3 files changed, 230 insertions, 117 deletions

diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index 781968a128ff..6ecf9ce4a4e6 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -83,7 +83,7 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
 /**
  * dev_pm_domain_attach - Attach a device to its PM domain.
  * @dev: Device to attach.
- * @power_on: Used to indicate whether we should power on the device.
+ * @flags: indicate whether we should power on/off the device on attach/detach
  *
  * The @dev may only be attached to a single PM domain. By iterating through
  * the available alternatives we try to find a valid PM domain for the device.
@@ -100,17 +100,20 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
  * Returns 0 on successfully attached PM domain, or when it is found that the
  * device doesn't need a PM domain, else a negative error code.
  */
-int dev_pm_domain_attach(struct device *dev, bool power_on)
+int dev_pm_domain_attach(struct device *dev, u32 flags)
 {
 	int ret;
 
 	if (dev->pm_domain)
 		return 0;
 
-	ret = acpi_dev_pm_attach(dev, power_on);
+	ret = acpi_dev_pm_attach(dev, !!(flags & PD_FLAG_ATTACH_POWER_ON));
 	if (!ret)
 		ret = genpd_dev_pm_attach(dev);
 
+	if (dev->pm_domain)
+		dev->power.detach_power_off = !!(flags & PD_FLAG_DETACH_POWER_OFF);
+
 	return ret < 0 ? ret : 0;
 }
 EXPORT_SYMBOL_GPL(dev_pm_domain_attach);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index bf77d28e959f..bb382a70d260 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -647,14 +647,27 @@ static void dpm_async_resume_children(struct device *dev, async_func_t func)
 	/*
 	 * Start processing "async" children of the device unless it's been
 	 * started already for them.
-	 *
-	 * This could have been done for the device's "async" consumers too, but
-	 * they either need to wait for their parents or the processing has
-	 * already started for them after their parents were processed.
 	 */
 	device_for_each_child(dev, func, dpm_async_with_cleanup);
 }
 
+static void dpm_async_resume_subordinate(struct device *dev, async_func_t func)
+{
+	struct device_link *link;
+	int idx;
+
+	dpm_async_resume_children(dev, func);
+
+	idx = device_links_read_lock();
+
+	/* Start processing the device's "async" consumers. */
+	list_for_each_entry_rcu(link, &dev->links.consumers, s_node)
+		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
+			dpm_async_with_cleanup(link->consumer, func);
+
+	device_links_read_unlock(idx);
+}
+
 static void dpm_clear_async_state(struct device *dev)
 {
 	reinit_completion(&dev->power.completion);
@@ -663,7 +676,14 @@ static void dpm_clear_async_state(struct device *dev)
 
 static bool dpm_root_device(struct device *dev)
 {
-	return !dev->parent;
+	lockdep_assert_held(&dpm_list_mtx);
+
+	/*
+	 * Since this function is required to run under dpm_list_mtx, the
+	 * list_empty() below will only return true if the device's list of
+	 * consumers is actually empty before calling it.
+	 */
+	return !dev->parent && list_empty(&dev->links.suppliers);
 }
 
 static void async_resume_noirq(void *data, async_cookie_t cookie);
@@ -747,12 +767,12 @@ Out:
 	TRACE_RESUME(error);
 
 	if (error) {
-		async_error = error;
+		WRITE_ONCE(async_error, error);
 		dpm_save_failed_dev(dev_name(dev));
 		pm_dev_err(dev, state, async ? " async noirq" : " noirq", error);
 	}
 
-	dpm_async_resume_children(dev, async_resume_noirq);
+	dpm_async_resume_subordinate(dev, async_resume_noirq);
 }
 
 static void async_resume_noirq(void *data, async_cookie_t cookie)
@@ -804,7 +824,7 @@ static void dpm_noirq_resume_devices(pm_message_t state)
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
 	dpm_show_time(starttime, state, 0, "noirq");
-	if (async_error)
+	if (READ_ONCE(async_error))
 		dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
 
 	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false);
@@ -890,12 +910,12 @@ Out:
 	complete_all(&dev->power.completion);
 
 	if (error) {
-		async_error = error;
+		WRITE_ONCE(async_error, error);
 		dpm_save_failed_dev(dev_name(dev));
 		pm_dev_err(dev, state, async ? " async early" : " early", error);
 	}
 
