Merge tag 'pm-for-3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates for 3.4 from Rafael Wysocki:
 "Assorted extensions and fixes including:

  * Introduction of early/late suspend/hibernation device callbacks.
  * Generic PM domains extensions and fixes.
  * devfreq updates from Axel Lin and MyungJoo Ham.
  * Device PM QoS updates.
  * Fixes of concurrency problems with wakeup sources.
  * System suspend and hibernation fixes."

* tag 'pm-for-3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (43 commits)
  PM / Domains: Check domain status during hibernation restore of devices
  PM / devfreq: add relation of recommended frequency.
  PM / shmobile: Make MTU2 driver use pm_genpd_dev_always_on()
  PM / shmobile: Make CMT driver use pm_genpd_dev_always_on()
  PM / shmobile: Make TMU driver use pm_genpd_dev_always_on()
  PM / Domains: Introduce "always on" device flag
  PM / Domains: Fix hibernation restore of devices, v2
  PM / Domains: Fix handling of wakeup devices during system resume
  sh_mmcif / PM: Use PM QoS latency constraint
  tmio_mmc / PM: Use PM QoS latency constraint
  PM / QoS: Make it possible to expose PM QoS latency constraints
  PM / Sleep: JBD and JBD2 missing set_freezable()
  PM / Domains: Fix include for PM_GENERIC_DOMAINS=n case
  PM / Freezer: Remove references to TIF_FREEZE in comments
  PM / Sleep: Add more wakeup source initialization routines
  PM / Hibernate: Enable usermodehelpers in hibernate() error path
  PM / Sleep: Make __pm_stay_awake() delete wakeup source timers
  PM / Sleep: Fix race conditions related to wakeup source timer function
  PM / Sleep: Fix possible infinite loop during wakeup source destruction
  PM / Hibernate: print physical addresses consistently with other parts of kernel
  ...

19 files changed, 869 insertions, 182 deletions

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 978bbf7ac6af..73ce9fbe9839 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -366,7 +366,7 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 	not_suspended = 0;
 	list_for_each_entry(pdd, &genpd->dev_list, list_node)
 		if (pdd->dev->driver && (!pm_runtime_suspended(pdd->dev)
-		    || pdd->dev->power.irq_safe))
+		    || pdd->dev->power.irq_safe || to_gpd_data(pdd)->always_on))
 			not_suspended++;
 
 	if (not_suspended > genpd->in_progress)
@@ -503,6 +503,9 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 
 	might_sleep_if(!genpd->dev_irq_safe);
 
+	if (dev_gpd_data(dev)->always_on)
+		return -EBUSY;
+
 	stop_ok = genpd->gov ? genpd->gov->stop_ok : NULL;
 	if (stop_ok && !stop_ok(dev))
 		return -EBUSY;
@@ -764,8 +767,10 @@ static int pm_genpd_prepare(struct device *dev)
 
 	genpd_acquire_lock(genpd);
 
-	if (genpd->prepared_count++ == 0)
+	if (genpd->prepared_count++ == 0) {
+		genpd->suspended_count = 0;
 		genpd->suspend_power_off = genpd->status == GPD_STATE_POWER_OFF;
+	}
 
 	genpd_release_lock(genpd);
 
@@ -820,17 +825,16 @@ static int pm_genpd_suspend(struct device *dev)
 }
 
 /**
- * pm_genpd_suspend_noirq - Late suspend of a device from an I/O PM domain.
+ * pm_genpd_suspend_late - Late suspend of a device from an I/O PM domain.
  * @dev: Device to suspend.
  *
  * Carry out a late suspend of a device under the assumption that its
  * pm_domain field points to the domain member of an object of type
  * struct generic_pm_domain representing a PM domain consisting of I/O devices.
  */
-static int pm_genpd_suspend_noirq(struct device *dev)
+static int pm_genpd_suspend_late(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	int ret;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -838,14 +842,28 @@ static int pm_genpd_suspend_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (genpd->suspend_power_off)
-		return 0;
+	return genpd->suspend_power_off ? 0 : genpd_suspend_late(genpd, dev);
+}
 
-	ret = genpd_suspend_late(genpd, dev);
-	if (ret)
-		return ret;
+/**
+ * pm_genpd_suspend_noirq - Completion of suspend of device in an I/O PM domain.
+ * @dev: Device to suspend.
+ *
+ * Stop the device and remove power from the domain if all devices in it have
+ * been stopped.
+ */
+static int pm_genpd_suspend_noirq(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
 
-	if (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	if (genpd->suspend_power_off || dev_gpd_data(dev)->always_on
+	    || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev)))
 		return 0;
 
 	genpd_stop_dev(genpd, dev);
@@ -862,13 +880,10 @@ static int pm_genpd_suspend_noirq(struct device *dev)
 }
 
 /**
- * pm_genpd_resume_noirq - Early resume of a device from an I/O power domain.
+ * pm_genpd_resume_noirq - Start of resume of device in an I/O PM domain.
  * @dev: Device to resume.
  *
- * Carry out an early resume of a device under the assumption that its
- * pm_domain field points to the domain member of an object of type
- * struct generic_pm_domain representing a power domain consisting of I/O
- * devices.
+ * Restore power to the device's PM domain, if necessary, and start the device.
  */
 static int pm_genpd_resume_noirq(struct device *dev)
 {
@@ -880,7 +895,8 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (genpd->suspend_power_off)
+	if (genpd->suspend_power_off || dev_gpd_data(dev)->always_on
+	    || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev)))
 		return 0;
 
 	/*
@@ -890,13 +906,34 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	 */
 	pm_genpd_poweron(genpd);
 	genpd->suspended_count--;
-	genpd_start_dev(genpd, dev);
 
-	return genpd_resume_early(genpd, dev);
+	return genpd_start_dev(genpd, dev);
 }
 
 /**
- * pm_genpd_resume - Resume a device belonging to an I/O power domain.
+ * pm_genpd_resume_early - Early resume of a device in an I/O PM domain.
+ * @dev: Device to resume.
+ *
+ * Carry out an early resume of a device under the assumption that its
+ * pm_domain field points to the domain member of an object of type
+ * struct generic_pm_domain representing a power domain consisting of I/O
+ * devices.
+ */
+static int pm_genpd_resume_early(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : genpd_resume_early(genpd, dev);
+}
+
+/**
+ * pm_genpd_resume - Resume of device in an I/O PM domain.
  * @dev: Device to resume.
  *
  * Resume a device under the assumption that its pm_domain field points to the
@@ -917,7 +954,7 @@ static int pm_genpd_resume(struct device *dev)
 }
 
 /**
- * pm_genpd_freeze - Freeze a device belonging to an I/O power domain.
+ * pm_genpd_freeze - Freezing a device in an I/O PM domain.
  * @dev: Device to freeze.
  *
  * Freeze a device under the assumption that its pm_domain field points to the
@@ -938,7 +975,29 @@ static int pm_genpd_freeze(struct device *dev)
 }
 
 /**
- * pm_genpd_freeze_noirq - Late freeze of a device from an I/O power domain.
+ * pm_genpd_freeze_late - Late freeze of a device in an I/O PM domain.
+ * @dev: Device to freeze.
+ *
+ * Carry out a late freeze of a device under the assumption that its
+ * pm_domain field points to the domain member of an object of type
+ * struct generic_pm_domain representing a power domain consisting of I/O
+ * devices.
+ */
+static int pm_genpd_freeze_late(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off ? 0 : genpd_freeze_late(genpd, dev);
+}
+
+/**
+ * pm_genpd_freeze_noirq - Completion of freezing a device in an I/O PM domain.
  * @dev: Device to freeze.
  *
  * Carry out a late freeze of a device under the assumption that its
@@ -949,7 +1008,6 @@ static int pm_genpd_freeze(struct device *dev)
 static int pm_genpd_freeze_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	int ret;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -957,20 +1015,33 @@ static int pm_genpd_freeze_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (genpd->suspend_power_off)
-		return 0;
+	return genpd->suspend_power_off || dev_gpd_data(dev)->always_on ?
+		0 : genpd_stop_dev(genpd, dev);
+}
 
