Merge tag 'pm-4.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "The majority of changes go into the cpufreq subsystem this time.

  To me, quite obviously, the biggest ticket item is the new "schedutil"
  governor.  Interestingly enough, it's the first new cpufreq governor
  since the beginning of the git era (except for some out-of-the-tree
  ones).

  There are two main differences between it and the existing governors.
  First, it uses the information provided by the scheduler directly for
  making its decisions, so it doesn't have to track anything by itself.
  Second, it can invoke drivers (supporting that feature) to adjust CPU
  performance right away without having to spawn work items to be
  executed in process context or similar.  Currently, the acpi-cpufreq
  driver is the only one supporting that mode of operation, but then it
  is used on a large number of systems.

  The "schedutil" governor as included here is very simple and mostly
  regarded as a foundation for future work on the integration of the
  scheduler with CPU power management (in fact, there is work in
  progress on top of it already).  Nevertheless it works and the
  preliminary results obtained with it are encouraging.

  There also is some consolidation of CPU frequency management for ARM
  platforms that can add their machine IDs the the new stub dt-platdev
  driver now and that will take care of creating the requisite platform
  device for cpufreq-dt, so it is not necessary to do that in platform
  code any more.  Several ARM platforms are switched over to using this
  generic mechanism.

  In addition to that, the intel_pstate driver is now going to respect
  CPU frequency limits set by the platform firmware (or a BMC) and
  provided via the ACPI _PPC object.

  The devfreq subsystem is getting a new "passive" governor for SoCs
  subsystems that will depend on somebody else to manage their voltage
  rails and its support for Samsung Exynos SoCs is consolidated.

  The rest is support for new hardware (Intel Broxton support in
  intel_idle for one example), bug fixes, optimizations and cleanups in
  a number of places.

  Specifics:

   - New cpufreq "schedutil" governor (making decisions based on CPU
     utilization information provided by the scheduler and capable of
     switching CPU frequencies right away if the underlying driver
     supports that) and support for fast frequency switching in the
     acpi-cpufreq driver (Rafael Wysocki)

   - Consolidation of CPU frequency management on ARM platforms allowing
     them to get rid of some platform-specific boilerplate code if they
     are going to use the cpufreq-dt driver (Viresh Kumar, Finley Xiao,
     Marc Gonzalez)

   - Support for ACPI _PPC and CPU frequency limits in the intel_pstate
     driver (Srinivas Pandruvada)

   - Fixes and cleanups in the cpufreq core and generic governor code
     (Rafael Wysocki, Sai Gurrappadi)

   - intel_pstate driver optimizations and cleanups (Rafael Wysocki,
     Philippe Longepe, Chen Yu, Joe Perches)

   - cpufreq powernv driver fixes and cleanups (Akshay Adiga, Shilpasri
     Bhat)

   - cpufreq qoriq driver fixes and cleanups (Jia Hongtao)

   - ACPI cpufreq driver cleanups (Viresh Kumar)

   - Assorted cpufreq driver updates (Ashwin Chaugule, Geliang Tang,
     Javier Martinez Canillas, Paul Gortmaker, Sudeep Holla)

   - Assorted cpufreq fixes and cleanups (Joe Perches, Arnd Bergmann)

   - Fixes and cleanups in the OPP (Operating Performance Points)
     framework, mostly related to OPP sharing, and reorganization of
     OF-dependent code in it (Viresh Kumar, Arnd Bergmann, Sudeep Holla)

   - New "passive" governor for devfreq (for SoC subsystems that will
     rely on someone else for the management of their power resources)
     and consolidation of devfreq support for Exynos platforms, coding
     style and typo fixes for devfreq (Chanwoo Choi, MyungJoo Ham)

   - PM core fixes and cleanups, mostly to make it work better with the
     generic power domains (genpd) framework, and updates for that
     framework (Ulf Hansson, Thierry Reding, Colin Ian King)

   - Intel Broxton support for the intel_idle driver (Len Brown)

   - cpuidle core optimization and fix (Daniel Lezcano, Dave Gerlach)

   - ARM cpuidle cleanups (Jisheng Zhang)

   - Intel Kabylake support for the RAPL power capping driver (Jacob
     Pan)

   - AVS (Adaptive Voltage Switching) rockchip-io driver update (Heiko
     Stuebner)

   - Updates for the cpupower tool (Arjun Sreedharan, Colin Ian King,
     Mattia Dongili, Thomas Renninger)"

* tag 'pm-4.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (112 commits)
  intel_pstate: Clean up get_target_pstate_use_performance()
  intel_pstate: Use sample.core_avg_perf in get_avg_pstate()
  intel_pstate: Clarify average performance computation
  intel_pstate: Avoid unnecessary synchronize_sched() during initialization
  cpufreq: schedutil: Make default depend on CONFIG_SMP
  cpufreq: powernv: del_timer_sync when global and local pstate are equal
  cpufreq: powernv: Move smp_call_function_any() out of irq safe block
  intel_pstate: Clean up intel_pstate_get()
  cpufreq: schedutil: Make it depend on CONFIG_SMP
  cpufreq: governor: Fix handling of special cases in dbs_update()
  PM / OPP: Move CONFIG_OF dependent code in a separate file
  cpufreq: intel_pstate: Ignore _PPC processing under HWP
  cpufreq: arm_big_little: use generic OPP functions for {init, free}_opp_table
  PM / OPP: add non-OF versions of dev_pm_opp_{cpumask_, }remove_table
  cpufreq: tango: Use generic platdev driver
  PM / OPP: pass cpumask by reference
  cpufreq: Fix GOV_LIMITS handling for the userspace governor
  cpupower: fix potential memory leak
  PM / devfreq: style/typo fixes
  PM / devfreq: exynos: Add the detailed correlation for Exynos5422 bus
  ..

86 files changed, 3971 insertions, 3294 deletions

diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 0e64a1b..3657ac1 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -159,7 +159,7 @@ int of_pm_clk_add_clks(struct device *dev)
 
 	count = of_count_phandle_with_args(dev->of_node, "clocks",
 					   "#clock-cells");
-	if (count == 0)
+	if (count <= 0)
 		return -ENODEV;
 
 	clks = kcalloc(count, sizeof(*clks), GFP_KERNEL);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 56705b5..de23b64 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -229,17 +229,6 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
 	return ret;
 }
 
-static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, save_state, dev);
-}
-
-static int genpd_restore_dev(struct generic_pm_domain *genpd,
-			struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, restore_state, dev);
-}
-
 static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 				     unsigned long val, void *ptr)
 {
@@ -372,17 +361,63 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 }
 
 /**
- * pm_genpd_runtime_suspend - Suspend a device belonging to I/O PM domain.
+ * __genpd_runtime_suspend - walk the hierarchy of ->runtime_suspend() callbacks
+ * @dev: Device to handle.
+ */
+static int __genpd_runtime_suspend(struct device *dev)
+{
+	int (*cb)(struct device *__dev);
+
+	if (dev->type && dev->type->pm)
+		cb = dev->type->pm->runtime_suspend;
+	else if (dev->class && dev->class->pm)
+		cb = dev->class->pm->runtime_suspend;
+	else if (dev->bus && dev->bus->pm)
+		cb = dev->bus->pm->runtime_suspend;
+	else
+		cb = NULL;
+
+	if (!cb && dev->driver && dev->driver->pm)
+		cb = dev->driver->pm->runtime_suspend;
+
+	return cb ? cb(dev) : 0;
+}
+
+/**
+ * __genpd_runtime_resume - walk the hierarchy of ->runtime_resume() callbacks
+ * @dev: Device to handle.
+ */
+static int __genpd_runtime_resume(struct device *dev)
+{
+	int (*cb)(struct device *__dev);
+
+	if (dev->type && dev->type->pm)
+		cb = dev->type->pm->runtime_resume;
+	else if (dev->class && dev->class->pm)
+		cb = dev->class->pm->runtime_resume;
+	else if (dev->bus && dev->bus->pm)
+		cb = dev->bus->pm->runtime_resume;
+	else
+		cb = NULL;
+
+	if (!cb && dev->driver && dev->driver->pm)
+		cb = dev->driver->pm->runtime_resume;
+
+	return cb ? cb(dev) : 0;
+}
+
+/**
+ * genpd_runtime_suspend - Suspend a device belonging to I/O PM domain.
  * @dev: Device to suspend.
  *
  * Carry out a runtime suspend of a device under the assumption that its
  * pm_domain field points to the domain member of an object of type
  * struct generic_pm_domain representing a PM domain consisting of I/O devices.
  */
-static int pm_genpd_runtime_suspend(struct device *dev)
+static int genpd_runtime_suspend(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	bool (*stop_ok)(struct device *__dev);
+	bool (*suspend_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;
@@ -401,21 +436,21 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 	 * 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 (runtime_pm && stop_ok && !stop_ok(dev))
+	suspend_ok = genpd->gov ? genpd->gov->suspend_ok : NULL;
+	if (runtime_pm && suspend_ok && !suspend_ok(dev))
 		return -EBUSY;
 
 	/* Measure suspend latency. */
 	if (runtime_pm)
 		time_start = ktime_get();
 
-	ret = genpd_save_dev(genpd, dev);
+	ret = __genpd_runtime_suspend(dev);
 	if (ret)
 		return ret;
 
 	ret = genpd_stop_dev(genpd, dev);
 	if (ret) {
-		genpd_restore_dev(genpd, dev);
+		__genpd_runtime_resume(dev);
 		return ret;
 	}
 
@@ -446,14 +481,14 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 }
 
 /**
- * pm_genpd_runtime_resume - Resume a device belonging to I/O PM domain.
+ * genpd_runtime_resume - Resume a device belonging to I/O PM domain.
  * @dev: Device to resume.
  *
  * Carry out a runtime resume of a device under the assumption that its
  * pm_domain field points to the domain member of an object of type
  * struct generic_pm_domain representing a PM domain consisting of I/O devices.
  */
-static int pm_genpd_runtime_resume(struct device *dev)
+static int genpd_runtime_resume(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
 	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
@@ -491,7 +526,7 @@ static int pm_genpd_runtime_resume(struct device *dev)
 	if (ret)
 		goto err_poweroff;
 
-	ret = genpd_restore_dev(genpd, dev);
+	ret = __genpd_runtime_resume(dev);
 	if (ret)
 		goto err_stop;
 
@@ -695,15 +730,6 @@ static int pm_genpd_prepare(struct device *dev)
 	 * at this point and a system wakeup event should be reported if it's
 	 * set up to wake up the system from sleep states.
 	 */
-	pm_runtime_get_noresume(dev);
-	if (pm_runtime_barrier(dev) && device_may_wakeup(dev))
-		pm_wakeup_event(dev, 0);
-
-	if (pm_wakeup_pending()) {
-		pm_runtime_put(dev);
-		return -EBUSY;
-	}
-
 	if (resume_needed(dev, genpd))
 		pm_runtime_resume(dev);
 
@@ -716,10 +742,8 @@ static int pm_genpd_prepare(struct device *dev)
 
 	mutex_unlock(&genpd->lock);
 
-	if (genpd->suspend_power_off) {
-		pm_runtime_put_noidle(dev);
+	if (genpd->suspend_power_off)
 		return 0;
-	}
 
 	/*
 	 * The PM domain must be in the GPD_STATE_ACTIVE state at this point,
@@ -741,7 +765,6 @@ static int pm_genpd_prepare(struct device *dev)
 		pm_runtime_enable(dev);
 	}
 
-	pm_runtime_put(dev);
 	return ret;
 }
 
@@ -1427,54 +1450,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain);
 
-/* Default device callbacks for generic PM domains. */
-
-/**
- * pm_genpd_default_save_state - Default "save device state" for PM domains.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_save_state(struct device *dev)
-{
-	int (*cb)(struct device *__dev);
-
-	if (dev->type && dev->type->pm)
-		cb = dev->type->pm->runtime_suspend;
-	else if (dev->class && dev->class->pm)
-		cb = dev->class->pm->runtime_suspend;
-	else if (dev->bus && dev->bus->pm)
-		cb = dev->bus->pm->runtime_suspend;
-	else
-		cb = NULL;
-
-	if (!cb && dev->driver && dev->driver->pm)
-		cb = dev->driver->pm->runtime_suspend;
-
-	return cb ? cb(dev) : 0;
-}
-
-/**
- * pm_genpd_default_restore_state - Default PM domains "restore device state".
- * @dev: Device to handle.
- */
-static int pm_genpd_default_restore_state(struct device *dev)
-{
-	int (*cb)(struct device *__dev);
-
-	if (dev->type && dev->type->pm)
-		cb = dev->type->pm->runtime_resume;
-	else if (dev->class && dev->class->pm)
-		cb = dev->class->pm->runtime_resume;
-	else if (dev->bus && dev->bus->pm)
-		cb = dev->bus->pm->runtime_resume;
-	else
-		cb = NULL;
-
-	if (!cb && dev->driver && dev->driver->pm)
-		cb = dev->driver->pm->runtime_resume;
-
-	return cb ? cb(dev) : 0;
-}
-
 /**
  * pm_genpd_init - Initialize a generic I/O PM domain object.
  * @genpd: PM domain object to initialize.
@@ -1498,8 +1473,8 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->device_count = 0;
 	genpd->max_off_time_ns = -1;
 	genpd->max_off_time_changed = true;
-	genpd->domain.ops.runtime_suspend = pm_genpd_runtime_suspend;
-	genpd->domain.ops.runtime_resume = pm_genpd_runtime_resume;
+	genpd->domain.ops.runtime_suspend = genpd_runtime_suspend;
+	genpd->domain.ops.runtime_resume = genpd_runtime_resume;
 	genpd->domain.ops.prepare = pm_genpd_prepare;
 	genpd->domain.ops.suspend = pm_genpd_suspend;
 	genpd->domain.ops.suspend_late = pm_genpd_suspend_late;
@@ -1520,8 +1495,6 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->domain.ops.restore_early = pm_genpd_resume_early;
 	genpd->domain.ops.restore = pm_genpd_resume;
 	genpd->domain.ops.complete = pm_genpd_complete;
-	genpd->dev_ops.save_state = pm_genpd_default_save_state;
-	genpd->dev_ops.restore_state = pm_genpd_default_restore_state;
 
 	if (genpd->flags & GENPD_FLAG_PM_CLK) {
 		genpd->dev_ops.stop = pm_clk_suspend;
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 00a5436..2e0fce7 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -37,10 +37,10 @@ static int dev_update_qos_constraint(struct device *dev, void *data)
 }
 
 /**
- * default_stop_ok - Default PM domain governor routine for stopping devices.
+ * default_suspend_ok - Default PM domain governor routine to suspend devices.
  * @dev: Device to check.
  */
-static bool default_stop_ok(struct device *dev)
+static bool default_suspend_ok(struct device *dev)
 {
 	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
 	unsigned long flags;
@@ -51,13 +51,13 @@ static bool default_stop_ok(struct device *dev)
 	spin_lock_irqsave(&dev->power.lock, flags);
 
 	if (!td->constraint_changed) {
-		bool ret = td->cached_stop_ok;
+		bool ret = td->cached_suspend_ok;
 
 		spin_unlock_irqrestore(&dev->power.lock, flags);
 		return ret;
 	}
 	td->constraint_changed = false;
-	td->cached_stop_ok = false;
+	td->cached_suspend_ok = false;
 	td->effective_constraint_ns = -1;
 	constraint_ns = __dev_pm_qos_read_value(dev);
 
@@ -83,13 +83,13 @@ static bool default_stop_ok(struct device *dev)
 			return false;
 	}
 	td->effective_constraint_ns = constraint_ns;
-	td->cached_stop_ok = constraint_ns >= 0;
+	td->cached_suspend_ok = constraint_ns >= 0;
 
 	/*
 	 * The children have been suspended already, so we don't need to take
-	 * their stop latencies into account here.
+	 * their suspend latencies into account here.
 	 */
-	return td->cached_stop_ok;
+	return td->cached_suspend_ok;
 }
 
 /**
@@ -150,7 +150,7 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd,
 		 */
 		td = &to_gpd_data(pdd)->td;
 		constraint_ns = td->effective_constraint_ns;
-		/* default_stop_ok() need not be called before us. */
+		/* default_suspend_ok() need not be called before us. */
 		if (constraint_ns < 0) {
 			constraint_ns = dev_pm_qos_read_value(pdd->dev);
 			constraint_ns *= NSEC_PER_USEC;
@@ -227,7 +227,7 @@ static bool always_on_power_down_ok(struct dev_pm_domain *domain)
 }
 
 struct dev_power_governor simple_qos_governor = {
-	.stop_ok = default_stop_ok,
+	.suspend_ok = default_suspend_ok,
 	.power_down_ok = default_power_down_ok,
 };
 
@@ -236,5 +236,5 @@ struct dev_power_governor simple_qos_governor = {
  */
 struct dev_power_governor pm_domain_always_on_gov = {
 	.power_down_ok = always_on_power_down_ok,
-	.stop_ok = default_stop_ok,
+	.suspend_ok = default_suspend_ok,
 };
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 6e7c3cc..c81667d 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1556,7 +1556,6 @@ int dpm_suspend(pm_message_t state)
 static int device_prepare(struct device *dev, pm_message_t state)
 {
 	int (*callback)(struct device *) = NULL;
-	char *info = NULL;
 	int ret = 0;
 
 	if (dev->power.syscore)
@@ -1579,24 +1578,17 @@ static int device_prepare(struct device *dev, pm_message_t state)
 		goto unlock;
 	}
 
-	if (dev->pm_domain) {
-		info = "preparing power domain ";
+	if (dev->pm_domain)
 		callback = dev->pm_domain->ops.prepare;
-	} else if (dev->type && dev->type->pm) {
-		info = "preparing type ";
+	else if (dev->type && dev->type->pm)
 		callback = dev->type->pm->prepare;
-	} else if (dev->class && dev->class->pm) {
-		info = "preparing class ";
+	else if (dev->class && dev->class->pm)
 		callback = dev->class->pm->prepare;
-	} else if (dev->bus && dev->bus->pm) {
-		info = "preparing bus ";
+	else if (dev->bus && dev->bus->pm)
 		callback = dev->bus->pm->prepare;
-	}
 
-	if (!callback && dev->driver && dev->driver->pm) {
-		info = "preparing driver ";
+	if (!callback && dev->driver && dev->driver->pm)
 		callback = dev->driver->pm->prepare;
-	}
 
 	if (callback)
 		ret = callback(dev);
diff --git a/drivers/base/power/opp/Makefile b/drivers/base/power/opp/Makefile
index 19837ef..e70ceb4 100644
--- a/drivers/base/power/opp/Makefile
+++ b/drivers/base/power/opp/Makefile
@@ -1,3 +1,4 @@
 ccflags-$(CONFIG_DEBUG_DRIVER)	:= -DDEBUG
 obj-y				+= core.o cpu.o
+obj-$(CONFIG_OF)		+= of.o
 obj-$(CONFIG_DEBUG_FS)		+= debugfs.o
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index d8f4cc2..7c04c87 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -18,7 +18,6 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/device.h>
-#include <linux/of.h>
 #include <linux/export.h>
 #include <linux/regulator/consumer.h>
 
@@ -29,7 +28,7 @@
  * from here, with each opp_table containing the list of opps it supports in
  * various states of availability.
  */
-static LIST_HEAD(opp_tables);
+LIST_HEAD(opp_tables);
 /* Lock to allow exclusive modification to the device and opp lists */
 DEFINE_MUTEX(opp_table_lock);
 
@@ -53,26 +52,6 @@ static struct opp_device *_find_opp_dev(const struct device *dev,
 	return NULL;
 }
 
-static struct opp_table *_managed_opp(const struct device_node *np)
-{
-	struct opp_table *opp_table;
-
-	list_for_each_entry_rcu(opp_table, &opp_tables, node) {
-		if (opp_table->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 opp_table->shared_opp ? opp_table : NULL;
-		}
-	}
-
-	return NULL;
-}
-
 /**
  * _find_opp_table() - find opp_table struct using device pointer
  * @dev:	device pointer used to lookup OPP table
@@ -757,7 +736,6 @@ static struct opp_table *_add_opp_table(struct device *dev)
 {
 	struct opp_table *opp_table;
 	struct opp_device *opp_dev;
-	struct device_node *np;
 	int ret;
 
 	/* Check for existing table for 'dev' first */
@@ -781,20 +759,7 @@ static struct opp_table *_add_opp_table(struct device *dev)
 		return NULL;
 	}
 
-	/*
-	 * Only required for backward compatibility with v1 bindings, but isn't
-	 * harmful for other cases. And so we do it unconditionally.
-	 */
-	np = of_node_get(dev->of_node);
-	if (np) {
-		u32 val;
-
-		if (!of_property_read_u32(np, "clock-latency", &val))
-			opp_table->clock_latency_ns_max = val;
-		of_property_read_u32(np, "voltage-tolerance",
-				     &opp_table->voltage_tolerance_v1);
-		of_node_put(np);
-	}
+	_of_init_opp_table(opp_table, dev);
 
 	/* Set regulator to a non-NULL error value */
 	opp_table->regulator = ERR_PTR(-ENXIO);
@@ -890,8 +855,8 @@ static void _kfree_opp_rcu(struct rcu_head *head)
  * It is assumed that the caller holds required mutex for an RCU updater
  * strategy.
  */
-static void _opp_remove(struct opp_table *opp_table,
-			struct dev_pm_opp *opp, bool notify)
+void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp,
+		 bool notify)
 {
 	/*
 	 * Notify the changes in the availability of the operable
@@ -952,8 +917,8 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
 
-static struct dev_pm_opp *_allocate_opp(struct device *dev,
-					struct opp_table **opp_table)
+struct dev_pm_opp *_allocate_opp(struct device *dev,
+				 struct opp_table **opp_table)
 {
 	struct dev_pm_opp *opp;
 
@@ -989,8 +954,8 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 	return true;
 }
 
-static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
-		    struct opp_table *opp_table)
+int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
+	     struct opp_table *opp_table)
 {
 	struct dev_pm_opp *opp;
 	struct list_head *head = &opp_table->opp_list;
@@ -1066,8 +1031,8 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
  *		Duplicate OPPs (both freq and volt are same) and !opp->available
  * -ENOMEM	Memory allocation failure
  */
-static int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
-		       bool dynamic)
+int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
+		bool dynamic)
 {
 	struct opp_table *opp_table;
 	struct dev_pm_opp *new_opp;
@@ -1112,83 +1077,6 @@ unlock:
 	return ret;
 }
 
-/* TODO: Support multiple regulators */
-static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
-			      struct opp_table *opp_table)
-{
-	u32 microvolt[3] = {0};
-	u32 val;
-	int count, ret;
-	struct property *prop = NULL;
-	char name[NAME_MAX];
-
-	/* Search for "opp-microvolt-<name>" */
-	if (opp_table->prop_name) {
-		snprintf(name, sizeof(name), "opp-microvolt-%s",
-			 opp_table->prop_name);
-		prop = of_find_property(opp->np, name, NULL);
-	}
-
-	if (!prop) {
-		/* Search for "opp-microvolt" */
-		sprintf(name, "opp-microvolt");
-		prop = of_find_property(opp->np, name, NULL);
-
-		/* Missing property isn't a problem, but an invalid entry is */
-		if (!prop)
-			return 0;
-	}
-
-	count = of_property_count_u32_elems(opp->np, name);
-	if (count < 0) {
-		dev_err(dev, "%s: Invalid %s property (%d)\n",
-			__func__, name, 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 %s property (%d)\n",
-			__func__, name, count);
-		return -EINVAL;
-	}
-
-	ret = of_property_read_u32_array(opp->np, name, microvolt, count);
-	if (ret) {
-		dev_err(dev, "%s: error parsing %s: %d\n", __func__, name, ret);
-		return -EINVAL;
-	}
-
-	opp->u_volt = microvolt[0];
-
-	if (count == 1) {
-		opp->u_volt_min = opp->u_volt;
-		opp->u_volt_max = opp->u_volt;
-	} else {
-		opp->u_volt_min = microvolt[1];
-		opp->u_volt_max = microvolt[2];
-	}
-
-	/* Search for "opp-microamp-<name>" */
-	prop = NULL;
-	if (opp_table->prop_name) {
-		snprintf(name, sizeof(name), "opp-microamp-%s",
-			 opp_table->prop_name);
-		prop = of_find_property(opp->np, name, NULL);
-	}
-
-	if (!prop) {
-		/* Search for "opp-microamp" */
-		sprintf(name, "opp-microamp");
-		prop = of_find_property(opp->np, name, NULL);
-	}
-
-	if (prop && !of_property_read_u32(opp->np, name, &val))
-		opp->u_amp = val;
-
-	return 0;
-}
-
 /**
  * dev_pm_opp_set_supported_hw() - Set supported platforms
  * @dev: Device for which supported-hw has to be set.
@@ -1517,144 +1405,6 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulator);
 
-static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table,
-			      struct device_node *np)
-{
-	unsigned int count = opp_table->supported_hw_count;
-	u32 version;
-	int ret;
-
-	if (!opp_table->supported_hw)
-		return true;
-
-	while (count--) {
-		ret = of_property_read_u32_index(np, "opp-supported-hw", count,
-						 &version);
-		if (ret) {
-			dev_warn(dev, "%s: failed to read opp-supported-hw property at index %d: %d\n",
-				 __func__, count, ret);
-			return false;
-		}
-
-		/* Both of these are bitwise masks of the versions */
-		if (!(version & opp_table->supported_hw[count]))
-			return false;
-	}
-
-	return true;
-}
-
-/**
- * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
- * @dev:	device for which we do this operation
- * @np:		device node
- *
- * This function adds an opp definition to the opp table 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 opp_table 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
- */
-static int _opp_add_static_v2(struct device *dev, struct device_node *np)
-{
-	struct opp_table *opp_table;
-	struct dev_pm_opp *new_opp;
-	u64 rate;
-	u32 val;
-	int ret;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
-	new_opp = _allocate_opp(dev, &opp_table);
-	if (!new_opp) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
-
-	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;
-	}
-
-	/* Check if the OPP supports hardware's hierarchy of versions or not */
-	if (!_opp_is_supported(dev, opp_table, np)) {
-		dev_dbg(dev, "OPP not supported by hardware: %llu\n", rate);
-		goto free_opp;
-	}
-
-	/*
-	 * 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, opp_table);
-	if (ret)
-		goto free_opp;
-
-	ret = _opp_add(dev, new_opp, opp_table);
-	if (ret)
-		goto free_opp;
-
-	/* OPP to select on device suspend */
-	if (of_property_read_bool(np, "opp-suspend")) {
-		if (opp_table->suspend_opp) {
-			dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n",
-				 __func__, opp_table->suspend_opp->rate,
-				 new_opp->rate);
-		} else {
-			new_opp->suspend = true;
-			opp_table->suspend_opp = new_opp;
-		}
-	}
-
-	if (new_opp->clock_latency_ns > opp_table->clock_latency_ns_max)
-		opp_table->clock_latency_ns_max = new_opp->clock_latency_ns;
-
-	mutex_unlock(&opp_table_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(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp);
-	return 0;
-
-free_opp:
-	_opp_remove(opp_table, new_opp, false);
-unlock:
-	mutex_unlock(&opp_table_lock);
-	return ret;
-}
-
 /**
  * dev_pm_opp_add()  - Add an OPP table from a table definitions
  * @dev:	device for which we do this operation
@@ -1842,21 +1592,11 @@ struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
 
-#ifdef CONFIG_OF
-/**
- * dev_pm_opp_of_remove_table() - Free OPP table entries created from static DT
- *				  entries
- * @dev:	device pointer used to lookup OPP table.
- *
- * Free OPPs created using static entries present in DT.
- *
- * Locking: The internal opp_table 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.
+/*
+ * Free OPPs either created using static entries present in DT or even the
+ * dynamically added entries based on remove_all param.
  */
-void dev_pm_opp_of_remove_table(struct device *dev)
+void _dev_pm_opp_remove_table(struct device *dev, bool remove_all)
 {
 	struct opp_table *opp_table;
 	struct dev_pm_opp *opp, *tmp;
@@ -1881,7 +1621,7 @@ void dev_pm_opp_of_remove_table(struct device *dev)
 	if (list_is_singular(&opp_table->dev_list)) {
 		/* Free static OPPs */
 		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
-			if (!opp->dynamic)
+			if (remove_all || !opp->dynamic)
 				_opp_remove(opp_table, opp, true);
 		}
 	} else {
@@ -1891,160 +1631,22 @@ void dev_pm_opp_of_remove_table(struct device *dev)
 unlock:
 	mutex_unlock(&opp_table_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 opp_table *opp_table;
-	int ret = 0, count = 0;
-
-	mutex_lock(&opp_table_lock);
-
-	opp_table = _managed_opp(opp_np);
-	if (opp_table) {
-		/* OPPs are already managed */
-		if (!_add_opp_dev(dev, opp_table))
-			ret = -ENOMEM;
-		mutex_unlock(&opp_table_lock);
-		return ret;
-	}
-	mutex_unlock(&opp_table_lock);
-
-	/* We have opp-table 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(&opp_table_lock);
-
-	opp_table = _find_opp_table(dev);
-	if (WARN_ON(IS_ERR(opp_table))) {
-		ret = PTR_ERR(opp_table);
-		mutex_unlock(&opp_table_lock);
-		goto free_table;
-	}
-
-	opp_table->np = opp_np;
-	opp_table->shared_opp = of_property_read_bool(opp_np, "opp-shared");
-
-	mutex_unlock(&opp_table_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;
-	int nr;
-
-	prop = of_find_property(dev->of_node, "operating-points", NULL);
-	if (!prop)
-		return -ENODEV;
-	if (!prop->value)
-		return -ENODATA;
-
-	/*
-	 * Each OPP is a set of tuples consisting of frequency and
-	 * voltage like <freq-kHz vol-uV>.
-	 */
-	nr = prop->length / sizeof(u32);
-	if (nr % 2) {
-		dev_err(dev, "%s: Invalid OPP table\n", __func__);
-		return -EINVAL;
-	}
-
-	val = prop->value;
-	while (nr) {
-		unsigned long freq = be32_to_cpup(val++) * 1000;
-		unsigned long volt = be32_to_cpup(val++);
-
-		if (_opp_add_v1(dev, freq, volt, false))
-			dev_warn(dev, "%s: Failed to add OPP %ld\n",
-				 __func__, freq);
-		nr -= 2;
-	}
-
-	return 0;
-}
 
 /**
- * dev_pm_opp_of_add_table() - Initialize opp table from device tree
+ * dev_pm_opp_remove_table() - Free all OPPs associated with the device
  * @dev:	device pointer used to lookup OPP table.
  *
- * Register the initial OPP table with the OPP library for given device.
+ * Free both OPPs created using static entries present in DT and the
+ * dynamically added entries.
  *
  * Locking: The internal opp_table 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
  */
-int dev_pm_opp_of_add_table(struct device *dev)
+void dev_pm_opp_remove_table(struct device *dev)
 {
-	struct device_node *opp_np;
-	int ret;
-
-	/*
-	 * 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);
-	}
-
-	ret = _of_add_opp_table_v2(dev, opp_np);
-	of_node_put(opp_np);
-
-	return ret;
+	_dev_pm_opp_remove_table(dev, true);
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
-#endif
+EXPORT_SYMBOL_GPL(dev_pm_opp_remove_table);
diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c
index ba2bdbd..83d6e7b 100644
--- a/drivers/base/power/opp/cpu.c
+++ b/drivers/base/power/opp/cpu.c
@@ -18,7 +18,6 @@
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/export.h>
-#include <linux/of.h>
 #include <linux/slab.h>
 
 #include "opp.h"
@@ -119,8 +118,66 @@ void dev_pm_opp_free_cpufreq_table(struct device *dev,
 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)
+void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of)
+{
+	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;
+		}
+
+		if (of)
+			dev_pm_opp_of_remove_table(cpu_dev);
+		else
+			dev_pm_opp_remove_table(cpu_dev);
+	}
+}
+
+/**
+ * dev_pm_opp_cpumask_remove_table() - Removes OPP table for @cpumask
+ * @cpumask:	cpumask for which OPP table needs to be removed
+ *
+ * This removes the OPP tables for CPUs present in the @cpumask.
+ * This should be used to remove all the OPPs entries associated with
+ * the cpus in @cpumask.
+ *
+ * Locking: The internal opp_table 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.
+ */
+void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask)
+{
+	_dev_pm_opp_cpumask_remove_table(cpumask, false);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_cpumask_remove_table);
+
+/**
+ * dev_pm_opp_set_sharing_cpus() - Mark OPP table as shared by few CPUs
+ * @cpu_dev:	CPU device for which we do this operation
+ * @cpumask:	cpumask of the CPUs which share the OPP table with @cpu_dev
+ *
+ * This marks OPP table of the @cpu_dev as shared by the CPUs present in
+ * @cpumask.
+ *
+ * Returns -ENODEV if OPP table isn't already present.
+ *
+ * Locking: The internal opp_table 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.
+ */
+int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
+				const struct cpumask *cpumask)
 {
 	struct opp_device *opp_dev;
 	struct opp_table *opp_table;
@@ -131,7 +188,7 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask)
 
 	opp_table = _find_opp_table(cpu_dev);
 	if (IS_ERR(opp_table)) {
-		ret = -EINVAL;
+		ret = PTR_ERR(opp_table);
 		goto unlock;
 	}
 
@@ -152,6 +209,9 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask)
 				__func__, cpu);
 			continue;
 		}
+
+		/* Mark opp-table as multiple CPUs are sharing it now */
+		opp_table->shared_opp = true;
 	}
 unlock:
 	mutex_unlock(&opp_table_lock);
@@ -160,112 +220,47 @@ unlock:
 }
 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.
+/**
+ * dev_pm_opp_get_sharing_cpus() - Get cpumask of CPUs sharing OPPs with @cpu_dev
+ * @cpu_dev:	CPU device for which we do this operation
+ * @cpumask:	cpumask to update with information of sharing CPUs
+ *
+ * This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev.
  *
- * Returns -ENOENT if operating-points-v2 bindings aren't supported.
+ * Returns -ENODEV if OPP table isn't already present.
+ *
+ * Locking: The internal opp_table 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.
  */
-int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask)
+int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *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;
-	}
-
-	cpumask_set_cpu(cpu_dev->id, cpumask);
-
-	/* 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;
+	struct opp_device *opp_dev;
+	struct opp_table *opp_table;
+	int ret = 0;
 
-		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;
-		}
+	mutex_lock(&opp_table_lock);
 
-		/* 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;
-		}
+	opp_table = _find_opp_table(cpu_dev);
+	if (IS_ERR(opp_table)) {
+		ret = PTR_ERR(opp_table);
+		goto unlock;
+	}
 
-		/* CPUs are sharing opp node */
-		if (np == tmp_np)
-			cpumask_set_cpu(cpu, cpumask);
+	cpumask_clear(cpumask);
 
-		of_node_put(tmp_np);
+	if (opp_table->shared_opp) {
+		list_for_each_entry(opp_dev, &opp_table->dev_list, node)
+			cpumask_set_cpu(opp_dev->dev->id, cpumask);
+	} else {
+		cpumask_set_cpu(cpu_dev->id, cpumask);
 	}
 
-put_cpu_node:
-	of_node_put(np);
+unlock:
+	mutex_unlock(&opp_table_lock);
+
 	return ret;
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_sharing_cpus);
-#endif
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_sharing_cpus);
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
new file mode 100644
index 0000000..94d2010
--- /dev/null
+++ b/drivers/base/power/opp/of.c
@@ -0,0 +1,591 @@
+/*
+ * Generic OPP OF helpers
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/export.h>
+
+#include "opp.h"
+
+static struct opp_table *_managed_opp(const struct device_node *np)
+{
+	struct opp_table *opp_table;
+
+	list_for_each_entry_rcu(opp_table, &opp_tables, node) {
+		if (opp_table->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 opp_table->shared_opp ? opp_table : NULL;
+		}
+	}
+
+	return NULL;
+}
+
+void _of_init_opp_table(struct opp_table *opp_table, struct device *dev)
+{
+	struct device_node *np;
+
+	/*
+	 * Only required for backward compatibility with v1 bindings, but isn't
+	 * harmful for other cases. And so we do it unconditionally.
+	 */
+	np = of_node_get(dev->of_node);
+	if (np) {
+		u32 val;
+
+		if (!of_property_read_u32(np, "clock-latency", &val))
+			opp_table->clock_latency_ns_max = val;
+		of_property_read_u32(np, "voltage-tolerance",
+				     &opp_table->voltage_tolerance_v1);
+		of_node_put(np);
+	}
+}
+
+static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table,
+			      struct device_node *np)
+{
+	unsigned int count = opp_table->supported_hw_count;
+	u32 version;
+	int ret;
+
+	if (!opp_table->supported_hw)
+		return true;
+
+	while (count--) {
+		ret = of_property_read_u32_index(np, "opp-supported-hw", count,
+						 &version);
+		if (ret) {
+			dev_warn(dev, "%s: failed to read opp-supported-hw property at index %d: %d\n",
+				 __func__, count, ret);
+			return false;
+		}
+
+		/* Both of these are bitwise masks of the versions */
+		if (!(version & opp_table->supported_hw[count]))
+			return false;
+	}
+
+	return true;
+}
+
+/* TODO: Support multiple regulators */
+static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
+			      struct opp_table *opp_table)
+{
+	u32 microvolt[3] = {0};
+	u32 val;
+	int count, ret;
+	struct property *prop = NULL;
+	char name[NAME_MAX];
+
+	/* Search for "opp-microvolt-<name>" */
+	if (opp_table->prop_name) {
+		snprintf(name, sizeof(name), "opp-microvolt-%s",
+			 opp_table->prop_name);
+		prop = of_find_property(opp->np, name, NULL);
+	}
+
+	if (!prop) {
+		/* Search for "opp-microvolt" */
+		sprintf(name, "opp-microvolt");
+		prop = of_find_property(opp->np, name, NULL);
+
+		/* Missing property isn't a problem, but an invalid entry is */
+		if (!prop)
+			return 0;
+	}
+
+	count = of_property_count_u32_elems(opp->np, name);
+	if (count < 0) {
+		dev_err(dev, "%s: Invalid %s property (%d)\n",
+			__func__, name, 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 %s property (%d)\n",
+			__func__, name, count);
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32_array(opp->np, name, microvolt, count);
+	if (ret) {
+		dev_err(dev, "%s: error parsing %s: %d\n", __func__, name, ret);
+		return -EINVAL;
+	}
+
+	opp->u_volt = microvolt[0];
+
+	if (count == 1) {
+		opp->u_volt_min = opp->u_volt;
+		opp->u_volt_max = opp->u_volt;
+	} else {
+		opp->u_volt_min = microvolt[1];
+		opp->u_volt_max = microvolt[2];
+	}
+
+	/* Search for "opp-microamp-<name>" */
+	prop = NULL;
+	if (opp_table->prop_name) {
+		snprintf(name, sizeof(name), "opp-microamp-%s",
+			 opp_table->prop_name);
+		prop = of_find_property(opp->np, name, NULL);
+	}
+
+	if (!prop) {
+		/* Search for "opp-microamp" */
+		sprintf(name, "opp-microamp");
+		prop = of_find_property(opp->np, name, NULL);
+	}
+
+	if (prop && !of_property_read_u32(opp->np, name, &val))
+		opp->u_amp = val;
+
+	return 0;
+}
+
+/**
+ * dev_pm_opp_of_remove_table() - Free OPP table entries created from static DT
+ *				  entries
+ * @dev:	device pointer used to lookup OPP table.
+ *
+ * Free OPPs created using static entries present in DT.
+ *
+ * Locking: The internal opp_table 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.
+ */
+void dev_pm_opp_of_remove_table(struct device *dev)
+{
+	_dev_pm_opp_remove_table(dev, false);
+}
+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);
+}
+
+/**
+ * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
+ * @dev:	device for which we do this operation
+ * @np:		device node
+ *
+ * This function adds an opp definition to the opp table 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 opp_table 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
+ */
+static int _opp_add_static_v2(struct device *dev, struct device_node *np)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *new_opp;
+	u64 rate;
+	u32 val;
+	int ret;
+
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
+
+	new_opp = _allocate_opp(dev, &opp_table);
+	if (!new_opp) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	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;
+	}
+
+	/* Check if the OPP supports hardware's hierarchy of versions or not */
+	if (!_opp_is_supported(dev, opp_table, np)) {
+		dev_dbg(dev, "OPP not supported by hardware: %llu\n", rate);
+		goto free_opp;
+	}
+
+	/*
+	 * 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, opp_table);
+	if (ret)
+		goto free_opp;
+
+	ret = _opp_add(dev, new_opp, opp_table);
+	if (ret)
+		goto free_opp;
+
+	/* OPP to select on device suspend */
+	if (of_property_read_bool(np, "opp-suspend")) {
+		if (opp_table->suspend_opp) {
+			dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n",
+				 __func__, opp_table->suspend_opp->rate,
+				 new_opp->rate);
+		} else {
+			new_opp->suspend = true;
+			opp_table->suspend_opp = new_opp;
+		}
+	}
+
+	if (new_opp->clock_latency_ns > opp_table->clock_latency_ns_max)
+		opp_table->clock_latency_ns_max = new_opp->clock_latency_ns;
+
+	mutex_unlock(&opp_table_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(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp);
+	return 0;
+
+free_opp:
+	_opp_remove(opp_table, new_opp, false);
+unlock:
+	mutex_unlock(&opp_table_lock);
+	return ret;
+}
+
+/* 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 opp_table *opp_table;
+	int ret = 0, count = 0;
+
+	mutex_lock(&opp_table_lock);
+
+	opp_table = _managed_opp(opp_np);
+	if (opp_table) {
+		/* OPPs are already managed */
+		if (!_add_opp_dev(dev, opp_table))
+			ret = -ENOMEM;
+		mutex_unlock(&opp_table_lock);
+		return ret;
+	}
+	mutex_unlock(&opp_table_lock);
+
+	/* We have opp-table 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(&opp_table_lock);
+
+	opp_table = _find_opp_table(dev);
+	if (WARN_ON(IS_ERR(opp_table))) {
+		ret = PTR_ERR(opp_table);
+		mutex_unlock(&opp_table_lock);
+		goto free_table;
+	}
+
+	opp_table->np = opp_np;
+	opp_table->shared_opp = of_property_read_bool(opp_np, "opp-shared");
+
+	mutex_unlock(&opp_table_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;
+	int nr;
+
+	prop = of_find_property(dev->of_node, "operating-points", NULL);
+	if (!prop)
+		return -ENODEV;
+	if (!prop->value)
+		return -ENODATA;
+
+	/*
+	 * Each OPP is a set of tuples consisting of frequency and
+	 * voltage like <freq-kHz vol-uV>.
+	 */
+	nr = prop->length / sizeof(u32);
+	if (nr % 2) {
+		dev_err(dev, "%s: Invalid OPP table\n", __func__);
+		return -EINVAL;
+	}
+
+	val = prop->value;
+	while (nr) {
+		unsigned long freq = be32_to_cpup(val++) * 1000;
+		unsigned long volt = be32_to_cpup(val++);
+
+		if (_opp_add_v1(dev, freq, volt, false))
+			dev_warn(dev, "%s: Failed to add OPP %ld\n",
+				 __func__, freq);
+		nr -= 2;
+	}
+
+	return 0;
+}
+
+/**
+ * dev_pm_opp_of_add_table() - Initialize opp table from device tree
+ * @dev:	device pointer used to lookup OPP table.
+ *
+ * Register the initial OPP table with the OPP library for given device.
+ *
+ * Locking: The internal opp_table 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
+ */
+int dev_pm_opp_of_add_table(struct device *dev)
+{
+	struct device_node *opp_np;
+	int ret;
+
+	/*
+	 * 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);
+	}
+
+	ret = _of_add_opp_table_v2(dev, opp_np);
+	of_node_put(opp_np);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
+
+/* CPU device specific helpers */
+
+/**
+ * dev_pm_opp_of_cpumask_remove_table() - Removes OPP table for @cpumask
+ * @cpumask:	cpumask for which OPP table needs to be removed
+ *
+ * This removes the OPP tables for CPUs present in the @cpumask.
+ * This should be used only to remove static entries created from DT.
+ *
+ * Locking: The internal opp_table 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.
+ */
+void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask)
+{
+	_dev_pm_opp_cpumask_remove_table(cpumask, true);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table);
+
+/**
+ * dev_pm_opp_of_cpumask_add_table() - Adds OPP table for @cpumask
+ * @cpumask:	cpumask for which OPP table needs to be added.
+ *
+ * This adds the OPP tables for CPUs present in the @cpumask.
+ *
+ * Locking: The internal opp_table 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.
+ */
+int dev_pm_opp_of_cpumask_add_table(const struct cpumask *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.
+ *
+ * Returns -ENOENT if operating-points-v2 bindings aren't supported.
+ */
+/**
+ * dev_pm_opp_of_get_sharing_cpus() - Get cpumask of CPUs sharing OPPs with
+ *				      @cpu_dev using operating-points-v2
+ *				      bindings.
+ *
+ * @cpu_dev:	CPU device for which we do this operation
+ * @cpumask:	cpumask to update with information of sharing CPUs
+ *
+ * This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev.
+ *
+ * Returns -ENOENT if operating-points-v2 isn't present for @cpu_dev.
+ *
+ * Locking: The internal opp_table 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.
+ */
+int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
+				   struct cpumask *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;
+	}
+
+	cpumask_set_cpu(cpu_dev->id, cpumask);
+
+	/* 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);
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index f67f806..20f3be2 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -28,6 +28,8 @@ struct regulator;
 /* Lock to allow exclusive modification to the device and opp lists */
 extern struct mutex opp_table_lock;
 
+extern struct list_head opp_tables;
+
 /*
  * Internal data structure organization with the OPP layer library is as
  * follows:
@@ -183,6 +185,18 @@ struct opp_table {
 struct opp_table *_find_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
 struct device_node *_of_get_opp_desc_node(struct device *dev);
+void _dev_pm_opp_remove_table(struct device *dev, bool remove_all);
+struct dev_pm_opp *_allocate_opp(struct device *dev, struct opp_table **opp_table);
+int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
+void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp, bool notify);
+int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, bool dynamic);
+void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of);
+
+#ifdef CONFIG_OF
+void _of_init_opp_table(struct opp_table *opp_table, struct device *dev);
+#else
+static inline void _of_init_opp_table(struct opp_table *opp_table, struct device *dev) {}
+#endif
 
 #ifdef CONFIG_DEBUG_FS
 void opp_debug_remove_one(struct dev_pm_opp *opp);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 4c70550..b746904 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1506,11 +1506,16 @@ int pm_runtime_force_resume(struct device *dev)
 		goto out;
 	}
 
-	ret = callback(dev);
+	ret = pm_runtime_set_active(dev);
 	if (ret)
 		goto out;
 
-	pm_runtime_set_active(dev);
+	ret = callback(dev);
+	if (ret) {
+		pm_runtime_set_suspended(dev);
+		goto out;
+	}
+
 	pm_runtime_mark_last_busy(dev);
 out:
 	pm_runtime_enable(dev);
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index a7f4585..b7445b6 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -18,7 +18,11 @@ config CPU_FREQ
 
 if CPU_FREQ
 
+config CPU_FREQ_GOV_ATTR_SET
+	bool
+
 config CPU_FREQ_GOV_COMMON
+	select CPU_FREQ_GOV_ATTR_SET
 	select IRQ_WORK
 	bool
 
@@ -103,6 +107,17 @@ config CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
 	  Be aware that not all cpufreq drivers support the conservative
 	  governor. If unsure have a look at the help section of the
 	  driver. Fallback governor will be the performance governor.
+
+config CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
+	bool "schedutil"
+	depends on SMP
+	select CPU_FREQ_GOV_SCHEDUTIL
+	select CPU_FREQ_GOV_PERFORMANCE
+	help
+	  Use the 'schedutil' CPUFreq governor by default. If unsure,
+	  have a look at the help section of that governor. The fallback
+	  governor will be 'performance'.
+
 endchoice
 
 config CPU_FREQ_GOV_PERFORMANCE
@@ -184,6 +199,26 @@ config CPU_FREQ_GOV_CONSERVATIVE
 
 	  If in doubt, say N.
 
