Better domain idle from device wakeup patterns

index 8143210a5c54..5d2ebacfd35e 100644
@@ -122,6 +122,27 @@ u64 pm_runtime_suspended_time(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_runtime_suspended_time);
 
+/**
+ * pm_runtime_set_next_wakeup_event - Notify PM framework of an impending event.
+ * @dev: Device to handle
+ * @next: impending interrupt/wakeup for the device
+ */
+int pm_runtime_set_next_event(struct device *dev, ktime_t next)
+{
+	unsigned long flags;
+	int ret = -EINVAL;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	if (ktime_before(ktime_get(), next)) {
+		dev->power.next_event = next;
+		ret = 0;
+	}
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_next_event);
+
 /**
  * pm_runtime_deactivate_timer - Deactivate given device's suspend timer.
  * @dev: Device to handle.

@@ -1415,6 +1436,9 @@ void pm_runtime_enable(struct device *dev)
 	     "Enabling runtime PM for inactive device (%s) with active children\n",
 	     dev_name(dev));
 
+	/* Reset the next wakeup for the device */
+	dev->power.next_event = KTIME_MAX;
+
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 }
 EXPORT_SYMBOL_GPL(pm_runtime_enable);

index a30a4b54df52..9051658674a4 100644
@@ -8,6 +8,7 @@
 #ifndef _LINUX_PM_H
 #define _LINUX_PM_H
 
+#include <linux/ktime.h>
 #include <linux/list.h>
 #include <linux/workqueue.h>
 #include <linux/spinlock.h>

@@ -616,6 +617,7 @@ struct dev_pm_info {
 	u64			active_time;
 	u64			suspended_time;
 	u64			accounting_timestamp;
+	ktime_t			next_event;
 #endif
 	struct pm_subsys_data	*subsys_data;  /* Owned by the subsystem. */
 	void (*set_latency_tolerance)(struct device *, s32);

index 6245caa18034..af6d35178335 100644
@@ -59,6 +59,7 @@ extern void pm_runtime_get_suppliers(struct device *dev);
 extern void pm_runtime_put_suppliers(struct device *dev);
 extern void pm_runtime_new_link(struct device *dev);
 extern void pm_runtime_drop_link(struct device *dev);
+extern int pm_runtime_set_next_event(struct device *dev, ktime_t next);
 
 /**
  * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter.

index 490ed7deb99a..2383421290f2 100644
@@ -117,6 +117,49 @@ static bool default_suspend_ok(struct device *dev)
 	return td->cached_suspend_ok;
 }
 
+static void update_domain_next_wakeup(struct generic_pm_domain *genpd, ktime_t now)
+{
+	ktime_t domain_wakeup = KTIME_MAX;
+	ktime_t next_wakeup;
+	struct pm_domain_data *pdd;
+	struct gpd_link *link;
+
+	/* Find the earliest wakeup for all devices in the domain */
+	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
+		next_wakeup = READ_ONCE(pdd->dev->power.next_event);
+		if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now))
+			if (ktime_before(next_wakeup, domain_wakeup))
+				domain_wakeup = next_wakeup;
+	}
+
+	/* Then find the earliest wakeup of from all the child domains */
+	list_for_each_entry(link, &genpd->parent_links, parent_node) {
+		next_wakeup = link->child->next_wakeup;
+		if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now))
+			if (ktime_before(next_wakeup, domain_wakeup))
+				domain_wakeup = next_wakeup;
+	}
+
+	genpd->next_wakeup = domain_wakeup;
+}
+
+static bool next_wakeup_allows_state(struct generic_pm_domain *genpd,
+				     unsigned int state, ktime_t now)
+{
+	s64 idle_time_ns, min_sleep_ns;
+	ktime_t domain_wakeup = genpd->next_wakeup;
+
+	min_sleep_ns = genpd->states[state].power_off_latency_ns +
+		       genpd->states[state].power_on_latency_ns +
+		       genpd->states[state].residency_ns;
+
+	idle_time_ns = ktime_to_ns(ktime_sub(domain_wakeup, now));
+	if (idle_time_ns < min_sleep_ns)
+		return false;
+
+	return true;
+}
+
 static bool __default_power_down_ok(struct dev_pm_domain *pd,
 				     unsigned int state)
 {

@@ -210,6 +253,33 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 {
 	struct generic_pm_domain *genpd = pd_to_genpd(pd);
 	struct gpd_link *link;
+	int state_idx;
+	ktime_t now = ktime_get();
+
+	/*
+	 * Find the next wakeup from devices that can determine their own wakeup
+	 * to find when the domain would wakeup and do it for every device down
+	 * the hierarchy. It is not worth while to sleep if the state's residency
+	 * cannot be met.
+	 */
+	update_domain_next_wakeup(genpd, now);
+	state_idx = genpd->state_count - 1;
+	if (genpd->next_wakeup != KTIME_MAX) {
+		/* Let's find out the deepest domain idle state, the devices prefer */
+		while (state_idx >= 0) {
+			if (next_wakeup_allows_state(genpd, state_idx, now)) {
+				genpd->max_off_time_changed = true;
+				break;
+			}
+			state_idx--;
+		}
+
+		if (state_idx < 0) {
+			state_idx = 0;
+			genpd->cached_power_down_ok = false;
+			goto done;
+		}
+	}
 
 	if (!genpd->max_off_time_changed) {
 		genpd->state_idx = genpd->cached_power_down_state_idx;

@@ -228,17 +298,20 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 	genpd->max_off_time_ns = -1;
 	genpd->max_off_time_changed = false;
 	genpd->cached_power_down_ok = true;
-	genpd->state_idx = genpd->state_count - 1;
 
-	/* Find a state to power down to, starting from the deepest. */
-	while (!__default_power_down_ok(pd, genpd->state_idx)) {
-		if (genpd->state_idx == 0) {
+	/* Find a state to power down to, starting from the state
+	 * determined by the next wakeup.
+	 */
+	while (!__default_power_down_ok(pd, state_idx)) {
+		if (state_idx == 0) {
 			genpd->cached_power_down_ok = false;
 			break;
 		}
-		genpd->state_idx--;
+		state_idx--;
 	}
 
+done:
+	genpd->state_idx = state_idx;
 	genpd->cached_power_down_state_idx = genpd->state_idx;
 	return genpd->cached_power_down_ok;
 }

index ee11502a575b..9ea6f666967b 100644
@@ -119,6 +119,7 @@ struct generic_pm_domain {
 				     unsigned int state);
 	struct gpd_dev_ops dev_ops;
 	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
+	ktime_t next_wakeup;
 	bool max_off_time_changed;
 	bool cached_power_down_ok;
 	bool cached_power_down_state_idx;