Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index ec5bb19..8fdd007 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -4,5 +4,6 @@
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
 obj-$(CONFIG_PM_GENERIC_DOMAINS)	+=  domain.o domain_governor.o
 obj-$(CONFIG_HAVE_CLK)	+= clock_ops.o
+obj-$(CONFIG_PM_QOS_KUNIT_TEST) += qos-test.o
 
 ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index 8db98a1..bbddb26 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -188,6 +188,26 @@
 EXPORT_SYMBOL_GPL(dev_pm_domain_detach);
 
 /**
+ * dev_pm_domain_start - Start the device through its PM domain.
+ * @dev: Device to start.
+ *
+ * This function should typically be called during probe by a subsystem/driver,
+ * when it needs to start its device from the PM domain's perspective. Note
+ * that, it's assumed that the PM domain is already powered on when this
+ * function is called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_domain_start(struct device *dev)
+{
+	if (dev->pm_domain && dev->pm_domain->start)
+		return dev->pm_domain->start(dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_start);
+
+/**
  * dev_pm_domain_set - Set PM domain of a device.
  * @dev: Device whose PM domain is to be set.
  * @pd: PM domain to be set, or NULL.
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 8428d02..7432689 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -123,7 +123,7 @@
 #define genpd_lock_interruptible(p)	p->lock_ops->lock_interruptible(p)
 #define genpd_unlock(p)			p->lock_ops->unlock(p)
 
-#define genpd_status_on(genpd)		(genpd->status == GPD_STATE_ACTIVE)
+#define genpd_status_on(genpd)		(genpd->status == GENPD_STATE_ON)
 #define genpd_is_irq_safe(genpd)	(genpd->flags & GENPD_FLAG_IRQ_SAFE)
 #define genpd_is_always_on(genpd)	(genpd->flags & GENPD_FLAG_ALWAYS_ON)
 #define genpd_is_active_wakeup(genpd)	(genpd->flags & GENPD_FLAG_ACTIVE_WAKEUP)
@@ -222,7 +222,7 @@
 	 * out of off and so update the idle time and vice
 	 * versa.
 	 */
-	if (genpd->status == GPD_STATE_ACTIVE) {
+	if (genpd->status == GENPD_STATE_ON) {
 		int state_idx = genpd->state_idx;
 
 		genpd->states[state_idx].idle_time =
@@ -263,18 +263,18 @@
 	/*
 	 * Traverse all sub-domains within the domain. This can be
 	 * done without any additional locking as the link->performance_state
-	 * field is protected by the master genpd->lock, which is already taken.
+	 * field is protected by the parent genpd->lock, which is already taken.
 	 *
 	 * Also note that link->performance_state (subdomain's performance state
-	 * requirement to master domain) is different from
-	 * link->slave->performance_state (current performance state requirement
+	 * requirement to parent domain) is different from
+	 * link->child->performance_state (current performance state requirement
 	 * of the devices/sub-domains of the subdomain) and so can have a
 	 * different value.
 	 *
 	 * Note that we also take vote from powered-off sub-domains into account
 	 * as the same is done for devices right now.
 	 */
-	list_for_each_entry(link, &genpd->master_links, master_node) {
+	list_for_each_entry(link, &genpd->parent_links, parent_node) {
 		if (link->performance_state > state)
 			state = link->performance_state;
 	}
@@ -285,40 +285,40 @@
 static int _genpd_set_performance_state(struct generic_pm_domain *genpd,
 					unsigned int state, int depth)
 {
-	struct generic_pm_domain *master;
+	struct generic_pm_domain *parent;
 	struct gpd_link *link;
-	int master_state, ret;
+	int parent_state, ret;
 
 	if (state == genpd->performance_state)
 		return 0;
 
-	/* Propagate to masters of genpd */
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		master = link->master;
+	/* Propagate to parents of genpd */
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		parent = link->parent;
 
-		if (!master->set_performance_state)
+		if (!parent->set_performance_state)
 			continue;
 
-		/* Find master's performance state */
+		/* Find parent's performance state */
 		ret = dev_pm_opp_xlate_performance_state(genpd->opp_table,
-							 master->opp_table,
+							 parent->opp_table,
 							 state);
 		if (unlikely(ret < 0))
 			goto err;
 
-		master_state = ret;
+		parent_state = ret;
 
-		genpd_lock_nested(master, depth + 1);
+		genpd_lock_nested(parent, depth + 1);
 
 		link->prev_performance_state = link->performance_state;
-		link->performance_state = master_state;
-		master_state = _genpd_reeval_performance_state(master,
-						master_state);
-		ret = _genpd_set_performance_state(master, master_state, depth + 1);
+		link->performance_state = parent_state;
+		parent_state = _genpd_reeval_performance_state(parent,
+						parent_state);
+		ret = _genpd_set_performance_state(parent, parent_state, depth + 1);
 		if (ret)
 			link->performance_state = link->prev_performance_state;
 
-		genpd_unlock(master);
+		genpd_unlock(parent);
 
 		if (ret)
 			goto err;
@@ -333,26 +333,26 @@
 
 err:
 	/* Encountered an error, lets rollback */
-	list_for_each_entry_continue_reverse(link, &genpd->slave_links,
-					     slave_node) {
-		master = link->master;
+	list_for_each_entry_continue_reverse(link, &genpd->child_links,
+					     child_node) {
+		parent = link->parent;
 
-		if (!master->set_performance_state)
+		if (!parent->set_performance_state)
 			continue;
 
-		genpd_lock_nested(master, depth + 1);
+		genpd_lock_nested(parent, depth + 1);
 
-		master_state = link->prev_performance_state;
-		link->performance_state = master_state;
+		parent_state = link->prev_performance_state;
+		link->performance_state = parent_state;
 
-		master_state = _genpd_reeval_performance_state(master,
-						master_state);
-		if (_genpd_set_performance_state(master, master_state, depth + 1)) {
+		parent_state = _genpd_reeval_performance_state(parent,
+						parent_state);
+		if (_genpd_set_performance_state(parent, parent_state, depth + 1)) {
 			pr_err("%s: Failed to roll back to %d performance state\n",
-			       master->name, master_state);
+			       parent->name, parent_state);
 		}
 
-		genpd_unlock(master);
+		genpd_unlock(parent);
 	}
 
 	return ret;
@@ -415,26 +415,45 @@
 	s64 elapsed_ns;
 	int ret;
 
-	if (!genpd->power_on)
-		return 0;
+	/* Notify consumers that we are about to power on. */
+	ret = raw_notifier_call_chain_robust(&genpd->power_notifiers,
+					     GENPD_NOTIFY_PRE_ON,
+					     GENPD_NOTIFY_OFF, NULL);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		return ret;
 
-	if (!timed)
-		return genpd->power_on(genpd);
+	if (!genpd->power_on)
+		goto out;
+
+	if (!timed) {
+		ret = genpd->power_on(genpd);
+		if (ret)
+			goto err;
+
+		goto out;
+	}
 
 	time_start = ktime_get();
 	ret = genpd->power_on(genpd);
 	if (ret)
-		return ret;
+		goto err;
 
 	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
 	if (elapsed_ns <= genpd->states[state_idx].power_on_latency_ns)
-		return ret;
+		goto out;
 
 	genpd->states[state_idx].power_on_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "on", elapsed_ns);
 
+out:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_ON, NULL);
+	return 0;
+err:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_OFF,
+				NULL);
 	return ret;
 }
 
@@ -445,27 +464,46 @@
 	s64 elapsed_ns;
 	int ret;
 
-	if (!genpd->power_off)
-		return 0;
+	/* Notify consumers that we are about to power off. */
+	ret = raw_notifier_call_chain_robust(&genpd->power_notifiers,
+					     GENPD_NOTIFY_PRE_OFF,
+					     GENPD_NOTIFY_ON, NULL);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		return ret;
 
-	if (!timed)
-		return genpd->power_off(genpd);
+	if (!genpd->power_off)
+		goto out;
+
+	if (!timed) {
+		ret = genpd->power_off(genpd);
+		if (ret)
+			goto busy;
+
+		goto out;
+	}
 
 	time_start = ktime_get();
 	ret = genpd->power_off(genpd);
 	if (ret)
-		return ret;
+		goto busy;
 
 	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
 	if (elapsed_ns <= genpd->states[state_idx].power_off_latency_ns)
-		return 0;
+		goto out;
 
 	genpd->states[state_idx].power_off_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "off", elapsed_ns);
 
+out:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_OFF,
+				NULL);
 	return 0;
+busy:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_ON, NULL);
+	return ret;
 }
 
 /**
@@ -497,6 +535,7 @@
 	struct pm_domain_data *pdd;
 	struct gpd_link *link;
 	unsigned int not_suspended = 0;
+	int ret;
 
 	/*
 	 * Do not try to power off the domain in the following situations:
@@ -544,44 +583,36 @@
 	if (!genpd->gov)
 		genpd->state_idx = 0;
 
-	if (genpd->power_off) {
-		int ret;
+	/* Don't power off, if a child domain is waiting to power on. */
+	if (atomic_read(&genpd->sd_count) > 0)
+		return -EBUSY;
 
-		if (atomic_read(&genpd->sd_count) > 0)
-			return -EBUSY;
-
-		/*
-		 * If sd_count > 0 at this point, one of the subdomains hasn't
-		 * managed to call genpd_power_on() for the master yet after
-		 * incrementing it.  In that case genpd_power_on() will wait
-		 * for us to drop the lock, so we can call .power_off() and let
-		 * the genpd_power_on() restore power for us (this shouldn't
-		 * happen very often).
-		 */
-		ret = _genpd_power_off(genpd, true);
-		if (ret)
-			return ret;
+	ret = _genpd_power_off(genpd, true);
+	if (ret) {
+		genpd->states[genpd->state_idx].rejected++;
+		return ret;
 	}
 
-	genpd->status = GPD_STATE_POWER_OFF;
+	genpd->status = GENPD_STATE_OFF;
 	genpd_update_accounting(genpd);
+	genpd->states[genpd->state_idx].usage++;
 
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		genpd_sd_counter_dec(link->master);
-		genpd_lock_nested(link->master, depth + 1);
-		genpd_power_off(link->master, false, depth + 1);
-		genpd_unlock(link->master);
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		genpd_sd_counter_dec(link->parent);
+		genpd_lock_nested(link->parent, depth + 1);
+		genpd_power_off(link->parent, false, depth + 1);
+		genpd_unlock(link->parent);
 	}
 
 	return 0;
 }
 
 /**
- * genpd_power_on - Restore power to a given PM domain and its masters.
+ * genpd_power_on - Restore power to a given PM domain and its parents.
  * @genpd: PM domain to power up.
  * @depth: nesting count for lockdep.
  *
- * Restore power to @genpd and all of its masters so that it is possible to
+ * Restore power to @genpd and all of its parents so that it is possible to
  * resume a device belonging to it.
  */
 static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
@@ -594,20 +625,20 @@
 
 	/*
 	 * The list is guaranteed not to change while the loop below is being
-	 * executed, unless one of the masters' .power_on() callbacks fiddles
+	 * executed, unless one of the parents' .power_on() callbacks fiddles
 	 * with it.
 	 */
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		struct generic_pm_domain *master = link->master;
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		struct generic_pm_domain *parent = link->parent;
 
-		genpd_sd_counter_inc(master);
+		genpd_sd_counter_inc(parent);
 
-		genpd_lock_nested(master, depth + 1);
-		ret = genpd_power_on(master, depth + 1);
-		genpd_unlock(master);
+		genpd_lock_nested(parent, depth + 1);
+		ret = genpd_power_on(parent, depth + 1);
+		genpd_unlock(parent);
 
 		if (ret) {
-			genpd_sd_counter_dec(master);
+			genpd_sd_counter_dec(parent);
 			goto err;
 		}
 	}
@@ -616,24 +647,31 @@
 	if (ret)
 		goto err;
 