+config CPU_FREQ_GOV_SCHEDUTIL
+	tristate "'schedutil' cpufreq policy governor"
+	depends on CPU_FREQ && SMP
+	select CPU_FREQ_GOV_ATTR_SET
+	select IRQ_WORK
+	help
+	  This governor makes decisions based on the utilization data provided
+	  by the scheduler.  It sets the CPU frequency to be proportional to
+	  the utilization/capacity ratio coming from the scheduler.  If the
+	  utilization is frequency-invariant, the new frequency is also
+	  proportional to the maximum available frequency.  If that is not the
+	  case, it is proportional to the current frequency of the CPU.  The
+	  frequency tipping point is at utilization/capacity equal to 80% in
+	  both cases.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called cpufreq_schedutil.
+
+	  If in doubt, say N.
+
 comment "CPU frequency scaling drivers"
 
 config CPUFREQ_DT
@@ -191,6 +226,7 @@ config CPUFREQ_DT
 	depends on HAVE_CLK && OF
 	# if CPU_THERMAL is on and THERMAL=m, CPUFREQ_DT cannot be =y:
 	depends on !CPU_THERMAL || THERMAL
+	select CPUFREQ_DT_PLATDEV
 	select PM_OPP
 	help
 	  This adds a generic DT based cpufreq driver for frequency management.
@@ -199,6 +235,15 @@ config CPUFREQ_DT
 
 	  If in doubt, say N.
 
+config CPUFREQ_DT_PLATDEV
+	bool
+	help
+	  This adds a generic DT based cpufreq platdev driver for frequency
+	  management.  This creates a 'cpufreq-dt' platform device, on the
+	  supported platforms.
+
+	  If in doubt, say N.
+
 if X86
 source "drivers/cpufreq/Kconfig.x86"
 endif
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 14b1f93..d89b8af 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -50,15 +50,6 @@ config ARM_HIGHBANK_CPUFREQ
 
 	  If in doubt, say N.
 
-config ARM_HISI_ACPU_CPUFREQ
-	tristate "Hisilicon ACPU CPUfreq driver"
-	depends on ARCH_HISI && CPUFREQ_DT
-	select PM_OPP
-	help
-	  This enables the hisilicon ACPU CPUfreq driver.
-
-	  If in doubt, say N.
-
 config ARM_IMX6Q_CPUFREQ
 	tristate "Freescale i.MX6 cpufreq support"
 	depends on ARCH_MXC
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index c59bdcb..adbd1de 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -5,6 +5,7 @@
 config X86_INTEL_PSTATE
        bool "Intel P state control"
        depends on X86
+       select ACPI_PROCESSOR if ACPI
        help
           This driver provides a P state for Intel core processors.
 	  The driver implements an internal governor and will become
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 9e63fb1..e1eb11e 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -11,8 +11,10 @@ obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE)	+= cpufreq_userspace.o
 obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND)	+= cpufreq_ondemand.o
 obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
 obj-$(CONFIG_CPU_FREQ_GOV_COMMON)		+= cpufreq_governor.o
+obj-$(CONFIG_CPU_FREQ_GOV_ATTR_SET)	+= cpufreq_governor_attr_set.o
 
 obj-$(CONFIG_CPUFREQ_DT)		+= cpufreq-dt.o
+obj-$(CONFIG_CPUFREQ_DT_PLATDEV)	+= cpufreq-dt-platdev.o
 
 ##################################################################################
 # x86 drivers.
@@ -53,7 +55,6 @@ obj-$(CONFIG_ARCH_DAVINCI)		+= davinci-cpufreq.o
 obj-$(CONFIG_UX500_SOC_DB8500)		+= dbx500-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS5440_CPUFREQ)	+= exynos5440-cpufreq.o
 obj-$(CONFIG_ARM_HIGHBANK_CPUFREQ)	+= highbank-cpufreq.o
-obj-$(CONFIG_ARM_HISI_ACPU_CPUFREQ)	+= hisi-acpu-cpufreq.o
 obj-$(CONFIG_ARM_IMX6Q_CPUFREQ)		+= imx6q-cpufreq.o
 obj-$(CONFIG_ARM_INTEGRATOR)		+= integrator-cpufreq.o
 obj-$(CONFIG_ARM_KIRKWOOD_CPUFREQ)	+= kirkwood-cpufreq.o
@@ -78,6 +79,7 @@ obj-$(CONFIG_ARM_TEGRA20_CPUFREQ)	+= tegra20-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
 obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ)	+= vexpress-spc-cpufreq.o
 obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o
+obj-$(CONFIG_MACH_MVEBU_V7)		+= mvebu-cpufreq.o
 
 
 ##################################################################################
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index fb57121..32a1505 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -25,6 +25,8 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -50,8 +52,6 @@ MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
 MODULE_DESCRIPTION("ACPI Processor P-States Driver");
 MODULE_LICENSE("GPL");
 
-#define PFX "acpi-cpufreq: "
-
 enum {
 	UNDEFINED_CAPABLE = 0,
 	SYSTEM_INTEL_MSR_CAPABLE,
@@ -65,7 +65,6 @@ enum {
 #define MSR_K7_HWCR_CPB_DIS	(1ULL << 25)
 
 struct acpi_cpufreq_data {
-	struct cpufreq_frequency_table *freq_table;
 	unsigned int resume;
 	unsigned int cpu_feature;
 	unsigned int acpi_perf_cpu;
@@ -200,8 +199,9 @@ static int check_amd_hwpstate_cpu(unsigned int cpuid)
 	return cpu_has(cpu, X86_FEATURE_HW_PSTATE);
 }
 
-static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
+static unsigned extract_io(struct cpufreq_policy *policy, u32 value)
 {
+	struct acpi_cpufreq_data *data = policy->driver_data;
 	struct acpi_processor_performance *perf;
 	int i;
 
@@ -209,13 +209,14 @@ static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
 
 	for (i = 0; i < perf->state_count; i++) {
 		if (value == perf->states[i].status)
-			return data->freq_table[i].frequency;
+			return policy->freq_table[i].frequency;
 	}
 	return 0;
 }
 
-static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
+static unsigned extract_msr(struct cpufreq_policy *policy, u32 msr)
 {
+	struct acpi_cpufreq_data *data = policy->driver_data;
 	struct cpufreq_frequency_table *pos;
 	struct acpi_processor_performance *perf;
 
@@ -226,20 +227,22 @@ static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
 
 	perf = to_perf_data(data);
 
-	cpufreq_for_each_entry(pos, data->freq_table)
+	cpufreq_for_each_entry(pos, policy->freq_table)
 		if (msr == perf->states[pos->driver_data].status)
 			return pos->frequency;
-	return data->freq_table[0].frequency;
+	return policy->freq_table[0].frequency;
 }
 
-static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data)
+static unsigned extract_freq(struct cpufreq_policy *policy, u32 val)
 {
+	struct acpi_cpufreq_data *data = policy->driver_data;
+
 	switch (data->cpu_feature) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
 	case SYSTEM_AMD_MSR_CAPABLE:
-		return extract_msr(val, data);
+		return extract_msr(policy, val);
 	case SYSTEM_IO_CAPABLE:
-		return extract_io(val, data);
+		return extract_io(policy, val);
 	default:
 		return 0;
 	}
@@ -374,11 +377,11 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 		return 0;
 
 	data = policy->driver_data;
-	if (unlikely(!data || !data->freq_table))
+	if (unlikely(!data || !policy->freq_table))
 		return 0;
 
-	cached_freq = data->freq_table[to_perf_data(data)->state].frequency;
-	freq = extract_freq(get_cur_val(cpumask_of(cpu), data), data);
+	cached_freq = policy->freq_table[to_perf_data(data)->state].frequency;
+	freq = extract_freq(policy, get_cur_val(cpumask_of(cpu), data));
 	if (freq != cached_freq) {
 		/*
 		 * The dreaded BIOS frequency change behind our back.
@@ -392,14 +395,15 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 	return freq;
 }
 
-static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
-				struct acpi_cpufreq_data *data)
+static unsigned int check_freqs(struct cpufreq_policy *policy,
+				const struct cpumask *mask, unsigned int freq)
 {
+	struct acpi_cpufreq_data *data = policy->driver_data;
 	unsigned int cur_freq;
 	unsigned int i;
 
 	for (i = 0; i < 100; i++) {
-		cur_freq = extract_freq(get_cur_val(mask, data), data);
+		cur_freq = extract_freq(policy, get_cur_val(mask, data));
 		if (cur_freq == freq)
 			return 1;
 		udelay(10);
@@ -416,12 +420,12 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	unsigned int next_perf_state = 0; /* Index into perf table */
 	int result = 0;
 
-	if (unlikely(data == NULL || data->freq_table == NULL)) {
+	if (unlikely(!data)) {
 		return -ENODEV;
 	}
 
 	perf = to_perf_data(data);
-	next_perf_state = data->freq_table[index].driver_data;
+	next_perf_state = policy->freq_table[index].driver_data;
 	if (perf->state == next_perf_state) {
 		if (unlikely(data->resume)) {
 			pr_debug("Called after resume, resetting to P%d\n",
@@ -444,8 +448,8 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	drv_write(data, mask, perf->states[next_perf_state].control);
 
 	if (acpi_pstate_strict) {
-		if (!check_freqs(mask, data->freq_table[index].frequency,
-					data)) {
+		if (!check_freqs(policy, mask,
+				 policy->freq_table[index].frequency)) {
 			pr_debug("acpi_cpufreq_target failed (%d)\n",
 				policy->cpu);
 			result = -EAGAIN;
@@ -458,6 +462,43 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	return result;
 }
 
+unsigned int acpi_cpufreq_fast_switch(struct cpufreq_policy *policy,
+				      unsigned int target_freq)
+{
+	struct acpi_cpufreq_data *data = policy->driver_data;
+	struct acpi_processor_performance *perf;
+	struct cpufreq_frequency_table *entry;
+	unsigned int next_perf_state, next_freq, freq;
+
+	/*
+	 * Find the closest frequency above target_freq.
+	 *
+	 * The table is sorted in the reverse order with respect to the
+	 * frequency and all of the entries are valid (see the initialization).
+	 */
+	entry = policy->freq_table;
+	do {
+		entry++;
+		freq = entry->frequency;
+	} while (freq >= target_freq && freq != CPUFREQ_TABLE_END);
+	entry--;
+	next_freq = entry->frequency;
+	next_perf_state = entry->driver_data;
+
+	perf = to_perf_data(data);
+	if (perf->state == next_perf_state) {
+		if (unlikely(data->resume))
+			data->resume = 0;
+		else
+			return next_freq;
+	}
+
+	data->cpu_freq_write(&perf->control_register,
+			     perf->states[next_perf_state].control);
+	perf->state = next_perf_state;
+	return next_freq;
+}
+
 static unsigned long
 acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
 {
@@ -611,10 +652,7 @@ static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c)
 		if ((c->x86 == 15) &&
 		    (c->x86_model == 6) &&
 		    (c->x86_mask == 8)) {
-			printk(KERN_INFO "acpi-cpufreq: Intel(R) "
-			    "Xeon(R) 7100 Errata AL30, processors may "
-			    "lock up on frequency changes: disabling "
-			    "acpi-cpufreq.\n");
+			pr_info("Intel(R) Xeon(R) 7100 Errata AL30, processors may lock up on frequency changes: disabling acpi-cpufreq\n");
 			return -ENODEV;
 		    }
 		}
@@ -631,6 +669,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	unsigned int result = 0;
 	struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
 	struct acpi_processor_performance *perf;
+	struct cpufreq_frequency_table *freq_table;
 #ifdef CONFIG_SMP
 	static int blacklisted;
 #endif
@@ -690,7 +729,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		cpumask_copy(data->freqdomain_cpus,
 			     topology_sibling_cpumask(cpu));
 		policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
-		pr_info_once(PFX "overriding BIOS provided _PSD data\n");
+		pr_info_once("overriding BIOS provided _PSD data\n");
 	}
 #endif
 
@@ -742,9 +781,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_unreg;
 	}
 
-	data->freq_table = kzalloc(sizeof(*data->freq_table) *
+	freq_table = kzalloc(sizeof(*freq_table) *
 		    (perf->state_count+1), GFP_KERNEL);
-	if (!data->freq_table) {
+	if (!freq_table) {
 		result = -ENOMEM;
 		goto err_unreg;
 	}
@@ -762,30 +801,29 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
 	    policy->cpuinfo.transition_latency > 20 * 1000) {
 		policy->cpuinfo.transition_latency = 20 * 1000;
-		printk_once(KERN_INFO
-			    "P-state transition latency capped at 20 uS\n");
+		pr_info_once("P-state transition latency capped at 20 uS\n");
 	}
 
 	/* table init */
 	for (i = 0; i < perf->state_count; i++) {
 		if (i > 0 && perf->states[i].core_frequency >=
-		    data->freq_table[valid_states-1].frequency / 1000)
+		    freq_table[valid_states-1].frequency / 1000)
 			continue;
 
-		data->freq_table[valid_states].driver_data = i;
-		data->freq_table[valid_states].frequency =
+		freq_table[valid_states].driver_data = i;
+		freq_table[valid_states].frequency =
 		    perf->states[i].core_frequency * 1000;
 		valid_states++;
 	}
-	data->freq_table[valid_states].frequency = CPUFREQ_TABLE_END;
+	freq_table[valid_states].frequency = CPUFREQ_TABLE_END;
 	perf->state = 0;
 
-	result = cpufreq_table_validate_and_show(policy, data->freq_table);
+	result = cpufreq_table_validate_and_show(policy, freq_table);
 	if (result)
 		goto err_freqfree;
 
 	if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
-		printk(KERN_WARNING FW_WARN "P-state 0 is not max freq\n");
+		pr_warn(FW_WARN "P-state 0 is not max freq\n");
 
 	switch (perf->control_register.space_id) {
 	case ACPI_ADR_SPACE_SYSTEM_IO:
@@ -821,10 +859,13 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 */
 	data->resume = 1;
 
+	policy->fast_switch_possible = !acpi_pstate_strict &&
+		!(policy_is_shared(policy) && policy->shared_type != CPUFREQ_SHARED_TYPE_ANY);
+
 	return result;
 
 err_freqfree:
-	kfree(data->freq_table);
+	kfree(freq_table);
 err_unreg:
 	acpi_processor_unregister_performance(cpu);
 err_free_mask:
@@ -842,13 +883,12 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 
 	pr_debug("acpi_cpufreq_cpu_exit\n");
 
-	if (data) {
-		policy->driver_data = NULL;
-		acpi_processor_unregister_performance(data->acpi_perf_cpu);
-		free_cpumask_var(data->freqdomain_cpus);
-		kfree(data->freq_table);
-		kfree(data);
-	}
+	policy->fast_switch_possible = false;
+	policy->driver_data = NULL;
+	acpi_processor_unregister_performance(data->acpi_perf_cpu);
+	free_cpumask_var(data->freqdomain_cpus);
+	kfree(policy->freq_table);
+	kfree(data);
 
 	return 0;
 }
@@ -876,6 +916,7 @@ static struct freq_attr *acpi_cpufreq_attr[] = {
 static struct cpufreq_driver acpi_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= acpi_cpufreq_target,
+	.fast_switch	= acpi_cpufreq_fast_switch,
 	.bios_limit	= acpi_processor_get_bios_limit,
 	.init		= acpi_cpufreq_cpu_init,
 	.exit		= acpi_cpufreq_cpu_exit,
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index c251247..4180422 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -298,7 +298,8 @@ static int merge_cluster_tables(void)
 	return 0;
 }
 
-static void _put_cluster_clk_and_freq_table(struct device *cpu_dev)
+static void _put_cluster_clk_and_freq_table(struct device *cpu_dev,
+					    const struct cpumask *cpumask)
 {
 	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
 
@@ -308,11 +309,12 @@ static void _put_cluster_clk_and_freq_table(struct device *cpu_dev)
 	clk_put(clk[cluster]);
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
 	if (arm_bL_ops->free_opp_table)
-		arm_bL_ops->free_opp_table(cpu_dev);
+		arm_bL_ops->free_opp_table(cpumask);
 	dev_dbg(cpu_dev, "%s: cluster: %d\n", __func__, cluster);
 }
 
-static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
+static void put_cluster_clk_and_freq_table(struct device *cpu_dev,
+					   const struct cpumask *cpumask)
 {
 	u32 cluster = cpu_to_cluster(cpu_dev->id);
 	int i;
@@ -321,7 +323,7 @@ static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
 		return;
 
 	if (cluster < MAX_CLUSTERS)
-		return _put_cluster_clk_and_freq_table(cpu_dev);
+		return _put_cluster_clk_and_freq_table(cpu_dev, cpumask);
 
 	for_each_present_cpu(i) {
 		struct device *cdev = get_cpu_device(i);
@@ -330,14 +332,15 @@ static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
 			return;
 		}
 
-		_put_cluster_clk_and_freq_table(cdev);
+		_put_cluster_clk_and_freq_table(cdev, cpumask);
 	}
 
 	/* free virtual table */
 	kfree(freq_table[cluster]);
 }
 
-static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
+static int _get_cluster_clk_and_freq_table(struct device *cpu_dev,
+					   const struct cpumask *cpumask)
 {
 	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
 	int ret;
@@ -345,7 +348,7 @@ static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 	if (freq_table[cluster])
 		return 0;
 
-	ret = arm_bL_ops->init_opp_table(cpu_dev);
+	ret = arm_bL_ops->init_opp_table(cpumask);
 	if (ret) {
 		dev_err(cpu_dev, "%s: init_opp_table failed, cpu: %d, err: %d\n",
 				__func__, cpu_dev->id, ret);
@@ -374,14 +377,15 @@ static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 
 free_opp_table:
 	if (arm_bL_ops->free_opp_table)
-		arm_bL_ops->free_opp_table(cpu_dev);
+		arm_bL_ops->free_opp_table(cpumask);
 out:
 	dev_err(cpu_dev, "%s: Failed to get data for cluster: %d\n", __func__,
 			cluster);
 	return ret;
 }
 
-static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
+static int get_cluster_clk_and_freq_table(struct device *cpu_dev,
+					  const struct cpumask *cpumask)
 {
 	u32 cluster = cpu_to_cluster(cpu_dev->id);
 	int i, ret;
@@ -390,7 +394,7 @@ static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
 		return 0;
 
 	if (cluster < MAX_CLUSTERS) {
-		ret = _get_cluster_clk_and_freq_table(cpu_dev);
+		ret = _get_cluster_clk_and_freq_table(cpu_dev, cpumask);
 		if (ret)
 			atomic_dec(&cluster_usage[cluster]);
 		return ret;
@@ -407,7 +411,7 @@ static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
 			return -ENODEV;
 		}
 
-		ret = _get_cluster_clk_and_freq_table(cdev);
+		ret = _get_cluster_clk_and_freq_table(cdev, cpumask);
 		if (ret)
 			goto put_clusters;
 	}
@@ -433,7 +437,7 @@ put_clusters:
 			return -ENODEV;
 		}
 
-		_put_cluster_clk_and_freq_table(cdev);
+		_put_cluster_clk_and_freq_table(cdev, cpumask);
 	}
 
 	atomic_dec(&cluster_usage[cluster]);
@@ -455,18 +459,6 @@ static int bL_cpufreq_init(struct cpufreq_policy *policy)
 		return -ENODEV;
 	}
 
-	ret = get_cluster_clk_and_freq_table(cpu_dev);
-	if (ret)
-		return ret;
-
-	ret = cpufreq_table_validate_and_show(policy, freq_table[cur_cluster]);
-	if (ret) {
-		dev_err(cpu_dev, "CPU %d, cluster: %d invalid freq table\n",
-				policy->cpu, cur_cluster);
-		put_cluster_clk_and_freq_table(cpu_dev);
-		return ret;
-	}
-
 	if (cur_cluster < MAX_CLUSTERS) {
 		int cpu;
 
@@ -479,6 +471,18 @@ static int bL_cpufreq_init(struct cpufreq_policy *policy)
 		per_cpu(physical_cluster, policy->cpu) = A15_CLUSTER;
 	}
 
+	ret = get_cluster_clk_and_freq_table(cpu_dev, policy->cpus);
+	if (ret)
+		return ret;
+
+	ret = cpufreq_table_validate_and_show(policy, freq_table[cur_cluster]);
+	if (ret) {
+		dev_err(cpu_dev, "CPU %d, cluster: %d invalid freq table\n",
+			policy->cpu, cur_cluster);
+		put_cluster_clk_and_freq_table(cpu_dev, policy->cpus);
+		return ret;
+	}
+
 	if (arm_bL_ops->get_transition_latency)
 		policy->cpuinfo.transition_latency =
 			arm_bL_ops->get_transition_latency(cpu_dev);
@@ -509,7 +513,7 @@ static int bL_cpufreq_exit(struct cpufreq_policy *policy)
 		return -ENODEV;
 	}
 
-	put_cluster_clk_and_freq_table(cpu_dev);
+	put_cluster_clk_and_freq_table(cpu_dev, policy->related_cpus);
 	dev_dbg(cpu_dev, "%s: Exited, cpu: %d\n", __func__, policy->cpu);
 
 	return 0;
diff --git a/drivers/cpufreq/arm_big_little.h b/drivers/cpufreq/arm_big_little.h
index b88889d..184d7c3 100644
--- a/drivers/cpufreq/arm_big_little.h
+++ b/drivers/cpufreq/arm_big_little.h
@@ -30,11 +30,11 @@ struct cpufreq_arm_bL_ops {
 	 * This must set opp table for cpu_dev in a similar way as done by
 	 * dev_pm_opp_of_add_table().
 	 */
-	int (*init_opp_table)(struct device *cpu_dev);
+	int (*init_opp_table)(const struct cpumask *cpumask);
 
 	/* Optional */
 	int (*get_transition_latency)(struct device *cpu_dev);
-	void (*free_opp_table)(struct device *cpu_dev);
+	void (*free_opp_table)(const struct cpumask *cpumask);
 };
 
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops);
diff --git a/drivers/cpufreq/arm_big_little_dt.c b/drivers/cpufreq/arm_big_little_dt.c
index 16ddeef..39b3f51 100644
--- a/drivers/cpufreq/arm_big_little_dt.c
+++ b/drivers/cpufreq/arm_big_little_dt.c
@@ -43,23 +43,6 @@ static struct device_node *get_cpu_node_with_valid_op(int cpu)
 	return np;
 }
 
-static int dt_init_opp_table(struct device *cpu_dev)
-{
-	struct device_node *np;
-	int ret;
-
-	np = of_node_get(cpu_dev->of_node);
-	if (!np) {
-		pr_err("failed to find cpu%d node\n", cpu_dev->id);
-		return -ENOENT;
-	}
-
-	ret = dev_pm_opp_of_add_table(cpu_dev);
-	of_node_put(np);
-
-	return ret;
-}
-
 static int dt_get_transition_latency(struct device *cpu_dev)
 {
 	struct device_node *np;
@@ -81,8 +64,8 @@ static int dt_get_transition_latency(struct device *cpu_dev)
 static struct cpufreq_arm_bL_ops dt_bL_ops = {
 	.name	= "dt-bl",
 	.get_transition_latency = dt_get_transition_latency,
-	.init_opp_table = dt_init_opp_table,
-	.free_opp_table = dev_pm_opp_of_remove_table,
+	.init_opp_table = dev_pm_opp_of_cpumask_add_table,
+	.free_opp_table = dev_pm_opp_of_cpumask_remove_table,
 };
 
 static int generic_bL_probe(struct platform_device *pdev)
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 7c0bdfb..8882b8e 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -173,4 +173,25 @@ out:
 	return -ENODEV;
 }
 
+static void __exit cppc_cpufreq_exit(void)
+{
+	struct cpudata *cpu;
+	int i;
+
+	cpufreq_unregister_driver(&cppc_cpufreq_driver);
+
+	for_each_possible_cpu(i) {
+		cpu = all_cpu_data[i];
+		free_cpumask_var(cpu->shared_cpu_map);
+		kfree(cpu);
+	}
+
+	kfree(all_cpu_data);
+}
+
+module_exit(cppc_cpufreq_exit);
+MODULE_AUTHOR("Ashwin Chaugule");
+MODULE_DESCRIPTION("CPUFreq driver based on the ACPI CPPC v5.0+ spec");
+MODULE_LICENSE("GPL");
+
 late_initcall(cppc_cpufreq_init);
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
new file mode 100644
index 0000000..3646b14
--- /dev/null
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -0,0 +1,94 @@
+/*
+ * Copyright (C) 2016 Linaro.
+ * Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * 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.
+ */
+
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+static const struct of_device_id machines[] __initconst = {
+	{ .compatible = "allwinner,sun4i-a10", },
+	{ .compatible = "allwinner,sun5i-a10s", },
+	{ .compatible = "allwinner,sun5i-a13", },
+	{ .compatible = "allwinner,sun5i-r8", },
+	{ .compatible = "allwinner,sun6i-a31", },
+	{ .compatible = "allwinner,sun6i-a31s", },
+	{ .compatible = "allwinner,sun7i-a20", },
+	{ .compatible = "allwinner,sun8i-a23", },
+	{ .compatible = "allwinner,sun8i-a33", },
+	{ .compatible = "allwinner,sun8i-a83t", },
+	{ .compatible = "allwinner,sun8i-h3", },
+
+	{ .compatible = "hisilicon,hi6220", },
+
+	{ .compatible = "fsl,imx27", },
+	{ .compatible = "fsl,imx51", },
+	{ .compatible = "fsl,imx53", },
+	{ .compatible = "fsl,imx7d", },
+
+	{ .compatible = "marvell,berlin", },
+
+	{ .compatible = "samsung,exynos3250", },
+	{ .compatible = "samsung,exynos4210", },
+	{ .compatible = "samsung,exynos4212", },
+	{ .compatible = "samsung,exynos4412", },
+	{ .compatible = "samsung,exynos5250", },
+#ifndef CONFIG_BL_SWITCHER
+	{ .compatible = "samsung,exynos5420", },
+	{ .compatible = "samsung,exynos5800", },
+#endif
+
+	{ .compatible = "renesas,emev2", },
+	{ .compatible = "renesas,r7s72100", },
+	{ .compatible = "renesas,r8a73a4", },
+	{ .compatible = "renesas,r8a7740", },
+	{ .compatible = "renesas,r8a7778", },
+	{ .compatible = "renesas,r8a7779", },
+	{ .compatible = "renesas,r8a7790", },
+	{ .compatible = "renesas,r8a7791", },
+	{ .compatible = "renesas,r8a7793", },
+	{ .compatible = "renesas,r8a7794", },
+	{ .compatible = "renesas,sh73a0", },
+
+	{ .compatible = "rockchip,rk2928", },
+	{ .compatible = "rockchip,rk3036", },
+	{ .compatible = "rockchip,rk3066a", },
+	{ .compatible = "rockchip,rk3066b", },
+	{ .compatible = "rockchip,rk3188", },
+	{ .compatible = "rockchip,rk3228", },
+	{ .compatible = "rockchip,rk3288", },
+	{ .compatible = "rockchip,rk3366", },
+	{ .compatible = "rockchip,rk3368", },
+	{ .compatible = "rockchip,rk3399", },
+
+	{ .compatible = "sigma,tango4" },
+
+	{ .compatible = "ti,omap2", },
+	{ .compatible = "ti,omap3", },
+	{ .compatible = "ti,omap4", },
+	{ .compatible = "ti,omap5", },
+
+	{ .compatible = "xlnx,zynq-7000", },
+};
+
+static int __init cpufreq_dt_platdev_init(void)
+{
+	struct device_node *np = of_find_node_by_path("/");
+
+	if (!np)
+		return -ENODEV;
+
+	if (!of_match_node(machines, np))
+		return -ENODEV;
+
+	of_node_put(of_root);
+
+	return PTR_ERR_OR_ZERO(platform_device_register_simple("cpufreq-dt", -1,
+							       NULL, 0));
+}
+device_initcall(cpufreq_dt_platdev_init);
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 5f8dbe6..3957de8 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -15,7 +15,6 @@
 #include <linux/cpu.h>
 #include <linux/cpu_cooling.h>
 #include <linux/cpufreq.h>
-#include <linux/cpufreq-dt.h>
 #include <linux/cpumask.h>
 #include <linux/err.h>
 #include <linux/module.h>
@@ -147,7 +146,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	struct clk *cpu_clk;
 	struct dev_pm_opp *suspend_opp;
 	unsigned int transition_latency;
-	bool opp_v1 = false;
+	bool fallback = false;
 	const char *name;
 	int ret;
 
@@ -167,14 +166,16 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	/* Get OPP-sharing information from "operating-points-v2" bindings */
 	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, policy->cpus);
 	if (ret) {
+		if (ret != -ENOENT)
+			goto out_put_clk;
+
 		/*
 		 * operating-points-v2 not supported, fallback to old method of
-		 * finding shared-OPPs for backward compatibility.
+		 * finding shared-OPPs for backward compatibility if the
+		 * platform hasn't set sharing CPUs.
 		 */
-		if (ret == -ENOENT)
-			opp_v1 = true;
-		else
-			goto out_put_clk;
+		if (dev_pm_opp_get_sharing_cpus(cpu_dev, policy->cpus))
+			fallback = true;
 	}
 
 	/*
@@ -214,11 +215,8 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_free_opp;
 	}
 
-	if (opp_v1) {
-		struct cpufreq_dt_platform_data *pd = cpufreq_get_driver_data();
-
-		if (!pd || !pd->independent_clocks)
-			cpumask_setall(policy->cpus);
+	if (fallback) {
+		cpumask_setall(policy->cpus);
 
 		/*
 		 * OPP tables are initialized only for policy->cpu, do it for
diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c
index db69eeb..5503d49 100644
--- a/drivers/cpufreq/cpufreq-nforce2.c
+++ b/drivers/cpufreq/cpufreq-nforce2.c
@@ -7,6 +7,8 @@
  *  BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -56,8 +58,6 @@ MODULE_PARM_DESC(fid, "CPU multiplier to use (11.5 = 115)");
 MODULE_PARM_DESC(min_fsb,
 		"Minimum FSB to use, if not defined: current FSB - 50");
 
-#define PFX "cpufreq-nforce2: "
-
 /**
  * nforce2_calc_fsb - calculate FSB
  * @pll: PLL value
@@ -174,13 +174,13 @@ static int nforce2_set_fsb(unsigned int fsb)
 	int pll = 0;
 
 	if ((fsb > max_fsb) || (fsb < NFORCE2_MIN_FSB)) {
-		printk(KERN_ERR PFX "FSB %d is out of range!\n", fsb);
+		pr_err("FSB %d is out of range!\n", fsb);
 		return -EINVAL;
 	}
 
 	tfsb = nforce2_fsb_read(0);
 	if (!tfsb) {
-		printk(KERN_ERR PFX "Error while reading the FSB\n");
+		pr_err("Error while reading the FSB\n");
 		return -EINVAL;
 	}
 
@@ -276,8 +276,7 @@ static int nforce2_target(struct cpufreq_policy *policy,
 	/* local_irq_save(flags); */
 
 	if (nforce2_set_fsb(target_fsb) < 0)
-		printk(KERN_ERR PFX "Changing FSB to %d failed\n",
-			target_fsb);
+		pr_err("Changing FSB to %d failed\n", target_fsb);
 	else
 		pr_debug("Changed FSB successfully to %d\n",
 			target_fsb);
@@ -325,8 +324,7 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy)
 	/* FIX: Get FID from CPU */
 	if (!fid) {
 		if (!cpu_khz) {
-			printk(KERN_WARNING PFX
-			"cpu_khz not set, can't calculate multiplier!\n");
+			pr_warn("cpu_khz not set, can't calculate multiplier!\n");
 			return -ENODEV;
 		}
 
@@ -341,8 +339,8 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy)
 		}
 	}
 
-	printk(KERN_INFO PFX "FSB currently at %i MHz, FID %d.%d\n", fsb,
-	       fid / 10, fid % 10);
+	pr_info("FSB currently at %i MHz, FID %d.%d\n",
+		fsb, fid / 10, fid % 10);
 
 	/* Set maximum FSB to FSB at boot time */
 	max_fsb = nforce2_fsb_read(1);
@@ -401,11 +399,9 @@ static int nforce2_detect_chipset(void)
 	if (nforce2_dev == NULL)
 		return -ENODEV;
 
-	printk(KERN_INFO PFX "Detected nForce2 chipset revision %X\n",
-	       nforce2_dev->revision);
-	printk(KERN_INFO PFX
-	       "FSB changing is maybe unstable and can lead to "
-	       "crashes and data loss.\n");
+	pr_info("Detected nForce2 chipset revision %X\n",
+		nforce2_dev->revision);
+	pr_info("FSB changing is maybe unstable and can lead to crashes and data loss\n");
 
 	return 0;
 }
@@ -423,7 +419,7 @@ static int __init nforce2_init(void)
 
 	/* detect chipset */
 	if (nforce2_detect_chipset()) {
-		printk(KERN_INFO PFX "No nForce2 chipset.\n");
+		pr_info("No nForce2 chipset\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index c4acfc5..035513b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -78,6 +78,11 @@ static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
 static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
 static int cpufreq_start_governor(struct cpufreq_policy *policy);
 
+static inline int cpufreq_exit_governor(struct cpufreq_policy *policy)
+{
+	return cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+}
+
 /**
  * Two notifier lists: the "policy" list is involved in the
  * validation process for a new CPU frequency policy; the
@@ -429,6 +434,73 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_freq_transition_end);
 
+/*
+ * Fast frequency switching status count.  Positive means "enabled", negative
+ * means "disabled" and 0 means "not decided yet".
+ */
+static int cpufreq_fast_switch_count;
+static DEFINE_MUTEX(cpufreq_fast_switch_lock);
+
+static void cpufreq_list_transition_notifiers(void)
+{
+	struct notifier_block *nb;
+
+	pr_info("Registered transition notifiers:\n");
+
+	mutex_lock(&cpufreq_transition_notifier_list.mutex);
+
+	for (nb = cpufreq_transition_notifier_list.head; nb; nb = nb->next)
+		pr_info("%pF\n", nb->notifier_call);
+
+	mutex_unlock(&cpufreq_transition_notifier_list.mutex);
+}
+
+/**
+ * cpufreq_enable_fast_switch - Enable fast frequency switching for policy.
+ * @policy: cpufreq policy to enable fast frequency switching for.
+ *
+ * Try to enable fast frequency switching for @policy.
+ *
+ * The attempt will fail if there is at least one transition notifier registered
+ * at this point, as fast frequency switching is quite fundamentally at odds
+ * with transition notifiers.  Thus if successful, it will make registration of
+ * transition notifiers fail going forward.
+ */
+void cpufreq_enable_fast_switch(struct cpufreq_policy *policy)
+{
+	lockdep_assert_held(&policy->rwsem);
+
+	if (!policy->fast_switch_possible)
+		return;
+
+	mutex_lock(&cpufreq_fast_switch_lock);
+	if (cpufreq_fast_switch_count >= 0) {
+		cpufreq_fast_switch_count++;
+		policy->fast_switch_enabled = true;
+	} else {
+		pr_warn("CPU%u: Fast frequency switching not enabled\n",
+			policy->cpu);
+		cpufreq_list_transition_notifiers();
+	}
+	mutex_unlock(&cpufreq_fast_switch_lock);
+}
+EXPORT_SYMBOL_GPL(cpufreq_enable_fast_switch);
+
+/**
+ * cpufreq_disable_fast_switch - Disable fast frequency switching for policy.
+ * @policy: cpufreq policy to disable fast frequency switching for.
+ */
+void cpufreq_disable_fast_switch(struct cpufreq_policy *policy)
+{
+	mutex_lock(&cpufreq_fast_switch_lock);
+	if (policy->fast_switch_enabled) {
+		policy->fast_switch_enabled = false;
+		if (!WARN_ON(cpufreq_fast_switch_count <= 0))
+			cpufreq_fast_switch_count--;
+	}
+	mutex_unlock(&cpufreq_fast_switch_lock);
+}
+EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch);
 
 /*********************************************************************
  *                          SYSFS INTERFACE                          *
@@ -1248,26 +1320,24 @@ out_free_policy:
  */
 static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 {
+	struct cpufreq_policy *policy;
 	unsigned cpu = dev->id;
-	int ret;
 
 	dev_dbg(dev, "%s: adding CPU%u\n", __func__, cpu);
 
-	if (cpu_online(cpu)) {
-		ret = cpufreq_online(cpu);
-	} else {
-		/*
-		 * A hotplug notifier will follow and we will handle it as CPU
-		 * online then.  For now, just create the sysfs link, unless
-		 * there is no policy or the link is already present.
-		 */
-		struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+	if (cpu_online(cpu))
+		return cpufreq_online(cpu);
 
-		ret = policy && !cpumask_test_and_set_cpu(cpu, policy->real_cpus)
-			? add_cpu_dev_symlink(policy, cpu) : 0;
-	}
+	/*
+	 * A hotplug notifier will follow and we will handle it as CPU online
+	 * then.  For now, just create the sysfs link, unless there is no policy
+	 * or the link is already present.
+	 */
+	policy = per_cpu(cpufreq_cpu_data, cpu);
+	if (!policy || cpumask_test_and_set_cpu(cpu, policy->real_cpus))
+		return 0;
 
-	return ret;
+	return add_cpu_dev_symlink(policy, cpu);
 }
 
 static void cpufreq_offline(unsigned int cpu)
@@ -1319,7 +1389,7 @@ static void cpufreq_offline(unsigned int cpu)
 
 	/* If cpu is last user of policy, free policy */
 	if (has_target()) {
-		ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		ret = cpufreq_exit_governor(policy);
 		if (ret)
 			pr_err("%s: Failed to exit governor\n", __func__);
 	}
@@ -1447,8 +1517,12 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
 
 	ret_freq = cpufreq_driver->get(policy->cpu);
 
-	/* Updating inactive policies is invalid, so avoid doing that. */
-	if (unlikely(policy_is_inactive(policy)))
+	/*
+	 * Updating inactive policies is invalid, so avoid doing that.  Also
+	 * if fast frequency switching is used with the given policy, the check
+	 * against policy->cur is pointless, so skip it in that case too.
+	 */
+	if (unlikely(policy_is_inactive(policy)) || policy->fast_switch_enabled)
 		return ret_freq;
 
 	if (ret_freq && policy->cur &&
@@ -1679,8 +1753,18 @@ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
 
 	switch (list) {
 	case CPUFREQ_TRANSITION_NOTIFIER:
+		mutex_lock(&cpufreq_fast_switch_lock);
+
+		if (cpufreq_fast_switch_count > 0) {
+			mutex_unlock(&cpufreq_fast_switch_lock);
+			return -EBUSY;
+		}
 		ret = srcu_notifier_chain_register(
 				&cpufreq_transition_notifier_list, nb);
+		if (!ret)
+			cpufreq_fast_switch_count--;
+
+		mutex_unlock(&cpufreq_fast_switch_lock);
 		break;
 	case CPUFREQ_POLICY_NOTIFIER:
 		ret = blocking_notifier_chain_register(
@@ -1713,8 +1797,14 @@ int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list)
 
 	switch (list) {
 	case CPUFREQ_TRANSITION_NOTIFIER:
+		mutex_lock(&cpufreq_fast_switch_lock);
+
 		ret = srcu_notifier_chain_unregister(
 				&cpufreq_transition_notifier_list, nb);
+		if (!ret && !WARN_ON(cpufreq_fast_switch_count >= 0))
+			cpufreq_fast_switch_count++;
+
+		mutex_unlock(&cpufreq_fast_switch_lock);
 		break;
 	case CPUFREQ_POLICY_NOTIFIER:
 		ret = blocking_notifier_chain_unregister(
@@ -1733,6 +1823,37 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier);
  *                              GOVERNORS                            *
  *********************************************************************/
 
+/**
+ * cpufreq_driver_fast_switch - Carry out a fast CPU frequency switch.
+ * @policy: cpufreq policy to switch the frequency for.
+ * @target_freq: New frequency to set (may be approximate).
+ *
+ * Carry out a fast frequency switch without sleeping.
+ *
+ * The driver's ->fast_switch() callback invoked by this function must be
+ * suitable for being called from within RCU-sched read-side critical sections
+ * and it is expected to select the minimum available frequency greater than or
+ * equal to @target_freq (CPUFREQ_RELATION_L).
+ *
+ * This function must not be called if policy->fast_switch_enabled is unset.
+ *
+ * Governors calling this function must guarantee that it will never be invoked
+ * twice in parallel for the same policy and that it will never be called in
+ * parallel with either ->target() or ->target_index() for the same policy.
+ *
+ * If CPUFREQ_ENTRY_INVALID is returned by the driver's ->fast_switch()
+ * callback to indicate an error condition, the hardware configuration must be
+ * preserved.
+ */
+unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
+					unsigned int target_freq)
+{
+	clamp_val(target_freq, policy->min, policy->max);
+
+	return cpufreq_driver->fast_switch(policy, target_freq);
+}
+EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
+
 /* Must set freqs->new to intermediate frequency */
 static int __target_intermediate(struct cpufreq_policy *policy,
 				 struct cpufreq_freqs *freqs, int index)
@@ -2108,7 +2229,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 			return ret;
 		}
 
-		ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		ret = cpufreq_exit_governor(policy);
 		if (ret) {
 			pr_err("%s: Failed to Exit Governor: %s (%d)\n",
 			       __func__, old_gov->name, ret);
@@ -2125,7 +2246,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 			pr_debug("cpufreq: governor change\n");
 			return 0;
 		}
-		cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		cpufreq_exit_governor(policy);
 	}
 
 	/* new governor failed, so re-start old one */
@@ -2193,16 +2314,13 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
 		cpufreq_online(cpu);
 		break;
 
 	case CPU_DOWN_PREPARE:
 		cpufreq_offline(cpu);
 		break;
-
-	case CPU_DOWN_FAILED:
-		cpufreq_online(cpu);
-		break;
 	}
 	return NOTIFY_OK;
 }
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index bf4913f..316df24 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -129,9 +129,10 @@ static struct notifier_block cs_cpufreq_notifier_block = {
 /************************** sysfs interface ************************/
 static struct dbs_governor cs_dbs_gov;
 
-static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
-		const char *buf, size_t count)
+static ssize_t store_sampling_down_factor(struct gov_attr_set *attr_set,
+					  const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -143,9 +144,10 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 	return count;
 }
 
-static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_up_threshold(struct gov_attr_set *attr_set,
+				  const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
@@ -158,9 +160,10 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_down_threshold(struct gov_attr_set *attr_set,
+				    const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
@@ -175,9 +178,10 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
-		const char *buf, size_t count)
+static ssize_t store_ignore_nice_load(struct gov_attr_set *attr_set,
+				      const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 
@@ -199,9 +203,10 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 	return count;
 }
 
-static ssize_t store_freq_step(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_freq_step(struct gov_attr_set *attr_set, const char *buf,
+			       size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 5f1147f..be498d5 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -43,9 +43,10 @@ static DEFINE_MUTEX(gov_dbs_data_mutex);
  * This must be called with dbs_data->mutex held, otherwise traversing
  * policy_dbs_list isn't safe.
  */
-ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
+ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf,
 			    size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct policy_dbs_info *policy_dbs;
 	unsigned int rate;
 	int ret;
@@ -59,7 +60,7 @@ ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
 	 * We are operating under dbs_data->mutex and so the list and its
 	 * entries can't be freed concurrently.
 	 */
-	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
+	list_for_each_entry(policy_dbs, &attr_set->policy_list, list) {
 		mutex_lock(&policy_dbs->timer_mutex);
 		/*
 		 * On 32-bit architectures this may race with the
@@ -96,13 +97,13 @@ void gov_update_cpu_data(struct dbs_data *dbs_data)
 {
 	struct policy_dbs_info *policy_dbs;
 
-	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
+	list_for_each_entry(policy_dbs, &dbs_data->attr_set.policy_list, list) {
 		unsigned int j;
 
 		for_each_cpu(j, policy_dbs->policy->cpus) {
 			struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
 
-			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall,
+			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_update_time,
 								  dbs_data->io_is_busy);
 			if (dbs_data->ignore_nice_load)
 				j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
@@ -111,54 +112,6 @@ void gov_update_cpu_data(struct dbs_data *dbs_data)
 }
 EXPORT_SYMBOL_GPL(gov_update_cpu_data);
 
