Merge tag 'pm-4.11-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 Operating Performance Points (OPP)
  framework and cpufreq this time, followed by devfreq and some
  scattered updates all over.

  The OPP changes are mostly related to switching over from RCU-based
  synchronization, that turned out to be overly complicated and
  problematic, to reference counting using krefs.

  In the cpufreq land there are core cleanups, documentation updates, a
  new driver for Broadcom BMIPS SoCs, a new cpufreq-dt sub-driver for TI
  SoCs that require special handling, ARM64 SoCs support for the qoriq
  driver, intel_pstate updates, powernv driver update and assorted
  fixes.

  The devfreq changes are mostly fixes related to the sysfs interface
  and some Exynos drivers updates.

  Apart from that, the cpuidle menu governor will support per-CPU PM QoS
  constraints for the wakeup latency now, some bugs in the wakeup IRQs
  framework are fixed, the generic power domains framework should handle
  asynchronous invocations of *noirq suspend/resume callbacks from now
  on, the analyze_suspend.py script is updated and there is a new tool
  for intel_pstate diagnostics.

  Specifics:

   - Operating Performance Points (OPP) framework fixes, cleanups and
     switch over from RCU-based synchronization to reference counting
     using krefs (Viresh Kumar, Wei Yongjun, Dave Gerlach)

   - cpufreq core cleanups and documentation updates (Viresh Kumar,
     Rafael Wysocki)

   - New cpufreq driver for Broadcom BMIPS SoCs (Markus Mayer)

   - New cpufreq-dt sub-driver for TI SoCs requiring special handling,
     like in the AM335x, AM437x, DRA7x, and AM57x families, along with
     new DT bindings for it (Dave Gerlach, Paul Gortmaker)

   - ARM64 SoCs support for the qoriq cpufreq driver (Tang Yuantian)

   - intel_pstate driver updates including a new sysfs knob to control
     the driver's operation mode and fixes related to the no_turbo sysfs
     knob and the hardware-managed P-states feature support (Rafael
     Wysocki, Srinivas Pandruvada)

   - New interface to export ultra-turbo frequencies for the powernv
     cpufreq driver (Shilpasri Bhat)

   - Assorted fixes for cpufreq drivers (Arnd Bergmann, Dan Carpenter,
     Wei Yongjun)

   - devfreq core fixes, mostly related to the sysfs interface exported
     by it (Chanwoo Choi, Chris Diamand)

   - Updates of the exynos-bus and exynos-ppmu devfreq drivers (Chanwoo
     Choi)

   - Device PM QoS extension to support CPUs and support for per-CPU
     wakeup (device resume) latency constraints in the cpuidle menu
     governor (Alex Shi)

   - Wakeup IRQs framework fixes (Grygorii Strashko)

   - Generic power domains framework update including a fix to make it
     handle asynchronous invocations of *noirq suspend/resume callbacks
     correctly (Ulf Hansson, Geert Uytterhoeven)

   - Assorted fixes and cleanups in the core suspend/hibernate code, PM
     QoS framework and x86 ACPI idle support code (Corentin Labbe, Geert
     Uytterhoeven, Geliang Tang, John Keeping, Nick Desaulniers)

   - Update of the analyze_suspend.py script is updated to version 4.5
     offering multiple improvements (Todd Brandt)

   - New tool for intel_pstate diagnostics using the pstate_sample
     tracepoint (Doug Smythies)"

* tag 'pm-4.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (85 commits)
  MAINTAINERS: cpufreq: add bmips-cpufreq.c
  PM / QoS: Fix memory leak on resume_latency.notifiers
  PM / Documentation: Spelling s/wrtie/write/
  PM / sleep: Fix test_suspend after sleep state rework
  cpufreq: CPPC: add ACPI_PROCESSOR dependency
  cpufreq: make ti-cpufreq explicitly non-modular
  cpufreq: Do not clear real_cpus mask on policy init
  tools/power/x86: Debug utility for intel_pstate driver
  AnalyzeSuspend: fix drag and zoom bug in javascript
  PM / wakeirq: report a wakeup_event on dedicated wekup irq
  PM / wakeirq: Fix spurious wake-up events for dedicated wakeirqs
  PM / wakeirq: Enable dedicated wakeirq for suspend
  cpufreq: dt: Don't use generic platdev driver for ti-cpufreq platforms
  cpufreq: ti: Add cpufreq driver to determine available OPPs at runtime
  Documentation: dt: add bindings for ti-cpufreq
  PM / OPP: Expose _of_get_opp_desc_node as dev_pm_opp API
  cpufreq: qoriq: Don't look at clock implementation details
  cpufreq: qoriq: add ARM64 SoCs support
  PM / Domains: Provide dummy governors if CONFIG_PM_GENERIC_DOMAINS=n
  cpufreq: brcmstb-avs-cpufreq: remove unnecessary platform_set_drvdata()
  ...

42 files changed, 1825 insertions, 1330 deletions

diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index f0b4a981b8d3..18b72eec3507 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -75,10 +75,8 @@ static int acpi_processor_ppc_notifier(struct notifier_block *nb,
 	struct acpi_processor *pr;
 	unsigned int ppc = 0;
 
-	if (event == CPUFREQ_START && ignore_ppc <= 0) {
+	if (ignore_ppc < 0)
 		ignore_ppc = 0;
-		return 0;
-	}
 
 	if (ignore_ppc)
 		return 0;
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 4c28e1a09786..2c3b359b3536 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -17,6 +17,7 @@
 #include <linux/of.h>
 #include <linux/cpufeature.h>
 #include <linux/tick.h>
+#include <linux/pm_qos.h>
 
 #include "base.h"
 
@@ -376,6 +377,7 @@ int register_cpu(struct cpu *cpu, int num)
 
 	per_cpu(cpu_sys_devices, num) = &cpu->dev;
 	register_cpu_under_node(num, cpu_to_node(num));
+	dev_pm_qos_expose_latency_limit(&cpu->dev, 0);
 
 	return 0;
 }
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 2997026b4dfb..3a75fb1b4126 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -130,7 +130,7 @@ static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
 
 	ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd);
 
-	/* Warn once for each IRQ safe dev in no sleep domain */
+	/* Warn once if IRQ safe dev in no sleep domain */
 	if (ret)
 		dev_warn_once(dev, "PM domain %s will not be powered off\n",
 				genpd->name);
@@ -201,7 +201,7 @@ static void genpd_sd_counter_inc(struct generic_pm_domain *genpd)
 	smp_mb__after_atomic();
 }
 
-static int genpd_power_on(struct generic_pm_domain *genpd, bool timed)
+static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 {
 	unsigned int state_idx = genpd->state_idx;
 	ktime_t time_start;
@@ -231,7 +231,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 	return ret;
 }
 
-static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
+static int _genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 {
 	unsigned int state_idx = genpd->state_idx;
 	ktime_t time_start;
@@ -262,10 +262,10 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 }
 
 /**
- * genpd_queue_power_off_work - Queue up the execution of genpd_poweroff().
+ * genpd_queue_power_off_work - Queue up the execution of genpd_power_off().
  * @genpd: PM domain to power off.
  *
- * Queue up the execution of genpd_poweroff() unless it's already been done
+ * Queue up the execution of genpd_power_off() unless it's already been done
  * before.
  */
 static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
@@ -274,14 +274,14 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
 }
 
 /**
- * genpd_poweron - Restore power to a given PM domain and its masters.
+ * genpd_power_on - Restore power to a given PM domain and its masters.
  * @genpd: PM domain to power up.
  * @depth: nesting count for lockdep.
  *
  * Restore power to @genpd and all of its masters so that it is possible to
  * resume a device belonging to it.
  */
-static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
+static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
 {
 	struct gpd_link *link;
 	int ret = 0;
@@ -300,7 +300,7 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
 		genpd_sd_counter_inc(master);
 
 		genpd_lock_nested(master, depth + 1);
-		ret = genpd_poweron(master, depth + 1);
+		ret = genpd_power_on(master, depth + 1);
 		genpd_unlock(master);
 
 		if (ret) {
@@ -309,7 +309,7 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
 		}
 	}
 
-	ret = genpd_power_on(genpd, true);
+	ret = _genpd_power_on(genpd, true);
 	if (ret)
 		goto err;
 
@@ -368,14 +368,14 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 }
 
 /**
- * genpd_poweroff - Remove power from a given PM domain.
+ * genpd_power_off - Remove power from a given PM domain.
  * @genpd: PM domain to power down.
  * @is_async: PM domain is powered down from a scheduled work
  *
  * If all of the @genpd's devices have been suspended and all of its subdomains
  * have been powered down, remove power from @genpd.
  */
-static int genpd_poweroff(struct generic_pm_domain *genpd, bool is_async)
+static int genpd_power_off(struct generic_pm_domain *genpd, bool is_async)
 {
 	struct pm_domain_data *pdd;
 	struct gpd_link *link;
@@ -427,13 +427,13 @@ static int genpd_poweroff(struct generic_pm_domain *genpd, bool is_async)
 
 		/*
 		 * If sd_count > 0 at this point, one of the subdomains hasn't
-		 * managed to call genpd_poweron() for the master yet after
-		 * incrementing it.  In that case genpd_poweron() will wait
+		 * managed to call genpd_power_on() for the master yet after
+		 * incrementing it.  In that case genpd_power_on() will wait
 		 * for us to drop the lock, so we can call .power_off() and let
-		 * the genpd_poweron() restore power for us (this shouldn't
+		 * the genpd_power_on() restore power for us (this shouldn't
 		 * happen very often).
 		 */
-		ret = genpd_power_off(genpd, true);
+		ret = _genpd_power_off(genpd, true);
 		if (ret)
 			return ret;
 	}
@@ -459,7 +459,7 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 	genpd = container_of(work, struct generic_pm_domain, power_off_work);
 
 	genpd_lock(genpd);
-	genpd_poweroff(genpd, true);
+	genpd_power_off(genpd, true);
 	genpd_unlock(genpd);
 }
 
@@ -578,7 +578,7 @@ static int genpd_runtime_suspend(struct device *dev)
 		return 0;
 
 	genpd_lock(genpd);
-	genpd_poweroff(genpd, false);
+	genpd_power_off(genpd, false);
 	genpd_unlock(genpd);
 
 	return 0;
@@ -618,7 +618,7 @@ static int genpd_runtime_resume(struct device *dev)
 	}
 
 	genpd_lock(genpd);
-	ret = genpd_poweron(genpd, 0);
+	ret = genpd_power_on(genpd, 0);
 	genpd_unlock(genpd);
 
 	if (ret)
@@ -658,7 +658,7 @@ err_poweroff:
 	if (!pm_runtime_is_irq_safe(dev) ||
 		(pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) {
 		genpd_lock(genpd);
-		genpd_poweroff(genpd, 0);
+		genpd_power_off(genpd, 0);
 		genpd_unlock(genpd);
 	}
 
@@ -674,9 +674,9 @@ static int __init pd_ignore_unused_setup(char *__unused)
 __setup("pd_ignore_unused", pd_ignore_unused_setup);
 
 /**
- * genpd_poweroff_unused - Power off all PM domains with no devices in use.
+ * genpd_power_off_unused - Power off all PM domains with no devices in use.
  */
-static int __init genpd_poweroff_unused(void)
+static int __init genpd_power_off_unused(void)
 {
 	struct generic_pm_domain *genpd;
 
@@ -694,7 +694,7 @@ static int __init genpd_poweroff_unused(void)
 
 	return 0;
 }
-late_initcall(genpd_poweroff_unused);
+late_initcall(genpd_power_off_unused);
 
 #if defined(CONFIG_PM_SLEEP) || defined(CONFIG_PM_GENERIC_DOMAINS_OF)
 
@@ -727,18 +727,20 @@ static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd,
 }
 
 /**
- * genpd_sync_poweroff - Synchronously power off a PM domain and its masters.
+ * genpd_sync_power_off - Synchronously power off a PM domain and its masters.
  * @genpd: PM domain to power off, if possible.
+ * @use_lock: use the lock.
+ * @depth: nesting count for lockdep.
  *
  * Check if the given PM domain can be powered off (during system suspend or
  * hibernation) and do that if so.  Also, in that case propagate to its masters.
  *
  * This function is only called in "noirq" and "syscore" stages of system power
- * transitions, so it need not acquire locks (all of the "noirq" callbacks are
- * executed sequentially, so it is guaranteed that it will never run twice in
- * parallel).
+ * transitions. The "noirq" callbacks may be executed asynchronously, thus in
+ * these cases the lock must be held.
  */
-static void genpd_sync_poweroff(struct generic_pm_domain *genpd)
+static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock,
+				 unsigned int depth)
 {
 	struct gpd_link *link;
 
@@ -751,26 +753,35 @@ static void genpd_sync_poweroff(struct generic_pm_domain *genpd)
 
 	/* Choose the deepest state when suspending */
 	genpd->state_idx = genpd->state_count - 1;
-	genpd_power_off(genpd, false);
+	_genpd_power_off(genpd, false);
 
 	genpd->status = GPD_STATE_POWER_OFF;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
 		genpd_sd_counter_dec(link->master);
-		genpd_sync_poweroff(link->master);
+
+		if (use_lock)
+			genpd_lock_nested(link->master, depth + 1);
+
+		genpd_sync_power_off(link->master, use_lock, depth + 1);
+
+		if (use_lock)
+			genpd_unlock(link->master);
 	}
 }
 
 /**
- * genpd_sync_poweron - Synchronously power on a PM domain and its masters.
+ * genpd_sync_power_on - Synchronously power on a PM domain and its masters.
  * @genpd: PM domain to power on.
+ * @use_lock: use the lock.
+ * @depth: nesting count for lockdep.
  *
  * This function is only called in "noirq" and "syscore" stages of system power
- * transitions, so it need not acquire locks (all of the "noirq" callbacks are
- * executed sequentially, so it is guaranteed that it will never run twice in
- * parallel).
+ * transitions. The "noirq" callbacks may be executed asynchronously, thus in
+ * these cases the lock must be held.
  */
-static void genpd_sync_poweron(struct generic_pm_domain *genpd)
+static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock,
+				unsigned int depth)
 {
 	struct gpd_link *link;
 
@@ -778,11 +789,18 @@ static void genpd_sync_poweron(struct generic_pm_domain *genpd)
 		return;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		genpd_sync_poweron(link->master);
 		genpd_sd_counter_inc(link->master);
+
+		if (use_lock)
+			genpd_lock_nested(link->master, depth + 1);
+
+		genpd_sync_power_on(link->master, use_lock, depth + 1);
+
+		if (use_lock)
+			genpd_unlock(link->master);
 	}
 
-	genpd_power_on(genpd, false);
+	_genpd_power_on(genpd, false);
 
 	genpd->status = GPD_STATE_ACTIVE;
 }
@@ -888,13 +906,10 @@ static int pm_genpd_suspend_noirq(struct device *dev)
 			return ret;
 	}
 
-	/*
-	 * Since all of the "noirq" callbacks are executed sequentially, it is
-	 * guaranteed that this function will never run twice in parallel for
-	 * the same PM domain, so it is not necessary to use locking here.
-	 */
+	genpd_lock(genpd);
 	genpd->suspended_count++;
-	genpd_sync_poweroff(genpd);
+	genpd_sync_power_off(genpd, true, 0);
+	genpd_unlock(genpd);
 
 	return 0;
 }
@@ -919,13 +934,10 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	if (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))
 		return 0;
 