-	genpd->status = GPD_STATE_ACTIVE;
+	genpd->status = GENPD_STATE_ON;
 	genpd_update_accounting(genpd);
 
 	return 0;
 
  err:
 	list_for_each_entry_continue_reverse(link,
-					&genpd->slave_links,
-					slave_node) {
-		genpd_sd_counter_dec(link->master);
-		genpd_lock_nested(link->master, depth + 1);
-		genpd_power_off(link->master, false, depth + 1);
-		genpd_unlock(link->master);
+					&genpd->child_links,
+					child_node) {
+		genpd_sd_counter_dec(link->parent);
+		genpd_lock_nested(link->parent, depth + 1);
+		genpd_power_off(link->parent, false, depth + 1);
+		genpd_unlock(link->parent);
 	}
 
 	return ret;
 }
 
+static int genpd_dev_pm_start(struct device *dev)
+{
+	struct generic_pm_domain *genpd = dev_to_genpd(dev);
+
+	return genpd_start_dev(genpd, dev);
+}
+
 static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 				     unsigned long val, void *ptr)
 {
@@ -922,34 +960,16 @@
 }
 late_initcall(genpd_power_off_unused);
 
-#if defined(CONFIG_PM_SLEEP) || defined(CONFIG_PM_GENERIC_DOMAINS_OF)
-
-static bool genpd_present(const struct generic_pm_domain *genpd)
-{
-	const struct generic_pm_domain *gpd;
-
-	if (IS_ERR_OR_NULL(genpd))
-		return false;
-
-	list_for_each_entry(gpd, &gpd_list, gpd_list_node)
-		if (gpd == genpd)
-			return true;
-
-	return false;
-}
-
-#endif
-
 #ifdef CONFIG_PM_SLEEP
 
 /**
- * genpd_sync_power_off - Synchronously power off a PM domain and its masters.
+ * genpd_sync_power_off - Synchronously power off a PM domain and its parents.
  * @genpd: PM domain to power off, if possible.
  * @use_lock: use the lock.
  * @depth: nesting count for lockdep.
  *
  * Check if the given PM domain can be powered off (during system suspend or
- * hibernation) and do that if so.  Also, in that case propagate to its masters.
+ * hibernation) and do that if so.  Also, in that case propagate to its parents.
  *
  * This function is only called in "noirq" and "syscore" stages of system power
  * transitions. The "noirq" callbacks may be executed asynchronously, thus in
@@ -972,23 +992,23 @@
 	if (_genpd_power_off(genpd, false))
 		return;
 
-	genpd->status = GPD_STATE_POWER_OFF;
+	genpd->status = GENPD_STATE_OFF;
 
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		genpd_sd_counter_dec(link->master);
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		genpd_sd_counter_dec(link->parent);
 
 		if (use_lock)
-			genpd_lock_nested(link->master, depth + 1);
+			genpd_lock_nested(link->parent, depth + 1);
 
-		genpd_sync_power_off(link->master, use_lock, depth + 1);
+		genpd_sync_power_off(link->parent, use_lock, depth + 1);
 
 		if (use_lock)
-			genpd_unlock(link->master);
+			genpd_unlock(link->parent);
 	}
 }
 
 /**
- * genpd_sync_power_on - Synchronously power on a PM domain and its masters.
+ * genpd_sync_power_on - Synchronously power on a PM domain and its parents.
  * @genpd: PM domain to power on.
  * @use_lock: use the lock.
  * @depth: nesting count for lockdep.
@@ -1005,21 +1025,20 @@
 	if (genpd_status_on(genpd))
 		return;
 
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		genpd_sd_counter_inc(link->master);
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		genpd_sd_counter_inc(link->parent);
 
 		if (use_lock)
-			genpd_lock_nested(link->master, depth + 1);
+			genpd_lock_nested(link->parent, depth + 1);
 
-		genpd_sync_power_on(link->master, use_lock, depth + 1);
+		genpd_sync_power_on(link->parent, use_lock, depth + 1);
 
 		if (use_lock)
-			genpd_unlock(link->master);
+			genpd_unlock(link->parent);
 	}
 
 	_genpd_power_on(genpd, false);
-
-	genpd->status = GPD_STATE_ACTIVE;
+	genpd->status = GENPD_STATE_ON;
 }
 
 /**
@@ -1292,13 +1311,14 @@
 	 * first time for the given domain in the present cycle.
 	 */
 	genpd_lock(genpd);
-	if (genpd->suspended_count++ == 0)
+	if (genpd->suspended_count++ == 0) {
 		/*
 		 * The boot kernel might put the domain into arbitrary state,
 		 * so make it appear as powered off to genpd_sync_power_on(),
 		 * so that it tries to power it on in case it was really off.
 		 */
-		genpd->status = GPD_STATE_POWER_OFF;
+		genpd->status = GENPD_STATE_OFF;
+	}
 
 	genpd_sync_power_on(genpd, true, 0);
 	genpd_unlock(genpd);
@@ -1354,8 +1374,8 @@
 {
 	struct generic_pm_domain *genpd;
 
-	genpd = dev_to_genpd(dev);
-	if (!genpd_present(genpd))
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
 		return;
 
 	if (suspend) {
@@ -1454,12 +1474,12 @@
 	if (!genpd_is_cpu_domain(genpd))
 		return;
 
-	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		struct generic_pm_domain *master = link->master;
+	list_for_each_entry(link, &genpd->child_links, child_node) {
+		struct generic_pm_domain *parent = link->parent;
 
-		genpd_lock_nested(master, depth + 1);
-		genpd_update_cpumask(master, cpu, set, depth + 1);
-		genpd_unlock(master);
+		genpd_lock_nested(parent, depth + 1);
+		genpd_update_cpumask(parent, cpu, set, depth + 1);
+		genpd_unlock(parent);
 	}
 
 	if (set)
@@ -1614,6 +1634,101 @@
 }
 EXPORT_SYMBOL_GPL(pm_genpd_remove_device);
 
+/**
+ * dev_pm_genpd_add_notifier - Add a genpd power on/off notifier for @dev
+ *
+ * @dev: Device that should be associated with the notifier
+ * @nb: The notifier block to register
+ *
+ * Users may call this function to add a genpd power on/off notifier for an
+ * attached @dev. Only one notifier per device is allowed. The notifier is
+ * sent when genpd is powering on/off the PM domain.
+ *
+ * It is assumed that the user guarantee that the genpd wouldn't be detached
+ * while this routine is getting called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb)
+{
+	struct generic_pm_domain *genpd;
+	struct generic_pm_domain_data *gpd_data;
+	int ret;
+
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
+		return -ENODEV;
+
+	if (WARN_ON(!dev->power.subsys_data ||
+		     !dev->power.subsys_data->domain_data))
+		return -EINVAL;
+
+	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
+	if (gpd_data->power_nb)
+		return -EEXIST;
+
+	genpd_lock(genpd);
+	ret = raw_notifier_chain_register(&genpd->power_notifiers, nb);
+	genpd_unlock(genpd);
+
+	if (ret) {
+		dev_warn(dev, "failed to add notifier for PM domain %s\n",
+			 genpd->name);
+		return ret;
+	}
+
+	gpd_data->power_nb = nb;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_add_notifier);
+
+/**
+ * dev_pm_genpd_remove_notifier - Remove a genpd power on/off notifier for @dev
+ *
+ * @dev: Device that is associated with the notifier
+ *
+ * Users may call this function to remove a genpd power on/off notifier for an
+ * attached @dev.
+ *
+ * It is assumed that the user guarantee that the genpd wouldn't be detached
+ * while this routine is getting called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_genpd_remove_notifier(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+	struct generic_pm_domain_data *gpd_data;
+	int ret;
+
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
+		return -ENODEV;
+
+	if (WARN_ON(!dev->power.subsys_data ||
+		     !dev->power.subsys_data->domain_data))
+		return -EINVAL;
+
+	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
+	if (!gpd_data->power_nb)
+		return -ENODEV;
+
+	genpd_lock(genpd);
+	ret = raw_notifier_chain_unregister(&genpd->power_notifiers,
+					    gpd_data->power_nb);
+	genpd_unlock(genpd);
+
+	if (ret) {
+		dev_warn(dev, "failed to remove notifier for PM domain %s\n",
+			 genpd->name);
+		return ret;
+	}
+
+	gpd_data->power_nb = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_remove_notifier);
+
 static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 			       struct generic_pm_domain *subdomain)
 {
@@ -1647,17 +1762,17 @@
 		goto out;
 	}
 
-	list_for_each_entry(itr, &genpd->master_links, master_node) {
-		if (itr->slave == subdomain && itr->master == genpd) {
+	list_for_each_entry(itr, &genpd->parent_links, parent_node) {
+		if (itr->child == subdomain && itr->parent == genpd) {
 			ret = -EINVAL;
 			goto out;
 		}
 	}
 
-	link->master = genpd;
-	list_add_tail(&link->master_node, &genpd->master_links);
-	link->slave = subdomain;
-	list_add_tail(&link->slave_node, &subdomain->slave_links);
+	link->parent = genpd;
+	list_add_tail(&link->parent_node, &genpd->parent_links);
+	link->child = subdomain;
+	list_add_tail(&link->child_node, &subdomain->child_links);
 	if (genpd_status_on(subdomain))
 		genpd_sd_counter_inc(genpd);
 
@@ -1671,7 +1786,7 @@
 
 /**
  * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain.
- * @genpd: Master PM domain to add the subdomain to.
+ * @genpd: Leader PM domain to add the subdomain to.
  * @subdomain: Subdomain to be added.
  */
 int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
@@ -1689,7 +1804,7 @@
 
 /**
  * pm_genpd_remove_subdomain - Remove a subdomain from an I/O PM domain.
- * @genpd: Master PM domain to remove the subdomain from.
+ * @genpd: Leader PM domain to remove the subdomain from.
  * @subdomain: Subdomain to be removed.
  */
 int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
@@ -1704,19 +1819,19 @@
 	genpd_lock(subdomain);
 	genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING);
 
-	if (!list_empty(&subdomain->master_links) || subdomain->device_count) {
+	if (!list_empty(&subdomain->parent_links) || subdomain->device_count) {
 		pr_warn("%s: unable to remove subdomain %s\n",
 			genpd->name, subdomain->name);
 		ret = -EBUSY;
 		goto out;
 	}
 
-	list_for_each_entry_safe(link, l, &genpd->master_links, master_node) {
-		if (link->slave != subdomain)
+	list_for_each_entry_safe(link, l, &genpd->parent_links, parent_node) {
+		if (link->child != subdomain)
 			continue;
 
-		list_del(&link->master_node);
-		list_del(&link->slave_node);
+		list_del(&link->parent_node);
+		list_del(&link->child_node);
 		kfree(link);
 		if (genpd_status_on(subdomain))
 			genpd_sd_counter_dec(genpd);
@@ -1781,14 +1896,15 @@
 	if (IS_ERR_OR_NULL(genpd))
 		return -EINVAL;
 
