These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

16 files changed, 1903 insertions, 937 deletions

diff --git a/kernel/drivers/base/power/Makefile b/kernel/drivers/base/power/Makefile
index 1cb854459..5998c5328 100644
--- a/kernel/drivers/base/power/Makefile
+++ b/kernel/drivers/base/power/Makefile
@@ -1,7 +1,7 @@
-obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o runtime.o
+obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o runtime.o wakeirq.o
 obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
-obj-$(CONFIG_PM_OPP)	+= opp.o
+obj-$(CONFIG_PM_OPP)	+= opp/
 obj-$(CONFIG_PM_GENERIC_DOMAINS)	+=  domain.o domain_governor.o
 obj-$(CONFIG_HAVE_CLK)	+= clock_ops.o
 
diff --git a/kernel/drivers/base/power/clock_ops.c b/kernel/drivers/base/power/clock_ops.c
index ac3c07db9..60ee5591e 100644
--- a/kernel/drivers/base/power/clock_ops.c
+++ b/kernel/drivers/base/power/clock_ops.c
@@ -15,8 +15,9 @@
 #include <linux/clkdev.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/pm_runtime.h>
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_CLK
 
 enum pce_status {
 	PCE_STATUS_NONE = 0,
@@ -65,7 +66,8 @@ static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
 	} else {
 		clk_prepare(ce->clk);
 		ce->status = PCE_STATUS_ACQUIRED;
-		dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
+		dev_dbg(dev, "Clock %pC con_id %s managed by runtime PM.\n",
+			ce->clk, ce->con_id);
 	}
 }
 
@@ -91,7 +93,7 @@ static int __pm_clk_add(struct device *dev, const char *con_id,
 			return -ENOMEM;
 		}
 	} else {
-		if (IS_ERR(clk) || !__clk_get(clk)) {
+		if (IS_ERR(clk)) {
 			kfree(ce);
 			return -ENOENT;
 		}
@@ -125,7 +127,9 @@ int pm_clk_add(struct device *dev, const char *con_id)
  * @clk: Clock pointer
  *
  * Add the clock to the list of clocks used for the power management of @dev.
- * It will increment refcount on clock pointer, use clk_put() on it when done.
+ * The power-management code will take control of the clock reference, so
+ * callers should not call clk_put() on @clk after this function sucessfully
+ * returned.
  */
 int pm_clk_add_clk(struct device *dev, struct clk *clk)
 {
@@ -365,7 +369,44 @@ static int pm_clk_notify(struct notifier_block *nb,
 	return 0;
 }
 
-#else /* !CONFIG_PM */
+int pm_clk_runtime_suspend(struct device *dev)
+{
+	int ret;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	ret = pm_generic_runtime_suspend(dev);
+	if (ret) {
+		dev_err(dev, "failed to suspend device\n");
+		return ret;
+	}
+
+	ret = pm_clk_suspend(dev);
+	if (ret) {
+		dev_err(dev, "failed to suspend clock\n");
+		pm_generic_runtime_resume(dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+int pm_clk_runtime_resume(struct device *dev)
+{
+	int ret;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	ret = pm_clk_resume(dev);
+	if (ret) {
+		dev_err(dev, "failed to resume clock\n");
+		return ret;
+	}
+
+	return pm_generic_runtime_resume(dev);
+}
+
+#else /* !CONFIG_PM_CLK */
 
 /**
  * enable_clock - Enable a device clock.
@@ -445,7 +486,7 @@ static int pm_clk_notify(struct notifier_block *nb,
 	return 0;
 }
 
-#endif /* !CONFIG_PM */
+#endif /* !CONFIG_PM_CLK */
 
 /**
  * pm_clk_add_notifier - Add bus type notifier for power management clocks.
diff --git a/kernel/drivers/base/power/domain.c b/kernel/drivers/base/power/domain.c
index 2327613d4..65f50eccd 100644
--- a/kernel/drivers/base/power/domain.c
+++ b/kernel/drivers/base/power/domain.c
@@ -6,6 +6,7 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
@@ -19,6 +20,8 @@
 #include <linux/suspend.h>
 #include <linux/export.h>
 
+#define GENPD_RETRY_MAX_MS	250		/* Approximate */
+
 #define GENPD_DEV_CALLBACK(genpd, type, callback, dev)		\
 ({								\
 	type (*__routine)(struct device *__d); 			\
@@ -31,43 +34,9 @@
 	__ret;							\
 })
 
-#define GENPD_DEV_TIMED_CALLBACK(genpd, type, callback, dev, field, name)	\
-({										\
-	ktime_t __start = ktime_get();						\
-	type __retval = GENPD_DEV_CALLBACK(genpd, type, callback, dev);		\
-	s64 __elapsed = ktime_to_ns(ktime_sub(ktime_get(), __start));		\
-	struct gpd_timing_data *__td = &dev_gpd_data(dev)->td;			\
-	if (!__retval && __elapsed > __td->field) {				\
-		__td->field = __elapsed;					\
-		dev_dbg(dev, name " latency exceeded, new value %lld ns\n",	\
-			__elapsed);						\
-		genpd->max_off_time_changed = true;				\
-		__td->constraint_changed = true;				\
-	}									\
-	__retval;								\
-})
-
 static LIST_HEAD(gpd_list);
 static DEFINE_MUTEX(gpd_list_lock);
 
-static struct generic_pm_domain *pm_genpd_lookup_name(const char *domain_name)
-{
-	struct generic_pm_domain *genpd = NULL, *gpd;
-
-	if (IS_ERR_OR_NULL(domain_name))
-		return NULL;
-
-	mutex_lock(&gpd_list_lock);
-	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
-		if (!strcmp(gpd->name, domain_name)) {
-			genpd = gpd;
-			break;
-		}
-	}
-	mutex_unlock(&gpd_list_lock);
-	return genpd;
-}
-
 /*
  * Get the generic PM domain for a particular struct device.
  * This validates the struct device pointer, the PM domain pointer,
@@ -107,14 +76,12 @@ static struct generic_pm_domain *dev_to_genpd(struct device *dev)
 
 static int genpd_stop_dev(struct generic_pm_domain *genpd, struct device *dev)
 {
-	return GENPD_DEV_TIMED_CALLBACK(genpd, int, stop, dev,
-					stop_latency_ns, "stop");
+	return GENPD_DEV_CALLBACK(genpd, int, stop, dev);
 }
 
 static int genpd_start_dev(struct generic_pm_domain *genpd, struct device *dev)
 {
-	return GENPD_DEV_TIMED_CALLBACK(genpd, int, start, dev,
-					start_latency_ns, "start");
+	return GENPD_DEV_CALLBACK(genpd, int, start, dev);
 }
 
 static bool genpd_sd_counter_dec(struct generic_pm_domain *genpd)
@@ -133,55 +100,7 @@ static void genpd_sd_counter_inc(struct generic_pm_domain *genpd)
 	smp_mb__after_atomic();
 }
 
-static void genpd_acquire_lock(struct generic_pm_domain *genpd)
-{
-	DEFINE_WAIT(wait);
-
-	mutex_lock(&genpd->lock);
-	/*
-	 * Wait for the domain to transition into either the active,
-	 * or the power off state.
-	 */
-	for (;;) {
-		prepare_to_wait(&genpd->status_wait_queue, &wait,
-				TASK_UNINTERRUPTIBLE);
-		if (genpd->status == GPD_STATE_ACTIVE
-		    || genpd->status == GPD_STATE_POWER_OFF)
-			break;
-		mutex_unlock(&genpd->lock);
-
-		schedule();
-
-		mutex_lock(&genpd->lock);
-	}
-	finish_wait(&genpd->status_wait_queue, &wait);
-}
-
-static void genpd_release_lock(struct generic_pm_domain *genpd)
-{
-	mutex_unlock(&genpd->lock);
-}
-
-static void genpd_set_active(struct generic_pm_domain *genpd)
-{
-	if (genpd->resume_count == 0)
-		genpd->status = GPD_STATE_ACTIVE;
-}
-
-static void genpd_recalc_cpu_exit_latency(struct generic_pm_domain *genpd)
-{
-	s64 usecs64;
-
-	if (!genpd->cpuidle_data)
-		return;
-
-	usecs64 = genpd->power_on_latency_ns;
-	do_div(usecs64, NSEC_PER_USEC);
-	usecs64 += genpd->cpuidle_data->saved_exit_latency;
-	genpd->cpuidle_data->idle_state->exit_latency = usecs64;
-}
-
-static int genpd_power_on(struct generic_pm_domain *genpd)
+static int genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 {
 	ktime_t time_start;
 	s64 elapsed_ns;
@@ -190,6 +109,9 @@ static int genpd_power_on(struct generic_pm_domain *genpd)
 	if (!genpd->power_on)
 		return 0;
 
+	if (!timed)
+		return genpd->power_on(genpd);
+
 	time_start = ktime_get();
 	ret = genpd->power_on(genpd);
 	if (ret)
@@ -201,14 +123,13 @@ static int genpd_power_on(struct generic_pm_domain *genpd)
 
 	genpd->power_on_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
-	genpd_recalc_cpu_exit_latency(genpd);
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "on", elapsed_ns);
 
 	return ret;
 }
 
-static int genpd_power_off(struct generic_pm_domain *genpd)
+static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 {
 	ktime_t time_start;
 	s64 elapsed_ns;
@@ -217,6 +138,9 @@ static int genpd_power_off(struct generic_pm_domain *genpd)
 	if (!genpd->power_off)
 		return 0;
 
+	if (!timed)
+		return genpd->power_off(genpd);
+
 	time_start = ktime_get();
 	ret = genpd->power_off(genpd);
 	if (ret == -EBUSY)
@@ -235,49 +159,35 @@ static int genpd_power_off(struct generic_pm_domain *genpd)
 }
 
 /**
- * __pm_genpd_poweron - Restore power to a given PM domain and its masters.
+ * genpd_queue_power_off_work - Queue up the execution of genpd_poweroff().
+ * @genpd: PM domait to power off.
+ *
+ * Queue up the execution of genpd_poweroff() unless it's already been done
+ * before.
+ */
+static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
+{
+	queue_work(pm_wq, &genpd->power_off_work);
+}
+
+static int genpd_poweron(struct generic_pm_domain *genpd);
+
+/**
+ * __genpd_poweron - Restore power to a given PM domain and its masters.
  * @genpd: PM domain to power up.
  *
  * Restore power to @genpd and all of its masters so that it is possible to
  * resume a device belonging to it.
  */
-static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
+static int __genpd_poweron(struct generic_pm_domain *genpd)
 {
 	struct gpd_link *link;
-	DEFINE_WAIT(wait);
 	int ret = 0;
 
-	/* If the domain's master is being waited for, we have to wait too. */
-	for (;;) {
-		prepare_to_wait(&genpd->status_wait_queue, &wait,
-				TASK_UNINTERRUPTIBLE);
-		if (genpd->status != GPD_STATE_WAIT_MASTER)
-			break;
-		mutex_unlock(&genpd->lock);
-
-		schedule();
-
-		mutex_lock(&genpd->lock);
-	}
-	finish_wait(&genpd->status_wait_queue, &wait);
-
 	if (genpd->status == GPD_STATE_ACTIVE
 	    || (genpd->prepared_count > 0 && genpd->suspend_power_off))
 		return 0;
 
-	if (genpd->status != GPD_STATE_POWER_OFF) {
-		genpd_set_active(genpd);
-		return 0;
-	}
-
-	if (genpd->cpuidle_data) {
-		cpuidle_pause_and_lock();
-		genpd->cpuidle_data->idle_state->disabled = true;
-		cpuidle_resume_and_unlock();
-		goto out;
-	}
-
 	/*
 	 * The list is guaranteed not to change while the loop below is being
 	 * executed, unless one of the masters' .power_on() callbacks fiddles
@@ -285,85 +195,55 @@ static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
 	 */
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
 		genpd_sd_counter_inc(link->master);
-		genpd->status = GPD_STATE_WAIT_MASTER;
 
-		mutex_unlock(&genpd->lock);
-
-		ret = pm_genpd_poweron(link->master);
-
-		mutex_lock(&genpd->lock);
-
-		/*
-		 * The "wait for parent" status is guaranteed not to change
-		 * while the master is powering on.
-		 */
-		genpd->status = GPD_STATE_POWER_OFF;
-		wake_up_all(&genpd->status_wait_queue);
+		ret = genpd_poweron(link->master);
 		if (ret) {
 			genpd_sd_counter_dec(link->master);
 			goto err;
 		}
 	}
 
-	ret = genpd_power_on(genpd);
+	ret = genpd_power_on(genpd, true);
 	if (ret)
 		goto err;
 
- out:
-	genpd_set_active(genpd);
-
+	genpd->status = GPD_STATE_ACTIVE;
 	return 0;
 
  err:
-	list_for_each_entry_continue_reverse(link, &genpd->slave_links, slave_node)
+	list_for_each_entry_continue_reverse(link,
+					&genpd->slave_links,
+					slave_node) {
 		genpd_sd_counter_dec(link->master);
+		genpd_queue_power_off_work(link->master);
+	}
 
 	return ret;
 }
 
 /**
- * pm_genpd_poweron - Restore power to a given PM domain and its masters.
+ * genpd_poweron - Restore power to a given PM domain and its masters.
  * @genpd: PM domain to power up.
  */
-int pm_genpd_poweron(struct generic_pm_domain *genpd)
+static int genpd_poweron(struct generic_pm_domain *genpd)
 {
 	int ret;
 
 	mutex_lock(&genpd->lock);
-	ret = __pm_genpd_poweron(genpd);
+	ret = __genpd_poweron(genpd);
 	mutex_unlock(&genpd->lock);
 	return ret;
 }
 
-/**
- * pm_genpd_name_poweron - Restore power to a given PM domain and its masters.
- * @domain_name: Name of the PM domain to power up.
- */
-int pm_genpd_name_poweron(const char *domain_name)
-{
-	struct generic_pm_domain *genpd;
-
-	genpd = pm_genpd_lookup_name(domain_name);
-	return genpd ? pm_genpd_poweron(genpd) : -EINVAL;
-}
-
-static int genpd_start_dev_no_timing(struct generic_pm_domain *genpd,
-				     struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, start, dev);
-}
-
 static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev)
 {
-	return GENPD_DEV_TIMED_CALLBACK(genpd, int, save_state, dev,
-					save_state_latency_ns, "state save");
+	return GENPD_DEV_CALLBACK(genpd, int, save_state, dev);
 }
 
-static int genpd_restore_dev(struct generic_pm_domain *genpd, struct device *dev)
+static int genpd_restore_dev(struct generic_pm_domain *genpd,
+			struct device *dev)
 {
-	return GENPD_DEV_TIMED_CALLBACK(genpd, int, restore_state, dev,
-					restore_state_latency_ns,
-					"state restore");
+	return GENPD_DEV_CALLBACK(genpd, int, restore_state, dev);
 }
 
 static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
@@ -407,133 +287,31 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 }
 