-	/*
-	 * Since all of the "noirq" callbacks are executed sequentially, it is
-	 * guaranteed that this function will never run twice in parallel for
-	 * the same PM domain, so it is not necessary to use locking here.
-	 */
-	genpd_sync_poweron(genpd);
+	genpd_lock(genpd);
+	genpd_sync_power_on(genpd, true, 0);
 	genpd->suspended_count--;
+	genpd_unlock(genpd);
 
 	if (genpd->dev_ops.stop && genpd->dev_ops.start)
 		ret = pm_runtime_force_resume(dev);
@@ -1002,22 +1014,20 @@ static int pm_genpd_restore_noirq(struct device *dev)
 		return -EINVAL;
 
 	/*
-	 * Since all of the "noirq" callbacks are executed sequentially, it is
-	 * guaranteed that this function will never run twice in parallel for
-	 * the same PM domain, so it is not necessary to use locking here.
-	 *
 	 * At this point suspended_count == 0 means we are being run for the
 	 * first time for the given domain in the present cycle.
 	 */
+	genpd_lock(genpd);
 	if (genpd->suspended_count++ == 0)
 		/*
 		 * The boot kernel might put the domain into arbitrary state,
-		 * so make it appear as powered off to genpd_sync_poweron(),
+		 * so make it appear as powered off to genpd_sync_power_on(),
 		 * so that it tries to power it on in case it was really off.
 		 */
 		genpd->status = GPD_STATE_POWER_OFF;
 
-	genpd_sync_poweron(genpd);
+	genpd_sync_power_on(genpd, true, 0);
+	genpd_unlock(genpd);
 
 	if (genpd->dev_ops.stop && genpd->dev_ops.start)
 		ret = pm_runtime_force_resume(dev);
@@ -1072,9 +1082,9 @@ static void genpd_syscore_switch(struct device *dev, bool suspend)
 
 	if (suspend) {
 		genpd->suspended_count++;
-		genpd_sync_poweroff(genpd);
+		genpd_sync_power_off(genpd, false, 0);
 	} else {
-		genpd_sync_poweron(genpd);
+		genpd_sync_power_on(genpd, false, 0);
 		genpd->suspended_count--;
 	}
 }
@@ -2043,7 +2053,7 @@ int genpd_dev_pm_attach(struct device *dev)
 	dev->pm_domain->sync = genpd_dev_pm_sync;
 
 	genpd_lock(pd);
-	ret = genpd_poweron(pd, 0);
+	ret = genpd_power_on(pd, 0);
 	genpd_unlock(pd);
 out:
 	return ret ? -EPROBE_DEFER : 0;
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 35ff06283738..91ec3232d630 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -32,13 +32,7 @@ LIST_HEAD(opp_tables);
 /* Lock to allow exclusive modification to the device and opp lists */
 DEFINE_MUTEX(opp_table_lock);
 
-#define opp_rcu_lockdep_assert()					\
-do {									\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
-			 !lockdep_is_held(&opp_table_lock),		\
-			 "Missing rcu_read_lock() or "			\
-			 "opp_table_lock protection");			\
-} while (0)
+static void dev_pm_opp_get(struct dev_pm_opp *opp);
 
 static struct opp_device *_find_opp_dev(const struct device *dev,
 					struct opp_table *opp_table)
@@ -52,38 +46,46 @@ static struct opp_device *_find_opp_dev(const struct device *dev,
 	return NULL;
 }
 
+static struct opp_table *_find_opp_table_unlocked(struct device *dev)
+{
+	struct opp_table *opp_table;
+
+	list_for_each_entry(opp_table, &opp_tables, node) {
+		if (_find_opp_dev(dev, opp_table)) {
+			_get_opp_table_kref(opp_table);
+
+			return opp_table;
+		}
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
 /**
  * _find_opp_table() - find opp_table struct using device pointer
  * @dev:	device pointer used to lookup OPP table
  *
- * Search OPP table for one containing matching device. Does a RCU reader
- * operation to grab the pointer needed.
+ * Search OPP table for one containing matching device.
  *
  * Return: pointer to 'struct opp_table' if found, otherwise -ENODEV or
  * -EINVAL based on type of error.
  *
- * Locking: For readers, this function must be called under rcu_read_lock().
- * opp_table is a RCU protected pointer, which means that opp_table is valid
- * as long as we are under RCU lock.
- *
- * For Writers, this function must be called with opp_table_lock held.
+ * The callers must call dev_pm_opp_put_opp_table() after the table is used.
  */
 struct opp_table *_find_opp_table(struct device *dev)
 {
 	struct opp_table *opp_table;
 
-	opp_rcu_lockdep_assert();
-
 	if (IS_ERR_OR_NULL(dev)) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry_rcu(opp_table, &opp_tables, node)
-		if (_find_opp_dev(dev, opp_table))
-			return opp_table;
+	mutex_lock(&opp_table_lock);
+	opp_table = _find_opp_table_unlocked(dev);
+	mutex_unlock(&opp_table_lock);
 
-	return ERR_PTR(-ENODEV);
+	return opp_table;
 }
 
 /**
@@ -94,29 +96,15 @@ struct opp_table *_find_opp_table(struct device *dev)
  * return 0
  *
  * This is useful only for devices with single power supply.
- *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. This means that opp which could have been fetched by
- * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
- * under RCU lock. The pointer returned by the opp_find_freq family must be
- * used in the same section as the usage of this function with the pointer
- * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
- * pointer.
  */
 unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 {
-	struct dev_pm_opp *tmp_opp;
-	unsigned long v = 0;
-
-	opp_rcu_lockdep_assert();
-
-	tmp_opp = rcu_dereference(opp);
-	if (IS_ERR_OR_NULL(tmp_opp))
+	if (IS_ERR_OR_NULL(opp)) {
 		pr_err("%s: Invalid parameters\n", __func__);
-	else
-		v = tmp_opp->supplies[0].u_volt;
+		return 0;
+	}
 
-	return v;
+	return opp->supplies[0].u_volt;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
 
@@ -126,29 +114,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
  *
  * Return: frequency in hertz corresponding to the opp, else
  * return 0
- *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. This means that opp which could have been fetched by
- * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
- * under RCU lock. The pointer returned by the opp_find_freq family must be
- * used in the same section as the usage of this function with the pointer
- * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
- * pointer.
  */
 unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 {
-	struct dev_pm_opp *tmp_opp;
-	unsigned long f = 0;
-
-	opp_rcu_lockdep_assert();
-
-	tmp_opp = rcu_dereference(opp);
-	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(opp) || !opp->available) {
 		pr_err("%s: Invalid parameters\n", __func__);
-	else
-		f = tmp_opp->rate;
+		return 0;
+	}
 
-	return f;
+	return opp->rate;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
 
@@ -161,28 +135,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
  * quickly. Running on them for longer times may overheat the chip.
  *
  * Return: true if opp is turbo opp, else false.
- *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. This means that opp which could have been fetched by
- * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
- * under RCU lock. The pointer returned by the opp_find_freq family must be
- * used in the same section as the usage of this function with the pointer
- * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
- * pointer.
  */
 bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp)
 {
-	struct dev_pm_opp *tmp_opp;
-
-	opp_rcu_lockdep_assert();
-
-	tmp_opp = rcu_dereference(opp);
-	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available) {
+	if (IS_ERR_OR_NULL(opp) || !opp->available) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return false;
 	}
 
-	return tmp_opp->turbo;
+	return opp->turbo;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
 
@@ -191,52 +152,29 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
  * @dev:	device for which we do this operation
  *
  * Return: This function returns the max clock latency in nanoseconds.
- *
- * Locking: This function takes rcu_read_lock().
  */
 unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
 {
 	struct opp_table *opp_table;
 	unsigned long clock_latency_ns;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table))
-		clock_latency_ns = 0;
-	else
-		clock_latency_ns = opp_table->clock_latency_ns_max;
-
-	rcu_read_unlock();
-	return clock_latency_ns;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
-
-static int _get_regulator_count(struct device *dev)
-{
-	struct opp_table *opp_table;
-	int count;
+		return 0;
 
-	rcu_read_lock();
+	clock_latency_ns = opp_table->clock_latency_ns_max;
 
-	opp_table = _find_opp_table(dev);
-	if (!IS_ERR(opp_table))
-		count = opp_table->regulator_count;
-	else
-		count = 0;
+	dev_pm_opp_put_opp_table(opp_table);
 
-	rcu_read_unlock();
-
-	return count;
+	return clock_latency_ns;
 }
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
 
 /**
  * dev_pm_opp_get_max_volt_latency() - Get max voltage latency in nanoseconds
  * @dev: device for which we do this operation
  *
  * Return: This function returns the max voltage latency in nanoseconds.
- *
- * Locking: This function takes rcu_read_lock().
  */
 unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 {
@@ -250,35 +188,33 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 		unsigned long max;
 	} *uV;
 
-	count = _get_regulator_count(dev);
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return 0;
+
+	count = opp_table->regulator_count;
 
 	/* Regulator may not be required for the device */
 	if (!count)
-		return 0;
+		goto put_opp_table;
 
 	regulators = kmalloc_array(count, sizeof(*regulators), GFP_KERNEL);
 	if (!regulators)
-		return 0;
+		goto put_opp_table;
 
 	uV = kmalloc_array(count, sizeof(*uV), GFP_KERNEL);
 	if (!uV)
 		goto free_regulators;
 
-	rcu_read_lock();
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		rcu_read_unlock();
-		goto free_uV;
-	}
-
 	memcpy(regulators, opp_table->regulators, count * sizeof(*regulators));
 
+	mutex_lock(&opp_table->lock);
+
 	for (i = 0; i < count; i++) {
 		uV[i].min = ~0;
 		uV[i].max = 0;
 
-		list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
+		list_for_each_entry(opp, &opp_table->opp_list, node) {
 			if (!opp->available)
 				continue;
 
@@ -289,7 +225,7 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 		}
 	}
 
-	rcu_read_unlock();
+	mutex_unlock(&opp_table->lock);
 
 	/*
 	 * The caller needs to ensure that opp_table (and hence the regulator)
@@ -301,10 +237,11 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 			latency_ns += ret * 1000;
 	}
 
-free_uV:
 	kfree(uV);
 free_regulators:
 	kfree(regulators);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return latency_ns;
 }
@@ -317,8 +254,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_volt_latency);
  *
  * Return: This function returns the max transition latency, in nanoseconds, to
  * switch from one OPP to other.
- *
- * Locking: This function takes rcu_read_lock().
  */
 unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev)
 {
@@ -328,32 +263,29 @@ unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_transition_latency);
 
 /**
- * dev_pm_opp_get_suspend_opp() - Get suspend opp
+ * dev_pm_opp_get_suspend_opp_freq() - Get frequency of suspend opp in Hz
  * @dev:	device for which we do this operation
  *
- * Return: This function returns pointer to the suspend opp if it is
- * defined and available, otherwise it returns NULL.
- *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * Return: This function returns the frequency of the OPP marked as suspend_opp
+ * if one is available, else returns 0;
  */
-struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev)
+unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
 {
 	struct opp_table *opp_table;
-
-	opp_rcu_lockdep_assert();
+	unsigned long freq = 0;
 
 	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table) || !opp_table->suspend_opp ||
-	    !opp_table->suspend_opp->available)
-		return NULL;
+	if (IS_ERR(opp_table))
+		return 0;
+
+	if (opp_table->suspend_opp && opp_table->suspend_opp->available)
+		freq = dev_pm_opp_get_freq(opp_table->suspend_opp);
 
-	return opp_table->suspend_opp;
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return freq;
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp);
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
 
 /**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp table
@@ -361,8 +293,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp);
  *
  * Return: This function returns the number of available opps if there are any,
  * else returns 0 if none or the corresponding error value.
- *
- * Locking: This function takes rcu_read_lock().
  */
 int dev_pm_opp_get_opp_count(struct device *dev)
 {
@@ -370,23 +300,24 @@ int dev_pm_opp_get_opp_count(struct device *dev)
 	struct dev_pm_opp *temp_opp;
 	int count = 0;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		count = PTR_ERR(opp_table);
 		dev_err(dev, "%s: OPP table not found (%d)\n",
 			__func__, count);
-		goto out_unlock;
+		return count;
 	}
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available)
 			count++;
 	}
 
-out_unlock:
-	rcu_read_unlock();
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
 	return count;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
@@ -411,11 +342,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
  * This provides a mechanism to enable an opp which is not available currently
  * or the opposite as well.
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					      unsigned long freq,
@@ -424,8 +352,6 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
-	opp_rcu_lockdep_assert();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		int r = PTR_ERR(opp_table);
@@ -434,14 +360,22 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 		return ERR_PTR(r);
 	}
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available == available &&
 				temp_opp->rate == freq) {
 			opp = temp_opp;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
 			break;
 		}
 	}
 
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
 	return opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
@@ -451,14 +385,21 @@ static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
 {
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available && temp_opp->rate >= *freq) {
 			opp = temp_opp;
 			*freq = opp->rate;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
 			break;
 		}
 	}
 
+	mutex_unlock(&opp_table->lock);
+
 	return opp;
 }
 
@@ -477,18 +418,14 @@ static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
  * ERANGE:	no match found for search
  * ENODEV:	if device not found in list of registered devices
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq)
 {
 	struct opp_table *opp_table;
-
-	opp_rcu_lockdep_assert();
+	struct dev_pm_opp *opp;
 
 	if (!dev || !freq) {
 		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
@@ -499,7 +436,11 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 	if (IS_ERR(opp_table))
 		return ERR_CAST(opp_table);
 
-	return _find_freq_ceil(opp_table, freq);
+	opp = _find_freq_ceil(opp_table, freq);
+
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
 
@@ -518,11 +459,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
  * ERANGE:	no match found for search
  * ENODEV:	if device not found in list of registered devices
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					      unsigned long *freq)
@@ -530,8 +468,6 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
-	opp_rcu_lockdep_assert();
-
 	if (!dev || !freq) {
 		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
 		return ERR_PTR(-EINVAL);
@@ -541,7 +477,9 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	if (IS_ERR(opp_table))
 		return ERR_CAST(opp_table);
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available) {
 			/* go to the next node, before choosing prev */
 			if (temp_opp->rate > *freq)
@@ -550,6 +488,13 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 				opp = temp_opp;
 		}
 	}
+
+	/* Increment the reference count of OPP */
+	if (!IS_ERR(opp))
+		dev_pm_opp_get(opp);
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
 	if (!IS_ERR(opp))
 		*freq = opp->rate;
 