-	INIT_LIST_HEAD(&genpd->master_links);
-	INIT_LIST_HEAD(&genpd->slave_links);
+	INIT_LIST_HEAD(&genpd->parent_links);
+	INIT_LIST_HEAD(&genpd->child_links);
 	INIT_LIST_HEAD(&genpd->dev_list);
+	RAW_INIT_NOTIFIER_HEAD(&genpd->power_notifiers);
 	genpd_lock_init(genpd);
 	genpd->gov = gov;
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
 	atomic_set(&genpd->sd_count, 0);
-	genpd->status = is_off ? GPD_STATE_POWER_OFF : GPD_STATE_ACTIVE;
+	genpd->status = is_off ? GENPD_STATE_OFF : GENPD_STATE_ON;
 	genpd->device_count = 0;
 	genpd->max_off_time_ns = -1;
 	genpd->max_off_time_changed = true;
@@ -1805,6 +1921,7 @@
 	genpd->domain.ops.poweroff_noirq = genpd_poweroff_noirq;
 	genpd->domain.ops.restore_noirq = genpd_restore_noirq;
 	genpd->domain.ops.complete = genpd_complete;
+	genpd->domain.start = genpd_dev_pm_start;
 
 	if (genpd->flags & GENPD_FLAG_PM_CLK) {
 		genpd->dev_ops.stop = pm_clk_suspend;
@@ -1858,15 +1975,15 @@
 		return -EBUSY;
 	}
 
-	if (!list_empty(&genpd->master_links) || genpd->device_count) {
+	if (!list_empty(&genpd->parent_links) || genpd->device_count) {
 		genpd_unlock(genpd);
 		pr_err("%s: unable to remove %s\n", __func__, genpd->name);
 		return -EBUSY;
 	}
 
-	list_for_each_entry_safe(link, l, &genpd->slave_links, slave_node) {
-		list_del(&link->master_node);
-		list_del(&link->slave_node);
+	list_for_each_entry_safe(link, l, &genpd->child_links, child_node) {
+		list_del(&link->parent_node);
+		list_del(&link->child_node);
 		kfree(link);
 	}
 
@@ -2020,6 +2137,16 @@
 	return 0;
 }
 
+static bool genpd_present(const struct generic_pm_domain *genpd)
+{
+	const struct generic_pm_domain *gpd;
+
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node)
+		if (gpd == genpd)
+			return true;
+	return false;
+}
+
 /**
  * of_genpd_add_provider_simple() - Register a simple PM domain provider
  * @np: Device node pointer associated with the PM domain provider.
@@ -2044,8 +2171,9 @@
 	if (genpd->set_performance_state) {
 		ret = dev_pm_opp_of_add_table(&genpd->dev);
 		if (ret) {
-			dev_err(&genpd->dev, "Failed to add OPP table: %d\n",
-				ret);
+			if (ret != -EPROBE_DEFER)
+				dev_err(&genpd->dev, "Failed to add OPP table: %d\n",
+					ret);
 			goto unlock;
 		}
 
@@ -2054,7 +2182,7 @@
 		 * state.
 		 */
 		genpd->opp_table = dev_pm_opp_get_opp_table(&genpd->dev);
-		WARN_ON(!genpd->opp_table);
+		WARN_ON(IS_ERR(genpd->opp_table));
 	}
 
 	ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
@@ -2111,8 +2239,9 @@
 		if (genpd->set_performance_state) {
 			ret = dev_pm_opp_of_add_table_indexed(&genpd->dev, i);
 			if (ret) {
-				dev_err(&genpd->dev, "Failed to add OPP table for index %d: %d\n",
-					i, ret);
+				if (ret != -EPROBE_DEFER)
+					dev_err(&genpd->dev, "Failed to add OPP table for index %d: %d\n",
+						i, ret);
 				goto error;
 			}
 
@@ -2121,7 +2250,7 @@
 			 * performance state.
 			 */
 			genpd->opp_table = dev_pm_opp_get_opp_table_indexed(&genpd->dev, i);
-			WARN_ON(!genpd->opp_table);
+			WARN_ON(IS_ERR(genpd->opp_table));
 		}
 
 		genpd->provider = &np->fwnode;
@@ -2303,6 +2432,44 @@
 EXPORT_SYMBOL_GPL(of_genpd_add_subdomain);
 
 /**
+ * of_genpd_remove_subdomain - Remove a subdomain from an I/O PM domain.
+ * @parent_spec: OF phandle args to use for parent PM domain look-up
+ * @subdomain_spec: OF phandle args to use for subdomain look-up
+ *
+ * Looks-up a parent PM domain and subdomain based upon phandle args
+ * provided and removes the subdomain from the parent PM domain. Returns a
+ * negative error code on failure.
+ */
+int of_genpd_remove_subdomain(struct of_phandle_args *parent_spec,
+			      struct of_phandle_args *subdomain_spec)
+{
+	struct generic_pm_domain *parent, *subdomain;
+	int ret;
+
+	mutex_lock(&gpd_list_lock);
+
+	parent = genpd_get_from_provider(parent_spec);
+	if (IS_ERR(parent)) {
+		ret = PTR_ERR(parent);
+		goto out;
+	}
+
+	subdomain = genpd_get_from_provider(subdomain_spec);
+	if (IS_ERR(subdomain)) {
+		ret = PTR_ERR(subdomain);
+		goto out;
+	}
+
+	ret = pm_genpd_remove_subdomain(parent, subdomain);
+
+out:
+	mutex_unlock(&gpd_list_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_genpd_remove_subdomain);
+
+/**
  * of_genpd_remove_last - Remove the last PM domain registered for a provider
  * @provider: Pointer to device structure associated with provider
  *
@@ -2764,8 +2931,8 @@
 			struct generic_pm_domain *genpd)
 {
 	static const char * const status_lookup[] = {
-		[GPD_STATE_ACTIVE] = "on",
-		[GPD_STATE_POWER_OFF] = "off"
+		[GENPD_STATE_ON] = "on",
+		[GENPD_STATE_OFF] = "off"
 	};
 	struct pm_domain_data *pm_data;
 	const char *kobj_path;
@@ -2789,12 +2956,12 @@
 
 	/*
 	 * Modifications on the list require holding locks on both
-	 * master and slave, so we are safe.
+	 * parent and child, so we are safe.
 	 * Also genpd->name is immutable.
 	 */
-	list_for_each_entry(link, &genpd->master_links, master_node) {
-		seq_printf(s, "%s", link->slave->name);
-		if (!list_is_last(&link->master_node, &genpd->master_links))
+	list_for_each_entry(link, &genpd->parent_links, parent_node) {
+		seq_printf(s, "%s", link->child->name);
+		if (!list_is_last(&link->parent_node, &genpd->parent_links))
 			seq_puts(s, ", ");
 	}
 
@@ -2822,7 +2989,7 @@
 	struct generic_pm_domain *genpd;
 	int ret = 0;
 
-	seq_puts(s, "domain                          status          slaves\n");
+	seq_puts(s, "domain                          status          children\n");
 	seq_puts(s, "    /device                                             runtime status\n");
 	seq_puts(s, "----------------------------------------------------------------------\n");
 
@@ -2843,8 +3010,8 @@
 static int status_show(struct seq_file *s, void *data)
 {
 	static const char * const status_lookup[] = {
-		[GPD_STATE_ACTIVE] = "on",
-		[GPD_STATE_POWER_OFF] = "off"
+		[GENPD_STATE_ON] = "on",
+		[GENPD_STATE_OFF] = "off"
 	};
 
 	struct generic_pm_domain *genpd = s->private;
@@ -2857,7 +3024,7 @@
 	if (WARN_ON_ONCE(genpd->status >= ARRAY_SIZE(status_lookup)))
 		goto exit;
 
-	if (genpd->status == GPD_STATE_POWER_OFF)
+	if (genpd->status == GENPD_STATE_OFF)
 		seq_printf(s, "%s-%u\n", status_lookup[genpd->status],
 			genpd->state_idx);
 	else
@@ -2877,8 +3044,8 @@
 	if (ret)
 		return -ERESTARTSYS;
 
-	list_for_each_entry(link, &genpd->master_links, master_node)
-		seq_printf(s, "%s\n", link->slave->name);
+	list_for_each_entry(link, &genpd->parent_links, parent_node)
+		seq_printf(s, "%s\n", link->child->name);
 
 	genpd_unlock(genpd);
 	return ret;
@@ -2894,19 +3061,20 @@
 	if (ret)
 		return -ERESTARTSYS;
 
-	seq_puts(s, "State          Time Spent(ms)\n");
+	seq_puts(s, "State          Time Spent(ms) Usage          Rejected\n");
 
 	for (i = 0; i < genpd->state_count; i++) {
 		ktime_t delta = 0;
 		s64 msecs;
 
-		if ((genpd->status == GPD_STATE_POWER_OFF) &&
+		if ((genpd->status == GENPD_STATE_OFF) &&
 				(genpd->state_idx == i))
 			delta = ktime_sub(ktime_get(), genpd->accounting_time);
 
 		msecs = ktime_to_ms(
 			ktime_add(genpd->states[i].idle_time, delta));
-		seq_printf(s, "S%-13i %lld\n", i, msecs);
+		seq_printf(s, "S%-13i %-14lld %-14llu %llu\n", i, msecs,
+			      genpd->states[i].usage, genpd->states[i].rejected);
 	}
 
 	genpd_unlock(genpd);
@@ -2923,7 +3091,7 @@
 	if (ret)
 		return -ERESTARTSYS;
 
-	if (genpd->status == GPD_STATE_ACTIVE)
+	if (genpd->status == GENPD_STATE_ON)
 		delta = ktime_sub(ktime_get(), genpd->accounting_time);
 
 	seq_printf(s, "%lld ms\n", ktime_to_ms(
@@ -2946,7 +3114,7 @@
 
 	for (i = 0; i < genpd->state_count; i++) {
 
-		if ((genpd->status == GPD_STATE_POWER_OFF) &&
+		if ((genpd->status == GENPD_STATE_OFF) &&
 				(genpd->state_idx == i))
 			delta = ktime_sub(ktime_get(), genpd->accounting_time);
 
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index daa8c76..490ed7d 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -135,8 +135,8 @@
 	 *
 	 * All subdomains have been powered off already at this point.
 	 */
-	list_for_each_entry(link, &genpd->master_links, master_node) {
-		struct generic_pm_domain *sd = link->slave;
+	list_for_each_entry(link, &genpd->parent_links, parent_node) {
+		struct generic_pm_domain *sd = link->child;
 		s64 sd_max_off_ns = sd->max_off_time_ns;
 
 		if (sd_max_off_ns < 0)
@@ -217,13 +217,13 @@
 	}
 
 	/*
-	 * We have to invalidate the cached results for the masters, so
+	 * We have to invalidate the cached results for the parents, so
 	 * use the observation that default_power_down_ok() is not
-	 * going to be called for any master until this instance
+	 * going to be called for any parent until this instance
 	 * returns.
 	 */
-	list_for_each_entry(link, &genpd->slave_links, slave_node)
-		link->master->max_off_time_changed = true;
+	list_for_each_entry(link, &genpd->child_links, child_node)
+		link->parent->max_off_time_changed = true;
 
 	genpd->max_off_time_ns = -1;
 	genpd->max_off_time_changed = false;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 23af545..4167e2a 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -40,6 +40,10 @@
 
 typedef int (*pm_callback_t)(struct device *);
 
+#define list_for_each_entry_rcu_locked(pos, head, member) \
+	list_for_each_entry_rcu(pos, head, member, \
+			device_links_read_lock_held())
+
 /*
  * The entries in the dpm_list list are in a depth first order, simply
  * because children are guaranteed to be discovered after parents, and
@@ -266,7 +270,7 @@
 	 * callbacks freeing the link objects for the links in the list we're
 	 * walking.
 	 */
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node)
 		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
 			dpm_wait(link->supplier, async);
 
@@ -323,7 +327,7 @@
 	 * continue instead of trying to continue in parallel with its
 	 * unregistration).
 	 */
-	list_for_each_entry_rcu(link, &dev->links.consumers, s_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.consumers, s_node)
 		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
 			dpm_wait(link->consumer, async);
 