 /**
- * __pm_genpd_save_device - Save the pre-suspend state of a device.
- * @pdd: Domain data of the device to save the state of.
- * @genpd: PM domain the device belongs to.
- */
-static int __pm_genpd_save_device(struct pm_domain_data *pdd,
-				  struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
-{
-	struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd);
-	struct device *dev = pdd->dev;
-	int ret = 0;
-
-	if (gpd_data->need_restore > 0)
-		return 0;
-
-	/*
-	 * If the value of the need_restore flag is still unknown at this point,
-	 * we trust that pm_genpd_poweroff() has verified that the device is
-	 * already runtime PM suspended.
-	 */
-	if (gpd_data->need_restore < 0) {
-		gpd_data->need_restore = 1;
-		return 0;
-	}
-
-	mutex_unlock(&genpd->lock);
-
-	genpd_start_dev(genpd, dev);
-	ret = genpd_save_dev(genpd, dev);
-	genpd_stop_dev(genpd, dev);
-
-	mutex_lock(&genpd->lock);
-
-	if (!ret)
-		gpd_data->need_restore = 1;
-
-	return ret;
-}
-
-/**
- * __pm_genpd_restore_device - Restore the pre-suspend state of a device.
- * @pdd: Domain data of the device to restore the state of.
- * @genpd: PM domain the device belongs to.
- */
-static void __pm_genpd_restore_device(struct pm_domain_data *pdd,
-				      struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
-{
-	struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd);
-	struct device *dev = pdd->dev;
-	int need_restore = gpd_data->need_restore;
-
-	gpd_data->need_restore = 0;
-	mutex_unlock(&genpd->lock);
-
-	genpd_start_dev(genpd, dev);
-
-	/*
-	 * Call genpd_restore_dev() for recently added devices too (need_restore
-	 * is negative then).
-	 */
-	if (need_restore)
-		genpd_restore_dev(genpd, dev);
-
-	mutex_lock(&genpd->lock);
-}
-
-/**
- * genpd_abort_poweroff - Check if a PM domain power off should be aborted.
- * @genpd: PM domain to check.
- *
- * Return true if a PM domain's status changed to GPD_STATE_ACTIVE during
- * a "power off" operation, which means that a "power on" has occured in the
- * meantime, or if its resume_count field is different from zero, which means
- * that one of its devices has been resumed in the meantime.
- */
-static bool genpd_abort_poweroff(struct generic_pm_domain *genpd)
-{
-	return genpd->status == GPD_STATE_WAIT_MASTER
-		|| genpd->status == GPD_STATE_ACTIVE || genpd->resume_count > 0;
-}
-
-/**
- * genpd_queue_power_off_work - Queue up the execution of pm_genpd_poweroff().
- * @genpd: PM domait to power off.
- *
- * Queue up the execution of pm_genpd_poweroff() unless it's already been done
- * before.
- */
-static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
-{
-	queue_work(pm_wq, &genpd->power_off_work);
-}
-
-/**
- * pm_genpd_poweroff - Remove power from a given PM domain.
+ * genpd_poweroff - Remove power from a given PM domain.
  * @genpd: PM domain to power down.
+ * @is_async: PM domain is powered down from a scheduled work
  *
  * If all of the @genpd's devices have been suspended and all of its subdomains
- * have been powered down, run the runtime suspend callbacks provided by all of
- * the @genpd's devices' drivers and remove power from @genpd.
+ * have been powered down, remove power from @genpd.
  */
-static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
+static int genpd_poweroff(struct generic_pm_domain *genpd, bool is_async)
 {
 	struct pm_domain_data *pdd;
 	struct gpd_link *link;
-	unsigned int not_suspended;
-	int ret = 0;
+	unsigned int not_suspended = 0;
 
- start:
 	/*
 	 * Do not try to power off the domain in the following situations:
 	 * (1) The domain is already in the "power off" state.
-	 * (2) The domain is waiting for its master to power up.
-	 * (3) One of the domain's devices is being resumed right now.
-	 * (4) System suspend is in progress.
+	 * (2) System suspend is in progress.
 	 */
 	if (genpd->status == GPD_STATE_POWER_OFF
-	    || genpd->status == GPD_STATE_WAIT_MASTER
-	    || genpd->resume_count > 0 || genpd->prepared_count > 0)
+	    || genpd->prepared_count > 0)
 		return 0;
 
 	if (atomic_read(&genpd->sd_count) > 0)
 		return -EBUSY;
 
-	not_suspended = 0;
 	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
 		enum pm_qos_flags_status stat;
 
@@ -543,83 +321,35 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		if (stat > PM_QOS_FLAGS_NONE)
 			return -EBUSY;
 
-		if (pdd->dev->driver && (!pm_runtime_suspended(pdd->dev)
-		    || pdd->dev->power.irq_safe))
+		if (!pm_runtime_suspended(pdd->dev) || pdd->dev->power.irq_safe)
 			not_suspended++;
 	}
 
-	if (not_suspended > genpd->in_progress)
+	if (not_suspended > 1 || (not_suspended == 1 && is_async))
 		return -EBUSY;
 
-	if (genpd->poweroff_task) {
-		/*
-		 * Another instance of pm_genpd_poweroff() is executing
-		 * callbacks, so tell it to start over and return.
-		 */
-		genpd->status = GPD_STATE_REPEAT;
-		return 0;
-	}
-
 	if (genpd->gov && genpd->gov->power_down_ok) {
 		if (!genpd->gov->power_down_ok(&genpd->domain))
 			return -EAGAIN;
 	}
 
-	genpd->status = GPD_STATE_BUSY;
-	genpd->poweroff_task = current;
-
-	list_for_each_entry_reverse(pdd, &genpd->dev_list, list_node) {
-		ret = atomic_read(&genpd->sd_count) == 0 ?
-			__pm_genpd_save_device(pdd, genpd) : -EBUSY;
-
-		if (genpd_abort_poweroff(genpd))
-			goto out;
-
-		if (ret) {
-			genpd_set_active(genpd);
-			goto out;
-		}
-
-		if (genpd->status == GPD_STATE_REPEAT) {
-			genpd->poweroff_task = NULL;
-			goto start;
-		}
-	}
-
-	if (genpd->cpuidle_data) {
-		/*
-		 * If cpuidle_data is set, cpuidle should turn the domain off
-		 * when the CPU in it is idle.  In that case we don't decrement
-		 * the subdomain counts of the master domains, so that power is
-		 * not removed from the current domain prematurely as a result
-		 * of cutting off the masters' power.
-		 */
-		genpd->status = GPD_STATE_POWER_OFF;
-		cpuidle_pause_and_lock();
-		genpd->cpuidle_data->idle_state->disabled = false;
-		cpuidle_resume_and_unlock();
-		goto out;
-	}
-
 	if (genpd->power_off) {
-		if (atomic_read(&genpd->sd_count) > 0) {
-			ret = -EBUSY;
-			goto out;
-		}
+		int ret;
+
+		if (atomic_read(&genpd->sd_count) > 0)
+			return -EBUSY;
 
 		/*
 		 * If sd_count > 0 at this point, one of the subdomains hasn't
-		 * managed to call pm_genpd_poweron() for the master yet after
-		 * incrementing it.  In that case pm_genpd_poweron() will wait
+		 * managed to call genpd_poweron() for the master yet after
+		 * incrementing it.  In that case genpd_poweron() will wait
 		 * for us to drop the lock, so we can call .power_off() and let
-		 * the pm_genpd_poweron() restore power for us (this shouldn't
+		 * the genpd_poweron() restore power for us (this shouldn't
 		 * happen very often).
 		 */
-		ret = genpd_power_off(genpd);
-		if (ret == -EBUSY) {
-			genpd_set_active(genpd);
-			goto out;
-		}
+		ret = genpd_power_off(genpd, true);
+		if (ret)
+			return ret;
 	}
 
 	genpd->status = GPD_STATE_POWER_OFF;
@@ -629,10 +359,7 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		genpd_queue_power_off_work(link->master);
 	}
 
- out:
-	genpd->poweroff_task = NULL;
-	wake_up_all(&genpd->status_wait_queue);
-	return ret;
+	return 0;
 }
 
 /**
@@ -645,9 +372,9 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 
 	genpd = container_of(work, struct generic_pm_domain, power_off_work);
 
-	genpd_acquire_lock(genpd);
-	pm_genpd_poweroff(genpd);
-	genpd_release_lock(genpd);
+	mutex_lock(&genpd->lock);
+	genpd_poweroff(genpd, true);
+	mutex_unlock(&genpd->lock);
 }
 
 /**
@@ -661,8 +388,11 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 static int pm_genpd_runtime_suspend(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	struct generic_pm_domain_data *gpd_data;
 	bool (*stop_ok)(struct device *__dev);
+	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
+	bool runtime_pm = pm_runtime_enabled(dev);
+	ktime_t time_start;
+	s64 elapsed_ns;
 	int ret;
 
 	dev_dbg(dev, "%s()\n", __func__);
@@ -671,14 +401,42 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
+	/*
+	 * A runtime PM centric subsystem/driver may re-use the runtime PM
+	 * callbacks for other purposes than runtime PM. In those scenarios
+	 * runtime PM is disabled. Under these circumstances, we shall skip
+	 * validating/measuring the PM QoS latency.
+	 */
 	stop_ok = genpd->gov ? genpd->gov->stop_ok : NULL;
-	if (stop_ok && !stop_ok(dev))
+	if (runtime_pm && stop_ok && !stop_ok(dev))
 		return -EBUSY;
 
-	ret = genpd_stop_dev(genpd, dev);
+	/* Measure suspend latency. */
+	if (runtime_pm)
+		time_start = ktime_get();
+
+	ret = genpd_save_dev(genpd, dev);
 	if (ret)
 		return ret;
 
+	ret = genpd_stop_dev(genpd, dev);
+	if (ret) {
+		genpd_restore_dev(genpd, dev);
+		return ret;
+	}
+
+	/* Update suspend latency value if the measured time exceeds it. */
+	if (runtime_pm) {
+		elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
+		if (elapsed_ns > td->suspend_latency_ns) {
+			td->suspend_latency_ns = elapsed_ns;
+			dev_dbg(dev, "suspend latency exceeded, %lld ns\n",
+				elapsed_ns);
+			genpd->max_off_time_changed = true;
+			td->constraint_changed = true;
+		}
+	}
+
 	/*
 	 * If power.irq_safe is set, this routine will be run with interrupts
 	 * off, so it can't use mutexes.
@@ -687,19 +445,7 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 		return 0;
 
 	mutex_lock(&genpd->lock);
-
-	/*
-	 * If we have an unknown state of the need_restore flag, it means none
-	 * of the runtime PM callbacks has been invoked yet. Let's update the
-	 * flag to reflect that the current state is active.
-	 */
-	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
-	if (gpd_data->need_restore < 0)
-		gpd_data->need_restore = 0;
-
-	genpd->in_progress++;
-	pm_genpd_poweroff(genpd);
-	genpd->in_progress--;
+	genpd_poweroff(genpd, false);
 	mutex_unlock(&genpd->lock);
 
 	return 0;
@@ -716,8 +462,12 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 static int pm_genpd_runtime_resume(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	DEFINE_WAIT(wait);
+	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
+	bool runtime_pm = pm_runtime_enabled(dev);
+	ktime_t time_start;
+	s64 elapsed_ns;
 	int ret;
+	bool timed = true;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -726,39 +476,37 @@ static int pm_genpd_runtime_resume(struct device *dev)
 		return -EINVAL;
 
 	/* If power.irq_safe, the PM domain is never powered off. */
-	if (dev->power.irq_safe)
-		return genpd_start_dev_no_timing(genpd, dev);
+	if (dev->power.irq_safe) {
+		timed = false;
+		goto out;
+	}
 
 	mutex_lock(&genpd->lock);
-	ret = __pm_genpd_poweron(genpd);
-	if (ret) {
-		mutex_unlock(&genpd->lock);
+	ret = __genpd_poweron(genpd);
+	mutex_unlock(&genpd->lock);
+
+	if (ret)
 		return ret;
-	}
-	genpd->status = GPD_STATE_BUSY;
-	genpd->resume_count++;
-	for (;;) {
-		prepare_to_wait(&genpd->status_wait_queue, &wait,
-				TASK_UNINTERRUPTIBLE);
-		/*
-		 * If current is the powering off task, we have been called
-		 * reentrantly from one of the device callbacks, so we should
-		 * not wait.
-		 */
-		if (!genpd->poweroff_task || genpd->poweroff_task == current)
-			break;
-		mutex_unlock(&genpd->lock);
 
-		schedule();
+ out:
+	/* Measure resume latency. */
+	if (timed && runtime_pm)
+		time_start = ktime_get();
 
-		mutex_lock(&genpd->lock);
+	genpd_start_dev(genpd, dev);
+	genpd_restore_dev(genpd, dev);
+
+	/* Update resume latency value if the measured time exceeds it. */
+	if (timed && runtime_pm) {
+		elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
+		if (elapsed_ns > td->resume_latency_ns) {
+			td->resume_latency_ns = elapsed_ns;
+			dev_dbg(dev, "resume latency exceeded, %lld ns\n",
+				elapsed_ns);
+			genpd->max_off_time_changed = true;
+			td->constraint_changed = true;
+		}
 	}
-	finish_wait(&genpd->status_wait_queue, &wait);
-	__pm_genpd_restore_device(dev->power.subsys_data->domain_data, genpd);
-	genpd->resume_count--;
-	genpd_set_active(genpd);
-	wake_up_all(&genpd->status_wait_queue);
-	mutex_unlock(&genpd->lock);
 
 	return 0;
 }
@@ -772,15 +520,15 @@ static int __init pd_ignore_unused_setup(char *__unused)
 __setup("pd_ignore_unused", pd_ignore_unused_setup);
 
 /**
- * pm_genpd_poweroff_unused - Power off all PM domains with no devices in use.
+ * genpd_poweroff_unused - Power off all PM domains with no devices in use.
  */
-void pm_genpd_poweroff_unused(void)
+static int __init genpd_poweroff_unused(void)
 {
 	struct generic_pm_domain *genpd;
 
 	if (pd_ignore_unused) {
 		pr_warn("genpd: Not disabling unused power domains\n");
-		return;
+		return 0;
 	}
 
 	mutex_lock(&gpd_list_lock);
@@ -789,11 +537,7 @@ void pm_genpd_poweroff_unused(void)
 		genpd_queue_power_off_work(genpd);
 
 	mutex_unlock(&gpd_list_lock);
-}
 
-static int __init genpd_poweroff_unused(void)
-{
-	pm_genpd_poweroff_unused();
 	return 0;
 }
 late_initcall(genpd_poweroff_unused);
@@ -827,6 +571,7 @@ static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd,
 /**
  * pm_genpd_sync_poweroff - Synchronously power off a PM domain and its masters.
  * @genpd: PM domain to power off, if possible.
+ * @timed: True if latency measurements are allowed.
  *
  * Check if the given PM domain can be powered off (during system suspend or
  * hibernation) and do that if so.  Also, in that case propagate to its masters.
@@ -836,7 +581,8 @@ static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd,
  * executed sequentially, so it is guaranteed that it will never run twice in
  * parallel).
  */
-static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd)
+static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd,
+				   bool timed)
 {
 	struct gpd_link *link;
 
@@ -847,38 +593,40 @@ static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd)
 	    || atomic_read(&genpd->sd_count) > 0)
 		return;
 