-static inline struct dbs_data *to_dbs_data(struct kobject *kobj)
-{
-	return container_of(kobj, struct dbs_data, kobj);
-}
-
-static inline struct governor_attr *to_gov_attr(struct attribute *attr)
-{
-	return container_of(attr, struct governor_attr, attr);
-}
-
-static ssize_t governor_show(struct kobject *kobj, struct attribute *attr,
-			     char *buf)
-{
-	struct dbs_data *dbs_data = to_dbs_data(kobj);
-	struct governor_attr *gattr = to_gov_attr(attr);
-
-	return gattr->show(dbs_data, buf);
-}
-
-static ssize_t governor_store(struct kobject *kobj, struct attribute *attr,
-			      const char *buf, size_t count)
-{
-	struct dbs_data *dbs_data = to_dbs_data(kobj);
-	struct governor_attr *gattr = to_gov_attr(attr);
-	int ret = -EBUSY;
-
-	mutex_lock(&dbs_data->mutex);
-
-	if (dbs_data->usage_count)
-		ret = gattr->store(dbs_data, buf, count);
-
-	mutex_unlock(&dbs_data->mutex);
-
-	return ret;
-}
-
-/*
- * Sysfs Ops for accessing governor attributes.
- *
- * All show/store invocations for governor specific sysfs attributes, will first
- * call the below show/store callbacks and the attribute specific callback will
- * be called from within it.
- */
-static const struct sysfs_ops governor_sysfs_ops = {
-	.show	= governor_show,
-	.store	= governor_store,
-};
-
 unsigned int dbs_update(struct cpufreq_policy *policy)
 {
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
@@ -184,14 +137,14 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 	/* Get Absolute Load */
 	for_each_cpu(j, policy->cpus) {
 		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
-		u64 cur_wall_time, cur_idle_time;
-		unsigned int idle_time, wall_time;
+		u64 update_time, cur_idle_time;
+		unsigned int idle_time, time_elapsed;
 		unsigned int load;
 
-		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time, io_busy);
+		cur_idle_time = get_cpu_idle_time(j, &update_time, io_busy);
 
-		wall_time = cur_wall_time - j_cdbs->prev_cpu_wall;
-		j_cdbs->prev_cpu_wall = cur_wall_time;
+		time_elapsed = update_time - j_cdbs->prev_update_time;
+		j_cdbs->prev_update_time = update_time;
 
 		idle_time = cur_idle_time - j_cdbs->prev_cpu_idle;
 		j_cdbs->prev_cpu_idle = cur_idle_time;
@@ -203,47 +156,62 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 			j_cdbs->prev_cpu_nice = cur_nice;
 		}
 
-		if (unlikely(!wall_time || wall_time < idle_time))
-			continue;
-
-		/*
-		 * If the CPU had gone completely idle, and a task just woke up
-		 * on this CPU now, it would be unfair to calculate 'load' the
-		 * usual way for this elapsed time-window, because it will show
-		 * near-zero load, irrespective of how CPU intensive that task
-		 * actually is. This is undesirable for latency-sensitive bursty
-		 * workloads.
-		 *
-		 * To avoid this, we reuse the 'load' from the previous
-		 * time-window and give this task a chance to start with a
-		 * reasonably high CPU frequency. (However, we shouldn't over-do
-		 * this copy, lest we get stuck at a high load (high frequency)
-		 * for too long, even when the current system load has actually
-		 * dropped down. So we perform the copy only once, upon the
-		 * first wake-up from idle.)
-		 *
-		 * Detecting this situation is easy: the governor's utilization
-		 * update handler would not have run during CPU-idle periods.
-		 * Hence, an unusually large 'wall_time' (as compared to the
-		 * sampling rate) indicates this scenario.
-		 *
-		 * prev_load can be zero in two cases and we must recalculate it
-		 * for both cases:
-		 * - during long idle intervals
-		 * - explicitly set to zero
-		 */
-		if (unlikely(wall_time > (2 * sampling_rate) &&
-			     j_cdbs->prev_load)) {
+		if (unlikely(!time_elapsed)) {
+			/*
+			 * That can only happen when this function is called
+			 * twice in a row with a very short interval between the
+			 * calls, so the previous load value can be used then.
+			 */
 			load = j_cdbs->prev_load;
-
+		} else if (unlikely(time_elapsed > 2 * sampling_rate &&
+				    j_cdbs->prev_load)) {
 			/*
-			 * Perform a destructive copy, to ensure that we copy
-			 * the previous load only once, upon the first wake-up
-			 * from idle.
+			 * If the CPU had gone completely idle and a task has
+			 * just woken up on this CPU now, it would be unfair to
+			 * calculate 'load' the usual way for this elapsed
+			 * time-window, because it would show near-zero load,
+			 * irrespective of how CPU intensive that task actually
+			 * was. This is undesirable for latency-sensitive bursty
+			 * workloads.
+			 *
+			 * To avoid this, reuse the 'load' from the previous
+			 * time-window and give this task a chance to start with
+			 * a reasonably high CPU frequency. However, that
+			 * shouldn't be over-done, lest we get stuck at a high
+			 * load (high frequency) for too long, even when the
+			 * current system load has actually dropped down, so
+			 * clear prev_load to guarantee that the load will be
+			 * computed again next time.
+			 *
+			 * Detecting this situation is easy: the governor's
+			 * utilization update handler would not have run during
+			 * CPU-idle periods.  Hence, an unusually large
+			 * 'time_elapsed' (as compared to the sampling rate)
+			 * indicates this scenario.
 			 */
+			load = j_cdbs->prev_load;
 			j_cdbs->prev_load = 0;
 		} else {
-			load = 100 * (wall_time - idle_time) / wall_time;
+			if (time_elapsed >= idle_time) {
+				load = 100 * (time_elapsed - idle_time) / time_elapsed;
+			} else {
+				/*
+				 * That can happen if idle_time is returned by
+				 * get_cpu_idle_time_jiffy().  In that case
+				 * idle_time is roughly equal to the difference
+				 * between time_elapsed and "busy time" obtained
+				 * from CPU statistics.  Then, the "busy time"
+				 * can end up being greater than time_elapsed
+				 * (for example, if jiffies_64 and the CPU
+				 * statistics are updated by different CPUs),
+				 * so idle_time may in fact be negative.  That
+				 * means, though, that the CPU was busy all
+				 * the time (on the rough average) during the
+				 * last sampling interval and 100 can be
+				 * returned as the load.
+				 */
+				load = (int)idle_time < 0 ? 100 : 0;
+			}
 			j_cdbs->prev_load = load;
 		}
 
@@ -254,43 +222,6 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(dbs_update);
 
-static void gov_set_update_util(struct policy_dbs_info *policy_dbs,
-				unsigned int delay_us)
-{
-	struct cpufreq_policy *policy = policy_dbs->policy;
-	int cpu;
-
-	gov_update_sample_delay(policy_dbs, delay_us);
-	policy_dbs->last_sample_time = 0;
-
-	for_each_cpu(cpu, policy->cpus) {
-		struct cpu_dbs_info *cdbs = &per_cpu(cpu_dbs, cpu);
-
-		cpufreq_set_update_util_data(cpu, &cdbs->update_util);
-	}
-}
-
-static inline void gov_clear_update_util(struct cpufreq_policy *policy)
-{
-	int i;
-
-	for_each_cpu(i, policy->cpus)
-		cpufreq_set_update_util_data(i, NULL);
-
-	synchronize_sched();
-}
-
-static void gov_cancel_work(struct cpufreq_policy *policy)
-{
-	struct policy_dbs_info *policy_dbs = policy->governor_data;
-
-	gov_clear_update_util(policy_dbs->policy);
-	irq_work_sync(&policy_dbs->irq_work);
-	cancel_work_sync(&policy_dbs->work);
-	atomic_set(&policy_dbs->work_count, 0);
-	policy_dbs->work_in_progress = false;
-}
-
 static void dbs_work_handler(struct work_struct *work)
 {
 	struct policy_dbs_info *policy_dbs;
@@ -378,6 +309,44 @@ static void dbs_update_util_handler(struct update_util_data *data, u64 time,
 	irq_work_queue(&policy_dbs->irq_work);
 }
 
+static void gov_set_update_util(struct policy_dbs_info *policy_dbs,
+				unsigned int delay_us)
+{
+	struct cpufreq_policy *policy = policy_dbs->policy;
+	int cpu;
+
+	gov_update_sample_delay(policy_dbs, delay_us);
+	policy_dbs->last_sample_time = 0;
+
+	for_each_cpu(cpu, policy->cpus) {
+		struct cpu_dbs_info *cdbs = &per_cpu(cpu_dbs, cpu);
+
+		cpufreq_add_update_util_hook(cpu, &cdbs->update_util,
+					     dbs_update_util_handler);
+	}
+}
+
+static inline void gov_clear_update_util(struct cpufreq_policy *policy)
+{
+	int i;
+
+	for_each_cpu(i, policy->cpus)
+		cpufreq_remove_update_util_hook(i);
+
+	synchronize_sched();
+}
+
+static void gov_cancel_work(struct cpufreq_policy *policy)
+{
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+
+	gov_clear_update_util(policy_dbs->policy);
+	irq_work_sync(&policy_dbs->irq_work);
+	cancel_work_sync(&policy_dbs->work);
+	atomic_set(&policy_dbs->work_count, 0);
+	policy_dbs->work_in_progress = false;
+}
+
 static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *policy,
 						     struct dbs_governor *gov)
 {
@@ -400,7 +369,6 @@ static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *poli
 		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
 
 		j_cdbs->policy_dbs = policy_dbs;
-		j_cdbs->update_util.func = dbs_update_util_handler;
 	}
 	return policy_dbs;
 }
@@ -449,10 +417,7 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy)
 		policy_dbs->dbs_data = dbs_data;
 		policy->governor_data = policy_dbs;
 
-		mutex_lock(&dbs_data->mutex);
-		dbs_data->usage_count++;
-		list_add(&policy_dbs->list, &dbs_data->policy_dbs_list);
-		mutex_unlock(&dbs_data->mutex);
+		gov_attr_set_get(&dbs_data->attr_set, &policy_dbs->list);
 		goto out;
 	}
 
@@ -462,8 +427,7 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy)
 		goto free_policy_dbs_info;
 	}
 
-	INIT_LIST_HEAD(&dbs_data->policy_dbs_list);
-	mutex_init(&dbs_data->mutex);
+	gov_attr_set_init(&dbs_data->attr_set, &policy_dbs->list);
 
 	ret = gov->init(dbs_data, !policy->governor->initialized);
 	if (ret)
@@ -483,14 +447,11 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy)
 	if (!have_governor_per_policy())
 		gov->gdbs_data = dbs_data;
 
-	policy->governor_data = policy_dbs;
-
 	policy_dbs->dbs_data = dbs_data;
-	dbs_data->usage_count = 1;
-	list_add(&policy_dbs->list, &dbs_data->policy_dbs_list);
+	policy->governor_data = policy_dbs;
 
 	gov->kobj_type.sysfs_ops = &governor_sysfs_ops;
-	ret = kobject_init_and_add(&dbs_data->kobj, &gov->kobj_type,
+	ret = kobject_init_and_add(&dbs_data->attr_set.kobj, &gov->kobj_type,
 				   get_governor_parent_kobj(policy),
 				   "%s", gov->gov.name);
 	if (!ret)
@@ -519,29 +480,21 @@ static int cpufreq_governor_exit(struct cpufreq_policy *policy)
 	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
 	struct dbs_data *dbs_data = policy_dbs->dbs_data;
-	int count;
+	unsigned int count;
 
 	/* Protect gov->gdbs_data against concurrent updates. */
 	mutex_lock(&gov_dbs_data_mutex);
 
-	mutex_lock(&dbs_data->mutex);
-	list_del(&policy_dbs->list);
-	count = --dbs_data->usage_count;
-	mutex_unlock(&dbs_data->mutex);
+	count = gov_attr_set_put(&dbs_data->attr_set, &policy_dbs->list);
 
-	if (!count) {
-		kobject_put(&dbs_data->kobj);
-
-		policy->governor_data = NULL;
+	policy->governor_data = NULL;
 
+	if (!count) {
 		if (!have_governor_per_policy())
 			gov->gdbs_data = NULL;
 
 		gov->exit(dbs_data, policy->governor->initialized == 1);
-		mutex_destroy(&dbs_data->mutex);
 		kfree(dbs_data);
-	} else {
-		policy->governor_data = NULL;
 	}
 
 	free_policy_dbs_info(policy_dbs, gov);
@@ -570,12 +523,12 @@ static int cpufreq_governor_start(struct cpufreq_policy *policy)
 
 	for_each_cpu(j, policy->cpus) {
 		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
-		unsigned int prev_load;
 
-		j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy);
-
-		prev_load = j_cdbs->prev_cpu_wall - j_cdbs->prev_cpu_idle;
-		j_cdbs->prev_load = 100 * prev_load / (unsigned int)j_cdbs->prev_cpu_wall;
+		j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_update_time, io_busy);
+		/*
+		 * Make the first invocation of dbs_update() compute the load.
+		 */
+		j_cdbs->prev_load = 0;
 
 		if (ignore_nice)
 			j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 61ff82f..34eb214 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -24,20 +24,6 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 
-/*
- * The polling frequency depends on the capability of the processor. Default
- * polling frequency is 1000 times the transition latency of the processor. The
- * governor will work on any processor with transition latency <= 10ms, using
- * appropriate sampling rate.
- *
- * For CPUs with transition latency > 10ms (mostly drivers with CPUFREQ_ETERNAL)
- * this governor will not work. All times here are in us (micro seconds).
- */
-#define MIN_SAMPLING_RATE_RATIO			(2)
-#define LATENCY_MULTIPLIER			(1000)
-#define MIN_LATENCY_MULTIPLIER			(20)
-#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)
-
 /* Ondemand Sampling types */
 enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
 
@@ -52,7 +38,7 @@ enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
 
 /* Governor demand based switching data (per-policy or global). */
 struct dbs_data {
-	int usage_count;
+	struct gov_attr_set attr_set;
 	void *tuners;
 	unsigned int min_sampling_rate;
 	unsigned int ignore_nice_load;
@@ -60,37 +46,27 @@ struct dbs_data {
 	unsigned int sampling_down_factor;
 	unsigned int up_threshold;
 	unsigned int io_is_busy;
-
-	struct kobject kobj;
-	struct list_head policy_dbs_list;
-	/*
-	 * Protect concurrent updates to governor tunables from sysfs,
-	 * policy_dbs_list and usage_count.
-	 */
-	struct mutex mutex;
 };
 
-/* Governor's specific attributes */
-struct dbs_data;
-struct governor_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct dbs_data *dbs_data, char *buf);
-	ssize_t (*store)(struct dbs_data *dbs_data, const char *buf,
-			 size_t count);
-};
+static inline struct dbs_data *to_dbs_data(struct gov_attr_set *attr_set)
+{
+	return container_of(attr_set, struct dbs_data, attr_set);
+}
 
 #define gov_show_one(_gov, file_name)					\
 static ssize_t show_##file_name						\
-(struct dbs_data *dbs_data, char *buf)					\
+(struct gov_attr_set *attr_set, char *buf)				\
 {									\
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);		\
 	struct _gov##_dbs_tuners *tuners = dbs_data->tuners;		\
 	return sprintf(buf, "%u\n", tuners->file_name);			\
 }
 
 #define gov_show_one_common(file_name)					\
 static ssize_t show_##file_name						\
-(struct dbs_data *dbs_data, char *buf)					\
+(struct gov_attr_set *attr_set, char *buf)				\
 {									\
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);		\
 	return sprintf(buf, "%u\n", dbs_data->file_name);		\
 }
 
@@ -135,7 +111,7 @@ static inline void gov_update_sample_delay(struct policy_dbs_info *policy_dbs,
 /* Per cpu structures */
 struct cpu_dbs_info {
 	u64 prev_cpu_idle;
-	u64 prev_cpu_wall;
+	u64 prev_update_time;
 	u64 prev_cpu_nice;
 	/*
 	 * Used to keep track of load in the previous interval. However, when
@@ -184,7 +160,7 @@ void od_register_powersave_bias_handler(unsigned int (*f)
 		(struct cpufreq_policy *, unsigned int, unsigned int),
 		unsigned int powersave_bias);
 void od_unregister_powersave_bias_handler(void);
-ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
+ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf,
 			    size_t count);
 void gov_update_cpu_data(struct dbs_data *dbs_data);
 #endif /* _CPUFREQ_GOVERNOR_H */
diff --git a/drivers/cpufreq/cpufreq_governor_attr_set.c b/drivers/cpufreq/cpufreq_governor_attr_set.c
new file mode 100644
index 0000000..52841f8
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_governor_attr_set.c
@@ -0,0 +1,84 @@
+/*
+ * Abstract code for CPUFreq governor tunable sysfs attributes.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * 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.
+ */
+
+#include "cpufreq_governor.h"
+
+static inline struct gov_attr_set *to_gov_attr_set(struct kobject *kobj)
+{
+	return container_of(kobj, struct gov_attr_set, kobj);
+}
+
+static inline struct governor_attr *to_gov_attr(struct attribute *attr)
+{
+	return container_of(attr, struct governor_attr, attr);
+}
+
+static ssize_t governor_show(struct kobject *kobj, struct attribute *attr,
+			     char *buf)
+{
+	struct governor_attr *gattr = to_gov_attr(attr);
+
+	return gattr->show(to_gov_attr_set(kobj), buf);
+}
+
+static ssize_t governor_store(struct kobject *kobj, struct attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct gov_attr_set *attr_set = to_gov_attr_set(kobj);
+	struct governor_attr *gattr = to_gov_attr(attr);
+	int ret;
+
+	mutex_lock(&attr_set->update_lock);
+	ret = attr_set->usage_count ? gattr->store(attr_set, buf, count) : -EBUSY;
+	mutex_unlock(&attr_set->update_lock);
+	return ret;
+}
+
+const struct sysfs_ops governor_sysfs_ops = {
+	.show	= governor_show,
+	.store	= governor_store,
+};
+EXPORT_SYMBOL_GPL(governor_sysfs_ops);
+
+void gov_attr_set_init(struct gov_attr_set *attr_set, struct list_head *list_node)
+{
+	INIT_LIST_HEAD(&attr_set->policy_list);
+	mutex_init(&attr_set->update_lock);
+	attr_set->usage_count = 1;
+	list_add(list_node, &attr_set->policy_list);
+}
+EXPORT_SYMBOL_GPL(gov_attr_set_init);
+
+void gov_attr_set_get(struct gov_attr_set *attr_set, struct list_head *list_node)
+{
+	mutex_lock(&attr_set->update_lock);
+	attr_set->usage_count++;
+	list_add(list_node, &attr_set->policy_list);
+	mutex_unlock(&attr_set->update_lock);
+}
+EXPORT_SYMBOL_GPL(gov_attr_set_get);
+
+unsigned int gov_attr_set_put(struct gov_attr_set *attr_set, struct list_head *list_node)
+{
+	unsigned int count;
+
+	mutex_lock(&attr_set->update_lock);
+	list_del(list_node);
+	count = --attr_set->usage_count;
+	mutex_unlock(&attr_set->update_lock);
+	if (count)
+		return count;
+
+	kobject_put(&attr_set->kobj);
+	mutex_destroy(&attr_set->update_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gov_attr_set_put);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index acd8027..3001634 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -207,9 +207,10 @@ static unsigned int od_dbs_timer(struct cpufreq_policy *policy)
 /************************** sysfs interface ************************/
 static struct dbs_governor od_dbs_gov;
 
-static ssize_t store_io_is_busy(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_io_is_busy(struct gov_attr_set *attr_set, const char *buf,
+				size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 
@@ -224,9 +225,10 @@ static ssize_t store_io_is_busy(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_up_threshold(struct gov_attr_set *attr_set,
+				  const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -240,9 +242,10 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
-		const char *buf, size_t count)
+static ssize_t store_sampling_down_factor(struct gov_attr_set *attr_set,
+					  const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct policy_dbs_info *policy_dbs;
 	unsigned int input;
 	int ret;
@@ -254,7 +257,7 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 	dbs_data->sampling_down_factor = input;
 
 	/* Reset down sampling multiplier in case it was active */
-	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
+	list_for_each_entry(policy_dbs, &attr_set->policy_list, list) {
 		/*
 		 * Doing this without locking might lead to using different
 		 * rate_mult values in od_update() and od_dbs_timer().
@@ -267,9 +270,10 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 	return count;
 }
 
-static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
-		const char *buf, size_t count)
+static ssize_t store_ignore_nice_load(struct gov_attr_set *attr_set,
+				      const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	unsigned int input;
 	int ret;
 
@@ -291,9 +295,10 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 	return count;
 }
 
-static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
+static ssize_t store_powersave_bias(struct gov_attr_set *attr_set,
+				    const char *buf, size_t count)
 {
+	struct dbs_data *dbs_data = to_dbs_data(attr_set);
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	struct policy_dbs_info *policy_dbs;
 	unsigned int input;
@@ -308,7 +313,7 @@ static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf,
 
 	od_tuners->powersave_bias = input;
 
-	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list)
+	list_for_each_entry(policy_dbs, &attr_set->policy_list, list)
 		ondemand_powersave_bias_init(policy_dbs->policy);
 
 	return count;
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index 4d16f45..9f3dec9 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 
 static DEFINE_PER_CPU(unsigned int, cpu_is_managed);
 static DEFINE_MUTEX(userspace_mutex);
@@ -31,6 +32,7 @@ static DEFINE_MUTEX(userspace_mutex);
 static int cpufreq_set(struct cpufreq_policy *policy, unsigned int freq)
 {
 	int ret = -EINVAL;
+	unsigned int *setspeed = policy->governor_data;
 
 	pr_debug("cpufreq_set for cpu %u, freq %u kHz\n", policy->cpu, freq);
 
@@ -38,6 +40,8 @@ static int cpufreq_set(struct cpufreq_policy *policy, unsigned int freq)
 	if (!per_cpu(cpu_is_managed, policy->cpu))
 		goto err;
 
+	*setspeed = freq;
+
 	ret = __cpufreq_driver_target(policy, freq, CPUFREQ_RELATION_L);
  err:
 	mutex_unlock(&userspace_mutex);
@@ -49,19 +53,45 @@ static ssize_t show_speed(struct cpufreq_policy *policy, char *buf)
 	return sprintf(buf, "%u\n", policy->cur);
 }
 
+static int cpufreq_userspace_policy_init(struct cpufreq_policy *policy)
+{
+	unsigned int *setspeed;
+
+	setspeed = kzalloc(sizeof(*setspeed), GFP_KERNEL);
+	if (!setspeed)
+		return -ENOMEM;
+
+	policy->governor_data = setspeed;
+	return 0;
+}
+
 static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 				   unsigned int event)
 {
+	unsigned int *setspeed = policy->governor_data;
 	unsigned int cpu = policy->cpu;
 	int rc = 0;
 
+	if (event == CPUFREQ_GOV_POLICY_INIT)
+		return cpufreq_userspace_policy_init(policy);
+
+	if (!setspeed)
+		return -EINVAL;
+
 	switch (event) {
+	case CPUFREQ_GOV_POLICY_EXIT:
+		mutex_lock(&userspace_mutex);
+		policy->governor_data = NULL;
+		kfree(setspeed);
+		mutex_unlock(&userspace_mutex);
+		break;
 	case CPUFREQ_GOV_START:
 		BUG_ON(!policy->cur);
 		pr_debug("started managing cpu %u\n", cpu);
 
 		mutex_lock(&userspace_mutex);
 		per_cpu(cpu_is_managed, cpu) = 1;
+		*setspeed = policy->cur;
 		mutex_unlock(&userspace_mutex);
 		break;
 	case CPUFREQ_GOV_STOP:
@@ -69,20 +99,23 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 
 		mutex_lock(&userspace_mutex);
 		per_cpu(cpu_is_managed, cpu) = 0;
+		*setspeed = 0;
 		mutex_unlock(&userspace_mutex);
 		break;
 	case CPUFREQ_GOV_LIMITS:
 		mutex_lock(&userspace_mutex);
-		pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz\n",
-			cpu, policy->min, policy->max,
-			policy->cur);
+		pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz, last set to %u kHz\n",
+			cpu, policy->min, policy->max, policy->cur, *setspeed);
 
-		if (policy->max < policy->cur)
+		if (policy->max < *setspeed)
 			__cpufreq_driver_target(policy, policy->max,
 						CPUFREQ_RELATION_H);
-		else if (policy->min > policy->cur)
+		else if (policy->min > *setspeed)
 			__cpufreq_driver_target(policy, policy->min,
 						CPUFREQ_RELATION_L);
+		else
+			__cpufreq_driver_target(policy, *setspeed,
+						CPUFREQ_RELATION_L);
 		mutex_unlock(&userspace_mutex);
 		break;
 	}
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index 4085244c..cdf097b 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -6,6 +6,8 @@
  *  BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -20,7 +22,7 @@
 #include <asm/msr.h>
 #include <asm/tsc.h>
 
-#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+#if IS_ENABLED(CONFIG_ACPI_PROCESSOR)
 #include <linux/acpi.h>
 #include <acpi/processor.h>
 #endif
@@ -33,7 +35,7 @@
 
 struct eps_cpu_data {
 	u32 fsb;
-#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+#if IS_ENABLED(CONFIG_ACPI_PROCESSOR)
 	u32 bios_limit;
 #endif
 	struct cpufreq_frequency_table freq_table[];
@@ -46,7 +48,7 @@ static int freq_failsafe_off;
 static int voltage_failsafe_off;
 static int set_max_voltage;
 
-#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+#if IS_ENABLED(CONFIG_ACPI_PROCESSOR)
 static int ignore_acpi_limit;
 
 static struct acpi_processor_performance *eps_acpi_cpu_perf;
@@ -141,11 +143,9 @@ static int eps_set_state(struct eps_cpu_data *centaur,
 	/* Print voltage and multiplier */
 	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
 	current_voltage = lo & 0xff;
-	printk(KERN_INFO "eps: Current voltage = %dmV\n",
-		current_voltage * 16 + 700);
+	pr_info("Current voltage = %dmV\n", current_voltage * 16 + 700);
 	current_multiplier = (lo >> 8) & 0xff;
-	printk(KERN_INFO "eps: Current multiplier = %d\n",
-		current_multiplier);
+	pr_info("Current multiplier = %d\n", current_multiplier);
 	}
 #endif
 	return 0;
@@ -166,7 +166,7 @@ static int eps_target(struct cpufreq_policy *policy, unsigned int index)
 	dest_state = centaur->freq_table[index].driver_data & 0xffff;
 	ret = eps_set_state(centaur, policy, dest_state);
 	if (ret)
-		printk(KERN_ERR "eps: Timeout!\n");
+		pr_err("Timeout!\n");
 	return ret;
 }
 
@@ -186,7 +186,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 	int k, step, voltage;
 	int ret;
 	int states;
-#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+#if IS_ENABLED(CONFIG_ACPI_PROCESSOR)
 	unsigned int limit;
 #endif
 
@@ -194,36 +194,36 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 		return -ENODEV;
 
 	/* Check brand */
-	printk(KERN_INFO "eps: Detected VIA ");
+	pr_info("Detected VIA ");
 
 	switch (c->x86_model) {
 	case 10:
 		rdmsr(0x1153, lo, hi);
 		brand = (((lo >> 2) ^ lo) >> 18) & 3;
-		printk(KERN_CONT "Model A ");
+		pr_cont("Model A ");
 		break;
 	case 13:
 		rdmsr(0x1154, lo, hi);
 		brand = (((lo >> 4) ^ (lo >> 2))) & 0x000000ff;
-		printk(KERN_CONT "Model D ");
+		pr_cont("Model D ");
 		break;
 	}
 
 	switch (brand) {
 	case EPS_BRAND_C7M:
-		printk(KERN_CONT "C7-M\n");
+		pr_cont("C7-M\n");
 		break;
 	case EPS_BRAND_C7:
-		printk(KERN_CONT "C7\n");
+		pr_cont("C7\n");
 		break;
 	case EPS_BRAND_EDEN:
-		printk(KERN_CONT "Eden\n");
+		pr_cont("Eden\n");
 		break;
 	case EPS_BRAND_C7D:
-		printk(KERN_CONT "C7-D\n");
+		pr_cont("C7-D\n");
 		break;
 	case EPS_BRAND_C3:
-		printk(KERN_CONT "C3\n");
+		pr_cont("C3\n");
 		return -ENODEV;
 		break;
 	}
@@ -235,7 +235,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 		/* Can be locked at 0 */
 		rdmsrl(MSR_IA32_MISC_ENABLE, val);
 		if (!(val & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
-			printk(KERN_INFO "eps: Can't enable Enhanced PowerSaver\n");
+			pr_info("Can't enable Enhanced PowerSaver\n");
 			return -ENODEV;
 		}
 	}
@@ -243,22 +243,19 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 	/* Print voltage and multiplier */
 	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
 	current_voltage = lo & 0xff;
-	printk(KERN_INFO "eps: Current voltage = %dmV\n",
-			current_voltage * 16 + 700);
+	pr_info("Current voltage = %dmV\n", current_voltage * 16 + 700);
 	current_multiplier = (lo >> 8) & 0xff;
-	printk(KERN_INFO "eps: Current multiplier = %d\n", current_multiplier);
+	pr_info("Current multiplier = %d\n", current_multiplier);
 
 	/* Print limits */
 	max_voltage = hi & 0xff;
-	printk(KERN_INFO "eps: Highest voltage = %dmV\n",
-			max_voltage * 16 + 700);
+	pr_info("Highest voltage = %dmV\n", max_voltage * 16 + 700);
 	max_multiplier = (hi >> 8) & 0xff;
-	printk(KERN_INFO "eps: Highest multiplier = %d\n", max_multiplier);
+	pr_info("Highest multiplier = %d\n", max_multiplier);
 	min_voltage = (hi >> 16) & 0xff;
-	printk(KERN_INFO "eps: Lowest voltage = %dmV\n",
-			min_voltage * 16 + 700);
+	pr_info("Lowest voltage = %dmV\n", min_voltage * 16 + 700);
 	min_multiplier = (hi >> 24) & 0xff;
-	printk(KERN_INFO "eps: Lowest multiplier = %d\n", min_multiplier);
+	pr_info("Lowest multiplier = %d\n", min_multiplier);
 
 	/* Sanity checks */
 	if (current_multiplier == 0 || max_multiplier == 0
@@ -276,34 +273,30 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 
 	/* Check for systems using underclocked CPU */
 	if (!freq_failsafe_off && max_multiplier != current_multiplier) {
-		printk(KERN_INFO "eps: Your processor is running at different "
-			"frequency then its maximum. Aborting.\n");
-		printk(KERN_INFO "eps: You can use freq_failsafe_off option "
-			"to disable this check.\n");
+		pr_info("Your processor is running at different frequency then its maximum. Aborting.\n");
+		pr_info("You can use freq_failsafe_off option to disable this check.\n");
 		return -EINVAL;
 	}
 	if (!voltage_failsafe_off && max_voltage != current_voltage) {
-		printk(KERN_INFO "eps: Your processor is running at different "
-			"voltage then its maximum. Aborting.\n");
-		printk(KERN_INFO "eps: You can use voltage_failsafe_off "
-			"option to disable this check.\n");
+		pr_info("Your processor is running at different voltage then its maximum. Aborting.\n");
+		pr_info("You can use voltage_failsafe_off option to disable this check.\n");
 		return -EINVAL;
 	}
 
 	/* Calc FSB speed */
 	fsb = cpu_khz / current_multiplier;
 
-#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+#if IS_ENABLED(CONFIG_ACPI_PROCESSOR)
 	/* Check for ACPI processor speed limit */
 	if (!ignore_acpi_limit && !eps_acpi_init()) {
 		if (!acpi_processor_get_bios_limit(policy->cpu, &limit)) {
-			printk(KERN_INFO "eps: ACPI limit %u.%uGHz\n",
+			pr_info("ACPI limit %u.%uGHz\n",
 				limit/1000000,
 				(limit%1000000)/10000);
 			eps_acpi_exit(policy);
 			/* Check if max_multiplier is in BIOS limits */
 			if (limit && max_multiplier * fsb > limit) {
-				printk(KERN_INFO "eps: Aborting.\n");
+				pr_info("Aborting\n");
 				return -EINVAL;
 			}
 		}
@@ -319,8 +312,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 		v = (set_max_voltage - 700) / 16;
 		/* Check if voltage is within limits */
 		if (v >= min_voltage && v <= max_voltage) {
-			printk(KERN_INFO "eps: Setting %dmV as maximum.\n",
-				v * 16 + 700);
+			pr_info("Setting %dmV as maximum\n", v * 16 + 700);
 			max_voltage = v;
 		}
 	}
@@ -341,7 +333,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 
 	/* Copy basic values */
 	centaur->fsb = fsb;
-#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+#if IS_ENABLED(CONFIG_ACPI_PROCESSOR)
 	centaur->bios_limit = limit;
 #endif
 
@@ -426,7 +418,7 @@ module_param(freq_failsafe_off, int, 0644);
 MODULE_PARM_DESC(freq_failsafe_off, "Disable current vs max frequency check");
 module_param(voltage_failsafe_off, int, 0644);
 MODULE_PARM_DESC(voltage_failsafe_off, "Disable current vs max voltage check");
-#if defined CONFIG_ACPI_PROCESSOR || defined CONFIG_ACPI_PROCESSOR_MODULE
+#if IS_ENABLED(CONFIG_ACPI_PROCESSOR)
 module_param(ignore_acpi_limit, int, 0644);
 MODULE_PARM_DESC(ignore_acpi_limit, "Don't check ACPI's processor speed limit");
 #endif
diff --git a/drivers/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c
index 1c06e78..bfce11c 100644
--- a/drivers/cpufreq/elanfreq.c
+++ b/drivers/cpufreq/elanfreq.c
@@ -16,6 +16,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -185,7 +187,7 @@ static int elanfreq_cpu_init(struct cpufreq_policy *policy)
 static int __init elanfreq_setup(char *str)
 {
 	max_freq = simple_strtoul(str, &str, 0);
-	printk(KERN_WARNING "You're using the deprecated elanfreq command line option. Use elanfreq.max_freq instead, please!\n");
+	pr_warn("You're using the deprecated elanfreq command line option. Use elanfreq.max_freq instead, please!\n");
 	return 1;
 }
 __setup("elanfreq=", elanfreq_setup);
diff --git a/drivers/cpufreq/hisi-acpu-cpufreq.c b/drivers/cpufreq/hisi-acpu-cpufreq.c
deleted file mode 100644
index 026d5b2..0000000
--- a/drivers/cpufreq/hisi-acpu-cpufreq.c
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * Hisilicon Platforms Using ACPU CPUFreq Support
- *
- * Copyright (c) 2015 Hisilicon Limited.
- * Copyright (c) 2015 Linaro Limited.
- *
- * Leo Yan <leo.yan@linaro.org>
- *
- * 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.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-
-static int __init hisi_acpu_cpufreq_driver_init(void)
-{
-	struct platform_device *pdev;
-
-	if (!of_machine_is_compatible("hisilicon,hi6220"))
-		return -ENODEV;
-
-	pdev = platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
-	return PTR_ERR_OR_ZERO(pdev);
-}
-module_init(hisi_acpu_cpufreq_driver_init);
-
-MODULE_AUTHOR("Leo Yan <leo.yan@linaro.org>");
-MODULE_DESCRIPTION("Hisilicon acpu cpufreq driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index 0202429..759612d 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -8,6 +8,8 @@
  *      Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -118,8 +120,7 @@ processor_get_freq (
 
 	if (ret) {
 		set_cpus_allowed_ptr(current, &saved_mask);
-		printk(KERN_WARNING "get performance failed with error %d\n",
-		       ret);
+		pr_warn("get performance failed with error %d\n", ret);
 		ret = 0;
 		goto migrate_end;
 	}
@@ -177,7 +178,7 @@ processor_set_freq (
 
 	ret = processor_set_pstate(value);
 	if (ret) {
-		printk(KERN_WARNING "Transition failed with error %d\n", ret);
+		pr_warn("Transition failed with error %d\n", ret);
 		retval = -ENODEV;
 		goto migrate_end;
 	}
@@ -291,8 +292,7 @@ acpi_cpufreq_cpu_init (
 	/* notify BIOS that we exist */
 	acpi_processor_notify_smm(THIS_MODULE);
 
-	printk(KERN_INFO "acpi-cpufreq: CPU%u - ACPI performance management "
-	       "activated.\n", cpu);
+	pr_info("CPU%u - ACPI performance management activated\n", cpu);
 
 	for (i = 0; i < data->acpi_data.state_count; i++)
 		pr_debug("     %cP%d: %d MHz, %d mW, %d uS, %d uS, 0x%x 0x%x\n",
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index b230eba..b76a98d 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -10,6 +10,8 @@
  * of the License.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
@@ -39,10 +41,17 @@
 #define ATOM_TURBO_RATIOS	0x66c
 #define ATOM_TURBO_VIDS		0x66d
 
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+#endif
+
 #define FRAC_BITS 8
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
 #define fp_toint(X) ((X) >> FRAC_BITS)
 
+#define EXT_BITS 6
+#define EXT_FRAC_BITS (EXT_BITS + FRAC_BITS)
+
 static inline int32_t mul_fp(int32_t x, int32_t y)
 {
 	return ((int64_t)x * (int64_t)y) >> FRAC_BITS;
@@ -64,12 +73,22 @@ static inline int ceiling_fp(int32_t x)
 	return ret;
 }
 
+static inline u64 mul_ext_fp(u64 x, u64 y)
+{
+	return (x * y) >> EXT_FRAC_BITS;
+}
+
+static inline u64 div_ext_fp(u64 x, u64 y)
+{
+	return div64_u64(x << EXT_FRAC_BITS, y);
+}
+
 /**
  * struct sample -	Store performance sample
- * @core_pct_busy:	Ratio of APERF/MPERF in percent, which is actual
+ * @core_avg_perf:	Ratio of APERF/MPERF which is the actual average
  *			performance during last sample period
  * @busy_scaled:	Scaled busy value which is used to calculate next
- *			P state. This can be different than core_pct_busy
+ *			P state. This can be different than core_avg_perf
  *			to account for cpu idle period
  * @aperf:		Difference of actual performance frequency clock count
  *			read from APERF MSR between last and current sample
@@ -84,7 +103,7 @@ static inline int ceiling_fp(int32_t x)
  * data for choosing next P State.
  */
 struct sample {
-	int32_t core_pct_busy;
+	int32_t core_avg_perf;
 	int32_t busy_scaled;
 	u64 aperf;
 	u64 mperf;
@@ -162,6 +181,7 @@ struct _pid {
  * struct cpudata -	Per CPU instance data storage
  * @cpu:		CPU number for this instance data
  * @update_util:	CPUFreq utility callback information
+ * @update_util_set:	CPUFreq utility callback is set
  * @pstate:		Stores P state limits for this CPU
  * @vid:		Stores VID limits for this CPU
  * @pid:		Stores PID parameters for this CPU
@@ -172,6 +192,8 @@ struct _pid {
  * @prev_cummulative_iowait: IO Wait time difference from last and
  *			current sample
  * @sample:		Storage for storing last Sample data
+ * @acpi_perf_data:	Stores ACPI perf information read from _PSS
+ * @valid_pss_table:	Set to true for valid ACPI _PSS entries found
  *
  * This structure stores per CPU instance data for all CPUs.
  */
@@ -179,6 +201,7 @@ struct cpudata {
 	int cpu;
 
 	struct update_util_data update_util;
+	bool   update_util_set;
 
 	struct pstate_data pstate;
 	struct vid_data vid;
@@ -190,6 +213,10 @@ struct cpudata {
 	u64	prev_tsc;
 	u64	prev_cummulative_iowait;
 	struct sample sample;
+#ifdef CONFIG_ACPI
+	struct acpi_processor_performance acpi_perf_data;
+	bool valid_pss_table;
+#endif
 };
 
 static struct cpudata **all_cpu_data;
@@ -258,6 +285,9 @@ static struct pstate_adjust_policy pid_params;
 static struct pstate_funcs pstate_funcs;
 static int hwp_active;
 
+#ifdef CONFIG_ACPI
+static bool acpi_ppc;
+#endif
 
 /**
  * struct perf_limits - Store user and policy limits
@@ -331,6 +361,124 @@ static struct perf_limits *limits = &performance_limits;
 static struct perf_limits *limits = &powersave_limits;
 #endif
 
+#ifdef CONFIG_ACPI
+
+static bool intel_pstate_get_ppc_enable_status(void)
+{
+	if (acpi_gbl_FADT.preferred_profile == PM_ENTERPRISE_SERVER ||
+	    acpi_gbl_FADT.preferred_profile == PM_PERFORMANCE_SERVER)
+		return true;
+
+	return acpi_ppc;
+}
+
+/*
+ * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and
+ * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and
+ * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state
+ * ratio, out of it only high 8 bits are used. For example 0x1700 is setting
+ * target ratio 0x17. The _PSS control value stores in a format which can be
+ * directly written to PERF_CTL MSR. But in intel_pstate driver this shift
+ * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()).
+ * This function converts the _PSS control value to intel pstate driver format
+ * for comparison and assignment.
+ */
+static int convert_to_native_pstate_format(struct cpudata *cpu, int index)
+{
+	return cpu->acpi_perf_data.states[index].control >> 8;
+}
+
+static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
+{
+	struct cpudata *cpu;
+	int turbo_pss_ctl;
+	int ret;
+	int i;
+
+	if (hwp_active)
+		return;
+
+	if (!intel_pstate_get_ppc_enable_status())
+		return;
+
+	cpu = all_cpu_data[policy->cpu];
+
+	ret = acpi_processor_register_performance(&cpu->acpi_perf_data,
+						  policy->cpu);
+	if (ret)
+		return;
+
+	/*
+	 * Check if the control value in _PSS is for PERF_CTL MSR, which should
+	 * guarantee that the states returned by it map to the states in our
+	 * list directly.
+	 */
+	if (cpu->acpi_perf_data.control_register.space_id !=
+						ACPI_ADR_SPACE_FIXED_HARDWARE)
+		goto err;
+
+	/*
+	 * If there is only one entry _PSS, simply ignore _PSS and continue as
+	 * usual without taking _PSS into account
+	 */
+	if (cpu->acpi_perf_data.state_count < 2)
+		goto err;
+
+	pr_debug("CPU%u - ACPI _PSS perf data\n", policy->cpu);
+	for (i = 0; i < cpu->acpi_perf_data.state_count; i++) {
+		pr_debug("     %cP%d: %u MHz, %u mW, 0x%x\n",
+			 (i == cpu->acpi_perf_data.state ? '*' : ' '), i,
+			 (u32) cpu->acpi_perf_data.states[i].core_frequency,
+			 (u32) cpu->acpi_perf_data.states[i].power,
+			 (u32) cpu->acpi_perf_data.states[i].control);
+	}
+
+	/*
+	 * The _PSS table doesn't contain whole turbo frequency range.
+	 * This just contains +1 MHZ above the max non turbo frequency,
+	 * with control value corresponding to max turbo ratio. But
+	 * when cpufreq set policy is called, it will call with this
+	 * max frequency, which will cause a reduced performance as
+	 * this driver uses real max turbo frequency as the max
+	 * frequency. So correct this frequency in _PSS table to
+	 * correct max turbo frequency based on the turbo ratio.
+	 * Also need to convert to MHz as _PSS freq is in MHz.
+	 */
+	turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0);
+	if (turbo_pss_ctl > cpu->pstate.max_pstate)
+		cpu->acpi_perf_data.states[0].core_frequency =
+					policy->cpuinfo.max_freq / 1000;
+	cpu->valid_pss_table = true;
+	pr_info("_PPC limits will be enforced\n");
+
+	return;
+
+ err:
+	cpu->valid_pss_table = false;
+	acpi_processor_unregister_performance(policy->cpu);
+}
+
+static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
+{
+	struct cpudata *cpu;
+
+	cpu = all_cpu_data[policy->cpu];
+	if (!cpu->valid_pss_table)
+		return;
+
+	acpi_processor_unregister_performance(policy->cpu);
+}
+
+#else
+static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
+{
+}
+
+static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
+{
+}
+#endif
+
 static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
 			     int deadband, int integral) {
 	pid->setpoint = int_tofp(setpoint);
@@ -341,17 +489,17 @@ static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
 
 static inline void pid_p_gain_set(struct _pid *pid, int percent)
 {
-	pid->p_gain = div_fp(int_tofp(percent), int_tofp(100));
+	pid->p_gain = div_fp(percent, 100);
 }
 
 static inline void pid_i_gain_set(struct _pid *pid, int percent)
 {
-	pid->i_gain = div_fp(int_tofp(percent), int_tofp(100));
+	pid->i_gain = div_fp(percent, 100);
 }
 
 static inline void pid_d_gain_set(struct _pid *pid, int percent)
 {
-	pid->d_gain = div_fp(int_tofp(percent), int_tofp(100));
+	pid->d_gain = div_fp(percent, 100);
 }
 
 static signed int pid_calc(struct _pid *pid, int32_t busy)
@@ -537,7 +685,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj,
 
 	total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1;
 	no_turbo = cpu->pstate.max_pstate - cpu->pstate.min_pstate + 1;
-	turbo_fp = div_fp(int_tofp(no_turbo), int_tofp(total));
+	turbo_fp = div_fp(no_turbo, total);
 	turbo_pct = 100 - fp_toint(mul_fp(turbo_fp, int_tofp(100)));
 	return sprintf(buf, "%u\n", turbo_pct);
 }
@@ -579,7 +727,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 
 	update_turbo_state();
 	if (limits->turbo_disabled) {
-		pr_warn("intel_pstate: Turbo disabled by BIOS or unavailable on processor\n");
+		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
 		return -EPERM;
 	}
 