-	dpm_async_resume_children(dev, async_resume_early);
+	dpm_async_resume_subordinate(dev, async_resume_early);
 }
 
 static void async_resume_early(void *data, async_cookie_t cookie)
@@ -951,7 +971,7 @@ void dpm_resume_early(pm_message_t state)
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
 	dpm_show_time(starttime, state, 0, "early");
-	if (async_error)
+	if (READ_ONCE(async_error))
 		dpm_save_failed_step(SUSPEND_RESUME_EARLY);
 
 	trace_suspend_resume(TPS("dpm_resume_early"), state.event, false);
@@ -1066,12 +1086,12 @@ static void device_resume(struct device *dev, pm_message_t state, bool async)
 	TRACE_RESUME(error);
 
 	if (error) {
-		async_error = error;
+		WRITE_ONCE(async_error, error);
 		dpm_save_failed_dev(dev_name(dev));
 		pm_dev_err(dev, state, async ? " async" : "", error);
 	}
 
-	dpm_async_resume_children(dev, async_resume);
+	dpm_async_resume_subordinate(dev, async_resume);
 }
 
 static void async_resume(void *data, async_cookie_t cookie)
@@ -1095,7 +1115,6 @@ void dpm_resume(pm_message_t state)
 	ktime_t starttime = ktime_get();
 
 	trace_suspend_resume(TPS("dpm_resume"), state.event, true);
-	might_sleep();
 
 	pm_transition = state;
 	async_error = 0;
@@ -1131,7 +1150,7 @@ void dpm_resume(pm_message_t state)
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
 	dpm_show_time(starttime, state, 0, NULL);
-	if (async_error)
+	if (READ_ONCE(async_error))
 		dpm_save_failed_step(SUSPEND_RESUME);
 
 	cpufreq_resume();
@@ -1198,7 +1217,6 @@ void dpm_complete(pm_message_t state)
 	struct list_head list;
 
 	trace_suspend_resume(TPS("dpm_complete"), state.event, true);
-	might_sleep();
 
 	INIT_LIST_HEAD(&list);
 	mutex_lock(&dpm_list_mtx);
@@ -1236,8 +1254,8 @@ void dpm_complete(pm_message_t state)
  */
 void dpm_resume_end(pm_message_t state)
 {
-	pm_restore_gfp_mask();
 	dpm_resume(state);
+	pm_restore_gfp_mask();
 	dpm_complete(state);
 }
 EXPORT_SYMBOL_GPL(dpm_resume_end);
@@ -1258,10 +1276,15 @@ static bool dpm_leaf_device(struct device *dev)
 		return false;
 	}
 
-	return true;
+	/*
+	 * Since this function is required to run under dpm_list_mtx, the
+	 * list_empty() below will only return true if the device's list of
+	 * consumers is actually empty before calling it.
+	 */
+	return list_empty(&dev->links.consumers);
 }
 
-static void dpm_async_suspend_parent(struct device *dev, async_func_t func)
+static bool dpm_async_suspend_parent(struct device *dev, async_func_t func)
 {
 	guard(mutex)(&dpm_list_mtx);
 
@@ -1273,11 +1296,47 @@ static void dpm_async_suspend_parent(struct device *dev, async_func_t func)
 	 * deleted before it.
 	 */
 	if (!device_pm_initialized(dev))
-		return;
+		return false;
 
 	/* Start processing the device's parent if it is "async". */
 	if (dev->parent)
 		dpm_async_with_cleanup(dev->parent, func);
+
+	return true;
+}
+
+static void dpm_async_suspend_superior(struct device *dev, async_func_t func)
+{
+	struct device_link *link;
+	int idx;
+
+	if (!dpm_async_suspend_parent(dev, func))
+		return;
+
+	idx = device_links_read_lock();
+
+	/* Start processing the device's "async" suppliers. */
+	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
+			dpm_async_with_cleanup(link->supplier, func);
+
+	device_links_read_unlock(idx);
+}
+
+static void dpm_async_suspend_complete_all(struct list_head *device_list)
+{
+	struct device *dev;
+
+	guard(mutex)(&async_wip_mtx);
+
+	list_for_each_entry_reverse(dev, device_list, power.entry) {
+		/*
+		 * In case the device is being waited for and async processing
+		 * has not started for it yet, let the waiters make progress.
+		 */
+		if (!dev->power.work_in_progress)
+			complete_all(&dev->power.completion);
+	}
 }
 