-	genpd_power_off(genpd);
+	genpd_power_off(genpd, timed);
 
 	genpd->status = GPD_STATE_POWER_OFF;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
 		genpd_sd_counter_dec(link->master);
-		pm_genpd_sync_poweroff(link->master);
+		pm_genpd_sync_poweroff(link->master, timed);
 	}
 }
 
 /**
  * pm_genpd_sync_poweron - Synchronously power on a PM domain and its masters.
  * @genpd: PM domain to power on.
+ * @timed: True if latency measurements are allowed.
  *
  * This function is only called in "noirq" and "syscore" stages of system power
  * transitions, so it need not acquire locks (all of the "noirq" callbacks are
  * executed sequentially, so it is guaranteed that it will never run twice in
  * parallel).
  */
-static void pm_genpd_sync_poweron(struct generic_pm_domain *genpd)
+static void pm_genpd_sync_poweron(struct generic_pm_domain *genpd,
+				  bool timed)
 {
 	struct gpd_link *link;
 
-	if (genpd->status != GPD_STATE_POWER_OFF)
+	if (genpd->status == GPD_STATE_ACTIVE)
 		return;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		pm_genpd_sync_poweron(link->master);
+		pm_genpd_sync_poweron(link->master, timed);
 		genpd_sd_counter_inc(link->master);
 	}
 
-	genpd_power_on(genpd);
+	genpd_power_on(genpd, timed);
 
 	genpd->status = GPD_STATE_ACTIVE;
 }
@@ -947,14 +695,14 @@ static int pm_genpd_prepare(struct device *dev)
 	if (resume_needed(dev, genpd))
 		pm_runtime_resume(dev);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->prepared_count++ == 0) {
 		genpd->suspended_count = 0;
 		genpd->suspend_power_off = genpd->status == GPD_STATE_POWER_OFF;
 	}
 
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	if (genpd->suspend_power_off) {
 		pm_runtime_put_noidle(dev);
@@ -963,7 +711,7 @@ static int pm_genpd_prepare(struct device *dev)
 
 	/*
 	 * The PM domain must be in the GPD_STATE_ACTIVE state at this point,
-	 * so pm_genpd_poweron() will return immediately, but if the device
+	 * so genpd_poweron() will return immediately, but if the device
 	 * is suspended (e.g. it's been stopped by genpd_stop_dev()), we need
 	 * to make it operational.
 	 */
@@ -1056,7 +804,7 @@ static int pm_genpd_suspend_noirq(struct device *dev)
 	 * the same PM domain, so it is not necessary to use locking here.
 	 */
 	genpd->suspended_count++;
-	pm_genpd_sync_poweroff(genpd);
+	pm_genpd_sync_poweroff(genpd, true);
 
 	return 0;
 }
@@ -1086,7 +834,7 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	 * guaranteed that this function will never run twice in parallel for
 	 * the same PM domain, so it is not necessary to use locking here.
 	 */
-	pm_genpd_sync_poweron(genpd);
+	pm_genpd_sync_poweron(genpd, true);
 	genpd->suspended_count--;
 
 	return genpd_start_dev(genpd, dev);
@@ -1217,7 +965,8 @@ static int pm_genpd_thaw_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_start_dev(genpd, dev);
+	return genpd->suspend_power_off ?
+		0 : genpd_start_dev(genpd, dev);
 }
 
 /**
@@ -1300,7 +1049,7 @@ static int pm_genpd_restore_noirq(struct device *dev)
 			 * If the domain was off before the hibernation, make
 			 * sure it will be off going forward.
 			 */
-			genpd_power_off(genpd);
+			genpd_power_off(genpd, true);
 
 			return 0;
 		}
@@ -1309,7 +1058,7 @@ static int pm_genpd_restore_noirq(struct device *dev)
 	if (genpd->suspend_power_off)
 		return 0;
 
-	pm_genpd_sync_poweron(genpd);
+	pm_genpd_sync_poweron(genpd, true);
 
 	return genpd_start_dev(genpd, dev);
 }
@@ -1367,9 +1116,9 @@ static void genpd_syscore_switch(struct device *dev, bool suspend)
 
 	if (suspend) {
 		genpd->suspended_count++;
-		pm_genpd_sync_poweroff(genpd);
+		pm_genpd_sync_poweroff(genpd, false);
 	} else {
-		pm_genpd_sync_poweron(genpd);
+		pm_genpd_sync_poweron(genpd, false);
 		genpd->suspended_count--;
 	}
 }
@@ -1427,7 +1176,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
 		gpd_data->td = *td;
 
 	gpd_data->base.dev = dev;
-	gpd_data->need_restore = -1;
 	gpd_data->td.constraint_changed = true;
 	gpd_data->td.effective_constraint_ns = -1;
 	gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier;
@@ -1489,7 +1237,7 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1506,7 +1254,7 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
 
  out:
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	if (ret)
 		genpd_free_dev_data(dev, gpd_data);
@@ -1517,18 +1265,6 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 }
 
 /**
- * __pm_genpd_name_add_device - Find I/O PM domain and add a device to it.
- * @domain_name: Name of the PM domain to add the device to.
- * @dev: Device to be added.
- * @td: Set of PM QoS timing parameters to attach to the device.
- */
-int __pm_genpd_name_add_device(const char *domain_name, struct device *dev,
-			       struct gpd_timing_data *td)
-{
-	return __pm_genpd_add_device(pm_genpd_lookup_name(domain_name), 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.
@@ -1550,7 +1286,7 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	gpd_data = to_gpd_data(pdd);
 	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1565,14 +1301,14 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 
 	list_del_init(&pdd->list_node);
 
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	genpd_free_dev_data(dev, gpd_data);
 
 	return 0;
 
  out:
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 	dev_pm_qos_add_notifier(dev, &gpd_data->nb);
 
 	return ret;
@@ -1586,23 +1322,19 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 			   struct generic_pm_domain *subdomain)
 {
-	struct gpd_link *link;
+	struct gpd_link *link, *itr;
 	int ret = 0;
 
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain)
 	    || genpd == subdomain)
 		return -EINVAL;
 
- start:
-	genpd_acquire_lock(genpd);
-	mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
+	link = kzalloc(sizeof(*link), GFP_KERNEL);
+	if (!link)
+		return -ENOMEM;
 
-	if (subdomain->status != GPD_STATE_POWER_OFF
-	    && subdomain->status != GPD_STATE_ACTIVE) {
-		mutex_unlock(&subdomain->lock);
-		genpd_release_lock(genpd);
-		goto start;
-	}
+	mutex_lock(&genpd->lock);
+	mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
 
 	if (genpd->status == GPD_STATE_POWER_OFF
 	    &&  subdomain->status != GPD_STATE_POWER_OFF) {
@@ -1610,18 +1342,13 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 		goto out;
 	}
 
-	list_for_each_entry(link, &genpd->master_links, master_node) {
-		if (link->slave == subdomain && link->master == genpd) {
+	list_for_each_entry(itr, &genpd->master_links, master_node) {
+		if (itr->slave == subdomain && itr->master == genpd) {
 			ret = -EINVAL;
 			goto out;
 		}
 	}
 
-	link = kzalloc(sizeof(*link), GFP_KERNEL);
-	if (!link) {
-		ret = -ENOMEM;
-		goto out;
-	}
 	link->master = genpd;
 	list_add_tail(&link->master_node, &genpd->master_links);
 	link->slave = subdomain;
@@ -1631,39 +1358,12 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 
  out:
 	mutex_unlock(&subdomain->lock);
-	genpd_release_lock(genpd);
-
+	mutex_unlock(&genpd->lock);
+	if (ret)
+		kfree(link);
 	return ret;
 }
-
-/**
- * pm_genpd_add_subdomain_names - Add a subdomain to an I/O PM domain.
- * @master_name: Name of the master PM domain to add the subdomain to.
- * @subdomain_name: Name of the subdomain to be added.
- */
-int pm_genpd_add_subdomain_names(const char *master_name,
-				 const char *subdomain_name)
-{
-	struct generic_pm_domain *master = NULL, *subdomain = NULL, *gpd;
-
-	if (IS_ERR_OR_NULL(master_name) || IS_ERR_OR_NULL(subdomain_name))
-		return -EINVAL;
-
-	mutex_lock(&gpd_list_lock);
-	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
-		if (!master && !strcmp(gpd->name, master_name))
-			master = gpd;
-
-		if (!subdomain && !strcmp(gpd->name, subdomain_name))
-			subdomain = gpd;
-
-		if (master && subdomain)
-			break;
-	}
-	mutex_unlock(&gpd_list_lock);
-
-	return pm_genpd_add_subdomain(master, subdomain);
-}
+EXPORT_SYMBOL_GPL(pm_genpd_add_subdomain);
 
 /**
  * pm_genpd_remove_subdomain - Remove a subdomain from an I/O PM domain.
@@ -1679,8 +1379,14 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain))
 		return -EINVAL;
 
- start:
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
+
+	if (!list_empty(&subdomain->slave_links) || subdomain->device_count) {
+		pr_warn("%s: unable to remove subdomain %s\n", genpd->name,
+			subdomain->name);
+		ret = -EBUSY;
+		goto out;
+	}
 
 	list_for_each_entry(link, &genpd->master_links, master_node) {
 		if (link->slave != subdomain)
@@ -1688,13 +1394,6 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 
 		mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
 
-		if (subdomain->status != GPD_STATE_POWER_OFF
-		    && subdomain->status != GPD_STATE_ACTIVE) {
-			mutex_unlock(&subdomain->lock);
-			genpd_release_lock(genpd);
-			goto start;
-		}
-
 		list_del(&link->master_node);
 		list_del(&link->slave_node);
 		kfree(link);
@@ -1707,128 +1406,12 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 		break;
 	}
 
-	genpd_release_lock(genpd);
-
-	return ret;
-}
-
-/**
- * pm_genpd_attach_cpuidle - Connect the given PM domain with cpuidle.
- * @genpd: PM domain to be connected with cpuidle.
- * @state: cpuidle state this domain can disable/enable.
- *
- * Make a PM domain behave as though it contained a CPU core, that is, instead
- * of calling its power down routine it will enable the given cpuidle state so
- * that the cpuidle subsystem can power it down (if possible and desirable).
- */
-int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
-{
-	struct cpuidle_driver *cpuidle_drv;
-	struct gpd_cpuidle_data *cpuidle_data;
-	struct cpuidle_state *idle_state;
-	int ret = 0;
-
-	if (IS_ERR_OR_NULL(genpd) || state < 0)
-		return -EINVAL;
-
-	genpd_acquire_lock(genpd);
-
-	if (genpd->cpuidle_data) {
-		ret = -EEXIST;
-		goto out;
-	}
-	cpuidle_data = kzalloc(sizeof(*cpuidle_data), GFP_KERNEL);
-	if (!cpuidle_data) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	cpuidle_drv = cpuidle_driver_ref();
-	if (!cpuidle_drv) {
-		ret = -ENODEV;
-		goto err_drv;
-	}
-	if (cpuidle_drv->state_count <= state) {
-		ret = -EINVAL;
-		goto err;
-	}
-	idle_state = &cpuidle_drv->states[state];
-	if (!idle_state->disabled) {
-		ret = -EAGAIN;
-		goto err;
-	}
-	cpuidle_data->idle_state = idle_state;
-	cpuidle_data->saved_exit_latency = idle_state->exit_latency;
-	genpd->cpuidle_data = cpuidle_data;
-	genpd_recalc_cpu_exit_latency(genpd);
-
- out:
-	genpd_release_lock(genpd);
-	return ret;
-
- err:
-	cpuidle_driver_unref();
-
- err_drv:
-	kfree(cpuidle_data);
-	goto out;
-}
-
-/**
- * pm_genpd_name_attach_cpuidle - Find PM domain and connect cpuidle to it.
- * @name: Name of the domain to connect to cpuidle.
- * @state: cpuidle state this domain can manipulate.
- */
-int pm_genpd_name_attach_cpuidle(const char *name, int state)
-{
-	return pm_genpd_attach_cpuidle(pm_genpd_lookup_name(name), state);
-}
-
-/**
- * pm_genpd_detach_cpuidle - Remove the cpuidle connection from a PM domain.
- * @genpd: PM domain to remove the cpuidle connection from.
- *
- * Remove the cpuidle connection set up by pm_genpd_attach_cpuidle() from the
- * given PM domain.
- */
-int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd)
-{
-	struct gpd_cpuidle_data *cpuidle_data;
-	struct cpuidle_state *idle_state;
-	int ret = 0;
-
-	if (IS_ERR_OR_NULL(genpd))
-		return -EINVAL;
-
-	genpd_acquire_lock(genpd);
-
-	cpuidle_data = genpd->cpuidle_data;
-	if (!cpuidle_data) {
-		ret = -ENODEV;
-		goto out;
-	}
-	idle_state = cpuidle_data->idle_state;
-	if (!idle_state->disabled) {
-		ret = -EAGAIN;
-		goto out;
-	}
-	idle_state->exit_latency = cpuidle_data->saved_exit_latency;
-	cpuidle_driver_unref();
-	genpd->cpuidle_data = NULL;
-	kfree(cpuidle_data);
+out:
+	mutex_unlock(&genpd->lock);
 
- out:
-	genpd_release_lock(genpd);
 	return ret;
 }
-
-/**
- * pm_genpd_name_detach_cpuidle - Find PM domain and disconnect cpuidle from it.
- * @name: Name of the domain to disconnect cpuidle from.
- */
-int pm_genpd_name_detach_cpuidle(const char *name)
-{
-	return pm_genpd_detach_cpuidle(pm_genpd_lookup_name(name));
-}
+EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain);
 
 /* Default device callbacks for generic PM domains. */
 
@@ -1896,12 +1479,8 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	mutex_init(&genpd->lock);
 	genpd->gov = gov;
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
-	genpd->in_progress = 0;
 	atomic_set(&genpd->sd_count, 0);
 	genpd->status = is_off ? GPD_STATE_POWER_OFF : GPD_STATE_ACTIVE;
-	init_waitqueue_head(&genpd->status_wait_queue);
-	genpd->poweroff_task = NULL;
-	genpd->resume_count = 0;
 	genpd->device_count = 0;
 	genpd->max_off_time_ns = -1;
 	genpd->max_off_time_changed = true;
@@ -1939,6 +1518,7 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
 }
+EXPORT_SYMBOL_GPL(pm_genpd_init);
 
 #ifdef CONFIG_PM_GENERIC_DOMAINS_OF
 /*
@@ -2112,7 +1692,7 @@ EXPORT_SYMBOL_GPL(of_genpd_get_from_provider);
 
 /**
  * genpd_dev_pm_detach - Detach a device from its PM domain.
- * @dev: Device to attach.
+ * @dev: Device to detach.
  * @power_off: Currently not used
  *
  * Try to locate a corresponding generic PM domain, which the device was
@@ -2121,6 +1701,7 @@ EXPORT_SYMBOL_GPL(of_genpd_get_from_provider);
 static void genpd_dev_pm_detach(struct device *dev, bool power_off)
 {
 	struct generic_pm_domain *pd;
+	unsigned int i;
 	int ret = 0;
 
 	pd = pm_genpd_lookup_dev(dev);
@@ -2129,10 +1710,12 @@ static void genpd_dev_pm_detach(struct device *dev, bool power_off)
 
 	dev_dbg(dev, "removing from PM domain %s\n", pd->name);
 