@@ -608,8 +756,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 				   limits->max_perf_pct);
 	limits->max_perf_pct = max(limits->min_perf_pct,
 				   limits->max_perf_pct);
-	limits->max_perf = div_fp(int_tofp(limits->max_perf_pct),
-				  int_tofp(100));
+	limits->max_perf = div_fp(limits->max_perf_pct, 100);
 
 	if (hwp_active)
 		intel_pstate_hwp_set_online_cpus();
@@ -633,8 +780,7 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 				   limits->min_perf_pct);
 	limits->min_perf_pct = min(limits->max_perf_pct,
 				   limits->min_perf_pct);
-	limits->min_perf = div_fp(int_tofp(limits->min_perf_pct),
-				  int_tofp(100));
+	limits->min_perf = div_fp(limits->min_perf_pct, 100);
 
 	if (hwp_active)
 		intel_pstate_hwp_set_online_cpus();
@@ -1019,15 +1165,11 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 	intel_pstate_set_min_pstate(cpu);
 }
 
-static inline void intel_pstate_calc_busy(struct cpudata *cpu)
+static inline void intel_pstate_calc_avg_perf(struct cpudata *cpu)
 {
 	struct sample *sample = &cpu->sample;
-	int64_t core_pct;
 
-	core_pct = int_tofp(sample->aperf) * int_tofp(100);
-	core_pct = div64_u64(core_pct, int_tofp(sample->mperf));
-
-	sample->core_pct_busy = (int32_t)core_pct;
+	sample->core_avg_perf = div_ext_fp(sample->aperf, sample->mperf);
 }
 
 static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
@@ -1070,9 +1212,14 @@ static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
 
 static inline int32_t get_avg_frequency(struct cpudata *cpu)
 {
-	return fp_toint(mul_fp(cpu->sample.core_pct_busy,
-			       int_tofp(cpu->pstate.max_pstate_physical *
-						cpu->pstate.scaling / 100)));
+	return mul_ext_fp(cpu->sample.core_avg_perf,
+			  cpu->pstate.max_pstate_physical * cpu->pstate.scaling);
+}
+
+static inline int32_t get_avg_pstate(struct cpudata *cpu)
+{
+	return mul_ext_fp(cpu->pstate.max_pstate_physical,
+			  cpu->sample.core_avg_perf);
 }
 
 static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
@@ -1107,49 +1254,43 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 	cpu_load = div64_u64(int_tofp(100) * mperf, sample->tsc);
 	cpu->sample.busy_scaled = cpu_load;
 
-	return cpu->pstate.current_pstate - pid_calc(&cpu->pid, cpu_load);
+	return get_avg_pstate(cpu) - pid_calc(&cpu->pid, cpu_load);
 }
 
 static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 {
-	int32_t core_busy, max_pstate, current_pstate, sample_ratio;
+	int32_t perf_scaled, max_pstate, current_pstate, sample_ratio;
 	u64 duration_ns;
 
 	/*
-	 * core_busy is the ratio of actual performance to max
-	 * max_pstate is the max non turbo pstate available
-	 * current_pstate was the pstate that was requested during
-	 * 	the last sample period.
-	 *
-	 * We normalize core_busy, which was our actual percent
-	 * performance to what we requested during the last sample
-	 * period. The result will be a percentage of busy at a
-	 * specified pstate.
+	 * perf_scaled is the average performance during the last sampling
+	 * period scaled by the ratio of the maximum P-state to the P-state
+	 * requested last time (in percent).  That measures the system's
+	 * response to the previous P-state selection.
 	 */
-	core_busy = cpu->sample.core_pct_busy;
-	max_pstate = int_tofp(cpu->pstate.max_pstate_physical);
-	current_pstate = int_tofp(cpu->pstate.current_pstate);
-	core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+	max_pstate = cpu->pstate.max_pstate_physical;
+	current_pstate = cpu->pstate.current_pstate;
+	perf_scaled = mul_ext_fp(cpu->sample.core_avg_perf,
+			       div_fp(100 * max_pstate, current_pstate));
 
 	/*
 	 * Since our utilization update callback will not run unless we are
 	 * in C0, check if the actual elapsed time is significantly greater (3x)
 	 * than our sample interval.  If it is, then we were idle for a long
-	 * enough period of time to adjust our busyness.
+	 * enough period of time to adjust our performance metric.
 	 */
 	duration_ns = cpu->sample.time - cpu->last_sample_time;
 	if ((s64)duration_ns > pid_params.sample_rate_ns * 3) {
-		sample_ratio = div_fp(int_tofp(pid_params.sample_rate_ns),
-				      int_tofp(duration_ns));
-		core_busy = mul_fp(core_busy, sample_ratio);
+		sample_ratio = div_fp(pid_params.sample_rate_ns, duration_ns);
+		perf_scaled = mul_fp(perf_scaled, sample_ratio);
 	} else {
 		sample_ratio = div_fp(100 * cpu->sample.mperf, cpu->sample.tsc);
 		if (sample_ratio < int_tofp(1))
-			core_busy = 0;
+			perf_scaled = 0;
 	}
 
-	cpu->sample.busy_scaled = core_busy;
-	return cpu->pstate.current_pstate - pid_calc(&cpu->pid, core_busy);
+	cpu->sample.busy_scaled = perf_scaled;
+	return cpu->pstate.current_pstate - pid_calc(&cpu->pid, perf_scaled);
 }
 
 static inline void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
@@ -1179,7 +1320,7 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 	intel_pstate_update_pstate(cpu, target_pstate);
 
 	sample = &cpu->sample;
-	trace_pstate_sample(fp_toint(sample->core_pct_busy),
+	trace_pstate_sample(mul_ext_fp(100, sample->core_avg_perf),
 		fp_toint(sample->busy_scaled),
 		from,
 		cpu->pstate.current_pstate,
@@ -1199,7 +1340,7 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time,
 		bool sample_taken = intel_pstate_sample(cpu, time);
 
 		if (sample_taken) {
-			intel_pstate_calc_busy(cpu);
+			intel_pstate_calc_avg_perf(cpu);
 			if (!hwp_active)
 				intel_pstate_adjust_busy_pstate(cpu);
 		}
@@ -1261,23 +1402,16 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 	intel_pstate_busy_pid_reset(cpu);
 
-	cpu->update_util.func = intel_pstate_update_util;
-
-	pr_debug("intel_pstate: controlling: cpu %d\n", cpunum);
+	pr_debug("controlling: cpu %d\n", cpunum);
 
 	return 0;
 }
 
 static unsigned int intel_pstate_get(unsigned int cpu_num)
 {
-	struct sample *sample;
-	struct cpudata *cpu;
+	struct cpudata *cpu = all_cpu_data[cpu_num];
 
-	cpu = all_cpu_data[cpu_num];
-	if (!cpu)
-		return 0;
-	sample = &cpu->sample;
-	return get_avg_frequency(cpu);
+	return cpu ? get_avg_frequency(cpu) : 0;
 }
 
 static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
@@ -1286,12 +1420,20 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
 
 	/* Prevent intel_pstate_update_util() from using stale data. */
 	cpu->sample.time = 0;
-	cpufreq_set_update_util_data(cpu_num, &cpu->update_util);
+	cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
+				     intel_pstate_update_util);
+	cpu->update_util_set = true;
 }
 
 static void intel_pstate_clear_update_util_hook(unsigned int cpu)
 {
-	cpufreq_set_update_util_data(cpu, NULL);
+	struct cpudata *cpu_data = all_cpu_data[cpu];
+
+	if (!cpu_data->update_util_set)
+		return;
+
+	cpufreq_remove_update_util_hook(cpu);
+	cpu_data->update_util_set = false;
 	synchronize_sched();
 }
 
@@ -1311,20 +1453,31 @@ static void intel_pstate_set_performance_limits(struct perf_limits *limits)
 
 static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 {
+	struct cpudata *cpu;
+
 	if (!policy->cpuinfo.max_freq)
 		return -ENODEV;
 
 	intel_pstate_clear_update_util_hook(policy->cpu);
 
+	cpu = all_cpu_data[0];
+	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate) {
+		if (policy->max < policy->cpuinfo.max_freq &&
+		    policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
+			pr_debug("policy->max > max non turbo frequency\n");
+			policy->max = policy->cpuinfo.max_freq;
+		}
+	}
+
 	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		limits = &performance_limits;
 		if (policy->max >= policy->cpuinfo.max_freq) {
-			pr_debug("intel_pstate: set performance\n");
+			pr_debug("set performance\n");
 			intel_pstate_set_performance_limits(limits);
 			goto out;
 		}
 	} else {
-		pr_debug("intel_pstate: set powersave\n");
+		pr_debug("set powersave\n");
 		limits = &powersave_limits;
 	}
 
@@ -1348,10 +1501,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	/* Make sure min_perf_pct <= max_perf_pct */
 	limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
 
-	limits->min_perf = div_fp(int_tofp(limits->min_perf_pct),
-				  int_tofp(100));
-	limits->max_perf = div_fp(int_tofp(limits->max_perf_pct),
-				  int_tofp(100));
+	limits->min_perf = div_fp(limits->min_perf_pct, 100);
+	limits->max_perf = div_fp(limits->max_perf_pct, 100);
 
  out:
 	intel_pstate_set_update_util_hook(policy->cpu);
@@ -1377,7 +1528,7 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 	int cpu_num = policy->cpu;
 	struct cpudata *cpu = all_cpu_data[cpu_num];
 
-	pr_debug("intel_pstate: CPU %d exiting\n", cpu_num);
+	pr_debug("CPU %d exiting\n", cpu_num);
 
 	intel_pstate_clear_update_util_hook(cpu_num);
 
@@ -1410,12 +1561,20 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	policy->cpuinfo.max_freq =
 		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+	intel_pstate_init_acpi_perf_limits(policy);
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	cpumask_set_cpu(policy->cpu, policy->cpus);
 
 	return 0;
 }
 
+static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
+{
+	intel_pstate_exit_perf_limits(policy);
+
+	return 0;
+}
+
 static struct cpufreq_driver intel_pstate_driver = {
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.verify		= intel_pstate_verify_policy,
@@ -1423,6 +1582,7 @@ static struct cpufreq_driver intel_pstate_driver = {
 	.resume		= intel_pstate_hwp_set_policy,
 	.get		= intel_pstate_get,
 	.init		= intel_pstate_cpu_init,
+	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_pstate_stop_cpu,
 	.name		= "intel_pstate",
 };
@@ -1466,8 +1626,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
 
 }
 
-#if IS_ENABLED(CONFIG_ACPI)
-#include <acpi/processor.h>
+#ifdef CONFIG_ACPI
 
 static bool intel_pstate_no_acpi_pss(void)
 {
@@ -1623,7 +1782,7 @@ hwp_cpu_matched:
 	if (intel_pstate_platform_pwr_mgmt_exists())
 		return -ENODEV;
 
-	pr_info("Intel P-state driver initializing.\n");
+	pr_info("Intel P-state driver initializing\n");
 
 	all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
 	if (!all_cpu_data)
@@ -1640,7 +1799,7 @@ hwp_cpu_matched:
 	intel_pstate_sysfs_expose_params();
 
 	if (hwp_active)
-		pr_info("intel_pstate: HWP enabled\n");
+		pr_info("HWP enabled\n");
 
 	return rc;
 out:
@@ -1666,13 +1825,19 @@ static int __init intel_pstate_setup(char *str)
 	if (!strcmp(str, "disable"))
 		no_load = 1;
 	if (!strcmp(str, "no_hwp")) {
-		pr_info("intel_pstate: HWP disabled\n");
+		pr_info("HWP disabled\n");
 		no_hwp = 1;
 	}
 	if (!strcmp(str, "force"))
 		force_load = 1;
 	if (!strcmp(str, "hwp_only"))
 		hwp_only = 1;
+
+#ifdef CONFIG_ACPI
+	if (!strcmp(str, "support_acpi_ppc"))
+		acpi_ppc = true;
+#endif
+
 	return 0;
 }
 early_param("intel_pstate", intel_pstate_setup);
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index 247bfa8..c46a12d 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -21,6 +21,8 @@
  *  BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -40,8 +42,6 @@
 
 #include "longhaul.h"
 
-#define PFX "longhaul: "
-
 #define TYPE_LONGHAUL_V1	1
 #define TYPE_LONGHAUL_V2	2
 #define TYPE_POWERSAVER		3
@@ -347,14 +347,13 @@ retry_loop:
 	freqs.new = calc_speed(longhaul_get_cpu_mult());
 	/* Check if requested frequency is set. */
 	if (unlikely(freqs.new != speed)) {
-		printk(KERN_INFO PFX "Failed to set requested frequency!\n");
+		pr_info("Failed to set requested frequency!\n");
 		/* Revision ID = 1 but processor is expecting revision key
 		 * equal to 0. Jumpers at the bottom of processor will change
 		 * multiplier and FSB, but will not change bits in Longhaul
 		 * MSR nor enable voltage scaling. */
 		if (!revid_errata) {
-			printk(KERN_INFO PFX "Enabling \"Ignore Revision ID\" "
-						"option.\n");
+			pr_info("Enabling \"Ignore Revision ID\" option\n");
 			revid_errata = 1;
 			msleep(200);
 			goto retry_loop;
@@ -364,11 +363,10 @@ retry_loop:
 		 * but it doesn't change frequency. I tried poking various
 		 * bits in northbridge registers, but without success. */
 		if (longhaul_flags & USE_ACPI_C3) {
-			printk(KERN_INFO PFX "Disabling ACPI C3 support.\n");
+			pr_info("Disabling ACPI C3 support\n");
 			longhaul_flags &= ~USE_ACPI_C3;
 			if (revid_errata) {
-				printk(KERN_INFO PFX "Disabling \"Ignore "
-						"Revision ID\" option.\n");
+				pr_info("Disabling \"Ignore Revision ID\" option\n");
 				revid_errata = 0;
 			}
 			msleep(200);
@@ -379,7 +377,7 @@ retry_loop:
 		 * RevID = 1. RevID errata will make things right. Just
 		 * to be 100% sure. */
 		if (longhaul_version == TYPE_LONGHAUL_V2) {
-			printk(KERN_INFO PFX "Switching to Longhaul ver. 1\n");
+			pr_info("Switching to Longhaul ver. 1\n");
 			longhaul_version = TYPE_LONGHAUL_V1;
 			msleep(200);
 			goto retry_loop;
@@ -387,8 +385,7 @@ retry_loop:
 	}
 
 	if (!bm_timeout) {
-		printk(KERN_INFO PFX "Warning: Timeout while waiting for "
-				"idle PCI bus.\n");
+		pr_info("Warning: Timeout while waiting for idle PCI bus\n");
 		return -EBUSY;
 	}
 
@@ -433,12 +430,12 @@ static int longhaul_get_ranges(void)
 	/* Get current frequency */
 	mult = longhaul_get_cpu_mult();
 	if (mult == -1) {
-		printk(KERN_INFO PFX "Invalid (reserved) multiplier!\n");
+		pr_info("Invalid (reserved) multiplier!\n");
 		return -EINVAL;
 	}
 	fsb = guess_fsb(mult);
 	if (fsb == 0) {
-		printk(KERN_INFO PFX "Invalid (reserved) FSB!\n");
+		pr_info("Invalid (reserved) FSB!\n");
 		return -EINVAL;
 	}
 	/* Get max multiplier - as we always did.
@@ -468,11 +465,11 @@ static int longhaul_get_ranges(void)
 		 print_speed(highest_speed/1000));
 
 	if (lowest_speed == highest_speed) {
-		printk(KERN_INFO PFX "highestspeed == lowest, aborting.\n");
+		pr_info("highestspeed == lowest, aborting\n");
 		return -EINVAL;
 	}
 	if (lowest_speed > highest_speed) {
-		printk(KERN_INFO PFX "nonsense! lowest (%d > %d) !\n",
+		pr_info("nonsense! lowest (%d > %d) !\n",
 			lowest_speed, highest_speed);
 		return -EINVAL;
 	}
@@ -538,16 +535,16 @@ static void longhaul_setup_voltagescaling(void)
 
 	rdmsrl(MSR_VIA_LONGHAUL, longhaul.val);
 	if (!(longhaul.bits.RevisionID & 1)) {
-		printk(KERN_INFO PFX "Voltage scaling not supported by CPU.\n");
+		pr_info("Voltage scaling not supported by CPU\n");
 		return;
 	}
 
 	if (!longhaul.bits.VRMRev) {
-		printk(KERN_INFO PFX "VRM 8.5\n");
+		pr_info("VRM 8.5\n");
 		vrm_mV_table = &vrm85_mV[0];
 		mV_vrm_table = &mV_vrm85[0];
 	} else {
-		printk(KERN_INFO PFX "Mobile VRM\n");
+		pr_info("Mobile VRM\n");
 		if (cpu_model < CPU_NEHEMIAH)
 			return;
 		vrm_mV_table = &mobilevrm_mV[0];
@@ -558,27 +555,21 @@ static void longhaul_setup_voltagescaling(void)
 	maxvid = vrm_mV_table[longhaul.bits.MaximumVID];
 
 	if (minvid.mV == 0 || maxvid.mV == 0 || minvid.mV > maxvid.mV) {
-		printk(KERN_INFO PFX "Bogus values Min:%d.%03d Max:%d.%03d. "
-					"Voltage scaling disabled.\n",
-					minvid.mV/1000, minvid.mV%1000,
-					maxvid.mV/1000, maxvid.mV%1000);
+		pr_info("Bogus values Min:%d.%03d Max:%d.%03d - Voltage scaling disabled\n",
+			minvid.mV/1000, minvid.mV%1000,
+			maxvid.mV/1000, maxvid.mV%1000);
 		return;
 	}
 
 	if (minvid.mV == maxvid.mV) {
-		printk(KERN_INFO PFX "Claims to support voltage scaling but "
-				"min & max are both %d.%03d. "
-				"Voltage scaling disabled\n",
-				maxvid.mV/1000, maxvid.mV%1000);
+		pr_info("Claims to support voltage scaling but min & max are both %d.%03d - Voltage scaling disabled\n",
+			maxvid.mV/1000, maxvid.mV%1000);
 		return;
 	}
 
 	/* How many voltage steps*/
 	numvscales = maxvid.pos - minvid.pos + 1;
-	printk(KERN_INFO PFX
-		"Max VID=%d.%03d  "
-		"Min VID=%d.%03d, "
-		"%d possible voltage scales\n",
+	pr_info("Max VID=%d.%03d  Min VID=%d.%03d, %d possible voltage scales\n",
 		maxvid.mV/1000, maxvid.mV%1000,
 		minvid.mV/1000, minvid.mV%1000,
 		numvscales);
@@ -617,12 +608,12 @@ static void longhaul_setup_voltagescaling(void)
 			pos = minvid.pos;
 		freq_pos->driver_data |= mV_vrm_table[pos] << 8;
 		vid = vrm_mV_table[mV_vrm_table[pos]];
-		printk(KERN_INFO PFX "f: %d kHz, index: %d, vid: %d mV\n",
+		pr_info("f: %d kHz, index: %d, vid: %d mV\n",
 			speed, (int)(freq_pos - longhaul_table), vid.mV);
 	}
 
 	can_scale_voltage = 1;
-	printk(KERN_INFO PFX "Voltage scaling enabled.\n");
+	pr_info("Voltage scaling enabled\n");
 }
 
 
@@ -720,8 +711,7 @@ static int enable_arbiter_disable(void)
 			pci_write_config_byte(dev, reg, pci_cmd);
 			pci_read_config_byte(dev, reg, &pci_cmd);
 			if (!(pci_cmd & 1<<7)) {
-				printk(KERN_ERR PFX
-					"Can't enable access to port 0x22.\n");
+				pr_err("Can't enable access to port 0x22\n");
 				status = 0;
 			}
 		}
@@ -758,8 +748,7 @@ static int longhaul_setup_southbridge(void)
 		if (pci_cmd & 1 << 7) {
 			pci_read_config_dword(dev, 0x88, &acpi_regs_addr);
 			acpi_regs_addr &= 0xff00;
-			printk(KERN_INFO PFX "ACPI I/O at 0x%x\n",
-					acpi_regs_addr);
+			pr_info("ACPI I/O at 0x%x\n", acpi_regs_addr);
 		}
 
 		pci_dev_put(dev);
@@ -853,14 +842,14 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy)
 			longhaul_version = TYPE_LONGHAUL_V1;
 	}
 
-	printk(KERN_INFO PFX "VIA %s CPU detected.  ", cpuname);
+	pr_info("VIA %s CPU detected.  ", cpuname);
 	switch (longhaul_version) {
 	case TYPE_LONGHAUL_V1:
 	case TYPE_LONGHAUL_V2:
-		printk(KERN_CONT "Longhaul v%d supported.\n", longhaul_version);
+		pr_cont("Longhaul v%d supported\n", longhaul_version);
 		break;
 	case TYPE_POWERSAVER:
-		printk(KERN_CONT "Powersaver supported.\n");
+		pr_cont("Powersaver supported\n");
 		break;
 	};
 
@@ -889,15 +878,14 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy)
 	if (!(longhaul_flags & USE_ACPI_C3
 	     || longhaul_flags & USE_NORTHBRIDGE)
 	    && ((pr == NULL) || !(pr->flags.bm_control))) {
-		printk(KERN_ERR PFX
-			"No ACPI support. Unsupported northbridge.\n");
+		pr_err("No ACPI support: Unsupported northbridge\n");
 		return -ENODEV;
 	}
 
 	if (longhaul_flags & USE_NORTHBRIDGE)
-		printk(KERN_INFO PFX "Using northbridge support.\n");
+		pr_info("Using northbridge support\n");
 	if (longhaul_flags & USE_ACPI_C3)
-		printk(KERN_INFO PFX "Using ACPI support.\n");
+		pr_info("Using ACPI support\n");
 
 	ret = longhaul_get_ranges();
 	if (ret != 0)
@@ -934,20 +922,18 @@ static int __init longhaul_init(void)
 		return -ENODEV;
 
 	if (!enable) {
-		printk(KERN_ERR PFX "Option \"enable\" not set. Aborting.\n");
+		pr_err("Option \"enable\" not set - Aborting\n");
 		return -ENODEV;
 	}
 #ifdef CONFIG_SMP
 	if (num_online_cpus() > 1) {
-		printk(KERN_ERR PFX "More than 1 CPU detected, "
-				"longhaul disabled.\n");
+		pr_err("More than 1 CPU detected, longhaul disabled\n");
 		return -ENODEV;
 	}
 #endif
 #ifdef CONFIG_X86_IO_APIC
 	if (boot_cpu_has(X86_FEATURE_APIC)) {
-		printk(KERN_ERR PFX "APIC detected. Longhaul is currently "
-				"broken in this configuration.\n");
+		pr_err("APIC detected. Longhaul is currently broken in this configuration.\n");
 		return -ENODEV;
 	}
 #endif
@@ -955,7 +941,7 @@ static int __init longhaul_init(void)
 	case 6 ... 9:
 		return cpufreq_register_driver(&longhaul_driver);
 	case 10:
-		printk(KERN_ERR PFX "Use acpi-cpufreq driver for VIA C7\n");
+		pr_err("Use acpi-cpufreq driver for VIA C7\n");
 	default:
 		;
 	}
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index cd593c1..6bbdac1 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -10,6 +10,9 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/cpufreq.h>
 #include <linux/module.h>
 #include <linux/err.h>
@@ -76,7 +79,7 @@ static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	cpuclk = clk_get(NULL, "cpu_clk");
 	if (IS_ERR(cpuclk)) {
-		printk(KERN_ERR "cpufreq: couldn't get CPU clk\n");
+		pr_err("couldn't get CPU clk\n");
 		return PTR_ERR(cpuclk);
 	}
 
@@ -163,7 +166,7 @@ static int __init cpufreq_init(void)
 	if (ret)
 		return ret;
 
-	pr_info("cpufreq: Loongson-2F CPU frequency driver.\n");
+	pr_info("Loongson-2F CPU frequency driver\n");
 
 	cpufreq_register_notifier(&loongson2_cpufreq_notifier_block,
 				  CPUFREQ_TRANSITION_NOTIFIER);
diff --git a/drivers/cpufreq/maple-cpufreq.c b/drivers/cpufreq/maple-cpufreq.c
index cc3408f..d9df893 100644
--- a/drivers/cpufreq/maple-cpufreq.c
+++ b/drivers/cpufreq/maple-cpufreq.c
@@ -13,6 +13,8 @@
 
 #undef DEBUG
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/errno.h>
@@ -174,7 +176,7 @@ static int __init maple_cpufreq_init(void)
 	/* Get first CPU node */
 	cpunode = of_cpu_device_node_get(0);
 	if (cpunode == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find any CPU 0 node\n");
+		pr_err("Can't find any CPU 0 node\n");
 		goto bail_noprops;
 	}
 
@@ -182,8 +184,7 @@ static int __init maple_cpufreq_init(void)
 	/* we actually don't care on which CPU to access PVR */
 	pvr_hi = PVR_VER(mfspr(SPRN_PVR));
 	if (pvr_hi != 0x3c && pvr_hi != 0x44) {
-		printk(KERN_ERR "cpufreq: Unsupported CPU version (%x)\n",
-				pvr_hi);
+		pr_err("Unsupported CPU version (%x)\n", pvr_hi);
 		goto bail_noprops;
 	}
 
@@ -222,8 +223,8 @@ static int __init maple_cpufreq_init(void)
 	maple_pmode_cur = -1;
 	maple_scom_switch_freq(maple_scom_query_freq());
 
-	printk(KERN_INFO "Registering Maple CPU frequency driver\n");
-	printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n",
+	pr_info("Registering Maple CPU frequency driver\n");
+	pr_info("Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n",
 		maple_cpu_freqs[1].frequency/1000,
 		maple_cpu_freqs[0].frequency/1000,
 		maple_cpu_freqs[maple_pmode_cur].frequency/1000);
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index 2058e6d..6f602c7 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -59,11 +59,8 @@ static LIST_HEAD(dvfs_info_list);
 static struct mtk_cpu_dvfs_info *mtk_cpu_dvfs_info_lookup(int cpu)
 {
 	struct mtk_cpu_dvfs_info *info;
-	struct list_head *list;
-
-	list_for_each(list, &dvfs_info_list) {
-		info = list_entry(list, struct mtk_cpu_dvfs_info, list_head);
 
+	list_for_each_entry(info, &dvfs_info_list, list_head) {
 		if (cpumask_test_cpu(cpu, &info->cpus))
 			return info;
 	}
@@ -524,8 +521,7 @@ static struct cpufreq_driver mt8173_cpufreq_driver = {
 
 static int mt8173_cpufreq_probe(struct platform_device *pdev)
 {
-	struct mtk_cpu_dvfs_info *info;
-	struct list_head *list, *tmp;
+	struct mtk_cpu_dvfs_info *info, *tmp;
 	int cpu, ret;
 
 	for_each_possible_cpu(cpu) {
@@ -559,11 +555,9 @@ static int mt8173_cpufreq_probe(struct platform_device *pdev)
 	return 0;
 
 release_dvfs_info_list:
-	list_for_each_safe(list, tmp, &dvfs_info_list) {
-		info = list_entry(list, struct mtk_cpu_dvfs_info, list_head);
-
+	list_for_each_entry_safe(info, tmp, &dvfs_info_list, list_head) {
 		mtk_cpu_dvfs_info_release(info);
-		list_del(list);
+		list_del(&info->list_head);
 	}
 
 	return ret;
diff --git a/drivers/cpufreq/mvebu-cpufreq.c b/drivers/cpufreq/mvebu-cpufreq.c
new file mode 100644
index 0000000..e920889
--- /dev/null
+++ b/drivers/cpufreq/mvebu-cpufreq.c
@@ -0,0 +1,107 @@
+/*
+ * CPUFreq support for Armada 370/XP platforms.
+ *
+ * Copyright (C) 2012-2016 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory Clement <gregory.clement@free-electrons.com>
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#define pr_fmt(fmt) "mvebu-pmsu: " fmt
+
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/resource.h>
+
+static int __init armada_xp_pmsu_cpufreq_init(void)
+{
+	struct device_node *np;
+	struct resource res;
+	int ret, cpu;
+
+	if (!of_machine_is_compatible("marvell,armadaxp"))
+		return 0;
+
+	/*
+	 * In order to have proper cpufreq handling, we need to ensure
+	 * that the Device Tree description of the CPU clock includes
+	 * the definition of the PMU DFS registers. If not, we do not
+	 * register the clock notifier and the cpufreq driver. This
+	 * piece of code is only for compatibility with old Device
+	 * Trees.
+	 */
+	np = of_find_compatible_node(NULL, NULL, "marvell,armada-xp-cpu-clock");
+	if (!np)
+		return 0;
+
+	ret = of_address_to_resource(np, 1, &res);
+	if (ret) {
+		pr_warn(FW_WARN "not enabling cpufreq, deprecated armada-xp-cpu-clock binding\n");
+		of_node_put(np);
+		return 0;
+	}
+
+	of_node_put(np);
+
+	/*
+	 * For each CPU, this loop registers the operating points
+	 * supported (which are the nominal CPU frequency and half of
+	 * it), and registers the clock notifier that will take care
+	 * of doing the PMSU part of a frequency transition.
+	 */
+	for_each_possible_cpu(cpu) {
+		struct device *cpu_dev;
+		struct clk *clk;
+		int ret;
+
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("Cannot get CPU %d\n", cpu);
+			continue;
+		}
+
+		clk = clk_get(cpu_dev, 0);
+		if (IS_ERR(clk)) {
+			pr_err("Cannot get clock for CPU %d\n", cpu);
+			return PTR_ERR(clk);
+		}
+
+		/*
+		 * In case of a failure of dev_pm_opp_add(), we don't
+		 * bother with cleaning up the registered OPP (there's
+		 * no function to do so), and simply cancel the
+		 * registration of the cpufreq device.
+		 */
+		ret = dev_pm_opp_add(cpu_dev, clk_get_rate(clk), 0);
+		if (ret) {
+			clk_put(clk);
+			return ret;
+		}
+
+		ret = dev_pm_opp_add(cpu_dev, clk_get_rate(clk) / 2, 0);
+		if (ret) {
+			clk_put(clk);
+			return ret;
+		}
+
+		ret = dev_pm_opp_set_sharing_cpus(cpu_dev,
+						  cpumask_of(cpu_dev->id));
+		if (ret)
+			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
+				__func__, ret);
+	}
+
+	platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
+	return 0;
+}
+device_initcall(armada_xp_pmsu_cpufreq_init);
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index e3866e0..cead9be 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -13,6 +13,9 @@
  * 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/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -163,13 +166,13 @@ static int omap_cpufreq_probe(struct platform_device *pdev)
 {
 	mpu_dev = get_cpu_device(0);
 	if (!mpu_dev) {
-		pr_warning("%s: unable to get the mpu device\n", __func__);
+		pr_warn("%s: unable to get the MPU device\n", __func__);
 		return -EINVAL;
 	}
 
 	mpu_reg = regulator_get(mpu_dev, "vcc");
 	if (IS_ERR(mpu_reg)) {
-		pr_warning("%s: unable to get MPU regulator\n", __func__);
+		pr_warn("%s: unable to get MPU regulator\n", __func__);
 		mpu_reg = NULL;
 	} else {
 		/* 
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index 5dd95da..fd77812 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -20,6 +20,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -35,8 +37,6 @@
 
 #include "speedstep-lib.h"
 
-#define PFX	"p4-clockmod: "
-
 /*
  * Duty Cycle (3bits), note DC_DISABLE is not specified in
  * intel docs i just use it to mean disable
@@ -124,11 +124,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c)
 {
 	if (c->x86 == 0x06) {
 		if (cpu_has(c, X86_FEATURE_EST))
-			printk_once(KERN_WARNING PFX "Warning: EST-capable "
-			       "CPU detected. The acpi-cpufreq module offers "
-			       "voltage scaling in addition to frequency "
-			       "scaling. You should use that instead of "
-			       "p4-clockmod, if possible.\n");
+			pr_warn_once("Warning: EST-capable CPU detected. The acpi-cpufreq module offers voltage scaling in addition to frequency scaling. You should use that instead of p4-clockmod, if possible.\n");
 		switch (c->x86_model) {
 		case 0x0E: /* Core */
 		case 0x0F: /* Core Duo */
@@ -152,11 +148,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c)
 	p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS;
 
 	if (speedstep_detect_processor() == SPEEDSTEP_CPU_P4M) {
-		printk(KERN_WARNING PFX "Warning: Pentium 4-M detected. "
-		       "The speedstep-ich or acpi cpufreq modules offer "
-		       "voltage scaling in addition of frequency scaling. "
-		       "You should use either one instead of p4-clockmod, "
-		       "if possible.\n");
+		pr_warn("Warning: Pentium 4-M detected. The speedstep-ich or acpi cpufreq modules offer voltage scaling in addition of frequency scaling. You should use either one instead of p4-clockmod, if possible.\n");
 		return speedstep_get_frequency(SPEEDSTEP_CPU_P4M);
 	}
 
@@ -265,8 +257,7 @@ static int __init cpufreq_p4_init(void)
 
 	ret = cpufreq_register_driver(&p4clockmod_driver);
 	if (!ret)
-		printk(KERN_INFO PFX "P4/Xeon(TM) CPU On-Demand Clock "
-				"Modulation available\n");
+		pr_info("P4/Xeon(TM) CPU On-Demand Clock Modulation available\n");
 
 	return ret;
 }
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c
index 1f49d97..b7b576e 100644
--- a/drivers/cpufreq/pmac32-cpufreq.c
+++ b/drivers/cpufreq/pmac32-cpufreq.c
@@ -13,6 +13,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/errno.h>
@@ -481,13 +483,13 @@ static int pmac_cpufreq_init_MacRISC3(struct device_node *cpunode)
 		freqs = of_get_property(cpunode, "bus-frequencies", &lenp);
 		lenp /= sizeof(u32);
 		if (freqs == NULL || lenp != 2) {
-			printk(KERN_ERR "cpufreq: bus-frequencies incorrect or missing\n");
+			pr_err("bus-frequencies incorrect or missing\n");
 			return 1;
 		}
 		ratio = of_get_property(cpunode, "processor-to-bus-ratio*2",
 						NULL);
 		if (ratio == NULL) {
-			printk(KERN_ERR "cpufreq: processor-to-bus-ratio*2 missing\n");
+			pr_err("processor-to-bus-ratio*2 missing\n");
 			return 1;
 		}
 
@@ -550,7 +552,7 @@ static int pmac_cpufreq_init_7447A(struct device_node *cpunode)
 	if (volt_gpio_np)
 		voltage_gpio = read_gpio(volt_gpio_np);
 	if (!voltage_gpio){
-		printk(KERN_ERR "cpufreq: missing cpu-vcore-select gpio\n");
+		pr_err("missing cpu-vcore-select gpio\n");
 		return 1;
 	}
 
@@ -675,9 +677,9 @@ out:
 	pmac_cpu_freqs[CPUFREQ_HIGH].frequency = hi_freq;
 	ppc_proc_freq = cur_freq * 1000ul;
 
-	printk(KERN_INFO "Registering PowerMac CPU frequency driver\n");
-	printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Boot: %d Mhz\n",
-	       low_freq/1000, hi_freq/1000, cur_freq/1000);
+	pr_info("Registering PowerMac CPU frequency driver\n");
+	pr_info("Low: %d Mhz, High: %d Mhz, Boot: %d Mhz\n",
+		low_freq/1000, hi_freq/1000, cur_freq/1000);
 
 	return cpufreq_register_driver(&pmac_cpufreq_driver);
 }
diff --git a/drivers/cpufreq/pmac64-cpufreq.c b/drivers/cpufreq/pmac64-cpufreq.c
index 4ff8687..267e089 100644
--- a/drivers/cpufreq/pmac64-cpufreq.c
+++ b/drivers/cpufreq/pmac64-cpufreq.c
@@ -12,6 +12,8 @@
 
 #undef DEBUG
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/errno.h>
@@ -138,7 +140,7 @@ static void g5_vdnap_switch_volt(int speed_mode)
 		usleep_range(1000, 1000);
 	}
 	if (done == 0)
-		printk(KERN_WARNING "cpufreq: Timeout in clock slewing !\n");
+		pr_warn("Timeout in clock slewing !\n");
 }
 
 
@@ -266,7 +268,7 @@ static int g5_pfunc_switch_freq(int speed_mode)
 		rc = pmf_call_one(pfunc_cpu_setfreq_low, NULL);
 
 	if (rc)
-		printk(KERN_WARNING "cpufreq: pfunc switch error %d\n", rc);
+		pr_warn("pfunc switch error %d\n", rc);
 
 	/* It's an irq GPIO so we should be able to just block here,
 	 * I'll do that later after I've properly tested the IRQ code for
@@ -282,7 +284,7 @@ static int g5_pfunc_switch_freq(int speed_mode)
 		usleep_range(500, 500);
 	}
 	if (done == 0)
-		printk(KERN_WARNING "cpufreq: Timeout in clock slewing !\n");
+		pr_warn("Timeout in clock slewing !\n");
 
 	/* If frequency is going down, last ramp the voltage */
 	if (speed_mode > g5_pmode_cur)
@@ -368,7 +370,7 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpunode)
 	}
 	pvr_hi = (*valp) >> 16;
 	if (pvr_hi != 0x3c && pvr_hi != 0x44) {
-		printk(KERN_ERR "cpufreq: Unsupported CPU version\n");
+		pr_err("Unsupported CPU version\n");
 		goto bail_noprops;
 	}
 
@@ -403,8 +405,7 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpunode)
 
 		root = of_find_node_by_path("/");
 		if (root == NULL) {
-			printk(KERN_ERR "cpufreq: Can't find root of "
-			       "device tree\n");
+			pr_err("Can't find root of device tree\n");
 			goto bail_noprops;
 		}
 		pfunc_set_vdnap0 = pmf_find_function(root, "set-vdnap0");
@@ -412,8 +413,7 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpunode)
 			pmf_find_function(root, "slewing-done");
 		if (pfunc_set_vdnap0 == NULL ||
 		    pfunc_vdnap0_complete == NULL) {
-			printk(KERN_ERR "cpufreq: Can't find required "
-			       "platform function\n");
+			pr_err("Can't find required platform function\n");
 			goto bail_noprops;
 		}
 
@@ -453,10 +453,10 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpunode)
 	g5_pmode_cur = -1;
 	g5_switch_freq(g5_query_freq());
 
-	printk(KERN_INFO "Registering G5 CPU frequency driver\n");
-	printk(KERN_INFO "Frequency method: %s, Voltage method: %s\n",
-	       freq_method, volt_method);
-	printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n",
+	pr_info("Registering G5 CPU frequency driver\n");
+	pr_info("Frequency method: %s, Voltage method: %s\n",
+		freq_method, volt_method);
+	pr_info("Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n",
 		g5_cpu_freqs[1].frequency/1000,
 		g5_cpu_freqs[0].frequency/1000,
 		g5_cpu_freqs[g5_pmode_cur].frequency/1000);
@@ -493,7 +493,7 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpunode)
 	if (cpuid != NULL)
 		eeprom = of_get_property(cpuid, "cpuid", NULL);
 	if (eeprom == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find cpuid EEPROM !\n");
+		pr_err("Can't find cpuid EEPROM !\n");
 		rc = -ENODEV;
 		goto bail;
 	}
@@ -511,7 +511,7 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpunode)
 		break;
 	}
 	if (hwclock == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find i2c clock chip !\n");
+		pr_err("Can't find i2c clock chip !\n");
 		rc = -ENODEV;
 		goto bail;
 	}
@@ -539,7 +539,7 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpunode)
 	/* Check we have minimum requirements */
 	if (pfunc_cpu_getfreq == NULL || pfunc_cpu_setfreq_high == NULL ||
 	    pfunc_cpu_setfreq_low == NULL || pfunc_slewing_done == NULL) {
-		printk(KERN_ERR "cpufreq: Can't find platform functions !\n");
+		pr_err("Can't find platform functions !\n");
 		rc = -ENODEV;
 		goto bail;
 	}
@@ -567,7 +567,7 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpunode)
 	/* Get max frequency from device-tree */
 	valp = of_get_property(cpunode, "clock-frequency", NULL);
 	if (!valp) {
-		printk(KERN_ERR "cpufreq: Can't find CPU frequency !\n");
+		pr_err("Can't find CPU frequency !\n");
 		rc = -ENODEV;
 		goto bail;
 	}
@@ -583,8 +583,7 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpunode)
 
 	/* Check for machines with no useful settings */
 	if (il == ih) {
-		printk(KERN_WARNING "cpufreq: No low frequency mode available"
-		       " on this model !\n");
+		pr_warn("No low frequency mode available on this model !\n");
 		rc = -ENODEV;
 		goto bail;
 	}
@@ -595,7 +594,7 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpunode)
 
 	/* Sanity check */
 	if (min_freq >= max_freq || min_freq < 1000) {
-		printk(KERN_ERR "cpufreq: Can't calculate low frequency !\n");
+		pr_err("Can't calculate low frequency !\n");
 		rc = -ENXIO;
 		goto bail;
 	}
@@ -619,10 +618,10 @@ static int __init g5_pm72_cpufreq_init(struct device_node *cpunode)
 	g5_pmode_cur = -1;
 	g5_switch_freq(g5_query_freq());
 
-	printk(KERN_INFO "Registering G5 CPU frequency driver\n");
-	printk(KERN_INFO "Frequency method: i2c/pfunc, "
-	       "Voltage method: %s\n", has_volt ? "i2c/pfunc" : "none");
-	printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n",
+	pr_info("Registering G5 CPU frequency driver\n");
+	pr_info("Frequency method: i2c/pfunc, Voltage method: %s\n",
+		has_volt ? "i2c/pfunc" : "none");
+	pr_info("Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n",
 		g5_cpu_freqs[1].frequency/1000,
 		g5_cpu_freqs[0].frequency/1000,
 		g5_cpu_freqs[g5_pmode_cur].frequency/1000);
@@ -654,7 +653,7 @@ static int __init g5_cpufreq_init(void)
 	/* Get first CPU node */
 	cpunode = of_cpu_device_node_get(0);
 	if (cpunode == NULL) {
-		pr_err("cpufreq: Can't find any CPU node\n");
+		pr_err("Can't find any CPU node\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c
index e6f24b2..dedd256 100644
--- a/drivers/cpufreq/powernow-k6.c
+++ b/drivers/cpufreq/powernow-k6.c
@@ -8,6 +8,8 @@
  *  BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -22,7 +24,6 @@
 #define POWERNOW_IOPORT 0xfff0          /* it doesn't matter where, as long
 					   as it is unused */
 
-#define PFX "powernow-k6: "
 static unsigned int                     busfreq;   /* FSB, in 10 kHz */
 static unsigned int                     max_multiplier;
 
@@ -141,7 +142,7 @@ static int powernow_k6_target(struct cpufreq_policy *policy,
 {
 
 	if (clock_ratio[best_i].driver_data > max_multiplier) {
-		printk(KERN_ERR PFX "invalid target frequency\n");
+		pr_err("invalid target frequency\n");
 		return -EINVAL;
 	}
 
@@ -175,13 +176,14 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
 				max_multiplier = param_max_multiplier;
 				goto have_max_multiplier;
 			}
-		printk(KERN_ERR "powernow-k6: invalid max_multiplier parameter, valid parameters 20, 30, 35, 40, 45, 50, 55, 60\n");
+		pr_err("invalid max_multiplier parameter, valid parameters 20, 30, 35, 40, 45, 50, 55, 60\n");
 		return -EINVAL;
 	}
 
 	if (!max_multiplier) {
-		printk(KERN_WARNING "powernow-k6: unknown frequency %u, cannot determine current multiplier\n", khz);
-		printk(KERN_WARNING "powernow-k6: use module parameters max_multiplier and bus_frequency\n");
+		pr_warn("unknown frequency %u, cannot determine current multiplier\n",
+			khz);
+		pr_warn("use module parameters max_multiplier and bus_frequency\n");
 		return -EOPNOTSUPP;
 	}
 
@@ -193,7 +195,7 @@ have_max_multiplier:
 			busfreq = param_busfreq / 10;
 			goto have_busfreq;
 		}
-		printk(KERN_ERR "powernow-k6: invalid bus_frequency parameter, allowed range 50000 - 150000 kHz\n");
+		pr_err("invalid bus_frequency parameter, allowed range 50000 - 150000 kHz\n");
 		return -EINVAL;
 	}
 
@@ -275,7 +277,7 @@ static int __init powernow_k6_init(void)
 		return -ENODEV;
 
 	if (!request_region(POWERNOW_IOPORT, 16, "PowerNow!")) {
-		printk(KERN_INFO PFX "PowerNow IOPORT region already used.\n");
+		pr_info("PowerNow IOPORT region already used\n");
 		return -EIO;
 	}
 
diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c
index c1ae199..9f013ed 100644
--- a/drivers/cpufreq/powernow-k7.c
+++ b/drivers/cpufreq/powernow-k7.c
@@ -13,6 +13,8 @@
  *  - We disable half multipliers if ACPI is used on A0 stepping CPUs.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -35,9 +37,6 @@
 
 #include "powernow-k7.h"
 
-#define PFX "powernow: "
-
-
 struct psb_s {
 	u8 signature[10];
 	u8 tableversion;
@@ -127,14 +126,13 @@ static int check_powernow(void)
 	maxei = cpuid_eax(0x80000000);
 	if (maxei < 0x80000007) {	/* Any powernow info ? */
 #ifdef MODULE
-		printk(KERN_INFO PFX "No powernow capabilities detected\n");
+		pr_info("No powernow capabilities detected\n");
 #endif
 		return 0;
 	}
 
 	if ((c->x86_model == 6) && (c->x86_mask == 0)) {
-		printk(KERN_INFO PFX "K7 660[A0] core detected, "
-				"enabling errata workarounds\n");
+		pr_info("K7 660[A0] core detected, enabling errata workarounds\n");
 		have_a0 = 1;
 	}
 
@@ -144,22 +142,22 @@ static int check_powernow(void)
 	if (!(edx & (1 << 1 | 1 << 2)))
 		return 0;
 
-	printk(KERN_INFO PFX "PowerNOW! Technology present. Can scale: ");
+	pr_info("PowerNOW! Technology present. Can scale: ");
 
 	if (edx & 1 << 1) {
-		printk("frequency");
+		pr_cont("frequency");
 		can_scale_bus = 1;
 	}
 
 	if ((edx & (1 << 1 | 1 << 2)) == 0x6)
-		printk(" and ");
+		pr_cont(" and ");
 
 	if (edx & 1 << 2) {
-		printk("voltage");
+		pr_cont("voltage");
 		can_scale_vid = 1;
 	}
 