-	ret = genpd_freeze_late(genpd, dev);
-	if (ret)
-		return ret;
+/**
+ * pm_genpd_thaw_noirq - Early thaw of device in an I/O PM domain.
+ * @dev: Device to thaw.
+ *
+ * Start the device, unless power has been removed from the domain already
+ * before the system transition.
+ */
+static int pm_genpd_thaw_noirq(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
 
-	genpd_stop_dev(genpd, dev);
+	dev_dbg(dev, "%s()\n", __func__);
 
-	return 0;
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -EINVAL;
+
+	return genpd->suspend_power_off || dev_gpd_data(dev)->always_on ?
+		0 : genpd_start_dev(genpd, dev);
 }
 
 /**
- * pm_genpd_thaw_noirq - Early thaw of a device from an I/O power domain.
+ * pm_genpd_thaw_early - Early thaw of device in an I/O PM domain.
  * @dev: Device to thaw.
  *
  * Carry out an early thaw of a device under the assumption that its
@@ -978,7 +1049,7 @@ static int pm_genpd_freeze_noirq(struct device *dev)
  * struct generic_pm_domain representing a power domain consisting of I/O
  * devices.
  */
-static int pm_genpd_thaw_noirq(struct device *dev)
+static int pm_genpd_thaw_early(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
 
@@ -988,12 +1059,7 @@ static int pm_genpd_thaw_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (genpd->suspend_power_off)
-		return 0;
-
-	genpd_start_dev(genpd, dev);
-
-	return genpd_thaw_early(genpd, dev);
+	return genpd->suspend_power_off ? 0 : genpd_thaw_early(genpd, dev);
 }
 
 /**
@@ -1018,13 +1084,11 @@ static int pm_genpd_thaw(struct device *dev)
 }
 
 /**
- * pm_genpd_restore_noirq - Early restore of a device from an I/O power domain.
+ * pm_genpd_restore_noirq - Start of restore of device in an I/O PM domain.
  * @dev: Device to resume.
  *
- * Carry out an early restore of a device under the assumption that its
- * pm_domain field points to the domain member of an object of type
- * struct generic_pm_domain representing a power domain consisting of I/O
- * devices.
+ * Make sure the domain will be in the same power state as before the
+ * hibernation the system is resuming from and start the device if necessary.
  */
 static int pm_genpd_restore_noirq(struct device *dev)
 {
@@ -1040,23 +1104,35 @@ static int pm_genpd_restore_noirq(struct device *dev)
 	 * Since all of the "noirq" callbacks are executed sequentially, it is
 	 * guaranteed that this function will never run twice in parallel for
 	 * the same PM domain, so it is not necessary to use locking here.
+	 *
+	 * At this point suspended_count == 0 means we are being run for the
+	 * first time for the given domain in the present cycle.
 	 */
-	genpd->status = GPD_STATE_POWER_OFF;
-	if (genpd->suspend_power_off) {
+	if (genpd->suspended_count++ == 0) {
 		/*
-		 * The boot kernel might put the domain into the power on state,
-		 * so make sure it really is powered off.
+		 * The boot kernel might put the domain into arbitrary state,
+		 * so make it appear as powered off to pm_genpd_poweron(), so
+		 * that it tries to power it on in case it was really off.
 		 */
-		if (genpd->power_off)
-			genpd->power_off(genpd);
-		return 0;
+		genpd->status = GPD_STATE_POWER_OFF;
+		if (genpd->suspend_power_off) {
+			/*
+			 * If the domain was off before the hibernation, make
+			 * sure it will be off going forward.
+			 */
+			if (genpd->power_off)
+				genpd->power_off(genpd);
+
+			return 0;
+		}
 	}
 
+	if (genpd->suspend_power_off)
+		return 0;
+
 	pm_genpd_poweron(genpd);
-	genpd->suspended_count--;
-	genpd_start_dev(genpd, dev);
 
-	return genpd_resume_early(genpd, dev);
+	return dev_gpd_data(dev)->always_on ? 0 : genpd_start_dev(genpd, dev);
 }
 
 /**
@@ -1099,11 +1175,15 @@ static void pm_genpd_complete(struct device *dev)
 
 #define pm_genpd_prepare		NULL
 #define pm_genpd_suspend		NULL
+#define pm_genpd_suspend_late		NULL
 #define pm_genpd_suspend_noirq		NULL
+#define pm_genpd_resume_early		NULL
 #define pm_genpd_resume_noirq		NULL
 #define pm_genpd_resume			NULL
 #define pm_genpd_freeze			NULL
+#define pm_genpd_freeze_late		NULL
 #define pm_genpd_freeze_noirq		NULL
+#define pm_genpd_thaw_early		NULL
 #define pm_genpd_thaw_noirq		NULL
 #define pm_genpd_thaw			NULL
 #define pm_genpd_restore_noirq		NULL
@@ -1171,6 +1251,38 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 }
 
 /**
+ * __pm_genpd_of_add_device - Add a device to an I/O PM domain.
+ * @genpd_node: Device tree node pointer representing a PM domain to which the
+ *   the device is added to.
+ * @dev: Device to be added.
+ * @td: Set of PM QoS timing parameters to attach to the device.
+ */
+int __pm_genpd_of_add_device(struct device_node *genpd_node, struct device *dev,
+			     struct gpd_timing_data *td)
+{
+	struct generic_pm_domain *genpd = NULL, *gpd;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (IS_ERR_OR_NULL(genpd_node) || IS_ERR_OR_NULL(dev))
+		return -EINVAL;
+
+	mutex_lock(&gpd_list_lock);
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+		if (gpd->of_node == genpd_node) {
+			genpd = gpd;
+			break;
+		}
+	}
+	mutex_unlock(&gpd_list_lock);
+
+	if (!genpd)
+		return -EINVAL;
+
+	return __pm_genpd_add_device(genpd, dev, td);
+}
+
+/**
  * pm_genpd_remove_device - Remove a device from an I/O PM domain.
  * @genpd: PM domain to remove the device from.
  * @dev: Device to be removed.
@@ -1216,6 +1328,26 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 }
 
 /**
+ * pm_genpd_dev_always_on - Set/unset the "always on" flag for a given device.
+ * @dev: Device to set/unset the flag for.
+ * @val: The new value of the device's "always on" flag.
+ */
+void pm_genpd_dev_always_on(struct device *dev, bool val)
+{
+	struct pm_subsys_data *psd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	psd = dev_to_psd(dev);
+	if (psd && psd->domain_data)
+		to_gpd_data(psd->domain_data)->always_on = val;
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_genpd_dev_always_on);
+
+/**
  * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain.
  * @genpd: Master PM domain to add the subdomain to.
  * @subdomain: Subdomain to be added.
@@ -1450,7 +1582,7 @@ static int pm_genpd_default_suspend_late(struct device *dev)
 {
 	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.suspend_late;
 
-	return cb ? cb(dev) : pm_generic_suspend_noirq(dev);
+	return cb ? cb(dev) : pm_generic_suspend_late(dev);
 }
 
 /**
@@ -1461,7 +1593,7 @@ static int pm_genpd_default_resume_early(struct device *dev)
 {
 	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.resume_early;
 
-	return cb ? cb(dev) : pm_generic_resume_noirq(dev);
+	return cb ? cb(dev) : pm_generic_resume_early(dev);
 }
 
 /**
@@ -1494,7 +1626,7 @@ static int pm_genpd_default_freeze_late(struct device *dev)
 {
 	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.freeze_late;
 
-	return cb ? cb(dev) : pm_generic_freeze_noirq(dev);
+	return cb ? cb(dev) : pm_generic_freeze_late(dev);
 }
 
 /**
@@ -1505,7 +1637,7 @@ static int pm_genpd_default_thaw_early(struct device *dev)
 {
 	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.thaw_early;
 
-	return cb ? cb(dev) : pm_generic_thaw_noirq(dev);
+	return cb ? cb(dev) : pm_generic_thaw_early(dev);
 }
 