-	while (1) {
+	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
 		ret = pm_genpd_remove_device(pd, dev);
 		if (ret != -EAGAIN)
 			break;
+
+		mdelay(i);
 		cond_resched();
 	}
 
@@ -2167,12 +1750,16 @@ static void genpd_dev_pm_sync(struct device *dev)
  * Both generic and legacy Samsung-specific DT bindings are supported to keep
  * backwards compatibility with existing DTBs.
  *
- * Returns 0 on successfully attached PM domain or negative error code.
+ * Returns 0 on successfully attached PM domain or negative error code. Note
+ * that if a power-domain exists for the device, but it cannot be found or
+ * turned on, then return -EPROBE_DEFER to ensure that the device is not
+ * probed and to re-try again later.
  */
 int genpd_dev_pm_attach(struct device *dev)
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
+	unsigned int i;
 	int ret;
 
 	if (!dev->of_node)
@@ -2199,34 +1786,36 @@ int genpd_dev_pm_attach(struct device *dev)
 	}
 
 	pd = of_genpd_get_from_provider(&pd_args);
+	of_node_put(pd_args.np);
 	if (IS_ERR(pd)) {
 		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
 			__func__, PTR_ERR(pd));
-		of_node_put(dev->of_node);
-		return PTR_ERR(pd);
+		return -EPROBE_DEFER;
 	}
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
 
-	while (1) {
+	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
 		ret = pm_genpd_add_device(pd, dev);
 		if (ret != -EAGAIN)
 			break;
+
+		mdelay(i);
 		cond_resched();
 	}
 
 	if (ret < 0) {
 		dev_err(dev, "failed to add to PM domain %s: %d",
 			pd->name, ret);
-		of_node_put(dev->of_node);
-		return ret;
+		goto out;
 	}
 
 	dev->pm_domain->detach = genpd_dev_pm_detach;
 	dev->pm_domain->sync = genpd_dev_pm_sync;
-	pm_genpd_poweron(pd);
+	ret = genpd_poweron(pd);
 
-	return 0;
+out:
+	return ret ? -EPROBE_DEFER : 0;
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
 #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
@@ -2274,9 +1863,6 @@ static int pm_genpd_summary_one(struct seq_file *s,
 {
 	static const char * const status_lookup[] = {
 		[GPD_STATE_ACTIVE] = "on",
-		[GPD_STATE_WAIT_MASTER] = "wait-master",
-		[GPD_STATE_BUSY] = "busy",
-		[GPD_STATE_REPEAT] = "off-in-progress",
 		[GPD_STATE_POWER_OFF] = "off"
 	};
 	struct pm_domain_data *pm_data;
@@ -2290,7 +1876,7 @@ static int pm_genpd_summary_one(struct seq_file *s,
 
 	if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup)))
 		goto exit;
-	seq_printf(s, "%-30s  %-15s  ", genpd->name, status_lookup[genpd->status]);
+	seq_printf(s, "%-30s  %-15s ", genpd->name, status_lookup[genpd->status]);
 
 	/*
 	 * Modifications on the list require holding locks on both
@@ -2325,8 +1911,8 @@ static int pm_genpd_summary_show(struct seq_file *s, void *data)
 	struct generic_pm_domain *genpd;
 	int ret = 0;
 
-	seq_puts(s, "    domain                      status         slaves\n");
-	seq_puts(s, "           /device                                      runtime status\n");
+	seq_puts(s, "domain                          status          slaves\n");
+	seq_puts(s, "    /device                                             runtime status\n");
 	seq_puts(s, "----------------------------------------------------------------------\n");
 
 	ret = mutex_lock_interruptible(&gpd_list_lock);
diff --git a/kernel/drivers/base/power/domain_governor.c b/kernel/drivers/base/power/domain_governor.c
index 2a4154a09..1e937ac5f 100644
--- a/kernel/drivers/base/power/domain_governor.c
+++ b/kernel/drivers/base/power/domain_governor.c
@@ -77,13 +77,14 @@ static bool default_stop_ok(struct device *dev)
 				      dev_update_qos_constraint);
 
 	if (constraint_ns > 0) {
-		constraint_ns -= td->start_latency_ns;
+		constraint_ns -= td->suspend_latency_ns +
+				td->resume_latency_ns;
 		if (constraint_ns == 0)
 			return false;
 	}
 	td->effective_constraint_ns = constraint_ns;
-	td->cached_stop_ok = constraint_ns > td->stop_latency_ns ||
-				constraint_ns == 0;
+	td->cached_stop_ok = constraint_ns >= 0;
+
 	/*
 	 * The children have been suspended already, so we don't need to take
 	 * their stop latencies into account here.
@@ -126,18 +127,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 
 	off_on_time_ns = genpd->power_off_latency_ns +
 				genpd->power_on_latency_ns;
-	/*
-	 * It doesn't make sense to remove power from the domain if saving
-	 * the state of all devices in it and the power off/power on operations
-	 * take too much time.
-	 *
-	 * All devices in this domain have been stopped already at this point.
-	 */
-	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
-		if (pdd->dev->driver)
-			off_on_time_ns +=
-				to_gpd_data(pdd)->td.save_state_latency_ns;
-	}
 
 	min_off_time_ns = -1;
 	/*
@@ -171,9 +160,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 		struct gpd_timing_data *td;
 		s64 constraint_ns;
 
-		if (!pdd->dev->driver)
-			continue;
-
 		/*
 		 * Check if the device is allowed to be off long enough for the
 		 * domain to turn off and on (that's how much time it will
@@ -193,7 +179,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 		 * constraint_ns cannot be negative here, because the device has
 		 * been suspended.
 		 */
-		constraint_ns -= td->restore_state_latency_ns;
 		if (constraint_ns <= off_on_time_ns)
 			return false;
 
diff --git a/kernel/drivers/base/power/generic_ops.c b/kernel/drivers/base/power/generic_ops.c
index 96a92db83..07c3c4a95 100644
--- a/kernel/drivers/base/power/generic_ops.c
+++ b/kernel/drivers/base/power/generic_ops.c
@@ -9,6 +9,7 @@
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/export.h>
+#include <linux/suspend.h>
 
 #ifdef CONFIG_PM
 /**
@@ -296,11 +297,27 @@ void pm_generic_complete(struct device *dev)
 
 	if (drv && drv->pm && drv->pm->complete)
 		drv->pm->complete(dev);
+}
 
+/**
+ * pm_complete_with_resume_check - Complete a device power transition.
+ * @dev: Device to handle.
+ *
+ * Complete a device power transition during a system-wide power transition and
+ * optionally schedule a runtime resume of the device if the system resume in
+ * progress has been initated by the platform firmware and the device had its
+ * power.direct_complete flag set.
+ */
+void pm_complete_with_resume_check(struct device *dev)
+{
+	pm_generic_complete(dev);
 	/*
-	 * Let runtime PM try to suspend devices that haven't been in use before
-	 * going into the system-wide sleep state we're resuming from.
+	 * If the device had been runtime-suspended before the system went into
+	 * the sleep state it is going out of and it has never been resumed till
+	 * now, resume it in case the firmware powered it up.
 	 */
-	pm_request_idle(dev);
+	if (dev->power.direct_complete && pm_resume_via_firmware())
+		pm_request_resume(dev);
 }
+EXPORT_SYMBOL_GPL(pm_complete_with_resume_check);
 #endif /* CONFIG_PM_SLEEP */
diff --git a/kernel/drivers/base/power/main.c b/kernel/drivers/base/power/main.c
index 3d874eca7..1710c26ba 100644
--- a/kernel/drivers/base/power/main.c
+++ b/kernel/drivers/base/power/main.c
@@ -24,6 +24,7 @@
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm-trace.h>
+#include <linux/pm_wakeirq.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/async.h>
@@ -587,6 +588,7 @@ void dpm_resume_noirq(pm_message_t state)
 	async_synchronize_full();
 	dpm_show_time(starttime, state, "noirq");
 	resume_device_irqs();
+	device_wakeup_disarm_wake_irqs();
 	cpuidle_resume();
 	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false);
 }
@@ -920,9 +922,7 @@ static void device_complete(struct device *dev, pm_message_t state)
 
 	if (callback) {
 		pm_dev_dbg(dev, state, info);
-		trace_device_pm_callback_start(dev, info, state.event);
 		callback(dev);
-		trace_device_pm_callback_end(dev, 0);
 	}
 
 	device_unlock(dev);
@@ -954,7 +954,9 @@ void dpm_complete(pm_message_t state)
 		list_move(&dev->power.entry, &list);
 		mutex_unlock(&dpm_list_mtx);
 
+		trace_device_pm_callback_start(dev, "", state.event);
 		device_complete(dev, state);
+		trace_device_pm_callback_end(dev, 0);
 
 		mutex_lock(&dpm_list_mtx);
 		put_device(dev);
@@ -1104,6 +1106,7 @@ int dpm_suspend_noirq(pm_message_t state)
 
 	trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true);
 	cpuidle_pause();
+	device_wakeup_arm_wake_irqs();
 	suspend_device_irqs();
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
@@ -1374,7 +1377,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	if (dev->power.direct_complete) {
 		if (pm_runtime_status_suspended(dev)) {
 			pm_runtime_disable(dev);
-			if (pm_runtime_suspended_if_enabled(dev))
+			if (pm_runtime_status_suspended(dev))
 				goto Complete;
 
 			pm_runtime_enable(dev);
@@ -1585,11 +1588,8 @@ static int device_prepare(struct device *dev, pm_message_t state)
 		callback = dev->driver->pm->prepare;
 	}
 
-	if (callback) {
-		trace_device_pm_callback_start(dev, info, state.event);
+	if (callback)
 		ret = callback(dev);
-		trace_device_pm_callback_end(dev, ret);
-	}
 
 	device_unlock(dev);
 
@@ -1631,7 +1631,9 @@ int dpm_prepare(pm_message_t state)
 		get_device(dev);
 		mutex_unlock(&dpm_list_mtx);
 
+		trace_device_pm_callback_start(dev, "", state.event);
 		error = device_prepare(dev, state);
+		trace_device_pm_callback_end(dev, error);
 
 		mutex_lock(&dpm_list_mtx);
 		if (error) {
diff --git a/kernel/drivers/base/power/opp/Makefile b/kernel/drivers/base/power/opp/Makefile
new file mode 100644
index 000000000..33c1e18c4
--- /dev/null
+++ b/kernel/drivers/base/power/opp/Makefile
@@ -0,0 +1,2 @@
+ccflags-$(CONFIG_DEBUG_DRIVER)	:= -DDEBUG
+obj-y				+= core.o cpu.o
diff --git a/kernel/drivers/base/power/opp.c b/kernel/drivers/base/power/opp/core.c
index 677fb2843..b8e76f750 100644
--- a/kernel/drivers/base/power/opp.c
+++ b/kernel/drivers/base/power/opp/core.c
@@ -11,93 +11,16 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/kernel.h>
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/device.h>
-#include <linux/list.h>
-#include <linux/rculist.h>
-#include <linux/rcupdate.h>
-#include <linux/pm_opp.h>
 #include <linux/of.h>
 #include <linux/export.h>
 
-/*
- * Internal data structure organization with the OPP layer library is as
- * follows:
- * dev_opp_list (root)
- *	|- device 1 (represents voltage domain 1)
- *	|	|- opp 1 (availability, freq, voltage)
- *	|	|- opp 2 ..
- *	...	...
- *	|	`- opp n ..
- *	|- device 2 (represents the next voltage domain)
- *	...
- *	`- device m (represents mth voltage domain)
- * device 1, 2.. are represented by dev_opp structure while each opp
- * is represented by the opp structure.
- */
-
-/**
- * struct dev_pm_opp - Generic OPP description structure
- * @node:	opp list node. The nodes are maintained throughout the lifetime
- *		of boot. It is expected only an optimal set of OPPs are
- *		added to the library by the SoC framework.
- *		RCU usage: opp list is traversed with RCU locks. node
- *		modification is possible realtime, hence the modifications
- *		are protected by the dev_opp_list_lock for integrity.
- *		IMPORTANT: the opp nodes should be maintained in increasing
- *		order.
- * @dynamic:	not-created from static DT entries.
- * @available:	true/false - marks if this OPP as available or not
- * @rate:	Frequency in hertz
- * @u_volt:	Nominal voltage in microvolts corresponding to this OPP
- * @dev_opp:	points back to the device_opp struct this opp belongs to
- * @rcu_head:	RCU callback head used for deferred freeing
- *
- * This structure stores the OPP information for a given device.
- */
-struct dev_pm_opp {
-	struct list_head node;
-
-	bool available;
-	bool dynamic;
-	unsigned long rate;
-	unsigned long u_volt;
-
-	struct device_opp *dev_opp;
-	struct rcu_head rcu_head;
-};
-
-/**
- * struct device_opp - Device opp structure
- * @node:	list node - contains the devices with OPPs that
- *		have been registered. Nodes once added are not modified in this
- *		list.
- *		RCU usage: nodes are not modified in the list of device_opp,
- *		however addition is possible and is secured by dev_opp_list_lock
- * @dev:	device pointer
- * @srcu_head:	notifier head to notify the OPP availability changes.
- * @rcu_head:	RCU callback head used for deferred freeing
- * @opp_list:	list of opps
- *
- * This is an internal data structure maintaining the link to opps attached to
- * a device. This structure is not meant to be shared to users as it is
- * meant for book keeping and private to OPP library.
- *
- * Because the opp structures can be used from both rcu and srcu readers, we
- * need to wait for the grace period of both of them before freeing any
- * resources. And so we have used kfree_rcu() from within call_srcu() handlers.
- */
-struct device_opp {
-	struct list_head node;
-
-	struct device *dev;
-	struct srcu_notifier_head srcu_head;
-	struct rcu_head rcu_head;
-	struct list_head opp_list;
-};
+#include "opp.h"
 
 /*
  * The root of the list of all devices. All device_opp structures branch off
@@ -106,16 +29,48 @@ struct device_opp {
  */
 static LIST_HEAD(dev_opp_list);
 /* Lock to allow exclusive modification to the device and opp lists */
-static DEFINE_MUTEX(dev_opp_list_lock);
+DEFINE_MUTEX(dev_opp_list_lock);
 
 #define opp_rcu_lockdep_assert()					\
 do {									\
-	rcu_lockdep_assert(rcu_read_lock_held() ||			\
-				lockdep_is_held(&dev_opp_list_lock),	\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
+				!lockdep_is_held(&dev_opp_list_lock),	\
 			   "Missing rcu_read_lock() or "		\
 			   "dev_opp_list_lock protection");		\
 } while (0)
 