-	printk(".\n");
+	pr_cont("\n");
 	return 1;
 }
 
@@ -427,16 +425,14 @@ err1:
 err05:
 	kfree(acpi_processor_perf);
 err0:
-	printk(KERN_WARNING PFX "ACPI perflib can not be used on "
-			"this platform\n");
+	pr_warn("ACPI perflib can not be used on this platform\n");
 	acpi_processor_perf = NULL;
 	return retval;
 }
 #else
 static int powernow_acpi_init(void)
 {
-	printk(KERN_INFO PFX "no support for ACPI processor found."
-	       "  Please recompile your kernel with ACPI processor\n");
+	pr_info("no support for ACPI processor found - please recompile your kernel with ACPI processor\n");
 	return -EINVAL;
 }
 #endif
@@ -468,8 +464,7 @@ static int powernow_decode_bios(int maxfid, int startvid)
 			psb = (struct psb_s *) p;
 			pr_debug("Table version: 0x%x\n", psb->tableversion);
 			if (psb->tableversion != 0x12) {
-				printk(KERN_INFO PFX "Sorry, only v1.2 tables"
-						" supported right now\n");
+				pr_info("Sorry, only v1.2 tables supported right now\n");
 				return -ENODEV;
 			}
 
@@ -481,10 +476,8 @@ static int powernow_decode_bios(int maxfid, int startvid)
 
 			latency = psb->settlingtime;
 			if (latency < 100) {
-				printk(KERN_INFO PFX "BIOS set settling time "
-						"to %d microseconds. "
-						"Should be at least 100. "
-						"Correcting.\n", latency);
+				pr_info("BIOS set settling time to %d microseconds. Should be at least 100. Correcting.\n",
+					latency);
 				latency = 100;
 			}
 			pr_debug("Settling Time: %d microseconds.\n",
@@ -516,10 +509,9 @@ static int powernow_decode_bios(int maxfid, int startvid)
 						p += 2;
 				}
 			}
-			printk(KERN_INFO PFX "No PST tables match this cpuid "
-					"(0x%x)\n", etuple);
-			printk(KERN_INFO PFX "This is indicative of a broken "
-					"BIOS.\n");
+			pr_info("No PST tables match this cpuid (0x%x)\n",
+				etuple);
+			pr_info("This is indicative of a broken BIOS\n");
 
 			return -EINVAL;
 		}
@@ -552,7 +544,7 @@ static int fixup_sgtc(void)
 	sgtc = 100 * m * latency;
 	sgtc = sgtc / 3;
 	if (sgtc > 0xfffff) {
-		printk(KERN_WARNING PFX "SGTC too large %d\n", sgtc);
+		pr_warn("SGTC too large %d\n", sgtc);
 		sgtc = 0xfffff;
 	}
 	return sgtc;
@@ -574,14 +566,10 @@ static unsigned int powernow_get(unsigned int cpu)
 
 static int acer_cpufreq_pst(const struct dmi_system_id *d)
 {
-	printk(KERN_WARNING PFX
-		"%s laptop with broken PST tables in BIOS detected.\n",
+	pr_warn("%s laptop with broken PST tables in BIOS detected\n",
 		d->ident);
-	printk(KERN_WARNING PFX
-		"You need to downgrade to 3A21 (09/09/2002), or try a newer "
-		"BIOS than 3A71 (01/20/2003)\n");
-	printk(KERN_WARNING PFX
-		"cpufreq scaling has been disabled as a result of this.\n");
+	pr_warn("You need to downgrade to 3A21 (09/09/2002), or try a newer BIOS than 3A71 (01/20/2003)\n");
+	pr_warn("cpufreq scaling has been disabled as a result of this\n");
 	return 0;
 }
 
@@ -616,40 +604,38 @@ static int powernow_cpu_init(struct cpufreq_policy *policy)
 
 	fsb = (10 * cpu_khz) / fid_codes[fidvidstatus.bits.CFID];
 	if (!fsb) {
-		printk(KERN_WARNING PFX "can not determine bus frequency\n");
+		pr_warn("can not determine bus frequency\n");
 		return -EINVAL;
 	}
 	pr_debug("FSB: %3dMHz\n", fsb/1000);
 
 	if (dmi_check_system(powernow_dmi_table) || acpi_force) {
-		printk(KERN_INFO PFX "PSB/PST known to be broken.  "
-				"Trying ACPI instead\n");
+		pr_info("PSB/PST known to be broken - trying ACPI instead\n");
 		result = powernow_acpi_init();
 	} else {
 		result = powernow_decode_bios(fidvidstatus.bits.MFID,
 				fidvidstatus.bits.SVID);
 		if (result) {
-			printk(KERN_INFO PFX "Trying ACPI perflib\n");
+			pr_info("Trying ACPI perflib\n");
 			maximum_speed = 0;
 			minimum_speed = -1;
 			latency = 0;
 			result = powernow_acpi_init();
 			if (result) {
-				printk(KERN_INFO PFX
-					"ACPI and legacy methods failed\n");
+				pr_info("ACPI and legacy methods failed\n");
 			}
 		} else {
 			/* SGTC use the bus clock as timer */
 			latency = fixup_sgtc();
-			printk(KERN_INFO PFX "SGTC: %d\n", latency);
+			pr_info("SGTC: %d\n", latency);
 		}
 	}
 
 	if (result)
 		return result;
 
-	printk(KERN_INFO PFX "Minimum speed %d MHz. Maximum speed %d MHz.\n",
-				minimum_speed/1000, maximum_speed/1000);
+	pr_info("Minimum speed %d MHz - Maximum speed %d MHz\n",
+		minimum_speed/1000, maximum_speed/1000);
 
 	policy->cpuinfo.transition_latency =
 		cpufreq_scale(2000000UL, fsb, latency);
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 39ac78c..54c4536 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -36,12 +36,56 @@
 #include <asm/reg.h>
 #include <asm/smp.h> /* Required for cpu_sibling_mask() in UP configs */
 #include <asm/opal.h>
+#include <linux/timer.h>
 
 #define POWERNV_MAX_PSTATES	256
 #define PMSR_PSAFE_ENABLE	(1UL << 30)
 #define PMSR_SPR_EM_DISABLE	(1UL << 31)
 #define PMSR_MAX(x)		((x >> 32) & 0xFF)
 
+#define MAX_RAMP_DOWN_TIME				5120
+/*
+ * On an idle system we want the global pstate to ramp-down from max value to
+ * min over a span of ~5 secs. Also we want it to initially ramp-down slowly and
+ * then ramp-down rapidly later on.
+ *
+ * This gives a percentage rampdown for time elapsed in milliseconds.
+ * ramp_down_percentage = ((ms * ms) >> 18)
+ *			~= 3.8 * (sec * sec)
+ *
+ * At 0 ms	ramp_down_percent = 0
+ * At 5120 ms	ramp_down_percent = 100
+ */
+#define ramp_down_percent(time)		((time * time) >> 18)
+
+/* Interval after which the timer is queued to bring down global pstate */
+#define GPSTATE_TIMER_INTERVAL				2000
+
+/**
+ * struct global_pstate_info -	Per policy data structure to maintain history of
+ *				global pstates
+ * @highest_lpstate:		The local pstate from which we are ramping down
+ * @elapsed_time:		Time in ms spent in ramping down from
+ *				highest_lpstate
+ * @last_sampled_time:		Time from boot in ms when global pstates were
+ *				last set
+ * @last_lpstate,last_gpstate:	Last set values for local and global pstates
+ * @timer:			Is used for ramping down if cpu goes idle for
+ *				a long time with global pstate held high
+ * @gpstate_lock:		A spinlock to maintain synchronization between
+ *				routines called by the timer handler and
+ *				governer's target_index calls
+ */
+struct global_pstate_info {
+	int highest_lpstate;
+	unsigned int elapsed_time;
+	unsigned int last_sampled_time;
+	int last_lpstate;
+	int last_gpstate;
+	spinlock_t gpstate_lock;
+	struct timer_list timer;
+};
+
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
 static bool rebooting, throttled, occ_reset;
 
@@ -94,6 +138,17 @@ static struct powernv_pstate_info {
 	int nr_pstates;
 } powernv_pstate_info;
 
+static inline void reset_gpstates(struct cpufreq_policy *policy)
+{
+	struct global_pstate_info *gpstates = policy->driver_data;
+
+	gpstates->highest_lpstate = 0;
+	gpstates->elapsed_time = 0;
+	gpstates->last_sampled_time = 0;
+	gpstates->last_lpstate = 0;
+	gpstates->last_gpstate = 0;
+}
+
 /*
  * Initialize the freq table based on data obtained
  * from the firmware passed via device-tree
@@ -285,6 +340,7 @@ static inline void set_pmspr(unsigned long sprn, unsigned long val)
 struct powernv_smp_call_data {
 	unsigned int freq;
 	int pstate_id;
+	int gpstate_id;
 };
 
 /*
@@ -343,19 +399,21 @@ static unsigned int powernv_cpufreq_get(unsigned int cpu)
  * (struct powernv_smp_call_data *) and the pstate_id which needs to be set
  * on this CPU should be present in freq_data->pstate_id.
  */
-static void set_pstate(void *freq_data)
+static void set_pstate(void *data)
 {
 	unsigned long val;
-	unsigned long pstate_ul =
-		((struct powernv_smp_call_data *) freq_data)->pstate_id;
+	struct powernv_smp_call_data *freq_data = data;
+	unsigned long pstate_ul = freq_data->pstate_id;
+	unsigned long gpstate_ul = freq_data->gpstate_id;
 
 	val = get_pmspr(SPRN_PMCR);
 	val = val & 0x0000FFFFFFFFFFFFULL;
 
 	pstate_ul = pstate_ul & 0xFF;
+	gpstate_ul = gpstate_ul & 0xFF;
 
 	/* Set both global(bits 56..63) and local(bits 48..55) PStates */
-	val = val | (pstate_ul << 56) | (pstate_ul << 48);
+	val = val | (gpstate_ul << 56) | (pstate_ul << 48);
 
 	pr_debug("Setting cpu %d pmcr to %016lX\n",
 			raw_smp_processor_id(), val);
@@ -424,6 +482,111 @@ next:
 	}
 }
 
+/**
+ * calc_global_pstate - Calculate global pstate
+ * @elapsed_time:	Elapsed time in milliseconds
+ * @local_pstate:	New local pstate
+ * @highest_lpstate:	pstate from which its ramping down
+ *
+ * Finds the appropriate global pstate based on the pstate from which its
+ * ramping down and the time elapsed in ramping down. It follows a quadratic
+ * equation which ensures that it reaches ramping down to pmin in 5sec.
+ */
+static inline int calc_global_pstate(unsigned int elapsed_time,
+				     int highest_lpstate, int local_pstate)
+{
+	int pstate_diff;
+
+	/*
+	 * Using ramp_down_percent we get the percentage of rampdown
+	 * that we are expecting to be dropping. Difference between
+	 * highest_lpstate and powernv_pstate_info.min will give a absolute
+	 * number of how many pstates we will drop eventually by the end of
+	 * 5 seconds, then just scale it get the number pstates to be dropped.
+	 */
+	pstate_diff =  ((int)ramp_down_percent(elapsed_time) *
+			(highest_lpstate - powernv_pstate_info.min)) / 100;
+
+	/* Ensure that global pstate is >= to local pstate */
+	if (highest_lpstate - pstate_diff < local_pstate)
+		return local_pstate;
+	else
+		return highest_lpstate - pstate_diff;
+}
+
+static inline void  queue_gpstate_timer(struct global_pstate_info *gpstates)
+{
+	unsigned int timer_interval;
+
+	/*
+	 * Setting up timer to fire after GPSTATE_TIMER_INTERVAL ms, But
+	 * if it exceeds MAX_RAMP_DOWN_TIME ms for ramp down time.
+	 * Set timer such that it fires exactly at MAX_RAMP_DOWN_TIME
+	 * seconds of ramp down time.
+	 */
+	if ((gpstates->elapsed_time + GPSTATE_TIMER_INTERVAL)
+	     > MAX_RAMP_DOWN_TIME)
+		timer_interval = MAX_RAMP_DOWN_TIME - gpstates->elapsed_time;
+	else
+		timer_interval = GPSTATE_TIMER_INTERVAL;
+
+	mod_timer_pinned(&gpstates->timer, jiffies +
+			msecs_to_jiffies(timer_interval));
+}
+
+/**
+ * gpstate_timer_handler
+ *
+ * @data: pointer to cpufreq_policy on which timer was queued
+ *
+ * This handler brings down the global pstate closer to the local pstate
+ * according quadratic equation. Queues a new timer if it is still not equal
+ * to local pstate
+ */
+void gpstate_timer_handler(unsigned long data)
+{
+	struct cpufreq_policy *policy = (struct cpufreq_policy *)data;
+	struct global_pstate_info *gpstates = policy->driver_data;
+	int gpstate_id;
+	unsigned int time_diff = jiffies_to_msecs(jiffies)
+					- gpstates->last_sampled_time;
+	struct powernv_smp_call_data freq_data;
+
+	if (!spin_trylock(&gpstates->gpstate_lock))
+		return;
+
+	gpstates->last_sampled_time += time_diff;
+	gpstates->elapsed_time += time_diff;
+	freq_data.pstate_id = gpstates->last_lpstate;
+
+	if ((gpstates->last_gpstate == freq_data.pstate_id) ||
+	    (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME)) {
+		gpstate_id = freq_data.pstate_id;
+		reset_gpstates(policy);
+		gpstates->highest_lpstate = freq_data.pstate_id;
+	} else {
+		gpstate_id = calc_global_pstate(gpstates->elapsed_time,
+						gpstates->highest_lpstate,
+						freq_data.pstate_id);
+	}
+
+	/*
+	 * If local pstate is equal to global pstate, rampdown is over
+	 * So timer is not required to be queued.
+	 */
+	if (gpstate_id != freq_data.pstate_id)
+		queue_gpstate_timer(gpstates);
+
+	freq_data.gpstate_id = gpstate_id;
+	gpstates->last_gpstate = freq_data.gpstate_id;
+	gpstates->last_lpstate = freq_data.pstate_id;
+
+	spin_unlock(&gpstates->gpstate_lock);
+
+	/* Timer may get migrated to a different cpu on cpu hot unplug */
+	smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1);
+}
+
 /*
  * powernv_cpufreq_target_index: Sets the frequency corresponding to
  * the cpufreq table entry indexed by new_index on the cpus in the
@@ -433,6 +596,8 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 					unsigned int new_index)
 {
 	struct powernv_smp_call_data freq_data;
+	unsigned int cur_msec, gpstate_id;
+	struct global_pstate_info *gpstates = policy->driver_data;
 
 	if (unlikely(rebooting) && new_index != get_nominal_index())
 		return 0;
@@ -440,28 +605,81 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 	if (!throttled)
 		powernv_cpufreq_throttle_check(NULL);
 
+	cur_msec = jiffies_to_msecs(get_jiffies_64());
+
+	spin_lock(&gpstates->gpstate_lock);
 	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
 
+	if (!gpstates->last_sampled_time) {
+		gpstate_id = freq_data.pstate_id;
+		gpstates->highest_lpstate = freq_data.pstate_id;
+		goto gpstates_done;
+	}
+
+	if (gpstates->last_gpstate > freq_data.pstate_id) {
+		gpstates->elapsed_time += cur_msec -
+						 gpstates->last_sampled_time;
+
+		/*
+		 * If its has been ramping down for more than MAX_RAMP_DOWN_TIME
+		 * we should be resetting all global pstate related data. Set it
+		 * equal to local pstate to start fresh.
+		 */
+		if (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME) {
+			reset_gpstates(policy);
+			gpstates->highest_lpstate = freq_data.pstate_id;
+			gpstate_id = freq_data.pstate_id;
+		} else {
+		/* Elaspsed_time is less than 5 seconds, continue to rampdown */
+			gpstate_id = calc_global_pstate(gpstates->elapsed_time,
+							gpstates->highest_lpstate,
+							freq_data.pstate_id);
+		}
+	} else {
+		reset_gpstates(policy);
+		gpstates->highest_lpstate = freq_data.pstate_id;
+		gpstate_id = freq_data.pstate_id;
+	}
+
+	/*
+	 * If local pstate is equal to global pstate, rampdown is over
+	 * So timer is not required to be queued.
+	 */
+	if (gpstate_id != freq_data.pstate_id)
+		queue_gpstate_timer(gpstates);
+	else
+		del_timer_sync(&gpstates->timer);
+
+gpstates_done:
+	freq_data.gpstate_id = gpstate_id;
+	gpstates->last_sampled_time = cur_msec;
+	gpstates->last_gpstate = freq_data.gpstate_id;
+	gpstates->last_lpstate = freq_data.pstate_id;
+
+	spin_unlock(&gpstates->gpstate_lock);
+
 	/*
 	 * Use smp_call_function to send IPI and execute the
 	 * mtspr on target CPU.  We could do that without IPI
 	 * if current CPU is within policy->cpus (core)
 	 */
 	smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1);
-
 	return 0;
 }
 
 static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	int base, i;
+	int base, i, ret;
+	struct kernfs_node *kn;
+	struct global_pstate_info *gpstates;
 
 	base = cpu_first_thread_sibling(policy->cpu);
 
 	for (i = 0; i < threads_per_core; i++)
 		cpumask_set_cpu(base + i, policy->cpus);
 
-	if (!policy->driver_data) {
+	kn = kernfs_find_and_get(policy->kobj.sd, throttle_attr_grp.name);
+	if (!kn) {
 		int ret;
 
 		ret = sysfs_create_group(&policy->kobj, &throttle_attr_grp);
@@ -470,13 +688,37 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy)
 				policy->cpu);
 			return ret;
 		}
-		/*
-		 * policy->driver_data is used as a flag for one-time
-		 * creation of throttle sysfs files.
-		 */
-		policy->driver_data = policy;
+	} else {
+		kernfs_put(kn);
 	}
-	return cpufreq_table_validate_and_show(policy, powernv_freqs);
+
+	gpstates =  kzalloc(sizeof(*gpstates), GFP_KERNEL);
+	if (!gpstates)
+		return -ENOMEM;
+
+	policy->driver_data = gpstates;
+
+	/* initialize timer */
+	init_timer_deferrable(&gpstates->timer);
+	gpstates->timer.data = (unsigned long)policy;
+	gpstates->timer.function = gpstate_timer_handler;
+	gpstates->timer.expires = jiffies +
+				msecs_to_jiffies(GPSTATE_TIMER_INTERVAL);
+	spin_lock_init(&gpstates->gpstate_lock);
+	ret = cpufreq_table_validate_and_show(policy, powernv_freqs);
+
+	if (ret < 0)
+		kfree(policy->driver_data);
+
+	return ret;
+}
+
+static int powernv_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+	/* timer is deleted in cpufreq_cpu_stop() */
+	kfree(policy->driver_data);
+
+	return 0;
 }
 
 static int powernv_cpufreq_reboot_notifier(struct notifier_block *nb,
@@ -604,15 +846,19 @@ static struct notifier_block powernv_cpufreq_opal_nb = {
 static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 {
 	struct powernv_smp_call_data freq_data;
+	struct global_pstate_info *gpstates = policy->driver_data;
 
 	freq_data.pstate_id = powernv_pstate_info.min;
+	freq_data.gpstate_id = powernv_pstate_info.min;
 	smp_call_function_single(policy->cpu, set_pstate, &freq_data, 1);
+	del_timer_sync(&gpstates->timer);
 }
 
 static struct cpufreq_driver powernv_cpufreq_driver = {
 	.name		= "powernv-cpufreq",
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= powernv_cpufreq_cpu_init,
+	.exit		= powernv_cpufreq_cpu_exit,
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= powernv_cpufreq_target_index,
 	.get		= powernv_cpufreq_get,
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.h b/drivers/cpufreq/ppc_cbe_cpufreq.h
index b4c00a5..3eace72 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq.h
+++ b/drivers/cpufreq/ppc_cbe_cpufreq.h
@@ -17,7 +17,7 @@ int cbe_cpufreq_get_pmode(int cpu);
 
 int cbe_cpufreq_set_pmode_pmi(int cpu, unsigned int pmode);
 
-#if defined(CONFIG_CPU_FREQ_CBE_PMI) || defined(CONFIG_CPU_FREQ_CBE_PMI_MODULE)
+#if IS_ENABLED(CONFIG_CPU_FREQ_CBE_PMI)
 extern bool cbe_cpufreq_has_pmi;
 #else
 #define cbe_cpufreq_has_pmi (0)
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index 7969f76..7c4cd5c 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -23,7 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/timer.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of_platform.h>
 
 #include <asm/processor.h>
@@ -142,15 +142,4 @@ static int __init cbe_cpufreq_pmi_init(void)
 
 	return 0;
 }
-
-static void __exit cbe_cpufreq_pmi_exit(void)
-{
-	cpufreq_unregister_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER);
-	pmi_unregister_handler(&cbe_pmi_handler);
-}
-
-module_init(cbe_cpufreq_pmi_init);
-module_exit(cbe_cpufreq_pmi_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
+device_initcall(cbe_cpufreq_pmi_init);
diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c
index 46fee15..ce345bf 100644
--- a/drivers/cpufreq/pxa2xx-cpufreq.c
+++ b/drivers/cpufreq/pxa2xx-cpufreq.c
@@ -29,6 +29,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
@@ -186,8 +188,7 @@ static int pxa_cpufreq_change_voltage(const struct pxa_freqs *pxa_freq)
 
 	ret = regulator_set_voltage(vcc_core, vmin, vmax);
 	if (ret)
-		pr_err("cpufreq: Failed to set vcc_core in [%dmV..%dmV]\n",
-		       vmin, vmax);
+		pr_err("Failed to set vcc_core in [%dmV..%dmV]\n", vmin, vmax);
 	return ret;
 }
 
@@ -195,10 +196,10 @@ static void __init pxa_cpufreq_init_voltages(void)
 {
 	vcc_core = regulator_get(NULL, "vcc_core");
 	if (IS_ERR(vcc_core)) {
-		pr_info("cpufreq: Didn't find vcc_core regulator\n");
+		pr_info("Didn't find vcc_core regulator\n");
 		vcc_core = NULL;
 	} else {
-		pr_info("cpufreq: Found vcc_core regulator\n");
+		pr_info("Found vcc_core regulator\n");
 	}
 }
 #else
@@ -233,9 +234,8 @@ static void pxa27x_guess_max_freq(void)
 {
 	if (!pxa27x_maxfreq) {
 		pxa27x_maxfreq = 416000;
-		printk(KERN_INFO "PXA CPU 27x max frequency not defined "
-		       "(pxa27x_maxfreq), assuming pxa271 with %dkHz maxfreq\n",
-		       pxa27x_maxfreq);
+		pr_info("PXA CPU 27x max frequency not defined (pxa27x_maxfreq), assuming pxa271 with %dkHz maxfreq\n",
+			pxa27x_maxfreq);
 	} else {
 		pxa27x_maxfreq *= 1000;
 	}
@@ -408,7 +408,7 @@ static int pxa_cpufreq_init(struct cpufreq_policy *policy)
 	 */
 	if (cpu_is_pxa25x()) {
 		find_freq_tables(&pxa255_freq_table, &pxa255_freqs);
-		pr_info("PXA255 cpufreq using %s frequency table\n",
+		pr_info("using %s frequency table\n",
 			pxa255_turbo_table ? "turbo" : "run");
 
 		cpufreq_table_validate_and_show(policy, pxa255_freq_table);
@@ -417,7 +417,7 @@ static int pxa_cpufreq_init(struct cpufreq_policy *policy)
 		cpufreq_table_validate_and_show(policy, pxa27x_freq_table);
 	}
 
-	printk(KERN_INFO "PXA CPU frequency change support initialized\n");
+	pr_info("frequency change support initialized\n");
 
 	return 0;
 }
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index b23e525..53d8c3f 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -301,10 +301,11 @@ err_np:
 	return -ENODEV;
 }
 
-static int __exit qoriq_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+static int qoriq_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
 	struct cpu_data *data = policy->driver_data;
 
+	cpufreq_cooling_unregister(data->cdev);
 	kfree(data->pclk);
 	kfree(data->table);
 	kfree(data);
@@ -333,8 +334,8 @@ static void qoriq_cpufreq_ready(struct cpufreq_policy *policy)
 		cpud->cdev = of_cpufreq_cooling_register(np,
 							 policy->related_cpus);
 
-		if (IS_ERR(cpud->cdev)) {
-			pr_err("Failed to register cooling device cpu%d: %ld\n",
+		if (IS_ERR(cpud->cdev) && PTR_ERR(cpud->cdev) != -ENOSYS) {
+			pr_err("cpu%d is not running as cooling device: %ld\n",
 					policy->cpu, PTR_ERR(cpud->cdev));
 
 			cpud->cdev = NULL;
@@ -348,7 +349,7 @@ static struct cpufreq_driver qoriq_cpufreq_driver = {
 	.name		= "qoriq_cpufreq",
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= qoriq_cpufreq_cpu_init,
-	.exit		= __exit_p(qoriq_cpufreq_cpu_exit),
+	.exit		= qoriq_cpufreq_cpu_exit,
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= qoriq_cpufreq_target,
 	.get		= cpufreq_generic_get,
diff --git a/drivers/cpufreq/s3c2412-cpufreq.c b/drivers/cpufreq/s3c2412-cpufreq.c
index eb26213..b04b6f0 100644
--- a/drivers/cpufreq/s3c2412-cpufreq.c
+++ b/drivers/cpufreq/s3c2412-cpufreq.c
@@ -10,6 +10,8 @@
  * published by the Free Software Foundation.
 */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
@@ -197,21 +199,20 @@ static int s3c2412_cpufreq_add(struct device *dev,
 
 	hclk = clk_get(NULL, "hclk");
 	if (IS_ERR(hclk)) {
-		printk(KERN_ERR "%s: cannot find hclk clock\n", __func__);
+		pr_err("cannot find hclk clock\n");
 		return -ENOENT;
 	}
 
 	fclk = clk_get(NULL, "fclk");
 	if (IS_ERR(fclk)) {
-		printk(KERN_ERR "%s: cannot find fclk clock\n", __func__);
+		pr_err("cannot find fclk clock\n");
 		goto err_fclk;
 	}
 
 	fclk_rate = clk_get_rate(fclk);
 	if (fclk_rate > 200000000) {
-		printk(KERN_INFO
-		       "%s: fclk %ld MHz, assuming 266MHz capable part\n",
-		       __func__, fclk_rate / 1000000);
+		pr_info("fclk %ld MHz, assuming 266MHz capable part\n",
+			fclk_rate / 1000000);
 		s3c2412_cpufreq_info.max.fclk = 266000000;
 		s3c2412_cpufreq_info.max.hclk = 133000000;
 		s3c2412_cpufreq_info.max.pclk =  66000000;
@@ -219,13 +220,13 @@ static int s3c2412_cpufreq_add(struct device *dev,
 
 	armclk = clk_get(NULL, "armclk");
 	if (IS_ERR(armclk)) {
-		printk(KERN_ERR "%s: cannot find arm clock\n", __func__);
+		pr_err("cannot find arm clock\n");
 		goto err_armclk;
 	}
 
 	xtal = clk_get(NULL, "xtal");
 	if (IS_ERR(xtal)) {
-		printk(KERN_ERR "%s: cannot find xtal clock\n", __func__);
+		pr_err("cannot find xtal clock\n");
 		goto err_xtal;
 	}
 
diff --git a/drivers/cpufreq/s3c2440-cpufreq.c b/drivers/cpufreq/s3c2440-cpufreq.c
index 0129f5c..d0d75b6 100644
--- a/drivers/cpufreq/s3c2440-cpufreq.c
+++ b/drivers/cpufreq/s3c2440-cpufreq.c
@@ -11,6 +11,8 @@
  * published by the Free Software Foundation.
 */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
@@ -66,7 +68,7 @@ static int s3c2440_cpufreq_calcdivs(struct s3c_cpufreq_config *cfg)
 		     __func__, fclk, armclk, hclk_max);
 
 	if (armclk > fclk) {
-		printk(KERN_WARNING "%s: armclk > fclk\n", __func__);
+		pr_warn("%s: armclk > fclk\n", __func__);
 		armclk = fclk;
 	}
 
@@ -273,7 +275,7 @@ static int s3c2440_cpufreq_add(struct device *dev,
 	armclk = s3c_cpufreq_clk_get(NULL, "armclk");
 
 	if (IS_ERR(xtal) || IS_ERR(hclk) || IS_ERR(fclk) || IS_ERR(armclk)) {
-		printk(KERN_ERR "%s: failed to get clocks\n", __func__);
+		pr_err("%s: failed to get clocks\n", __func__);
 		return -ENOENT;
 	}
 
diff --git a/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c b/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c
index 9b7b428..4d976e8 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c
@@ -10,6 +10,8 @@
  * published by the Free Software Foundation.
 */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/interrupt.h>
@@ -178,7 +180,7 @@ static int __init s3c_freq_debugfs_init(void)
 {
 	dbgfs_root = debugfs_create_dir("s3c-cpufreq", NULL);
 	if (IS_ERR(dbgfs_root)) {
-		printk(KERN_ERR "%s: error creating debugfs root\n", __func__);
+		pr_err("%s: error creating debugfs root\n", __func__);
 		return PTR_ERR(dbgfs_root);
 	}
 
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index 68ef8fd..ae8eaed 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -10,6 +10,8 @@
  * published by the Free Software Foundation.
 */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
@@ -175,7 +177,7 @@ static int s3c_cpufreq_settarget(struct cpufreq_policy *policy,
 	cpu_new.freq.fclk = cpu_new.pll.frequency;
 
 	if (s3c_cpufreq_calcdivs(&cpu_new) < 0) {
-		printk(KERN_ERR "no divisors for %d\n", target_freq);
+		pr_err("no divisors for %d\n", target_freq);
 		goto err_notpossible;
 	}
 
@@ -187,7 +189,7 @@ static int s3c_cpufreq_settarget(struct cpufreq_policy *policy,
 
 	if (cpu_new.freq.hclk != cpu_cur.freq.hclk) {
 		if (s3c_cpufreq_calcio(&cpu_new) < 0) {
-			printk(KERN_ERR "%s: no IO timings\n", __func__);
+			pr_err("%s: no IO timings\n", __func__);
 			goto err_notpossible;
 		}
 	}
@@ -262,7 +264,7 @@ static int s3c_cpufreq_settarget(struct cpufreq_policy *policy,
 	return 0;
 
  err_notpossible:
-	printk(KERN_ERR "no compatible settings for %d\n", target_freq);
+	pr_err("no compatible settings for %d\n", target_freq);
 	return -EINVAL;
 }
 
@@ -331,7 +333,7 @@ static int s3c_cpufreq_target(struct cpufreq_policy *policy,
 						     &index);
 
 		if (ret < 0) {
-			printk(KERN_ERR "%s: no PLL available\n", __func__);
+			pr_err("%s: no PLL available\n", __func__);
 			goto err_notpossible;
 		}
 
@@ -346,7 +348,7 @@ static int s3c_cpufreq_target(struct cpufreq_policy *policy,
 	return s3c_cpufreq_settarget(policy, target_freq, pll);
 
  err_notpossible:
-	printk(KERN_ERR "no compatible settings for %d\n", target_freq);
+	pr_err("no compatible settings for %d\n", target_freq);
 	return -EINVAL;
 }
 
@@ -356,7 +358,7 @@ struct clk *s3c_cpufreq_clk_get(struct device *dev, const char *name)
 
 	clk = clk_get(dev, name);
 	if (IS_ERR(clk))
-		printk(KERN_ERR "cpufreq: failed to get clock '%s'\n", name);
+		pr_err("failed to get clock '%s'\n", name);
 
 	return clk;
 }
@@ -378,15 +380,16 @@ static int __init s3c_cpufreq_initclks(void)
 
 	if (IS_ERR(clk_fclk) || IS_ERR(clk_hclk) || IS_ERR(clk_pclk) ||
 	    IS_ERR(_clk_mpll) || IS_ERR(clk_arm) || IS_ERR(_clk_xtal)) {
-		printk(KERN_ERR "%s: could not get clock(s)\n", __func__);
+		pr_err("%s: could not get clock(s)\n", __func__);
 		return -ENOENT;
 	}
 
-	printk(KERN_INFO "%s: clocks f=%lu,h=%lu,p=%lu,a=%lu\n", __func__,
-	       clk_get_rate(clk_fclk) / 1000,
-	       clk_get_rate(clk_hclk) / 1000,
-	       clk_get_rate(clk_pclk) / 1000,
-	       clk_get_rate(clk_arm) / 1000);
+	pr_info("%s: clocks f=%lu,h=%lu,p=%lu,a=%lu\n",
+		__func__,
+		clk_get_rate(clk_fclk) / 1000,
+		clk_get_rate(clk_hclk) / 1000,
+		clk_get_rate(clk_pclk) / 1000,
+		clk_get_rate(clk_arm) / 1000);
 
 	return 0;
 }
@@ -424,7 +427,7 @@ static int s3c_cpufreq_resume(struct cpufreq_policy *policy)
 
 	ret = s3c_cpufreq_settarget(NULL, suspend_freq, &suspend_pll);
 	if (ret) {
-		printk(KERN_ERR "%s: failed to reset pll/freq\n", __func__);
+		pr_err("%s: failed to reset pll/freq\n", __func__);
 		return ret;
 	}
 
@@ -449,13 +452,12 @@ static struct cpufreq_driver s3c24xx_driver = {
 int s3c_cpufreq_register(struct s3c_cpufreq_info *info)
 {
 	if (!info || !info->name) {
-		printk(KERN_ERR "%s: failed to pass valid information\n",
-		       __func__);
+		pr_err("%s: failed to pass valid information\n", __func__);
 		return -EINVAL;
 	}
 
-	printk(KERN_INFO "S3C24XX CPU Frequency driver, %s cpu support\n",
-	       info->name);
+	pr_info("S3C24XX CPU Frequency driver, %s cpu support\n",
+		info->name);
 
 	/* check our driver info has valid data */
 
@@ -478,7 +480,7 @@ int __init s3c_cpufreq_setboard(struct s3c_cpufreq_board *board)
 	struct s3c_cpufreq_board *ours;
 
 	if (!board) {
-		printk(KERN_INFO "%s: no board data\n", __func__);
+		pr_info("%s: no board data\n", __func__);
 		return -EINVAL;
 	}
 
@@ -487,7 +489,7 @@ int __init s3c_cpufreq_setboard(struct s3c_cpufreq_board *board)
 
 	ours = kzalloc(sizeof(*ours), GFP_KERNEL);
 	if (ours == NULL) {
-		printk(KERN_ERR "%s: no memory\n", __func__);
+		pr_err("%s: no memory\n", __func__);
 		return -ENOMEM;
 	}
 
@@ -502,15 +504,15 @@ static int __init s3c_cpufreq_auto_io(void)
 	int ret;
 
 	if (!cpu_cur.info->get_iotiming) {
-		printk(KERN_ERR "%s: get_iotiming undefined\n", __func__);
+		pr_err("%s: get_iotiming undefined\n", __func__);
 		return -ENOENT;
 	}
 
-	printk(KERN_INFO "%s: working out IO settings\n", __func__);
+	pr_info("%s: working out IO settings\n", __func__);
 
 	ret = (cpu_cur.info->get_iotiming)(&cpu_cur, &s3c24xx_iotiming);
 	if (ret)
-		printk(KERN_ERR "%s: failed to get timings\n", __func__);
+		pr_err("%s: failed to get timings\n", __func__);
 
 	return ret;
 }
@@ -561,7 +563,7 @@ static void s3c_cpufreq_update_loctkime(void)
 	val = calc_locktime(rate, cpu_cur.info->locktime_u) << bits;
 	val |= calc_locktime(rate, cpu_cur.info->locktime_m);
 
-	printk(KERN_INFO "%s: new locktime is 0x%08x\n", __func__, val);
+	pr_info("%s: new locktime is 0x%08x\n", __func__, val);
 	__raw_writel(val, S3C2410_LOCKTIME);
 }
 
@@ -580,7 +582,7 @@ static int s3c_cpufreq_build_freq(void)
 
 	ftab = kzalloc(sizeof(*ftab) * size, GFP_KERNEL);
 	if (!ftab) {
-		printk(KERN_ERR "%s: no memory for tables\n", __func__);
+		pr_err("%s: no memory for tables\n", __func__);
 		return -ENOMEM;
 	}
 
@@ -608,15 +610,14 @@ static int __init s3c_cpufreq_initcall(void)
 		if (cpu_cur.board->auto_io) {
 			ret = s3c_cpufreq_auto_io();
 			if (ret) {
-				printk(KERN_ERR "%s: failed to get io timing\n",
+				pr_err("%s: failed to get io timing\n",
 				       __func__);
 				goto out;
 			}
 		}
 
 		if (cpu_cur.board->need_io && !cpu_cur.info->set_iotiming) {
-			printk(KERN_ERR "%s: no IO support registered\n",
-			       __func__);
+			pr_err("%s: no IO support registered\n", __func__);
 			ret = -EINVAL;
 			goto out;
 		}
@@ -666,9 +667,9 @@ int s3c_plltab_register(struct cpufreq_frequency_table *plls,
 		vals += plls_no;
 		vals->frequency = CPUFREQ_TABLE_END;
 
-		printk(KERN_INFO "cpufreq: %d PLL entries\n", plls_no);
+		pr_info("%d PLL entries\n", plls_no);
 	} else
-		printk(KERN_ERR "cpufreq: no memory for PLL tables\n");
+		pr_err("no memory for PLL tables\n");
 
 	return vals ? 0 : -ENOMEM;
 }
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index a145b31..06d8591 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -9,6 +9,8 @@
  * published by the Free Software Foundation.
 */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -205,7 +207,7 @@ static void s5pv210_set_refresh(enum s5pv210_dmc_port ch, unsigned long freq)
 	} else if (ch == DMC1) {
 		reg = (dmc_base[1] + 0x30);
 	} else {
-		printk(KERN_ERR "Cannot find DMC port\n");
+		pr_err("Cannot find DMC port\n");
 		return;
 	}
 
@@ -534,7 +536,7 @@ static int s5pv210_cpu_init(struct cpufreq_policy *policy)
 	mem_type = check_mem_type(dmc_base[0]);
 
 	if ((mem_type != LPDDR) && (mem_type != LPDDR2)) {
-		printk(KERN_ERR "CPUFreq doesn't support this memory type\n");
+		pr_err("CPUFreq doesn't support this memory type\n");
 		ret = -EINVAL;
 		goto out_dmc1;
 	}
@@ -635,13 +637,13 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev)
 
 	arm_regulator = regulator_get(NULL, "vddarm");
 	if (IS_ERR(arm_regulator)) {
-		pr_err("failed to get regulator vddarm");
+		pr_err("failed to get regulator vddarm\n");
 		return PTR_ERR(arm_regulator);
 	}
 
 	int_regulator = regulator_get(NULL, "vddint");
 	if (IS_ERR(int_regulator)) {
-		pr_err("failed to get regulator vddint");
+		pr_err("failed to get regulator vddint\n");
 		regulator_put(arm_regulator);
 		return PTR_ERR(int_regulator);
 	}
diff --git a/drivers/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c
index ac84e48..4225501 100644
--- a/drivers/cpufreq/sc520_freq.c
+++ b/drivers/cpufreq/sc520_freq.c
@@ -13,6 +13,8 @@
  *	2005-03-30: - initial revision
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -30,8 +32,6 @@
 
 static __u8 __iomem *cpuctl;
 
-#define PFX "sc520_freq: "
-
 static struct cpufreq_frequency_table sc520_freq_table[] = {
 	{0, 0x01,	100000},
 	{0, 0x02,	133000},
@@ -44,8 +44,8 @@ static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu)
 
 	switch (clockspeed_reg & 0x03) {
 	default:
-		printk(KERN_ERR PFX "error: cpuctl register has unexpected "
-				"value %02x\n", clockspeed_reg);
+		pr_err("error: cpuctl register has unexpected value %02x\n",
+		       clockspeed_reg);
 	case 0x01:
 		return 100000;
 	case 0x02:
@@ -112,7 +112,7 @@ static int __init sc520_freq_init(void)
 
 	cpuctl = ioremap((unsigned long)(MMCR_BASE + OFFS_CPUCTL), 1);
 	if (!cpuctl) {
-		printk(KERN_ERR "sc520_freq: error: failed to remap memory\n");
+		pr_err("sc520_freq: error: failed to remap memory\n");
 		return -ENOMEM;
 	}
 
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index de5e89b..e8a7bf5 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -18,6 +18,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -38,10 +39,20 @@ static struct scpi_dvfs_info *scpi_get_dvfs_info(struct device *cpu_dev)
 	return scpi_ops->dvfs_get_info(domain);
 }
 
-static int scpi_opp_table_ops(struct device *cpu_dev, bool remove)
+static int scpi_get_transition_latency(struct device *cpu_dev)
 {
-	int idx, ret = 0;
+	struct scpi_dvfs_info *info = scpi_get_dvfs_info(cpu_dev);
+
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+	return info->latency;
+}
+
+static int scpi_init_opp_table(const struct cpumask *cpumask)
+{
+	int idx, ret;
 	struct scpi_opp *opp;
+	struct device *cpu_dev = get_cpu_device(cpumask_first(cpumask));
 	struct scpi_dvfs_info *info = scpi_get_dvfs_info(cpu_dev);
 
 	if (IS_ERR(info))
@@ -51,11 +62,7 @@ static int scpi_opp_table_ops(struct device *cpu_dev, bool remove)
 		return -EIO;
 
 	for (opp = info->opps, idx = 0; idx < info->count; idx++, opp++) {
-		if (remove)
-			dev_pm_opp_remove(cpu_dev, opp->freq);
-		else
-			ret = dev_pm_opp_add(cpu_dev, opp->freq,
-					     opp->m_volt * 1000);
+		ret = dev_pm_opp_add(cpu_dev, opp->freq, opp->m_volt * 1000);
 		if (ret) {
 			dev_warn(cpu_dev, "failed to add opp %uHz %umV\n",
 				 opp->freq, opp->m_volt);
@@ -64,33 +71,19 @@ static int scpi_opp_table_ops(struct device *cpu_dev, bool remove)
 			return ret;
 		}
 	}
-	return ret;
-}
 
-static int scpi_get_transition_latency(struct device *cpu_dev)
-{
-	struct scpi_dvfs_info *info = scpi_get_dvfs_info(cpu_dev);
-
-	if (IS_ERR(info))
-		return PTR_ERR(info);
-	return info->latency;
-}
-
-static int scpi_init_opp_table(struct device *cpu_dev)
-{
-	return scpi_opp_table_ops(cpu_dev, false);
-}
-
-static void scpi_free_opp_table(struct device *cpu_dev)
-{
-	scpi_opp_table_ops(cpu_dev, true);
+	ret = dev_pm_opp_set_sharing_cpus(cpu_dev, cpumask);
+	if (ret)
+		dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
+			__func__, ret);
+	return ret;
 }
 
 static struct cpufreq_arm_bL_ops scpi_cpufreq_ops = {
 	.name	= "scpi",
 	.get_transition_latency = scpi_get_transition_latency,
 	.init_opp_table = scpi_init_opp_table,
-	.free_opp_table = scpi_free_opp_table,
+	.free_opp_table = dev_pm_opp_cpumask_remove_table,
 };
 
 static int scpi_cpufreq_probe(struct platform_device *pdev)
diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c
index 7d4a315..41bc539 100644
--- a/drivers/cpufreq/speedstep-centrino.c
+++ b/drivers/cpufreq/speedstep-centrino.c
@@ -13,6 +13,8 @@
  * Copyright (C) 2003 Jeremy Fitzhardinge <jeremy@goop.org>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -27,7 +29,6 @@
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
 
-#define PFX		"speedstep-centrino: "
 #define MAINTAINER	"linux-pm@vger.kernel.org"
 
 #define INTEL_MSR_RANGE	(0xffff)
@@ -386,8 +387,7 @@ static int centrino_cpu_init(struct cpufreq_policy *policy)
 		/* check to see if it stuck */
 		rdmsr(MSR_IA32_MISC_ENABLE, l, h);
 		if (!(l & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
-			printk(KERN_INFO PFX
-				"couldn't enable Enhanced SpeedStep\n");
+			pr_info("couldn't enable Enhanced SpeedStep\n");
 			return -ENODEV;
 		}
 	}
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index 37555c6..b86953a 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -18,6 +18,8 @@
  *                        SPEEDSTEP - DEFINITIONS                    *
  *********************************************************************/
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -68,13 +70,13 @@ static int speedstep_find_register(void)
 	/* get PMBASE */
 	pci_read_config_dword(speedstep_chipset_dev, 0x40, &pmbase);
 	if (!(pmbase & 0x01)) {
-		printk(KERN_ERR "speedstep-ich: could not find speedstep register\n");
+		pr_err("could not find speedstep register\n");
 		return -ENODEV;
 	}
 
 	pmbase &= 0xFFFFFFFE;
 	if (!pmbase) {
-		printk(KERN_ERR "speedstep-ich: could not find speedstep register\n");
+		pr_err("could not find speedstep register\n");
 		return -ENODEV;
 	}
 
@@ -136,7 +138,7 @@ static void speedstep_set_state(unsigned int state)
 		pr_debug("change to %u MHz succeeded\n",
 			speedstep_get_frequency(speedstep_processor) / 1000);
 	else
-		printk(KERN_ERR "cpufreq: change failed - I/O error\n");
+		pr_err("change failed - I/O error\n");
 
 	return;
 }
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index 15d3214..1b80621 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -8,6 +8,8 @@
  *  BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -153,7 +155,7 @@ static unsigned int pentium_core_get_frequency(void)
 		fsb = 333333;
 		break;
 	default:
-		printk(KERN_ERR "PCORE - MSR_FSB_FREQ undefined value");
+		pr_err("PCORE - MSR_FSB_FREQ undefined value\n");
 	}
 
 	rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp);
@@ -453,11 +455,8 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 		 */
 		if (*transition_latency > 10000000 ||
 		    *transition_latency < 50000) {
-			printk(KERN_WARNING PFX "frequency transition "
-					"measured seems out of range (%u "
-					"nSec), falling back to a safe one of"
-					"%u nSec.\n",
-					*transition_latency, 500000);
+			pr_warn("frequency transition measured seems out of range (%u nSec), falling back to a safe one of %u nSec\n",
+				*transition_latency, 500000);
 			*transition_latency = 500000;
 		}
 	}
diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c
index 819229e..770a9ae 100644
--- a/drivers/cpufreq/speedstep-smi.c
+++ b/drivers/cpufreq/speedstep-smi.c
@@ -12,6 +12,8 @@
  *                        SPEEDSTEP - DEFINITIONS                    *
  *********************************************************************/
 
+#define pr_fmt(fmt) "cpufreq: " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -204,9 +206,8 @@ static void speedstep_set_state(unsigned int state)
 			(speedstep_freqs[new_state].frequency / 1000),
 			retry, result);
 	else
-		printk(KERN_ERR "cpufreq: change to state %u "
-			"failed with new_state %u and result %u\n",
-			state, new_state, result);
+		pr_err("change to state %u failed with new_state %u and result %u\n",
+		       state, new_state, result);
 
 	return;
 }
diff --git a/drivers/cpufreq/tegra124-cpufreq.c b/drivers/cpufreq/tegra124-cpufreq.c
index 20bcceb..4353025 100644
--- a/drivers/cpufreq/tegra124-cpufreq.c
+++ b/drivers/cpufreq/tegra124-cpufreq.c
@@ -14,7 +14,6 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/clk.h>
-#include <linux/cpufreq-dt.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -69,10 +68,6 @@ static void tegra124_cpu_switch_to_pllx(struct tegra124_cpufreq_priv *priv)
 	clk_set_parent(priv->cpu_clk, priv->pllx_clk);
 }
 
-static struct cpufreq_dt_platform_data cpufreq_dt_pd = {
-	.independent_clocks = false,
-};
-
 static int tegra124_cpufreq_probe(struct platform_device *pdev)
 {
 	struct tegra124_cpufreq_priv *priv;
@@ -129,8 +124,6 @@ static int tegra124_cpufreq_probe(struct platform_device *pdev)
 
 	cpufreq_dt_devinfo.name = "cpufreq-dt";
 	cpufreq_dt_devinfo.parent = &pdev->dev;
-	cpufreq_dt_devinfo.data = &cpufreq_dt_pd;
-	cpufreq_dt_devinfo.size_data = sizeof(cpufreq_dt_pd);
 
 	priv->cpufreq_dt_pdev =
 		platform_device_register_full(&cpufreq_dt_devinfo);
diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c
index 433e93f..87e5bdc 100644
--- a/drivers/cpufreq/vexpress-spc-cpufreq.c
+++ b/drivers/cpufreq/vexpress-spc-cpufreq.c
@@ -18,6 +18,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -26,8 +27,9 @@
 
 #include "arm_big_little.h"
 
-static int ve_spc_init_opp_table(struct device *cpu_dev)
+static int ve_spc_init_opp_table(const struct cpumask *cpumask)
 {
+	struct device *cpu_dev = get_cpu_device(cpumask_first(cpumask));
 	/*
 	 * platform specific SPC code must initialise the opp table
 	 * so just check if the OPP count is non-zero
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index f996efc..2b8e6ce 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -173,7 +173,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 
 	struct cpuidle_state *target_state = &drv->states[index];
 	bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
-	ktime_t time_start, time_end;
+	u64 time_start, time_end;
 	s64 diff;
 
 	/*
@@ -195,13 +195,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	sched_idle_set_state(target_state);
 
 	trace_cpu_idle_rcuidle(index, dev->cpu);
-	time_start = ktime_get();
+	time_start = local_clock();
 
 	stop_critical_timings();
 	entered_state = target_state->enter(dev, drv, index);
 	start_critical_timings();
 
-	time_end = ktime_get();
+	time_end = local_clock();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 
 	/* The cpu is no longer idle or about to enter idle. */
@@ -217,7 +217,11 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	if (!cpuidle_state_is_coupled(drv, entered_state))
 		local_irq_enable();
 
-	diff = ktime_to_us(ktime_sub(time_end, time_start));
+	/*
+	 * local_clock() returns the time in nanosecond, let's shift
+	 * by 10 (divide by 1024) to have microsecond based time.
+	 */
+	diff = (time_end - time_start) >> 10;
 	if (diff > INT_MAX)
 		diff = INT_MAX;
 
@@ -433,6 +437,8 @@ static void __cpuidle_unregister_device(struct cpuidle_device *dev)
 	list_del(&dev->device_list);
 	per_cpu(cpuidle_devices, dev->cpu) = NULL;
 	module_put(drv->owner);
+
+	dev->registered = 0;
 }
 
 static void __cpuidle_device_init(struct cpuidle_device *dev)
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index 4de78c5..78dac0e 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -64,30 +64,32 @@ config DEVFREQ_GOV_USERSPACE
 	  Otherwise, the governor does not change the frequency
 	  given at the initialization.
 