 /**
@@ -1557,23 +1689,28 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->poweroff_task = NULL;
 	genpd->resume_count = 0;
 	genpd->device_count = 0;
-	genpd->suspended_count = 0;
 	genpd->max_off_time_ns = -1;
 	genpd->domain.ops.runtime_suspend = pm_genpd_runtime_suspend;
 	genpd->domain.ops.runtime_resume = pm_genpd_runtime_resume;
 	genpd->domain.ops.runtime_idle = pm_generic_runtime_idle;
 	genpd->domain.ops.prepare = pm_genpd_prepare;
 	genpd->domain.ops.suspend = pm_genpd_suspend;
+	genpd->domain.ops.suspend_late = pm_genpd_suspend_late;
 	genpd->domain.ops.suspend_noirq = pm_genpd_suspend_noirq;
 	genpd->domain.ops.resume_noirq = pm_genpd_resume_noirq;
+	genpd->domain.ops.resume_early = pm_genpd_resume_early;
 	genpd->domain.ops.resume = pm_genpd_resume;
 	genpd->domain.ops.freeze = pm_genpd_freeze;
+	genpd->domain.ops.freeze_late = pm_genpd_freeze_late;
 	genpd->domain.ops.freeze_noirq = pm_genpd_freeze_noirq;
 	genpd->domain.ops.thaw_noirq = pm_genpd_thaw_noirq;
+	genpd->domain.ops.thaw_early = pm_genpd_thaw_early;
 	genpd->domain.ops.thaw = pm_genpd_thaw;
 	genpd->domain.ops.poweroff = pm_genpd_suspend;
+	genpd->domain.ops.poweroff_late = pm_genpd_suspend_late;
 	genpd->domain.ops.poweroff_noirq = pm_genpd_suspend_noirq;
 	genpd->domain.ops.restore_noirq = pm_genpd_restore_noirq;
+	genpd->domain.ops.restore_early = pm_genpd_resume_early;
 	genpd->domain.ops.restore = pm_genpd_resume;
 	genpd->domain.ops.complete = pm_genpd_complete;
 	genpd->dev_ops.save_state = pm_genpd_default_save_state;
diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c
index 10bdd793f0bd..d03d290f31c2 100644
--- a/drivers/base/power/generic_ops.c
+++ b/drivers/base/power/generic_ops.c
@@ -92,59 +92,28 @@ int pm_generic_prepare(struct device *dev)
 }
 
 /**
- * __pm_generic_call - Generic suspend/freeze/poweroff/thaw subsystem callback.
- * @dev: Device to handle.
- * @event: PM transition of the system under way.
- * @bool: Whether or not this is the "noirq" stage.
- *
- * Execute the PM callback corresponding to @event provided by the driver of
- * @dev, if defined, and return its error code.    Return 0 if the callback is
- * not present.
+ * pm_generic_suspend_noirq - Generic suspend_noirq callback for subsystems.
+ * @dev: Device to suspend.
  */
-static int __pm_generic_call(struct device *dev, int event, bool noirq)
+int pm_generic_suspend_noirq(struct device *dev)
 {
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
-	int (*callback)(struct device *);
-
-	if (!pm)
-		return 0;
-
-	switch (event) {
-	case PM_EVENT_SUSPEND:
-		callback = noirq ? pm->suspend_noirq : pm->suspend;
-		break;
-	case PM_EVENT_FREEZE:
-		callback = noirq ? pm->freeze_noirq : pm->freeze;
-		break;
-	case PM_EVENT_HIBERNATE:
-		callback = noirq ? pm->poweroff_noirq : pm->poweroff;
-		break;
-	case PM_EVENT_RESUME:
-		callback = noirq ? pm->resume_noirq : pm->resume;
-		break;
-	case PM_EVENT_THAW:
-		callback = noirq ? pm->thaw_noirq : pm->thaw;
-		break;
-	case PM_EVENT_RESTORE:
-		callback = noirq ? pm->restore_noirq : pm->restore;
-		break;
-	default:
-		callback = NULL;
-		break;
-	}
 
-	return callback ? callback(dev) : 0;
+	return pm && pm->suspend_noirq ? pm->suspend_noirq(dev) : 0;
 }
+EXPORT_SYMBOL_GPL(pm_generic_suspend_noirq);
 
 /**
- * pm_generic_suspend_noirq - Generic suspend_noirq callback for subsystems.
+ * pm_generic_suspend_late - Generic suspend_late callback for subsystems.
  * @dev: Device to suspend.
  */
-int pm_generic_suspend_noirq(struct device *dev)
+int pm_generic_suspend_late(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_SUSPEND, true);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->suspend_late ? pm->suspend_late(dev) : 0;
 }
-EXPORT_SYMBOL_GPL(pm_generic_suspend_noirq);
+EXPORT_SYMBOL_GPL(pm_generic_suspend_late);
 
 /**
  * pm_generic_suspend - Generic suspend callback for subsystems.
@@ -152,7 +121,9 @@ EXPORT_SYMBOL_GPL(pm_generic_suspend_noirq);
  */
 int pm_generic_suspend(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_SUSPEND, false);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->suspend ? pm->suspend(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_suspend);
 
@@ -162,17 +133,33 @@ EXPORT_SYMBOL_GPL(pm_generic_suspend);
  */
 int pm_generic_freeze_noirq(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_FREEZE, true);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->freeze_noirq ? pm->freeze_noirq(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_freeze_noirq);
 
 /**
+ * pm_generic_freeze_late - Generic freeze_late callback for subsystems.
+ * @dev: Device to freeze.
+ */
+int pm_generic_freeze_late(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->freeze_late ? pm->freeze_late(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_freeze_late);
+
+/**
  * pm_generic_freeze - Generic freeze callback for subsystems.
  * @dev: Device to freeze.
  */
 int pm_generic_freeze(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_FREEZE, false);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->freeze ? pm->freeze(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_freeze);
 
@@ -182,17 +169,33 @@ EXPORT_SYMBOL_GPL(pm_generic_freeze);
  */
 int pm_generic_poweroff_noirq(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_HIBERNATE, true);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->poweroff_noirq ? pm->poweroff_noirq(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_poweroff_noirq);
 
 /**
+ * pm_generic_poweroff_late - Generic poweroff_late callback for subsystems.
+ * @dev: Device to handle.
+ */
+int pm_generic_poweroff_late(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->poweroff_late ? pm->poweroff_late(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_poweroff_late);
+
+/**
  * pm_generic_poweroff - Generic poweroff callback for subsystems.
  * @dev: Device to handle.
  */
 int pm_generic_poweroff(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_HIBERNATE, false);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->poweroff ? pm->poweroff(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_poweroff);
 
@@ -202,17 +205,33 @@ EXPORT_SYMBOL_GPL(pm_generic_poweroff);
  */
 int pm_generic_thaw_noirq(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_THAW, true);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->thaw_noirq ? pm->thaw_noirq(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_thaw_noirq);
 
 /**
+ * pm_generic_thaw_early - Generic thaw_early callback for subsystems.
+ * @dev: Device to thaw.
+ */
+int pm_generic_thaw_early(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->thaw_early ? pm->thaw_early(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_thaw_early);
+
+/**
  * pm_generic_thaw - Generic thaw callback for subsystems.
  * @dev: Device to thaw.
  */
 int pm_generic_thaw(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_THAW, false);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->thaw ? pm->thaw(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_thaw);
 
@@ -222,17 +241,33 @@ EXPORT_SYMBOL_GPL(pm_generic_thaw);
  */
 int pm_generic_resume_noirq(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_RESUME, true);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->resume_noirq ? pm->resume_noirq(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_resume_noirq);
 
 /**
+ * pm_generic_resume_early - Generic resume_early callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_resume_early(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->resume_early ? pm->resume_early(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_resume_early);
+
+/**
  * pm_generic_resume - Generic resume callback for subsystems.
  * @dev: Device to resume.
  */
 int pm_generic_resume(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_RESUME, false);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->resume ? pm->resume(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_resume);
 
@@ -242,17 +277,33 @@ EXPORT_SYMBOL_GPL(pm_generic_resume);
  */
 int pm_generic_restore_noirq(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_RESTORE, true);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->restore_noirq ? pm->restore_noirq(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_restore_noirq);
 