 /**
@@ -1328,7 +1387,7 @@ static void async_suspend_noirq(void *data, async_cookie_t cookie);
  * The driver of @dev will not receive interrupts while this function is being
  * executed.
  */
-static int device_suspend_noirq(struct device *dev, pm_message_t state, bool async)
+static void device_suspend_noirq(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -1339,7 +1398,7 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state, bool asy
 
 	dpm_wait_for_subordinate(dev, async);
 
-	if (async_error)
+	if (READ_ONCE(async_error))
 		goto Complete;
 
 	if (dev->power.syscore || dev->power.direct_complete)
@@ -1372,7 +1431,7 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state, bool asy
 Run:
 	error = dpm_run_callback(callback, dev, state, info);
 	if (error) {
-		async_error = error;
+		WRITE_ONCE(async_error, error);
 		dpm_save_failed_dev(dev_name(dev));
 		pm_dev_err(dev, state, async ? " async noirq" : " noirq", error);
 		goto Complete;
@@ -1398,12 +1457,10 @@ Complete:
 	complete_all(&dev->power.completion);
 	TRACE_SUSPEND(error);
 
-	if (error || async_error)
-		return error;
-
-	dpm_async_suspend_parent(dev, async_suspend_noirq);
+	if (error || READ_ONCE(async_error))
+		return;
 
-	return 0;
+	dpm_async_suspend_superior(dev, async_suspend_noirq);
 }
 
 static void async_suspend_noirq(void *data, async_cookie_t cookie)
@@ -1418,7 +1475,7 @@ static int dpm_noirq_suspend_devices(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 	struct device *dev;
-	int error = 0;
+	int error;
 
 	trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true);
 
@@ -1449,13 +1506,14 @@ static int dpm_noirq_suspend_devices(pm_message_t state)
 
 		mutex_unlock(&dpm_list_mtx);
 
-		error = device_suspend_noirq(dev, state, false);
+		device_suspend_noirq(dev, state, false);
 
 		put_device(dev);
 
 		mutex_lock(&dpm_list_mtx);
 
-		if (error || async_error) {
+		if (READ_ONCE(async_error)) {
+			dpm_async_suspend_complete_all(&dpm_late_early_list);
 			/*
 			 * Move all devices to the target list to resume them
 			 * properly.
@@ -1468,9 +1526,8 @@ static int dpm_noirq_suspend_devices(pm_message_t state)
 	mutex_unlock(&dpm_list_mtx);
 
 	async_synchronize_full();
-	if (!error)
-		error = async_error;
 
+	error = READ_ONCE(async_error);
 	if (error)
 		dpm_save_failed_step(SUSPEND_SUSPEND_NOIRQ);
 
@@ -1525,7 +1582,7 @@ static void async_suspend_late(void *data, async_cookie_t cookie);
  *
  * Runtime PM is disabled for @dev while this function is being executed.
  */
-static int device_suspend_late(struct device *dev, pm_message_t state, bool async)
+static void device_suspend_late(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -1542,11 +1599,11 @@ static int device_suspend_late(struct device *dev, pm_message_t state, bool asyn
 
 	dpm_wait_for_subordinate(dev, async);
 
-	if (async_error)
+	if (READ_ONCE(async_error))
 		goto Complete;
 
 	if (pm_wakeup_pending()) {
-		async_error = -EBUSY;
+		WRITE_ONCE(async_error, -EBUSY);
 		goto Complete;
 	}
 
@@ -1580,7 +1637,7 @@ static int device_suspend_late(struct device *dev, pm_message_t state, bool asyn
 Run:
 	error = dpm_run_callback(callback, dev, state, info);
 	if (error) {
-		async_error = error;
+		WRITE_ONCE(async_error, error);
 		dpm_save_failed_dev(dev_name(dev));
 		pm_dev_err(dev, state, async ? " async late" : " late", error);
 		goto Complete;
@@ -1594,12 +1651,10 @@ Complete:
 	TRACE_SUSPEND(error);
 	complete_all(&dev->power.completion);
 