+static struct device_list_opp *_find_list_dev(const struct device *dev,
+					      struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	list_for_each_entry(list_dev, &dev_opp->dev_list, node)
+		if (list_dev->dev == dev)
+			return list_dev;
+
+	return NULL;
+}
+
+static struct device_opp *_managed_opp(const struct device_node *np)
+{
+	struct device_opp *dev_opp;
+
+	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node) {
+		if (dev_opp->np == np) {
+			/*
+			 * Multiple devices can point to the same OPP table and
+			 * so will have same node-pointer, np.
+			 *
+			 * But the OPPs will be considered as shared only if the
+			 * OPP table contains a "opp-shared" property.
+			 */
+			return dev_opp->shared_opp ? dev_opp : NULL;
+		}
+	}
+
+	return NULL;
+}
+
 /**
  * _find_device_opp() - find device_opp struct using device pointer
  * @dev:	device pointer used to lookup device OPPs
@@ -126,31 +81,32 @@ do {									\
  * Return: pointer to 'struct device_opp' if found, otherwise -ENODEV or
  * -EINVAL based on type of error.
  *
- * Locking: This function must be called under rcu_read_lock(). device_opp
- * is a RCU protected pointer. This means that device_opp is valid as long
- * as we are under RCU lock.
+ * Locking: For readers, this function must be called under rcu_read_lock().
+ * device_opp is a RCU protected pointer, which means that device_opp is valid
+ * as long as we are under RCU lock.
+ *
+ * For Writers, this function must be called with dev_opp_list_lock held.
  */
-static struct device_opp *_find_device_opp(struct device *dev)
+struct device_opp *_find_device_opp(struct device *dev)
 {
-	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+	struct device_opp *dev_opp;
+
+	opp_rcu_lockdep_assert();
 
-	if (unlikely(IS_ERR_OR_NULL(dev))) {
+	if (IS_ERR_OR_NULL(dev)) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry_rcu(tmp_dev_opp, &dev_opp_list, node) {
-		if (tmp_dev_opp->dev == dev) {
-			dev_opp = tmp_dev_opp;
-			break;
-		}
-	}
+	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node)
+		if (_find_list_dev(dev, dev_opp))
+			return dev_opp;
 
-	return dev_opp;
+	return ERR_PTR(-ENODEV);
 }
 
 /**
- * dev_pm_opp_get_voltage() - Gets the voltage corresponding to an available opp
+ * dev_pm_opp_get_voltage() - Gets the voltage corresponding to an opp
  * @opp:	opp for which voltage has to be returned for
  *
  * Return: voltage in micro volt corresponding to the opp, else
@@ -172,7 +128,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp))
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		v = tmp_opp->u_volt;
@@ -204,7 +160,7 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		f = tmp_opp->rate;
@@ -214,6 +170,94 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
 
 /**
+ * dev_pm_opp_is_turbo() - Returns if opp is turbo OPP or not
+ * @opp: opp for which turbo mode is being verified
+ *
+ * Turbo OPPs are not for normal use, and can be enabled (under certain
+ * conditions) for short duration of times to finish high throughput work
+ * quickly. Running on them for longer times may overheat the chip.
+ *
+ * Return: true if opp is turbo opp, else false.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. This means that opp which could have been fetched by
+ * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp)
+{
+	struct dev_pm_opp *tmp_opp;
+
+	opp_rcu_lockdep_assert();
+
+	tmp_opp = rcu_dereference(opp);
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return false;
+	}
+
+	return tmp_opp->turbo;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
+
+/**
+ * dev_pm_opp_get_max_clock_latency() - Get max clock latency in nanoseconds
+ * @dev:	device for which we do this operation
+ *
+ * Return: This function returns the max clock latency in nanoseconds.
+ *
+ * Locking: This function takes rcu_read_lock().
+ */
+unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	unsigned long clock_latency_ns;
+
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		clock_latency_ns = 0;
+	else
+		clock_latency_ns = dev_opp->clock_latency_ns_max;
+
+	rcu_read_unlock();
+	return clock_latency_ns;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
+
+/**
+ * dev_pm_opp_get_suspend_opp() - Get suspend opp
+ * @dev:	device for which we do this operation
+ *
+ * Return: This function returns pointer to the suspend opp if it is
+ * defined and available, otherwise it returns NULL.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev)
+{
+	struct device_opp *dev_opp;
+
+	opp_rcu_lockdep_assert();
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp) || !dev_opp->suspend_opp ||
+	    !dev_opp->suspend_opp->available)
+		return NULL;
+
+	return dev_opp->suspend_opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp);
+
+/**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list
  * @dev:	device for which we do this operation
  *
@@ -407,18 +451,57 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
+/* List-dev Helpers */
+static void _kfree_list_dev_rcu(struct rcu_head *head)
+{
+	struct device_list_opp *list_dev;
+
+	list_dev = container_of(head, struct device_list_opp, rcu_head);
+	kfree_rcu(list_dev, rcu_head);
+}
+
+static void _remove_list_dev(struct device_list_opp *list_dev,
+			     struct device_opp *dev_opp)
+{
+	list_del(&list_dev->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &list_dev->rcu_head,
+		  _kfree_list_dev_rcu);
+}
+
+struct device_list_opp *_add_list_dev(const struct device *dev,
+				      struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	list_dev = kzalloc(sizeof(*list_dev), GFP_KERNEL);
+	if (!list_dev)
+		return NULL;
+
+	/* Initialize list-dev */
+	list_dev->dev = dev;
+	list_add_rcu(&list_dev->node, &dev_opp->dev_list);
+
+	return list_dev;
+}
+
 /**
- * _add_device_opp() - Allocate a new device OPP table
+ * _add_device_opp() - Find device OPP table or allocate a new one
  * @dev:	device for which we do this operation
  *
- * New device node which uses OPPs - used when multiple devices with OPP tables
- * are maintained.
+ * It tries to find an existing table first, if it couldn't find one, it
+ * allocates a new OPP table and returns that.
  *
  * Return: valid device_opp pointer if success, else NULL.
  */
 static struct device_opp *_add_device_opp(struct device *dev)
 {
 	struct device_opp *dev_opp;
+	struct device_list_opp *list_dev;
+
+	/* Check for existing list for 'dev' first */
+	dev_opp = _find_device_opp(dev);
+	if (!IS_ERR(dev_opp))
+		return dev_opp;
 
 	/*
 	 * Allocate a new device OPP table. In the infrequent case where a new
@@ -428,7 +511,14 @@ static struct device_opp *_add_device_opp(struct device *dev)
 	if (!dev_opp)
 		return NULL;
 
-	dev_opp->dev = dev;
+	INIT_LIST_HEAD(&dev_opp->dev_list);
+
+	list_dev = _add_list_dev(dev, dev_opp);
+	if (!list_dev) {
+		kfree(dev_opp);
+		return NULL;
+	}
+
 	srcu_init_notifier_head(&dev_opp->srcu_head);
 	INIT_LIST_HEAD(&dev_opp->opp_list);
 
@@ -438,117 +528,197 @@ static struct device_opp *_add_device_opp(struct device *dev)
 }
 
 /**
- * _opp_add_dynamic() - Allocate a dynamic OPP.
- * @dev:	device for which we do this operation
- * @freq:	Frequency in Hz for this OPP
- * @u_volt:	Voltage in uVolts for this OPP
- * @dynamic:	Dynamically added OPPs.
+ * _kfree_device_rcu() - Free device_opp RCU handler
+ * @head:	RCU head
+ */
+static void _kfree_device_rcu(struct rcu_head *head)
+{
+	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+
+	kfree_rcu(device_opp, rcu_head);
+}
+
+/**
+ * _remove_device_opp() - Removes a device OPP table
+ * @dev_opp: device OPP table to be removed.
  *
- * This function adds an opp definition to the opp list and returns status.
- * The opp is made available by default and it can be controlled using
- * dev_pm_opp_enable/disable functions and may be removed by dev_pm_opp_remove.
+ * Removes/frees device OPP table it it doesn't contain any OPPs.
+ */
+static void _remove_device_opp(struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	if (!list_empty(&dev_opp->opp_list))
+		return;
+
+	list_dev = list_first_entry(&dev_opp->dev_list, struct device_list_opp,
+				    node);
+
+	_remove_list_dev(list_dev, dev_opp);
+
+	/* dev_list must be empty now */
+	WARN_ON(!list_empty(&dev_opp->dev_list));
+
+	list_del_rcu(&dev_opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
+		  _kfree_device_rcu);
+}
+
+/**
+ * _kfree_opp_rcu() - Free OPP RCU handler
+ * @head:	RCU head
+ */
+static void _kfree_opp_rcu(struct rcu_head *head)
+{
+	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
+
+	kfree_rcu(opp, rcu_head);
+}
+
+/**
+ * _opp_remove()  - Remove an OPP from a table definition
+ * @dev_opp:	points back to the device_opp struct this opp belongs to
+ * @opp:	pointer to the OPP to remove
+ * @notify:	OPP_EVENT_REMOVE notification should be sent or not
+ *
+ * This function removes an opp definition from the opp list.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * It is assumed that the caller holds required mutex for an RCU updater
+ * strategy.
+ */
+static void _opp_remove(struct device_opp *dev_opp,
+			struct dev_pm_opp *opp, bool notify)
+{
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	if (notify)
+		srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
+	list_del_rcu(&opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+
+	_remove_device_opp(dev_opp);
+}
+
+/**
+ * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * @dev:	device for which we do this operation
+ * @freq:	OPP to remove with matching 'freq'
  *
- * NOTE: "dynamic" parameter impacts OPPs added by the of_init_opp_table and
- * freed by of_free_opp_table.
+ * This function removes an opp from the opp list.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
- *
- * Return:
- * 0		On success OR
- *		Duplicate OPPs (both freq and volt are same) and opp->available
- * -EEXIST	Freq are same and volt are different OR
- *		Duplicate OPPs (both freq and volt are same) and !opp->available
- * -ENOMEM	Memory allocation failure
  */
-static int _opp_add_dynamic(struct device *dev, unsigned long freq,
-			    long u_volt, bool dynamic)
+void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 {
-	struct device_opp *dev_opp = NULL;
-	struct dev_pm_opp *opp, *new_opp;
-	struct list_head *head;
-	int ret;
-
-	/* allocate new OPP node */
-	new_opp = kzalloc(sizeof(*new_opp), GFP_KERNEL);
-	if (!new_opp)
-		return -ENOMEM;
+	struct dev_pm_opp *opp;
+	struct device_opp *dev_opp;
+	bool found = false;
 
 	/* Hold our list modification lock here */
 	mutex_lock(&dev_opp_list_lock);
 
-	/* populate the opp table */
-	new_opp->rate = freq;
-	new_opp->u_volt = u_volt;
-	new_opp->available = true;
-	new_opp->dynamic = dynamic;
-
-	/* Check for existing list for 'dev' */
 	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		dev_opp = _add_device_opp(dev);
-		if (!dev_opp) {
-			ret = -ENOMEM;
-			goto free_opp;
+	if (IS_ERR(dev_opp))
+		goto unlock;
+
+	list_for_each_entry(opp, &dev_opp->opp_list, node) {
+		if (opp->rate == freq) {
+			found = true;
+			break;
 		}
+	}
 
-		head = &dev_opp->opp_list;
-		goto list_add;
+	if (!found) {
+		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
+			 __func__, freq);
+		goto unlock;
 	}
 
+	_opp_remove(dev_opp, opp, true);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
+
+static struct dev_pm_opp *_allocate_opp(struct device *dev,
+					struct device_opp **dev_opp)
+{
+	struct dev_pm_opp *opp;
+
+	/* allocate new OPP node */
+	opp = kzalloc(sizeof(*opp), GFP_KERNEL);
+	if (!opp)
+		return NULL;
+
+	INIT_LIST_HEAD(&opp->node);
+
+	*dev_opp = _add_device_opp(dev);
+	if (!*dev_opp) {
+		kfree(opp);
+		return NULL;
+	}
+
+	return opp;
+}
+
+static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
+		    struct device_opp *dev_opp)
+{
+	struct dev_pm_opp *opp;
+	struct list_head *head = &dev_opp->opp_list;
+
 	/*
-	 * Insert new OPP in order of increasing frequency
-	 * and discard if already present
+	 * Insert new OPP in order of increasing frequency and discard if
+	 * already present.
+	 *
+	 * Need to use &dev_opp->opp_list in the condition part of the 'for'
+	 * loop, don't replace it with head otherwise it will become an infinite
+	 * loop.
 	 */
-	head = &dev_opp->opp_list;
 	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
-		if (new_opp->rate <= opp->rate)
-			break;
-		else
+		if (new_opp->rate > opp->rate) {
 			head = &opp->node;
-	}
+			continue;
+		}
 
-	/* Duplicate OPPs ? */
-	if (new_opp->rate == opp->rate) {
-		ret = opp->available && new_opp->u_volt == opp->u_volt ?
-			0 : -EEXIST;
+		if (new_opp->rate < opp->rate)
+			break;
 
+		/* Duplicate OPPs */
 		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
 			 __func__, opp->rate, opp->u_volt, opp->available,
 			 new_opp->rate, new_opp->u_volt, new_opp->available);
-		goto free_opp;
+
+		return opp->available && new_opp->u_volt == opp->u_volt ?
+			0 : -EEXIST;
 	}
 
-list_add:
 	new_opp->dev_opp = dev_opp;
 	list_add_rcu(&new_opp->node, head);
-	mutex_unlock(&dev_opp_list_lock);
 
-	/*
-	 * Notify the changes in the availability of the operable
-	 * frequency/voltage list.
-	 */
-	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
 	return 0;
-
-free_opp:
-	mutex_unlock(&dev_opp_list_lock);
-	kfree(new_opp);
-	return ret;
 }
 
 /**
- * dev_pm_opp_add()  - Add an OPP table from a table definitions
+ * _opp_add_v1() - Allocate a OPP based on v1 bindings.
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP
  * @u_volt:	Voltage in uVolts for this OPP
+ * @dynamic:	Dynamically added OPPs.
  *
  * This function adds an opp definition to the opp list and returns status.
  * The opp is made available by default and it can be controlled using
- * dev_pm_opp_enable/disable functions.
+ * dev_pm_opp_enable/disable functions and may be removed by dev_pm_opp_remove.
+ *
+ * NOTE: "dynamic" parameter impacts OPPs added by the dev_pm_opp_of_add_table
+ * and freed by dev_pm_opp_of_remove_table.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -563,107 +733,222 @@ free_opp:
  *		Duplicate OPPs (both freq and volt are same) and !opp->available
  * -ENOMEM	Memory allocation failure
  */
-int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+static int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
+		       bool dynamic)
 {
-	return _opp_add_dynamic(dev, freq, u_volt, true);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_add);
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp;
+	int ret;
 
-/**
- * _kfree_opp_rcu() - Free OPP RCU handler
- * @head:	RCU head
- */
-static void _kfree_opp_rcu(struct rcu_head *head)
-{
-	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
 
-	kfree_rcu(opp, rcu_head);
-}
+	new_opp = _allocate_opp(dev, &dev_opp);
+	if (!new_opp) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
 
-/**
- * _kfree_device_rcu() - Free device_opp RCU handler
- * @head:	RCU head
- */
-static void _kfree_device_rcu(struct rcu_head *head)
-{
-	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+	/* populate the opp table */
+	new_opp->rate = freq;
+	new_opp->u_volt = u_volt;
+	new_opp->available = true;
+	new_opp->dynamic = dynamic;
 
-	kfree_rcu(device_opp, rcu_head);
-}
+	ret = _opp_add(dev, new_opp, dev_opp);
+	if (ret)
+		goto free_opp;
+
+	mutex_unlock(&dev_opp_list_lock);
 