 /**
+ * pm_generic_restore_early - Generic restore_early callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_restore_early(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->restore_early ? pm->restore_early(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_restore_early);
+
+/**
  * pm_generic_restore - Generic restore callback for subsystems.
  * @dev: Device to restore.
  */
 int pm_generic_restore(struct device *dev)
 {
-	return __pm_generic_call(dev, PM_EVENT_RESTORE, false);
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->restore ? pm->restore(dev) : 0;
 }
 EXPORT_SYMBOL_GPL(pm_generic_restore);
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index e2cc3d2e0ecc..b462c0e341cb 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -47,6 +47,7 @@ typedef int (*pm_callback_t)(struct device *);
 LIST_HEAD(dpm_list);
 LIST_HEAD(dpm_prepared_list);
 LIST_HEAD(dpm_suspended_list);
+LIST_HEAD(dpm_late_early_list);
 LIST_HEAD(dpm_noirq_list);
 
 struct suspend_stats suspend_stats;
@@ -246,6 +247,40 @@ static pm_callback_t pm_op(const struct dev_pm_ops *ops, pm_message_t state)
 }
 
 /**
+ * pm_late_early_op - Return the PM operation appropriate for given PM event.
+ * @ops: PM operations to choose from.
+ * @state: PM transition of the system being carried out.
+ *
+ * Runtime PM is disabled for @dev while this function is being executed.
+ */
+static pm_callback_t pm_late_early_op(const struct dev_pm_ops *ops,
+				      pm_message_t state)
+{
+	switch (state.event) {
+#ifdef CONFIG_SUSPEND
+	case PM_EVENT_SUSPEND:
+		return ops->suspend_late;
+	case PM_EVENT_RESUME:
+		return ops->resume_early;
+#endif /* CONFIG_SUSPEND */
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+	case PM_EVENT_FREEZE:
+	case PM_EVENT_QUIESCE:
+		return ops->freeze_late;
+	case PM_EVENT_HIBERNATE:
+		return ops->poweroff_late;
+	case PM_EVENT_THAW:
+	case PM_EVENT_RECOVER:
+		return ops->thaw_early;
+	case PM_EVENT_RESTORE:
+		return ops->restore_early;
+#endif /* CONFIG_HIBERNATE_CALLBACKS */
+	}
+
+	return NULL;
+}
+
+/**
  * pm_noirq_op - Return the PM operation appropriate for given PM event.
  * @ops: PM operations to choose from.
  * @state: PM transition of the system being carried out.
@@ -374,21 +409,21 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
 	TRACE_RESUME(0);
 
 	if (dev->pm_domain) {
-		info = "EARLY power domain ";
+		info = "noirq power domain ";
 		callback = pm_noirq_op(&dev->pm_domain->ops, state);
 	} else if (dev->type && dev->type->pm) {
-		info = "EARLY type ";
+		info = "noirq type ";
 		callback = pm_noirq_op(dev->type->pm, state);
 	} else if (dev->class && dev->class->pm) {
-		info = "EARLY class ";
+		info = "noirq class ";
 		callback = pm_noirq_op(dev->class->pm, state);
 	} else if (dev->bus && dev->bus->pm) {
-		info = "EARLY bus ";
+		info = "noirq bus ";
 		callback = pm_noirq_op(dev->bus->pm, state);
 	}
 
 	if (!callback && dev->driver && dev->driver->pm) {
-		info = "EARLY driver ";
+		info = "noirq driver ";
 		callback = pm_noirq_op(dev->driver->pm, state);
 	}
 
@@ -399,13 +434,13 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
 }
 
 /**
- * dpm_resume_noirq - Execute "early resume" callbacks for non-sysdev devices.
+ * dpm_resume_noirq - Execute "noirq resume" callbacks for all devices.
  * @state: PM transition of the system being carried out.
  *
- * Call the "noirq" resume handlers for all devices marked as DPM_OFF_IRQ and
+ * Call the "noirq" resume handlers for all devices in dpm_noirq_list and
  * enable device drivers to receive interrupts.
  */
-void dpm_resume_noirq(pm_message_t state)
+static void dpm_resume_noirq(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 
@@ -415,7 +450,7 @@ void dpm_resume_noirq(pm_message_t state)
 		int error;
 
 		get_device(dev);
-		list_move_tail(&dev->power.entry, &dpm_suspended_list);
+		list_move_tail(&dev->power.entry, &dpm_late_early_list);
 		mutex_unlock(&dpm_list_mtx);
 
 		error = device_resume_noirq(dev, state);
@@ -423,6 +458,80 @@ void dpm_resume_noirq(pm_message_t state)
 			suspend_stats.failed_resume_noirq++;
 			dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
 			dpm_save_failed_dev(dev_name(dev));
+			pm_dev_err(dev, state, " noirq", error);
+		}
+
+		mutex_lock(&dpm_list_mtx);
+		put_device(dev);
+	}
+	mutex_unlock(&dpm_list_mtx);
+	dpm_show_time(starttime, state, "noirq");
+	resume_device_irqs();
+}
+
+/**
+ * device_resume_early - Execute an "early resume" callback for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ *
+ * Runtime PM is disabled for @dev while this function is being executed.
+ */
+static int device_resume_early(struct device *dev, pm_message_t state)
+{
+	pm_callback_t callback = NULL;
+	char *info = NULL;
+	int error = 0;
+
+	TRACE_DEVICE(dev);
+	TRACE_RESUME(0);
+
+	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 && dev->driver && dev->driver->pm) {
+		info = "early driver ";
+		callback = pm_late_early_op(dev->driver->pm, state);
+	}
+
+	error = dpm_run_callback(callback, dev, state, info);
+
+	TRACE_RESUME(error);
+	return error;
+}
+
+/**
+ * dpm_resume_early - Execute "early resume" callbacks for all devices.
+ * @state: PM transition of the system being carried out.
+ */
+static void dpm_resume_early(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+
+	mutex_lock(&dpm_list_mtx);
+	while (!list_empty(&dpm_late_early_list)) {
+		struct device *dev = to_device(dpm_late_early_list.next);
+		int error;
+
+		get_device(dev);
+		list_move_tail(&dev->power.entry, &dpm_suspended_list);
+		mutex_unlock(&dpm_list_mtx);
+
+		error = device_resume_early(dev, state);
+		if (error) {
+			suspend_stats.failed_resume_early++;
+			dpm_save_failed_step(SUSPEND_RESUME_EARLY);
+			dpm_save_failed_dev(dev_name(dev));
 			pm_dev_err(dev, state, " early", error);
 		}
 
@@ -431,9 +540,18 @@ void dpm_resume_noirq(pm_message_t state)
 	}
 	mutex_unlock(&dpm_list_mtx);
 	dpm_show_time(starttime, state, "early");
-	resume_device_irqs();
 }
-EXPORT_SYMBOL_GPL(dpm_resume_noirq);
+
+/**
+ * dpm_resume_start - Execute "noirq" and "early" device callbacks.
+ * @state: PM transition of the system being carried out.
+ */
+void dpm_resume_start(pm_message_t state)
+{
+	dpm_resume_noirq(state);
+	dpm_resume_early(state);
+}
+EXPORT_SYMBOL_GPL(dpm_resume_start);
 
 /**
  * device_resume - Execute "resume" callbacks for given device.
@@ -716,21 +834,21 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 	char *info = NULL;
 
 	if (dev->pm_domain) {
-		info = "LATE power domain ";
+		info = "noirq power domain ";
 		callback = pm_noirq_op(&dev->pm_domain->ops, state);
 	} else if (dev->type && dev->type->pm) {
-		info = "LATE type ";
+		info = "noirq type ";
 		callback = pm_noirq_op(dev->type->pm, state);
 	} else if (dev->class && dev->class->pm) {
-		info = "LATE class ";
+		info = "noirq class ";
 		callback = pm_noirq_op(dev->class->pm, state);
 	} else if (dev->bus && dev->bus->pm) {
-		info = "LATE bus ";
+		info = "noirq bus ";
 		callback = pm_noirq_op(dev->bus->pm, state);
 	}
 
 	if (!callback && dev->driver && dev->driver->pm) {
-		info = "LATE driver ";
+		info = "noirq driver ";
 		callback = pm_noirq_op(dev->driver->pm, state);
 	}
 