-	if (error || async_error)
-		return error;
-
-	dpm_async_suspend_parent(dev, async_suspend_late);
+	if (error || READ_ONCE(async_error))
+		return;
 
-	return 0;
+	dpm_async_suspend_superior(dev, async_suspend_late);
 }
 
 static void async_suspend_late(void *data, async_cookie_t cookie)
@@ -1618,7 +1673,7 @@ int dpm_suspend_late(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 	struct device *dev;
-	int error = 0;
+	int error;
 
 	trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true);
 
@@ -1651,13 +1706,14 @@ int dpm_suspend_late(pm_message_t state)
 
 		mutex_unlock(&dpm_list_mtx);
 
-		error = device_suspend_late(dev, state, false);
+		device_suspend_late(dev, state, false);
 
 		put_device(dev);
 
 		mutex_lock(&dpm_list_mtx);
 
-		if (error || async_error) {
+		if (READ_ONCE(async_error)) {
+			dpm_async_suspend_complete_all(&dpm_suspended_list);
 			/*
 			 * Move all devices to the target list to resume them
 			 * properly.
@@ -1670,9 +1726,8 @@ int dpm_suspend_late(pm_message_t state)
 	mutex_unlock(&dpm_list_mtx);
 
 	async_synchronize_full();
-	if (!error)
-		error = async_error;
 
+	error = READ_ONCE(async_error);
 	if (error) {
 		dpm_save_failed_step(SUSPEND_SUSPEND_LATE);
 		dpm_resume_early(resume_event(state));
@@ -1761,7 +1816,7 @@ static void async_suspend(void *data, async_cookie_t cookie);
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being suspended asynchronously.
  */
-static int device_suspend(struct device *dev, pm_message_t state, bool async)
+static void device_suspend(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -1773,7 +1828,7 @@ static int device_suspend(struct device *dev, pm_message_t state, bool async)
 
 	dpm_wait_for_subordinate(dev, async);
 
-	if (async_error) {
+	if (READ_ONCE(async_error)) {
 		dev->power.direct_complete = false;
 		goto Complete;
 	}
@@ -1793,7 +1848,7 @@ static int device_suspend(struct device *dev, pm_message_t state, bool async)
 
 	if (pm_wakeup_pending()) {
 		dev->power.direct_complete = false;
-		async_error = -EBUSY;
+		WRITE_ONCE(async_error, -EBUSY);
 		goto Complete;
 	}
 
@@ -1877,7 +1932,7 @@ static int device_suspend(struct device *dev, pm_message_t state, bool async)
 
  Complete:
 	if (error) {
-		async_error = error;
+		WRITE_ONCE(async_error, error);
 		dpm_save_failed_dev(dev_name(dev));
 		pm_dev_err(dev, state, async ? " async" : "", error);
 	}
@@ -1885,12 +1940,10 @@ static int device_suspend(struct device *dev, pm_message_t state, bool async)
 	complete_all(&dev->power.completion);
 	TRACE_SUSPEND(error);
 
-	if (error || async_error)
-		return error;
-
-	dpm_async_suspend_parent(dev, async_suspend);
+	if (error || READ_ONCE(async_error))
+		return;
 
-	return 0;
+	dpm_async_suspend_superior(dev, async_suspend);
 }
 
 static void async_suspend(void *data, async_cookie_t cookie)
@@ -1909,7 +1962,7 @@ int dpm_suspend(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 	struct device *dev;
-	int error = 0;
+	int error;
 
 	trace_suspend_resume(TPS("dpm_suspend"), state.event, true);
 	might_sleep();
@@ -1944,13 +1997,14 @@ int dpm_suspend(pm_message_t state)
 
 		mutex_unlock(&dpm_list_mtx);
 
-		error = device_suspend(dev, state, false);
+		device_suspend(dev, state, false);
 
 		put_device(dev);
 
 		mutex_lock(&dpm_list_mtx);
 
-		if (error || async_error) {
+		if (READ_ONCE(async_error)) {
+			dpm_async_suspend_complete_all(&dpm_prepared_list);
 			/*
 			 * Move all devices to the target list to resume them
 			 * properly.
@@ -1963,9 +2017,8 @@ int dpm_suspend(pm_message_t state)
 	mutex_unlock(&dpm_list_mtx);
 
 	async_synchronize_full();
-	if (!error)
-		error = async_error;
 