-/**
- * _opp_remove()  - Remove an OPP from a table definition
- * @dev_opp:	points back to the device_opp struct this opp belongs to
- * @opp:	pointer to the OPP to remove
- *
- * This function removes an opp definition from the opp list.
- *
- * Locking: The internal device_opp and opp structures are RCU protected.
- * It is assumed that the caller holds required mutex for an RCU updater
- * strategy.
- */
-static void _opp_remove(struct device_opp *dev_opp,
-			struct dev_pm_opp *opp)
-{
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
-	list_del_rcu(&opp->node);
-	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
+	return 0;
+
+free_opp:
+	_opp_remove(dev_opp, new_opp, false);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+	return ret;
+}
+
+/* TODO: Support multiple regulators */
+static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev)
+{
+	u32 microvolt[3] = {0};
+	u32 val;
+	int count, ret;
+
+	/* Missing property isn't a problem, but an invalid entry is */
+	if (!of_find_property(opp->np, "opp-microvolt", NULL))
+		return 0;
 
-	if (list_empty(&dev_opp->opp_list)) {
-		list_del_rcu(&dev_opp->node);
-		call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
-			  _kfree_device_rcu);
+	count = of_property_count_u32_elems(opp->np, "opp-microvolt");
+	if (count < 0) {
+		dev_err(dev, "%s: Invalid opp-microvolt property (%d)\n",
+			__func__, count);
+		return count;
 	}
+
+	/* There can be one or three elements here */
+	if (count != 1 && count != 3) {
+		dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n",
+			__func__, count);
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32_array(opp->np, "opp-microvolt", microvolt,
+					 count);
+	if (ret) {
+		dev_err(dev, "%s: error parsing opp-microvolt: %d\n", __func__,
+			ret);
+		return -EINVAL;
+	}
+
+	opp->u_volt = microvolt[0];
+	opp->u_volt_min = microvolt[1];
+	opp->u_volt_max = microvolt[2];
+
+	if (!of_property_read_u32(opp->np, "opp-microamp", &val))
+		opp->u_amp = val;
+
+	return 0;
 }
 
 /**
- * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
  * @dev:	device for which we do this operation
- * @freq:	OPP to remove with matching 'freq'
+ * @np:		device node
  *
- * This function removes an opp from the opp list.
+ * This function adds an opp definition to the opp list and returns status. The
+ * opp can be controlled using dev_pm_opp_enable/disable functions and may be
+ * removed by dev_pm_opp_remove.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -EINVAL	Failed parsing the OPP node
  */
-void dev_pm_opp_remove(struct device *dev, unsigned long freq)
+static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 {
-	struct dev_pm_opp *opp;
 	struct device_opp *dev_opp;
-	bool found = false;
+	struct dev_pm_opp *new_opp;
+	u64 rate;
+	u32 val;
+	int ret;
 
 	/* Hold our list modification lock here */
 	mutex_lock(&dev_opp_list_lock);
 
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp))
+	new_opp = _allocate_opp(dev, &dev_opp);
+	if (!new_opp) {
+		ret = -ENOMEM;
 		goto unlock;
+	}
 
-	list_for_each_entry(opp, &dev_opp->opp_list, node) {
-		if (opp->rate == freq) {
-			found = true;
-			break;
-		}
+	ret = of_property_read_u64(np, "opp-hz", &rate);
+	if (ret < 0) {
+		dev_err(dev, "%s: opp-hz not found\n", __func__);
+		goto free_opp;
 	}
 
-	if (!found) {
-		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
-			 __func__, freq);
-		goto unlock;
+	/*
+	 * Rate is defined as an unsigned long in clk API, and so casting
+	 * explicitly to its type. Must be fixed once rate is 64 bit
+	 * guaranteed in clk API.
+	 */
+	new_opp->rate = (unsigned long)rate;
+	new_opp->turbo = of_property_read_bool(np, "turbo-mode");
+
+	new_opp->np = np;
+	new_opp->dynamic = false;
+	new_opp->available = true;
+
+	if (!of_property_read_u32(np, "clock-latency-ns", &val))
+		new_opp->clock_latency_ns = val;
+
+	ret = opp_parse_supplies(new_opp, dev);
+	if (ret)
+		goto free_opp;
+
+	ret = _opp_add(dev, new_opp, dev_opp);
+	if (ret)
+		goto free_opp;
+
+	/* OPP to select on device suspend */
+	if (of_property_read_bool(np, "opp-suspend")) {
+		if (dev_opp->suspend_opp)
+			dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n",
+				 __func__, dev_opp->suspend_opp->rate,
+				 new_opp->rate);
+		else
+			dev_opp->suspend_opp = new_opp;
 	}
 
-	_opp_remove(dev_opp, opp);
+	if (new_opp->clock_latency_ns > dev_opp->clock_latency_ns_max)
+		dev_opp->clock_latency_ns_max = new_opp->clock_latency_ns;
+
+	mutex_unlock(&dev_opp_list_lock);
+
+	pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n",
+		 __func__, new_opp->turbo, new_opp->rate, new_opp->u_volt,
+		 new_opp->u_volt_min, new_opp->u_volt_max,
+		 new_opp->clock_latency_ns);
+
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
+	return 0;
+
+free_opp:
+	_opp_remove(dev_opp, new_opp, false);
 unlock:
 	mutex_unlock(&dev_opp_list_lock);
+	return ret;
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
+
+/**
+ * dev_pm_opp_add()  - Add an OPP table from a table definitions
+ * @dev:	device for which we do this operation
+ * @freq:	Frequency in Hz for this OPP
+ * @u_volt:	Voltage in uVolts for this OPP
+ *
+ * This function adds an opp definition to the opp list and returns status.
+ * The opp is made available by default and it can be controlled using
+ * dev_pm_opp_enable/disable functions.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ */
+int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+{
+	return _opp_add_v1(dev, freq, u_volt, true);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 
 /**
  * _opp_set_availability() - helper to set the availability of an opp
@@ -675,7 +960,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
  * share a common logic which is isolated here.
  *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
  * successful.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
@@ -763,7 +1048,7 @@ unlock:
  * mutex locking or synchronize_rcu() blocking calls cannot be used.
  *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
  * successful.
  */
 int dev_pm_opp_enable(struct device *dev, unsigned long freq)
@@ -789,7 +1074,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable);
  * mutex locking or synchronize_rcu() blocking calls cannot be used.
  *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
  * successful.
  */
 int dev_pm_opp_disable(struct device *dev, unsigned long freq)
@@ -825,28 +1110,127 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
 
 #ifdef CONFIG_OF
 /**
- * of_init_opp_table() - Initialize opp table from device tree
+ * dev_pm_opp_of_remove_table() - Free OPP table entries created from static DT
+ *				  entries
  * @dev:	device pointer used to lookup device OPPs.
  *
- * Register the initial OPP table with the OPP library for given device.
+ * Free OPPs created using static entries present in DT.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function indirectly uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
- *
- * Return:
- * 0		On success OR
- *		Duplicate OPPs (both freq and volt are same) and opp->available
- * -EEXIST	Freq are same and volt are different OR
- *		Duplicate OPPs (both freq and volt are same) and !opp->available
- * -ENOMEM	Memory allocation failure
- * -ENODEV	when 'operating-points' property is not found or is invalid data
- *		in device node.
- * -ENODATA	when empty 'operating-points' property is found
  */
-int of_init_opp_table(struct device *dev)
+void dev_pm_opp_of_remove_table(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *opp, *tmp;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Check for existing list for 'dev' */
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int error = PTR_ERR(dev_opp);
+
+		if (error != -ENODEV)
+			WARN(1, "%s: dev_opp: %d\n",
+			     IS_ERR_OR_NULL(dev) ?
+					"Invalid device" : dev_name(dev),
+			     error);
+		goto unlock;
+	}
+
+	/* Find if dev_opp manages a single device */
+	if (list_is_singular(&dev_opp->dev_list)) {
+		/* Free static OPPs */
+		list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
+			if (!opp->dynamic)
+				_opp_remove(dev_opp, opp, true);
+		}
+	} else {
+		_remove_list_dev(_find_list_dev(dev, dev_opp), dev_opp);
+	}
+
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
+
+/* Returns opp descriptor node for a device, caller must do of_node_put() */
+struct device_node *_of_get_opp_desc_node(struct device *dev)
+{
+	/*
+	 * TODO: Support for multiple OPP tables.
+	 *
+	 * There should be only ONE phandle present in "operating-points-v2"
+	 * property.
+	 */
+
+	return of_parse_phandle(dev->of_node, "operating-points-v2", 0);
+}
+
+/* Initializes OPP tables based on new bindings */
+static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
+{
+	struct device_node *np;
+	struct device_opp *dev_opp;
+	int ret = 0, count = 0;
+
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = _managed_opp(opp_np);
+	if (dev_opp) {
+		/* OPPs are already managed */
+		if (!_add_list_dev(dev, dev_opp))
+			ret = -ENOMEM;
+		mutex_unlock(&dev_opp_list_lock);
+		return ret;
+	}
+	mutex_unlock(&dev_opp_list_lock);
+
+	/* We have opp-list node now, iterate over it and add OPPs */
+	for_each_available_child_of_node(opp_np, np) {
+		count++;
+
+		ret = _opp_add_static_v2(dev, np);
+		if (ret) {
+			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
+				ret);
+			goto free_table;
+		}
+	}
+
+	/* There should be one of more OPP defined */
+	if (WARN_ON(!count))
+		return -ENOENT;
+
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = _find_device_opp(dev);
+	if (WARN_ON(IS_ERR(dev_opp))) {
+		ret = PTR_ERR(dev_opp);
+		mutex_unlock(&dev_opp_list_lock);
+		goto free_table;
+	}
+
+	dev_opp->np = opp_np;
+	dev_opp->shared_opp = of_property_read_bool(opp_np, "opp-shared");
+
+	mutex_unlock(&dev_opp_list_lock);
+
+	return 0;
+
+free_table:
+	dev_pm_opp_of_remove_table(dev);
+
+	return ret;
+}
+
+/* Initializes OPP tables based on old-deprecated bindings */
+static int _of_add_opp_table_v1(struct device *dev)
 {
 	const struct property *prop;
 	const __be32 *val;
@@ -873,7 +1257,7 @@ int of_init_opp_table(struct device *dev)
 		unsigned long freq = be32_to_cpup(val++) * 1000;
 		unsigned long volt = be32_to_cpup(val++);
 
-		if (_opp_add_dynamic(dev, freq, volt, false))
+		if (_opp_add_v1(dev, freq, volt, false))
 			dev_warn(dev, "%s: Failed to add OPP %ld\n",
 				 __func__, freq);
 		nr -= 2;
@@ -881,47 +1265,52 @@ int of_init_opp_table(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(of_init_opp_table);
 
 /**
- * of_free_opp_table() - Free OPP table entries created from static DT entries
+ * dev_pm_opp_of_add_table() - Initialize opp table from device tree
  * @dev:	device pointer used to lookup device OPPs.
  *
- * Free OPPs created using static entries present in DT.
+ * Register the initial OPP table with the OPP library for given device.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function indirectly uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -ENODEV	when 'operating-points' property is not found or is invalid data
+ *		in device node.
+ * -ENODATA	when empty 'operating-points' property is found
+ * -EINVAL	when invalid entries are found in opp-v2 table
  */
-void of_free_opp_table(struct device *dev)
+int dev_pm_opp_of_add_table(struct device *dev)
 {
-	struct device_opp *dev_opp;
-	struct dev_pm_opp *opp, *tmp;
+	struct device_node *opp_np;
+	int ret;
 
-	/* Check for existing list for 'dev' */
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		int error = PTR_ERR(dev_opp);
-		if (error != -ENODEV)
-			WARN(1, "%s: dev_opp: %d\n",
-			     IS_ERR_OR_NULL(dev) ?
-					"Invalid device" : dev_name(dev),
-			     error);
-		return;
+	/*
+	 * OPPs have two version of bindings now. The older one is deprecated,
+	 * try for the new binding first.
+	 */
+	opp_np = _of_get_opp_desc_node(dev);
+	if (!opp_np) {
+		/*
+		 * Try old-deprecated bindings for backward compatibility with
+		 * older dtbs.
+		 */
+		return _of_add_opp_table_v1(dev);
 	}
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
-
-	/* Free static OPPs */
-	list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
-		if (!opp->dynamic)
-			_opp_remove(dev_opp, opp);
-	}
+	ret = _of_add_opp_table_v2(dev, opp_np);
+	of_node_put(opp_np);
 