@@ -557,34 +502,6 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
-/*
- * The caller needs to ensure that opp_table (and hence the clk) isn't freed,
- * while clk returned here is used.
- */
-static struct clk *_get_opp_clk(struct device *dev)
-{
-	struct opp_table *opp_table;
-	struct clk *clk;
-
-	rcu_read_lock();
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
-		clk = ERR_CAST(opp_table);
-		goto unlock;
-	}
-
-	clk = opp_table->clk;
-	if (IS_ERR(clk))
-		dev_err(dev, "%s: No clock available for the device\n",
-			__func__);
-
-unlock:
-	rcu_read_unlock();
-	return clk;
-}
-
 static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 			    struct dev_pm_opp_supply *supply)
 {
@@ -680,8 +597,6 @@ restore_voltage:
  *
  * This configures the power-supplies and clock source to the levels specified
  * by the OPP corresponding to the target_freq.
- *
- * Locking: This function takes rcu_read_lock().
  */
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 {
@@ -700,9 +615,19 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		return -EINVAL;
 	}
 
-	clk = _get_opp_clk(dev);
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
+		return PTR_ERR(opp_table);
+	}
+
+	clk = opp_table->clk;
+	if (IS_ERR(clk)) {
+		dev_err(dev, "%s: No clock available for the device\n",
+			__func__);
+		ret = PTR_ERR(clk);
+		goto put_opp_table;
+	}
 
 	freq = clk_round_rate(clk, target_freq);
 	if ((long)freq <= 0)
@@ -714,16 +639,8 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	if (old_freq == freq) {
 		dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n",
 			__func__, freq);
-		return 0;
-	}
-
-	rcu_read_lock();
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
-		rcu_read_unlock();
-		return PTR_ERR(opp_table);
+		ret = 0;
+		goto put_opp_table;
 	}
 
 	old_opp = _find_freq_ceil(opp_table, &old_freq);
@@ -737,8 +654,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		ret = PTR_ERR(opp);
 		dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n",
 			__func__, freq, ret);
-		rcu_read_unlock();
-		return ret;
+		goto put_old_opp;
 	}
 
 	dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", __func__,
@@ -748,8 +664,8 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 
 	/* Only frequency scaling */
 	if (!regulators) {
-		rcu_read_unlock();
-		return _generic_set_opp_clk_only(dev, clk, old_freq, freq);
+		ret = _generic_set_opp_clk_only(dev, clk, old_freq, freq);
+		goto put_opps;
 	}
 
 	if (opp_table->set_opp)
@@ -773,28 +689,26 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	data->new_opp.rate = freq;
 	memcpy(data->new_opp.supplies, opp->supplies, size);
 
-	rcu_read_unlock();
+	ret = set_opp(data);
 
-	return set_opp(data);
+put_opps:
+	dev_pm_opp_put(opp);
+put_old_opp:
+	if (!IS_ERR(old_opp))
+		dev_pm_opp_put(old_opp);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate);
 
 /* OPP-dev Helpers */
-static void _kfree_opp_dev_rcu(struct rcu_head *head)
-{
-	struct opp_device *opp_dev;
-
-	opp_dev = container_of(head, struct opp_device, rcu_head);
-	kfree_rcu(opp_dev, rcu_head);
-}
-
 static void _remove_opp_dev(struct opp_device *opp_dev,
 			    struct opp_table *opp_table)
 {
 	opp_debug_unregister(opp_dev, opp_table);
 	list_del(&opp_dev->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp_dev->rcu_head,
-		  _kfree_opp_dev_rcu);
+	kfree(opp_dev);
 }
 
 struct opp_device *_add_opp_dev(const struct device *dev,
@@ -809,7 +723,7 @@ struct opp_device *_add_opp_dev(const struct device *dev,
 
 	/* Initialize opp-dev */
 	opp_dev->dev = dev;
-	list_add_rcu(&opp_dev->node, &opp_table->dev_list);
+	list_add(&opp_dev->node, &opp_table->dev_list);
 
 	/* Create debugfs entries for the opp_table */
 	ret = opp_debug_register(opp_dev, opp_table);
@@ -820,26 +734,12 @@ struct opp_device *_add_opp_dev(const struct device *dev,
 	return opp_dev;
 }
 
-/**
- * _add_opp_table() - Find OPP table or allocate a new one
- * @dev:	device for which we do this operation
- *
- * It tries to find an existing table first, if it couldn't find one, it
- * allocates a new OPP table and returns that.
- *
- * Return: valid opp_table pointer if success, else NULL.
- */
-static struct opp_table *_add_opp_table(struct device *dev)
+static struct opp_table *_allocate_opp_table(struct device *dev)
 {
 	struct opp_table *opp_table;
 	struct opp_device *opp_dev;
 	int ret;
 
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (!IS_ERR(opp_table))
-		return opp_table;
-
 	/*
 	 * Allocate a new OPP table. In the infrequent case where a new
 	 * device is needed to be added, we pay this penalty.
@@ -867,50 +767,45 @@ static struct opp_table *_add_opp_table(struct device *dev)
 				ret);
 	}
 
-	srcu_init_notifier_head(&opp_table->srcu_head);
+	BLOCKING_INIT_NOTIFIER_HEAD(&opp_table->head);
 	INIT_LIST_HEAD(&opp_table->opp_list);
+	mutex_init(&opp_table->lock);
+	kref_init(&opp_table->kref);
 
 	/* Secure the device table modification */
-	list_add_rcu(&opp_table->node, &opp_tables);
+	list_add(&opp_table->node, &opp_tables);
 	return opp_table;
 }
 
-/**
- * _kfree_device_rcu() - Free opp_table RCU handler
- * @head:	RCU head
- */
-static void _kfree_device_rcu(struct rcu_head *head)
+void _get_opp_table_kref(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table = container_of(head, struct opp_table,
-						   rcu_head);
-
-	kfree_rcu(opp_table, rcu_head);
+	kref_get(&opp_table->kref);
 }
 
-/**
- * _remove_opp_table() - Removes a OPP table
- * @opp_table: OPP table to be removed.
- *
- * Removes/frees OPP table if it doesn't contain any OPPs.
- */
-static void _remove_opp_table(struct opp_table *opp_table)
+struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
 {
-	struct opp_device *opp_dev;
+	struct opp_table *opp_table;
 
-	if (!list_empty(&opp_table->opp_list))
-		return;
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
 
-	if (opp_table->supported_hw)
-		return;
+	opp_table = _find_opp_table_unlocked(dev);
+	if (!IS_ERR(opp_table))
+		goto unlock;
 
-	if (opp_table->prop_name)
-		return;
+	opp_table = _allocate_opp_table(dev);
 
-	if (opp_table->regulators)
-		return;
+unlock:
+	mutex_unlock(&opp_table_lock);
 
-	if (opp_table->set_opp)
-		return;
+	return opp_table;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_table);
+
+static void _opp_table_kref_release(struct kref *kref)
+{
+	struct opp_table *opp_table = container_of(kref, struct opp_table, kref);
+	struct opp_device *opp_dev;
 
 	/* Release clk */
 	if (!IS_ERR(opp_table->clk))
@@ -924,63 +819,60 @@ static void _remove_opp_table(struct opp_table *opp_table)
 	/* dev_list must be empty now */
 	WARN_ON(!list_empty(&opp_table->dev_list));
 
-	list_del_rcu(&opp_table->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp_table->rcu_head,
-		  _kfree_device_rcu);
+	mutex_destroy(&opp_table->lock);
+	list_del(&opp_table->node);
+	kfree(opp_table);
+
+	mutex_unlock(&opp_table_lock);
 }
 
-/**
- * _kfree_opp_rcu() - Free OPP RCU handler
- * @head:	RCU head
- */
-static void _kfree_opp_rcu(struct rcu_head *head)
+void dev_pm_opp_put_opp_table(struct opp_table *opp_table)
 {
-	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
+	kref_put_mutex(&opp_table->kref, _opp_table_kref_release,
+		       &opp_table_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_put_opp_table);
 
-	kfree_rcu(opp, rcu_head);
+void _opp_free(struct dev_pm_opp *opp)
+{
+	kfree(opp);
 }
 
-/**
- * _opp_remove()  - Remove an OPP from a table definition
- * @opp_table:	points back to the opp_table struct this opp belongs to
- * @opp:	pointer to the OPP to remove
- * @notify:	OPP_EVENT_REMOVE notification should be sent or not
- *
- * This function removes an opp definition from the opp table.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * It is assumed that the caller holds required mutex for an RCU updater
- * strategy.
- */
-void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp,
-		 bool notify)
+static void _opp_kref_release(struct kref *kref)
 {
+	struct dev_pm_opp *opp = container_of(kref, struct dev_pm_opp, kref);
+	struct opp_table *opp_table = opp->opp_table;
+
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	if (notify)
-		srcu_notifier_call_chain(&opp_table->srcu_head,
-					 OPP_EVENT_REMOVE, opp);
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_REMOVE, opp);
 	opp_debug_remove_one(opp);
-	list_del_rcu(&opp->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	list_del(&opp->node);
+	kfree(opp);
 
-	_remove_opp_table(opp_table);
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+}
+
+static void dev_pm_opp_get(struct dev_pm_opp *opp)
+{
+	kref_get(&opp->kref);
 }
 
+void dev_pm_opp_put(struct dev_pm_opp *opp)
+{
+	kref_put_mutex(&opp->kref, _opp_kref_release, &opp->opp_table->lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_put);
+
 /**
  * dev_pm_opp_remove()  - Remove an OPP from OPP table
  * @dev:	device for which we do this operation
  * @freq:	OPP to remove with matching 'freq'
  *
  * This function removes an opp from the opp table.
- *
- * 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_remove(struct device *dev, unsigned long freq)
 {
@@ -988,12 +880,11 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 	struct opp_table *opp_table;
 	bool found = false;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table))
-		goto unlock;
+		return;
+
+	mutex_lock(&opp_table->lock);
 
 	list_for_each_entry(opp, &opp_table->opp_list, node) {
 		if (opp->rate == freq) {
@@ -1002,28 +893,23 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 		}
 	}
 
-	if (!found) {
+	mutex_unlock(&opp_table->lock);
+
+	if (found) {
+		dev_pm_opp_put(opp);
+	} else {
 		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
 			 __func__, freq);
-		goto unlock;
 	}
 
-	_opp_remove(opp_table, opp, true);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
 
-struct dev_pm_opp *_allocate_opp(struct device *dev,
-				 struct opp_table **opp_table)
+struct dev_pm_opp *_opp_allocate(struct opp_table *table)
 {
 	struct dev_pm_opp *opp;
 	int count, supply_size;
-	struct opp_table *table;
-
-	table = _add_opp_table(dev);
-	if (!table)
-		return NULL;
 
 	/* Allocate space for at least one supply */
 	count = table->regulator_count ? table->regulator_count : 1;
@@ -1031,17 +917,13 @@ struct dev_pm_opp *_allocate_opp(struct device *dev,
 
 	/* allocate new OPP node and supplies structures */
 	opp = kzalloc(sizeof(*opp) + supply_size, GFP_KERNEL);
-	if (!opp) {
-		kfree(table);
+	if (!opp)
 		return NULL;
-	}
 
 	/* Put the supplies at the end of the OPP structure as an empty array */
 	opp->supplies = (struct dev_pm_opp_supply *)(opp + 1);
 	INIT_LIST_HEAD(&opp->node);
 
-	*opp_table = table;
-
 	return opp;
 }
 
@@ -1067,11 +949,21 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 	return true;
 }
 
+/*
+ * Returns:
+ * 0: On success. And appropriate error message for duplicate OPPs.
+ * -EBUSY: For OPP with same freq/volt and is available. The callers of
+ *  _opp_add() must return 0 if they receive -EBUSY from it. This is to make
+ *  sure we don't print error messages unnecessarily if different parts of
+ *  kernel try to initialize the OPP table.
+ * -EEXIST: For OPP with same freq but different volt or is unavailable. This
+ *  should be considered an error by the callers of _opp_add().
+ */
 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;
+	struct list_head *head;
 	int ret;
 
 	/*
@@ -1082,7 +974,10 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	 * loop, don't replace it with head otherwise it will become an infinite
 	 * loop.
 	 */
-	list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+	head = &opp_table->opp_list;
+
+	list_for_each_entry(opp, &opp_table->opp_list, node) {
 		if (new_opp->rate > opp->rate) {
 			head = &opp->node;
 			continue;
@@ -1098,12 +993,21 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 			 new_opp->supplies[0].u_volt, new_opp->available);
 
 		/* Should we compare voltages for all regulators here ? */
-		return opp->available &&
-		       new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? 0 : -EEXIST;
+		ret = opp->available &&
+		      new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
+
+		mutex_unlock(&opp_table->lock);
+		return ret;
 	}
 
+	list_add(&new_opp->node, head);
+	mutex_unlock(&opp_table->lock);
+
 	new_opp->opp_table = opp_table;
-	list_add_rcu(&new_opp->node, head);
+	kref_init(&new_opp->kref);
+
+	/* Get a reference to the OPP table */
+	_get_opp_table_kref(opp_table);
 
 	ret = opp_debug_create_one(new_opp, opp_table);
 	if (ret)
@@ -1121,6 +1025,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 
 /**
  * _opp_add_v1() - Allocate a OPP based on v1 bindings.
+ * @opp_table:	OPP table
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP
  * @u_volt:	Voltage in uVolts for this OPP
@@ -1133,12 +1038,6 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
  * NOTE: "dynamic" parameter impacts OPPs added by the dev_pm_opp_of_add_table
  * and freed by dev_pm_opp_of_remove_table.
  *
- * Locking: The internal 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
@@ -1146,22 +1045,16 @@ 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
  */
-int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
-		bool dynamic)
+int _opp_add_v1(struct opp_table *opp_table, struct device *dev,
+		unsigned long freq, long u_volt, bool dynamic)
 {
-	struct opp_table *opp_table;
 	struct dev_pm_opp *new_opp;
 	unsigned long tol;
 	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;
-	}
+	new_opp = _opp_allocate(opp_table);
+	if (!new_opp)
+		return -ENOMEM;
 
 	/* populate the opp table */
 	new_opp->rate = freq;
@@ -1173,22 +1066,23 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 	new_opp->dynamic = dynamic;
 
 	ret = _opp_add(dev, new_opp, opp_table);
-	if (ret)
+	if (ret) {
+		/* Don't return error for duplicate OPPs */
+		if (ret == -EBUSY)
+			ret = 0;
 		goto free_opp;
-
-	mutex_unlock(&opp_table_lock);
+	}
 
 	/*
 	 * 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);
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADD, new_opp);
 	return 0;
 
 free_opp:
-	_opp_remove(opp_table, new_opp, false);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	_opp_free(new_opp);
+
 	return ret;
 }
 
@@ -1202,27 +1096,16 @@ unlock:
  * specify the hierarchy of versions it supports. OPP layer will then enable
  * OPPs, which are available for those versions, based on its 'opp-supported-hw'
  * property.
- *
- * 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_supported_hw(struct device *dev, const u32 *versions,
-				unsigned int count)
+struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
+			const u32 *versions, unsigned int count)
 {
 	struct opp_table *opp_table;
-	int ret = 0;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
+	int ret;
 
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
@@ -1243,65 +1126,40 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
 	}
 
 	opp_table->supported_hw_count = count;
-	mutex_unlock(&opp_table_lock);
-	return 0;
+
+	return opp_table;
 
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw);
 