@@ -359,7 +363,6 @@
 	case PM_EVENT_THAW:
 	case PM_EVENT_RECOVER:
 		return ops->thaw;
-		break;
 	case PM_EVENT_RESTORE:
 		return ops->restore;
 #endif /* CONFIG_HIBERNATE_CALLBACKS */
@@ -515,7 +518,7 @@
 	struct dpm_watchdog *wd = from_timer(wd, t, timer);
 
 	dev_emerg(wd->dev, "**** DPM device timeout ****\n");
-	show_stack(wd->tsk, NULL);
+	show_stack(wd->tsk, NULL, KERN_EMERG);
 	panic("%s %s: unrecoverable failure\n",
 		dev_driver_string(wd->dev), dev_name(wd->dev));
 }
@@ -558,72 +561,26 @@
 /*------------------------- Resume routines -------------------------*/
 
 /**
- * suspend_event - Return a "suspend" message for given "resume" one.
- * @resume_msg: PM message representing a system-wide resume transition.
- */
-static pm_message_t suspend_event(pm_message_t resume_msg)
-{
-	switch (resume_msg.event) {
-	case PM_EVENT_RESUME:
-		return PMSG_SUSPEND;
-	case PM_EVENT_THAW:
-	case PM_EVENT_RESTORE:
-		return PMSG_FREEZE;
-	case PM_EVENT_RECOVER:
-		return PMSG_HIBERNATE;
-	}
-	return PMSG_ON;
-}
-
-/**
- * dev_pm_may_skip_resume - System-wide device resume optimization check.
+ * dev_pm_skip_resume - System-wide device resume optimization check.
  * @dev: Target device.
  *
- * Checks whether or not the device may be left in suspend after a system-wide
- * transition to the working state.
+ * Return:
+ * - %false if the transition under way is RESTORE.
+ * - Return value of dev_pm_skip_suspend() if the transition under way is THAW.
+ * - The logical negation of %power.must_resume otherwise (that is, when the
+ *   transition under way is RESUME).
  */
-bool dev_pm_may_skip_resume(struct device *dev)
+bool dev_pm_skip_resume(struct device *dev)
 {
-	return !dev->power.must_resume && pm_transition.event != PM_EVENT_RESTORE;
+	if (pm_transition.event == PM_EVENT_RESTORE)
+		return false;
+
+	if (pm_transition.event == PM_EVENT_THAW)
+		return dev_pm_skip_suspend(dev);
+
+	return !dev->power.must_resume;
 }
 
-static pm_callback_t dpm_subsys_resume_noirq_cb(struct device *dev,
-						pm_message_t state,
-						const char **info_p)
-{
-	pm_callback_t callback;
-	const char *info;
-
-	if (dev->pm_domain) {
-		info = "noirq power domain ";
-		callback = pm_noirq_op(&dev->pm_domain->ops, state);
-	} else if (dev->type && dev->type->pm) {
-		info = "noirq type ";
-		callback = pm_noirq_op(dev->type->pm, state);
-	} else if (dev->class && dev->class->pm) {
-		info = "noirq class ";
-		callback = pm_noirq_op(dev->class->pm, state);
-	} else if (dev->bus && dev->bus->pm) {
-		info = "noirq bus ";
-		callback = pm_noirq_op(dev->bus->pm, state);
-	} else {
-		return NULL;
-	}
-
-	if (info_p)
-		*info_p = info;
-
-	return callback;
-}
-
-static pm_callback_t dpm_subsys_suspend_noirq_cb(struct device *dev,
-						 pm_message_t state,
-						 const char **info_p);
-
-static pm_callback_t dpm_subsys_suspend_late_cb(struct device *dev,
-						pm_message_t state,
-						const char **info_p);
-
 /**
  * device_resume_noirq - Execute a "noirq resume" callback for given device.
  * @dev: Device to handle.
@@ -635,8 +592,8 @@
  */
 static int device_resume_noirq(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback;
-	const char *info;
+	pm_callback_t callback = NULL;
+	const char *info = NULL;
 	bool skip_resume;
 	int error = 0;
 
@@ -652,37 +609,41 @@
 	if (!dpm_wait_for_superior(dev, async))
 		goto Out;
 
-	skip_resume = dev_pm_may_skip_resume(dev);
+	skip_resume = dev_pm_skip_resume(dev);
+	/*
+	 * If the driver callback is skipped below or by the middle layer
+	 * callback and device_resume_early() also skips the driver callback for
+	 * this device later, it needs to appear as "suspended" to PM-runtime,
+	 * so change its status accordingly.
+	 *
+	 * Otherwise, the device is going to be resumed, so set its PM-runtime
+	 * status to "active", but do that only if DPM_FLAG_SMART_SUSPEND is set
+	 * to avoid confusing drivers that don't use it.
+	 */
+	if (skip_resume)
+		pm_runtime_set_suspended(dev);
+	else if (dev_pm_skip_suspend(dev))
+		pm_runtime_set_active(dev);
 
-	callback = dpm_subsys_resume_noirq_cb(dev, state, &info);
+	if (dev->pm_domain) {
+		info = "noirq power domain ";
+		callback = pm_noirq_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "noirq type ";
+		callback = pm_noirq_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "noirq class ";
+		callback = pm_noirq_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "noirq bus ";
+		callback = pm_noirq_op(dev->bus->pm, state);
+	}
 	if (callback)
 		goto Run;
 
 	if (skip_resume)
 		goto Skip;
 
-	if (dev_pm_smart_suspend_and_suspended(dev)) {
-		pm_message_t suspend_msg = suspend_event(state);
-
-		/*
-		 * If "freeze" callbacks have been skipped during a transition
-		 * related to hibernation, the subsequent "thaw" callbacks must
-		 * be skipped too or bad things may happen.  Otherwise, resume
-		 * callbacks are going to be run for the device, so its runtime
-		 * PM status must be changed to reflect the new state after the
-		 * transition under way.
-		 */
-		if (!dpm_subsys_suspend_late_cb(dev, suspend_msg, NULL) &&
-		    !dpm_subsys_suspend_noirq_cb(dev, suspend_msg, NULL)) {
-			if (state.event == PM_EVENT_THAW) {
-				skip_resume = true;
-				goto Skip;
-			} else {
-				pm_runtime_set_active(dev);
-			}
-		}
-	}
-
 	if (dev->driver && dev->driver->pm) {
 		info = "noirq driver ";
 		callback = pm_noirq_op(dev->driver->pm, state);
@@ -694,20 +655,6 @@
 Skip:
 	dev->power.is_noirq_suspended = false;
 
-	if (skip_resume) {
-		/* Make the next phases of resume skip the device. */
-		dev->power.is_late_suspended = false;
-		dev->power.is_suspended = false;
-		/*
-		 * The device is going to be left in suspend, but it might not
-		 * have been in runtime suspend before the system suspended, so
-		 * its runtime PM status needs to be updated to avoid confusing
-		 * the runtime PM framework when runtime PM is enabled for the
-		 * device again.
-		 */
-		pm_runtime_set_suspended(dev);
-	}
-
 Out:
 	complete_all(&dev->power.completion);
 	TRACE_RESUME(error);
@@ -806,35 +753,6 @@
 	cpuidle_resume();
 }
 
-static pm_callback_t dpm_subsys_resume_early_cb(struct device *dev,
-						pm_message_t state,
-						const char **info_p)
-{
-	pm_callback_t callback;
-	const char *info;
-
-	if (dev->pm_domain) {
-		info = "early power domain ";
-		callback = pm_late_early_op(&dev->pm_domain->ops, state);
-	} else if (dev->type && dev->type->pm) {
-		info = "early type ";
-		callback = pm_late_early_op(dev->type->pm, state);
-	} else if (dev->class && dev->class->pm) {
-		info = "early class ";
-		callback = pm_late_early_op(dev->class->pm, state);
-	} else if (dev->bus && dev->bus->pm) {
-		info = "early bus ";
-		callback = pm_late_early_op(dev->bus->pm, state);
-	} else {
-		return NULL;
-	}
-
-	if (info_p)
-		*info_p = info;
-
-	return callback;
-}
-
 /**
  * device_resume_early - Execute an "early resume" callback for given device.
  * @dev: Device to handle.
@@ -845,8 +763,8 @@
  */
 static int device_resume_early(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback;
-	const char *info;
+	pm_callback_t callback = NULL;
+	const char *info = NULL;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -861,17 +779,37 @@
 	if (!dpm_wait_for_superior(dev, async))
 		goto Out;
 
-	callback = dpm_subsys_resume_early_cb(dev, state, &info);
+	if (dev->pm_domain) {
+		info = "early power domain ";
+		callback = pm_late_early_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "early type ";
+		callback = pm_late_early_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "early class ";
+		callback = pm_late_early_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "early bus ";
+		callback = pm_late_early_op(dev->bus->pm, state);
+	}
+	if (callback)
+		goto Run;
 
-	if (!callback && dev->driver && dev->driver->pm) {
+	if (dev_pm_skip_resume(dev))
+		goto Skip;
+
+	if (dev->driver && dev->driver->pm) {
 		info = "early driver ";
 		callback = pm_late_early_op(dev->driver->pm, state);
 	}
 
+Run:
 	error = dpm_run_callback(callback, dev, state, info);
+
+Skip:
 	dev->power.is_late_suspended = false;
 
- Out:
+Out:
 	TRACE_RESUME(error);
 
 	pm_runtime_enable(dev);
@@ -1115,7 +1053,7 @@
 	const char *info = NULL;
 
 	if (dev->power.syscore)
-		return;
+		goto out;
 
 	device_lock(dev);
 
@@ -1145,6 +1083,7 @@
 
 	device_unlock(dev);
 
+out:
 	pm_runtime_put(dev);
 }
 
@@ -1235,67 +1174,12 @@
 
 	idx = device_links_read_lock();
 
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node)
 		link->supplier->power.must_resume = true;
 
 	device_links_read_unlock(idx);
 }
 
-static pm_callback_t dpm_subsys_suspend_noirq_cb(struct device *dev,
-						 pm_message_t state,
-						 const char **info_p)
-{
-	pm_callback_t callback;
-	const char *info;
-
-	if (dev->pm_domain) {
-		info = "noirq power domain ";
-		callback = pm_noirq_op(&dev->pm_domain->ops, state);
-	} else if (dev->type && dev->type->pm) {
-		info = "noirq type ";
-		callback = pm_noirq_op(dev->type->pm, state);
-	} else if (dev->class && dev->class->pm) {
-		info = "noirq class ";
-		callback = pm_noirq_op(dev->class->pm, state);
-	} else if (dev->bus && dev->bus->pm) {
-		info = "noirq bus ";
-		callback = pm_noirq_op(dev->bus->pm, state);
-	} else {
-		return NULL;
-	}
-
-	if (info_p)
-		*info_p = info;
-
-	return callback;
-}
-
-static bool device_must_resume(struct device *dev, pm_message_t state,
-			       bool no_subsys_suspend_noirq)
-{
-	pm_message_t resume_msg = resume_event(state);
-
-	/*
-	 * If all of the device driver's "noirq", "late" and "early" callbacks
-	 * are invoked directly by the core, the decision to allow the device to
-	 * stay in suspend can be based on its current runtime PM status and its
-	 * wakeup settings.
-	 */
-	if (no_subsys_suspend_noirq &&
-	    !dpm_subsys_suspend_late_cb(dev, state, NULL) &&
-	    !dpm_subsys_resume_early_cb(dev, resume_msg, NULL) &&
-	    !dpm_subsys_resume_noirq_cb(dev, resume_msg, NULL))
-		return !pm_runtime_status_suspended(dev) &&
-			(resume_msg.event != PM_EVENT_RESUME ||
-			 (device_can_wakeup(dev) && !device_may_wakeup(dev)));
-
-	/*
-	 * The only safe strategy here is to require that if the device may not
-	 * be left in suspend, resume callbacks must be invoked for it.
-	 */
-	return !dev->power.may_skip_resume;
-}
-
 /**
  * __device_suspend_noirq - Execute a "noirq suspend" callback for given device.
  * @dev: Device to handle.
@@ -1307,9 +1191,8 @@
  */
 static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback;
-	const char *info;
-	bool no_subsys_cb = false;
+	pm_callback_t callback = NULL;
+	const char *info = NULL;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -1323,13 +1206,23 @@
 	if (dev->power.syscore || dev->power.direct_complete)
 		goto Complete;
 