@@ -738,21 +856,21 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 }
 
 /**
- * dpm_suspend_noirq - Execute "late suspend" callbacks for non-sysdev devices.
+ * dpm_suspend_noirq - Execute "noirq suspend" callbacks for all devices.
  * @state: PM transition of the system being carried out.
  *
  * Prevent device drivers from receiving interrupts and call the "noirq" suspend
  * handlers for all non-sysdev devices.
  */
-int dpm_suspend_noirq(pm_message_t state)
+static int dpm_suspend_noirq(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 	int error = 0;
 
 	suspend_device_irqs();
 	mutex_lock(&dpm_list_mtx);
-	while (!list_empty(&dpm_suspended_list)) {
-		struct device *dev = to_device(dpm_suspended_list.prev);
+	while (!list_empty(&dpm_late_early_list)) {
+		struct device *dev = to_device(dpm_late_early_list.prev);
 
 		get_device(dev);
 		mutex_unlock(&dpm_list_mtx);
@@ -761,7 +879,7 @@ int dpm_suspend_noirq(pm_message_t state)
 
 		mutex_lock(&dpm_list_mtx);
 		if (error) {
-			pm_dev_err(dev, state, " late", error);
+			pm_dev_err(dev, state, " noirq", error);
 			suspend_stats.failed_suspend_noirq++;
 			dpm_save_failed_step(SUSPEND_SUSPEND_NOIRQ);
 			dpm_save_failed_dev(dev_name(dev));
@@ -776,10 +894,95 @@ int dpm_suspend_noirq(pm_message_t state)
 	if (error)
 		dpm_resume_noirq(resume_event(state));
 	else
+		dpm_show_time(starttime, state, "noirq");
+	return error;
+}
+
+/**
+ * device_suspend_late - Execute a "late suspend" callback for given device.
+ * @dev: Device to handle.
+ * @state: PM transition of the system being carried out.
+ *
+ * Runtime PM is disabled for @dev while this function is being executed.
+ */
+static int device_suspend_late(struct device *dev, pm_message_t state)
+{
+	pm_callback_t callback = NULL;
+	char *info = NULL;
+
+	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 && dev->driver && dev->driver->pm) {
+		info = "late driver ";
+		callback = pm_late_early_op(dev->driver->pm, state);
+	}
+
+	return dpm_run_callback(callback, dev, state, info);
+}
+
+/**
+ * dpm_suspend_late - Execute "late suspend" callbacks for all devices.
+ * @state: PM transition of the system being carried out.
+ */
+static int dpm_suspend_late(pm_message_t state)
+{
+	ktime_t starttime = ktime_get();
+	int error = 0;
+
+	mutex_lock(&dpm_list_mtx);
+	while (!list_empty(&dpm_suspended_list)) {
+		struct device *dev = to_device(dpm_suspended_list.prev);
+
+		get_device(dev);
+		mutex_unlock(&dpm_list_mtx);
+
+		error = device_suspend_late(dev, state);
+
+		mutex_lock(&dpm_list_mtx);
+		if (error) {
+			pm_dev_err(dev, state, " late", error);
+			suspend_stats.failed_suspend_late++;
+			dpm_save_failed_step(SUSPEND_SUSPEND_LATE);
+			dpm_save_failed_dev(dev_name(dev));
+			put_device(dev);
+			break;
+		}
+		if (!list_empty(&dev->power.entry))
+			list_move(&dev->power.entry, &dpm_late_early_list);
+		put_device(dev);
+	}
+	mutex_unlock(&dpm_list_mtx);
+	if (error)
+		dpm_resume_early(resume_event(state));
+	else
 		dpm_show_time(starttime, state, "late");
+
 	return error;
 }
-EXPORT_SYMBOL_GPL(dpm_suspend_noirq);
+
+/**
+ * dpm_suspend_end - Execute "late" and "noirq" device suspend callbacks.
+ * @state: PM transition of the system being carried out.
+ */
+int dpm_suspend_end(pm_message_t state)
+{
+	int error = dpm_suspend_late(state);
+
+	return error ? : dpm_suspend_noirq(state);
+}
+EXPORT_SYMBOL_GPL(dpm_suspend_end);
 
 /**
  * legacy_suspend - Execute a legacy (bus or class) suspend callback for device.
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 9bf62323aaf3..eeb4bff9505c 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -71,6 +71,8 @@ extern void dpm_sysfs_remove(struct device *dev);
 extern void rpm_sysfs_remove(struct device *dev);
 extern int wakeup_sysfs_add(struct device *dev);
 extern void wakeup_sysfs_remove(struct device *dev);
+extern int pm_qos_sysfs_add(struct device *dev);
+extern void pm_qos_sysfs_remove(struct device *dev);
 
 #else /* CONFIG_PM */
 
@@ -79,5 +81,7 @@ static inline void dpm_sysfs_remove(struct device *dev) {}
 static inline void rpm_sysfs_remove(struct device *dev) {}
 static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
 static inline void wakeup_sysfs_remove(struct device *dev) {}
+static inline int pm_qos_sysfs_add(struct device *dev) { return 0; }
+static inline void pm_qos_sysfs_remove(struct device *dev) {}
 
 #endif
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index c5d358837461..71855570922d 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -41,6 +41,7 @@
 #include <linux/mutex.h>
 #include <linux/export.h>
 
+#include "power.h"
 
 static DEFINE_MUTEX(dev_pm_qos_mtx);
 
@@ -166,6 +167,12 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 	struct dev_pm_qos_request *req, *tmp;
 	struct pm_qos_constraints *c;
 
+	/*
+	 * If the device's PM QoS resume latency limit has been exposed to user
+	 * space, it has to be hidden at this point.
+	 */
+	dev_pm_qos_hide_latency_limit(dev);
+
 	mutex_lock(&dev_pm_qos_mtx);
 
 	dev->power.power_state = PMSG_INVALID;
@@ -445,3 +452,57 @@ int dev_pm_qos_add_ancestor_request(struct device *dev,
 	return error;
 }
 EXPORT_SYMBOL_GPL(dev_pm_qos_add_ancestor_request);
+
+#ifdef CONFIG_PM_RUNTIME
+static void __dev_pm_qos_drop_user_request(struct device *dev)
+{
+	dev_pm_qos_remove_request(dev->power.pq_req);
+	dev->power.pq_req = 0;
+}
+
+/**
+ * dev_pm_qos_expose_latency_limit - Expose PM QoS latency limit to user space.
+ * @dev: Device whose PM QoS latency limit is to be exposed to user space.
+ * @value: Initial value of the latency limit.
+ */
+int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
+{
+	struct dev_pm_qos_request *req;
+	int ret;
+
+	if (!device_is_registered(dev) || value < 0)
+		return -EINVAL;
+
+	if (dev->power.pq_req)
+		return -EEXIST;
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	ret = dev_pm_qos_add_request(dev, req, value);
+	if (ret < 0)
+		return ret;
+
+	dev->power.pq_req = req;
+	ret = pm_qos_sysfs_add(dev);
+	if (ret)
+		__dev_pm_qos_drop_user_request(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_limit);
+
+/**
+ * dev_pm_qos_hide_latency_limit - Hide PM QoS latency limit from user space.
+ * @dev: Device whose PM QoS latency limit is to be hidden from user space.
+ */
+void dev_pm_qos_hide_latency_limit(struct device *dev)
+{
+	if (dev->power.pq_req) {
+		pm_qos_sysfs_remove(dev);
+		__dev_pm_qos_drop_user_request(dev);
+	}
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_limit);
+#endif /* CONFIG_PM_RUNTIME */
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index adf41be0ea66..95c12f6cb5b9 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -5,6 +5,7 @@
 #include <linux/device.h>
 #include <linux/string.h>
 #include <linux/export.h>
+#include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
 #include <linux/atomic.h>
 #include <linux/jiffies.h>
@@ -217,6 +218,31 @@ static ssize_t autosuspend_delay_ms_store(struct device *dev,
 static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
 		autosuspend_delay_ms_store);
 