 /**
  * dev_pm_opp_put_supported_hw() - Releases resources blocked for supported hw
- * @dev: Device for which supported-hw has to be put.
+ * @opp_table: OPP table returned by dev_pm_opp_set_supported_hw().
  *
  * This is required only for the V2 bindings, and is called for a matching
  * dev_pm_opp_set_supported_hw(). Until this is called, the opp_table structure
  * will not be freed.
- *
- * 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_put_supported_hw(struct device *dev)
+void dev_pm_opp_put_supported_hw(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "Failed to find opp_table: %ld\n",
-			PTR_ERR(opp_table));
-		goto unlock;
-	}
-
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
 	if (!opp_table->supported_hw) {
-		dev_err(dev, "%s: Doesn't have supported hardware list\n",
-			__func__);
-		goto unlock;
+		pr_err("%s: Doesn't have supported hardware list\n",
+		       __func__);
+		return;
 	}
 
 	kfree(opp_table->supported_hw);
 	opp_table->supported_hw = NULL;
 	opp_table->supported_hw_count = 0;
 
-	/* Try freeing opp_table if this was the last blocking resource */
-	_remove_opp_table(opp_table);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
 
@@ -1314,26 +1172,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
  * specify the extn to be used for certain property names. The properties to
  * which the extension will apply are opp-microvolt and opp-microamp. OPP core
  * should postfix the property name with -<name> while looking for them.
- *
- * 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_prop_name(struct device *dev, const char *name)
+struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
 	struct opp_table *opp_table;
-	int ret = 0;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
+	int ret;
 
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
@@ -1352,63 +1199,37 @@ int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 		goto err;
 	}
 
-	mutex_unlock(&opp_table_lock);
-	return 0;
+	return opp_table;
 
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name);
 
 /**
  * dev_pm_opp_put_prop_name() - Releases resources blocked for prop-name
- * @dev: Device for which the prop-name has to be put.
+ * @opp_table: OPP table returned by dev_pm_opp_set_prop_name().
  *
  * This is required only for the V2 bindings, and is called for a matching
  * dev_pm_opp_set_prop_name(). Until this is called, the opp_table structure
  * will not be freed.
- *
- * 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_put_prop_name(struct device *dev)
+void dev_pm_opp_put_prop_name(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "Failed to find opp_table: %ld\n",
-			PTR_ERR(opp_table));
-		goto unlock;
-	}
-
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
 	if (!opp_table->prop_name) {
-		dev_err(dev, "%s: Doesn't have a prop-name\n", __func__);
-		goto unlock;
+		pr_err("%s: Doesn't have a prop-name\n", __func__);
+		return;
 	}
 
 	kfree(opp_table->prop_name);
 	opp_table->prop_name = NULL;
 
-	/* Try freeing opp_table if this was the last blocking resource */
-	_remove_opp_table(opp_table);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name);
 
@@ -1455,12 +1276,6 @@ static void _free_set_opp_data(struct opp_table *opp_table)
  * well.
  *
  * This must be called before any OPPs are initialized for the device.
- *
- * 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.
  */
 struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 					    const char * const names[],
@@ -1470,13 +1285,9 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 	struct regulator *reg;
 	int ret, i;
 
-	mutex_lock(&opp_table_lock);
-
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* This should be called before OPPs are initialized */
 	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
@@ -1518,7 +1329,6 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 	if (ret)
 		goto free_regulators;
 
-	mutex_unlock(&opp_table_lock);
 	return opp_table;
 
 free_regulators:
@@ -1529,9 +1339,7 @@ free_regulators:
 	opp_table->regulators = NULL;
 	opp_table->regulator_count = 0;
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ERR_PTR(ret);
 }
@@ -1540,22 +1348,14 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulators);
 /**
  * dev_pm_opp_put_regulators() - Releases resources blocked for regulator
  * @opp_table: OPP table returned from dev_pm_opp_set_regulators().
- *
- * 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_put_regulators(struct opp_table *opp_table)
 {
 	int i;
 
-	mutex_lock(&opp_table_lock);
-
 	if (!opp_table->regulators) {
 		pr_err("%s: Doesn't have regulators set\n", __func__);
-		goto unlock;
+		return;
 	}
 
 	/* Make sure there are no concurrent readers while updating opp_table */
@@ -1570,11 +1370,7 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 	opp_table->regulators = NULL;
 	opp_table->regulator_count = 0;
 
-	/* Try freeing opp_table if this was the last blocking resource */
-	_remove_opp_table(opp_table);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
 
@@ -1587,29 +1383,19 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
  * regulators per device), instead of the generic OPP set rate helper.
  *
  * This must be called before any OPPs are initialized for the device.
- *
- * 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_register_set_opp_helper(struct device *dev,
+struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 			int (*set_opp)(struct dev_pm_set_opp_data *data))
 {
 	struct opp_table *opp_table;
 	int ret;
 
 	if (!set_opp)
-		return -EINVAL;
-
-	mutex_lock(&opp_table_lock);
+		return ERR_PTR(-EINVAL);
 
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* This should be called before OPPs are initialized */
 	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
@@ -1625,47 +1411,28 @@ int dev_pm_opp_register_set_opp_helper(struct device *dev,
 
 	opp_table->set_opp = set_opp;
 
-	mutex_unlock(&opp_table_lock);
-	return 0;
+	return opp_table;
 
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
 
 /**
  * dev_pm_opp_register_put_opp_helper() - Releases resources blocked for
  *					   set_opp helper
- * @dev: Device for which custom set_opp helper has to be cleared.
+ * @opp_table: OPP table returned from dev_pm_opp_register_set_opp_helper().
  *
- * 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.
+ * Release resources blocked for platform specific set_opp helper.
  */
-void dev_pm_opp_register_put_opp_helper(struct device *dev)
+void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table;
-
-	mutex_lock(&opp_table_lock);
-
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "Failed to find opp_table: %ld\n",
-			PTR_ERR(opp_table));
-		goto unlock;
-	}
-
 	if (!opp_table->set_opp) {
-		dev_err(dev, "%s: Doesn't have custom set_opp helper set\n",
-			__func__);
-		goto unlock;
+		pr_err("%s: Doesn't have custom set_opp helper set\n",
+		       __func__);
+		return;
 	}
 
 	/* Make sure there are no concurrent readers while updating opp_table */
@@ -1673,11 +1440,7 @@ void dev_pm_opp_register_put_opp_helper(struct device *dev)
 
 	opp_table->set_opp = NULL;
 
-	/* Try freeing opp_table if this was the last blocking resource */
-	_remove_opp_table(opp_table);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
 
@@ -1691,12 +1454,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
  * The opp is made available by default and it can be controlled using
  * dev_pm_opp_enable/disable functions.
  *
- * 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
@@ -1706,7 +1463,17 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
  */
 int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 {
-	return _opp_add_v1(dev, freq, u_volt, true);
+	struct opp_table *opp_table;
+	int ret;
+
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
+
+	ret = _opp_add_v1(opp_table, dev, freq, u_volt, true);
+
+	dev_pm_opp_put_opp_table(opp_table);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 
@@ -1716,41 +1483,30 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add);
  * @freq:		OPP frequency to modify availability
  * @availability_req:	availability status requested for this opp
  *
- * Set the availability of an OPP with an RCU operation, opp_{enable,disable}
- * share a common logic which is isolated here.
+ * Set the availability of an OPP, opp_{enable,disable} share a common logic
+ * which is isolated here.
  *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
  * copy operation, returns 0 if no modification was done OR modification was
  * successful.
- *
- * 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 locking or synchronize_rcu() blocking calls cannot be used.
  */
 static int _opp_set_availability(struct device *dev, unsigned long freq,
 				 bool availability_req)
 {
 	struct opp_table *opp_table;
-	struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
+	struct dev_pm_opp *tmp_opp, *opp = ERR_PTR(-ENODEV);
 	int r = 0;
 
-	/* keep the node allocated */
-	new_opp = kmalloc(sizeof(*new_opp), GFP_KERNEL);
-	if (!new_opp)
-		return -ENOMEM;
-
-	mutex_lock(&opp_table_lock);
-
 	/* Find the opp_table */
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		r = PTR_ERR(opp_table);
 		dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
-		goto unlock;
+		return r;
 	}
 
+	mutex_lock(&opp_table->lock);
+
 	/* Do we have the frequency? */
 	list_for_each_entry(tmp_opp, &opp_table->opp_list, node) {
 		if (tmp_opp->rate == freq) {
@@ -1758,6 +1514,7 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 			break;
 		}
 	}
+
 	if (IS_ERR(opp)) {
 		r = PTR_ERR(opp);
 		goto unlock;
@@ -1766,29 +1523,20 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 	/* Is update really needed? */
 	if (opp->available == availability_req)
 		goto unlock;
-	/* copy the old data over */
-	*new_opp = *opp;
 
-	/* plug in new node */
-	new_opp->available = availability_req;
-
-	list_replace_rcu(&opp->node, &new_opp->node);
-	mutex_unlock(&opp_table_lock);
-	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	opp->available = availability_req;
 
 	/* Notify the change of the OPP availability */
 	if (availability_req)
-		srcu_notifier_call_chain(&opp_table->srcu_head,
-					 OPP_EVENT_ENABLE, new_opp);
+		blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE,
+					     opp);
 	else
-		srcu_notifier_call_chain(&opp_table->srcu_head,
-					 OPP_EVENT_DISABLE, new_opp);
-
-	return 0;
+		blocking_notifier_call_chain(&opp_table->head,
+					     OPP_EVENT_DISABLE, opp);
 
 unlock:
-	mutex_unlock(&opp_table_lock);
-	kfree(new_opp);
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
 	return r;
 }
 
@@ -1801,12 +1549,6 @@ unlock:
  * corresponding error value. It is meant to be used for users an OPP available
  * after being temporarily made unavailable with dev_pm_opp_disable.
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly uses RCU and 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 locking or synchronize_rcu() blocking calls cannot be used.
- *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
  * copy operation, returns 0 if no modification was done OR modification was
  * successful.
@@ -1827,12 +1569,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable);
  * control by users to make this OPP not available until the circumstances are
  * right to make it available again (with a call to dev_pm_opp_enable).
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly uses RCU and 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 locking or synchronize_rcu() blocking calls cannot be used.
- *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
  * copy operation, returns 0 if no modification was done OR modification was
  * successful.
@@ -1844,41 +1580,78 @@ int dev_pm_opp_disable(struct device *dev, unsigned long freq)
 EXPORT_SYMBOL_GPL(dev_pm_opp_disable);
 
 /**
- * dev_pm_opp_get_notifier() - find notifier_head of the device with opp
- * @dev:	device pointer used to lookup OPP table.
+ * dev_pm_opp_register_notifier() - Register OPP notifier for the device
+ * @dev:	Device for which notifier needs to be registered
+ * @nb:		Notifier block to be registered
  *
- * Return: pointer to  notifier head if found, otherwise -ENODEV or
- * -EINVAL based on type of error casted as pointer. value must be checked
- *  with IS_ERR to determine valid pointer or error result.
+ * Return: 0 on success or a negative error value.
+ */
+int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb)
+{
+	struct opp_table *opp_table;
+	int ret;
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
+
+	ret = blocking_notifier_chain_register(&opp_table->head, nb);
+
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_pm_opp_register_notifier);
+
+/**
+ * dev_pm_opp_unregister_notifier() - Unregister OPP notifier for the device
+ * @dev:	Device for which notifier needs to be unregistered
+ * @nb:		Notifier block to be unregistered
  *
- * Locking: This function must be called under rcu_read_lock(). opp_table is a
- * RCU protected pointer. The reason for the same is that the opp pointer which
- * is returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * Return: 0 on success or a negative error value.
  */
-struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev)
+int dev_pm_opp_unregister_notifier(struct device *dev,
+				   struct notifier_block *nb)
 {
-	struct opp_table *opp_table = _find_opp_table(dev);
+	struct opp_table *opp_table;
+	int ret;
 
+	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table))
-		return ERR_CAST(opp_table); /* matching type */
+		return PTR_ERR(opp_table);
+
+	ret = blocking_notifier_chain_unregister(&opp_table->head, nb);
 
-	return &opp_table->srcu_head;
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return ret;
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
+EXPORT_SYMBOL(dev_pm_opp_unregister_notifier);
 
 /*
  * 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_remove_table(struct device *dev, bool remove_all)
+void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev,
+			      bool remove_all)
 {
-	struct opp_table *opp_table;
 	struct dev_pm_opp *opp, *tmp;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
+	/* Find if opp_table manages a single device */
+	if (list_is_singular(&opp_table->dev_list)) {
+		/* Free static OPPs */
+		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
+			if (remove_all || !opp->dynamic)
+				dev_pm_opp_put(opp);
+		}
+	} else {
+		_remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table);
+	}
+}
+
+void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all)
+{
+	struct opp_table *opp_table;
 
 	/* Check for existing table for 'dev' */
 	opp_table = _find_opp_table(dev);
@@ -1890,22 +1663,12 @@ void _dev_pm_opp_remove_table(struct device *dev, bool remove_all)
 			     IS_ERR_OR_NULL(dev) ?
 					"Invalid device" : dev_name(dev),
 			     error);
-		goto unlock;
+		return;
 	}
 
-	/* Find if opp_table manages a single device */
-	if (list_is_singular(&opp_table->dev_list)) {
-		/* Free static OPPs */
-		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
-			if (remove_all || !opp->dynamic)
-				_opp_remove(opp_table, opp, true);
-		}
-	} else {
-		_remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table);
-	}
+	_dev_pm_opp_remove_table(opp_table, dev, remove_all);
 
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 
 /**
@@ -1914,15 +1677,9 @@ unlock:
  *
  * 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.
  */
 void dev_pm_opp_remove_table(struct device *dev)
 {
-	_dev_pm_opp_remove_table(dev, true);
+	_dev_pm_opp_find_and_remove_table(dev, true);
 }
 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 8c3434bdb26d..2d87bc1adf38 100644
--- a/drivers/base/power/opp/cpu.c
+++ b/drivers/base/power/opp/cpu.c
@@ -42,11 +42,6 @@
  *
  * WARNING: It is  important for the callers to ensure refreshing their copy of
  * the table if any of the mentioned functions have been invoked in the interim.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Since we just use the regular accessor functions to access the internal data
- * structures, we use RCU read lock inside this function. As a result, users of
- * this function DONOT need to use explicit locks for invoking.
  */
 int dev_pm_opp_init_cpufreq_table(struct device *dev,
 				  struct cpufreq_frequency_table **table)
@@ -56,19 +51,13 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 	int i, max_opps, ret = 0;
 	unsigned long rate;
 
-	rcu_read_lock();
-
 	max_opps = dev_pm_opp_get_opp_count(dev);
-	if (max_opps <= 0) {
-		ret = max_opps ? max_opps : -ENODATA;
-		goto out;
-	}
+	if (max_opps <= 0)
+		return max_opps ? max_opps : -ENODATA;
 
 	freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC);
-	if (!freq_table) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!freq_table)
+		return -ENOMEM;
 
 	for (i = 0, rate = 0; i < max_opps; i++, rate++) {
 		/* find next rate */
@@ -83,6 +72,8 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 		/* Is Boost/turbo opp ? */
 		if (dev_pm_opp_is_turbo(opp))
 			freq_table[i].flags = CPUFREQ_BOOST_FREQ;
+
+		dev_pm_opp_put(opp);
 	}
 
 	freq_table[i].driver_data = i;
@@ -91,7 +82,6 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 	*table = &freq_table[0];
 
 out:
-	rcu_read_unlock();
 	if (ret)
 		kfree(freq_table);
 