-	mutex_unlock(&dev_opp_list_lock);
+	return ret;
 }
-EXPORT_SYMBOL_GPL(of_free_opp_table);
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
 #endif
diff --git a/kernel/drivers/base/power/opp/cpu.c b/kernel/drivers/base/power/opp/cpu.c
new file mode 100644
index 000000000..7b445e88a
--- /dev/null
+++ b/kernel/drivers/base/power/opp/cpu.c
@@ -0,0 +1,270 @@
+/*
+ * Generic OPP helper interface for CPU device
+ *
+ * Copyright (C) 2009-2014 Texas Instruments Incorporated.
+ *	Nishanth Menon
+ *	Romit Dasgupta
+ *	Kevin Hilman
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+
+#include "opp.h"
+
+#ifdef CONFIG_CPU_FREQ
+
+/**
+ * dev_pm_opp_init_cpufreq_table() - create a cpufreq table for a device
+ * @dev:	device for which we do this operation
+ * @table:	Cpufreq table returned back to caller
+ *
+ * Generate a cpufreq table for a provided device- this assumes that the
+ * opp list is already initialized and ready for usage.
+ *
+ * This function allocates required memory for the cpufreq table. It is
+ * expected that the caller does the required maintenance such as freeing
+ * the table as required.
+ *
+ * Returns -EINVAL for bad pointers, -ENODEV if the device is not found, -ENOMEM
+ * if no memory available for the operation (table is not populated), returns 0
+ * if successful and table is populated.
+ *
+ * WARNING: It is  important for the callers to ensure refreshing their copy of
+ * the table if any of the mentioned functions have been invoked in the interim.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Since we just use the regular accessor functions to access the internal data
+ * structures, we use RCU read lock inside this function. As a result, users of
+ * this function DONOT need to use explicit locks for invoking.
+ */
+int dev_pm_opp_init_cpufreq_table(struct device *dev,
+				  struct cpufreq_frequency_table **table)
+{
+	struct dev_pm_opp *opp;
+	struct cpufreq_frequency_table *freq_table = NULL;
+	int i, max_opps, ret = 0;
+	unsigned long rate;
+
+	rcu_read_lock();
+
+	max_opps = dev_pm_opp_get_opp_count(dev);
+	if (max_opps <= 0) {
+		ret = max_opps ? max_opps : -ENODATA;
+		goto out;
+	}
+
+	freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC);
+	if (!freq_table) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0, rate = 0; i < max_opps; i++, rate++) {
+		/* find next rate */
+		opp = dev_pm_opp_find_freq_ceil(dev, &rate);
+		if (IS_ERR(opp)) {
+			ret = PTR_ERR(opp);
+			goto out;
+		}
+		freq_table[i].driver_data = i;
+		freq_table[i].frequency = rate / 1000;
+
+		/* Is Boost/turbo opp ? */
+		if (dev_pm_opp_is_turbo(opp))
+			freq_table[i].flags = CPUFREQ_BOOST_FREQ;
+	}
+
+	freq_table[i].driver_data = i;
+	freq_table[i].frequency = CPUFREQ_TABLE_END;
+
+	*table = &freq_table[0];
+
+out:
+	rcu_read_unlock();
+	if (ret)
+		kfree(freq_table);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_init_cpufreq_table);
+
+/**
+ * dev_pm_opp_free_cpufreq_table() - free the cpufreq table
+ * @dev:	device for which we do this operation
+ * @table:	table to free
+ *
+ * Free up the table allocated by dev_pm_opp_init_cpufreq_table
+ */
+void dev_pm_opp_free_cpufreq_table(struct device *dev,
+				   struct cpufreq_frequency_table **table)
+{
+	if (!table)
+		return;
+
+	kfree(*table);
+	*table = NULL;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_free_cpufreq_table);
+#endif	/* CONFIG_CPU_FREQ */
+
+/* Required only for V1 bindings, as v2 can manage it from DT itself */
+int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask)
+{
+	struct device_list_opp *list_dev;
+	struct device_opp *dev_opp;
+	struct device *dev;
+	int cpu, ret = 0;
+
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = _find_device_opp(cpu_dev);
+	if (IS_ERR(dev_opp)) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	for_each_cpu(cpu, cpumask) {
+		if (cpu == cpu_dev->id)
+			continue;
+
+		dev = get_cpu_device(cpu);
+		if (!dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
+
+		list_dev = _add_list_dev(dev, dev_opp);
+		if (!list_dev) {
+			dev_err(dev, "%s: failed to add list-dev for cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
+	}
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus);
+
+#ifdef CONFIG_OF
+void dev_pm_opp_of_cpumask_remove_table(cpumask_var_t cpumask)
+{
+	struct device *cpu_dev;
+	int cpu;
+
+	WARN_ON(cpumask_empty(cpumask));
+
+	for_each_cpu(cpu, cpumask) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__,
+			       cpu);
+			continue;
+		}
+
+		dev_pm_opp_of_remove_table(cpu_dev);
+	}
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table);
+
+int dev_pm_opp_of_cpumask_add_table(cpumask_var_t cpumask)
+{
+	struct device *cpu_dev;
+	int cpu, ret = 0;
+
+	WARN_ON(cpumask_empty(cpumask));
+
+	for_each_cpu(cpu, cpumask) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__,
+			       cpu);
+			continue;
+		}
+
+		ret = dev_pm_opp_of_add_table(cpu_dev);
+		if (ret) {
+			pr_err("%s: couldn't find opp table for cpu:%d, %d\n",
+			       __func__, cpu, ret);
+
+			/* Free all other OPPs */
+			dev_pm_opp_of_cpumask_remove_table(cpumask);
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_add_table);
+
+/*
+ * Works only for OPP v2 bindings.
+ *
+ * cpumask should be already set to mask of cpu_dev->id.
+ * Returns -ENOENT if operating-points-v2 bindings aren't supported.
+ */
+int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask)
+{
+	struct device_node *np, *tmp_np;
+	struct device *tcpu_dev;
+	int cpu, ret = 0;
+
+	/* Get OPP descriptor node */
+	np = _of_get_opp_desc_node(cpu_dev);
+	if (!np) {
+		dev_dbg(cpu_dev, "%s: Couldn't find cpu_dev node.\n", __func__);
+		return -ENOENT;
+	}
+
+	/* OPPs are shared ? */
+	if (!of_property_read_bool(np, "opp-shared"))
+		goto put_cpu_node;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == cpu_dev->id)
+			continue;
+
+		tcpu_dev = get_cpu_device(cpu);
+		if (!tcpu_dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			ret = -ENODEV;
+			goto put_cpu_node;
+		}
+
+		/* Get OPP descriptor node */
+		tmp_np = _of_get_opp_desc_node(tcpu_dev);
+		if (!tmp_np) {
+			dev_err(tcpu_dev, "%s: Couldn't find tcpu_dev node.\n",
+				__func__);
+			ret = -ENOENT;
+			goto put_cpu_node;
+		}
+
+		/* CPUs are sharing opp node */
+		if (np == tmp_np)
+			cpumask_set_cpu(cpu, cpumask);
+
+		of_node_put(tmp_np);
+	}
+
+put_cpu_node:
+	of_node_put(np);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_sharing_cpus);
+#endif
diff --git a/kernel/drivers/base/power/opp/opp.h b/kernel/drivers/base/power/opp/opp.h
new file mode 100644
index 000000000..7366b2aa8
--- /dev/null
+++ b/kernel/drivers/base/power/opp/opp.h
@@ -0,0 +1,146 @@
+/*
+ * Generic OPP Interface
+ *
+ * Copyright (C) 2009-2010 Texas Instruments Incorporated.
+ *	Nishanth Menon
+ *	Romit Dasgupta
+ *	Kevin Hilman
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __DRIVER_OPP_H__
+#define __DRIVER_OPP_H__
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/pm_opp.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+
+/* Lock to allow exclusive modification to the device and opp lists */
+extern struct mutex dev_opp_list_lock;
+
+/*
+ * Internal data structure organization with the OPP layer library is as
+ * follows:
+ * dev_opp_list (root)
+ *	|- device 1 (represents voltage domain 1)
+ *	|	|- opp 1 (availability, freq, voltage)
+ *	|	|- opp 2 ..
+ *	...	...
+ *	|	`- opp n ..
+ *	|- device 2 (represents the next voltage domain)
+ *	...
+ *	`- device m (represents mth voltage domain)
+ * device 1, 2.. are represented by dev_opp structure while each opp
+ * is represented by the opp structure.
+ */
+
+/**
+ * struct dev_pm_opp - Generic OPP description structure
+ * @node:	opp list node. The nodes are maintained throughout the lifetime
+ *		of boot. It is expected only an optimal set of OPPs are
+ *		added to the library by the SoC framework.
+ *		RCU usage: opp list is traversed with RCU locks. node
+ *		modification is possible realtime, hence the modifications
+ *		are protected by the dev_opp_list_lock for integrity.
+ *		IMPORTANT: the opp nodes should be maintained in increasing
+ *		order.
+ * @dynamic:	not-created from static DT entries.
+ * @available:	true/false - marks if this OPP as available or not
+ * @turbo:	true if turbo (boost) OPP
+ * @rate:	Frequency in hertz
+ * @u_volt:	Target voltage in microvolts corresponding to this OPP
+ * @u_volt_min:	Minimum voltage in microvolts corresponding to this OPP
+ * @u_volt_max:	Maximum voltage in microvolts corresponding to this OPP
+ * @u_amp:	Maximum current drawn by the device in microamperes
+ * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
+ *		frequency from any other OPP's frequency.
+ * @dev_opp:	points back to the device_opp struct this opp belongs to
+ * @rcu_head:	RCU callback head used for deferred freeing
+ * @np:		OPP's device node.
+ *
+ * This structure stores the OPP information for a given device.
+ */
+struct dev_pm_opp {
+	struct list_head node;
+
+	bool available;
+	bool dynamic;
+	bool turbo;
+	unsigned long rate;
+
+	unsigned long u_volt;
+	unsigned long u_volt_min;
+	unsigned long u_volt_max;
+	unsigned long u_amp;
+	unsigned long clock_latency_ns;
+
+	struct device_opp *dev_opp;
+	struct rcu_head rcu_head;
+
+	struct device_node *np;
+};
+
+/**
+ * struct device_list_opp - devices managed by 'struct device_opp'
+ * @node:	list node
+ * @dev:	device to which the struct object belongs
+ * @rcu_head:	RCU callback head used for deferred freeing
+ *
+ * This is an internal data structure maintaining the list of devices that are
+ * managed by 'struct device_opp'.
+ */
+struct device_list_opp {
+	struct list_head node;
+	const struct device *dev;
+	struct rcu_head rcu_head;
+};
+
+/**
+ * struct device_opp - Device opp structure
+ * @node:	list node - contains the devices with OPPs that
+ *		have been registered. Nodes once added are not modified in this
+ *		list.
+ *		RCU usage: nodes are not modified in the list of device_opp,
+ *		however addition is possible and is secured by dev_opp_list_lock
+ * @srcu_head:	notifier head to notify the OPP availability changes.
+ * @rcu_head:	RCU callback head used for deferred freeing
+ * @dev_list:	list of devices that share these OPPs
+ * @opp_list:	list of opps
+ * @np:		struct device_node pointer for opp's DT node.
+ * @shared_opp: OPP is shared between multiple devices.
+ *
+ * This is an internal data structure maintaining the link to opps attached to
+ * a device. This structure is not meant to be shared to users as it is
+ * meant for book keeping and private to OPP library.
+ *
+ * Because the opp structures can be used from both rcu and srcu readers, we
+ * need to wait for the grace period of both of them before freeing any
+ * resources. And so we have used kfree_rcu() from within call_srcu() handlers.
+ */
+struct device_opp {
+	struct list_head node;
+
+	struct srcu_notifier_head srcu_head;
+	struct rcu_head rcu_head;
+	struct list_head dev_list;
+	struct list_head opp_list;
+
+	struct device_node *np;
+	unsigned long clock_latency_ns_max;
+	bool shared_opp;
+	struct dev_pm_opp *suspend_opp;
+};
+
+/* Routines internal to opp core */
+struct device_opp *_find_device_opp(struct device *dev);
+struct device_list_opp *_add_list_dev(const struct device *dev,
+				      struct device_opp *dev_opp);
+struct device_node *_of_get_opp_desc_node(struct device *dev);
+
+#endif		/* __DRIVER_OPP_H__ */
diff --git a/kernel/drivers/base/power/power.h b/kernel/drivers/base/power/power.h
index b6b8a273c..998fa6b23 100644
--- a/kernel/drivers/base/power/power.h
+++ b/kernel/drivers/base/power/power.h
@@ -20,6 +20,46 @@ static inline void pm_runtime_early_init(struct device *dev)
 extern void pm_runtime_init(struct device *dev);
 extern void pm_runtime_remove(struct device *dev);
 
+struct wake_irq {
+	struct device *dev;
+	int irq;
+	bool dedicated_irq:1;
+};
+
+extern void dev_pm_arm_wake_irq(struct wake_irq *wirq);
+extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq);
+
+#ifdef CONFIG_PM_SLEEP
+
+extern int device_wakeup_attach_irq(struct device *dev,
+				    struct wake_irq *wakeirq);
+extern void device_wakeup_detach_irq(struct device *dev);
+extern void device_wakeup_arm_wake_irqs(void);
+extern void device_wakeup_disarm_wake_irqs(void);
+
+#else
+
+static inline int
+device_wakeup_attach_irq(struct device *dev,
+			 struct wake_irq *wakeirq)
+{
+	return 0;
+}
+
+static inline void device_wakeup_detach_irq(struct device *dev)
+{
+}
+
+static inline void device_wakeup_arm_wake_irqs(void)
+{
+}
+
+static inline void device_wakeup_disarm_wake_irqs(void)
+{
+}
+
+#endif /* CONFIG_PM_SLEEP */
+
 /*
  * sysfs.c
  */
@@ -33,6 +73,8 @@ extern int pm_qos_sysfs_add_resume_latency(struct device *dev);
 extern void pm_qos_sysfs_remove_resume_latency(struct device *dev);
 extern int pm_qos_sysfs_add_flags(struct device *dev);
 extern void pm_qos_sysfs_remove_flags(struct device *dev);
+extern int pm_qos_sysfs_add_latency_tolerance(struct device *dev);
+extern void pm_qos_sysfs_remove_latency_tolerance(struct device *dev);
 
 #else /* CONFIG_PM */
 
@@ -52,6 +94,14 @@ 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) {}
 
+static inline void dev_pm_arm_wake_irq(struct wake_irq *wirq)
+{
+}
+
+static inline void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
+{
+}
+
 #endif
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/kernel/drivers/base/power/qos.c b/kernel/drivers/base/power/qos.c
index e56d538d0..7f3646e45 100644
--- a/kernel/drivers/base/power/qos.c
+++ b/kernel/drivers/base/power/qos.c
@@ -883,3 +883,40 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
 	mutex_unlock(&dev_pm_qos_mtx);
 	return ret;
 }
+
+/**
+ * dev_pm_qos_expose_latency_tolerance - Expose latency tolerance to userspace
+ * @dev: Device whose latency tolerance to expose
+ */
+int dev_pm_qos_expose_latency_tolerance(struct device *dev)
+{
+	int ret;
+
+	if (!dev->power.set_latency_tolerance)
+		return -EINVAL;
+
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+	ret = pm_qos_sysfs_add_latency_tolerance(dev);
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_tolerance);
+
+/**
+ * dev_pm_qos_hide_latency_tolerance - Hide latency tolerance from userspace
+ * @dev: Device whose latency tolerance to hide
+ */
+void dev_pm_qos_hide_latency_tolerance(struct device *dev)
+{
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+	pm_qos_sysfs_remove_latency_tolerance(dev);
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+
+	/* Remove the request from user space now */
+	pm_runtime_get_sync(dev);
+	dev_pm_qos_update_user_latency_tolerance(dev,
+		PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT);
+	pm_runtime_put(dev);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_tolerance);
diff --git a/kernel/drivers/base/power/runtime.c b/kernel/drivers/base/power/runtime.c
index 5070c4fe8..e1a10a03d 100644
--- a/kernel/drivers/base/power/runtime.c
+++ b/kernel/drivers/base/power/runtime.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <linux/export.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_wakeirq.h>
 #include <trace/events/rpm.h>
 #include "power.h"
 
@@ -514,6 +515,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
 
+	dev_pm_enable_wake_irq(dev);
 	retval = rpm_callback(callback, dev);
 	if (retval)
 		goto fail;
@@ -552,6 +554,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	return retval;
 
  fail:
+	dev_pm_disable_wake_irq(dev);
 	__update_runtime_status(dev, RPM_ACTIVE);
 	dev->power.deferred_resume = false;
 	wake_up_all(&dev->power.wait_queue);
@@ -734,13 +737,16 @@ static int rpm_resume(struct device *dev, int rpmflags)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_resume);
 
+	dev_pm_disable_wake_irq(dev);
 	retval = rpm_callback(callback, dev);
 	if (retval) {
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_cancel_pending(dev);
+		dev_pm_enable_wake_irq(dev);
 	} else {
  no_callback:
 		__update_runtime_status(dev, RPM_ACTIVE);
+		pm_runtime_mark_last_busy(dev);
 		if (parent)
 			atomic_inc(&parent->power.child_count);
 	}
diff --git a/kernel/drivers/base/power/sysfs.c b/kernel/drivers/base/power/sysfs.c
index d2be3f9c2..a7b46798c 100644
--- a/kernel/drivers/base/power/sysfs.c
+++ b/kernel/drivers/base/power/sysfs.c
@@ -738,6 +738,17 @@ void pm_qos_sysfs_remove_flags(struct device *dev)
 	sysfs_unmerge_group(&dev->kobj, &pm_qos_flags_attr_group);
 }
 