+static ssize_t pm_qos_latency_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", dev->power.pq_req->node.prio);
+}
+
+static ssize_t pm_qos_latency_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t n)
+{
+	s32 value;
+	int ret;
+
+	if (kstrtos32(buf, 0, &value))
+		return -EINVAL;
+
+	if (value < 0)
+		return -EINVAL;
+
+	ret = dev_pm_qos_update_request(dev->power.pq_req, value);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_resume_latency_us, 0644,
+		   pm_qos_latency_show, pm_qos_latency_store);
 #endif /* CONFIG_PM_RUNTIME */
 
 #ifdef CONFIG_PM_SLEEP
@@ -490,6 +516,17 @@ static struct attribute_group pm_runtime_attr_group = {
 	.attrs	= runtime_attrs,
 };
 
+static struct attribute *pm_qos_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_pm_qos_resume_latency_us.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	NULL,
+};
+static struct attribute_group pm_qos_attr_group = {
+	.name	= power_group_name,
+	.attrs	= pm_qos_attrs,
+};
+
 int dpm_sysfs_add(struct device *dev)
 {
 	int rc;
@@ -530,6 +567,16 @@ void wakeup_sysfs_remove(struct device *dev)
 	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
 }
 
+int pm_qos_sysfs_add(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj, &pm_qos_attr_group);
+}
+
+void pm_qos_sysfs_remove(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_attr_group);
+}
+
 void rpm_sysfs_remove(struct device *dev)
 {
 	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index caf995fb774b..2a3e581b8dcd 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -53,6 +53,23 @@ static void pm_wakeup_timer_fn(unsigned long data);
 static LIST_HEAD(wakeup_sources);
 
 /**
+ * wakeup_source_prepare - Prepare a new wakeup source for initialization.
+ * @ws: Wakeup source to prepare.
+ * @name: Pointer to the name of the new wakeup source.
+ *
+ * Callers must ensure that the @name string won't be freed when @ws is still in
+ * use.
+ */
+void wakeup_source_prepare(struct wakeup_source *ws, const char *name)
+{
+	if (ws) {
+		memset(ws, 0, sizeof(*ws));
+		ws->name = name;
+	}
+}
+EXPORT_SYMBOL_GPL(wakeup_source_prepare);
+
+/**
  * wakeup_source_create - Create a struct wakeup_source object.
  * @name: Name of the new wakeup source.
  */
@@ -60,37 +77,44 @@ struct wakeup_source *wakeup_source_create(const char *name)
 {
 	struct wakeup_source *ws;
 
-	ws = kzalloc(sizeof(*ws), GFP_KERNEL);
+	ws = kmalloc(sizeof(*ws), GFP_KERNEL);
 	if (!ws)
 		return NULL;
 
-	spin_lock_init(&ws->lock);
-	if (name)
-		ws->name = kstrdup(name, GFP_KERNEL);
-
+	wakeup_source_prepare(ws, name ? kstrdup(name, GFP_KERNEL) : NULL);
 	return ws;
 }
 EXPORT_SYMBOL_GPL(wakeup_source_create);
 
 /**
+ * wakeup_source_drop - Prepare a struct wakeup_source object for destruction.
+ * @ws: Wakeup source to prepare for destruction.
+ *
+ * Callers must ensure that __pm_stay_awake() or __pm_wakeup_event() will never
+ * be run in parallel with this function for the same wakeup source object.
+ */
+void wakeup_source_drop(struct wakeup_source *ws)
+{
+	if (!ws)
+		return;
+
+	del_timer_sync(&ws->timer);
+	__pm_relax(ws);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_drop);
+
+/**
  * wakeup_source_destroy - Destroy a struct wakeup_source object.
  * @ws: Wakeup source to destroy.
+ *
+ * Use only for wakeup source objects created with wakeup_source_create().
  */
 void wakeup_source_destroy(struct wakeup_source *ws)
 {
 	if (!ws)
 		return;
 
-	spin_lock_irq(&ws->lock);
-	while (ws->active) {
-		spin_unlock_irq(&ws->lock);
-
-		schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT));
-
-		spin_lock_irq(&ws->lock);
-	}
-	spin_unlock_irq(&ws->lock);
-
+	wakeup_source_drop(ws);
 	kfree(ws->name);
 	kfree(ws);
 }
@@ -105,6 +129,7 @@ void wakeup_source_add(struct wakeup_source *ws)
 	if (WARN_ON(!ws))
 		return;
 
+	spin_lock_init(&ws->lock);
 	setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws);
 	ws->active = false;
 
@@ -152,8 +177,10 @@ EXPORT_SYMBOL_GPL(wakeup_source_register);
  */
 void wakeup_source_unregister(struct wakeup_source *ws)
 {
-	wakeup_source_remove(ws);
-	wakeup_source_destroy(ws);
+	if (ws) {
+		wakeup_source_remove(ws);
+		wakeup_source_destroy(ws);
+	}
 }
 EXPORT_SYMBOL_GPL(wakeup_source_unregister);
 
@@ -349,7 +376,6 @@ static void wakeup_source_activate(struct wakeup_source *ws)
 {
 	ws->active = true;
 	ws->active_count++;
-	ws->timer_expires = jiffies;
 	ws->last_time = ktime_get();
 
 	/* Increment the counter of events in progress. */
@@ -370,9 +396,14 @@ void __pm_stay_awake(struct wakeup_source *ws)
 		return;
 
 	spin_lock_irqsave(&ws->lock, flags);
+
 	ws->event_count++;
 	if (!ws->active)
 		wakeup_source_activate(ws);
+
+	del_timer(&ws->timer);
+	ws->timer_expires = 0;
+
 	spin_unlock_irqrestore(&ws->lock, flags);
 }
 EXPORT_SYMBOL_GPL(__pm_stay_awake);
@@ -438,6 +469,7 @@ static void wakeup_source_deactivate(struct wakeup_source *ws)
 		ws->max_time = duration;
 
 	del_timer(&ws->timer);
+	ws->timer_expires = 0;
 
 	/*
 	 * Increment the counter of registered wakeup events and decrement the
@@ -492,11 +524,22 @@ EXPORT_SYMBOL_GPL(pm_relax);
  * pm_wakeup_timer_fn - Delayed finalization of a wakeup event.
  * @data: Address of the wakeup source object associated with the event source.
  *
- * Call __pm_relax() for the wakeup source whose address is stored in @data.
+ * Call wakeup_source_deactivate() for the wakeup source whose address is stored
+ * in @data if it is currently active and its timer has not been canceled and
+ * the expiration time of the timer is not in future.
  */
 static void pm_wakeup_timer_fn(unsigned long data)
 {
-	__pm_relax((struct wakeup_source *)data);
+	struct wakeup_source *ws = (struct wakeup_source *)data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	if (ws->active && ws->timer_expires
+	    && time_after_eq(jiffies, ws->timer_expires))
+		wakeup_source_deactivate(ws);
+
+	spin_unlock_irqrestore(&ws->lock, flags);
 }
 
 /**
@@ -534,7 +577,7 @@ void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec)
 	if (!expires)
 		expires = 1;
 
-	if (time_after(expires, ws->timer_expires)) {
+	if (!ws->timer_expires || time_after(expires, ws->timer_expires)) {
 		mod_timer(&ws->timer, expires);
 		ws->timer_expires = expires;
 	}
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index ca09bc421ddb..32fe9ef5cc5c 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -32,6 +32,7 @@
 #include <linux/sh_timer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pm_domain.h>
 
 struct sh_cmt_priv {
 	void __iomem *mapbase;
@@ -689,6 +690,9 @@ static int __devinit sh_cmt_probe(struct platform_device *pdev)
 	struct sh_cmt_priv *p = platform_get_drvdata(pdev);
 	int ret;
 
