1 files changed, 220 insertions, 50 deletions

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 3148b10dc2e..67c7938e430 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -13,6 +13,43 @@
 #include <trace/events/rpm.h>
 #include "power.h"
 
+#define RPM_GET_CALLBACK(dev, cb)				\
+({								\
+	int (*__rpm_cb)(struct device *__d);			\
+								\
+	if (dev->pm_domain)					\
+		__rpm_cb = dev->pm_domain->ops.cb;		\
+	else if (dev->type && dev->type->pm)			\
+		__rpm_cb = dev->type->pm->cb;			\
+	else if (dev->class && dev->class->pm)			\
+		__rpm_cb = dev->class->pm->cb;			\
+	else if (dev->bus && dev->bus->pm)			\
+		__rpm_cb = dev->bus->pm->cb;			\
+	else							\
+		__rpm_cb = NULL;				\
+								\
+	if (!__rpm_cb && dev->driver && dev->driver->pm)	\
+		__rpm_cb = dev->driver->pm->cb;			\
+								\
+	__rpm_cb;						\
+})
+
+static int (*rpm_get_suspend_cb(struct device *dev))(struct device *)
+{
+	return RPM_GET_CALLBACK(dev, runtime_suspend);
+}
+
+static int (*rpm_get_resume_cb(struct device *dev))(struct device *)
+{
+	return RPM_GET_CALLBACK(dev, runtime_resume);
+}
+
+#ifdef CONFIG_PM_RUNTIME
+static int (*rpm_get_idle_cb(struct device *dev))(struct device *)
+{
+	return RPM_GET_CALLBACK(dev, runtime_idle);
+}
+
 static int rpm_resume(struct device *dev, int rpmflags);
 static int rpm_suspend(struct device *dev, int rpmflags);
 
@@ -124,6 +161,76 @@ unsigned long pm_runtime_autosuspend_expiration(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
 
+static int dev_memalloc_noio(struct device *dev, void *data)
+{
+	return dev->power.memalloc_noio;
+}
+
+/*
+ * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag.
+ * @dev: Device to handle.
+ * @enable: True for setting the flag and False for clearing the flag.
+ *
+ * Set the flag for all devices in the path from the device to the
+ * root device in the device tree if @enable is true, otherwise clear
+ * the flag for devices in the path whose siblings don't set the flag.
+ *
+ * The function should only be called by block device, or network
+ * device driver for solving the deadlock problem during runtime
+ * resume/suspend:
+ *
+ *     If memory allocation with GFP_KERNEL is called inside runtime
+ *     resume/suspend callback of any one of its ancestors(or the
+ *     block device itself), the deadlock may be triggered inside the
+ *     memory allocation since it might not complete until the block
+ *     device becomes active and the involed page I/O finishes. The
+ *     situation is pointed out first by Alan Stern. Network device
+ *     are involved in iSCSI kind of situation.
+ *
+ * The lock of dev_hotplug_mutex is held in the function for handling
+ * hotplug race because pm_runtime_set_memalloc_noio() may be called
+ * in async probe().
+ *
+ * The function should be called between device_add() and device_del()
+ * on the affected device(block/network device).
+ */
+void pm_runtime_set_memalloc_noio(struct device *dev, bool enable)
+{
+	static DEFINE_MUTEX(dev_hotplug_mutex);
+
+	mutex_lock(&dev_hotplug_mutex);
+	for (;;) {
+		bool enabled;
+
+		/* hold power lock since bitfield is not SMP-safe. */
+		spin_lock_irq(&dev->power.lock);
+		enabled = dev->power.memalloc_noio;
+		dev->power.memalloc_noio = enable;
+		spin_unlock_irq(&dev->power.lock);
+
+		/*
+		 * not need to enable ancestors any more if the device
+		 * has been enabled.
+		 */
+		if (enabled && enable)
+			break;
+
+		dev = dev->parent;
+
+		/*
+		 * clear flag of the parent device only if all the
+		 * children don't set the flag because ancestor's
+		 * flag was set by any one of the descendants.
+		 */
+		if (!dev || (!enable &&
+			     device_for_each_child(dev, NULL,
+						   dev_memalloc_noio)))
+			break;
+	}
+	mutex_unlock(&dev_hotplug_mutex);
+}
+EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio);
+
 /**
  * rpm_check_suspend_allowed - Test whether a device may be suspended.
  * @dev: Device to test.
@@ -188,7 +295,8 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
  * Check if the device's runtime PM status allows it to be suspended.  If
  * another idle notification has been started earlier, return immediately.  If
  * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise
- * run the ->runtime_idle() callback directly.
+ * run the ->runtime_idle() callback directly. If the ->runtime_idle callback
+ * doesn't exist or if it returns 0, call rpm_suspend with the RPM_AUTO flag.
  *
  * This function must be called under dev->power.lock with interrupts disabled.
  */
@@ -223,11 +331,8 @@ static int rpm_idle(struct device *dev, int rpmflags)
 	/* Pending requests need to be canceled. */
 	dev->power.request = RPM_REQ_NONE;
 