+int pm_qos_sysfs_add_latency_tolerance(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj,
+				 &pm_qos_latency_tolerance_attr_group);
+}
+
+void pm_qos_sysfs_remove_latency_tolerance(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group);
+}
+
 void rpm_sysfs_remove(struct device *dev)
 {
 	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
diff --git a/kernel/drivers/base/power/wakeirq.c b/kernel/drivers/base/power/wakeirq.c
new file mode 100644
index 000000000..0d77cd6fd
--- /dev/null
+++ b/kernel/drivers/base/power/wakeirq.c
@@ -0,0 +1,277 @@
+/*
+ * wakeirq.c - Device wakeirq helper functions
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/pm_runtime.h>
+#include <linux/pm_wakeirq.h>
+
+#include "power.h"
+
+/**
+ * dev_pm_attach_wake_irq - Attach device interrupt as a wake IRQ
+ * @dev: Device entry
+ * @irq: Device wake-up capable interrupt
+ * @wirq: Wake irq specific data
+ *
+ * Internal function to attach either a device IO interrupt or a
+ * dedicated wake-up interrupt as a wake IRQ.
+ */
+static int dev_pm_attach_wake_irq(struct device *dev, int irq,
+				  struct wake_irq *wirq)
+{
+	unsigned long flags;
+	int err;
+
+	if (!dev || !wirq)
+		return -EINVAL;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	if (dev_WARN_ONCE(dev, dev->power.wakeirq,
+			  "wake irq already initialized\n")) {
+		spin_unlock_irqrestore(&dev->power.lock, flags);
+		return -EEXIST;
+	}
+
+	err = device_wakeup_attach_irq(dev, wirq);
+	if (!err)
+		dev->power.wakeirq = wirq;
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+	return err;
+}
+
+/**
+ * dev_pm_set_wake_irq - Attach device IO interrupt as wake IRQ
+ * @dev: Device entry
+ * @irq: Device IO interrupt
+ *
+ * Attach a device IO interrupt as a wake IRQ. The wake IRQ gets
+ * automatically configured for wake-up from suspend  based
+ * on the device specific sysfs wakeup entry. Typically called
+ * during driver probe after calling device_init_wakeup().
+ */
+int dev_pm_set_wake_irq(struct device *dev, int irq)
+{
+	struct wake_irq *wirq;
+	int err;
+
+	if (irq < 0)
+		return -EINVAL;
+
+	wirq = kzalloc(sizeof(*wirq), GFP_KERNEL);
+	if (!wirq)
+		return -ENOMEM;
+
+	wirq->dev = dev;
+	wirq->irq = irq;
+
+	err = dev_pm_attach_wake_irq(dev, irq, wirq);
+	if (err)
+		kfree(wirq);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(dev_pm_set_wake_irq);
+
+/**
+ * dev_pm_clear_wake_irq - Detach a device IO interrupt wake IRQ
+ * @dev: Device entry
+ *
+ * Detach a device wake IRQ and free resources.
+ *
+ * Note that it's OK for drivers to call this without calling
+ * dev_pm_set_wake_irq() as all the driver instances may not have
+ * a wake IRQ configured. This avoid adding wake IRQ specific
+ * checks into the drivers.
+ */
+void dev_pm_clear_wake_irq(struct device *dev)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+	unsigned long flags;
+
+	if (!wirq)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	device_wakeup_detach_irq(dev);
+	dev->power.wakeirq = NULL;
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	if (wirq->dedicated_irq)
+		free_irq(wirq->irq, wirq);
+	kfree(wirq);
+}
+EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq);
+
+/**
+ * handle_threaded_wake_irq - Handler for dedicated wake-up interrupts
+ * @irq: Device specific dedicated wake-up interrupt
+ * @_wirq: Wake IRQ data
+ *
+ * Some devices have a separate wake-up interrupt in addition to the
+ * device IO interrupt. The wake-up interrupt signals that a device
+ * should be woken up from it's idle state. This handler uses device
+ * specific pm_runtime functions to wake the device, and then it's
+ * up to the device to do whatever it needs to. Note that as the
+ * device may need to restore context and start up regulators, we
+ * use a threaded IRQ.
+ *
+ * Also note that we are not resending the lost device interrupts.
+ * We assume that the wake-up interrupt just needs to wake-up the
+ * device, and then device's pm_runtime_resume() can deal with the
+ * situation.
+ */
+static irqreturn_t handle_threaded_wake_irq(int irq, void *_wirq)
+{
+	struct wake_irq *wirq = _wirq;
+	int res;
+
+	/* We don't want RPM_ASYNC or RPM_NOWAIT here */
+	res = pm_runtime_resume(wirq->dev);
+	if (res < 0)
+		dev_warn(wirq->dev,
+			 "wake IRQ with no resume: %i\n", res);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * dev_pm_set_dedicated_wake_irq - Request a dedicated wake-up interrupt
+ * @dev: Device entry
+ * @irq: Device wake-up interrupt
+ *
+ * Unless your hardware has separate wake-up interrupts in addition
+ * to the device IO interrupts, you don't need this.
+ *
+ * Sets up a threaded interrupt handler for a device that has
+ * a dedicated wake-up interrupt in addition to the device IO
+ * interrupt.
+ *
+ * The interrupt starts disabled, and needs to be managed for
+ * the device by the bus code or the device driver using
+ * dev_pm_enable_wake_irq() and dev_pm_disable_wake_irq()
+ * functions.
+ */
+int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
+{
+	struct wake_irq *wirq;
+	int err;
+
+	if (irq < 0)
+		return -EINVAL;
+
+	wirq = kzalloc(sizeof(*wirq), GFP_KERNEL);
+	if (!wirq)
+		return -ENOMEM;
+
+	wirq->dev = dev;
+	wirq->irq = irq;
+	wirq->dedicated_irq = true;
+	irq_set_status_flags(irq, IRQ_NOAUTOEN);
+
+	/*
+	 * Consumer device may need to power up and restore state
+	 * so we use a threaded irq.
+	 */
+	err = request_threaded_irq(irq, NULL, handle_threaded_wake_irq,
+				   IRQF_ONESHOT, dev_name(dev), wirq);
+	if (err)
+		goto err_free;
+
+	err = dev_pm_attach_wake_irq(dev, irq, wirq);
+	if (err)
+		goto err_free_irq;
+
+	return err;
+
+err_free_irq:
+	free_irq(irq, wirq);
+err_free:
+	kfree(wirq);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq);
+
+/**
+ * dev_pm_enable_wake_irq - Enable device wake-up interrupt
+ * @dev: Device
+ *
+ * Called from the bus code or the device driver for
+ * runtime_suspend() to enable the wake-up interrupt while
+ * the device is running.
+ *
+ * Note that for runtime_suspend()) the wake-up interrupts
+ * should be unconditionally enabled unlike for suspend()
+ * that is conditional.
+ */
+void dev_pm_enable_wake_irq(struct device *dev)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (wirq && wirq->dedicated_irq)
+		enable_irq(wirq->irq);
+}
+EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq);
+
+/**
+ * dev_pm_disable_wake_irq - Disable device wake-up interrupt
+ * @dev: Device
+ *
+ * Called from the bus code or the device driver for
+ * runtime_resume() to disable the wake-up interrupt while
+ * the device is running.
+ */
+void dev_pm_disable_wake_irq(struct device *dev)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (wirq && wirq->dedicated_irq)
+		disable_irq_nosync(wirq->irq);
+}
+EXPORT_SYMBOL_GPL(dev_pm_disable_wake_irq);
+
+/**
+ * dev_pm_arm_wake_irq - Arm device wake-up
+ * @wirq: Device wake-up interrupt
+ *
+ * Sets up the wake-up event conditionally based on the
+ * device_may_wake().
+ */
+void dev_pm_arm_wake_irq(struct wake_irq *wirq)
+{
+	if (!wirq)
+		return;
+
+	if (device_may_wakeup(wirq->dev))
+		enable_irq_wake(wirq->irq);
+}
+
+/**
+ * dev_pm_disarm_wake_irq - Disarm device wake-up
+ * @wirq: Device wake-up interrupt
+ *
+ * Clears up the wake-up event conditionally based on the
+ * device_may_wake().
+ */
+void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
+{
+	if (!wirq)
+		return;
+
+	if (device_may_wakeup(wirq->dev))
+		disable_irq_wake(wirq->irq);
+}
diff --git a/kernel/drivers/base/power/wakeup.c b/kernel/drivers/base/power/wakeup.c
index 77262009f..a1e0b9ab8 100644
--- a/kernel/drivers/base/power/wakeup.c
+++ b/kernel/drivers/base/power/wakeup.c
@@ -14,6 +14,7 @@
 #include <linux/suspend.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/pm_wakeirq.h>
 #include <trace/events/power.h>
 
 #include "power.h"
@@ -24,6 +25,9 @@
  */
 bool events_check_enabled __read_mostly;
 
+/* First wakeup IRQ seen by the kernel in the last cycle. */
+unsigned int pm_wakeup_irq __read_mostly;
+
 /* If set and the system is suspending, terminate the suspend. */
 static bool pm_abort_suspend __read_mostly;
 
@@ -56,6 +60,11 @@ static LIST_HEAD(wakeup_sources);
 
 static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue);
 
+static struct wakeup_source deleted_ws = {
+	.name = "deleted",
+	.lock =  __SPIN_LOCK_UNLOCKED(deleted_ws.lock),
+};
+
 /**
  * wakeup_source_prepare - Prepare a new wakeup source for initialization.
  * @ws: Wakeup source to prepare.
@@ -85,7 +94,7 @@ struct wakeup_source *wakeup_source_create(const char *name)
 	if (!ws)
 		return NULL;
 
-	wakeup_source_prepare(ws, name ? kstrdup(name, GFP_KERNEL) : NULL);
+	wakeup_source_prepare(ws, name ? kstrdup_const(name, GFP_KERNEL) : NULL);
 	return ws;
 }
 EXPORT_SYMBOL_GPL(wakeup_source_create);
@@ -107,6 +116,34 @@ void wakeup_source_drop(struct wakeup_source *ws)
 }
 EXPORT_SYMBOL_GPL(wakeup_source_drop);
 
+/*
+ * Record wakeup_source statistics being deleted into a dummy wakeup_source.
+ */
+static void wakeup_source_record(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&deleted_ws.lock, flags);
+
+	if (ws->event_count) {
+		deleted_ws.total_time =
+			ktime_add(deleted_ws.total_time, ws->total_time);
+		deleted_ws.prevent_sleep_time =
+			ktime_add(deleted_ws.prevent_sleep_time,
+				  ws->prevent_sleep_time);
+		deleted_ws.max_time =
+			ktime_compare(deleted_ws.max_time, ws->max_time) > 0 ?
+				deleted_ws.max_time : ws->max_time;
+		deleted_ws.event_count += ws->event_count;
+		deleted_ws.active_count += ws->active_count;
+		deleted_ws.relax_count += ws->relax_count;
+		deleted_ws.expire_count += ws->expire_count;
+		deleted_ws.wakeup_count += ws->wakeup_count;
+	}
+
+	spin_unlock_irqrestore(&deleted_ws.lock, flags);
+}
+
 /**
  * wakeup_source_destroy - Destroy a struct wakeup_source object.
  * @ws: Wakeup source to destroy.
@@ -119,7 +156,8 @@ void wakeup_source_destroy(struct wakeup_source *ws)
 		return;
 
 	wakeup_source_drop(ws);
-	kfree(ws->name);
+	wakeup_source_record(ws);
+	kfree_const(ws->name);
 	kfree(ws);
 }
 EXPORT_SYMBOL_GPL(wakeup_source_destroy);
@@ -239,6 +277,86 @@ int device_wakeup_enable(struct device *dev)
 EXPORT_SYMBOL_GPL(device_wakeup_enable);
 
 /**
+ * device_wakeup_attach_irq - Attach a wakeirq to a wakeup source
+ * @dev: Device to handle
+ * @wakeirq: Device specific wakeirq entry
+ *
+ * Attach a device wakeirq to the wakeup source so the device
+ * wake IRQ can be configured automatically for suspend and
+ * resume.
+ *
+ * Call under the device's power.lock lock.
+ */
+int device_wakeup_attach_irq(struct device *dev,
+			     struct wake_irq *wakeirq)
+{
+	struct wakeup_source *ws;
+
+	ws = dev->power.wakeup;
+	if (!ws) {
+		dev_err(dev, "forgot to call call device_init_wakeup?\n");
+		return -EINVAL;
+	}
+
+	if (ws->wakeirq)
+		return -EEXIST;
+
+	ws->wakeirq = wakeirq;
+	return 0;
+}
+
+/**
+ * device_wakeup_detach_irq - Detach a wakeirq from a wakeup source
+ * @dev: Device to handle
+ *
+ * Removes a device wakeirq from the wakeup source.
+ *
+ * Call under the device's power.lock lock.
+ */
+void device_wakeup_detach_irq(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	ws = dev->power.wakeup;
+	if (ws)
+		ws->wakeirq = NULL;
+}
+
+/**
+ * device_wakeup_arm_wake_irqs(void)
+ *
+ * Itereates over the list of device wakeirqs to arm them.
+ */
+void device_wakeup_arm_wake_irqs(void)
+{
+	struct wakeup_source *ws;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		if (ws->wakeirq)
+			dev_pm_arm_wake_irq(ws->wakeirq);
+	}
+	rcu_read_unlock();
+}
+
+/**
+ * device_wakeup_disarm_wake_irqs(void)
+ *
+ * Itereates over the list of device wakeirqs to disarm them.
+ */
+void device_wakeup_disarm_wake_irqs(void)
+{
+	struct wakeup_source *ws;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		if (ws->wakeirq)
+			dev_pm_disarm_wake_irq(ws->wakeirq);
+	}
+	rcu_read_unlock();
+}
+
+/**
  * device_wakeup_detach - Detach a device's wakeup source object from it.
  * @dev: Device to detach the wakeup source object from.
  *
@@ -351,6 +469,20 @@ int device_set_wakeup_enable(struct device *dev, bool enable)
 }
 EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
 
+/**
+ * wakeup_source_not_registered - validate the given wakeup source.
+ * @ws: Wakeup source to be validated.
+ */
+static bool wakeup_source_not_registered(struct wakeup_source *ws)
+{
+	/*
+	 * Use timer struct to check if the given source is initialized
+	 * by wakeup_source_add.
+	 */
+	return ws->timer.function != pm_wakeup_timer_fn ||
+		   ws->timer.data != (unsigned long)ws;
+}
+
 /*
  * The functions below use the observation that each wakeup event starts a
  * period in which the system should not be suspended.  The moment this period
@@ -391,6 +523,10 @@ static void wakeup_source_activate(struct wakeup_source *ws)
 {
 	unsigned int cec;
 
+	if (WARN_ONCE(wakeup_source_not_registered(ws),
+			"unregistered wakeup source\n"))
+		return;
+
 	/*
 	 * active wakeup source should bring the system
 	 * out of PM_SUSPEND_FREEZE state
@@ -735,6 +871,15 @@ EXPORT_SYMBOL_GPL(pm_system_wakeup);
 void pm_wakeup_clear(void)
 {
 	pm_abort_suspend = false;
+	pm_wakeup_irq = 0;
+}
+
+void pm_system_irq_wakeup(unsigned int irq_number)
+{
+	if (pm_wakeup_irq == 0) {
+		pm_wakeup_irq = irq_number;
+		pm_system_wakeup();
+	}
 }
 
 /**
@@ -894,6 +1039,8 @@ static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
 		print_wakeup_source_stats(m, ws);
 	rcu_read_unlock();
 
+	print_wakeup_source_stats(m, &deleted_ws);
+
 	return 0;
 }