+config DEVFREQ_GOV_PASSIVE
+	tristate "Passive"
+	help
+	  Sets the frequency based on the frequency of its parent devfreq
+	  device. This governor does not change the frequency by itself
+	  through sysfs entries. The passive governor recommends that
+	  devfreq device uses the OPP table to get the frequency/voltage.
+
 comment "DEVFREQ Drivers"
 
-config ARM_EXYNOS4_BUS_DEVFREQ
-	bool "ARM Exynos4210/4212/4412 Memory Bus DEVFREQ Driver"
-	depends on (CPU_EXYNOS4210 || SOC_EXYNOS4212 || SOC_EXYNOS4412) && !ARCH_MULTIPLATFORM
+config ARM_EXYNOS_BUS_DEVFREQ
+	bool "ARM EXYNOS Generic Memory Bus DEVFREQ Driver"
+	depends on ARCH_EXYNOS
 	select DEVFREQ_GOV_SIMPLE_ONDEMAND
+	select DEVFREQ_GOV_PASSIVE
+	select DEVFREQ_EVENT_EXYNOS_PPMU
+	select PM_DEVFREQ_EVENT
 	select PM_OPP
 	help
-	  This adds the DEVFREQ driver for Exynos4210 memory bus (vdd_int)
-	  and Exynos4212/4412 memory interface and bus (vdd_mif + vdd_int).
-	  It reads PPMU counters of memory controllers and adjusts
-	  the operating frequencies and voltages with OPP support.
+	  This adds the common DEVFREQ driver for Exynos Memory bus. Exynos
+	  Memory bus has one more group of memory bus (e.g, MIF and INT block).
+	  Each memory bus group could contain many memoby bus block. It reads
+	  PPMU counters of memory controllers by using DEVFREQ-event device
+	  and adjusts the operating frequencies and voltages with OPP support.
 	  This does not yet operate with optimal voltages.
 
-config ARM_EXYNOS5_BUS_DEVFREQ
-	tristate "ARM Exynos5250 Bus DEVFREQ Driver"
-	depends on SOC_EXYNOS5250
-	select DEVFREQ_GOV_SIMPLE_ONDEMAND
-	select PM_OPP
-	help
-	  This adds the DEVFREQ driver for Exynos5250 bus interface (vdd_int).
-	  It reads PPMU counters of memory controllers and adjusts the
-	  operating frequencies and voltages with OPP support.
-
 config ARM_TEGRA_DEVFREQ
        tristate "Tegra DEVFREQ Driver"
        depends on ARCH_TEGRA_124_SOC
diff --git a/drivers/devfreq/Makefile b/drivers/devfreq/Makefile
index 5134f9e..09f11d9 100644
--- a/drivers/devfreq/Makefile
+++ b/drivers/devfreq/Makefile
@@ -4,10 +4,10 @@ obj-$(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)	+= governor_simpleondemand.o
 obj-$(CONFIG_DEVFREQ_GOV_PERFORMANCE)	+= governor_performance.o
 obj-$(CONFIG_DEVFREQ_GOV_POWERSAVE)	+= governor_powersave.o
 obj-$(CONFIG_DEVFREQ_GOV_USERSPACE)	+= governor_userspace.o
+obj-$(CONFIG_DEVFREQ_GOV_PASSIVE)	+= governor_passive.o
 
 # DEVFREQ Drivers
-obj-$(CONFIG_ARM_EXYNOS4_BUS_DEVFREQ)	+= exynos/
-obj-$(CONFIG_ARM_EXYNOS5_BUS_DEVFREQ)	+= exynos/
+obj-$(CONFIG_ARM_EXYNOS_BUS_DEVFREQ)	+= exynos-bus.o
 obj-$(CONFIG_ARM_TEGRA_DEVFREQ)		+= tegra-devfreq.o
 
 # DEVFREQ Event Drivers
diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c
index 38bf144..39b048e 100644
--- a/drivers/devfreq/devfreq-event.c
+++ b/drivers/devfreq/devfreq-event.c
@@ -235,6 +235,11 @@ struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(struct device *dev,
 
 	mutex_lock(&devfreq_event_list_lock);
 	list_for_each_entry(edev, &devfreq_event_list, node) {
+		if (edev->dev.parent && edev->dev.parent->of_node == node)
+			goto out;
+	}
+
+	list_for_each_entry(edev, &devfreq_event_list, node) {
 		if (!strcmp(edev->desc->name, node->name))
 			goto out;
 	}
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 984c5e9..1d6c803 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -25,6 +25,7 @@
 #include <linux/list.h>
 #include <linux/printk.h>
 #include <linux/hrtimer.h>
+#include <linux/of.h>
 #include "governor.h"
 
 static struct class *devfreq_class;
@@ -188,6 +189,29 @@ static struct devfreq_governor *find_devfreq_governor(const char *name)
 	return ERR_PTR(-ENODEV);
 }
 
+static int devfreq_notify_transition(struct devfreq *devfreq,
+		struct devfreq_freqs *freqs, unsigned int state)
+{
+	if (!devfreq)
+		return -EINVAL;
+
+	switch (state) {
+	case DEVFREQ_PRECHANGE:
+		srcu_notifier_call_chain(&devfreq->transition_notifier_list,
+				DEVFREQ_PRECHANGE, freqs);
+		break;
+
+	case DEVFREQ_POSTCHANGE:
+		srcu_notifier_call_chain(&devfreq->transition_notifier_list,
+				DEVFREQ_POSTCHANGE, freqs);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* Load monitoring helper functions for governors use */
 
 /**
@@ -199,7 +223,8 @@ static struct devfreq_governor *find_devfreq_governor(const char *name)
  */
 int update_devfreq(struct devfreq *devfreq)
 {
-	unsigned long freq;
+	struct devfreq_freqs freqs;
+	unsigned long freq, cur_freq;
 	int err = 0;
 	u32 flags = 0;
 
@@ -233,10 +258,22 @@ int update_devfreq(struct devfreq *devfreq)
 		flags |= DEVFREQ_FLAG_LEAST_UPPER_BOUND; /* Use LUB */
 	}
 
+	if (devfreq->profile->get_cur_freq)
+		devfreq->profile->get_cur_freq(devfreq->dev.parent, &cur_freq);
+	else
+		cur_freq = devfreq->previous_freq;
+
+	freqs.old = cur_freq;
+	freqs.new = freq;
+	devfreq_notify_transition(devfreq, &freqs, DEVFREQ_PRECHANGE);
+
 	err = devfreq->profile->target(devfreq->dev.parent, &freq, flags);
 	if (err)
 		return err;
 
+	freqs.new = freq;
+	devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE);
+
 	if (devfreq->profile->freq_table)
 		if (devfreq_update_status(devfreq, freq))
 			dev_err(&devfreq->dev,
@@ -541,6 +578,8 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		goto err_out;
 	}
 
+	srcu_init_notifier_head(&devfreq->transition_notifier_list);
+
 	mutex_unlock(&devfreq->lock);
 
 	mutex_lock(&devfreq_list_lock);
@@ -639,6 +678,49 @@ struct devfreq *devm_devfreq_add_device(struct device *dev,
 }
 EXPORT_SYMBOL(devm_devfreq_add_device);
 
+#ifdef CONFIG_OF
+/*
+ * devfreq_get_devfreq_by_phandle - Get the devfreq device from devicetree
+ * @dev - instance to the given device
+ * @index - index into list of devfreq
+ *
+ * return the instance of devfreq device
+ */
+struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
+{
+	struct device_node *node;
+	struct devfreq *devfreq;
+
+	if (!dev)
+		return ERR_PTR(-EINVAL);
+
+	if (!dev->of_node)
+		return ERR_PTR(-EINVAL);
+
+	node = of_parse_phandle(dev->of_node, "devfreq", index);
+	if (!node)
+		return ERR_PTR(-ENODEV);
+
+	mutex_lock(&devfreq_list_lock);
+	list_for_each_entry(devfreq, &devfreq_list, node) {
+		if (devfreq->dev.parent
+			&& devfreq->dev.parent->of_node == node) {
+			mutex_unlock(&devfreq_list_lock);
+			return devfreq;
+		}
+	}
+	mutex_unlock(&devfreq_list_lock);
+
+	return ERR_PTR(-EPROBE_DEFER);
+}
+#else
+struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
+{
+	return ERR_PTR(-ENODEV);
+}
+#endif /* CONFIG_OF */
+EXPORT_SYMBOL_GPL(devfreq_get_devfreq_by_phandle);
+
 /**
  * devm_devfreq_remove_device() - Resource-managed devfreq_remove_device()
  * @dev:	the device to add devfreq feature.
@@ -1266,6 +1348,129 @@ void devm_devfreq_unregister_opp_notifier(struct device *dev,
 }
 EXPORT_SYMBOL(devm_devfreq_unregister_opp_notifier);
 
+/**
+ * devfreq_register_notifier() - Register a driver with devfreq
+ * @devfreq:	The devfreq object.
+ * @nb:		The notifier block to register.
+ * @list:	DEVFREQ_TRANSITION_NOTIFIER.
+ */
+int devfreq_register_notifier(struct devfreq *devfreq,
+				struct notifier_block *nb,
+				unsigned int list)
+{
+	int ret = 0;
+
+	if (!devfreq)
+		return -EINVAL;
+
+	switch (list) {
+	case DEVFREQ_TRANSITION_NOTIFIER:
+		ret = srcu_notifier_chain_register(
+				&devfreq->transition_notifier_list, nb);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(devfreq_register_notifier);
+
+/*
+ * devfreq_unregister_notifier() - Unregister a driver with devfreq
+ * @devfreq:	The devfreq object.
+ * @nb:		The notifier block to be unregistered.
+ * @list:	DEVFREQ_TRANSITION_NOTIFIER.
+ */
+int devfreq_unregister_notifier(struct devfreq *devfreq,
+				struct notifier_block *nb,
+				unsigned int list)
+{
+	int ret = 0;
+
+	if (!devfreq)
+		return -EINVAL;
+
+	switch (list) {
+	case DEVFREQ_TRANSITION_NOTIFIER:
+		ret = srcu_notifier_chain_unregister(
+				&devfreq->transition_notifier_list, nb);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(devfreq_unregister_notifier);
+
+struct devfreq_notifier_devres {
+	struct devfreq *devfreq;
+	struct notifier_block *nb;
+	unsigned int list;
+};
+
+static void devm_devfreq_notifier_release(struct device *dev, void *res)
+{
+	struct devfreq_notifier_devres *this = res;
+
+	devfreq_unregister_notifier(this->devfreq, this->nb, this->list);
+}
+
+/**
+ * devm_devfreq_register_notifier()
+	- Resource-managed devfreq_register_notifier()
+ * @dev:	The devfreq user device. (parent of devfreq)
+ * @devfreq:	The devfreq object.
+ * @nb:		The notifier block to be unregistered.
+ * @list:	DEVFREQ_TRANSITION_NOTIFIER.
+ */
+int devm_devfreq_register_notifier(struct device *dev,
+				struct devfreq *devfreq,
+				struct notifier_block *nb,
+				unsigned int list)
+{
+	struct devfreq_notifier_devres *ptr;
+	int ret;
+
+	ptr = devres_alloc(devm_devfreq_notifier_release, sizeof(*ptr),
+				GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	ret = devfreq_register_notifier(devfreq, nb, list);
+	if (ret) {
+		devres_free(ptr);
+		return ret;
+	}
+
+	ptr->devfreq = devfreq;
+	ptr->nb = nb;
+	ptr->list = list;
+	devres_add(dev, ptr);
+
+	return 0;
+}
+EXPORT_SYMBOL(devm_devfreq_register_notifier);
+
+/**
+ * devm_devfreq_unregister_notifier()
+	- Resource-managed devfreq_unregister_notifier()
+ * @dev:	The devfreq user device. (parent of devfreq)
+ * @devfreq:	The devfreq object.
+ * @nb:		The notifier block to be unregistered.
+ * @list:	DEVFREQ_TRANSITION_NOTIFIER.
+ */
+void devm_devfreq_unregister_notifier(struct device *dev,
+				struct devfreq *devfreq,
+				struct notifier_block *nb,
+				unsigned int list)
+{
+	WARN_ON(devres_release(dev, devm_devfreq_notifier_release,
+			       devm_devfreq_dev_match, devfreq));
+}
+EXPORT_SYMBOL(devm_devfreq_unregister_notifier);
+
 MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
 MODULE_DESCRIPTION("devfreq class support");
 MODULE_LICENSE("GPL");
diff --git a/drivers/devfreq/event/Kconfig b/drivers/devfreq/event/Kconfig
index a11720a..1e8b4f4 100644
--- a/drivers/devfreq/event/Kconfig
+++ b/drivers/devfreq/event/Kconfig
@@ -13,6 +13,14 @@ menuconfig PM_DEVFREQ_EVENT
 