-	callback = dpm_subsys_suspend_noirq_cb(dev, state, &info);
+	if (dev->pm_domain) {
+		info = "noirq power domain ";
+		callback = pm_noirq_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "noirq type ";
+		callback = pm_noirq_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "noirq class ";
+		callback = pm_noirq_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "noirq bus ";
+		callback = pm_noirq_op(dev->bus->pm, state);
+	}
 	if (callback)
 		goto Run;
 
-	no_subsys_cb = !dpm_subsys_suspend_late_cb(dev, state, NULL);
-
-	if (dev_pm_smart_suspend_and_suspended(dev) && no_subsys_cb)
+	if (dev_pm_skip_suspend(dev))
 		goto Skip;
 
 	if (dev->driver && dev->driver->pm) {
@@ -1347,13 +1240,16 @@
 Skip:
 	dev->power.is_noirq_suspended = true;
 
-	if (dev_pm_test_driver_flags(dev, DPM_FLAG_LEAVE_SUSPENDED)) {
-		dev->power.must_resume = dev->power.must_resume ||
-				atomic_read(&dev->power.usage_count) > 1 ||
-				device_must_resume(dev, state, no_subsys_cb);
-	} else {
+	/*
+	 * Skipping the resume of devices that were in use right before the
+	 * system suspend (as indicated by their PM-runtime usage counters)
+	 * would be suboptimal.  Also resume them if doing that is not allowed
+	 * to be skipped.
+	 */
+	if (atomic_read(&dev->power.usage_count) > 1 ||
+	    !(dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME) &&
+	      dev->power.may_skip_resume))
 		dev->power.must_resume = true;
-	}
 
 	if (dev->power.must_resume)
 		dpm_superior_set_must_resume(dev);
@@ -1470,35 +1366,6 @@
 	spin_unlock_irq(&parent->power.lock);
 }
 
-static pm_callback_t dpm_subsys_suspend_late_cb(struct device *dev,
-						pm_message_t state,
-						const char **info_p)
-{
-	pm_callback_t callback;
-	const char *info;
-
-	if (dev->pm_domain) {
-		info = "late power domain ";
-		callback = pm_late_early_op(&dev->pm_domain->ops, state);
-	} else if (dev->type && dev->type->pm) {
-		info = "late type ";
-		callback = pm_late_early_op(dev->type->pm, state);
-	} else if (dev->class && dev->class->pm) {
-		info = "late class ";
-		callback = pm_late_early_op(dev->class->pm, state);
-	} else if (dev->bus && dev->bus->pm) {
-		info = "late bus ";
-		callback = pm_late_early_op(dev->bus->pm, state);
-	} else {
-		return NULL;
-	}
-
-	if (info_p)
-		*info_p = info;
-
-	return callback;
-}
-
 /**
  * __device_suspend_late - Execute a "late suspend" callback for given device.
  * @dev: Device to handle.
@@ -1509,8 +1376,8 @@
  */
 static int __device_suspend_late(struct device *dev, pm_message_t state, bool async)
 {
-	pm_callback_t callback;
-	const char *info;
+	pm_callback_t callback = NULL;
+	const char *info = NULL;
 	int error = 0;
 
 	TRACE_DEVICE(dev);
@@ -1531,12 +1398,23 @@
 	if (dev->power.syscore || dev->power.direct_complete)
 		goto Complete;
 
-	callback = dpm_subsys_suspend_late_cb(dev, state, &info);
+	if (dev->pm_domain) {
+		info = "late power domain ";
+		callback = pm_late_early_op(&dev->pm_domain->ops, state);
+	} else if (dev->type && dev->type->pm) {
+		info = "late type ";
+		callback = pm_late_early_op(dev->type->pm, state);
+	} else if (dev->class && dev->class->pm) {
+		info = "late class ";
+		callback = pm_late_early_op(dev->class->pm, state);
+	} else if (dev->bus && dev->bus->pm) {
+		info = "late bus ";
+		callback = pm_late_early_op(dev->bus->pm, state);
+	}
 	if (callback)
 		goto Run;
 
-	if (dev_pm_smart_suspend_and_suspended(dev) &&
-	    !dpm_subsys_suspend_noirq_cb(dev, state, NULL))
+	if (dev_pm_skip_suspend(dev))
 		goto Skip;
 
 	if (dev->driver && dev->driver->pm) {
@@ -1695,7 +1573,7 @@
 
 	idx = device_links_read_lock();
 
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) {
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) {
 		spin_lock_irq(&link->supplier->power.lock);
 		link->supplier->power.direct_complete = false;
 		spin_unlock_irq(&link->supplier->power.lock);
@@ -1766,8 +1644,8 @@
 		dev->power.direct_complete = false;
 	}
 
-	dev->power.may_skip_resume = false;
-	dev->power.must_resume = false;
+	dev->power.may_skip_resume = true;
+	dev->power.must_resume = !dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME);
 
 	dpm_watchdog_set(&wd, dev);
 	device_lock(dev);
@@ -1919,13 +1797,6 @@
 	int (*callback)(struct device *) = NULL;
 	int ret = 0;
 
-	if (dev->power.syscore)
-		return 0;
-
-	WARN_ON(!pm_runtime_enabled(dev) &&
-		dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND |
-					      DPM_FLAG_LEAVE_SUSPENDED));
-
 	/*
 	 * If a device's parent goes into runtime suspend at the wrong time,
 	 * it won't be possible to resume the device.  To prevent this we
@@ -1934,6 +1805,9 @@
 	 */
 	pm_runtime_get_noresume(dev);
 
+	if (dev->power.syscore)
+		return 0;
+
 	device_lock(dev);
 
 	dev->power.wakeup_path = false;
@@ -1973,9 +1847,8 @@
 	 */
 	spin_lock_irq(&dev->power.lock);
 	dev->power.direct_complete = state.event == PM_EVENT_SUSPEND &&
-		((pm_runtime_suspended(dev) && ret > 0) ||
-		 dev->power.no_pm_callbacks) &&
-		!dev_pm_test_driver_flags(dev, DPM_FLAG_NEVER_SKIP);
+		(ret > 0 || dev->power.no_pm_callbacks) &&
+		!dev_pm_test_driver_flags(dev, DPM_FLAG_NO_DIRECT_COMPLETE);
 	spin_unlock_irq(&dev->power.lock);
 	return 0;
 }
@@ -2133,7 +2006,7 @@
 	spin_unlock_irq(&dev->power.lock);
 }
 
-bool dev_pm_smart_suspend_and_suspended(struct device *dev)
+bool dev_pm_skip_suspend(struct device *dev)
 {
 	return dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) &&
 		pm_runtime_status_suspended(dev);
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 39a06a0..54292cd 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -74,6 +74,7 @@
 extern void pm_qos_sysfs_remove_flags(struct device *dev);
 extern int pm_qos_sysfs_add_latency_tolerance(struct device *dev);
 extern void pm_qos_sysfs_remove_latency_tolerance(struct device *dev);
+extern int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid);
 
 #else /* CONFIG_PM */
 
@@ -88,6 +89,8 @@
 
 static inline int dpm_sysfs_add(struct device *dev) { return 0; }
 static inline void dpm_sysfs_remove(struct device *dev) {}
+static inline int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid,
+					 kgid_t kgid) { return 0; }
 
 #endif
 
@@ -117,6 +120,13 @@
 	return dev->power.in_dpm_list;
 }
 
+/* drivers/base/power/wakeup_stats.c */
+extern int wakeup_source_sysfs_add(struct device *parent,
+				   struct wakeup_source *ws);
+extern void wakeup_source_sysfs_remove(struct wakeup_source *ws);
+
+extern int pm_wakeup_source_sysfs_add(struct device *parent);
+
 #else /* !CONFIG_PM_SLEEP */
 
 static inline void device_pm_sleep_init(struct device *dev) {}
@@ -141,6 +151,11 @@
 	return device_is_registered(dev);
 }
 
+static inline int pm_wakeup_source_sysfs_add(struct device *parent)
+{
+	return 0;
+}
+
 #endif /* !CONFIG_PM_SLEEP */
 
 static inline void device_pm_init(struct device *dev)
@@ -149,21 +164,3 @@
 	device_pm_sleep_init(dev);
 	pm_runtime_init(dev);
 }
-
-#ifdef CONFIG_PM_SLEEP
-
-/* drivers/base/power/wakeup_stats.c */
-extern int wakeup_source_sysfs_add(struct device *parent,
-				   struct wakeup_source *ws);
-extern void wakeup_source_sysfs_remove(struct wakeup_source *ws);
-
-extern int pm_wakeup_source_sysfs_add(struct device *parent);
-
-#else /* !CONFIG_PM_SLEEP */
-
-static inline int pm_wakeup_source_sysfs_add(struct device *parent)
-{
-	return 0;
-}
-
-#endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/base/power/qos-test.c b/drivers/base/power/qos-test.c
new file mode 100644
index 0000000..79fc6c4
--- /dev/null
+++ b/drivers/base/power/qos-test.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 NXP
+ */
+#include <kunit/test.h>
+#include <linux/pm_qos.h>
+
+/* Basic test for aggregating two "min" requests */
+static void freq_qos_test_min(struct kunit *test)
+{
+	struct freq_constraints	qos;
+	struct freq_qos_request	req1, req2;
+	int ret;
+
+	freq_constraints_init(&qos);
+	memset(&req1, 0, sizeof(req1));
+	memset(&req2, 0, sizeof(req2));
+
+	ret = freq_qos_add_request(&qos, &req1, FREQ_QOS_MIN, 1000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	ret = freq_qos_add_request(&qos, &req2, FREQ_QOS_MIN, 2000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 2000);
+
+	ret = freq_qos_remove_request(&req2);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 1000);
+
+	ret = freq_qos_remove_request(&req1);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN),
+			FREQ_QOS_MIN_DEFAULT_VALUE);
+}
+
+/* Test that requests for MAX_DEFAULT_VALUE have no effect */
+static void freq_qos_test_maxdef(struct kunit *test)
+{
+	struct freq_constraints	qos;
+	struct freq_qos_request	req1, req2;
+	int ret;
+
+	freq_constraints_init(&qos);
+	memset(&req1, 0, sizeof(req1));
+	memset(&req2, 0, sizeof(req2));
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX),
+			FREQ_QOS_MAX_DEFAULT_VALUE);
+
+	ret = freq_qos_add_request(&qos, &req1, FREQ_QOS_MAX,
+			FREQ_QOS_MAX_DEFAULT_VALUE);
+	KUNIT_EXPECT_EQ(test, ret, 0);
+	ret = freq_qos_add_request(&qos, &req2, FREQ_QOS_MAX,
+			FREQ_QOS_MAX_DEFAULT_VALUE);
+	KUNIT_EXPECT_EQ(test, ret, 0);
+
+	/* Add max 1000 */
+	ret = freq_qos_update_request(&req1, 1000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 1000);
+
+	/* Add max 2000, no impact */
+	ret = freq_qos_update_request(&req2, 2000);
+	KUNIT_EXPECT_EQ(test, ret, 0);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 1000);
+
+	/* Remove max 1000, new max 2000 */
+	ret = freq_qos_remove_request(&req1);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 2000);
+}
+
+/*
+ * Test that a freq_qos_request can be added again after removal
+ *
+ * This issue was solved by commit 05ff1ba412fd ("PM: QoS: Invalidate frequency
+ * QoS requests after removal")
+ */
+static void freq_qos_test_readd(struct kunit *test)
+{
+	struct freq_constraints	qos;
+	struct freq_qos_request	req;
+	int ret;
+
+	freq_constraints_init(&qos);
+	memset(&req, 0, sizeof(req));
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN),
+			FREQ_QOS_MIN_DEFAULT_VALUE);
+
+	/* Add */
+	ret = freq_qos_add_request(&qos, &req, FREQ_QOS_MIN, 1000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 1000);
+
+	/* Remove */
+	ret = freq_qos_remove_request(&req);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN),
+			FREQ_QOS_MIN_DEFAULT_VALUE);
+
+	/* Add again */
+	ret = freq_qos_add_request(&qos, &req, FREQ_QOS_MIN, 2000);
+	KUNIT_EXPECT_EQ(test, ret, 1);
+	KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 2000);
+}
+
+static struct kunit_case pm_qos_test_cases[] = {
+	KUNIT_CASE(freq_qos_test_min),
+	KUNIT_CASE(freq_qos_test_maxdef),
+	KUNIT_CASE(freq_qos_test_readd),
+	{},
+};
+
+static struct kunit_suite pm_qos_test_module = {
+	.name = "qos-kunit-test",
+	.test_cases = pm_qos_test_cases,
+};
+kunit_test_suites(&pm_qos_test_module);
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 350dcaf..8e93167 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -115,10 +115,20 @@
 
 	spin_lock_irqsave(&dev->power.lock, flags);
 
