.suspend_time = ktime_set(0, 0);
-	dev->power.max_time_suspended_ns = -1;
-
 	init_waitqueue_head(&dev->power.wait_queue);
 }
 
@@ -1389,28 +1315,3 @@ void pm_runtime_remove(struct device *dev)
 	if (dev->power.irq_safe && dev->parent)
 		pm_runtime_put_sync(dev->parent);
 }
-
-/**
- * pm_runtime_update_max_time_suspended - Update device's suspend time data.
- * @dev: Device to handle.
- * @delta_ns: Value to subtract from the device's max_time_suspended_ns field.
- *
- * Update the device's power.max_time_suspended_ns field by subtracting
- * @delta_ns from it.  The resulting value of power.max_time_suspended_ns is
- * never negative.
- */
-void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev->power.lock, flags);
-
-	if (delta_ns > 0 && dev->power.max_time_suspended_ns > 0) {
-		if (dev->power.max_time_suspended_ns > delta_ns)
-			dev->power.max_time_suspended_ns -= delta_ns;
-		else
-			dev->power.max_time_suspended_ns = 0;
-	}
-
-	spin_unlock_irqrestore(&dev->power.lock, flags);
-}
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 95c12f6cb5b9..48be2ad4dd2c 100644
--- a/drivers/base/power/sysfs.c
+++ b/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,
 };
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 2a3e581b8dcd..cbb463b3a750 100644
--- a/drivers/base/power/wakeup.c
+++ b/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);
@@ -609,24 +650,6 @@ 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.
  *
  * Compare the current number of registered wakeup events with its preserved
@@ -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)