@@ -147,12 +137,6 @@ void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of)
  * 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)
 {
@@ -169,12 +153,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_cpumask_remove_table);
  * @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)
@@ -184,13 +162,9 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
 	struct device *dev;
 	int cpu, ret = 0;
 
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _find_opp_table(cpu_dev);
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
-		goto unlock;
-	}
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
 
 	for_each_cpu(cpu, cpumask) {
 		if (cpu == cpu_dev->id)
@@ -213,8 +187,8 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
 		/* Mark opp-table as multiple CPUs are sharing it now */
 		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
 	}
-unlock:
-	mutex_unlock(&opp_table_lock);
+
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
@@ -229,12 +203,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus);
  *
  * Returns -ENODEV if OPP table isn't already present and -EINVAL if the OPP
  * table's status is access-unknown.
- *
- * 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_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 {
@@ -242,17 +210,13 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 	struct opp_table *opp_table;
 	int ret = 0;
 
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _find_opp_table(cpu_dev);
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
-		goto unlock;
-	}
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
 
 	if (opp_table->shared_opp == OPP_TABLE_ACCESS_UNKNOWN) {
 		ret = -EINVAL;
-		goto unlock;
+		goto put_opp_table;
 	}
 
 	cpumask_clear(cpumask);
@@ -264,8 +228,8 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 		cpumask_set_cpu(cpu_dev->id, cpumask);
 	}
 
-unlock:
-	mutex_unlock(&opp_table_lock);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 3f7d2591b173..779428676f63 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -24,9 +24,11 @@
 
 static struct opp_table *_managed_opp(const struct device_node *np)
 {
-	struct opp_table *opp_table;
+	struct opp_table *opp_table, *managed_table = NULL;
+
+	mutex_lock(&opp_table_lock);
 
-	list_for_each_entry_rcu(opp_table, &opp_tables, node) {
+	list_for_each_entry(opp_table, &opp_tables, node) {
 		if (opp_table->np == np) {
 			/*
 			 * Multiple devices can point to the same OPP table and
@@ -35,14 +37,18 @@ static struct opp_table *_managed_opp(const struct device_node *np)
 			 * But the OPPs will be considered as shared only if the
 			 * OPP table contains a "opp-shared" property.
 			 */
-			if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED)
-				return opp_table;
+			if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) {
+				_get_opp_table_kref(opp_table);
+				managed_table = opp_table;
+			}
 
-			return NULL;
+			break;
 		}
 	}
 
-	return NULL;
+	mutex_unlock(&opp_table_lock);
+
+	return managed_table;
 }
 
 void _of_init_opp_table(struct opp_table *opp_table, struct device *dev)
@@ -229,34 +235,28 @@ free_microvolt:
  * @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);
+	_dev_pm_opp_find_and_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() */
-static struct device_node *_of_get_opp_desc_node(struct device *dev)
+struct device_node *dev_pm_opp_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);
 }
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node);
 
 /**
  * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
+ * @opp_table:	OPP table
  * @dev:	device for which we do this operation
  * @np:		device node
  *
@@ -264,12 +264,6 @@ static struct device_node *_of_get_opp_desc_node(struct device *dev)
  * 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
@@ -278,22 +272,17 @@ static struct device_node *_of_get_opp_desc_node(struct device *dev)
  * -ENOMEM	Memory allocation failure
  * -EINVAL	Failed parsing the OPP node
  */
-static int _opp_add_static_v2(struct device *dev, struct device_node *np)
+static int _opp_add_static_v2(struct opp_table *opp_table, 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;
-	}
+	new_opp = _opp_allocate(opp_table);
+	if (!new_opp)
+		return -ENOMEM;
 
 	ret = of_property_read_u64(np, "opp-hz", &rate);
 	if (ret < 0) {
@@ -327,8 +316,12 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 		goto free_opp;
 
 	ret = _opp_add(dev, new_opp, opp_table);
-	if (ret)
+	if (ret) {
+		/* Don't return error for duplicate OPPs */
+		if (ret == -EBUSY)
+			ret = 0;
 		goto free_opp;
+	}
 
 	/* OPP to select on device suspend */
 	if (of_property_read_bool(np, "opp-suspend")) {
@@ -345,8 +338,6 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	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->supplies[0].u_volt, new_opp->supplies[0].u_volt_min,
@@ -356,13 +347,12 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	 * 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);
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADD, new_opp);
 	return 0;
 
 free_opp:
-	_opp_remove(opp_table, new_opp, false);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	_opp_free(new_opp);
+
 	return ret;
 }
 
@@ -373,41 +363,35 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_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;
+		goto put_opp_table;
 	}
-	mutex_unlock(&opp_table_lock);
+
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
 
 	/* 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);
+		ret = _opp_add_static_v2(opp_table, dev, np);
 		if (ret) {
 			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
 				ret);
-			goto free_table;
+			_dev_pm_opp_remove_table(opp_table, dev, false);
+			goto put_opp_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;
+	if (WARN_ON(!count)) {
+		ret = -ENOENT;
+		goto put_opp_table;
 	}
 
 	opp_table->np = opp_np;
@@ -416,12 +400,8 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 	else
 		opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE;
 
-	mutex_unlock(&opp_table_lock);
-
-	return 0;
-
-free_table:
-	dev_pm_opp_of_remove_table(dev);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
@@ -429,9 +409,10 @@ free_table:
 /* Initializes OPP tables based on old-deprecated bindings */
 static int _of_add_opp_table_v1(struct device *dev)
 {
+	struct opp_table *opp_table;
 	const struct property *prop;
 	const __be32 *val;
-	int nr;
+	int nr, ret = 0;
 
 	prop = of_find_property(dev->of_node, "operating-points", NULL);
 	if (!prop)
@@ -449,18 +430,27 @@ static int _of_add_opp_table_v1(struct device *dev)
 		return -EINVAL;
 	}
 
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
+
 	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);
+		ret = _opp_add_v1(opp_table, dev, freq, volt, false);
+		if (ret) {
+			dev_err(dev, "%s: Failed to add OPP %ld (%d)\n",
+				__func__, freq, ret);
+			_dev_pm_opp_remove_table(opp_table, dev, false);
+			break;
+		}
 		nr -= 2;
 	}
 
-	return 0;
+	dev_pm_opp_put_opp_table(opp_table);
+	return ret;
 }
 
 /**
@@ -469,12 +459,6 @@ static int _of_add_opp_table_v1(struct device *dev)
  *
  * 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
@@ -495,7 +479,7 @@ int dev_pm_opp_of_add_table(struct device *dev)
 	 * 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);
+	opp_np = dev_pm_opp_of_get_opp_desc_node(dev);
 	if (!opp_np) {
 		/*
 		 * Try old-deprecated bindings for backward compatibility with
@@ -519,12 +503,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
  *
  * 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)
 {
@@ -537,12 +515,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table);
  * @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)
 {
@@ -590,12 +562,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_add_table);
  * 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)
@@ -605,7 +571,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 	int cpu, ret = 0;
 
 	/* Get OPP descriptor node */
-	np = _of_get_opp_desc_node(cpu_dev);
+	np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
 	if (!np) {
 		dev_dbg(cpu_dev, "%s: Couldn't find opp node.\n", __func__);
 		return -ENOENT;
@@ -630,7 +596,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 		}
 
 		/* Get OPP descriptor node */
-		tmp_np = _of_get_opp_desc_node(tcpu_dev);
+		tmp_np = dev_pm_opp_of_get_opp_desc_node(tcpu_dev);
 		if (!tmp_np) {
 			dev_err(tcpu_dev, "%s: Couldn't find opp node.\n",
 				__func__);
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index af9f2b849a66..166eef990599 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -16,11 +16,11 @@
 
 #include <linux/device.h>
 #include <linux/kernel.h>
+#include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <linux/pm_opp.h>
-#include <linux/rculist.h>
-#include <linux/rcupdate.h>
+#include <linux/notifier.h>
 
 struct clk;
 struct regulator;
@@ -51,11 +51,9 @@ extern struct list_head opp_tables;
  * @node:	opp table node. The nodes are maintained throughout the lifetime
  *		of boot. It is expected only an optimal set of OPPs are
  *		added to the library by the SoC framework.
- *		RCU usage: opp table is traversed with RCU locks. node
- *		modification is possible realtime, hence the modifications
- *		are protected by the opp_table_lock for integrity.
  *		IMPORTANT: the opp nodes should be maintained in increasing
  *		order.
+ * @kref:	for reference count of the OPP.
  * @available:	true/false - marks if this OPP as available or not
  * @dynamic:	not-created from static DT entries.
  * @turbo:	true if turbo (boost) OPP
@@ -65,7 +63,6 @@ extern struct list_head opp_tables;
  * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
  *		frequency from any other OPP's frequency.
  * @opp_table:	points back to the opp_table struct this opp belongs to
- * @rcu_head:	RCU callback head used for deferred freeing
  * @np:		OPP's device node.
  * @dentry:	debugfs dentry pointer (per opp)
  *
@@ -73,6 +70,7 @@ extern struct list_head opp_tables;
  */
 struct dev_pm_opp {
 	struct list_head node;
+	struct kref kref;
 
 	bool available;
 	bool dynamic;
@@ -85,7 +83,6 @@ struct dev_pm_opp {
 	unsigned long clock_latency_ns;
 
 	struct opp_table *opp_table;
-	struct rcu_head rcu_head;
 
 	struct device_node *np;
 
@@ -98,7 +95,6 @@ struct dev_pm_opp {
  * struct opp_device - devices managed by 'struct opp_table'
  * @node:	list node
  * @dev:	device to which the struct object belongs
- * @rcu_head:	RCU callback head used for deferred freeing
  * @dentry:	debugfs dentry pointer (per device)
  *
  * This is an internal data structure maintaining the devices that are managed
@@ -107,7 +103,6 @@ struct dev_pm_opp {
 struct opp_device {
 	struct list_head node;
 	const struct device *dev;
-	struct rcu_head rcu_head;
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
@@ -125,12 +120,11 @@ enum opp_table_access {
  * @node:	table node - contains the devices with OPPs that
  *		have been registered. Nodes once added are not modified in this
  *		table.
- *		RCU usage: nodes are not modified in the table of opp_table,
- *		however addition is possible and is secured by opp_table_lock
- * @srcu_head:	notifier head to notify the OPP availability changes.
- * @rcu_head:	RCU callback head used for deferred freeing
+ * @head:	notifier head to notify the OPP availability changes.
  * @dev_list:	list of devices that share these OPPs
  * @opp_list:	table of opps
+ * @kref:	for reference count of the table.
+ * @lock:	mutex protecting the opp_list.
  * @np:		struct device_node pointer for opp's DT node.
  * @clock_latency_ns_max: Max clock latency in nanoseconds.
  * @shared_opp: OPP is shared between multiple devices.
@@ -151,18 +145,15 @@ enum opp_table_access {
  * This is an internal data structure maintaining the link to opps attached to
  * a device. This structure is not meant to be shared to users as it is
  * meant for book keeping and private to OPP library.
- *
- * Because the opp structures can be used from both rcu and srcu readers, we
- * need to wait for the grace period of both of them before freeing any
- * resources. And so we have used kfree_rcu() from within call_srcu() handlers.
  */
 struct opp_table {
 	struct list_head node;
 
-	struct srcu_notifier_head srcu_head;
-	struct rcu_head rcu_head;
+	struct blocking_notifier_head head;
 	struct list_head dev_list;
 	struct list_head opp_list;
+	struct kref kref;
+	struct mutex lock;
 
 	struct device_node *np;
 	unsigned long clock_latency_ns_max;
@@ -190,14 +181,17 @@ struct opp_table {
 };
 
 /* Routines internal to opp core */
+void _get_opp_table_kref(struct opp_table *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);
-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);
+void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev, bool remove_all);
+void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all);
+struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table);
+void _opp_free(struct dev_pm_opp *opp);
 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);
+int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic);
 void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of);
+struct opp_table *_add_opp_table(struct device *dev);
 
 #ifdef CONFIG_OF
 void _of_init_opp_table(struct opp_table *opp_table, struct device *dev);
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 58fcc758334e..d888d9869b6a 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -281,7 +281,7 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 	dev->power.qos = ERR_PTR(-ENODEV);
 	spin_unlock_irq(&dev->power.lock);
 
-	kfree(c->notifiers);
+	kfree(qos->resume_latency.notifiers);
 	kfree(qos);
 
  out:
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 404d94c6c8bc..ae0429827f31 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -141,6 +141,13 @@ static irqreturn_t handle_threaded_wake_irq(int irq, void *_wirq)
 	struct wake_irq *wirq = _wirq;
 	int res;
 
+	/* Maybe abort suspend? */
+	if (irqd_is_wakeup_set(irq_get_irq_data(irq))) {
+		pm_wakeup_event(wirq->dev, 0);
+
+		return IRQ_HANDLED;
+	}
+
 	/* We don't want RPM_ASYNC or RPM_NOWAIT here */
 	res = pm_runtime_resume(wirq->dev);
 	if (res < 0)
@@ -183,6 +190,9 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 	wirq->irq = irq;
 	irq_set_status_flags(irq, IRQ_NOAUTOEN);
 
+	/* Prevent deferred spurious wakeirqs with disable_irq_nosync() */
+	irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY);
+
 	/*
 	 * Consumer device may need to power up and restore state
 	 * so we use a threaded irq.
@@ -312,8 +322,12 @@ void dev_pm_arm_wake_irq(struct wake_irq *wirq)
 	if (!wirq)
 		return;
 
-	if (device_may_wakeup(wirq->dev))
+	if (device_may_wakeup(wirq->dev)) {
+		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)
+			enable_irq(wirq->irq);
+
 		enable_irq_wake(wirq->irq);
+	}
 }
 
 /**
@@ -328,6 +342,10 @@ void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
 	if (!wirq)
 		return;
 
-	if (device_may_wakeup(wirq->dev))
+	if (device_may_wakeup(wirq->dev)) {
 		disable_irq_wake(wirq->irq);
+
+		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)
+			disable_irq_nosync(wirq->irq);
+	}
 }
diff --git a/drivers/clk/tegra/clk-dfll.c b/drivers/clk/tegra/clk-dfll.c
index f010562534eb..2c44aeb0b97c 100644
--- a/drivers/clk/tegra/clk-dfll.c
+++ b/drivers/clk/tegra/clk-dfll.c
@@ -633,16 +633,12 @@ static int find_lut_index_for_rate(struct tegra_dfll *td, unsigned long rate)
 	struct dev_pm_opp *opp;
 	int i, uv;
 
-	rcu_read_lock();
-
 	opp = dev_pm_opp_find_freq_ceil(td->soc->dev, &rate);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp))
 		return PTR_ERR(opp);
-	}
-	uv = dev_pm_opp_get_voltage(opp);
 
-	rcu_read_unlock();
+	uv = dev_pm_opp_get_voltage(opp);
+	dev_pm_opp_put(opp);
 
 	for (i = 0; i < td->i2c_lut_size; i++) {
 		if (regulator_list_voltage(td->vdd_reg, td->i2c_lut[i]) == uv)
@@ -1440,8 +1436,6 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 	struct dev_pm_opp *opp;
 	int lut;
 
-	rcu_read_lock();
-
 	rate = ULONG_MAX;
 	opp = dev_pm_opp_find_freq_floor(td->soc->dev, &rate);
 	if (IS_ERR(opp)) {
@@ -1449,6 +1443,7 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 		goto out;
 	}
 	v_max = dev_pm_opp_get_voltage(opp);
+	dev_pm_opp_put(opp);
 
 	v = td->soc->cvb->min_millivolts * 1000;
 	lut = find_vdd_map_entry_exact(td, v);
@@ -1465,6 +1460,8 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 		if (v_opp <= td->soc->cvb->min_millivolts * 1000)
 			td->dvco_rate_min = dev_pm_opp_get_freq(opp);
 
+		dev_pm_opp_put(opp);
+
 		for (;;) {
 			v += max(1, (v_max - v) / (MAX_DFLL_VOLTAGES - j));
 			if (v >= v_opp)
@@ -1496,8 +1493,6 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 		ret = 0;
 
 out:
-	rcu_read_unlock();
-
 	return ret;
 }
 
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index d8b164a7c4e5..4ebae43118ef 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -37,14 +37,6 @@ config CPU_FREQ_STAT
 
 	  If in doubt, say N.
 