-	if (type == DEV_PM_QOS_RESUME_LATENCY) {
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
 		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT
 			: pm_qos_read_value(&qos->resume_latency);
-	} else {
+		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE
+			: freq_qos_read_value(&qos->freq, FREQ_QOS_MIN);
+		break;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE
+			: freq_qos_read_value(&qos->freq, FREQ_QOS_MAX);
+		break;
+	default:
 		WARN_ON(1);
 		ret = 0;
 	}
@@ -159,6 +169,10 @@
 			req->dev->power.set_latency_tolerance(req->dev, value);
 		}
 		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = freq_qos_apply(&req->data.freq, action, value);
+		break;
 	case DEV_PM_QOS_FLAGS:
 		ret = pm_qos_update_flags(&qos->flags, &req->data.flr,
 					  action, value);
@@ -209,6 +223,8 @@
 	c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
 	c->type = PM_QOS_MIN;
 
+	freq_constraints_init(&qos->freq);
+
 	INIT_LIST_HEAD(&qos->flags.list);
 
 	spin_lock_irq(&dev->power.lock);
@@ -269,6 +285,20 @@
 		memset(req, 0, sizeof(*req));
 	}
 
+	c = &qos->freq.min_freq;
+	plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) {
+		apply_constraint(req, PM_QOS_REMOVE_REQ,
+				 PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
+
+	c = &qos->freq.max_freq;
+	plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) {
+		apply_constraint(req, PM_QOS_REMOVE_REQ,
+				 PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
+
 	f = &qos->flags;
 	list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) {
 		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
@@ -314,11 +344,22 @@
 		ret = dev_pm_qos_constraints_allocate(dev);
 
 	trace_dev_pm_qos_add_request(dev_name(dev), type, value);
-	if (!ret) {
-		req->dev = dev;
-		req->type = type;
+	if (ret)
+		return ret;
+
+	req->dev = dev;
+	req->type = type;
+	if (req->type == DEV_PM_QOS_MIN_FREQUENCY)
+		ret = freq_qos_add_request(&dev->power.qos->freq,
+					   &req->data.freq,
+					   FREQ_QOS_MIN, value);
+	else if (req->type == DEV_PM_QOS_MAX_FREQUENCY)
+		ret = freq_qos_add_request(&dev->power.qos->freq,
+					   &req->data.freq,
+					   FREQ_QOS_MAX, value);
+	else
 		ret = apply_constraint(req, PM_QOS_ADD_REQ, value);
-	}
+
 	return ret;
 }
 
@@ -382,6 +423,10 @@
 	case DEV_PM_QOS_LATENCY_TOLERANCE:
 		curr_value = req->data.pnode.prio;
 		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		curr_value = req->data.freq.pnode.prio;
+		break;
 	case DEV_PM_QOS_FLAGS:
 		curr_value = req->data.flr.flags;
 		break;
@@ -507,6 +552,14 @@
 		ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers,
 						       notifier);
 		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		ret = freq_qos_add_notifier(&dev->power.qos->freq,
+					    FREQ_QOS_MIN, notifier);
+		break;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = freq_qos_add_notifier(&dev->power.qos->freq,
+					    FREQ_QOS_MAX, notifier);
+		break;
 	default:
 		WARN_ON(1);
 		ret = -EINVAL;
@@ -546,6 +599,14 @@
 		ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers,
 							 notifier);
 		break;
+	case DEV_PM_QOS_MIN_FREQUENCY:
+		ret = freq_qos_remove_notifier(&dev->power.qos->freq,
+					       FREQ_QOS_MIN, notifier);
+		break;
+	case DEV_PM_QOS_MAX_FREQUENCY:
+		ret = freq_qos_remove_notifier(&dev->power.qos->freq,
+					       FREQ_QOS_MAX, notifier);
+		break;
 	default:
 		WARN_ON(1);
 		ret = -EINVAL;
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 8fbd376..1573319 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -305,19 +305,40 @@
 	return 0;
 }
 
+/**
+ * pm_runtime_release_supplier - Drop references to device link's supplier.
+ * @link: Target device link.
+ * @check_idle: Whether or not to check if the supplier device is idle.
+ *
+ * Drop all runtime PM references associated with @link to its supplier device
+ * and if @check_idle is set, check if that device is idle (and so it can be
+ * suspended).
+ */
+void pm_runtime_release_supplier(struct device_link *link, bool check_idle)
+{
+	struct device *supplier = link->supplier;
+
+	/*
+	 * The additional power.usage_count check is a safety net in case
+	 * the rpm_active refcount becomes saturated, in which case
+	 * refcount_dec_not_one() would return true forever, but it is not
+	 * strictly necessary.
+	 */
+	while (refcount_dec_not_one(&link->rpm_active) &&
+	       atomic_read(&supplier->power.usage_count) > 0)
+		pm_runtime_put_noidle(supplier);
+
+	if (check_idle)
+		pm_request_idle(supplier);
+}
+
 static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend)
 {
 	struct device_link *link;
 
 	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
-				device_links_read_lock_held()) {
-
-		while (refcount_dec_not_one(&link->rpm_active))
-			pm_runtime_put_noidle(link->supplier);
-
-		if (try_to_suspend)
-			pm_request_idle(link->supplier);
-	}
+				device_links_read_lock_held())
+		pm_runtime_release_supplier(link, try_to_suspend);
 }
 
 static void rpm_put_suppliers(struct device *dev)
@@ -542,13 +563,11 @@
 
  repeat:
 	retval = rpm_check_suspend_allowed(dev);
-
 	if (retval < 0)
-		;	/* Conditions are wrong. */
+		goto out;	/* Conditions are wrong. */
 
 	/* Synchronous suspends are not allowed in the RPM_RESUMING state. */
-	else if (dev->power.runtime_status == RPM_RESUMING &&
-	    !(rpmflags & RPM_ASYNC))
+	if (dev->power.runtime_status == RPM_RESUMING && !(rpmflags & RPM_ASYNC))
 		retval = -EAGAIN;
 	if (retval)
 		goto out;
@@ -1036,8 +1055,10 @@
 	int retval;
 
 	if (rpmflags & RPM_GET_PUT) {
-		if (!atomic_dec_and_test(&dev->power.usage_count))
+		if (!atomic_dec_and_test(&dev->power.usage_count)) {
+			trace_rpm_usage_rcuidle(dev, rpmflags);
 			return 0;
+		}
 	}
 
 	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
@@ -1068,8 +1089,10 @@
 	int retval;
 
 	if (rpmflags & RPM_GET_PUT) {
-		if (!atomic_dec_and_test(&dev->power.usage_count))
+		if (!atomic_dec_and_test(&dev->power.usage_count)) {
+			trace_rpm_usage_rcuidle(dev, rpmflags);
 			return 0;
+		}
 	}
 
 	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
@@ -1113,28 +1136,49 @@
 EXPORT_SYMBOL_GPL(__pm_runtime_resume);
 
 /**
- * pm_runtime_get_if_in_use - Conditionally bump up the device's usage counter.
+ * pm_runtime_get_if_active - Conditionally bump up device usage counter.
  * @dev: Device to handle.
+ * @ign_usage_count: Whether or not to look at the current usage counter value.
  *
- * Return -EINVAL if runtime PM is disabled for the device.
+ * Return -EINVAL if runtime PM is disabled for @dev.
  *
- * If that's not the case and if the device's runtime PM status is RPM_ACTIVE
- * and the runtime PM usage counter is nonzero, increment the counter and
- * return 1.  Otherwise return 0 without changing the counter.
+ * Otherwise, if the runtime PM status of @dev is %RPM_ACTIVE and either
+ * @ign_usage_count is %true or the runtime PM usage counter of @dev is not
+ * zero, increment the usage counter of @dev and return 1. Otherwise, return 0
+ * without changing the usage counter.
+ *
+ * If @ign_usage_count is %true, this function can be used to prevent suspending
+ * the device when its runtime PM status is %RPM_ACTIVE.
+ *
+ * If @ign_usage_count is %false, this function can be used to prevent
+ * suspending the device when both its runtime PM status is %RPM_ACTIVE and its
+ * runtime PM usage counter is not zero.
+ *
+ * The caller is resposible for decrementing the runtime PM usage counter of
+ * @dev after this function has returned a positive value for it.
  */
-int pm_runtime_get_if_in_use(struct device *dev)
+int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count)
 {
 	unsigned long flags;
 	int retval;
 
 	spin_lock_irqsave(&dev->power.lock, flags);
-	retval = dev->power.disable_depth > 0 ? -EINVAL :
-		dev->power.runtime_status == RPM_ACTIVE
-			&& atomic_inc_not_zero(&dev->power.usage_count);
+	if (dev->power.disable_depth > 0) {
+		retval = -EINVAL;
+	} else if (dev->power.runtime_status != RPM_ACTIVE) {
+		retval = 0;
+	} else if (ign_usage_count) {
+		retval = 1;
+		atomic_inc(&dev->power.usage_count);
+	} else {
+		retval = atomic_inc_not_zero(&dev->power.usage_count);
+	}
+	trace_rpm_usage_rcuidle(dev, 0);
 	spin_unlock_irqrestore(&dev->power.lock, flags);
+
 	return retval;
 }
-EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use);
+EXPORT_SYMBOL_GPL(pm_runtime_get_if_active);
 
 /**
  * __pm_runtime_set_status - Set runtime PM status of a device.
@@ -1464,6 +1508,8 @@
 	dev->power.runtime_auto = true;
 	if (atomic_dec_and_test(&dev->power.usage_count))
 		rpm_idle(dev, RPM_AUTO | RPM_ASYNC);
+	else
+		trace_rpm_usage_rcuidle(dev, RPM_AUTO | RPM_ASYNC);
 
  out:
 	spin_unlock_irq(&dev->power.lock);
@@ -1531,6 +1577,8 @@
 		if (!old_use || old_delay >= 0) {
 			atomic_inc(&dev->power.usage_count);
 			rpm_resume(dev, 0);
+		} else {
+			trace_rpm_usage_rcuidle(dev, 0);
 		}
 	}
 