+	error = READ_ONCE(async_error);
 	if (error)
 		dpm_save_failed_step(SUSPEND_SUSPEND);
 
@@ -1999,7 +2052,7 @@ static bool device_prepare_smart_suspend(struct device *dev)
 	idx = device_links_read_lock();
 
 	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) {
-		if (!(link->flags & DL_FLAG_PM_RUNTIME))
+		if (!device_link_test(link, DL_FLAG_PM_RUNTIME))
 			continue;
 
 		if (!dev_pm_smart_suspend(link->supplier) &&
@@ -2110,7 +2163,6 @@ int dpm_prepare(pm_message_t state)
 	int error = 0;
 
 	trace_suspend_resume(TPS("dpm_prepare"), state.event, true);
-	might_sleep();
 
 	/*
 	 * Give a chance for the known devices to complete their probes, before
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index c55a7c70bc1a..3e84dc4122de 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -19,10 +19,24 @@
 
 typedef int (*pm_callback_t)(struct device *);
 
+static inline pm_callback_t get_callback_ptr(const void *start, size_t offset)
+{
+	return *(pm_callback_t *)(start + offset);
+}
+
+static pm_callback_t __rpm_get_driver_callback(struct device *dev,
+					       size_t cb_offset)
+{
+	if (dev->driver && dev->driver->pm)
+		return get_callback_ptr(dev->driver->pm, cb_offset);
+
+	return NULL;
+}
+
 static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset)
 {
-	pm_callback_t cb;
 	const struct dev_pm_ops *ops;
+	pm_callback_t cb = NULL;
 
 	if (dev->pm_domain)
 		ops = &dev->pm_domain->ops;
@@ -36,12 +50,10 @@ static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset)
 		ops = NULL;
 
 	if (ops)
-		cb = *(pm_callback_t *)((void *)ops + cb_offset);
-	else
-		cb = NULL;
+		cb = get_callback_ptr(ops, cb_offset);
 
-	if (!cb && dev->driver && dev->driver->pm)
-		cb = *(pm_callback_t *)((void *)dev->driver->pm + cb_offset);
+	if (!cb)
+		cb = __rpm_get_driver_callback(dev, cb_offset);
 
 	return cb;
 }
@@ -290,7 +302,7 @@ static int rpm_get_suppliers(struct device *dev)
 				device_links_read_lock_held()) {
 		int retval;
 
-		if (!(link->flags & DL_FLAG_PM_RUNTIME))
+		if (!device_link_test(link, DL_FLAG_PM_RUNTIME))
 			continue;
 
 		retval = pm_runtime_get_sync(link->supplier);
@@ -1191,10 +1203,12 @@ EXPORT_SYMBOL_GPL(__pm_runtime_resume);
  *
  * Return -EINVAL if runtime PM is disabled for @dev.
  *
- * 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.
+ * Otherwise, if its runtime PM status is %RPM_ACTIVE and (1) @ign_usage_count
+ * is set, or (2) @dev is not ignoring children and its active child count is
+ * nonero, or (3) 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.
@@ -1216,7 +1230,8 @@ static int pm_runtime_get_conditional(struct device *dev, bool ign_usage_count)
 		retval = -EINVAL;
 	} else if (dev->power.runtime_status != RPM_ACTIVE) {
 		retval = 0;
-	} else if (ign_usage_count) {
+	} else if (ign_usage_count || (!dev->power.ignore_children &&
+		   atomic_read(&dev->power.child_count) > 0)) {
 		retval = 1;
 		atomic_inc(&dev->power.usage_count);
 	} else {
@@ -1249,10 +1264,16 @@ EXPORT_SYMBOL_GPL(pm_runtime_get_if_active);
  * @dev: Target device.
  *
  * Increment the runtime PM usage counter of @dev if its runtime PM status is
- * %RPM_ACTIVE and its runtime PM usage counter is greater than 0, in which case
- * it returns 1. If the device is in a different state or its usage_count is 0,
- * 0 is returned. -EINVAL is returned if runtime PM is disabled for the device,
- * in which case also the usage_count will remain unmodified.
+ * %RPM_ACTIVE and its runtime PM usage counter is greater than 0 or it is not
+ * ignoring children and its active child count is nonzero.  1 is returned in
+ * this case.
+ *
+ * If @dev is in a different state or it is not in use (that is, its usage
+ * counter is 0, or it is ignoring children, or its active child count is 0),
+ * 0 is returned.
+ *
+ * -EINVAL is returned if runtime PM is disabled for the device, in which case
+ * also the usage counter of @dev is not updated.
  */
 int pm_runtime_get_if_in_use(struct device *dev)
 {
@@ -1827,7 +1848,7 @@ void pm_runtime_init(struct device *dev)
 	dev->power.request_pending = false;
 	dev->power.request = RPM_REQ_NONE;
 	dev->power.deferred_resume = false;
-	dev->power.needs_force_resume = 0;
+	dev->power.needs_force_resume = false;
 	INIT_WORK(&dev->power.work, pm_runtime_work);
 
