PM / core: Add LEAVE_SUSPENDED driver flag

Define and document a new driver flag, DPM_FLAG_LEAVE_SUSPENDED, to
instruct the PM core and middle-layer (bus type, PM domain, etc.)
code that it is desirable to leave the device in runtime suspend
after system-wide transitions to the working state (for example,
the device may be slow to resume and it may be better to avoid
resuming it right away).

Generally, the middle-layer code involved in the handling of the
device is expected to indicate to the PM core whether or not the
device may be left in suspend with the help of the device's
power.may_skip_resume status bit.  That has to happen in the "noirq"
phase of the preceding system suspend (or analogous) transition.
The middle layer is then responsible for handling the device as
appropriate in its "noirq" resume callback which is executed
regardless of whether or not the device may be left suspended, but
the other resume callbacks (except for ->complete) will be skipped
automatically by the core if the device really can be left in
suspend.

The additional power.must_resume status bit introduced for the
implementation of this mechanisn is used internally by the PM core
to track the requirement to resume the device (which may depend on
its children etc).

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>

1 files changed, 68 insertions, 5 deletions

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index db2f04415927..73ec6796d9e1 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -526,6 +526,18 @@ static void dpm_watchdog_clear(struct dpm_watchdog *wd)
 /*------------------------- Resume routines -------------------------*/
 
 /**
+ * dev_pm_may_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.
+ */
+bool dev_pm_may_skip_resume(struct device *dev)
+{
+	return !dev->power.must_resume && pm_transition.event != PM_EVENT_RESTORE;
+}
+
+/**
  * device_resume_noirq - Execute a "noirq resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
@@ -573,6 +585,19 @@ static int device_resume_noirq(struct device *dev, pm_message_t state, bool asyn
 	error = dpm_run_callback(callback, dev, state, info);
 	dev->power.is_noirq_suspended = false;
 
+	if (dev_pm_may_skip_resume(dev)) {
+		/*
+		 * 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);
+		dev->power.is_late_suspended = false;
+		dev->power.is_suspended = false;
+	}
+
  Out:
 	complete_all(&dev->power.completion);
 	TRACE_RESUME(error);
@@ -1074,6 +1099,22 @@ static pm_message_t resume_event(pm_message_t sleep_state)
 	return PMSG_ON;
 }
 
+static void dpm_superior_set_must_resume(struct device *dev)
+{
+	struct device_link *link;
+	int idx;
+
+	if (dev->parent)
+		dev->parent->power.must_resume = true;
+
+	idx = device_links_read_lock();
+
+	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+		link->supplier->power.must_resume = true;
+
+	device_links_read_unlock(idx);
+}
+
 /**
  * __device_suspend_noirq - Execute a "noirq suspend" callback for given device.
  * @dev: Device to handle.
@@ -1125,10 +1166,28 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a
 	}
 
 	error = dpm_run_callback(callback, dev, state, info);
-	if (!error)
-		dev->power.is_noirq_suspended = true;
-	else
+	if (error) {
 		async_error = error;
+		goto Complete;
+	}
+
+	dev->power.is_noirq_suspended = true;
+
+	if (dev_pm_test_driver_flags(dev, DPM_FLAG_LEAVE_SUSPENDED)) {
+		/*
+		 * 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.
+		 */
+		dev->power.must_resume = dev->power.must_resume ||
+					!dev->power.may_skip_resume ||
+					atomic_read(&dev->power.usage_count) > 1;
+	} else {
+		dev->power.must_resume = true;
+	}
+
+	if (dev->power.must_resume)
+		dpm_superior_set_must_resume(dev);
 
 Complete:
 	complete_all(&dev->power.completion);
@@ -1485,6 +1544,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 		dev->power.direct_complete = false;
 	}
 
+	dev->power.may_skip_resume = false;
+	dev->power.must_resume = false;
+
 	dpm_watchdog_set(&wd, dev);
 	device_lock(dev);
 
@@ -1650,8 +1712,9 @@ static int device_prepare(struct device *dev, pm_message_t state)
 	if (dev->power.syscore)
 		return 0;
 
-	WARN_ON(dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) &&
-		!pm_runtime_enabled(dev));
+	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,