@@ -1728,9 +1776,7 @@
 		return;
 
 	pm_runtime_drop_link_count(link->consumer);
-
-	while (refcount_dec_not_one(&link->rpm_active))
-		pm_runtime_put(link->supplier);
+	pm_runtime_release_supplier(link, true);
 }
 
 static bool pm_runtime_need_not_resume(struct device *dev)
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index d7d82db..a1474fb 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* sysfs entries for device PM */
 #include <linux/device.h>
+#include <linux/kobject.h>
 #include <linux/string.h>
 #include <linux/export.h>
 #include <linux/pm_qos.h>
@@ -100,8 +101,8 @@
 static ssize_t control_show(struct device *dev, struct device_attribute *attr,
 			    char *buf)
 {
-	return sprintf(buf, "%s\n",
-				dev->power.runtime_auto ? ctrl_auto : ctrl_on);
+	return sysfs_emit(buf, "%s\n",
+			  dev->power.runtime_auto ? ctrl_auto : ctrl_on);
 }
 
 static ssize_t control_store(struct device * dev, struct device_attribute *attr,
@@ -121,67 +122,71 @@
 static DEVICE_ATTR_RW(control);
 
 static ssize_t runtime_active_time_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+					struct device_attribute *attr,
+					char *buf)
 {
-	int ret;
 	u64 tmp = pm_runtime_active_time(dev);
+
 	do_div(tmp, NSEC_PER_MSEC);
-	ret = sprintf(buf, "%llu\n", tmp);
-	return ret;
+
+	return sysfs_emit(buf, "%llu\n", tmp);
 }
 
 static DEVICE_ATTR_RO(runtime_active_time);
 
 static ssize_t runtime_suspended_time_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+					   struct device_attribute *attr,
+					   char *buf)
 {
-	int ret;
 	u64 tmp = pm_runtime_suspended_time(dev);
+
 	do_div(tmp, NSEC_PER_MSEC);
-	ret = sprintf(buf, "%llu\n", tmp);
-	return ret;
+
+	return sysfs_emit(buf, "%llu\n", tmp);
 }
 
 static DEVICE_ATTR_RO(runtime_suspended_time);
 
 static ssize_t runtime_status_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
+				   struct device_attribute *attr, char *buf)
 {
-	const char *p;
+	const char *output;
 
 	if (dev->power.runtime_error) {
-		p = "error\n";
+		output = "error";
 	} else if (dev->power.disable_depth) {
-		p = "unsupported\n";
+		output = "unsupported";
 	} else {
 		switch (dev->power.runtime_status) {
 		case RPM_SUSPENDED:
-			p = "suspended\n";
+			output = "suspended";
 			break;
 		case RPM_SUSPENDING:
-			p = "suspending\n";
+			output = "suspending";
 			break;
 		case RPM_RESUMING:
-			p = "resuming\n";
+			output = "resuming";
 			break;
 		case RPM_ACTIVE:
-			p = "active\n";
+			output = "active";
 			break;
 		default:
 			return -EIO;
 		}
 	}
-	return sprintf(buf, p);
+	return sysfs_emit(buf, "%s\n", output);
 }
 
 static DEVICE_ATTR_RO(runtime_status);
 
 static ssize_t autosuspend_delay_ms_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
+					 struct device_attribute *attr,
+					 char *buf)
 {
 	if (!dev->power.use_autosuspend)
 		return -EIO;
-	return sprintf(buf, "%d\n", dev->power.autosuspend_delay);
+
+	return sysfs_emit(buf, "%d\n", dev->power.autosuspend_delay);
 }
 
 static ssize_t autosuspend_delay_ms_store(struct device *dev,
@@ -210,11 +215,11 @@
 	s32 value = dev_pm_qos_requested_resume_latency(dev);
 
 	if (value == 0)
-		return sprintf(buf, "n/a\n");
+		return sysfs_emit(buf, "n/a\n");
 	if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
 		value = 0;
 
-	return sprintf(buf, "%d\n", value);
+	return sysfs_emit(buf, "%d\n", value);
 }
 
 static ssize_t pm_qos_resume_latency_us_store(struct device *dev,
@@ -254,11 +259,11 @@
 	s32 value = dev_pm_qos_get_user_latency_tolerance(dev);
 
 	if (value < 0)
-		return sprintf(buf, "auto\n");
+		return sysfs_emit(buf, "%s\n", "auto");
 	if (value == PM_QOS_LATENCY_ANY)
-		return sprintf(buf, "any\n");
+		return sysfs_emit(buf, "%s\n", "any");
 
-	return sprintf(buf, "%d\n", value);
+	return sysfs_emit(buf, "%d\n", value);
 }
 
 static ssize_t pm_qos_latency_tolerance_us_store(struct device *dev,
@@ -290,8 +295,8 @@
 					struct device_attribute *attr,
 					char *buf)
 {
-	return sprintf(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev)
-					& PM_QOS_FLAG_NO_POWER_OFF));
+	return sysfs_emit(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev)
+					  & PM_QOS_FLAG_NO_POWER_OFF));
 }
 
 static ssize_t pm_qos_no_power_off_store(struct device *dev,
@@ -319,9 +324,9 @@
 static ssize_t wakeup_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
-	return sprintf(buf, "%s\n", device_can_wakeup(dev)
-		? (device_may_wakeup(dev) ? _enabled : _disabled)
-		: "");
+	return sysfs_emit(buf, "%s\n", device_can_wakeup(dev)
+			  ? (device_may_wakeup(dev) ? _enabled : _disabled)
+			  : "");
 }
 
 static ssize_t wakeup_store(struct device *dev, struct device_attribute *attr,
@@ -344,7 +349,7 @@
 static ssize_t wakeup_count_show(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
-	unsigned long count = 0;
+	unsigned long count;
 	bool enabled = false;
 
 	spin_lock_irq(&dev->power.lock);
@@ -353,7 +358,10 @@
 		enabled = true;
 	}
 	spin_unlock_irq(&dev->power.lock);
-	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lu\n", count);
 }
 
 static DEVICE_ATTR_RO(wakeup_count);
@@ -362,7 +370,7 @@
 					struct device_attribute *attr,
 					char *buf)
 {
-	unsigned long count = 0;
+	unsigned long count;
 	bool enabled = false;
 
 	spin_lock_irq(&dev->power.lock);
@@ -371,7 +379,10 @@
 		enabled = true;
 	}
 	spin_unlock_irq(&dev->power.lock);
-	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lu\n", count);
 }
 
 static DEVICE_ATTR_RO(wakeup_active_count);
@@ -380,7 +391,7 @@
 				       struct device_attribute *attr,
 				       char *buf)
 {
-	unsigned long count = 0;
+	unsigned long count;
 	bool enabled = false;
 
 	spin_lock_irq(&dev->power.lock);
@@ -389,7 +400,10 @@
 		enabled = true;
 	}
 	spin_unlock_irq(&dev->power.lock);
-	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lu\n", count);
 }
 
 static DEVICE_ATTR_RO(wakeup_abort_count);
@@ -398,7 +412,7 @@
 					struct device_attribute *attr,
 					char *buf)
 {
-	unsigned long count = 0;
+	unsigned long count;
 	bool enabled = false;
 
 	spin_lock_irq(&dev->power.lock);
@@ -407,7 +421,10 @@
 		enabled = true;
 	}
 	spin_unlock_irq(&dev->power.lock);
-	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lu\n", count);
 }
 
 static DEVICE_ATTR_RO(wakeup_expire_count);
@@ -415,7 +432,7 @@
 static ssize_t wakeup_active_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
-	unsigned int active = 0;
+	unsigned int active;
 	bool enabled = false;
 
 	spin_lock_irq(&dev->power.lock);
@@ -424,7 +441,10 @@
 		enabled = true;
 	}
 	spin_unlock_irq(&dev->power.lock);
-	return enabled ? sprintf(buf, "%u\n", active) : sprintf(buf, "\n");
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%u\n", active);
 }
 
 static DEVICE_ATTR_RO(wakeup_active);
@@ -433,7 +453,7 @@
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	s64 msec = 0;
+	s64 msec;
 	bool enabled = false;
 
 	spin_lock_irq(&dev->power.lock);
@@ -442,7 +462,10 @@
 		enabled = true;
 	}
 	spin_unlock_irq(&dev->power.lock);
-	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lld\n", msec);
 }
 
 static DEVICE_ATTR_RO(wakeup_total_time_ms);
@@ -450,7 +473,7 @@
 static ssize_t wakeup_max_time_ms_show(struct device *dev,
 				       struct device_attribute *attr, char *buf)
 {
-	s64 msec = 0;
+	s64 msec;
 	bool enabled = false;
 
 	spin_lock_irq(&dev->power.lock);
@@ -459,7 +482,10 @@
 		enabled = true;
 	}
 	spin_unlock_irq(&dev->power.lock);
-	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lld\n", msec);
 }
 
 static DEVICE_ATTR_RO(wakeup_max_time_ms);
@@ -468,7 +494,7 @@
 					struct device_attribute *attr,
 					char *buf)
 {
-	s64 msec = 0;
+	s64 msec;
 	bool enabled = false;
 
 	spin_lock_irq(&dev->power.lock);
@@ -477,7 +503,18 @@
 		enabled = true;
 	}
 	spin_unlock_irq(&dev->power.lock);
-	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lld\n", msec);
+}
+
+static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid,
+						kgid_t kgid)
+{
+	if (dev->power.wakeup && dev->power.wakeup->dev)
+		return device_change_owner(dev->power.wakeup->dev, kuid, kgid);
+	return 0;
 }
 
 static DEVICE_ATTR_RO(wakeup_last_time_ms);
@@ -487,7 +524,7 @@
 						 struct device_attribute *attr,
 						 char *buf)
 {
-	s64 msec = 0;
+	s64 msec;
 	bool enabled = false;
 
 	spin_lock_irq(&dev->power.lock);
@@ -496,18 +533,27 @@
 		enabled = true;
 	}
 	spin_unlock_irq(&dev->power.lock);
-	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+
+	if (!enabled)
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%lld\n", msec);
 }
 
 static DEVICE_ATTR_RO(wakeup_prevent_sleep_time_ms);
 #endif /* CONFIG_PM_AUTOSLEEP */
-#endif /* CONFIG_PM_SLEEP */
+#else /* CONFIG_PM_SLEEP */
+static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid,
+						kgid_t kgid)
+{
+	return 0;
+}
+#endif
 
 #ifdef CONFIG_PM_ADVANCED_DEBUG
 static ssize_t runtime_usage_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", atomic_read(&dev->power.usage_count));
+	return sysfs_emit(buf, "%d\n", atomic_read(&dev->power.usage_count));
 }
 static DEVICE_ATTR_RO(runtime_usage);
 
@@ -515,21 +561,26 @@
 					struct device_attribute *attr,
 					char *buf)
 {
-	return sprintf(buf, "%d\n", dev->power.ignore_children ?
-		0 : atomic_read(&dev->power.child_count));
+	return sysfs_emit(buf, "%d\n", dev->power.ignore_children ?
+			  0 : atomic_read(&dev->power.child_count));
 }
 static DEVICE_ATTR_RO(runtime_active_kids);
 
 static ssize_t runtime_enabled_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
-	if (dev->power.disable_depth && (dev->power.runtime_auto == false))
-		return sprintf(buf, "disabled & forbidden\n");
-	if (dev->power.disable_depth)
-		return sprintf(buf, "disabled\n");
-	if (dev->power.runtime_auto == false)
-		return sprintf(buf, "forbidden\n");
-	return sprintf(buf, "enabled\n");
+	const char *output;
+
+	if (dev->power.disable_depth && !dev->power.runtime_auto)
+		output = "disabled & forbidden";
+	else if (dev->power.disable_depth)
+		output = "disabled";
+	else if (!dev->power.runtime_auto)
+		output = "forbidden";
+	else
+		output = "enabled";
+
+	return sysfs_emit(buf, "%s\n", output);
 }
 static DEVICE_ATTR_RO(runtime_enabled);
 