-config CPU_FREQ_STAT_DETAILS
-	bool "CPU frequency transition statistics details"
-	depends on CPU_FREQ_STAT
-	help
-	  Show detailed CPU frequency transition table in sysfs.
-
-	  If in doubt, say N.
-
 choice
 	prompt "Default CPUFreq governor"
 	default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1100_CPUFREQ || ARM_SA1110_CPUFREQ
@@ -271,6 +263,16 @@ config IA64_ACPI_CPUFREQ
 endif
 
 if MIPS
+config BMIPS_CPUFREQ
+	tristate "BMIPS CPUfreq Driver"
+	help
+	  This option adds a CPUfreq driver for BMIPS processors with
+	  support for configurable CPU frequency.
+
+	  For now, BMIPS5 chips are supported (such as the Broadcom 7425).
+
+	  If in doubt, say N.
+
 config LOONGSON2_CPUFREQ
 	tristate "Loongson2 CPUFreq Driver"
 	help
@@ -332,7 +334,7 @@ endif
 
 config QORIQ_CPUFREQ
 	tristate "CPU frequency scaling driver for Freescale QorIQ SoCs"
-	depends on OF && COMMON_CLK && (PPC_E500MC || ARM)
+	depends on OF && COMMON_CLK && (PPC_E500MC || ARM || ARM64)
 	depends on !CPU_THERMAL || THERMAL
 	select CLK_QORIQ
 	help
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 920c469f3953..74fa5c5904d3 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -247,6 +247,17 @@ config ARM_TEGRA124_CPUFREQ
 	help
 	  This adds the CPUFreq driver support for Tegra124 SOCs.
 
+config ARM_TI_CPUFREQ
+	bool "Texas Instruments CPUFreq support"
+	depends on ARCH_OMAP2PLUS
+	help
+	  This driver enables valid OPPs on the running platform based on
+	  values contained within the SoC in use. Enable this in order to
+	  use the cpufreq-dt driver on all Texas Instruments platforms that
+	  provide dt based operating-points-v2 tables with opp-supported-hw
+	  data provided. Required for cpufreq support on AM335x, AM437x,
+	  DRA7x, and AM57x platforms.
+
 config ARM_PXA2xx_CPUFREQ
 	tristate "Intel PXA2xx CPUfreq driver"
 	depends on PXA27x || PXA25x
@@ -257,7 +268,7 @@ config ARM_PXA2xx_CPUFREQ
 
 config ACPI_CPPC_CPUFREQ
 	tristate "CPUFreq driver based on the ACPI CPPC spec"
-	depends on ACPI
+	depends on ACPI_PROCESSOR
 	select ACPI_CPPC_LIB
 	default n
 	help
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 1e46c3918e7a..9f5a8045f36d 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -77,6 +77,7 @@ obj-$(CONFIG_ARM_SPEAR_CPUFREQ)		+= spear-cpufreq.o
 obj-$(CONFIG_ARM_STI_CPUFREQ)		+= sti-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA20_CPUFREQ)	+= tegra20-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
+obj-$(CONFIG_ARM_TI_CPUFREQ)		+= ti-cpufreq.o
 obj-$(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
@@ -98,6 +99,7 @@ obj-$(CONFIG_POWERNV_CPUFREQ)		+= powernv-cpufreq.o
 # Other platform drivers
 obj-$(CONFIG_AVR32_AT32AP_CPUFREQ)	+= at32ap-cpufreq.o
 obj-$(CONFIG_BFIN_CPU_FREQ)		+= blackfin-cpufreq.o
+obj-$(CONFIG_BMIPS_CPUFREQ)		+= bmips-cpufreq.o
 obj-$(CONFIG_CRIS_MACH_ARTPEC3)		+= cris-artpec3-cpufreq.o
 obj-$(CONFIG_ETRAXFS)			+= cris-etraxfs-cpufreq.o
 obj-$(CONFIG_IA64_ACPI_CPUFREQ)		+= ia64-acpi-cpufreq.o
diff --git a/drivers/cpufreq/bmips-cpufreq.c b/drivers/cpufreq/bmips-cpufreq.c
new file mode 100644
index 000000000000..1653151b77df
--- /dev/null
+++ b/drivers/cpufreq/bmips-cpufreq.c
@@ -0,0 +1,188 @@
+/*
+ * CPU frequency scaling for Broadcom BMIPS SoCs
+ *
+ * Copyright (c) 2017 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+
+/* for mips_hpt_frequency */
+#include <asm/time.h>
+
+#define BMIPS_CPUFREQ_PREFIX	"bmips"
+#define BMIPS_CPUFREQ_NAME	BMIPS_CPUFREQ_PREFIX "-cpufreq"
+
+#define TRANSITION_LATENCY	(25 * 1000)	/* 25 us */
+
+#define BMIPS5_CLK_DIV_SET_SHIFT	0x7
+#define BMIPS5_CLK_DIV_SHIFT		0x4
+#define BMIPS5_CLK_DIV_MASK		0xf
+
+enum bmips_type {
+	BMIPS5000,
+	BMIPS5200,
+};
+
+struct cpufreq_compat {
+	const char *compatible;
+	unsigned int bmips_type;
+	unsigned int clk_mult;
+	unsigned int max_freqs;
+};
+
+#define BMIPS(c, t, m, f) { \
+	.compatible = c, \
+	.bmips_type = (t), \
+	.clk_mult = (m), \
+	.max_freqs = (f), \
+}
+
+static struct cpufreq_compat bmips_cpufreq_compat[] = {
+	BMIPS("brcm,bmips5000", BMIPS5000, 8, 4),
+	BMIPS("brcm,bmips5200", BMIPS5200, 8, 4),
+	{ }
+};
+
+static struct cpufreq_compat *priv;
+
+static int htp_freq_to_cpu_freq(unsigned int clk_mult)
+{
+	return mips_hpt_frequency * clk_mult / 1000;
+}
+
+static struct cpufreq_frequency_table *
+bmips_cpufreq_get_freq_table(const struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *table;
+	unsigned long cpu_freq;
+	int i;
+
+	cpu_freq = htp_freq_to_cpu_freq(priv->clk_mult);
+
+	table = kmalloc((priv->max_freqs + 1) * sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < priv->max_freqs; i++) {
+		table[i].frequency = cpu_freq / (1 << i);
+		table[i].driver_data = i;
+	}
+	table[i].frequency = CPUFREQ_TABLE_END;
+
+	return table;
+}
+
+static unsigned int bmips_cpufreq_get(unsigned int cpu)
+{
+	unsigned int div;
+	uint32_t mode;
+
+	switch (priv->bmips_type) {
+	case BMIPS5200:
+	case BMIPS5000:
+		mode = read_c0_brcm_mode();
+		div = ((mode >> BMIPS5_CLK_DIV_SHIFT) & BMIPS5_CLK_DIV_MASK);
+		break;
+	default:
+		div = 0;
+	}
+
+	return htp_freq_to_cpu_freq(priv->clk_mult) / (1 << div);
+}
+
+static int bmips_cpufreq_target_index(struct cpufreq_policy *policy,
+				      unsigned int index)
+{
+	unsigned int div = policy->freq_table[index].driver_data;
+
+	switch (priv->bmips_type) {
+	case BMIPS5200:
+	case BMIPS5000:
+		change_c0_brcm_mode(BMIPS5_CLK_DIV_MASK << BMIPS5_CLK_DIV_SHIFT,
+				    (1 << BMIPS5_CLK_DIV_SET_SHIFT) |
+				    (div << BMIPS5_CLK_DIV_SHIFT));
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return 0;
+}
+
+static int bmips_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	kfree(policy->freq_table);
+
+	return 0;
+}
+
+static int bmips_cpufreq_init(struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *freq_table;
+	int ret;
+
+	freq_table = bmips_cpufreq_get_freq_table(policy);
+	if (IS_ERR(freq_table)) {
+		ret = PTR_ERR(freq_table);
+		pr_err("%s: couldn't determine frequency table (%d).\n",
+			BMIPS_CPUFREQ_NAME, ret);
+		return ret;
+	}
+
+	ret = cpufreq_generic_init(policy, freq_table, TRANSITION_LATENCY);
+	if (ret)
+		bmips_cpufreq_exit(policy);
+	else
+		pr_info("%s: registered\n", BMIPS_CPUFREQ_NAME);
+
+	return ret;
+}
+
+static struct cpufreq_driver bmips_cpufreq_driver = {
+	.flags		= CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.verify		= cpufreq_generic_frequency_table_verify,
+	.target_index	= bmips_cpufreq_target_index,
+	.get		= bmips_cpufreq_get,
+	.init		= bmips_cpufreq_init,
+	.exit		= bmips_cpufreq_exit,
+	.attr		= cpufreq_generic_attr,
+	.name		= BMIPS_CPUFREQ_PREFIX,
+};
+
+static int __init bmips_cpufreq_probe(void)
+{
+	struct cpufreq_compat *cc;
+	struct device_node *np;
+
+	for (cc = bmips_cpufreq_compat; cc->compatible; cc++) {
+		np = of_find_compatible_node(NULL, "cpu", cc->compatible);
+		if (np) {
+			of_node_put(np);
+			priv = cc;
+			break;
+		}
+	}
+
+	/* We hit the guard element of the array. No compatible CPU found. */
+	if (!cc->compatible)
+		return -ENODEV;
+
+	return cpufreq_register_driver(&bmips_cpufreq_driver);
+}
+device_initcall(bmips_cpufreq_probe);
+
+MODULE_AUTHOR("Markus Mayer <mmayer@broadcom.com>");
+MODULE_DESCRIPTION("CPUfreq driver for Broadcom BMIPS SoCs");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index c94360671f41..7281a2c19c36 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -878,7 +878,6 @@ unmap_intr_base:
 	iounmap(priv->avs_intr_base);
 unmap_base:
 	iounmap(priv->base);
-	platform_set_drvdata(pdev, NULL);
 
 	return ret;
 }
@@ -1042,7 +1041,6 @@ static int brcm_avs_cpufreq_remove(struct platform_device *pdev)
 	priv = platform_get_drvdata(pdev);
 	iounmap(priv->base);
 	iounmap(priv->avs_intr_base);
-	platform_set_drvdata(pdev, NULL);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 7fcaf26e8f81..921b4a6c3d16 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -87,8 +87,6 @@ static const struct of_device_id machines[] __initconst = {
 	{ .compatible = "socionext,uniphier-ld11", },
 	{ .compatible = "socionext,uniphier-ld20", },
 
-	{ .compatible = "ti,am33xx", },
-	{ .compatible = "ti,dra7", },
 	{ .compatible = "ti,omap2", },
 	{ .compatible = "ti,omap3", },
 	{ .compatible = "ti,omap4", },
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 269013311e79..c943787d761e 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -148,7 +148,6 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	struct private_data *priv;
 	struct device *cpu_dev;
 	struct clk *cpu_clk;
-	struct dev_pm_opp *suspend_opp;
 	unsigned int transition_latency;
 	bool fallback = false;
 	const char *name;
@@ -252,11 +251,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	policy->driver_data = priv;
 	policy->clk = cpu_clk;
 
-	rcu_read_lock();
-	suspend_opp = dev_pm_opp_get_suspend_opp(cpu_dev);
-	if (suspend_opp)
-		policy->suspend_freq = dev_pm_opp_get_freq(suspend_opp) / 1000;
-	rcu_read_unlock();
+	policy->suspend_freq = dev_pm_opp_get_suspend_opp_freq(cpu_dev) / 1000;
 
 	ret = cpufreq_table_validate_and_show(policy, freq_table);
 	if (ret) {
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 3e9b319a2e79..a47543281864 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1078,15 +1078,11 @@ err_free_policy:
 	return NULL;
 }
 
-static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify)
+static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
 {
 	struct kobject *kobj;
 	struct completion *cmp;
 
-	if (notify)
-		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-					     CPUFREQ_REMOVE_POLICY, policy);
-
 	down_write(&policy->rwsem);
 	cpufreq_stats_free_table(policy);
 	kobj = &policy->kobj;
@@ -1104,7 +1100,7 @@ static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify)
 	pr_debug("wait complete\n");
 }
 
-static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify)
+static void cpufreq_policy_free(struct cpufreq_policy *policy)
 {
 	unsigned long flags;
 	int cpu;
@@ -1117,7 +1113,7 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify)
 		per_cpu(cpufreq_cpu_data, cpu) = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	cpufreq_policy_put_kobj(policy, notify);
+	cpufreq_policy_put_kobj(policy);
 	free_cpumask_var(policy->real_cpus);
 	free_cpumask_var(policy->related_cpus);
 	free_cpumask_var(policy->cpus);
@@ -1170,8 +1166,6 @@ static int cpufreq_online(unsigned int cpu)
 	if (new_policy) {
 		/* related_cpus should at least include policy->cpus. */
 		cpumask_copy(policy->related_cpus, policy->cpus);
-		/* Clear mask of registered CPUs */
-		cpumask_clear(policy->real_cpus);
 	}
 
 	/*
@@ -1244,17 +1238,12 @@ static int cpufreq_online(unsigned int cpu)
 			goto out_exit_policy;
 
 		cpufreq_stats_create_table(policy);
-		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-				CPUFREQ_CREATE_POLICY, policy);
 
 		write_lock_irqsave(&cpufreq_driver_lock, flags);
 		list_add(&policy->policy_list, &cpufreq_policy_list);
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 	}
 
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-				     CPUFREQ_START, policy);
-
 	ret = cpufreq_init_policy(policy);
 	if (ret) {
 		pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n",
@@ -1282,7 +1271,7 @@ out_exit_policy:
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 out_free_policy:
-	cpufreq_policy_free(policy, !new_policy);
+	cpufreq_policy_free(policy);
 	return ret;
 }
 