-	if (dev->power.no_callbacks) {
-		/* Assume ->runtime_idle() callback would have suspended. */
-		retval = rpm_suspend(dev, rpmflags);
+	if (dev->power.no_callbacks)
 		goto out;
-	}
 
 	/* Carry out an asynchronous or a synchronous idle notification. */
 	if (rpmflags & RPM_ASYNC) {
@@ -236,34 +341,23 @@ static int rpm_idle(struct device *dev, int rpmflags)
 			dev->power.request_pending = true;
 			queue_work(pm_wq, &dev->power.work);
 		}
-		goto out;
+		trace_rpm_return_int(dev, _THIS_IP_, 0);
+		return 0;
 	}
 
 	dev->power.idle_notification = true;
 
-	if (dev->pm_domain)
-		callback = dev->pm_domain->ops.runtime_idle;
-	else if (dev->type && dev->type->pm)
-		callback = dev->type->pm->runtime_idle;
-	else if (dev->class && dev->class->pm)
-		callback = dev->class->pm->runtime_idle;
-	else if (dev->bus && dev->bus->pm)
-		callback = dev->bus->pm->runtime_idle;
-	else
-		callback = NULL;
-
-	if (!callback && dev->driver && dev->driver->pm)
-		callback = dev->driver->pm->runtime_idle;
+	callback = rpm_get_idle_cb(dev);
 
 	if (callback)
-		__rpm_callback(callback, dev);
+		retval = __rpm_callback(callback, dev);
 
 	dev->power.idle_notification = false;
 	wake_up_all(&dev->power.wait_queue);
 
  out:
 	trace_rpm_return_int(dev, _THIS_IP_, retval);
-	return retval;
+	return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO);
 }
 
 /**
@@ -278,7 +372,24 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev)
 	if (!cb)
 		return -ENOSYS;
 
-	retval = __rpm_callback(cb, dev);
+	if (dev->power.memalloc_noio) {
+		unsigned int noio_flag;
+
+		/*
+		 * Deadlock might be caused if memory allocation with
+		 * GFP_KERNEL happens inside runtime_suspend and
+		 * runtime_resume callbacks of one block device's
+		 * ancestor or the block device itself. Network
+		 * device might be thought as part of iSCSI block
+		 * device, so network device and its ancestor should
+		 * be marked as memalloc_noio too.
+		 */
+		noio_flag = memalloc_noio_save();
+		retval = __rpm_callback(cb, dev);
+		memalloc_noio_restore(noio_flag);
+	} else {
+		retval = __rpm_callback(cb, dev);
+	}
 
 	dev->power.runtime_error = retval;
 	return retval != -EACCES ? retval : -EIO;
@@ -406,19 +517,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
 	__update_runtime_status(dev, RPM_SUSPENDING);
 
-	if (dev->pm_domain)
-		callback = dev->pm_domain->ops.runtime_suspend;
-	else if (dev->type && dev->type->pm)
-		callback = dev->type->pm->runtime_suspend;
-	else if (dev->class && dev->class->pm)
-		callback = dev->class->pm->runtime_suspend;
-	else if (dev->bus && dev->bus->pm)
-		callback = dev->bus->pm->runtime_suspend;
-	else
-		callback = NULL;
-
-	if (!callback && dev->driver && dev->driver->pm)
-		callback = dev->driver->pm->runtime_suspend;
+	callback = rpm_get_suspend_cb(dev);
 
 	retval = rpm_callback(callback, dev);
 	if (retval)
@@ -638,19 +737,7 @@ static int rpm_resume(struct device *dev, int rpmflags)
 