@@ -537,9 +588,9 @@
 static ssize_t async_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
-	return sprintf(buf, "%s\n",
-			device_async_suspend_enabled(dev) ?
-				_enabled : _disabled);
+	return sysfs_emit(buf, "%s\n",
+			  device_async_suspend_enabled(dev) ?
+			  _enabled : _disabled);
 }
 
 static ssize_t async_store(struct device *dev, struct device_attribute *attr,
@@ -652,7 +703,7 @@
 	if (rc)
 		return rc;
 
-	if (pm_runtime_callbacks_present(dev)) {
+	if (!pm_runtime_has_no_callbacks(dev)) {
 		rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group);
 		if (rc)
 			goto err_out;
@@ -684,14 +735,59 @@
 	return rc;
 }
 
+int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid)
+{
+	int rc;
+
+	if (device_pm_not_required(dev))
+		return 0;
+
+	rc = sysfs_group_change_owner(&dev->kobj, &pm_attr_group, kuid, kgid);
+	if (rc)
+		return rc;
+
+	if (!pm_runtime_has_no_callbacks(dev)) {
+		rc = sysfs_group_change_owner(
+			&dev->kobj, &pm_runtime_attr_group, kuid, kgid);
+		if (rc)
+			return rc;
+	}
+
+	if (device_can_wakeup(dev)) {
+		rc = sysfs_group_change_owner(&dev->kobj, &pm_wakeup_attr_group,
+					      kuid, kgid);
+		if (rc)
+			return rc;
+
+		rc = dpm_sysfs_wakeup_change_owner(dev, kuid, kgid);
+		if (rc)
+			return rc;
+	}
+
+	if (dev->power.set_latency_tolerance) {
+		rc = sysfs_group_change_owner(
+			&dev->kobj, &pm_qos_latency_tolerance_attr_group, kuid,
+			kgid);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
 int wakeup_sysfs_add(struct device *dev)
 {
-	return sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+	int ret = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+
+	if (!ret)
+		kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+
+	return ret;
 }
 
 void wakeup_sysfs_remove(struct device *dev)
 {
 	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
+	kobject_uevent(&dev->kobj, KOBJ_CHANGE);
 }
 
 int pm_qos_sysfs_add_resume_latency(struct device *dev)
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 9a9dec6..9466503 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -269,7 +269,7 @@
 	.notifier_call = pm_trace_notify,
 };
 
-static int early_resume_init(void)
+static int __init early_resume_init(void)
 {
 	if (!x86_platform.legacy.rtc)
 		return 0;
@@ -279,7 +279,7 @@
 	return 0;
 }
 
-static int late_resume_init(void)
+static int __init late_resume_init(void)
 {
 	unsigned int val = hash_value_early_read;
 	unsigned int user, file, dev;
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 5ce77d1..8e02108 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -272,7 +272,7 @@
 {
 	struct wake_irq *wirq = dev->power.wakeirq;
 
-	if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK)))
+	if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK))
 		return;
 
 	if (likely(wirq->status & WAKE_IRQ_DEDICATED_MANAGED)) {
@@ -299,7 +299,7 @@
 {
 	struct wake_irq *wirq = dev->power.wakeirq;
 
-	if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK)))
+	if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK))
 		return;
 
 	if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED)
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 92f0960..8997e02 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -24,6 +24,9 @@
 #define pm_suspend_target_state	(PM_SUSPEND_ON)
 #endif
 
+#define list_for_each_entry_rcu_locked(pos, head, member) \
+	list_for_each_entry_rcu(pos, head, member, \
+		srcu_read_lock_held(&wakeup_srcu))
 /*
  * If set, the suspend/hibernate code will abort transitions to a sleep state
  * if wakeup events are registered during or immediately before the transition.
@@ -31,7 +34,8 @@
 bool events_check_enabled __read_mostly;
 
 /* First wakeup IRQ seen by the kernel in the last cycle. */
-unsigned int pm_wakeup_irq __read_mostly;
+static unsigned int wakeup_irq[2] __read_mostly;
+static DEFINE_RAW_SPINLOCK(wakeup_irq_lock);
 
 /* If greater than 0 and the system is suspending, terminate the suspend. */
 static atomic_t pm_abort_suspend __read_mostly;
@@ -250,6 +254,60 @@
 EXPORT_SYMBOL_GPL(wakeup_source_unregister);
 
 /**
+ * wakeup_sources_read_lock - Lock wakeup source list for read.
+ *
+ * Returns an index of srcu lock for struct wakeup_srcu.
+ * This index must be passed to the matching wakeup_sources_read_unlock().
+ */
+int wakeup_sources_read_lock(void)
+{
+	return srcu_read_lock(&wakeup_srcu);
+}
+EXPORT_SYMBOL_GPL(wakeup_sources_read_lock);
+
+/**
+ * wakeup_sources_read_unlock - Unlock wakeup source list.
+ * @idx: return value from corresponding wakeup_sources_read_lock()
+ */
+void wakeup_sources_read_unlock(int idx)
+{
+	srcu_read_unlock(&wakeup_srcu, idx);
+}
+EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock);
+
+/**
+ * wakeup_sources_walk_start - Begin a walk on wakeup source list
+ *
+ * Returns first object of the list of wakeup sources.
+ *
+ * Note that to be safe, wakeup sources list needs to be locked by calling
+ * wakeup_source_read_lock() for this.
+ */
+struct wakeup_source *wakeup_sources_walk_start(void)
+{
+	struct list_head *ws_head = &wakeup_sources;
+
+	return list_entry_rcu(ws_head->next, struct wakeup_source, entry);
+}
+EXPORT_SYMBOL_GPL(wakeup_sources_walk_start);
+
+/**
+ * wakeup_sources_walk_next - Get next wakeup source from the list
+ * @ws: Previous wakeup source object
+ *
+ * Note that to be safe, wakeup sources list needs to be locked by calling
+ * wakeup_source_read_lock() for this.
+ */
+struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws)
+{
+	struct list_head *ws_head = &wakeup_sources;
+
+	return list_next_or_null_rcu(ws_head, &ws->entry,
+				struct wakeup_source, entry);
+}
+EXPORT_SYMBOL_GPL(wakeup_sources_walk_next);
+
+/**
  * device_wakeup_attach - Attach a wakeup source object to a device object.
  * @dev: Device to handle.
  * @ws: Wakeup source object to attach to @dev.
@@ -353,7 +411,7 @@
 	int srcuidx;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry)
 		dev_pm_arm_wake_irq(ws->wakeirq);
 	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
@@ -369,7 +427,7 @@
 	int srcuidx;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry)
 		dev_pm_disarm_wake_irq(ws->wakeirq);
 	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
@@ -822,7 +880,7 @@
 	struct wakeup_source *last_activity_ws = NULL;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
 		if (ws->active) {
 			pm_pr_dbg("active wakeup source: %s\n", ws->name);
 			active = 1;
@@ -884,19 +942,45 @@
 	atomic_dec_if_positive(&pm_abort_suspend);
 }
 
-void pm_wakeup_clear(bool reset)
+void pm_wakeup_clear(unsigned int irq_number)
 {
-	pm_wakeup_irq = 0;
-	if (reset)
+	raw_spin_lock_irq(&wakeup_irq_lock);
+
+	if (irq_number && wakeup_irq[0] == irq_number)
+		wakeup_irq[0] = wakeup_irq[1];
+	else
+		wakeup_irq[0] = 0;
+
+	wakeup_irq[1] = 0;
+
+	raw_spin_unlock_irq(&wakeup_irq_lock);
+
+	if (!irq_number)
 		atomic_set(&pm_abort_suspend, 0);
 }
 
 void pm_system_irq_wakeup(unsigned int irq_number)
 {
-	if (pm_wakeup_irq == 0) {
-		pm_wakeup_irq = irq_number;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&wakeup_irq_lock, flags);
+
+	if (wakeup_irq[0] == 0)
+		wakeup_irq[0] = irq_number;
+	else if (wakeup_irq[1] == 0)
+		wakeup_irq[1] = irq_number;
+	else
+		irq_number = 0;
+
+	raw_spin_unlock_irqrestore(&wakeup_irq_lock, flags);
+
+	if (irq_number)
 		pm_system_wakeup();
-	}
+}
+
+unsigned int pm_wakeup_irq(void)
+{
+	return wakeup_irq[0];
 }
 
 /**
@@ -973,7 +1057,7 @@
 	int srcuidx;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
 		spin_lock_irq(&ws->lock);
 		if (ws->autosleep_enabled != set) {
 			ws->autosleep_enabled = set;
@@ -1052,7 +1136,7 @@
 	}
 
 	*srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
 		if (n-- <= 0)
 			return ws;
 	}
diff --git a/drivers/base/power/wakeup_stats.c b/drivers/base/power/wakeup_stats.c
index c773491..d638259 100644
--- a/drivers/base/power/wakeup_stats.c
+++ b/drivers/base/power/wakeup_stats.c
@@ -26,7 +26,7 @@
 {									\
 	struct wakeup_source *ws = dev_get_drvdata(dev);		\
 									\
-	return sprintf(buf, "%lu\n", ws->_name);			\
+	return sysfs_emit(buf, "%lu\n", ws->_name);			\
 }									\
 static DEVICE_ATTR_RO(_name)
 
@@ -42,7 +42,7 @@
 	ktime_t active_time =
 		ws->active ? ktime_sub(ktime_get(), ws->last_time) : 0;
 
-	return sprintf(buf, "%lld\n", ktime_to_ms(active_time));
+	return sysfs_emit(buf, "%lld\n", ktime_to_ms(active_time));
 }
 static DEVICE_ATTR_RO(active_time_ms);
 
@@ -57,7 +57,8 @@
 		active_time = ktime_sub(ktime_get(), ws->last_time);
 		total_time = ktime_add(total_time, active_time);
 	}
-	return sprintf(buf, "%lld\n", ktime_to_ms(total_time));
+
+	return sysfs_emit(buf, "%lld\n", ktime_to_ms(total_time));
 }
 static DEVICE_ATTR_RO(total_time_ms);
 
@@ -73,7 +74,8 @@
 		if (active_time > max_time)
 			max_time = active_time;
 	}
-	return sprintf(buf, "%lld\n", ktime_to_ms(max_time));
+
+	return sysfs_emit(buf, "%lld\n", ktime_to_ms(max_time));
 }
 static DEVICE_ATTR_RO(max_time_ms);
 
@@ -82,7 +84,7 @@
 {
 	struct wakeup_source *ws = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%lld\n", ktime_to_ms(ws->last_time));
+	return sysfs_emit(buf, "%lld\n", ktime_to_ms(ws->last_time));
 }
 static DEVICE_ATTR_RO(last_change_ms);
 
@@ -91,7 +93,7 @@
 {
 	struct wakeup_source *ws = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%s\n", ws->name);
+	return sysfs_emit(buf, "%s\n", ws->name);
 }
 static DEVICE_ATTR_RO(name);
 
@@ -106,7 +108,8 @@
 		prevent_sleep_time = ktime_add(prevent_sleep_time,
 			ktime_sub(ktime_get(), ws->start_prevent_time));
 	}
-	return sprintf(buf, "%lld\n", ktime_to_ms(prevent_sleep_time));
+
+	return sysfs_emit(buf, "%lld\n", ktime_to_ms(prevent_sleep_time));
 }
 static DEVICE_ATTR_RO(prevent_suspend_time_ms);