 	dev->power.timer_expires = 0;
@@ -1854,6 +1875,11 @@ void pm_runtime_reinit(struct device *dev)
 				pm_runtime_put(dev->parent);
 		}
 	}
+	/*
+	 * Clear power.needs_force_resume in case it has been set by
+	 * pm_runtime_force_suspend() invoked from a driver remove callback.
+	 */
+	dev->power.needs_force_resume = false;
 }
 
 /**
@@ -1879,7 +1905,7 @@ void pm_runtime_get_suppliers(struct device *dev)
 
 	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
 				device_links_read_lock_held())
-		if (link->flags & DL_FLAG_PM_RUNTIME) {
+		if (device_link_test(link, DL_FLAG_PM_RUNTIME)) {
 			link->supplier_preactivated = true;
 			pm_runtime_get_sync(link->supplier);
 		}
@@ -1933,7 +1959,7 @@ static void pm_runtime_drop_link_count(struct device *dev)
  */
 void pm_runtime_drop_link(struct device_link *link)
 {
-	if (!(link->flags & DL_FLAG_PM_RUNTIME))
+	if (!device_link_test(link, DL_FLAG_PM_RUNTIME))
 		return;
 
 	pm_runtime_drop_link_count(link->consumer);
@@ -1941,13 +1967,23 @@ void pm_runtime_drop_link(struct device_link *link)
 	pm_request_idle(link->supplier);
 }
 
-bool pm_runtime_need_not_resume(struct device *dev)
+static pm_callback_t get_callback(struct device *dev, size_t cb_offset)
 {
-	return atomic_read(&dev->power.usage_count) <= 1 &&
-		(atomic_read(&dev->power.child_count) == 0 ||
-		 dev->power.ignore_children);
+	/*
+	 * Setting power.strict_midlayer means that the middle layer
+	 * code does not want its runtime PM callbacks to be invoked via
+	 * pm_runtime_force_suspend() and pm_runtime_force_resume(), so
+	 * return a direct pointer to the driver callback in that case.
+	 */
+	if (dev_pm_strict_midlayer_is_set(dev))
+		return __rpm_get_driver_callback(dev, cb_offset);
+
+	return __rpm_get_callback(dev, cb_offset);
 }
 
+#define GET_CALLBACK(dev, callback) \
+		get_callback(dev, offsetof(struct dev_pm_ops, callback))
+
 /**
  * pm_runtime_force_suspend - Force a device into suspend state if needed.
  * @dev: Device to suspend.
@@ -1964,10 +2000,6 @@ bool pm_runtime_need_not_resume(struct device *dev)
  * sure the device is put into low power state and it should only be used during
  * system-wide PM transitions to sleep states.  It assumes that the analogous
  * pm_runtime_force_resume() will be used to resume the device.
- *
- * Do not use with DPM_FLAG_SMART_SUSPEND as this can lead to an inconsistent
- * state where this function has called the ->runtime_suspend callback but the
- * PM core marks the driver as runtime active.
  */
 int pm_runtime_force_suspend(struct device *dev)
 {
@@ -1975,10 +2007,10 @@ int pm_runtime_force_suspend(struct device *dev)
 	int ret;
 
 	pm_runtime_disable(dev);
-	if (pm_runtime_status_suspended(dev))
+	if (pm_runtime_status_suspended(dev) || dev->power.needs_force_resume)
 		return 0;
 