+	if (!is_early_platform_device(pdev))
+		pm_genpd_dev_always_on(&pdev->dev, true);
+
 	if (p) {
 		dev_info(&pdev->dev, "kept as earlytimer\n");
 		return 0;
diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c
index db8d5955bad4..a2172f690418 100644
--- a/drivers/clocksource/sh_mtu2.c
+++ b/drivers/clocksource/sh_mtu2.c
@@ -31,6 +31,7 @@
 #include <linux/sh_timer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pm_domain.h>
 
 struct sh_mtu2_priv {
 	void __iomem *mapbase;
@@ -306,6 +307,9 @@ static int __devinit sh_mtu2_probe(struct platform_device *pdev)
 	struct sh_mtu2_priv *p = platform_get_drvdata(pdev);
 	int ret;
 
+	if (!is_early_platform_device(pdev))
+		pm_genpd_dev_always_on(&pdev->dev, true);
+
 	if (p) {
 		dev_info(&pdev->dev, "kept as earlytimer\n");
 		return 0;
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index 079e96ad44e8..97f54b634be4 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -32,6 +32,7 @@
 #include <linux/sh_timer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pm_domain.h>
 
 struct sh_tmu_priv {
 	void __iomem *mapbase;
@@ -410,6 +411,9 @@ static int __devinit sh_tmu_probe(struct platform_device *pdev)
 	struct sh_tmu_priv *p = platform_get_drvdata(pdev);
 	int ret;
 
+	if (!is_early_platform_device(pdev))
+		pm_genpd_dev_always_on(&pdev->dev, true);
+
 	if (p) {
 		dev_info(&pdev->dev, "kept as earlytimer\n");
 		return 0;
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index c189b82f5ece..70c31d43fff3 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -83,6 +83,7 @@ int update_devfreq(struct devfreq *devfreq)
 {
 	unsigned long freq;
 	int err = 0;
+	u32 flags = 0;
 
 	if (!mutex_is_locked(&devfreq->lock)) {
 		WARN(true, "devfreq->lock must be locked by the caller.\n");
@@ -94,7 +95,24 @@ int update_devfreq(struct devfreq *devfreq)
 	if (err)
 		return err;
 
-	err = devfreq->profile->target(devfreq->dev.parent, &freq);
+	/*
+	 * Adjust the freuqency with user freq and QoS.
+	 *
+	 * List from the highest proiority
+	 * max_freq (probably called by thermal when it's too hot)
+	 * min_freq
+	 */
+
+	if (devfreq->min_freq && freq < devfreq->min_freq) {
+		freq = devfreq->min_freq;
+		flags &= ~DEVFREQ_FLAG_LEAST_UPPER_BOUND; /* Use GLB */
+	}
+	if (devfreq->max_freq && freq > devfreq->max_freq) {
+		freq = devfreq->max_freq;
+		flags |= DEVFREQ_FLAG_LEAST_UPPER_BOUND; /* Use LUB */
+	}
+
+	err = devfreq->profile->target(devfreq->dev.parent, &freq, flags);
 	if (err)
 		return err;
 
@@ -501,12 +519,82 @@ static ssize_t show_central_polling(struct device *dev,
 		       !to_devfreq(dev)->governor->no_central_polling);
 }
 
+static ssize_t store_min_freq(struct device *dev, struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct devfreq *df = to_devfreq(dev);
+	unsigned long value;
+	int ret;
+	unsigned long max;
+
+	ret = sscanf(buf, "%lu", &value);
+	if (ret != 1)
+		goto out;
+
+	mutex_lock(&df->lock);
+	max = df->max_freq;
+	if (value && max && value > max) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	df->min_freq = value;
+	update_devfreq(df);
+	ret = count;
+unlock:
+	mutex_unlock(&df->lock);
+out:
+	return ret;
+}
+
+static ssize_t show_min_freq(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	return sprintf(buf, "%lu\n", to_devfreq(dev)->min_freq);
+}
+
+static ssize_t store_max_freq(struct device *dev, struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct devfreq *df = to_devfreq(dev);
+	unsigned long value;
+	int ret;
+	unsigned long min;
+
+	ret = sscanf(buf, "%lu", &value);
+	if (ret != 1)
+		goto out;
+
+	mutex_lock(&df->lock);
+	min = df->min_freq;
+	if (value && min && value < min) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	df->max_freq = value;
+	update_devfreq(df);
+	ret = count;
+unlock:
+	mutex_unlock(&df->lock);
+out:
+	return ret;
+}
+
+static ssize_t show_max_freq(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	return sprintf(buf, "%lu\n", to_devfreq(dev)->max_freq);
+}
+
 static struct device_attribute devfreq_attrs[] = {
 	__ATTR(governor, S_IRUGO, show_governor, NULL),
 	__ATTR(cur_freq, S_IRUGO, show_freq, NULL),
 	__ATTR(central_polling, S_IRUGO, show_central_polling, NULL),
 	__ATTR(polling_interval, S_IRUGO | S_IWUSR, show_polling_interval,
 	       store_polling_interval),
+	__ATTR(min_freq, S_IRUGO | S_IWUSR, show_min_freq, store_min_freq),
+	__ATTR(max_freq, S_IRUGO | S_IWUSR, show_max_freq, store_max_freq),
 	{ },
 };
 
@@ -555,14 +643,30 @@ module_exit(devfreq_exit);
  *			     freq value given to target callback.
  * @dev		The devfreq user device. (parent of devfreq)
  * @freq	The frequency given to target function
+ * @flags	Flags handed from devfreq framework.
  *
  */
-struct opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq)
+struct opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq,
+				    u32 flags)
 {
-	struct opp *opp = opp_find_freq_ceil(dev, freq);
+	struct opp *opp;
 
-	if (opp == ERR_PTR(-ENODEV))
+	if (flags & DEVFREQ_FLAG_LEAST_UPPER_BOUND) {
+		/* The freq is an upper bound. opp should be lower */
 		opp = opp_find_freq_floor(dev, freq);
+
+		/* If not available, use the closest opp */
+		if (opp == ERR_PTR(-ENODEV))
+			opp = opp_find_freq_ceil(dev, freq);
+	} else {
+		/* The freq is an lower bound. opp should be higher */
+		opp = opp_find_freq_ceil(dev, freq);
+
+		/* If not available, use the closest opp */
+		if (opp == ERR_PTR(-ENODEV))
+			opp = opp_find_freq_floor(dev, freq);
+	}
+
 	return opp;
 }
 
diff --git a/drivers/devfreq/exynos4_bus.c b/drivers/devfreq/exynos4_bus.c
index 6460577d6701..1a361e99965a 100644
--- a/drivers/devfreq/exynos4_bus.c
+++ b/drivers/devfreq/exynos4_bus.c
@@ -619,15 +619,19 @@ static int exynos4_bus_setvolt(struct busfreq_data *data, struct opp *opp,
 	return err;
 }
 
-static int exynos4_bus_target(struct device *dev, unsigned long *_freq)
+static int exynos4_bus_target(struct device *dev, unsigned long *_freq,
+			      u32 flags)
 {
 	int err = 0;
 	struct platform_device *pdev = container_of(dev, struct platform_device,
 						    dev);
 	struct busfreq_data *data = platform_get_drvdata(pdev);
-	struct opp *opp = devfreq_recommended_opp(dev, _freq);
-	unsigned long old_freq = opp_get_freq(data->curr_opp);
+	struct opp *opp = devfreq_recommended_opp(dev, _freq, flags);
 	unsigned long freq = opp_get_freq(opp);
+	unsigned long old_freq = opp_get_freq(data->curr_opp);
+
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
 
 	if (old_freq == freq)
 		return 0;
@@ -689,9 +693,7 @@ static int exynos4_get_busier_dmc(struct busfreq_data *data)
 static int exynos4_bus_get_dev_status(struct device *dev,
 				      struct devfreq_dev_status *stat)
 {
-	struct platform_device *pdev = container_of(dev, struct platform_device,
-						    dev);
-	struct busfreq_data *data = platform_get_drvdata(pdev);
+	struct busfreq_data *data = dev_get_drvdata(dev);
 	int busier_dmc;
 	int cycles_x2 = 2; /* 2 x cycles */
 	void __iomem *addr;
@@ -739,9 +741,7 @@ static int exynos4_bus_get_dev_status(struct device *dev,
 