 if PM_DEVFREQ_EVENT
 
+config DEVFREQ_EVENT_EXYNOS_NOCP
+	bool "EXYNOS NoC (Network On Chip) Probe DEVFREQ event Driver"
+	depends on ARCH_EXYNOS
+	select PM_OPP
+	help
+	  This add the devfreq-event driver for Exynos SoC. It provides NoC
+	  (Network on Chip) Probe counters to measure the bandwidth of AXI bus.
+
 config DEVFREQ_EVENT_EXYNOS_PPMU
 	bool "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver"
 	depends on ARCH_EXYNOS
diff --git a/drivers/devfreq/event/Makefile b/drivers/devfreq/event/Makefile
index be146ea..3d6afd3 100644
--- a/drivers/devfreq/event/Makefile
+++ b/drivers/devfreq/event/Makefile
@@ -1,2 +1,4 @@
 # Exynos DEVFREQ Event Drivers
+
+obj-$(CONFIG_DEVFREQ_EVENT_EXYNOS_NOCP) += exynos-nocp.o
 obj-$(CONFIG_DEVFREQ_EVENT_EXYNOS_PPMU) += exynos-ppmu.o
diff --git a/drivers/devfreq/event/exynos-nocp.c b/drivers/devfreq/event/exynos-nocp.c
new file mode 100644
index 0000000..6b6a5f3
--- /dev/null
+++ b/drivers/devfreq/event/exynos-nocp.c
@@ -0,0 +1,304 @@
+/*
+ * exynos-nocp.c - EXYNOS NoC (Network On Chip) Probe support
+ *
+ * Copyright (c) 2016 Samsung Electronics Co., Ltd.
+ * Author : Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * 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.
+ */
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/devfreq-event.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include "exynos-nocp.h"
+
+struct exynos_nocp {
+	struct devfreq_event_dev *edev;
+	struct devfreq_event_desc desc;
+
+	struct device *dev;
+
+	struct regmap *regmap;
+	struct clk *clk;
+};
+
+/*
+ * The devfreq-event ops structure for nocp probe.
+ */
+static int exynos_nocp_set_event(struct devfreq_event_dev *edev)
+{
+	struct exynos_nocp *nocp = devfreq_event_get_drvdata(edev);
+	int ret;
+
+	/* Disable NoC probe */
+	ret = regmap_update_bits(nocp->regmap, NOCP_MAIN_CTL,
+				NOCP_MAIN_CTL_STATEN_MASK, 0);
+	if (ret < 0) {
+		dev_err(nocp->dev, "failed to disable the NoC probe device\n");
+		return ret;
+	}
+
+	/* Set a statistics dump period to 0 */
+	ret = regmap_write(nocp->regmap, NOCP_STAT_PERIOD, 0x0);
+	if (ret < 0)
+		goto out;
+
+	/* Set the IntEvent fields of *_SRC */
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_0_SRC,
+				NOCP_CNT_SRC_INTEVENT_MASK,
+				NOCP_CNT_SRC_INTEVENT_BYTE_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_1_SRC,
+				NOCP_CNT_SRC_INTEVENT_MASK,
+				NOCP_CNT_SRC_INTEVENT_CHAIN_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_2_SRC,
+				NOCP_CNT_SRC_INTEVENT_MASK,
+				NOCP_CNT_SRC_INTEVENT_CYCLE_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_3_SRC,
+				NOCP_CNT_SRC_INTEVENT_MASK,
+				NOCP_CNT_SRC_INTEVENT_CHAIN_MASK);
+	if (ret < 0)
+		goto out;
+
+
+	/* Set an alarm with a max/min value of 0 to generate StatALARM */
+	ret = regmap_write(nocp->regmap, NOCP_STAT_ALARM_MIN, 0x0);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_write(nocp->regmap, NOCP_STAT_ALARM_MAX, 0x0);
+	if (ret < 0)
+		goto out;
+
+	/* Set AlarmMode */
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_0_ALARM_MODE,
+				NOCP_CNT_ALARM_MODE_MASK,
+				NOCP_CNT_ALARM_MODE_MIN_MAX_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_1_ALARM_MODE,
+				NOCP_CNT_ALARM_MODE_MASK,
+				NOCP_CNT_ALARM_MODE_MIN_MAX_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_2_ALARM_MODE,
+				NOCP_CNT_ALARM_MODE_MASK,
+				NOCP_CNT_ALARM_MODE_MIN_MAX_MASK);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_update_bits(nocp->regmap, NOCP_COUNTERS_3_ALARM_MODE,
+				NOCP_CNT_ALARM_MODE_MASK,
+				NOCP_CNT_ALARM_MODE_MIN_MAX_MASK);
+	if (ret < 0)
+		goto out;
+
+	/* Enable the measurements by setting AlarmEn and StatEn */
+	ret = regmap_update_bits(nocp->regmap, NOCP_MAIN_CTL,
+			NOCP_MAIN_CTL_STATEN_MASK | NOCP_MAIN_CTL_ALARMEN_MASK,
+			NOCP_MAIN_CTL_STATEN_MASK | NOCP_MAIN_CTL_ALARMEN_MASK);
+	if (ret < 0)
+		goto out;
+
+	/* Set GlobalEN */
+	ret = regmap_update_bits(nocp->regmap, NOCP_CFG_CTL,
+				NOCP_CFG_CTL_GLOBALEN_MASK,
+				NOCP_CFG_CTL_GLOBALEN_MASK);
+	if (ret < 0)
+		goto out;
+
+	/* Enable NoC probe */
+	ret = regmap_update_bits(nocp->regmap, NOCP_MAIN_CTL,
+				NOCP_MAIN_CTL_STATEN_MASK,
+				NOCP_MAIN_CTL_STATEN_MASK);
+	if (ret < 0)
+		goto out;
+
+	return 0;
+
+out:
+	/* Reset NoC probe */
+	if (regmap_update_bits(nocp->regmap, NOCP_MAIN_CTL,
+				NOCP_MAIN_CTL_STATEN_MASK, 0)) {
+		dev_err(nocp->dev, "Failed to reset NoC probe device\n");
+	}
+
+	return ret;
+}
+
+static int exynos_nocp_get_event(struct devfreq_event_dev *edev,
+				struct devfreq_event_data *edata)
+{
+	struct exynos_nocp *nocp = devfreq_event_get_drvdata(edev);
+	unsigned int counter[4];
+	int ret;
+
+	/* Read cycle count */
+	ret = regmap_read(nocp->regmap, NOCP_COUNTERS_0_VAL, &counter[0]);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_read(nocp->regmap, NOCP_COUNTERS_1_VAL, &counter[1]);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_read(nocp->regmap, NOCP_COUNTERS_2_VAL, &counter[2]);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_read(nocp->regmap, NOCP_COUNTERS_3_VAL, &counter[3]);
+	if (ret < 0)
+		goto out;
+
+	edata->load_count = ((counter[1] << 16) | counter[0]);
+	edata->total_count = ((counter[3] << 16) | counter[2]);
+
+	dev_dbg(&edev->dev, "%s (event: %ld/%ld)\n", edev->desc->name,
+					edata->load_count, edata->total_count);
+
+	return 0;
+
+out:
+	edata->load_count = 0;
+	edata->total_count = 0;
+
+	dev_err(nocp->dev, "Failed to read the counter of NoC probe device\n");
+
+	return ret;
+}
+
+static const struct devfreq_event_ops exynos_nocp_ops = {
+	.set_event = exynos_nocp_set_event,
+	.get_event = exynos_nocp_get_event,
+};
+
+static const struct of_device_id exynos_nocp_id_match[] = {
+	{ .compatible = "samsung,exynos5420-nocp", },
+	{ /* sentinel */ },
+};
+
+static struct regmap_config exynos_nocp_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = NOCP_COUNTERS_3_VAL,
+};
+
+static int exynos_nocp_parse_dt(struct platform_device *pdev,
+				struct exynos_nocp *nocp)
+{
+	struct device *dev = nocp->dev;
+	struct device_node *np = dev->of_node;
+	struct resource *res;
+	void __iomem *base;
+
+	if (!np) {
+		dev_err(dev, "failed to find devicetree node\n");
+		return -EINVAL;
+	}
+
+	nocp->clk = devm_clk_get(dev, "nocp");
+	if (IS_ERR(nocp->clk))
+		nocp->clk = NULL;
+
+	/* Maps the memory mapped IO to control nocp register */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (IS_ERR(res))
+		return PTR_ERR(res);
+
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	exynos_nocp_regmap_config.max_register = resource_size(res) - 4;
+
+	nocp->regmap = devm_regmap_init_mmio(dev, base,
+					&exynos_nocp_regmap_config);
+	if (IS_ERR(nocp->regmap)) {
+		dev_err(dev, "failed to initialize regmap\n");
+		return PTR_ERR(nocp->regmap);
+	}
+
+	return 0;
+}
+
+static int exynos_nocp_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct exynos_nocp *nocp;
+	int ret;
+
+	nocp = devm_kzalloc(&pdev->dev, sizeof(*nocp), GFP_KERNEL);
+	if (!nocp)
+		return -ENOMEM;
+
+	nocp->dev = &pdev->dev;
+
+	/* Parse dt data to get resource */
+	ret = exynos_nocp_parse_dt(pdev, nocp);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"failed to parse devicetree for resource\n");
+		return ret;
+	}
+
+	/* Add devfreq-event device to measure the bandwidth of NoC */
+	nocp->desc.ops = &exynos_nocp_ops;
+	nocp->desc.driver_data = nocp;
+	nocp->desc.name = np->full_name;
+	nocp->edev = devm_devfreq_event_add_edev(&pdev->dev, &nocp->desc);
+	if (IS_ERR(nocp->edev)) {
+		dev_err(&pdev->dev,
+			"failed to add devfreq-event device\n");
+		return PTR_ERR(nocp->edev);
+	}
+	platform_set_drvdata(pdev, nocp);
+
+	clk_prepare_enable(nocp->clk);
+
+	pr_info("exynos-nocp: new NoC Probe device registered: %s\n",
+			dev_name(dev));
+
+	return 0;
+}
+
+static int exynos_nocp_remove(struct platform_device *pdev)
+{
+	struct exynos_nocp *nocp = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(nocp->clk);
+
+	return 0;
+}
+
+static struct platform_driver exynos_nocp_driver = {
+	.probe	= exynos_nocp_probe,
+	.remove	= exynos_nocp_remove,
+	.driver = {
+		.name	= "exynos-nocp",
+		.of_match_table = exynos_nocp_id_match,
+	},
+};
+module_platform_driver(exynos_nocp_driver);
+
+MODULE_DESCRIPTION("Exynos NoC (Network on Chip) Probe driver");
+MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/devfreq/event/exynos-nocp.h b/drivers/devfreq/event/exynos-nocp.h
new file mode 100644
index 0000000..28564db
--- /dev/null
+++ b/drivers/devfreq/event/exynos-nocp.h
@@ -0,0 +1,78 @@
+/*
+ * exynos-nocp.h - EXYNOS NoC (Network on Chip) Probe header file
+ *
+ * Copyright (c) 2016 Samsung Electronics Co., Ltd.
+ * Author : Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * 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 __EXYNOS_NOCP_H__
+#define __EXYNOS_NOCP_H__
+
+enum nocp_reg {
+	NOCP_ID_REVISION_ID		= 0x04,
+	NOCP_MAIN_CTL			= 0x08,
+	NOCP_CFG_CTL			= 0x0C,
+
+	NOCP_STAT_PERIOD		= 0x24,
+	NOCP_STAT_GO			= 0x28,
+	NOCP_STAT_ALARM_MIN		= 0x2C,
+	NOCP_STAT_ALARM_MAX		= 0x30,
+	NOCP_STAT_ALARM_STATUS		= 0x34,
+	NOCP_STAT_ALARM_CLR		= 0x38,
+
+	NOCP_COUNTERS_0_SRC		= 0x138,
+	NOCP_COUNTERS_0_ALARM_MODE	= 0x13C,
+	NOCP_COUNTERS_0_VAL		= 0x140,
+
+	NOCP_COUNTERS_1_SRC		= 0x14C,
+	NOCP_COUNTERS_1_ALARM_MODE	= 0x150,
+	NOCP_COUNTERS_1_VAL		= 0x154,
+
+	NOCP_COUNTERS_2_SRC		= 0x160,
+	NOCP_COUNTERS_2_ALARM_MODE	= 0x164,
+	NOCP_COUNTERS_2_VAL		= 0x168,
+
+	NOCP_COUNTERS_3_SRC		= 0x174,
+	NOCP_COUNTERS_3_ALARM_MODE	= 0x178,
+	NOCP_COUNTERS_3_VAL		= 0x17C,
+};
+
+/* NOCP_MAIN_CTL register */
+#define NOCP_MAIN_CTL_ERREN_MASK		BIT(0)
+#define NOCP_MAIN_CTL_TRACEEN_MASK		BIT(1)
+#define NOCP_MAIN_CTL_PAYLOADEN_MASK		BIT(2)
+#define NOCP_MAIN_CTL_STATEN_MASK		BIT(3)
+#define NOCP_MAIN_CTL_ALARMEN_MASK		BIT(4)
+#define NOCP_MAIN_CTL_STATCONDDUMP_MASK	BIT(5)
+#define NOCP_MAIN_CTL_INTRUSIVEMODE_MASK	BIT(6)
+
+/* NOCP_CFG_CTL register */
+#define NOCP_CFG_CTL_GLOBALEN_MASK		BIT(0)
+#define NOCP_CFG_CTL_ACTIVE_MASK		BIT(1)
+
+/* NOCP_COUNTERS_x_SRC register */
+#define NOCP_CNT_SRC_INTEVENT_SHIFT		0
+#define NOCP_CNT_SRC_INTEVENT_MASK		(0x1F << NOCP_CNT_SRC_INTEVENT_SHIFT)
+#define NOCP_CNT_SRC_INTEVENT_OFF_MASK		(0x0 << NOCP_CNT_SRC_INTEVENT_SHIFT)
+#define NOCP_CNT_SRC_INTEVENT_CYCLE_MASK	(0x1 << NOCP_CNT_SRC_INTEVENT_SHIFT)
+#define NOCP_CNT_SRC_INTEVENT_IDLE_MASK		(0x2 << NOCP_CNT_SRC_INTEVENT_SHIFT)
+#define NOCP_CNT_SRC_INTEVENT_XFER_MASK		(0x3 << NOCP_CNT_SRC_INTEVENT_SHIFT)
+#define NOCP_CNT_SRC_INTEVENT_BUSY_MASK		(0x4 << NOCP_CNT_SRC_INTEVENT_SHIFT)
+#define NOCP_CNT_SRC_INTEVENT_WAIT_MASK		(0x5 << NOCP_CNT_SRC_INTEVENT_SHIFT)
+#define NOCP_CNT_SRC_INTEVENT_PKT_MASK		(0x6 << NOCP_CNT_SRC_INTEVENT_SHIFT)
+#define NOCP_CNT_SRC_INTEVENT_BYTE_MASK		(0x8 << NOCP_CNT_SRC_INTEVENT_SHIFT)
+#define NOCP_CNT_SRC_INTEVENT_CHAIN_MASK	(0x10 << NOCP_CNT_SRC_INTEVENT_SHIFT)
+
+/* NOCP_COUNTERS_x_ALARM_MODE register */
+#define NOCP_CNT_ALARM_MODE_SHIFT		0
+#define NOCP_CNT_ALARM_MODE_MASK		(0x3 << NOCP_CNT_ALARM_MODE_SHIFT)
+#define NOCP_CNT_ALARM_MODE_OFF_MASK		(0x0 << NOCP_CNT_ALARM_MODE_SHIFT)
+#define NOCP_CNT_ALARM_MODE_MIN_MASK		(0x1 << NOCP_CNT_ALARM_MODE_SHIFT)
+#define NOCP_CNT_ALARM_MODE_MAX_MASK		(0x2 << NOCP_CNT_ALARM_MODE_SHIFT)
+#define NOCP_CNT_ALARM_MODE_MIN_MAX_MASK	(0x3 << NOCP_CNT_ALARM_MODE_SHIFT)
+
+#endif /* __EXYNOS_NOCP_H__ */
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
new file mode 100644
index 0000000..2363d0a
--- /dev/null
+++ b/drivers/devfreq/exynos-bus.c
@@ -0,0 +1,570 @@
+/*
+ * Generic Exynos Bus frequency driver with DEVFREQ Framework
+ *
+ * Copyright (c) 2016 Samsung Electronics Co., Ltd.
+ * Author : Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * This driver support Exynos Bus frequency feature by using
+ * DEVFREQ framework and is based on drivers/devfreq/exynos/exynos4_bus.c.
+ *
+ * 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.
+ */
+
+#include <linux/clk.h>
+#include <linux/devfreq.h>
+#include <linux/devfreq-event.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/pm_opp.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+
+#define DEFAULT_SATURATION_RATIO	40
+#define DEFAULT_VOLTAGE_TOLERANCE	2
+
+struct exynos_bus {
+	struct device *dev;
+
+	struct devfreq *devfreq;
+	struct devfreq_event_dev **edev;
+	unsigned int edev_count;
+	struct mutex lock;
+
+	struct dev_pm_opp *curr_opp;
+
+	struct regulator *regulator;
+	struct clk *clk;
+	unsigned int voltage_tolerance;
+	unsigned int ratio;
+};
+
+/*
+ * Control the devfreq-event device to get the current state of bus
+ */
+#define exynos_bus_ops_edev(ops)				\
+static int exynos_bus_##ops(struct exynos_bus *bus)		\
+{								\
+	int i, ret;						\
+								\
+	for (i = 0; i < bus->edev_count; i++) {			\
+		if (!bus->edev[i])				\
+			continue;				\
+		ret = devfreq_event_##ops(bus->edev[i]);	\
+		if (ret < 0)					\
+			return ret;				\
+	}							\
+								\
+	return 0;						\
+}
+exynos_bus_ops_edev(enable_edev);
+exynos_bus_ops_edev(disable_edev);
+exynos_bus_ops_edev(set_event);
+
+static int exynos_bus_get_event(struct exynos_bus *bus,
+				struct devfreq_event_data *edata)
+{
+	struct devfreq_event_data event_data;
+	unsigned long load_count = 0, total_count = 0;
+	int i, ret = 0;
+
+	for (i = 0; i < bus->edev_count; i++) {
+		if (!bus->edev[i])
+			continue;
+
+		ret = devfreq_event_get_event(bus->edev[i], &event_data);
+		if (ret < 0)
+			return ret;
+
+		if (i == 0 || event_data.load_count > load_count) {
+			load_count = event_data.load_count;
+			total_count = event_data.total_count;
+		}
+	}
+
+	edata->load_count = load_count;
+	edata->total_count = total_count;
+
+	return ret;
+}
+
+/*
+ * Must necessary function for devfreq simple-ondemand governor
+ */
+static int exynos_bus_target(struct device *dev, unsigned long *freq, u32 flags)
+{
+	struct exynos_bus *bus = dev_get_drvdata(dev);
+	struct dev_pm_opp *new_opp;
+	unsigned long old_freq, new_freq, old_volt, new_volt, tol;
+	int ret = 0;
+
+	/* Get new opp-bus instance according to new bus clock */
+	rcu_read_lock();
+	new_opp = devfreq_recommended_opp(dev, freq, flags);
+	if (IS_ERR(new_opp)) {
+		dev_err(dev, "failed to get recommended opp instance\n");
+		rcu_read_unlock();
+		return PTR_ERR(new_opp);
+	}
+
+	new_freq = dev_pm_opp_get_freq(new_opp);
+	new_volt = dev_pm_opp_get_voltage(new_opp);
+	old_freq = dev_pm_opp_get_freq(bus->curr_opp);
+	old_volt = dev_pm_opp_get_voltage(bus->curr_opp);
+	rcu_read_unlock();
+
+	if (old_freq == new_freq)
+		return 0;
+	tol = new_volt * bus->voltage_tolerance / 100;
+
+	/* Change voltage and frequency according to new OPP level */
+	mutex_lock(&bus->lock);
+
+	if (old_freq < new_freq) {
+		ret = regulator_set_voltage_tol(bus->regulator, new_volt, tol);
+		if (ret < 0) {
+			dev_err(bus->dev, "failed to set voltage\n");
+			goto out;
+		}
+	}
+
+	ret = clk_set_rate(bus->clk, new_freq);
+	if (ret < 0) {
+		dev_err(dev, "failed to change clock of bus\n");
+		clk_set_rate(bus->clk, old_freq);
+		goto out;
+	}
+
+	if (old_freq > new_freq) {
+		ret = regulator_set_voltage_tol(bus->regulator, new_volt, tol);
+		if (ret < 0) {
+			dev_err(bus->dev, "failed to set voltage\n");
+			goto out;
+		}
+	}
+	bus->curr_opp = new_opp;
+
+	dev_dbg(dev, "Set the frequency of bus (%lukHz -> %lukHz)\n",
+			old_freq/1000, new_freq/1000);
+out:
+	mutex_unlock(&bus->lock);
+
+	return ret;
+}
+
+static int exynos_bus_get_dev_status(struct device *dev,
+				     struct devfreq_dev_status *stat)
+{
+	struct exynos_bus *bus = dev_get_drvdata(dev);
+	struct devfreq_event_data edata;
+	int ret;
+
+	rcu_read_lock();
+	stat->current_frequency = dev_pm_opp_get_freq(bus->curr_opp);
+	rcu_read_unlock();
+
+	ret = exynos_bus_get_event(bus, &edata);
+	if (ret < 0) {
+		stat->total_time = stat->busy_time = 0;
+		goto err;
+	}
+
+	stat->busy_time = (edata.load_count * 100) / bus->ratio;
+	stat->total_time = edata.total_count;
+
+	dev_dbg(dev, "Usage of devfreq-event : %lu/%lu\n", stat->busy_time,
+							stat->total_time);
+
+err:
+	ret = exynos_bus_set_event(bus);
+	if (ret < 0) {
+		dev_err(dev, "failed to set event to devfreq-event devices\n");
+		return ret;
+	}
+
+	return ret;
+}
+
+static void exynos_bus_exit(struct device *dev)
+{
+	struct exynos_bus *bus = dev_get_drvdata(dev);
+	int ret;
+
+	ret = exynos_bus_disable_edev(bus);
+	if (ret < 0)
+		dev_warn(dev, "failed to disable the devfreq-event devices\n");
+
+	if (bus->regulator)
+		regulator_disable(bus->regulator);
+
+	dev_pm_opp_of_remove_table(dev);
+	clk_disable_unprepare(bus->clk);
+}
+
+/*
+ * Must necessary function for devfreq passive governor
+ */
+static int exynos_bus_passive_target(struct device *dev, unsigned long *freq,
+					u32 flags)
+{
+	struct exynos_bus *bus = dev_get_drvdata(dev);
+	struct dev_pm_opp *new_opp;
+	unsigned long old_freq, new_freq;
+	int ret = 0;
+
+	/* Get new opp-bus instance according to new bus clock */
+	rcu_read_lock();
+	new_opp = devfreq_recommended_opp(dev, freq, flags);
+	if (IS_ERR(new_opp)) {
+		dev_err(dev, "failed to get recommended opp instance\n");
+		rcu_read_unlock();
+		return PTR_ERR(new_opp);
+	}
+
+	new_freq = dev_pm_opp_get_freq(new_opp);
+	old_freq = dev_pm_opp_get_freq(bus->curr_opp);
+	rcu_read_unlock();
+
+	if (old_freq == new_freq)
+		return 0;
+
+	/* Change the frequency according to new OPP level */
+	mutex_lock(&bus->lock);
+
+	ret = clk_set_rate(bus->clk, new_freq);
+	if (ret < 0) {
+		dev_err(dev, "failed to set the clock of bus\n");
+		goto out;
+	}
+
+	*freq = new_freq;
+	bus->curr_opp = new_opp;
+
+	dev_dbg(dev, "Set the frequency of bus (%lukHz -> %lukHz)\n",
+			old_freq/1000, new_freq/1000);
+out:
+	mutex_unlock(&bus->lock);
+
+	return ret;
+}
+
+static void exynos_bus_passive_exit(struct device *dev)
+{
+	struct exynos_bus *bus = dev_get_drvdata(dev);
+
+	dev_pm_opp_of_remove_table(dev);
+	clk_disable_unprepare(bus->clk);
+}
+
+static int exynos_bus_parent_parse_of(struct device_node *np,
+					struct exynos_bus *bus)
+{
+	struct device *dev = bus->dev;
+	int i, ret, count, size;
+
+	/* Get the regulator to provide each bus with the power */
+	bus->regulator = devm_regulator_get(dev, "vdd");
+	if (IS_ERR(bus->regulator)) {
+		dev_err(dev, "failed to get VDD regulator\n");
+		return PTR_ERR(bus->regulator);
+	}
+
+	ret = regulator_enable(bus->regulator);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable VDD regulator\n");
+		return ret;
+	}
+
+	/*
+	 * Get the devfreq-event devices to get the current utilization of
+	 * buses. This raw data will be used in devfreq ondemand governor.
+	 */
+	count = devfreq_event_get_edev_count(dev);
+	if (count < 0) {
+		dev_err(dev, "failed to get the count of devfreq-event dev\n");
+		ret = count;
+		goto err_regulator;
+	}
+	bus->edev_count = count;
+
+	size = sizeof(*bus->edev) * count;
+	bus->edev = devm_kzalloc(dev, size, GFP_KERNEL);
+	if (!bus->edev) {
+		ret = -ENOMEM;
+		goto err_regulator;
+	}
+
+	for (i = 0; i < count; i++) {
+		bus->edev[i] = devfreq_event_get_edev_by_phandle(dev, i);
+		if (IS_ERR(bus->edev[i])) {
+			ret = -EPROBE_DEFER;
+			goto err_regulator;
+		}
+	}
+
+	/*
+	 * Optionally, Get the saturation ratio according to Exynos SoC
+	 * When measuring the utilization of each AXI bus with devfreq-event
+	 * devices, the measured real cycle might be much lower than the
+	 * total cycle of bus during sampling rate. In result, the devfreq
+	 * simple-ondemand governor might not decide to change the current
+	 * frequency due to too utilization (= real cycle/total cycle).
+	 * So, this property is used to adjust the utilization when calculating
+	 * the busy_time in exynos_bus_get_dev_status().
+	 */
+	if (of_property_read_u32(np, "exynos,saturation-ratio", &bus->ratio))
+		bus->ratio = DEFAULT_SATURATION_RATIO;
+
+	if (of_property_read_u32(np, "exynos,voltage-tolerance",
+					&bus->voltage_tolerance))
+		bus->voltage_tolerance = DEFAULT_VOLTAGE_TOLERANCE;
+
+	return 0;
+
+err_regulator:
+	regulator_disable(bus->regulator);
+
+	return ret;
+}
+
+static int exynos_bus_parse_of(struct device_node *np,
+			      struct exynos_bus *bus)
+{
+	struct device *dev = bus->dev;
+	unsigned long rate;
+	int ret;
+
+	/* Get the clock to provide each bus with source clock */
+	bus->clk = devm_clk_get(dev, "bus");
+	if (IS_ERR(bus->clk)) {
+		dev_err(dev, "failed to get bus clock\n");
+		return PTR_ERR(bus->clk);
+	}
+
+	ret = clk_prepare_enable(bus->clk);
+	if (ret < 0) {
+		dev_err(dev, "failed to get enable clock\n");
+		return ret;
+	}
+
+	/* Get the freq and voltage from OPP table to scale the bus freq */
+	rcu_read_lock();
+	ret = dev_pm_opp_of_add_table(dev);
+	if (ret < 0) {
+		dev_err(dev, "failed to get OPP table\n");
+		rcu_read_unlock();
+		goto err_clk;
+	}
+
+	rate = clk_get_rate(bus->clk);
+	bus->curr_opp = devfreq_recommended_opp(dev, &rate, 0);
+	if (IS_ERR(bus->curr_opp)) {
+		dev_err(dev, "failed to find dev_pm_opp\n");
+		rcu_read_unlock();
+		ret = PTR_ERR(bus->curr_opp);
+		goto err_opp;
+	}
+	rcu_read_unlock();
+
+	return 0;
+
+err_opp:
+	dev_pm_opp_of_remove_table(dev);
+err_clk:
+	clk_disable_unprepare(bus->clk);
+
+	return ret;
+}
+
+static int exynos_bus_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct devfreq_dev_profile *profile;
+	struct devfreq_simple_ondemand_data *ondemand_data;
+	struct devfreq_passive_data *passive_data;
+	struct devfreq *parent_devfreq;
+	struct exynos_bus *bus;
+	int ret, max_state;
+	unsigned long min_freq, max_freq;
+
+	if (!np) {
+		dev_err(dev, "failed to find devicetree node\n");
+		return -EINVAL;
+	}
+
+	bus = devm_kzalloc(&pdev->dev, sizeof(*bus), GFP_KERNEL);
+	if (!bus)
+		return -ENOMEM;
+	mutex_init(&bus->lock);
+	bus->dev = &pdev->dev;
+	platform_set_drvdata(pdev, bus);
+
+	/* Parse the device-tree to get the resource information */
+	ret = exynos_bus_parse_of(np, bus);
+	if (ret < 0)
+		goto err;
+
+	profile = devm_kzalloc(dev, sizeof(*profile), GFP_KERNEL);
+	if (!profile) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	if (of_parse_phandle(dev->of_node, "devfreq", 0))
+		goto passive;
+	else
+		ret = exynos_bus_parent_parse_of(np, bus);
+
+	if (ret < 0)
+		goto err;
+
+	/* Initialize the struct profile and governor data for parent device */
+	profile->polling_ms = 50;
+	profile->target = exynos_bus_target;
+	profile->get_dev_status = exynos_bus_get_dev_status;
+	profile->exit = exynos_bus_exit;
+
+	ondemand_data = devm_kzalloc(dev, sizeof(*ondemand_data), GFP_KERNEL);
+	if (!ondemand_data) {
+		ret = -ENOMEM;
+		goto err;
+	}
+	ondemand_data->upthreshold = 40;
+	ondemand_data->downdifferential = 5;
+
+	/* Add devfreq device to monitor and handle the exynos bus */
+	bus->devfreq = devm_devfreq_add_device(dev, profile, "simple_ondemand",
+						ondemand_data);
+	if (IS_ERR(bus->devfreq)) {
+		dev_err(dev, "failed to add devfreq device\n");
+		ret = PTR_ERR(bus->devfreq);
+		goto err;
+	}
+
+	/* Register opp_notifier to catch the change of OPP  */
+	ret = devm_devfreq_register_opp_notifier(dev, bus->devfreq);
+	if (ret < 0) {
+		dev_err(dev, "failed to register opp notifier\n");
+		goto err;
+	}
+
+	/*
+	 * Enable devfreq-event to get raw data which is used to determine
+	 * current bus load.
+	 */
+	ret = exynos_bus_enable_edev(bus);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable devfreq-event devices\n");
+		goto err;
+	}
+
+	ret = exynos_bus_set_event(bus);
+	if (ret < 0) {
+		dev_err(dev, "failed to set event to devfreq-event devices\n");
+		goto err;
+	}
+
+	goto out;
+passive:
+	/* Initialize the struct profile and governor data for passive device */
+	profile->target = exynos_bus_passive_target;
+	profile->exit = exynos_bus_passive_exit;
+
+	/* Get the instance of parent devfreq device */
+	parent_devfreq = devfreq_get_devfreq_by_phandle(dev, 0);
+	if (IS_ERR(parent_devfreq)) {
+		ret = -EPROBE_DEFER;
+		goto err;
+	}
+
+	passive_data = devm_kzalloc(dev, sizeof(*passive_data), GFP_KERNEL);
+	if (!passive_data) {
+		ret = -ENOMEM;
+		goto err;
+	}
+	passive_data->parent = parent_devfreq;
+
+	/* Add devfreq device for exynos bus with passive governor */
+	bus->devfreq = devm_devfreq_add_device(dev, profile, "passive",
+						passive_data);
+	if (IS_ERR(bus->devfreq)) {
+		dev_err(dev,
+			"failed to add devfreq dev with passive governor\n");
+		ret = -EPROBE_DEFER;
+		goto err;
+	}
+
+out:
+	max_state = bus->devfreq->profile->max_state;
+	min_freq = (bus->devfreq->profile->freq_table[0] / 1000);
+	max_freq = (bus->devfreq->profile->freq_table[max_state - 1] / 1000);
+	pr_info("exynos-bus: new bus device registered: %s (%6ld KHz ~ %6ld KHz)\n",
+			dev_name(dev), min_freq, max_freq);
+
+	return 0;
+
+err:
+	dev_pm_opp_of_remove_table(dev);
+	clk_disable_unprepare(bus->clk);
+
+	return ret;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int exynos_bus_resume(struct device *dev)
+{
+	struct exynos_bus *bus = dev_get_drvdata(dev);
+	int ret;
+
+	ret = exynos_bus_enable_edev(bus);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable the devfreq-event devices\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int exynos_bus_suspend(struct device *dev)
+{
+	struct exynos_bus *bus = dev_get_drvdata(dev);
+	int ret;
+
+	ret = exynos_bus_disable_edev(bus);
+	if (ret < 0) {
+		dev_err(dev, "failed to disable the devfreq-event devices\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops exynos_bus_pm = {
+	SET_SYSTEM_SLEEP_PM_OPS(exynos_bus_suspend, exynos_bus_resume)
+};
+
+static const struct of_device_id exynos_bus_of_match[] = {
+	{ .compatible = "samsung,exynos-bus", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, exynos_bus_of_match);
+
+static struct platform_driver exynos_bus_platdrv = {
+	.probe		= exynos_bus_probe,
+	.driver = {
+		.name	= "exynos-bus",
+		.pm	= &exynos_bus_pm,
+		.of_match_table = of_match_ptr(exynos_bus_of_match),
+	},
+};
+module_platform_driver(exynos_bus_platdrv);
+
+MODULE_DESCRIPTION("Generic Exynos Bus frequency driver");
+MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/devfreq/exynos/Makefile b/drivers/devfreq/exynos/Makefile
deleted file mode 100644
index 49bc917..0000000
--- a/drivers/devfreq/exynos/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-# Exynos DEVFREQ Drivers
-obj-$(CONFIG_ARM_EXYNOS4_BUS_DEVFREQ)	+= exynos_ppmu.o exynos4_bus.o
-obj-$(CONFIG_ARM_EXYNOS5_BUS_DEVFREQ)	+= exynos_ppmu.o exynos5_bus.o
diff --git a/drivers/devfreq/exynos/exynos4_bus.c b/drivers/devfreq/exynos/exynos4_bus.c
deleted file mode 100644
index da95092..0000000
--- a/drivers/devfreq/exynos/exynos4_bus.c
+++ /dev/null
@@ -1,1055 +0,0 @@
-/* drivers/devfreq/exynos4210_memorybus.c
- *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *	MyungJoo Ham <myungjoo.ham@samsung.com>
- *
- * EXYNOS4 - Memory/Bus clock frequency scaling support in DEVFREQ framework
- *	This version supports EXYNOS4210 only. This changes bus frequencies
- *	and vddint voltages. Exynos4412/4212 should be able to be supported
- *	with minor modifications.
- *
- * 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.
- *
- */
-
-#include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/mutex.h>
-#include <linux/suspend.h>
-#include <linux/pm_opp.h>
-#include <linux/devfreq.h>
-#include <linux/platform_device.h>
-#include <linux/regulator/consumer.h>
-#include <linux/module.h>
-
-#include <mach/map.h>
-
-#include "exynos_ppmu.h"
-#include "exynos4_bus.h"
-
-#define MAX_SAFEVOLT	1200000 /* 1.2V */
-
-enum exynos4_busf_type {
-	TYPE_BUSF_EXYNOS4210,
-	TYPE_BUSF_EXYNOS4x12,
-};
-
-/* Assume that the bus is saturated if the utilization is 40% */
-#define BUS_SATURATION_RATIO	40
-
-enum busclk_level_idx {
-	LV_0 = 0,
-	LV_1,
-	LV_2,
-	LV_3,
-	LV_4,
-	_LV_END
-};
-
-enum exynos_ppmu_idx {
-	PPMU_DMC0,
-	PPMU_DMC1,
-	PPMU_END,
-};
-
-#define EX4210_LV_MAX	LV_2
-#define EX4x12_LV_MAX	LV_4
-#define EX4210_LV_NUM	(LV_2 + 1)
-#define EX4x12_LV_NUM	(LV_4 + 1)
-
-/**
- * struct busfreq_opp_info - opp information for bus
- * @rate:	Frequency in hertz
- * @volt:	Voltage in microvolts corresponding to this OPP
- */
-struct busfreq_opp_info {
-	unsigned long rate;
-	unsigned long volt;
-};
-
-struct busfreq_data {
-	enum exynos4_busf_type type;
-	struct device *dev;
-	struct devfreq *devfreq;
-	bool disabled;
-	struct regulator *vdd_int;
-	struct regulator *vdd_mif; /* Exynos4412/4212 only */
-	struct busfreq_opp_info curr_oppinfo;
-	struct busfreq_ppmu_data ppmu_data;
-
-	struct notifier_block pm_notifier;
-	struct mutex lock;
-
-	/* Dividers calculated at boot/probe-time */
-	unsigned int dmc_divtable[_LV_END]; /* DMC0 */
-	unsigned int top_divtable[_LV_END];
-};
-
-/* 4210 controls clock of mif and voltage of int */
-static struct bus_opp_table exynos4210_busclk_table[] = {
-	{LV_0, 400000, 1150000},
-	{LV_1, 267000, 1050000},
-	{LV_2, 133000, 1025000},
-	{0, 0, 0},
-};
-
-/*
- * MIF is the main control knob clock for Exynos4x12 MIF/INT
- * clock and voltage of both mif/int are controlled.
- */
-static struct bus_opp_table exynos4x12_mifclk_table[] = {
-	{LV_0, 400000, 1100000},
-	{LV_1, 267000, 1000000},
-	{LV_2, 160000, 950000},
-	{LV_3, 133000, 950000},
-	{LV_4, 100000, 950000},
-	{0, 0, 0},
-};
-
-/*
- * INT is not the control knob of 4x12. LV_x is not meant to represent
- * the current performance. (MIF does)
- */
-static struct bus_opp_table exynos4x12_intclk_table[] = {
-	{LV_0, 200000, 1000000},
-	{LV_1, 160000, 950000},
-	{LV_2, 133000, 925000},
-	{LV_3, 100000, 900000},
-	{0, 0, 0},
-};
-
-/* TODO: asv volt definitions are "__initdata"? */
-/* Some chips have different operating voltages */
-static unsigned int exynos4210_asv_volt[][EX4210_LV_NUM] = {
-	{1150000, 1050000, 1050000},
-	{1125000, 1025000, 1025000},
-	{1100000, 1000000, 1000000},
-	{1075000, 975000, 975000},
-	{1050000, 950000, 950000},
-};
-
-static unsigned int exynos4x12_mif_step_50[][EX4x12_LV_NUM] = {
-	/* 400      267     160     133     100 */
-	{1050000, 950000, 900000, 900000, 900000}, /* ASV0 */
-	{1050000, 950000, 900000, 900000, 900000}, /* ASV1 */
-	{1050000, 950000, 900000, 900000, 900000}, /* ASV2 */
-	{1050000, 900000, 900000, 900000, 900000}, /* ASV3 */
-	{1050000, 900000, 900000, 900000, 850000}, /* ASV4 */
-	{1050000, 900000, 900000, 850000, 850000}, /* ASV5 */
-	{1050000, 900000, 850000, 850000, 850000}, /* ASV6 */
-	{1050000, 900000, 850000, 850000, 850000}, /* ASV7 */
-	{1050000, 900000, 850000, 850000, 850000}, /* ASV8 */
-};
-
-static unsigned int exynos4x12_int_volt[][EX4x12_LV_NUM] = {
-	/* 200    160      133     100 */
-	{1000000, 950000, 925000, 900000}, /* ASV0 */
-	{975000,  925000, 925000, 900000}, /* ASV1 */
-	{950000,  925000, 900000, 875000}, /* ASV2 */
-	{950000,  900000, 900000, 875000}, /* ASV3 */
-	{925000,  875000, 875000, 875000}, /* ASV4 */
-	{900000,  850000, 850000, 850000}, /* ASV5 */
-	{900000,  850000, 850000, 850000}, /* ASV6 */
-	{900000,  850000, 850000, 850000}, /* ASV7 */
-	{900000,  850000, 850000, 850000}, /* ASV8 */
-};
-
-/*** Clock Divider Data for Exynos4210 ***/
-static unsigned int exynos4210_clkdiv_dmc0[][8] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVACP, DIVACP_PCLK, DIVDPHY, DIVDMC, DIVDMCD
-	 *		DIVDMCP, DIVCOPY2, DIVCORE_TIMERS }
-	 */
-
-	/* DMC L0: 400MHz */
-	{ 3, 1, 1, 1, 1, 1, 3, 1 },
-	/* DMC L1: 266.7MHz */
-	{ 4, 1, 1, 2, 1, 1, 3, 1 },
-	/* DMC L2: 133MHz */
-	{ 5, 1, 1, 5, 1, 1, 3, 1 },
-};
-static unsigned int exynos4210_clkdiv_top[][5] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVACLK200, DIVACLK100, DIVACLK160, DIVACLK133, DIVONENAND }
-	 */
-	/* ACLK200 L0: 200MHz */
-	{ 3, 7, 4, 5, 1 },
-	/* ACLK200 L1: 160MHz */
-	{ 4, 7, 5, 6, 1 },
-	/* ACLK200 L2: 133MHz */
-	{ 5, 7, 7, 7, 1 },
-};
-static unsigned int exynos4210_clkdiv_lr_bus[][2] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVGDL/R, DIVGPL/R }
-	 */
-	/* ACLK_GDL/R L1: 200MHz */
-	{ 3, 1 },
-	/* ACLK_GDL/R L2: 160MHz */
-	{ 4, 1 },
-	/* ACLK_GDL/R L3: 133MHz */
-	{ 5, 1 },
-};
-
-/*** Clock Divider Data for Exynos4212/4412 ***/
-static unsigned int exynos4x12_clkdiv_dmc0[][6] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVACP, DIVACP_PCLK, DIVDPHY, DIVDMC, DIVDMCD
-	 *              DIVDMCP}
-	 */
-
-	/* DMC L0: 400MHz */
-	{3, 1, 1, 1, 1, 1},
-	/* DMC L1: 266.7MHz */
-	{4, 1, 1, 2, 1, 1},
-	/* DMC L2: 160MHz */
-	{5, 1, 1, 4, 1, 1},
-	/* DMC L3: 133MHz */
-	{5, 1, 1, 5, 1, 1},
-	/* DMC L4: 100MHz */
-	{7, 1, 1, 7, 1, 1},
-};
-static unsigned int exynos4x12_clkdiv_dmc1[][6] = {
-	/*
-	 * Clock divider value for following
-	 * { G2DACP, DIVC2C, DIVC2C_ACLK }
-	 */
-
-	/* DMC L0: 400MHz */
-	{3, 1, 1},
-	/* DMC L1: 266.7MHz */
-	{4, 2, 1},
-	/* DMC L2: 160MHz */
-	{5, 4, 1},
-	/* DMC L3: 133MHz */
-	{5, 5, 1},
-	/* DMC L4: 100MHz */
-	{7, 7, 1},
-};
-static unsigned int exynos4x12_clkdiv_top[][5] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVACLK266_GPS, DIVACLK100, DIVACLK160,
-		DIVACLK133, DIVONENAND }
-	 */
-
-	/* ACLK_GDL/R L0: 200MHz */
-	{2, 7, 4, 5, 1},
-	/* ACLK_GDL/R L1: 200MHz */
-	{2, 7, 4, 5, 1},
-	/* ACLK_GDL/R L2: 160MHz */
-	{4, 7, 5, 7, 1},
-	/* ACLK_GDL/R L3: 133MHz */
-	{4, 7, 5, 7, 1},
-	/* ACLK_GDL/R L4: 100MHz */
-	{7, 7, 7, 7, 1},
-};
-static unsigned int exynos4x12_clkdiv_lr_bus[][2] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVGDL/R, DIVGPL/R }
-	 */
-
-	/* ACLK_GDL/R L0: 200MHz */
-	{3, 1},
-	/* ACLK_GDL/R L1: 200MHz */
-	{3, 1},
-	/* ACLK_GDL/R L2: 160MHz */
-	{4, 1},
-	/* ACLK_GDL/R L3: 133MHz */
-	{5, 1},
-	/* ACLK_GDL/R L4: 100MHz */
-	{7, 1},
-};
-static unsigned int exynos4x12_clkdiv_sclkip[][3] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVMFC, DIVJPEG, DIVFIMC0~3}
-	 */
-
-	/* SCLK_MFC: 200MHz */
-	{3, 3, 4},
-	/* SCLK_MFC: 200MHz */
-	{3, 3, 4},
-	/* SCLK_MFC: 160MHz */
-	{4, 4, 5},
-	/* SCLK_MFC: 133MHz */
-	{5, 5, 5},
-	/* SCLK_MFC: 100MHz */
-	{7, 7, 7},
-};
-
-
-static int exynos4210_set_busclk(struct busfreq_data *data,
-				 struct busfreq_opp_info *oppi)
-{
-	unsigned int index;
-	unsigned int tmp;
-
-	for (index = LV_0; index < EX4210_LV_NUM; index++)
-		if (oppi->rate == exynos4210_busclk_table[index].clk)
-			break;
-
-	if (index == EX4210_LV_NUM)
-		return -EINVAL;
-
-	/* Change Divider - DMC0 */
-	tmp = data->dmc_divtable[index];
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_DMC0);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_DMC0);
-	} while (tmp & 0x11111111);
-
-	/* Change Divider - TOP */
-	tmp = data->top_divtable[index];
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_TOP);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_TOP);
-	} while (tmp & 0x11111);
-
-	/* Change Divider - LEFTBUS */
-	tmp = __raw_readl(EXYNOS4_CLKDIV_LEFTBUS);
-
-	tmp &= ~(EXYNOS4_CLKDIV_BUS_GDLR_MASK | EXYNOS4_CLKDIV_BUS_GPLR_MASK);
-
-	tmp |= ((exynos4210_clkdiv_lr_bus[index][0] <<
-				EXYNOS4_CLKDIV_BUS_GDLR_SHIFT) |
-		(exynos4210_clkdiv_lr_bus[index][1] <<
-				EXYNOS4_CLKDIV_BUS_GPLR_SHIFT));
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_LEFTBUS);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_LEFTBUS);
-	} while (tmp & 0x11);
-
-	/* Change Divider - RIGHTBUS */
-	tmp = __raw_readl(EXYNOS4_CLKDIV_RIGHTBUS);
-
-	tmp &= ~(EXYNOS4_CLKDIV_BUS_GDLR_MASK | EXYNOS4_CLKDIV_BUS_GPLR_MASK);
-
-	tmp |= ((exynos4210_clkdiv_lr_bus[index][0] <<
-				EXYNOS4_CLKDIV_BUS_GDLR_SHIFT) |
-		(exynos4210_clkdiv_lr_bus[index][1] <<
-				EXYNOS4_CLKDIV_BUS_GPLR_SHIFT));
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_RIGHTBUS);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_RIGHTBUS);
-	} while (tmp & 0x11);
-
-	return 0;
-}
-
-static int exynos4x12_set_busclk(struct busfreq_data *data,
-				 struct busfreq_opp_info *oppi)
-{
-	unsigned int index;
-	unsigned int tmp;
-
-	for (index = LV_0; index < EX4x12_LV_NUM; index++)
-		if (oppi->rate == exynos4x12_mifclk_table[index].clk)
-			break;
-
-	if (index == EX4x12_LV_NUM)
-		return -EINVAL;
-
-	/* Change Divider - DMC0 */
-	tmp = data->dmc_divtable[index];
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_DMC0);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_DMC0);
-	} while (tmp & 0x11111111);
-
-	/* Change Divider - DMC1 */
-	tmp = __raw_readl(EXYNOS4_CLKDIV_DMC1);
-
-	tmp &= ~(EXYNOS4_CLKDIV_DMC1_G2D_ACP_MASK |
-		EXYNOS4_CLKDIV_DMC1_C2C_MASK |
-		EXYNOS4_CLKDIV_DMC1_C2CACLK_MASK);
-
-	tmp |= ((exynos4x12_clkdiv_dmc1[index][0] <<
-				EXYNOS4_CLKDIV_DMC1_G2D_ACP_SHIFT) |
-		(exynos4x12_clkdiv_dmc1[index][1] <<
-				EXYNOS4_CLKDIV_DMC1_C2C_SHIFT) |
-		(exynos4x12_clkdiv_dmc1[index][2] <<
-				EXYNOS4_CLKDIV_DMC1_C2CACLK_SHIFT));
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_DMC1);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_DMC1);
-	} while (tmp & 0x111111);
-
-	/* Change Divider - TOP */
-	tmp = __raw_readl(EXYNOS4_CLKDIV_TOP);
-
-	tmp &= ~(EXYNOS4_CLKDIV_TOP_ACLK266_GPS_MASK |
-		EXYNOS4_CLKDIV_TOP_ACLK100_MASK |
-		EXYNOS4_CLKDIV_TOP_ACLK160_MASK |
-		EXYNOS4_CLKDIV_TOP_ACLK133_MASK |
-		EXYNOS4_CLKDIV_TOP_ONENAND_MASK);
-
-	tmp |= ((exynos4x12_clkdiv_top[index][0] <<
-				EXYNOS4_CLKDIV_TOP_ACLK266_GPS_SHIFT) |
-		(exynos4x12_clkdiv_top[index][1] <<
-				EXYNOS4_CLKDIV_TOP_ACLK100_SHIFT) |
-		(exynos4x12_clkdiv_top[index][2] <<
-				EXYNOS4_CLKDIV_TOP_ACLK160_SHIFT) |
-		(exynos4x12_clkdiv_top[index][3] <<
-				EXYNOS4_CLKDIV_TOP_ACLK133_SHIFT) |
-		(exynos4x12_clkdiv_top[index][4] <<
-				EXYNOS4_CLKDIV_TOP_ONENAND_SHIFT));
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_TOP);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_TOP);
-	} while (tmp & 0x11111);
-
-	/* Change Divider - LEFTBUS */
-	tmp = __raw_readl(EXYNOS4_CLKDIV_LEFTBUS);
-
-	tmp &= ~(EXYNOS4_CLKDIV_BUS_GDLR_MASK | EXYNOS4_CLKDIV_BUS_GPLR_MASK);
-
-	tmp |= ((exynos4x12_clkdiv_lr_bus[index][0] <<
-				EXYNOS4_CLKDIV_BUS_GDLR_SHIFT) |
-		(exynos4x12_clkdiv_lr_bus[index][1] <<
-				EXYNOS4_CLKDIV_BUS_GPLR_SHIFT));
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_LEFTBUS);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_LEFTBUS);
-	} while (tmp & 0x11);
-
-	/* Change Divider - RIGHTBUS */
-	tmp = __raw_readl(EXYNOS4_CLKDIV_RIGHTBUS);
-
-	tmp &= ~(EXYNOS4_CLKDIV_BUS_GDLR_MASK | EXYNOS4_CLKDIV_BUS_GPLR_MASK);
-
-	tmp |= ((exynos4x12_clkdiv_lr_bus[index][0] <<
-				EXYNOS4_CLKDIV_BUS_GDLR_SHIFT) |
-		(exynos4x12_clkdiv_lr_bus[index][1] <<
-				EXYNOS4_CLKDIV_BUS_GPLR_SHIFT));
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_RIGHTBUS);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_RIGHTBUS);
-	} while (tmp & 0x11);
-
-	/* Change Divider - MFC */
-	tmp = __raw_readl(EXYNOS4_CLKDIV_MFC);
-
-	tmp &= ~(EXYNOS4_CLKDIV_MFC_MASK);
-
-	tmp |= ((exynos4x12_clkdiv_sclkip[index][0] <<
-				EXYNOS4_CLKDIV_MFC_SHIFT));
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_MFC);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_MFC);
-	} while (tmp & 0x1);
-
-	/* Change Divider - JPEG */
-	tmp = __raw_readl(EXYNOS4_CLKDIV_CAM1);
-
-	tmp &= ~(EXYNOS4_CLKDIV_CAM1_JPEG_MASK);
-
-	tmp |= ((exynos4x12_clkdiv_sclkip[index][1] <<
-				EXYNOS4_CLKDIV_CAM1_JPEG_SHIFT));
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_CAM1);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_CAM1);
-	} while (tmp & 0x1);
-
-	/* Change Divider - FIMC0~3 */
-	tmp = __raw_readl(EXYNOS4_CLKDIV_CAM);
-
-	tmp &= ~(EXYNOS4_CLKDIV_CAM_FIMC0_MASK | EXYNOS4_CLKDIV_CAM_FIMC1_MASK |
-		EXYNOS4_CLKDIV_CAM_FIMC2_MASK | EXYNOS4_CLKDIV_CAM_FIMC3_MASK);
-
-	tmp |= ((exynos4x12_clkdiv_sclkip[index][2] <<
-				EXYNOS4_CLKDIV_CAM_FIMC0_SHIFT) |
-		(exynos4x12_clkdiv_sclkip[index][2] <<
-				EXYNOS4_CLKDIV_CAM_FIMC1_SHIFT) |
-		(exynos4x12_clkdiv_sclkip[index][2] <<
-				EXYNOS4_CLKDIV_CAM_FIMC2_SHIFT) |
-		(exynos4x12_clkdiv_sclkip[index][2] <<
-				EXYNOS4_CLKDIV_CAM_FIMC3_SHIFT));
-
-	__raw_writel(tmp, EXYNOS4_CLKDIV_CAM);
-
-	do {
-		tmp = __raw_readl(EXYNOS4_CLKDIV_STAT_CAM1);
-	} while (tmp & 0x1111);
-
-	return 0;
-}
-
-static int exynos4x12_get_intspec(unsigned long mifclk)
-{
-	int i = 0;
-
-	while (exynos4x12_intclk_table[i].clk) {
-		if (exynos4x12_intclk_table[i].clk <= mifclk)
-			return i;
-		i++;
-	}
-
-	return -EINVAL;
-}
-
-static int exynos4_bus_setvolt(struct busfreq_data *data,
-			       struct busfreq_opp_info *oppi,
-			       struct busfreq_opp_info *oldoppi)
-{
-	int err = 0, tmp;
-	unsigned long volt = oppi->volt;
-
-	switch (data->type) {
-	case TYPE_BUSF_EXYNOS4210:
-		/* OPP represents DMC clock + INT voltage */
-		err = regulator_set_voltage(data->vdd_int, volt,
-					    MAX_SAFEVOLT);
-		break;
-	case TYPE_BUSF_EXYNOS4x12:
-		/* OPP represents MIF clock + MIF voltage */
-		err = regulator_set_voltage(data->vdd_mif, volt,
-					    MAX_SAFEVOLT);
-		if (err)
-			break;
-
-		tmp = exynos4x12_get_intspec(oppi->rate);
-		if (tmp < 0) {
-			err = tmp;
-			regulator_set_voltage(data->vdd_mif,
-					      oldoppi->volt,
-					      MAX_SAFEVOLT);
-			break;
-		}
-		err = regulator_set_voltage(data->vdd_int,
-					    exynos4x12_intclk_table[tmp].volt,
-					    MAX_SAFEVOLT);
-		/*  Try to recover */
-		if (err)
-			regulator_set_voltage(data->vdd_mif,
-					      oldoppi->volt,
-					      MAX_SAFEVOLT);
-		break;
-	default:
-		err = -EINVAL;
-	}
-
-	return err;
-}
-
-static int exynos4_bus_target(struct device *dev, unsigned long *_freq,
-			      u32 flags)
-{
-	int err = 0;
-	struct platform_device *pdev = container_of(dev, struct platform_device,
-						    dev);
-	struct busfreq_data *data = platform_get_drvdata(pdev);
-	struct dev_pm_opp *opp;
-	unsigned long freq;
-	unsigned long old_freq = data->curr_oppinfo.rate;
-	struct busfreq_opp_info	new_oppinfo;
-
-	rcu_read_lock();
-	opp = devfreq_recommended_opp(dev, _freq, flags);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
-		return PTR_ERR(opp);
-	}
-	new_oppinfo.rate = dev_pm_opp_get_freq(opp);
-	new_oppinfo.volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
-	freq = new_oppinfo.rate;
-
-	if (old_freq == freq)
-		return 0;
-
-	dev_dbg(dev, "targeting %lukHz %luuV\n", freq, new_oppinfo.volt);
-
-	mutex_lock(&data->lock);
-
-	if (data->disabled)
-		goto out;
-
-	if (old_freq < freq)
-		err = exynos4_bus_setvolt(data, &new_oppinfo,
-					  &data->curr_oppinfo);
-	if (err)
-		goto out;
-
-	if (old_freq != freq) {
-		switch (data->type) {
-		case TYPE_BUSF_EXYNOS4210:
-			err = exynos4210_set_busclk(data, &new_oppinfo);
-			break;
-		case TYPE_BUSF_EXYNOS4x12:
-			err = exynos4x12_set_busclk(data, &new_oppinfo);
-			break;
-		default:
-			err = -EINVAL;
-		}
-	}
-	if (err)
-		goto out;
-
-	if (old_freq > freq)
-		err = exynos4_bus_setvolt(data, &new_oppinfo,
-					  &data->curr_oppinfo);
-	if (err)
-		goto out;
-
-	data->curr_oppinfo = new_oppinfo;
-out:
-	mutex_unlock(&data->lock);
-	return err;
-}
-
-static int exynos4_bus_get_dev_status(struct device *dev,
-				      struct devfreq_dev_status *stat)
-{
-	struct busfreq_data *data = dev_get_drvdata(dev);
-	struct busfreq_ppmu_data *ppmu_data = &data->ppmu_data;
-	int busier;
-
-	exynos_read_ppmu(ppmu_data);
-	busier = exynos_get_busier_ppmu(ppmu_data);
-	stat->current_frequency = data->curr_oppinfo.rate;
-
-	/* Number of cycles spent on memory access */
-	stat->busy_time = ppmu_data->ppmu[busier].count[PPMU_PMNCNT3];
-	stat->busy_time *= 100 / BUS_SATURATION_RATIO;
-	stat->total_time = ppmu_data->ppmu[busier].ccnt;
-
-	/* If the counters have overflown, retry */
-	if (ppmu_data->ppmu[busier].ccnt_overflow ||
-	    ppmu_data->ppmu[busier].count_overflow[0])
-		return -EAGAIN;
-
-	return 0;
-}
-
-static struct devfreq_dev_profile exynos4_devfreq_profile = {
-	.initial_freq	= 400000,
-	.polling_ms	= 50,
-	.target		= exynos4_bus_target,
-	.get_dev_status	= exynos4_bus_get_dev_status,
-};
-
-static int exynos4210_init_tables(struct busfreq_data *data)
-{
-	u32 tmp;
-	int mgrp;
-	int i, err = 0;
-
-	tmp = __raw_readl(EXYNOS4_CLKDIV_DMC0);
-	for (i = LV_0; i < EX4210_LV_NUM; i++) {
-		tmp &= ~(EXYNOS4_CLKDIV_DMC0_ACP_MASK |
-			EXYNOS4_CLKDIV_DMC0_ACPPCLK_MASK |
-			EXYNOS4_CLKDIV_DMC0_DPHY_MASK |
-			EXYNOS4_CLKDIV_DMC0_DMC_MASK |
-			EXYNOS4_CLKDIV_DMC0_DMCD_MASK |
-			EXYNOS4_CLKDIV_DMC0_DMCP_MASK |
-			EXYNOS4_CLKDIV_DMC0_COPY2_MASK |
-			EXYNOS4_CLKDIV_DMC0_CORETI_MASK);
-
-		tmp |= ((exynos4210_clkdiv_dmc0[i][0] <<
-					EXYNOS4_CLKDIV_DMC0_ACP_SHIFT) |
-			(exynos4210_clkdiv_dmc0[i][1] <<
-					EXYNOS4_CLKDIV_DMC0_ACPPCLK_SHIFT) |
-			(exynos4210_clkdiv_dmc0[i][2] <<
-					EXYNOS4_CLKDIV_DMC0_DPHY_SHIFT) |
-			(exynos4210_clkdiv_dmc0[i][3] <<
-					EXYNOS4_CLKDIV_DMC0_DMC_SHIFT) |
-			(exynos4210_clkdiv_dmc0[i][4] <<
-					EXYNOS4_CLKDIV_DMC0_DMCD_SHIFT) |
-			(exynos4210_clkdiv_dmc0[i][5] <<
-					EXYNOS4_CLKDIV_DMC0_DMCP_SHIFT) |
-			(exynos4210_clkdiv_dmc0[i][6] <<
-					EXYNOS4_CLKDIV_DMC0_COPY2_SHIFT) |
-			(exynos4210_clkdiv_dmc0[i][7] <<
-					EXYNOS4_CLKDIV_DMC0_CORETI_SHIFT));
-
-		data->dmc_divtable[i] = tmp;
-	}
-
-	tmp = __raw_readl(EXYNOS4_CLKDIV_TOP);
-	for (i = LV_0; i <  EX4210_LV_NUM; i++) {
-		tmp &= ~(EXYNOS4_CLKDIV_TOP_ACLK200_MASK |
-			EXYNOS4_CLKDIV_TOP_ACLK100_MASK |
-			EXYNOS4_CLKDIV_TOP_ACLK160_MASK |
-			EXYNOS4_CLKDIV_TOP_ACLK133_MASK |
-			EXYNOS4_CLKDIV_TOP_ONENAND_MASK);
-
-		tmp |= ((exynos4210_clkdiv_top[i][0] <<
-					EXYNOS4_CLKDIV_TOP_ACLK200_SHIFT) |
-			(exynos4210_clkdiv_top[i][1] <<
-					EXYNOS4_CLKDIV_TOP_ACLK100_SHIFT) |
-			(exynos4210_clkdiv_top[i][2] <<
-					EXYNOS4_CLKDIV_TOP_ACLK160_SHIFT) |
-			(exynos4210_clkdiv_top[i][3] <<
-					EXYNOS4_CLKDIV_TOP_ACLK133_SHIFT) |
-			(exynos4210_clkdiv_top[i][4] <<
-					EXYNOS4_CLKDIV_TOP_ONENAND_SHIFT));
-
-		data->top_divtable[i] = tmp;
-	}
-
-	/*
-	 * TODO: init tmp based on busfreq_data
-	 * (device-tree or platform-data)
-	 */
-	tmp = 0; /* Max voltages for the reliability of the unknown */
-
-	pr_debug("ASV Group of Exynos4 is %d\n", tmp);
-	/* Use merged grouping for voltage */
-	switch (tmp) {
-	case 0:
-		mgrp = 0;
-		break;
-	case 1:
-	case 2:
-		mgrp = 1;
-		break;
-	case 3:
-	case 4:
-		mgrp = 2;
-		break;
-	case 5:
-	case 6:
-		mgrp = 3;
-		break;
-	case 7:
-		mgrp = 4;
-		break;
-	default:
-		pr_warn("Unknown ASV Group. Use max voltage.\n");
-		mgrp = 0;
-	}
-
-	for (i = LV_0; i < EX4210_LV_NUM; i++)
-		exynos4210_busclk_table[i].volt = exynos4210_asv_volt[mgrp][i];
-
-	for (i = LV_0; i < EX4210_LV_NUM; i++) {
-		err = dev_pm_opp_add(data->dev, exynos4210_busclk_table[i].clk,
-			      exynos4210_busclk_table[i].volt);
-		if (err) {
-			dev_err(data->dev, "Cannot add opp entries.\n");
-			return err;
-		}
-	}
-
-
-	return 0;
-}
-
-static int exynos4x12_init_tables(struct busfreq_data *data)
-{
-	unsigned int i;
-	unsigned int tmp;
-	int ret;
-
-	/* Enable pause function for DREX2 DVFS */
-	tmp = __raw_readl(EXYNOS4_DMC_PAUSE_CTRL);
-	tmp |= EXYNOS4_DMC_PAUSE_ENABLE;
-	__raw_writel(tmp, EXYNOS4_DMC_PAUSE_CTRL);
-
-	tmp = __raw_readl(EXYNOS4_CLKDIV_DMC0);
-
-	for (i = 0; i <  EX4x12_LV_NUM; i++) {
-		tmp &= ~(EXYNOS4_CLKDIV_DMC0_ACP_MASK |
-			EXYNOS4_CLKDIV_DMC0_ACPPCLK_MASK |
-			EXYNOS4_CLKDIV_DMC0_DPHY_MASK |
-			EXYNOS4_CLKDIV_DMC0_DMC_MASK |
-			EXYNOS4_CLKDIV_DMC0_DMCD_MASK |
-			EXYNOS4_CLKDIV_DMC0_DMCP_MASK);
-
-		tmp |= ((exynos4x12_clkdiv_dmc0[i][0] <<
-					EXYNOS4_CLKDIV_DMC0_ACP_SHIFT) |
-			(exynos4x12_clkdiv_dmc0[i][1] <<
-					EXYNOS4_CLKDIV_DMC0_ACPPCLK_SHIFT) |
-			(exynos4x12_clkdiv_dmc0[i][2] <<
-					EXYNOS4_CLKDIV_DMC0_DPHY_SHIFT) |
-			(exynos4x12_clkdiv_dmc0[i][3] <<
-					EXYNOS4_CLKDIV_DMC0_DMC_SHIFT) |
-			(exynos4x12_clkdiv_dmc0[i][4] <<
-					EXYNOS4_CLKDIV_DMC0_DMCD_SHIFT) |
-			(exynos4x12_clkdiv_dmc0[i][5] <<
-					EXYNOS4_CLKDIV_DMC0_DMCP_SHIFT));
-
-		data->dmc_divtable[i] = tmp;
-	}
-
-	tmp = 0; /* Max voltages for the reliability of the unknown */
-
-	if (tmp > 8)
-		tmp = 0;
-	pr_debug("ASV Group of Exynos4x12 is %d\n", tmp);
-
-	for (i = 0; i < EX4x12_LV_NUM; i++) {
-		exynos4x12_mifclk_table[i].volt =
-			exynos4x12_mif_step_50[tmp][i];
-		exynos4x12_intclk_table[i].volt =
-			exynos4x12_int_volt[tmp][i];
-	}
-
-	for (i = 0; i < EX4x12_LV_NUM; i++) {
-		ret = dev_pm_opp_add(data->dev, exynos4x12_mifclk_table[i].clk,
-			      exynos4x12_mifclk_table[i].volt);
-		if (ret) {
-			dev_err(data->dev, "Fail to add opp entries.\n");
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-static int exynos4_busfreq_pm_notifier_event(struct notifier_block *this,
-		unsigned long event, void *ptr)
-{
-	struct busfreq_data *data = container_of(this, struct busfreq_data,
-						 pm_notifier);
-	struct dev_pm_opp *opp;
-	struct busfreq_opp_info	new_oppinfo;
-	unsigned long maxfreq = ULONG_MAX;
-	int err = 0;
-
-	switch (event) {
-	case PM_SUSPEND_PREPARE:
-		/* Set Fastest and Deactivate DVFS */
-		mutex_lock(&data->lock);
-
-		data->disabled = true;
-
-		rcu_read_lock();
-		opp = dev_pm_opp_find_freq_floor(data->dev, &maxfreq);
-		if (IS_ERR(opp)) {
-			rcu_read_unlock();
-			dev_err(data->dev, "%s: unable to find a min freq\n",
-				__func__);
-			mutex_unlock(&data->lock);
-			return PTR_ERR(opp);
-		}
-		new_oppinfo.rate = dev_pm_opp_get_freq(opp);
-		new_oppinfo.volt = dev_pm_opp_get_voltage(opp);
-		rcu_read_unlock();
-
-		err = exynos4_bus_setvolt(data, &new_oppinfo,
-					  &data->curr_oppinfo);
-		if (err)
-			goto unlock;
-
-		switch (data->type) {
-		case TYPE_BUSF_EXYNOS4210:
-			err = exynos4210_set_busclk(data, &new_oppinfo);
-			break;
-		case TYPE_BUSF_EXYNOS4x12:
-			err = exynos4x12_set_busclk(data, &new_oppinfo);
-			break;
-		default:
-			err = -EINVAL;
-		}
-		if (err)
-			goto unlock;
-
-		data->curr_oppinfo = new_oppinfo;
-unlock:
-		mutex_unlock(&data->lock);
-		if (err)
-			return err;
-		return NOTIFY_OK;
-	case PM_POST_RESTORE:
-	case PM_POST_SUSPEND:
-		/* Reactivate */
-		mutex_lock(&data->lock);
-		data->disabled = false;
-		mutex_unlock(&data->lock);
-		return NOTIFY_OK;
-	}
-
-	return NOTIFY_DONE;
-}
-
-static int exynos4_busfreq_probe(struct platform_device *pdev)
-{
-	struct busfreq_data *data;
-	struct busfreq_ppmu_data *ppmu_data;
-	struct dev_pm_opp *opp;
-	struct device *dev = &pdev->dev;
-	int err = 0;
-
-	data = devm_kzalloc(&pdev->dev, sizeof(struct busfreq_data), GFP_KERNEL);
-	if (data == NULL) {
-		dev_err(dev, "Cannot allocate memory.\n");
-		return -ENOMEM;
-	}
-
-	ppmu_data = &data->ppmu_data;
-	ppmu_data->ppmu_end = PPMU_END;
-	ppmu_data->ppmu = devm_kzalloc(dev,
-				       sizeof(struct exynos_ppmu) * PPMU_END,
-				       GFP_KERNEL);
-	if (!ppmu_data->ppmu) {
-		dev_err(dev, "Failed to allocate memory for exynos_ppmu\n");
-		return -ENOMEM;
-	}
-
-	data->type = pdev->id_entry->driver_data;
-	ppmu_data->ppmu[PPMU_DMC0].hw_base = S5P_VA_DMC0;
-	ppmu_data->ppmu[PPMU_DMC1].hw_base = S5P_VA_DMC1;
-	data->pm_notifier.notifier_call = exynos4_busfreq_pm_notifier_event;
-	data->dev = dev;
-	mutex_init(&data->lock);
-
-	switch (data->type) {
-	case TYPE_BUSF_EXYNOS4210:
-		err = exynos4210_init_tables(data);
-		break;
-	case TYPE_BUSF_EXYNOS4x12:
-		err = exynos4x12_init_tables(data);
-		break;
-	default:
-		dev_err(dev, "Cannot determine the device id %d\n", data->type);
-		err = -EINVAL;
-	}
-	if (err) {
-		dev_err(dev, "Cannot initialize busfreq table %d\n",
-			     data->type);
-		return err;
-	}
-
-	data->vdd_int = devm_regulator_get(dev, "vdd_int");
-	if (IS_ERR(data->vdd_int)) {
-		dev_err(dev, "Cannot get the regulator \"vdd_int\"\n");
-		return PTR_ERR(data->vdd_int);
-	}
-	if (data->type == TYPE_BUSF_EXYNOS4x12) {
-		data->vdd_mif = devm_regulator_get(dev, "vdd_mif");
-		if (IS_ERR(data->vdd_mif)) {
-			dev_err(dev, "Cannot get the regulator \"vdd_mif\"\n");
-			return PTR_ERR(data->vdd_mif);
-		}
-	}
-
-	rcu_read_lock();
-	opp = dev_pm_opp_find_freq_floor(dev,
-					 &exynos4_devfreq_profile.initial_freq);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
-		dev_err(dev, "Invalid initial frequency %lu kHz.\n",
-			exynos4_devfreq_profile.initial_freq);
-		return PTR_ERR(opp);
-	}
-	data->curr_oppinfo.rate = dev_pm_opp_get_freq(opp);
-	data->curr_oppinfo.volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
-
-	platform_set_drvdata(pdev, data);
-
-	data->devfreq = devm_devfreq_add_device(dev, &exynos4_devfreq_profile,
-					   "simple_ondemand", NULL);
-	if (IS_ERR(data->devfreq))
-		return PTR_ERR(data->devfreq);
-
-	/*
-	 * Start PPMU (Performance Profiling Monitoring Unit) to check
-	 * utilization of each IP in the Exynos4 SoC.
-	 */
-	busfreq_mon_reset(ppmu_data);
-
-	/* Register opp_notifier for Exynos4 busfreq */
-	err = devm_devfreq_register_opp_notifier(dev, data->devfreq);
-	if (err < 0) {
-		dev_err(dev, "Failed to register opp notifier\n");
-		return err;
-	}
-
-	/* Register pm_notifier for Exynos4 busfreq */
-	err = register_pm_notifier(&data->pm_notifier);
-	if (err) {
-		dev_err(dev, "Failed to setup pm notifier\n");
-		return err;
-	}
-
-	return 0;
-}
-
-static int exynos4_busfreq_remove(struct platform_device *pdev)
-{
-	struct busfreq_data *data = platform_get_drvdata(pdev);
-
-	/* Unregister all of notifier chain */
-	unregister_pm_notifier(&data->pm_notifier);
-
-	return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int exynos4_busfreq_resume(struct device *dev)
-{
-	struct busfreq_data *data = dev_get_drvdata(dev);
-	struct busfreq_ppmu_data *ppmu_data = &data->ppmu_data;
-
-	busfreq_mon_reset(ppmu_data);
-	return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(exynos4_busfreq_pm_ops, NULL, exynos4_busfreq_resume);
-
-static const struct platform_device_id exynos4_busfreq_id[] = {
-	{ "exynos4210-busfreq", TYPE_BUSF_EXYNOS4210 },
-	{ "exynos4412-busfreq", TYPE_BUSF_EXYNOS4x12 },
-	{ "exynos4212-busfreq", TYPE_BUSF_EXYNOS4x12 },
-	{ },
-};
-
-static struct platform_driver exynos4_busfreq_driver = {
-	.probe	= exynos4_busfreq_probe,
-	.remove	= exynos4_busfreq_remove,
-	.id_table = exynos4_busfreq_id,
-	.driver = {
-		.name	= "exynos4-busfreq",
-		.pm	= &exynos4_busfreq_pm_ops,
-	},
-};
-
-static int __init exynos4_busfreq_init(void)
-{
-	return platform_driver_register(&exynos4_busfreq_driver);
-}
-late_initcall(exynos4_busfreq_init);
-
-static void __exit exynos4_busfreq_exit(void)
-{
-	platform_driver_unregister(&exynos4_busfreq_driver);
-}
-module_exit(exynos4_busfreq_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("EXYNOS4 busfreq driver with devfreq framework");
-MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
diff --git a/drivers/devfreq/exynos/exynos4_bus.h b/drivers/devfreq/exynos/exynos4_bus.h
deleted file mode 100644
index 94c73c1..0000000
--- a/drivers/devfreq/exynos/exynos4_bus.h
+++ /dev/null
@@ -1,110 +0,0 @@
-/*
- * Copyright (c) 2013 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * EXYNOS4 BUS header
- *
- * 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 __DEVFREQ_EXYNOS4_BUS_H
-#define __DEVFREQ_EXYNOS4_BUS_H __FILE__
-
-#include <mach/map.h>
-
-#define EXYNOS4_CLKDIV_LEFTBUS			(S5P_VA_CMU + 0x04500)
-#define EXYNOS4_CLKDIV_STAT_LEFTBUS		(S5P_VA_CMU + 0x04600)
-
-#define EXYNOS4_CLKDIV_RIGHTBUS			(S5P_VA_CMU + 0x08500)
-#define EXYNOS4_CLKDIV_STAT_RIGHTBUS		(S5P_VA_CMU + 0x08600)
-
-#define EXYNOS4_CLKDIV_TOP			(S5P_VA_CMU + 0x0C510)
-#define EXYNOS4_CLKDIV_CAM			(S5P_VA_CMU + 0x0C520)
-#define EXYNOS4_CLKDIV_MFC			(S5P_VA_CMU + 0x0C528)
-
-#define EXYNOS4_CLKDIV_STAT_TOP			(S5P_VA_CMU + 0x0C610)
-#define EXYNOS4_CLKDIV_STAT_MFC			(S5P_VA_CMU + 0x0C628)
-
-#define EXYNOS4210_CLKGATE_IP_IMAGE		(S5P_VA_CMU + 0x0C930)
-#define EXYNOS4212_CLKGATE_IP_IMAGE		(S5P_VA_CMU + 0x04930)
-
-#define EXYNOS4_CLKDIV_DMC0			(S5P_VA_CMU + 0x10500)
-#define EXYNOS4_CLKDIV_DMC1			(S5P_VA_CMU + 0x10504)
-#define EXYNOS4_CLKDIV_STAT_DMC0		(S5P_VA_CMU + 0x10600)
-#define EXYNOS4_CLKDIV_STAT_DMC1		(S5P_VA_CMU + 0x10604)
-
-#define EXYNOS4_DMC_PAUSE_CTRL			(S5P_VA_CMU + 0x11094)
-#define EXYNOS4_DMC_PAUSE_ENABLE		(1 << 0)
-
-#define EXYNOS4_CLKDIV_DMC0_ACP_SHIFT		(0)
-#define EXYNOS4_CLKDIV_DMC0_ACP_MASK		(0x7 << EXYNOS4_CLKDIV_DMC0_ACP_SHIFT)
-#define EXYNOS4_CLKDIV_DMC0_ACPPCLK_SHIFT	(4)
-#define EXYNOS4_CLKDIV_DMC0_ACPPCLK_MASK	(0x7 << EXYNOS4_CLKDIV_DMC0_ACPPCLK_SHIFT)
-#define EXYNOS4_CLKDIV_DMC0_DPHY_SHIFT		(8)
-#define EXYNOS4_CLKDIV_DMC0_DPHY_MASK		(0x7 << EXYNOS4_CLKDIV_DMC0_DPHY_SHIFT)
-#define EXYNOS4_CLKDIV_DMC0_DMC_SHIFT		(12)
-#define EXYNOS4_CLKDIV_DMC0_DMC_MASK		(0x7 << EXYNOS4_CLKDIV_DMC0_DMC_SHIFT)
-#define EXYNOS4_CLKDIV_DMC0_DMCD_SHIFT		(16)
-#define EXYNOS4_CLKDIV_DMC0_DMCD_MASK		(0x7 << EXYNOS4_CLKDIV_DMC0_DMCD_SHIFT)
-#define EXYNOS4_CLKDIV_DMC0_DMCP_SHIFT		(20)
-#define EXYNOS4_CLKDIV_DMC0_DMCP_MASK		(0x7 << EXYNOS4_CLKDIV_DMC0_DMCP_SHIFT)
-#define EXYNOS4_CLKDIV_DMC0_COPY2_SHIFT		(24)
-#define EXYNOS4_CLKDIV_DMC0_COPY2_MASK		(0x7 << EXYNOS4_CLKDIV_DMC0_COPY2_SHIFT)
-#define EXYNOS4_CLKDIV_DMC0_CORETI_SHIFT	(28)
-#define EXYNOS4_CLKDIV_DMC0_CORETI_MASK		(0x7 << EXYNOS4_CLKDIV_DMC0_CORETI_SHIFT)
-
-#define EXYNOS4_CLKDIV_DMC1_G2D_ACP_SHIFT	(0)
-#define EXYNOS4_CLKDIV_DMC1_G2D_ACP_MASK	(0xf << EXYNOS4_CLKDIV_DMC1_G2D_ACP_SHIFT)
-#define EXYNOS4_CLKDIV_DMC1_C2C_SHIFT		(4)
-#define EXYNOS4_CLKDIV_DMC1_C2C_MASK		(0x7 << EXYNOS4_CLKDIV_DMC1_C2C_SHIFT)
-#define EXYNOS4_CLKDIV_DMC1_PWI_SHIFT		(8)
-#define EXYNOS4_CLKDIV_DMC1_PWI_MASK		(0xf << EXYNOS4_CLKDIV_DMC1_PWI_SHIFT)
-#define EXYNOS4_CLKDIV_DMC1_C2CACLK_SHIFT	(12)
-#define EXYNOS4_CLKDIV_DMC1_C2CACLK_MASK	(0x7 << EXYNOS4_CLKDIV_DMC1_C2CACLK_SHIFT)
-#define EXYNOS4_CLKDIV_DMC1_DVSEM_SHIFT		(16)
-#define EXYNOS4_CLKDIV_DMC1_DVSEM_MASK		(0x7f << EXYNOS4_CLKDIV_DMC1_DVSEM_SHIFT)
-#define EXYNOS4_CLKDIV_DMC1_DPM_SHIFT		(24)
-#define EXYNOS4_CLKDIV_DMC1_DPM_MASK		(0x7f << EXYNOS4_CLKDIV_DMC1_DPM_SHIFT)
-
-#define EXYNOS4_CLKDIV_MFC_SHIFT		(0)
-#define EXYNOS4_CLKDIV_MFC_MASK			(0x7 << EXYNOS4_CLKDIV_MFC_SHIFT)
-
-#define EXYNOS4_CLKDIV_TOP_ACLK200_SHIFT	(0)
-#define EXYNOS4_CLKDIV_TOP_ACLK200_MASK		(0x7 << EXYNOS4_CLKDIV_TOP_ACLK200_SHIFT)
-#define EXYNOS4_CLKDIV_TOP_ACLK100_SHIFT	(4)
-#define EXYNOS4_CLKDIV_TOP_ACLK100_MASK		(0xF << EXYNOS4_CLKDIV_TOP_ACLK100_SHIFT)
-#define EXYNOS4_CLKDIV_TOP_ACLK160_SHIFT	(8)
-#define EXYNOS4_CLKDIV_TOP_ACLK160_MASK		(0x7 << EXYNOS4_CLKDIV_TOP_ACLK160_SHIFT)
-#define EXYNOS4_CLKDIV_TOP_ACLK133_SHIFT	(12)
-#define EXYNOS4_CLKDIV_TOP_ACLK133_MASK		(0x7 << EXYNOS4_CLKDIV_TOP_ACLK133_SHIFT)
-#define EXYNOS4_CLKDIV_TOP_ONENAND_SHIFT	(16)
-#define EXYNOS4_CLKDIV_TOP_ONENAND_MASK		(0x7 << EXYNOS4_CLKDIV_TOP_ONENAND_SHIFT)
-#define EXYNOS4_CLKDIV_TOP_ACLK266_GPS_SHIFT	(20)
-#define EXYNOS4_CLKDIV_TOP_ACLK266_GPS_MASK	(0x7 << EXYNOS4_CLKDIV_TOP_ACLK266_GPS_SHIFT)
-#define EXYNOS4_CLKDIV_TOP_ACLK400_MCUISP_SHIFT	(24)
-#define EXYNOS4_CLKDIV_TOP_ACLK400_MCUISP_MASK	(0x7 << EXYNOS4_CLKDIV_TOP_ACLK400_MCUISP_SHIFT)
-
-#define EXYNOS4_CLKDIV_BUS_GDLR_SHIFT		(0)
-#define EXYNOS4_CLKDIV_BUS_GDLR_MASK		(0x7 << EXYNOS4_CLKDIV_BUS_GDLR_SHIFT)
-#define EXYNOS4_CLKDIV_BUS_GPLR_SHIFT		(4)
-#define EXYNOS4_CLKDIV_BUS_GPLR_MASK		(0x7 << EXYNOS4_CLKDIV_BUS_GPLR_SHIFT)
-
-#define EXYNOS4_CLKDIV_CAM_FIMC0_SHIFT		(0)
-#define EXYNOS4_CLKDIV_CAM_FIMC0_MASK		(0xf << EXYNOS4_CLKDIV_CAM_FIMC0_SHIFT)
-#define EXYNOS4_CLKDIV_CAM_FIMC1_SHIFT		(4)
-#define EXYNOS4_CLKDIV_CAM_FIMC1_MASK		(0xf << EXYNOS4_CLKDIV_CAM_FIMC1_SHIFT)
-#define EXYNOS4_CLKDIV_CAM_FIMC2_SHIFT		(8)
-#define EXYNOS4_CLKDIV_CAM_FIMC2_MASK		(0xf << EXYNOS4_CLKDIV_CAM_FIMC2_SHIFT)
-#define EXYNOS4_CLKDIV_CAM_FIMC3_SHIFT		(12)
-#define EXYNOS4_CLKDIV_CAM_FIMC3_MASK		(0xf << EXYNOS4_CLKDIV_CAM_FIMC3_SHIFT)
-
-#define EXYNOS4_CLKDIV_CAM1			(S5P_VA_CMU + 0x0C568)
-
-#define EXYNOS4_CLKDIV_STAT_CAM1		(S5P_VA_CMU + 0x0C668)
-
-#define EXYNOS4_CLKDIV_CAM1_JPEG_SHIFT		(0)
-#define EXYNOS4_CLKDIV_CAM1_JPEG_MASK		(0xf << EXYNOS4_CLKDIV_CAM1_JPEG_SHIFT)
-
-#endif /* __DEVFREQ_EXYNOS4_BUS_H */
diff --git a/drivers/devfreq/exynos/exynos5_bus.c b/drivers/devfreq/exynos/exynos5_bus.c
deleted file mode 100644
index 297ea30..0000000
--- a/drivers/devfreq/exynos/exynos5_bus.c
+++ /dev/null
@@ -1,431 +0,0 @@
-/*
- * Copyright (c) 2012 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * EXYNOS5 INT clock frequency scaling support using DEVFREQ framework
- * Based on work done by Jonghwan Choi <jhbird.choi@samsung.com>
- * Support for only EXYNOS5250 is present.
- *
- * 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.
- *
- */
-
-#include <linux/module.h>
-#include <linux/devfreq.h>
-#include <linux/io.h>
-#include <linux/pm_opp.h>
-#include <linux/slab.h>
-#include <linux/suspend.h>
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/platform_device.h>
-#include <linux/pm_qos.h>
-#include <linux/regulator/consumer.h>
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
-
-#include "exynos_ppmu.h"
-
-#define MAX_SAFEVOLT			1100000 /* 1.10V */
-/* Assume that the bus is saturated if the utilization is 25% */
-#define INT_BUS_SATURATION_RATIO	25
-
-enum int_level_idx {
-	LV_0,
-	LV_1,
-	LV_2,
-	LV_3,
-	LV_4,
-	_LV_END
-};
-
-enum exynos_ppmu_list {
-	PPMU_RIGHT,
-	PPMU_END,
-};
-
-struct busfreq_data_int {
-	struct device *dev;
-	struct devfreq *devfreq;
-	struct regulator *vdd_int;
-	struct busfreq_ppmu_data ppmu_data;
-	unsigned long curr_freq;
-	bool disabled;
-
-	struct notifier_block pm_notifier;
-	struct mutex lock;
-	struct pm_qos_request int_req;
-	struct clk *int_clk;
-};
-
-struct int_bus_opp_table {
-	unsigned int idx;
-	unsigned long clk;
-	unsigned long volt;
-};
-
-static struct int_bus_opp_table exynos5_int_opp_table[] = {
-	{LV_0, 266000, 1025000},
-	{LV_1, 200000, 1025000},
-	{LV_2, 160000, 1025000},
-	{LV_3, 133000, 1025000},
-	{LV_4, 100000, 1025000},
-	{0, 0, 0},
-};
-
-static int exynos5_int_setvolt(struct busfreq_data_int *data,
-				unsigned long volt)
-{
-	return regulator_set_voltage(data->vdd_int, volt, MAX_SAFEVOLT);
-}
-
-static int exynos5_busfreq_int_target(struct device *dev, unsigned long *_freq,
-			      u32 flags)
-{
-	int err = 0;
-	struct platform_device *pdev = container_of(dev, struct platform_device,
-						    dev);
-	struct busfreq_data_int *data = platform_get_drvdata(pdev);
-	struct dev_pm_opp *opp;
-	unsigned long old_freq, freq;
-	unsigned long volt;
-
-	rcu_read_lock();
-	opp = devfreq_recommended_opp(dev, _freq, flags);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
-		dev_err(dev, "%s: Invalid OPP.\n", __func__);
-		return PTR_ERR(opp);
-	}
-
-	freq = dev_pm_opp_get_freq(opp);
-	volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
-
-	old_freq = data->curr_freq;
-
-	if (old_freq == freq)
-		return 0;
-
-	dev_dbg(dev, "targeting %lukHz %luuV\n", freq, volt);
-
-	mutex_lock(&data->lock);
-
-	if (data->disabled)
-		goto out;
-
-	if (freq > exynos5_int_opp_table[0].clk)
-		pm_qos_update_request(&data->int_req, freq * 16 / 1000);
-	else
-		pm_qos_update_request(&data->int_req, -1);
-
-	if (old_freq < freq)
-		err = exynos5_int_setvolt(data, volt);
-	if (err)
-		goto out;
-
-	err = clk_set_rate(data->int_clk, freq * 1000);
-
-	if (err)
-		goto out;
-
-	if (old_freq > freq)
-		err = exynos5_int_setvolt(data, volt);
-	if (err)
-		goto out;
-
-	data->curr_freq = freq;
-out:
-	mutex_unlock(&data->lock);
-	return err;
-}
-
-static int exynos5_int_get_dev_status(struct device *dev,
-				      struct devfreq_dev_status *stat)
-{
-	struct platform_device *pdev = container_of(dev, struct platform_device,
-						    dev);
-	struct busfreq_data_int *data = platform_get_drvdata(pdev);
-	struct busfreq_ppmu_data *ppmu_data = &data->ppmu_data;
-	int busier_dmc;
-
-	exynos_read_ppmu(ppmu_data);
-	busier_dmc = exynos_get_busier_ppmu(ppmu_data);
-
-	stat->current_frequency = data->curr_freq;
-
-	/* Number of cycles spent on memory access */
-	stat->busy_time = ppmu_data->ppmu[busier_dmc].count[PPMU_PMNCNT3];
-	stat->busy_time *= 100 / INT_BUS_SATURATION_RATIO;
-	stat->total_time = ppmu_data->ppmu[busier_dmc].ccnt;
-
-	return 0;
-}
-
-static struct devfreq_dev_profile exynos5_devfreq_int_profile = {
-	.initial_freq		= 160000,
-	.polling_ms		= 100,
-	.target			= exynos5_busfreq_int_target,
-	.get_dev_status		= exynos5_int_get_dev_status,
-};
-
-static int exynos5250_init_int_tables(struct busfreq_data_int *data)
-{
-	int i, err = 0;
-
-	for (i = LV_0; i < _LV_END; i++) {
-		err = dev_pm_opp_add(data->dev, exynos5_int_opp_table[i].clk,
-				exynos5_int_opp_table[i].volt);
-		if (err) {
-			dev_err(data->dev, "Cannot add opp entries.\n");
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-static int exynos5_busfreq_int_pm_notifier_event(struct notifier_block *this,
-		unsigned long event, void *ptr)
-{
-	struct busfreq_data_int *data = container_of(this,
-					struct busfreq_data_int, pm_notifier);
-	struct dev_pm_opp *opp;
-	unsigned long maxfreq = ULONG_MAX;
-	unsigned long freq;
-	unsigned long volt;
-	int err = 0;
-
-	switch (event) {
-	case PM_SUSPEND_PREPARE:
-		/* Set Fastest and Deactivate DVFS */
-		mutex_lock(&data->lock);
-
-		data->disabled = true;
-
-		rcu_read_lock();
-		opp = dev_pm_opp_find_freq_floor(data->dev, &maxfreq);
-		if (IS_ERR(opp)) {
-			rcu_read_unlock();
-			err = PTR_ERR(opp);
-			goto unlock;
-		}
-		freq = dev_pm_opp_get_freq(opp);
-		volt = dev_pm_opp_get_voltage(opp);
-		rcu_read_unlock();
-
-		err = exynos5_int_setvolt(data, volt);
-		if (err)
-			goto unlock;
-
-		err = clk_set_rate(data->int_clk, freq * 1000);
-
-		if (err)
-			goto unlock;
-
-		data->curr_freq = freq;
-unlock:
-		mutex_unlock(&data->lock);
-		if (err)
-			return NOTIFY_BAD;
-		return NOTIFY_OK;
-	case PM_POST_RESTORE:
-	case PM_POST_SUSPEND:
-		/* Reactivate */
-		mutex_lock(&data->lock);
-		data->disabled = false;
-		mutex_unlock(&data->lock);
-		return NOTIFY_OK;
-	}
-
-	return NOTIFY_DONE;
-}
-
-static int exynos5_busfreq_int_probe(struct platform_device *pdev)
-{
-	struct busfreq_data_int *data;
-	struct busfreq_ppmu_data *ppmu_data;
-	struct dev_pm_opp *opp;
-	struct device *dev = &pdev->dev;
-	struct device_node *np;
-	unsigned long initial_freq;
-	unsigned long initial_volt;
-	int err = 0;
-	int i;
-
-	data = devm_kzalloc(&pdev->dev, sizeof(struct busfreq_data_int),
-				GFP_KERNEL);
-	if (data == NULL) {
-		dev_err(dev, "Cannot allocate memory.\n");
-		return -ENOMEM;
-	}
-
-	ppmu_data = &data->ppmu_data;
-	ppmu_data->ppmu_end = PPMU_END;
-	ppmu_data->ppmu = devm_kzalloc(dev,
-				       sizeof(struct exynos_ppmu) * PPMU_END,
-				       GFP_KERNEL);
-	if (!ppmu_data->ppmu) {
-		dev_err(dev, "Failed to allocate memory for exynos_ppmu\n");
-		return -ENOMEM;
-	}
-
-	np = of_find_compatible_node(NULL, NULL, "samsung,exynos5250-ppmu");
-	if (np == NULL) {
-		pr_err("Unable to find PPMU node\n");
-		return -ENOENT;
-	}
-
-	for (i = 0; i < ppmu_data->ppmu_end; i++) {
-		/* map PPMU memory region */
-		ppmu_data->ppmu[i].hw_base = of_iomap(np, i);
-		if (ppmu_data->ppmu[i].hw_base == NULL) {
-			dev_err(&pdev->dev, "failed to map memory region\n");
-			return -ENOMEM;
-		}
-	}
-	data->pm_notifier.notifier_call = exynos5_busfreq_int_pm_notifier_event;
-	data->dev = dev;
-	mutex_init(&data->lock);
-
-	err = exynos5250_init_int_tables(data);
-	if (err)
-		return err;
-
-	data->vdd_int = devm_regulator_get(dev, "vdd_int");
-	if (IS_ERR(data->vdd_int)) {
-		dev_err(dev, "Cannot get the regulator \"vdd_int\"\n");
-		return PTR_ERR(data->vdd_int);
-	}
-
-	data->int_clk = devm_clk_get(dev, "int_clk");
-	if (IS_ERR(data->int_clk)) {
-		dev_err(dev, "Cannot get clock \"int_clk\"\n");
-		return PTR_ERR(data->int_clk);
-	}
-
-	rcu_read_lock();
-	opp = dev_pm_opp_find_freq_floor(dev,
-			&exynos5_devfreq_int_profile.initial_freq);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
-		dev_err(dev, "Invalid initial frequency %lu kHz.\n",
-		       exynos5_devfreq_int_profile.initial_freq);
-		return PTR_ERR(opp);
-	}
-	initial_freq = dev_pm_opp_get_freq(opp);
-	initial_volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
-	data->curr_freq = initial_freq;
-
-	err = clk_set_rate(data->int_clk, initial_freq * 1000);
-	if (err) {
-		dev_err(dev, "Failed to set initial frequency\n");
-		return err;
-	}
-
-	err = exynos5_int_setvolt(data, initial_volt);
-	if (err)
-		return err;
-
-	platform_set_drvdata(pdev, data);
-
-	busfreq_mon_reset(ppmu_data);
-
-	data->devfreq = devm_devfreq_add_device(dev, &exynos5_devfreq_int_profile,
-					   "simple_ondemand", NULL);
-	if (IS_ERR(data->devfreq))
-		return PTR_ERR(data->devfreq);
-
-	err = devm_devfreq_register_opp_notifier(dev, data->devfreq);
-	if (err < 0) {
-		dev_err(dev, "Failed to register opp notifier\n");
-		return err;
-	}
-
-	err = register_pm_notifier(&data->pm_notifier);
-	if (err) {
-		dev_err(dev, "Failed to setup pm notifier\n");
-		return err;
-	}
-
-	/* TODO: Add a new QOS class for int/mif bus */
-	pm_qos_add_request(&data->int_req, PM_QOS_NETWORK_THROUGHPUT, -1);
-
-	return 0;
-}
-
-static int exynos5_busfreq_int_remove(struct platform_device *pdev)
-{
-	struct busfreq_data_int *data = platform_get_drvdata(pdev);
-
-	pm_qos_remove_request(&data->int_req);
-	unregister_pm_notifier(&data->pm_notifier);
-
-	return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int exynos5_busfreq_int_resume(struct device *dev)
-{
-	struct platform_device *pdev = container_of(dev, struct platform_device,
-						    dev);
-	struct busfreq_data_int *data = platform_get_drvdata(pdev);
-	struct busfreq_ppmu_data *ppmu_data = &data->ppmu_data;
-
-	busfreq_mon_reset(ppmu_data);
-	return 0;
-}
-static const struct dev_pm_ops exynos5_busfreq_int_pm = {
-	.resume	= exynos5_busfreq_int_resume,
-};
-#endif
-static SIMPLE_DEV_PM_OPS(exynos5_busfreq_int_pm_ops, NULL,
-			 exynos5_busfreq_int_resume);
-
-/* platform device pointer for exynos5 devfreq device. */
-static struct platform_device *exynos5_devfreq_pdev;
-
-static struct platform_driver exynos5_busfreq_int_driver = {
-	.probe		= exynos5_busfreq_int_probe,
-	.remove		= exynos5_busfreq_int_remove,
-	.driver		= {
-		.name		= "exynos5-bus-int",
-		.pm		= &exynos5_busfreq_int_pm_ops,
-	},
-};
-
-static int __init exynos5_busfreq_int_init(void)
-{
-	int ret;
-
-	ret = platform_driver_register(&exynos5_busfreq_int_driver);
-	if (ret < 0)
-		goto out;
-
-	exynos5_devfreq_pdev =
-		platform_device_register_simple("exynos5-bus-int", -1, NULL, 0);
-	if (IS_ERR(exynos5_devfreq_pdev)) {
-		ret = PTR_ERR(exynos5_devfreq_pdev);
-		goto out1;
-	}
-
-	return 0;
-out1:
-	platform_driver_unregister(&exynos5_busfreq_int_driver);
-out:
-	return ret;
-}
-late_initcall(exynos5_busfreq_int_init);
-
-static void __exit exynos5_busfreq_int_exit(void)
-{
-	platform_device_unregister(exynos5_devfreq_pdev);
-	platform_driver_unregister(&exynos5_busfreq_int_driver);
-}
-module_exit(exynos5_busfreq_int_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("EXYNOS5 busfreq driver with devfreq framework");
diff --git a/drivers/devfreq/exynos/exynos_ppmu.c b/drivers/devfreq/exynos/exynos_ppmu.c
deleted file mode 100644
index 97b75e5..0000000
--- a/drivers/devfreq/exynos/exynos_ppmu.c
+++ /dev/null
@@ -1,119 +0,0 @@
-/*
- * Copyright (c) 2012 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * EXYNOS - PPMU support
- *
- * 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.
- */
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/io.h>
-
-#include "exynos_ppmu.h"
-
-void exynos_ppmu_reset(void __iomem *ppmu_base)
-{
-	__raw_writel(PPMU_CYCLE_RESET | PPMU_COUNTER_RESET, ppmu_base);
-	__raw_writel(PPMU_ENABLE_CYCLE  |
-		     PPMU_ENABLE_COUNT0 |
-		     PPMU_ENABLE_COUNT1 |
-		     PPMU_ENABLE_COUNT2 |
-		     PPMU_ENABLE_COUNT3,
-		     ppmu_base + PPMU_CNTENS);
-}
-
-void exynos_ppmu_setevent(void __iomem *ppmu_base, unsigned int ch,
-			unsigned int evt)
-{
-	__raw_writel(evt, ppmu_base + PPMU_BEVTSEL(ch));
-}
-
-void exynos_ppmu_start(void __iomem *ppmu_base)
-{
-	__raw_writel(PPMU_ENABLE, ppmu_base);
-}
-
-void exynos_ppmu_stop(void __iomem *ppmu_base)
-{
-	__raw_writel(PPMU_DISABLE, ppmu_base);
-}
-
-unsigned int exynos_ppmu_read(void __iomem *ppmu_base, unsigned int ch)
-{
-	unsigned int total;
-
-	if (ch == PPMU_PMNCNT3)
-		total = ((__raw_readl(ppmu_base + PMCNT_OFFSET(ch)) << 8) |
-			  __raw_readl(ppmu_base + PMCNT_OFFSET(ch + 1)));
-	else
-		total = __raw_readl(ppmu_base + PMCNT_OFFSET(ch));
-
-	return total;
-}
-
-void busfreq_mon_reset(struct busfreq_ppmu_data *ppmu_data)
-{
-	unsigned int i;
-
-	for (i = 0; i < ppmu_data->ppmu_end; i++) {
-		void __iomem *ppmu_base = ppmu_data->ppmu[i].hw_base;
-
-		/* Reset the performance and cycle counters */
-		exynos_ppmu_reset(ppmu_base);
-
-		/* Setup count registers to monitor read/write transactions */
-		ppmu_data->ppmu[i].event[PPMU_PMNCNT3] = RDWR_DATA_COUNT;
-		exynos_ppmu_setevent(ppmu_base, PPMU_PMNCNT3,
-					ppmu_data->ppmu[i].event[PPMU_PMNCNT3]);
-
-		exynos_ppmu_start(ppmu_base);
-	}
-}
-EXPORT_SYMBOL(busfreq_mon_reset);
-
-void exynos_read_ppmu(struct busfreq_ppmu_data *ppmu_data)
-{
-	int i, j;
-
-	for (i = 0; i < ppmu_data->ppmu_end; i++) {
-		void __iomem *ppmu_base = ppmu_data->ppmu[i].hw_base;
-
-		exynos_ppmu_stop(ppmu_base);
-
-		/* Update local data from PPMU */
-		ppmu_data->ppmu[i].ccnt = __raw_readl(ppmu_base + PPMU_CCNT);
-
-		for (j = PPMU_PMNCNT0; j < PPMU_PMNCNT_MAX; j++) {
-			if (ppmu_data->ppmu[i].event[j] == 0)
-				ppmu_data->ppmu[i].count[j] = 0;
-			else
-				ppmu_data->ppmu[i].count[j] =
-					exynos_ppmu_read(ppmu_base, j);
-		}
-	}
-
-	busfreq_mon_reset(ppmu_data);
-}
-EXPORT_SYMBOL(exynos_read_ppmu);
-
-int exynos_get_busier_ppmu(struct busfreq_ppmu_data *ppmu_data)
-{
-	unsigned int count = 0;
-	int i, j, busy = 0;
-
-	for (i = 0; i < ppmu_data->ppmu_end; i++) {
-		for (j = PPMU_PMNCNT0; j < PPMU_PMNCNT_MAX; j++) {
-			if (ppmu_data->ppmu[i].count[j] > count) {
-				count = ppmu_data->ppmu[i].count[j];
-				busy = i;
-			}
-		}
-	}
-
-	return busy;
-}
-EXPORT_SYMBOL(exynos_get_busier_ppmu);
diff --git a/drivers/devfreq/exynos/exynos_ppmu.h b/drivers/devfreq/exynos/exynos_ppmu.h
deleted file mode 100644
index 71f17ba..0000000
--- a/drivers/devfreq/exynos/exynos_ppmu.h
+++ /dev/null
@@ -1,86 +0,0 @@
-/*
- * Copyright (c) 2012 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com/
- *
- * EXYNOS PPMU header
- *
- * 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 __DEVFREQ_EXYNOS_PPMU_H
-#define __DEVFREQ_EXYNOS_PPMU_H __FILE__
-
-#include <linux/ktime.h>
-
-/* For PPMU Control */
-#define PPMU_ENABLE             BIT(0)
-#define PPMU_DISABLE            0x0
-#define PPMU_CYCLE_RESET        BIT(1)
-#define PPMU_COUNTER_RESET      BIT(2)
-
-#define PPMU_ENABLE_COUNT0      BIT(0)
-#define PPMU_ENABLE_COUNT1      BIT(1)
-#define PPMU_ENABLE_COUNT2      BIT(2)
-#define PPMU_ENABLE_COUNT3      BIT(3)
-#define PPMU_ENABLE_CYCLE       BIT(31)
-
-#define PPMU_CNTENS		0x10
-#define PPMU_FLAG		0x50
-#define PPMU_CCNT_OVERFLOW	BIT(31)
-#define PPMU_CCNT		0x100
-
-#define PPMU_PMCNT0		0x110
-#define PPMU_PMCNT_OFFSET	0x10
-#define PMCNT_OFFSET(x)		(PPMU_PMCNT0 + (PPMU_PMCNT_OFFSET * x))
-
-#define PPMU_BEVT0SEL		0x1000
-#define PPMU_BEVTSEL_OFFSET	0x100
-#define PPMU_BEVTSEL(x)		(PPMU_BEVT0SEL + (ch * PPMU_BEVTSEL_OFFSET))
-
-/* For Event Selection */
-#define RD_DATA_COUNT		0x5
-#define WR_DATA_COUNT		0x6
-#define RDWR_DATA_COUNT		0x7
-
-enum ppmu_counter {
-	PPMU_PMNCNT0,
-	PPMU_PMCCNT1,
-	PPMU_PMNCNT2,
-	PPMU_PMNCNT3,
-	PPMU_PMNCNT_MAX,
-};
-
-struct bus_opp_table {
-	unsigned int idx;
-	unsigned long clk;
-	unsigned long volt;
-};
-
-struct exynos_ppmu {
-	void __iomem *hw_base;
-	unsigned int ccnt;
-	unsigned int event[PPMU_PMNCNT_MAX];
-	unsigned int count[PPMU_PMNCNT_MAX];
-	unsigned long long ns;
-	ktime_t reset_time;
-	bool ccnt_overflow;
-	bool count_overflow[PPMU_PMNCNT_MAX];
-};
-
-struct busfreq_ppmu_data {
-	struct exynos_ppmu *ppmu;
-	int ppmu_end;
-};
-
-void exynos_ppmu_reset(void __iomem *ppmu_base);
-void exynos_ppmu_setevent(void __iomem *ppmu_base, unsigned int ch,
-			unsigned int evt);
-void exynos_ppmu_start(void __iomem *ppmu_base);
-void exynos_ppmu_stop(void __iomem *ppmu_base);
-unsigned int exynos_ppmu_read(void __iomem *ppmu_base, unsigned int ch);
-void busfreq_mon_reset(struct busfreq_ppmu_data *ppmu_data);
-void exynos_read_ppmu(struct busfreq_ppmu_data *ppmu_data);
-int exynos_get_busier_ppmu(struct busfreq_ppmu_data *ppmu_data);
-#endif /* __DEVFREQ_EXYNOS_PPMU_H */
diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c
new file mode 100644
index 0000000..9ef46e2
--- /dev/null
+++ b/drivers/devfreq/governor_passive.c
@@ -0,0 +1,205 @@
+/*
+ * linux/drivers/devfreq/governor_passive.c
+ *
+ * Copyright (C) 2016 Samsung Electronics
+ * Author: Chanwoo Choi <cw00.choi@samsung.com>
+ * Author: MyungJoo Ham <myungjoo.ham@samsung.com>
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/devfreq.h>
+#include "governor.h"
+
+static int devfreq_passive_get_target_freq(struct devfreq *devfreq,
+					unsigned long *freq)
+{
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	struct devfreq *parent_devfreq = (struct devfreq *)p_data->parent;
+	unsigned long child_freq = ULONG_MAX;
+	struct dev_pm_opp *opp;
+	int i, count, ret = 0;
+
+	/*
+	 * If the devfreq device with passive governor has the specific method
+	 * to determine the next frequency, should use the get_target_freq()
+	 * of struct devfreq_passive_data.
+	 */
+	if (p_data->get_target_freq) {
+		ret = p_data->get_target_freq(devfreq, freq);
+		goto out;
+	}
+
+	/*
+	 * If the parent and passive devfreq device uses the OPP table,
+	 * get the next frequency by using the OPP table.
+	 */
+
+	/*
+	 * - parent devfreq device uses the governors except for passive.
+	 * - passive devfreq device uses the passive governor.
+	 *
+	 * Each devfreq has the OPP table. After deciding the new frequency
+	 * from the governor of parent devfreq device, the passive governor
+	 * need to get the index of new frequency on OPP table of parent
+	 * device. And then the index is used for getting the suitable
+	 * new frequency for passive devfreq device.
+	 */
+	if (!devfreq->profile || !devfreq->profile->freq_table
+		|| devfreq->profile->max_state <= 0)
+		return -EINVAL;
+
+	/*
+	 * The passive governor have to get the correct frequency from OPP
+	 * list of parent device. Because in this case, *freq is temporary
+	 * value which is decided by ondemand governor.
+	 */
+	rcu_read_lock();
+	opp = devfreq_recommended_opp(parent_devfreq->dev.parent, freq, 0);
+	rcu_read_unlock();
+	if (IS_ERR(opp)) {
+		ret = PTR_ERR(opp);
+		goto out;
+	}
+
+	/*
+	 * Get the OPP table's index of decided freqeuncy by governor
+	 * of parent device.
+	 */
+	for (i = 0; i < parent_devfreq->profile->max_state; i++)
+		if (parent_devfreq->profile->freq_table[i] == *freq)
+			break;
+
+	if (i == parent_devfreq->profile->max_state) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Get the suitable frequency by using index of parent device. */
+	if (i < devfreq->profile->max_state) {
+		child_freq = devfreq->profile->freq_table[i];
+	} else {
+		count = devfreq->profile->max_state;
+		child_freq = devfreq->profile->freq_table[count - 1];
+	}
+
+	/* Return the suitable frequency for passive device. */
+	*freq = child_freq;
+
+out:
+	return ret;
+}
+
+static int update_devfreq_passive(struct devfreq *devfreq, unsigned long freq)
+{
+	int ret;
+
+	if (!devfreq->governor)
+		return -EINVAL;
+
+	mutex_lock_nested(&devfreq->lock, SINGLE_DEPTH_NESTING);
+
+	ret = devfreq->governor->get_target_freq(devfreq, &freq);
+	if (ret < 0)
+		goto out;
+
+	ret = devfreq->profile->target(devfreq->dev.parent, &freq, 0);
+	if (ret < 0)
+		goto out;
+
+	devfreq->previous_freq = freq;
+
+out:
+	mutex_unlock(&devfreq->lock);
+
+	return 0;
+}
+
+static int devfreq_passive_notifier_call(struct notifier_block *nb,
+				unsigned long event, void *ptr)
+{
+	struct devfreq_passive_data *data
+			= container_of(nb, struct devfreq_passive_data, nb);
+	struct devfreq *devfreq = (struct devfreq *)data->this;
+	struct devfreq *parent = (struct devfreq *)data->parent;
+	struct devfreq_freqs *freqs = (struct devfreq_freqs *)ptr;
+	unsigned long freq = freqs->new;
+
+	switch (event) {
+	case DEVFREQ_PRECHANGE:
+		if (parent->previous_freq > freq)
+			update_devfreq_passive(devfreq, freq);
+		break;
+	case DEVFREQ_POSTCHANGE:
+		if (parent->previous_freq < freq)
+			update_devfreq_passive(devfreq, freq);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int devfreq_passive_event_handler(struct devfreq *devfreq,
+				unsigned int event, void *data)
+{
+	struct device *dev = devfreq->dev.parent;
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	struct devfreq *parent = (struct devfreq *)p_data->parent;
+	struct notifier_block *nb = &p_data->nb;
+	int ret = 0;
+
+	if (!parent)
+		return -EPROBE_DEFER;
+
+	switch (event) {
+	case DEVFREQ_GOV_START:
+		if (!p_data->this)
+			p_data->this = devfreq;
+
+		nb->notifier_call = devfreq_passive_notifier_call;
+		ret = devm_devfreq_register_notifier(dev, parent, nb,
+					DEVFREQ_TRANSITION_NOTIFIER);
+		break;
+	case DEVFREQ_GOV_STOP:
+		devm_devfreq_unregister_notifier(dev, parent, nb,
+					DEVFREQ_TRANSITION_NOTIFIER);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static struct devfreq_governor devfreq_passive = {
+	.name = "passive",
+	.get_target_freq = devfreq_passive_get_target_freq,
+	.event_handler = devfreq_passive_event_handler,
+};
+
+static int __init devfreq_passive_init(void)
+{
+	return devfreq_add_governor(&devfreq_passive);
+}
+subsys_initcall(devfreq_passive_init);
+
+static void __exit devfreq_passive_exit(void)
+{
+	int ret;
+
+	ret = devfreq_remove_governor(&devfreq_passive);
+	if (ret)
+		pr_err("%s: failed remove governor %d\n", __func__, ret);
+}
+module_exit(devfreq_passive_exit);
+
+MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>");
+MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
+MODULE_DESCRIPTION("DEVFREQ Passive governor");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c
index b5d0580..fa4ea22 100644
--- a/drivers/firmware/psci.c
+++ b/drivers/firmware/psci.c
@@ -355,7 +355,7 @@ int psci_cpu_suspend_enter(unsigned long index)
 