@@ -1403,7 +1392,7 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	remove_cpu_dev_symlink(policy, dev);
 
 	if (cpumask_empty(policy->real_cpus))
-		cpufreq_policy_free(policy, true);
+		cpufreq_policy_free(policy);
 }
 
 /**
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 17048bbec287..f570ead62454 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -24,9 +24,7 @@ struct cpufreq_stats {
 	unsigned int last_index;
 	u64 *time_in_state;
 	unsigned int *freq_table;
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	unsigned int *trans_table;
-#endif
 };
 
 static int cpufreq_stats_update(struct cpufreq_stats *stats)
@@ -45,9 +43,7 @@ static void cpufreq_stats_clear_table(struct cpufreq_stats *stats)
 	unsigned int count = stats->max_state;
 
 	memset(stats->time_in_state, 0, count * sizeof(u64));
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	memset(stats->trans_table, 0, count * count * sizeof(int));
-#endif
 	stats->last_time = get_jiffies_64();
 	stats->total_trans = 0;
 }
@@ -83,7 +79,6 @@ static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf,
 	return count;
 }
 
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 {
 	struct cpufreq_stats *stats = policy->stats;
@@ -128,7 +123,6 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 	return len;
 }
 cpufreq_freq_attr_ro(trans_table);
-#endif
 
 cpufreq_freq_attr_ro(total_trans);
 cpufreq_freq_attr_ro(time_in_state);
@@ -138,9 +132,7 @@ static struct attribute *default_attrs[] = {
 	&total_trans.attr,
 	&time_in_state.attr,
 	&reset.attr,
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	&trans_table.attr,
-#endif
 	NULL
 };
 static struct attribute_group stats_attr_group = {
@@ -199,9 +191,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 
 	alloc_size = count * sizeof(int) + count * sizeof(u64);
 
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	alloc_size += count * count * sizeof(int);
-#endif
 
 	/* Allocate memory for time_in_state/freq_table/trans_table in one go */
 	stats->time_in_state = kzalloc(alloc_size, GFP_KERNEL);
@@ -210,9 +200,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 
 	stats->freq_table = (unsigned int *)(stats->time_in_state + count);
 
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	stats->trans_table = stats->freq_table + count;
-#endif
 
 	stats->max_state = count;
 
@@ -258,8 +246,6 @@ void cpufreq_stats_record_transition(struct cpufreq_policy *policy,
 	cpufreq_stats_update(stats);
 
 	stats->last_index = new_index;
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	stats->trans_table[old_index * stats->max_state + new_index]++;
-#endif
 	stats->total_trans++;
 }
diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index c0f3373706f4..9180d34cc9fc 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -118,12 +118,10 @@ static int init_div_table(void)
 	unsigned int tmp, clk_div, ema_div, freq, volt_id;
 	struct dev_pm_opp *opp;
 
-	rcu_read_lock();
 	cpufreq_for_each_entry(pos, freq_tbl) {
 		opp = dev_pm_opp_find_freq_exact(dvfs_info->dev,
 					pos->frequency * 1000, true);
 		if (IS_ERR(opp)) {
-			rcu_read_unlock();
 			dev_err(dvfs_info->dev,
 				"failed to find valid OPP for %u KHZ\n",
 				pos->frequency);
@@ -140,6 +138,7 @@ static int init_div_table(void)
 
 		/* Calculate EMA */
 		volt_id = dev_pm_opp_get_voltage(opp);
+
 		volt_id = (MAX_VOLTAGE - volt_id) / VOLTAGE_STEP;
 		if (volt_id < PMIC_HIGH_VOLT) {
 			ema_div = (CPUEMA_HIGH << P0_7_CPUEMA_SHIFT) |
@@ -157,9 +156,9 @@ static int init_div_table(void)
 
 		__raw_writel(tmp, dvfs_info->base + XMU_PMU_P0_7 + 4 *
 						(pos - freq_tbl));
+		dev_pm_opp_put(opp);
 	}
 
-	rcu_read_unlock();
 	return 0;
 }
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index ef1fa8145419..7719b02e04f5 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -53,16 +53,15 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 	freq_hz = new_freq * 1000;
 	old_freq = clk_get_rate(arm_clk) / 1000;
 
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		dev_err(cpu_dev, "failed to find OPP for %ld\n", freq_hz);
 		return PTR_ERR(opp);
 	}
 
 	volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
+
 	volt_old = regulator_get_voltage(arm_reg);
 
 	dev_dbg(cpu_dev, "%u MHz, %ld mV --> %u MHz, %ld mV\n",
@@ -321,14 +320,15 @@ soc_opp_out:
 	 * freq_table initialised from OPP is therefore sorted in the
 	 * same order.
 	 */
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_exact(cpu_dev,
 				  freq_table[0].frequency * 1000, true);
 	min_volt = dev_pm_opp_get_voltage(opp);
+	dev_pm_opp_put(opp);
 	opp = dev_pm_opp_find_freq_exact(cpu_dev,
 				  freq_table[--num].frequency * 1000, true);
 	max_volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
+
 	ret = regulator_set_voltage_time(arm_reg, min_volt, max_volt);
 	if (ret > 0)
 		transition_latency += ret * 1000;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 50bd6d987fc3..eb0f7fb71685 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -358,6 +358,8 @@ static struct pstate_funcs pstate_funcs __read_mostly;
 static int hwp_active __read_mostly;
 static bool per_cpu_limits __read_mostly;
 
+static bool driver_registered __read_mostly;
+
 #ifdef CONFIG_ACPI
 static bool acpi_ppc;
 #endif
@@ -394,6 +396,7 @@ static struct perf_limits *limits = &performance_limits;
 static struct perf_limits *limits = &powersave_limits;
 #endif
 
+static DEFINE_MUTEX(intel_pstate_driver_lock);
 static DEFINE_MUTEX(intel_pstate_limits_lock);
 
 #ifdef CONFIG_ACPI
@@ -538,7 +541,6 @@ static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
 
 	acpi_processor_unregister_performance(policy->cpu);
 }
-
 #else
 static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
 {
@@ -873,7 +875,10 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
 
 		rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
 		hw_min = HWP_LOWEST_PERF(cap);
-		hw_max = HWP_HIGHEST_PERF(cap);
+		if (limits->no_turbo)
+			hw_max = HWP_GUARANTEED_PERF(cap);
+		else
+			hw_max = HWP_HIGHEST_PERF(cap);
 		range = hw_max - hw_min;
 
 		max_perf_pct = perf_limits->max_perf_pct;
@@ -887,11 +892,6 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
 
 		adj_range = max_perf_pct * range / 100;
 		max = hw_min + adj_range;
-		if (limits->no_turbo) {
-			hw_max = HWP_GUARANTEED_PERF(cap);
-			if (hw_max < max)
-				max = hw_max;
-		}
 
 		value &= ~HWP_MAX_PERF(~0L);
 		value |= HWP_MAX_PERF(max);
@@ -1007,35 +1007,57 @@ static int pid_param_get(void *data, u64 *val)
 }
 DEFINE_SIMPLE_ATTRIBUTE(fops_pid_param, pid_param_get, pid_param_set, "%llu\n");
 
+static struct dentry *debugfs_parent;
+
 struct pid_param {
 	char *name;
 	void *value;
+	struct dentry *dentry;
 };
 
 static struct pid_param pid_files[] = {
-	{"sample_rate_ms", &pid_params.sample_rate_ms},
-	{"d_gain_pct", &pid_params.d_gain_pct},
-	{"i_gain_pct", &pid_params.i_gain_pct},
-	{"deadband", &pid_params.deadband},
-	{"setpoint", &pid_params.setpoint},
-	{"p_gain_pct", &pid_params.p_gain_pct},
-	{NULL, NULL}
+	{"sample_rate_ms", &pid_params.sample_rate_ms, },
+	{"d_gain_pct", &pid_params.d_gain_pct, },
+	{"i_gain_pct", &pid_params.i_gain_pct, },
+	{"deadband", &pid_params.deadband, },
+	{"setpoint", &pid_params.setpoint, },
+	{"p_gain_pct", &pid_params.p_gain_pct, },
+	{NULL, NULL, }
 };
 
-static void __init intel_pstate_debug_expose_params(void)
+static void intel_pstate_debug_expose_params(void)
 {
-	struct dentry *debugfs_parent;
-	int i = 0;
+	int i;
 
 	debugfs_parent = debugfs_create_dir("pstate_snb", NULL);
 	if (IS_ERR_OR_NULL(debugfs_parent))
 		return;
-	while (pid_files[i].name) {
-		debugfs_create_file(pid_files[i].name, 0660,
-				    debugfs_parent, pid_files[i].value,
-				    &fops_pid_param);
-		i++;
+
+	for (i = 0; pid_files[i].name; i++) {
+		struct dentry *dentry;
+
+		dentry = debugfs_create_file(pid_files[i].name, 0660,
+					     debugfs_parent, pid_files[i].value,
+					     &fops_pid_param);
+		if (!IS_ERR(dentry))
+			pid_files[i].dentry = dentry;
+	}
+}
+
+static void intel_pstate_debug_hide_params(void)
+{
+	int i;
+
+	if (IS_ERR_OR_NULL(debugfs_parent))
+		return;
+
+	for (i = 0; pid_files[i].name; i++) {
+		debugfs_remove(pid_files[i].dentry);
+		pid_files[i].dentry = NULL;
 	}
+
+	debugfs_remove(debugfs_parent);
+	debugfs_parent = NULL;
 }
 
 /************************** debugfs end ************************/
@@ -1048,6 +1070,34 @@ static void __init intel_pstate_debug_expose_params(void)
 		return sprintf(buf, "%u\n", limits->object);		\
 	}
 
+static ssize_t intel_pstate_show_status(char *buf);
+static int intel_pstate_update_status(const char *buf, size_t size);
+
+static ssize_t show_status(struct kobject *kobj,
+			   struct attribute *attr, char *buf)
+{
+	ssize_t ret;
+
+	mutex_lock(&intel_pstate_driver_lock);
+	ret = intel_pstate_show_status(buf);
+	mutex_unlock(&intel_pstate_driver_lock);
+
+	return ret;
+}
+
+static ssize_t store_status(struct kobject *a, struct attribute *b,
+			    const char *buf, size_t count)
+{
+	char *p = memchr(buf, '\n', count);
+	int ret;
+
+	mutex_lock(&intel_pstate_driver_lock);
+	ret = intel_pstate_update_status(buf, p ? p - buf : count);
+	mutex_unlock(&intel_pstate_driver_lock);
+
+	return ret < 0 ? ret : count;
+}
+
 static ssize_t show_turbo_pct(struct kobject *kobj,
 				struct attribute *attr, char *buf)
 {
@@ -1055,12 +1105,22 @@ static ssize_t show_turbo_pct(struct kobject *kobj,
 	int total, no_turbo, turbo_pct;
 	uint32_t turbo_fp;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	cpu = all_cpu_data[0];
 
 	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(no_turbo, total);
 	turbo_pct = 100 - fp_toint(mul_fp(turbo_fp, int_tofp(100)));
+
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return sprintf(buf, "%u\n", turbo_pct);
 }
 
@@ -1070,8 +1130,18 @@ static ssize_t show_num_pstates(struct kobject *kobj,
 	struct cpudata *cpu;
 	int total;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	cpu = all_cpu_data[0];
 	total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1;
+
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return sprintf(buf, "%u\n", total);
 }
 
@@ -1080,12 +1150,21 @@ static ssize_t show_no_turbo(struct kobject *kobj,
 {
 	ssize_t ret;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	update_turbo_state();
 	if (limits->turbo_disabled)
 		ret = sprintf(buf, "%u\n", limits->turbo_disabled);
 	else
 		ret = sprintf(buf, "%u\n", limits->no_turbo);
 
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return ret;
 }
 
@@ -1099,12 +1178,20 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	mutex_lock(&intel_pstate_limits_lock);
 
 	update_turbo_state();
 	if (limits->turbo_disabled) {
 		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
 		mutex_unlock(&intel_pstate_limits_lock);
+		mutex_unlock(&intel_pstate_driver_lock);
 		return -EPERM;
 	}
 
@@ -1114,6 +1201,8 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 
 	intel_pstate_update_policies();
 
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return count;
 }
 
@@ -1127,6 +1216,13 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	mutex_lock(&intel_pstate_limits_lock);
 
 	limits->max_sysfs_pct = clamp_t(int, input, 0 , 100);
@@ -1142,6 +1238,8 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 
 	intel_pstate_update_policies();
 
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return count;
 }
 
@@ -1155,6 +1253,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	mutex_lock(&intel_pstate_limits_lock);
 
 	limits->min_sysfs_pct = clamp_t(int, input, 0 , 100);
@@ -1170,12 +1275,15 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 
 	intel_pstate_update_policies();
 
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return count;
 }
 
 show_one(max_perf_pct, max_perf_pct);
 show_one(min_perf_pct, min_perf_pct);
 
+define_one_global_rw(status);
 define_one_global_rw(no_turbo);
 define_one_global_rw(max_perf_pct);
 define_one_global_rw(min_perf_pct);
@@ -1183,6 +1291,7 @@ define_one_global_ro(turbo_pct);
 define_one_global_ro(num_pstates);
 
 static struct attribute *intel_pstate_attributes[] = {
+	&status.attr,
 	&no_turbo.attr,
 	&turbo_pct.attr,
 	&num_pstates.attr,
@@ -1364,48 +1473,71 @@ static int core_get_max_pstate_physical(void)
 	return (value >> 8) & 0xFF;
 }
 
+static int core_get_tdp_ratio(u64 plat_info)
+{
+	/* Check how many TDP levels present */
+	if (plat_info & 0x600000000) {
+		u64 tdp_ctrl;
+		u64 tdp_ratio;
+		int tdp_msr;
+		int err;
+
+		/* Get the TDP level (0, 1, 2) to get ratios */
+		err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
+		if (err)
+			return err;
+
+		/* TDP MSR are continuous starting at 0x648 */
+		tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x03);
+		err = rdmsrl_safe(tdp_msr, &tdp_ratio);
+		if (err)
+			return err;
+
+		/* For level 1 and 2, bits[23:16] contain the ratio */
+		if (tdp_ctrl & 0x03)
+			tdp_ratio >>= 16;
+
+		tdp_ratio &= 0xff; /* ratios are only 8 bits long */
+		pr_debug("tdp_ratio %x\n", (int)tdp_ratio);
+
+		return (int)tdp_ratio;
+	}
+
+	return -ENXIO;
+}
+
 static int core_get_max_pstate(void)
 {
 	u64 tar;
 	u64 plat_info;
 	int max_pstate;
+	int tdp_ratio;
 	int err;
 
 	rdmsrl(MSR_PLATFORM_INFO, plat_info);
 	max_pstate = (plat_info >> 8) & 0xFF;
 