 static void exynos4_bus_exit(struct device *dev)
 {
-	struct platform_device *pdev = container_of(dev, struct platform_device,
-						    dev);
-	struct busfreq_data *data = platform_get_drvdata(pdev);
+	struct busfreq_data *data = dev_get_drvdata(dev);
 
 	devfreq_unregister_opp_notifier(dev, data->devfreq);
 }
@@ -1087,9 +1087,7 @@ static __devexit int exynos4_busfreq_remove(struct platform_device *pdev)
 
 static int exynos4_busfreq_resume(struct device *dev)
 {
-	struct platform_device *pdev = container_of(dev, struct platform_device,
-						    dev);
-	struct busfreq_data *data = platform_get_drvdata(pdev);
+	struct busfreq_data *data = dev_get_drvdata(dev);
 
 	busfreq_mon_reset(data);
 	return 0;
@@ -1132,4 +1130,3 @@ module_exit(exynos4_busfreq_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("EXYNOS4 busfreq driver with devfreq framework");
 MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
-MODULE_ALIAS("exynos4-busfreq");
diff --git a/drivers/devfreq/governor_performance.c b/drivers/devfreq/governor_performance.c
index c0596b291761..574a06b1b1de 100644
--- a/drivers/devfreq/governor_performance.c
+++ b/drivers/devfreq/governor_performance.c
@@ -18,7 +18,10 @@ static int devfreq_performance_func(struct devfreq *df,
 	 * target callback should be able to get floor value as
 	 * said in devfreq.h
 	 */
-	*freq = UINT_MAX;
+	if (!df->max_freq)
+		*freq = UINT_MAX;
+	else
+		*freq = df->max_freq;
 	return 0;
 }
 
diff --git a/drivers/devfreq/governor_powersave.c b/drivers/devfreq/governor_powersave.c
index 2483a85a266f..d742d4a82d6a 100644
--- a/drivers/devfreq/governor_powersave.c
+++ b/drivers/devfreq/governor_powersave.c
@@ -18,7 +18,7 @@ static int devfreq_powersave_func(struct devfreq *df,
 	 * target callback should be able to get ceiling value as
 	 * said in devfreq.h
 	 */
-	*freq = 0;
+	*freq = df->min_freq;
 	return 0;
 }
 
diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c
index efad8dcf9028..a2e3eae79011 100644
--- a/drivers/devfreq/governor_simpleondemand.c
+++ b/drivers/devfreq/governor_simpleondemand.c
@@ -25,6 +25,7 @@ static int devfreq_simple_ondemand_func(struct devfreq *df,
 	unsigned int dfso_upthreshold = DFSO_UPTHRESHOLD;
 	unsigned int dfso_downdifferential = DFSO_DOWNDIFFERENCTIAL;
 	struct devfreq_simple_ondemand_data *data = df->data;
+	unsigned long max = (df->max_freq) ? df->max_freq : UINT_MAX;
 
 	if (err)
 		return err;
@@ -41,7 +42,7 @@ static int devfreq_simple_ondemand_func(struct devfreq *df,
 
 	/* Assume MAX if it is going to be divided by zero */
 	if (stat.total_time == 0) {
-		*freq = UINT_MAX;
+		*freq = max;
 		return 0;
 	}
 
@@ -54,13 +55,13 @@ static int devfreq_simple_ondemand_func(struct devfreq *df,
 	/* Set MAX if it's busy enough */
 	if (stat.busy_time * 100 >
 	    stat.total_time * dfso_upthreshold) {
-		*freq = UINT_MAX;
+		*freq = max;
 		return 0;
 	}
 
 	/* Set MAX if we do not know the initial frequency */
 	if (stat.current_frequency == 0) {
-		*freq = UINT_MAX;
+		*freq = max;
 		return 0;
 	}
 
@@ -79,6 +80,11 @@ static int devfreq_simple_ondemand_func(struct devfreq *df,
 	b = div_u64(b, (dfso_upthreshold - dfso_downdifferential / 2));
 	*freq = (unsigned long) b;
 
+	if (df->min_freq && *freq < df->min_freq)
+		*freq = df->min_freq;
+	if (df->max_freq && *freq > df->max_freq)
+		*freq = df->max_freq;
+
 	return 0;
 }
 
diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c
index 4f8b563da782..0681246fc89d 100644
--- a/drivers/devfreq/governor_userspace.c
+++ b/drivers/devfreq/governor_userspace.c
@@ -25,10 +25,19 @@ static int devfreq_userspace_func(struct devfreq *df, unsigned long *freq)
 {
 	struct userspace_data *data = df->data;
 
-	if (!data->valid)
+	if (data->valid) {
+		unsigned long adjusted_freq = data->user_frequency;
+
+		if (df->max_freq && adjusted_freq > df->max_freq)
+			adjusted_freq = df->max_freq;
+
+		if (df->min_freq && adjusted_freq < df->min_freq)
+			adjusted_freq = df->min_freq;
+
+		*freq = adjusted_freq;
+	} else {
 		*freq = df->previous_freq; /* No user freq specified yet */
-	else
-		*freq = data->user_frequency;
+	}
 	return 0;
 }
 
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 352d4797865b..75a485448796 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -56,6 +56,7 @@
 #include <linux/mmc/sh_mmcif.h>
 #include <linux/pagemap.h>
 #include <linux/platform_device.h>
+#include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
 #include <linux/spinlock.h>
 #include <linux/module.h>
@@ -1346,6 +1347,8 @@ static int __devinit sh_mmcif_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto clean_up5;
 
+	dev_pm_qos_expose_latency_limit(&pdev->dev, 100);
+
 	dev_info(&pdev->dev, "driver version %s\n", DRIVER_VERSION);
 	dev_dbg(&pdev->dev, "chip ver H'%04x\n",
 		sh_mmcif_readl(host->addr, MMCIF_CE_VERSION) & 0x0000ffff);
@@ -1376,6 +1379,8 @@ static int __devexit sh_mmcif_remove(struct platform_device *pdev)
 	host->dying = true;
 	pm_runtime_get_sync(&pdev->dev);
 
+	dev_pm_qos_hide_latency_limit(&pdev->dev);
+
 	mmc_remove_host(host->mmc);
 	sh_mmcif_writel(host->addr, MMCIF_CE_INT_MASK, MASK_ALL);
 
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 5f9ad74fbf80..e21988901c36 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -39,6 +39,7 @@
 #include <linux/module.h>
 #include <linux/pagemap.h>
 #include <linux/platform_device.h>
+#include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
 #include <linux/scatterlist.h>
 #include <linux/spinlock.h>
@@ -955,6 +956,8 @@ int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host,
 
 	mmc_add_host(mmc);
 
+	dev_pm_qos_expose_latency_limit(&pdev->dev, 100);
+
 	/* Unmask the IRQs we want to know about */
 	if (!_host->chan_rx)
 		irq_mask |= TMIO_MASK_READOP;
@@ -993,6 +996,8 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 		|| host->mmc->caps & MMC_CAP_NONREMOVABLE)
 		pm_runtime_get_sync(&pdev->dev);
 
+	dev_pm_qos_hide_latency_limit(&pdev->dev);
+
 	mmc_remove_host(host->mmc);
 	cancel_work_sync(&host->done);
 	cancel_delayed_work_sync(&host->delayed_reset_work);
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index ce4fa0831860..9e14ae6cd49c 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -129,9 +129,9 @@ static void do_suspend(void)
 	printk(KERN_DEBUG "suspending xenstore...\n");
 	xs_suspend();
 
-	err = dpm_suspend_noirq(PMSG_FREEZE);
+	err = dpm_suspend_end(PMSG_FREEZE);
 	if (err) {
-		printk(KERN_ERR "dpm_suspend_noirq failed: %d\n", err);
+		printk(KERN_ERR "dpm_suspend_end failed: %d\n", err);
 		goto out_resume;
 	}
 
@@ -149,7 +149,7 @@ static void do_suspend(void)
 
 	err = stop_machine(xen_suspend, &si, cpumask_of(0));
 
-	dpm_resume_noirq(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
+	dpm_resume_start(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
 
 	if (err) {
 		printk(KERN_ERR "failed to start xen_suspend: %d\n", err);