 	__update_runtime_status(dev, RPM_RESUMING);
 
-	if (dev->pm_domain)
-		callback = dev->pm_domain->ops.runtime_resume;
-	else if (dev->type && dev->type->pm)
-		callback = dev->type->pm->runtime_resume;
-	else if (dev->class && dev->class->pm)
-		callback = dev->class->pm->runtime_resume;
-	else if (dev->bus && dev->bus->pm)
-		callback = dev->bus->pm->runtime_resume;
-	else
-		callback = NULL;
-
-	if (!callback && dev->driver && dev->driver->pm)
-		callback = dev->driver->pm->runtime_resume;
+	callback = rpm_get_resume_cb(dev);
 
 	retval = rpm_callback(callback, dev);
 	if (retval) {
@@ -1044,7 +1131,7 @@ EXPORT_SYMBOL_GPL(pm_runtime_barrier);
  * @dev: Device to handle.
  * @check_resume: If set, check if there's a resume request for the device.
  *
- * Increment power.disable_depth for the device and if was zero previously,
+ * Increment power.disable_depth for the device and if it was zero previously,
  * cancel all pending runtime PM requests for the device and wait for all
  * operations in progress to complete.  The device can be either active or
  * suspended after its runtime PM has been disabled.
@@ -1313,5 +1400,88 @@ void pm_runtime_remove(struct device *dev)
 	if (dev->power.runtime_status == RPM_ACTIVE)
 		pm_runtime_set_suspended(dev);
 	if (dev->power.irq_safe && dev->parent)
-		pm_runtime_put_sync(dev->parent);
+		pm_runtime_put(dev->parent);
+}
+#endif
+
+/**
+ * pm_runtime_force_suspend - Force a device into suspend state if needed.
+ * @dev: Device to suspend.
+ *
+ * Disable runtime PM so we safely can check the device's runtime PM status and
+ * if it is active, invoke it's .runtime_suspend callback to bring it into
+ * suspend state. Keep runtime PM disabled to preserve the state unless we
+ * encounter errors.
+ *
+ * Typically this function may be invoked from a system suspend callback to make
+ * sure the device is put into low power state.
+ */
+int pm_runtime_force_suspend(struct device *dev)
+{
+	int (*callback)(struct device *);
+	int ret = 0;
+
+	pm_runtime_disable(dev);
+
+	/*
+	 * Note that pm_runtime_status_suspended() returns false while
+	 * !CONFIG_PM_RUNTIME, which means the device will be put into low
+	 * power state.
+	 */
+	if (pm_runtime_status_suspended(dev))
+		return 0;
+
+	callback = rpm_get_suspend_cb(dev);
+
+	if (!callback) {
+		ret = -ENOSYS;
+		goto err;
+	}
+
+	ret = callback(dev);
+	if (ret)
+		goto err;
+
+	pm_runtime_set_suspended(dev);
+	return 0;
+err:
+	pm_runtime_enable(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_force_suspend);
+
+/**
+ * pm_runtime_force_resume - Force a device into resume state.
+ * @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 brings the device into full power. We update the runtime PM
+ * status and re-enables runtime PM.
+ *
+ * Typically this function may be invoked from a system resume callback to make
+ * sure the device is put into full power state.
+ */
+int pm_runtime_force_resume(struct device *dev)
+{
+	int (*callback)(struct device *);
+	int ret = 0;
+
+	callback = rpm_get_resume_cb(dev);
+
+	if (!callback) {
+		ret = -ENOSYS;
+		goto out;
+	}
+
+	ret = callback(dev);
+	if (ret)
+		goto out;
+
+	pm_runtime_set_active(dev);
+	pm_runtime_mark_last_busy(dev);
+out:
+	pm_runtime_enable(dev);
+	return ret;
 }
+EXPORT_SYMBOL_GPL(pm_runtime_force_resume);