-	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
+	callback = GET_CALLBACK(dev, runtime_suspend);
 
 	dev_pm_enable_wake_irq_check(dev, true);
 	ret = callback ? callback(dev) : 0;
@@ -1990,15 +2022,16 @@ int pm_runtime_force_suspend(struct device *dev)
 	/*
 	 * If the device can stay in suspend after the system-wide transition
 	 * to the working state that will follow, drop the children counter of
-	 * its parent, but set its status to RPM_SUSPENDED anyway in case this
-	 * function will be called again for it in the meantime.
+	 * its parent and the usage counters of its suppliers.  Otherwise, set
+	 * power.needs_force_resume to let pm_runtime_force_resume() know that
+	 * the device needs to be taken care of and to prevent this function
+	 * from handling the device again in case the device is passed to it
+	 * once more subsequently.
 	 */
-	if (pm_runtime_need_not_resume(dev)) {
+	if (pm_runtime_need_not_resume(dev))
 		pm_runtime_set_suspended(dev);
-	} else {
-		__update_runtime_status(dev, RPM_SUSPENDED);
-		dev->power.needs_force_resume = 1;
-	}
+	else
+		dev->power.needs_force_resume = true;
 
 	return 0;
 
@@ -2009,33 +2042,37 @@ err:
 }
 EXPORT_SYMBOL_GPL(pm_runtime_force_suspend);
 
+#ifdef CONFIG_PM_SLEEP
+
 /**
  * pm_runtime_force_resume - Force a device into resume state if needed.
  * @dev: Device to resume.
  *
- * Prior invoking this function we expect the user to have brought the device
- * into low power state by a call to pm_runtime_force_suspend(). Here we reverse
- * those actions and bring the device into full power, if it is expected to be
- * used on system resume.  In the other case, we defer the resume to be managed
- * via runtime PM.
+ * This function expects that either pm_runtime_force_suspend() has put the
+ * device into a low-power state prior to calling it, or the device had been
+ * runtime-suspended before the preceding system-wide suspend transition and it
+ * was left in suspend during that transition.
  *
- * Typically this function may be invoked from a system resume callback.
+ * The actions carried out by pm_runtime_force_suspend(), or by a runtime
+ * suspend in general, are reversed and the device is brought back into full
+ * power if it is expected to be used on system resume, which is the case when
+ * its needs_force_resume flag is set or when its smart_suspend flag is set and
+ * its runtime PM status is "active".
+ *
+ * In other cases, the resume is deferred to be managed via runtime PM.
+ *
+ * Typically, this function may be invoked from a system resume callback.
  */
 int pm_runtime_force_resume(struct device *dev)
 {
 	int (*callback)(struct device *);
 	int ret = 0;
 
-	if (!dev->power.needs_force_resume)
+	if (!dev->power.needs_force_resume && (!dev_pm_smart_suspend(dev) ||
+	    pm_runtime_status_suspended(dev)))
 		goto out;
 
-	/*
-	 * The value of the parent's children counter is correct already, so
-	 * just update the status of the device.
-	 */
-	__update_runtime_status(dev, RPM_ACTIVE);
-
-	callback = RPM_GET_CALLBACK(dev, runtime_resume);
+	callback = GET_CALLBACK(dev, runtime_resume);
 
 	dev_pm_disable_wake_irq_check(dev, false);
 	ret = callback ? callback(dev) : 0;
@@ -2046,9 +2083,30 @@ int pm_runtime_force_resume(struct device *dev)
 	}
 
 	pm_runtime_mark_last_busy(dev);
+
 out:
-	dev->power.needs_force_resume = 0;
+	/*
+	 * The smart_suspend flag can be cleared here because it is not going
+	 * to be necessary until the next system-wide suspend transition that
+	 * will update it again.
+	 */
+	dev->power.smart_suspend = false;
+	/*
+	 * Also clear needs_force_resume to make this function skip devices that
+	 * have been seen by it once.
+	 */
+	dev->power.needs_force_resume = false;
+
 	pm_runtime_enable(dev);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pm_runtime_force_resume);
+
+bool pm_runtime_need_not_resume(struct device *dev)
+{
+	return atomic_read(&dev->power.usage_count) <= 1 &&
+		(atomic_read(&dev->power.child_count) == 0 ||
+		 dev->power.ignore_children);
+}
+
+#endif /* CONFIG_PM_SLEEP */