 /* ARM specific CPU idle operations */
 #ifdef CONFIG_ARM
-static struct cpuidle_ops psci_cpuidle_ops __initdata = {
+static const struct cpuidle_ops psci_cpuidle_ops __initconst = {
 	.suspend = psci_cpu_suspend_enter,
 	.init = psci_dt_cpu_init_idle,
 };
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index c6935de..c966492 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -766,6 +766,67 @@ static struct cpuidle_state knl_cstates[] = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state bxt_cstates[] = {
+	{
+		.name = "C1-BXT",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00),
+		.exit_latency = 2,
+		.target_residency = 2,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.name = "C1E-BXT",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01),
+		.exit_latency = 10,
+		.target_residency = 20,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.name = "C6-BXT",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 133,
+		.target_residency = 133,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.name = "C7s-BXT",
+		.desc = "MWAIT 0x31",
+		.flags = MWAIT2flg(0x31) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 155,
+		.target_residency = 155,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.name = "C8-BXT",
+		.desc = "MWAIT 0x40",
+		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 1000,
+		.target_residency = 1000,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.name = "C9-BXT",
+		.desc = "MWAIT 0x50",
+		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 2000,
+		.target_residency = 2000,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.name = "C10-BXT",
+		.desc = "MWAIT 0x60",
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 10000,
+		.target_residency = 10000,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.enter = NULL }
+};
+
 /**
  * intel_idle
  * @dev: cpuidle_device
@@ -950,6 +1011,11 @@ static const struct idle_cpu idle_cpu_knl = {
 	.state_table = knl_cstates,
 };
 
+static const struct idle_cpu idle_cpu_bxt = {
+	.state_table = bxt_cstates,
+	.disable_promotion_to_c1e = true,
+};
+
 #define ICPU(model, cpu) \
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (unsigned long)&cpu }
 
@@ -985,6 +1051,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	ICPU(0x9e, idle_cpu_skl),
 	ICPU(0x55, idle_cpu_skx),
 	ICPU(0x57, idle_cpu_knl),
+	ICPU(0x5c, idle_cpu_bxt),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
@@ -1075,6 +1142,73 @@ static void ivt_idle_state_table_update(void)
 
 	/* else, 1 and 2 socket systems use default ivt_cstates */
 }
+
+/*
+ * Translate IRTL (Interrupt Response Time Limit) MSR to usec
+ */
+
+static unsigned int irtl_ns_units[] = {
+	1, 32, 1024, 32768, 1048576, 33554432, 0, 0 };
+
+static unsigned long long irtl_2_usec(unsigned long long irtl)
+{
+	unsigned long long ns;
+
+	ns = irtl_ns_units[(irtl >> 10) & 0x3];
+
+	return div64_u64((irtl & 0x3FF) * ns, 1000);
+}
+/*
+ * bxt_idle_state_table_update(void)
+ *
+ * On BXT, we trust the IRTL to show the definitive maximum latency
+ * We use the same value for target_residency.
+ */
+static void bxt_idle_state_table_update(void)
+{
+	unsigned long long msr;
+
+	rdmsrl(MSR_PKGC6_IRTL, msr);
+	if (msr) {
+		unsigned int usec = irtl_2_usec(msr);
+
+		bxt_cstates[2].exit_latency = usec;
+		bxt_cstates[2].target_residency = usec;
+	}
+
+	rdmsrl(MSR_PKGC7_IRTL, msr);
+	if (msr) {
+		unsigned int usec = irtl_2_usec(msr);
+
+		bxt_cstates[3].exit_latency = usec;
+		bxt_cstates[3].target_residency = usec;
+	}
+
+	rdmsrl(MSR_PKGC8_IRTL, msr);
+	if (msr) {
+		unsigned int usec = irtl_2_usec(msr);
+
+		bxt_cstates[4].exit_latency = usec;
+		bxt_cstates[4].target_residency = usec;
+	}
+
+	rdmsrl(MSR_PKGC9_IRTL, msr);
+	if (msr) {
+		unsigned int usec = irtl_2_usec(msr);
+
+		bxt_cstates[5].exit_latency = usec;
+		bxt_cstates[5].target_residency = usec;
+	}
+
+	rdmsrl(MSR_PKGC10_IRTL, msr);
+	if (msr) {
+		unsigned int usec = irtl_2_usec(msr);
+
+		bxt_cstates[6].exit_latency = usec;
+		bxt_cstates[6].target_residency = usec;
+	}
+
+}
 /*
  * sklh_idle_state_table_update(void)
  *
@@ -1130,6 +1264,9 @@ static void intel_idle_state_table_update(void)
 	case 0x3e: /* IVT */
 		ivt_idle_state_table_update();
 		break;
+	case 0x5c: /* BXT */
+		bxt_idle_state_table_update();
+		break;
 	case 0x5e: /* SKL-H */
 		sklh_idle_state_table_update();
 		break;
diff --git a/drivers/mmc/host/toshsd.c b/drivers/mmc/host/toshsd.c
index e2cdd5f..553ef41 100644
--- a/drivers/mmc/host/toshsd.c
+++ b/drivers/mmc/host/toshsd.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/pm.h>
+#include <linux/pm_runtime.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
 
diff --git a/drivers/power/avs/rockchip-io-domain.c b/drivers/power/avs/rockchip-io-domain.c
index 8986382..01b6d3f 100644
--- a/drivers/power/avs/rockchip-io-domain.c
+++ b/drivers/power/avs/rockchip-io-domain.c
@@ -336,6 +336,7 @@ static int rockchip_iodomain_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	const struct of_device_id *match;
 	struct rockchip_iodomain *iod;
+	struct device *parent;
 	int i, ret = 0;
 
 	if (!np)
@@ -351,7 +352,14 @@ static int rockchip_iodomain_probe(struct platform_device *pdev)
 	match = of_match_node(rockchip_iodomain_match, np);
 	iod->soc_data = (struct rockchip_iodomain_soc_data *)match->data;
 
-	iod->grf = syscon_regmap_lookup_by_phandle(np, "rockchip,grf");
+	parent = pdev->dev.parent;
+	if (parent && parent->of_node) {
+		iod->grf = syscon_node_to_regmap(parent->of_node);
+	} else {
+		dev_dbg(&pdev->dev, "falling back to old binding\n");
+		iod->grf = syscon_regmap_lookup_by_phandle(np, "rockchip,grf");
+	}
+
 	if (IS_ERR(iod->grf)) {
 		dev_err(&pdev->dev, "couldn't find grf regmap\n");
 		return PTR_ERR(iod->grf);
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index f2201d4..b2766b8 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -1115,6 +1115,8 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	RAPL_CPU(0X5C, rapl_defaults_core),/* Broxton */
 	RAPL_CPU(0x5E, rapl_defaults_core),/* Skylake-H/S */
 	RAPL_CPU(0x57, rapl_defaults_hsw_server),/* Knights Landing */
+	RAPL_CPU(0x8E, rapl_defaults_core),/* Kabylake */
+	RAPL_CPU(0x9E, rapl_defaults_core),/* Kabylake */
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_ids);
diff --git a/drivers/soc/qcom/spm.c b/drivers/soc/qcom/spm.c
index 5548a31..1fcbb22 100644
--- a/drivers/soc/qcom/spm.c
+++ b/drivers/soc/qcom/spm.c
@@ -274,7 +274,7 @@ check_spm:
 	return per_cpu(cpu_spm_drv, cpu) ? 0 : -ENXIO;
 }
 
-static struct cpuidle_ops qcom_cpuidle_ops __initdata = {
+static const struct cpuidle_ops qcom_cpuidle_ops __initconst = {
 	.suspend = qcom_idle_enter,
 	.init = qcom_cpuidle_init,
 };