+	tdp_ratio = core_get_tdp_ratio(plat_info);
+	if (tdp_ratio <= 0)
+		return max_pstate;
+
+	if (hwp_active) {
+		/* Turbo activation ratio is not used on HWP platforms */
+		return tdp_ratio;
+	}
+
 	err = rdmsrl_safe(MSR_TURBO_ACTIVATION_RATIO, &tar);
 	if (!err) {
+		int tar_levels;
+
 		/* Do some sanity checking for safety */
-		if (plat_info & 0x600000000) {
-			u64 tdp_ctrl;
-			u64 tdp_ratio;
-			int tdp_msr;
-
-			err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
-			if (err)
-				goto skip_tar;
-
-			tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x3);
-			err = rdmsrl_safe(tdp_msr, &tdp_ratio);
-			if (err)
-				goto skip_tar;
-
-			/* For level 1 and 2, bits[23:16] contain the ratio */
-			if (tdp_ctrl)
-				tdp_ratio >>= 16;
-
-			tdp_ratio &= 0xff; /* ratios are only 8 bits long */
-			if (tdp_ratio - 1 == tar) {
-				max_pstate = tar;
-				pr_debug("max_pstate=TAC %x\n", max_pstate);
-			} else {
-				goto skip_tar;
-			}
+		tar_levels = tar & 0xff;
+		if (tdp_ratio - 1 == tar_levels) {
+			max_pstate = tar_levels;
+			pr_debug("max_pstate=TAC %x\n", max_pstate);
 		}
 	}
 
-skip_tar:
 	return max_pstate;
 }
 
@@ -2072,6 +2204,20 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 
 static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
 {
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+	struct perf_limits *perf_limits;
+
+	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE)
+		perf_limits = &performance_limits;
+	else
+		perf_limits = &powersave_limits;
+
+	update_turbo_state();
+	policy->cpuinfo.max_freq = perf_limits->turbo_disabled ||
+					perf_limits->no_turbo ?
+					cpu->pstate.max_freq :
+					cpu->pstate.turbo_freq;
+
 	cpufreq_verify_within_cpu_limits(policy);
 
 	if (policy->policy != CPUFREQ_POLICY_POWERSAVE &&
@@ -2299,6 +2445,111 @@ static struct cpufreq_driver intel_cpufreq = {
 
 static struct cpufreq_driver *intel_pstate_driver = &intel_pstate;
 
+static void intel_pstate_driver_cleanup(void)
+{
+	unsigned int cpu;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		if (all_cpu_data[cpu]) {
+			if (intel_pstate_driver == &intel_pstate)
+				intel_pstate_clear_update_util_hook(cpu);
+
+			kfree(all_cpu_data[cpu]);
+			all_cpu_data[cpu] = NULL;
+		}
+	}
+	put_online_cpus();
+}
+
+static int intel_pstate_register_driver(void)
+{
+	int ret;
+
+	ret = cpufreq_register_driver(intel_pstate_driver);
+	if (ret) {
+		intel_pstate_driver_cleanup();
+		return ret;
+	}
+
+	mutex_lock(&intel_pstate_limits_lock);
+	driver_registered = true;
+	mutex_unlock(&intel_pstate_limits_lock);
+
+	if (intel_pstate_driver == &intel_pstate && !hwp_active &&
+	    pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
+		intel_pstate_debug_expose_params();
+
+	return 0;
+}
+
+static int intel_pstate_unregister_driver(void)
+{
+	if (hwp_active)
+		return -EBUSY;
+
+	if (intel_pstate_driver == &intel_pstate && !hwp_active &&
+	    pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
+		intel_pstate_debug_hide_params();
+
+	mutex_lock(&intel_pstate_limits_lock);
+	driver_registered = false;
+	mutex_unlock(&intel_pstate_limits_lock);
+
+	cpufreq_unregister_driver(intel_pstate_driver);
+	intel_pstate_driver_cleanup();
+
+	return 0;
+}
+
+static ssize_t intel_pstate_show_status(char *buf)
+{
+	if (!driver_registered)
+		return sprintf(buf, "off\n");
+
+	return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ?
+					"active" : "passive");
+}
+
+static int intel_pstate_update_status(const char *buf, size_t size)
+{
+	int ret;
+
+	if (size == 3 && !strncmp(buf, "off", size))
+		return driver_registered ?
+			intel_pstate_unregister_driver() : -EINVAL;
+
+	if (size == 6 && !strncmp(buf, "active", size)) {
+		if (driver_registered) {
+			if (intel_pstate_driver == &intel_pstate)
+				return 0;
+
+			ret = intel_pstate_unregister_driver();
+			if (ret)
+				return ret;
+		}
+
+		intel_pstate_driver = &intel_pstate;
+		return intel_pstate_register_driver();
+	}
+
+	if (size == 7 && !strncmp(buf, "passive", size)) {
+		if (driver_registered) {
+			if (intel_pstate_driver != &intel_pstate)
+				return 0;
+
+			ret = intel_pstate_unregister_driver();
+			if (ret)
+				return ret;
+		}
+
+		intel_pstate_driver = &intel_cpufreq;
+		return intel_pstate_register_driver();
+	}
+
+	return -EINVAL;
+}
+
 static int no_load __initdata;
 static int no_hwp __initdata;
 static int hwp_only __initdata;
@@ -2486,9 +2737,9 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = {
 
 static int __init intel_pstate_init(void)
 {
-	int cpu, rc = 0;
 	const struct x86_cpu_id *id;
 	struct cpu_defaults *cpu_def;
+	int rc = 0;
 
 	if (no_load)
 		return -ENODEV;
@@ -2520,45 +2771,29 @@ hwp_cpu_matched:
 	if (intel_pstate_platform_pwr_mgmt_exists())
 		return -ENODEV;
 
+	if (!hwp_active && hwp_only)
+		return -ENOTSUPP;
+
 	pr_info("Intel P-state driver initializing\n");
 
 	all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
 	if (!all_cpu_data)
 		return -ENOMEM;
 
-	if (!hwp_active && hwp_only)
-		goto out;
-
 	intel_pstate_request_control_from_smm();
 
-	rc = cpufreq_register_driver(intel_pstate_driver);
-	if (rc)
-		goto out;
-
-	if (intel_pstate_driver == &intel_pstate && !hwp_active &&
-	    pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
-		intel_pstate_debug_expose_params();
-
 	intel_pstate_sysfs_expose_params();
 
+	mutex_lock(&intel_pstate_driver_lock);
+	rc = intel_pstate_register_driver();
+	mutex_unlock(&intel_pstate_driver_lock);
+	if (rc)
+		return rc;
+
 	if (hwp_active)
 		pr_info("HWP enabled\n");
 
-	return rc;
-out:
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		if (all_cpu_data[cpu]) {
-			if (intel_pstate_driver == &intel_pstate)
-				intel_pstate_clear_update_util_hook(cpu);
-
-			kfree(all_cpu_data[cpu]);
-		}
-	}
-
-	put_online_cpus();
-	vfree(all_cpu_data);
-	return -ENODEV;
+	return 0;
 }
 device_initcall(intel_pstate_init);
 
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index 643f43179df1..ab25b1235a5e 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -232,16 +232,14 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
 
 	freq_hz = freq_table[index].frequency * 1000;
 
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		pr_err("cpu%d: failed to find OPP for %ld\n",
 		       policy->cpu, freq_hz);
 		return PTR_ERR(opp);
 	}
 	vproc = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	/*
 	 * If the new voltage or the intermediate voltage is higher than the
@@ -411,16 +409,14 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
 
 	/* Search a safe voltage for intermediate frequency. */
 	rate = clk_get_rate(inter_clk);
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &rate);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		pr_err("failed to get intermediate opp for cpu%d\n", cpu);
 		ret = PTR_ERR(opp);
 		goto out_free_opp_table;
 	}
 	info->intermediate_voltage = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	info->cpu_dev = cpu_dev;
 	info->proc_reg = proc_reg;
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 376e63ca94e8..71e81bbf031b 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -63,16 +63,14 @@ static int omap_target(struct cpufreq_policy *policy, unsigned int index)
 	freq = ret;
 
 	if (mpu_reg) {
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_ceil(mpu_dev, &freq);
 		if (IS_ERR(opp)) {
-			rcu_read_unlock();
 			dev_err(mpu_dev, "%s: unable to find MPU OPP for %d\n",
 				__func__, new_freq);
 			return -EINVAL;
 		}
 		volt = dev_pm_opp_get_voltage(opp);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		tol = volt * OPP_TOLERANCE / 100;
 		volt_old = regulator_get_voltage(mpu_reg);
 	}
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 37671b545880..3ff5160451b4 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -144,6 +144,7 @@ static struct powernv_pstate_info {
 	unsigned int max;
 	unsigned int nominal;
 	unsigned int nr_pstates;
+	bool wof_enabled;
 } powernv_pstate_info;
 
 /* Use following macros for conversions between pstate_id and index */
@@ -203,6 +204,7 @@ static int init_powernv_pstates(void)
 	const __be32 *pstate_ids, *pstate_freqs;
 	u32 len_ids, len_freqs;
 	u32 pstate_min, pstate_max, pstate_nominal;
+	u32 pstate_turbo, pstate_ultra_turbo;
 
 	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
 	if (!power_mgt) {
@@ -225,8 +227,29 @@ static int init_powernv_pstates(void)
 		pr_warn("ibm,pstate-nominal not found\n");
 		return -ENODEV;
 	}
+
+	if (of_property_read_u32(power_mgt, "ibm,pstate-ultra-turbo",
+				 &pstate_ultra_turbo)) {
+		powernv_pstate_info.wof_enabled = false;
+		goto next;
+	}
+
+	if (of_property_read_u32(power_mgt, "ibm,pstate-turbo",
+				 &pstate_turbo)) {
+		powernv_pstate_info.wof_enabled = false;
+		goto next;
+	}
+
+	if (pstate_turbo == pstate_ultra_turbo)
+		powernv_pstate_info.wof_enabled = false;
+	else
+		powernv_pstate_info.wof_enabled = true;
+
+next:
 	pr_info("cpufreq pstate min %d nominal %d max %d\n", pstate_min,
 		pstate_nominal, pstate_max);
+	pr_info("Workload Optimized Frequency is %s in the platform\n",
+		(powernv_pstate_info.wof_enabled) ? "enabled" : "disabled");
 
 	pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids);
 	if (!pstate_ids) {
@@ -268,6 +291,13 @@ static int init_powernv_pstates(void)
 			powernv_pstate_info.nominal = i;
 		else if (id == pstate_min)
 			powernv_pstate_info.min = i;
+
+		if (powernv_pstate_info.wof_enabled && id == pstate_turbo) {
+			int j;
+
+			for (j = i - 1; j >= (int)powernv_pstate_info.max; j--)
+				powernv_freqs[j].flags = CPUFREQ_BOOST_FREQ;
+		}
 	}
 
 	/* End of list marker entry */
@@ -305,9 +335,12 @@ static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy,
 struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq =
 	__ATTR_RO(cpuinfo_nominal_freq);
 
+#define SCALING_BOOST_FREQS_ATTR_INDEX		2
+
 static struct freq_attr *powernv_cpu_freq_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
 	&cpufreq_freq_attr_cpuinfo_nominal_freq,
+	&cpufreq_freq_attr_scaling_boost_freqs,
 	NULL,
 };
 
@@ -1013,11 +1046,22 @@ static int __init powernv_cpufreq_init(void)
 	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
 	opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb);
 
+	if (powernv_pstate_info.wof_enabled)
+		powernv_cpufreq_driver.boost_enabled = true;
+	else
+		powernv_cpu_freq_attr[SCALING_BOOST_FREQS_ATTR_INDEX] = NULL;
+
 	rc = cpufreq_register_driver(&powernv_cpufreq_driver);
-	if (!rc)
-		return 0;
+	if (rc) {
+		pr_info("Failed to register the cpufreq driver (%d)\n", rc);
+		goto cleanup_notifiers;
+	}
 
-	pr_info("Failed to register the cpufreq driver (%d)\n", rc);
+	if (powernv_pstate_info.wof_enabled)
+		cpufreq_enable_boost_support();
+
+	return 0;
+cleanup_notifiers:
 	unregister_all_notifiers();
 	clean_chip_info();
 out:
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index dc112481a408..eeaa92251512 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -100,9 +100,6 @@ static int pmi_notifier(struct notifier_block *nb,
 	/* Should this really be called for CPUFREQ_ADJUST and CPUFREQ_NOTIFY
 	 * policy events?)
 	 */
-	if (event == CPUFREQ_START)
-		return 0;
-
 	node = cbe_cpu_to_node(policy->cpu);
 
 	pr_debug("got notified, event=%lu, node=%u\n", event, node);
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index 53d8c3fb16f6..a6fefac8afe4 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -11,6 +11,7 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/clk.h>
+#include <linux/clk-provider.h>
 #include <linux/cpufreq.h>
 #include <linux/cpu_cooling.h>
 #include <linux/errno.h>
@@ -37,53 +38,20 @@ struct cpu_data {
 	struct thermal_cooling_device *cdev;
 };
 
+/*
+ * Don't use cpufreq on this SoC -- used when the SoC would have otherwise
+ * matched a more generic compatible.
+ */
+#define SOC_BLACKLIST		1
+
 /**
  * struct soc_data - SoC specific data
- * @freq_mask: mask the disallowed frequencies
- * @flag: unique flags
+ * @flags: SOC_xxx
  */
 struct soc_data {
-	u32 freq_mask[4];
-	u32 flag;
-};
-
-#define FREQ_MASK	1
-/* see hardware specification for the allowed frqeuencies */
-static const struct soc_data sdata[] = {
-	{ /* used by p2041 and p3041 */
-		.freq_mask = {0x8, 0x8, 0x2, 0x2},
-		.flag = FREQ_MASK,
-	},
-	{ /* used by p5020 */
-		.freq_mask = {0x8, 0x2},
-		.flag = FREQ_MASK,
-	},
-	{ /* used by p4080, p5040 */
-		.freq_mask = {0},
-		.flag = 0,
-	},
+	u32 flags;
 };
 
-/*
- * the minimum allowed core frequency, in Hz
- * for chassis v1.0, >= platform frequency
- * for chassis v2.0, >= platform frequency / 2
- */
-static u32 min_cpufreq;
-static const u32 *fmask;
-
-#if defined(CONFIG_ARM)
-static int get_cpu_physical_id(int cpu)
-{
-	return topology_core_id(cpu);
-}
-#else
-static int get_cpu_physical_id(int cpu)
-{
-	return get_hard_smp_processor_id(cpu);
-}
-#endif
-
 static u32 get_bus_freq(void)
 {
 	struct device_node *soc;
@@ -101,9 +69,10 @@ static u32 get_bus_freq(void)
 	return sysfreq;
 }
 
-static struct device_node *cpu_to_clk_node(int cpu)
+static struct clk *cpu_to_clk(int cpu)
 {
-	struct device_node *np, *clk_np;
+	struct device_node *np;
+	struct clk *clk;
 
 	if (!cpu_present(cpu))
 		return NULL;
@@ -112,37 +81,28 @@ static struct device_node *cpu_to_clk_node(int cpu)
 	if (!np)
 		return NULL;
 
-	clk_np = of_parse_phandle(np, "clocks", 0);
-	if (!clk_np)
-		return NULL;
-
+	clk = of_clk_get(np, 0);
 	of_node_put(np);
-
-	return clk_np;
+	return clk;
 }
 
 /* traverse cpu nodes to get cpu mask of sharing clock wire */
 static void set_affected_cpus(struct cpufreq_policy *policy)
 {
-	struct device_node *np, *clk_np;
 	struct cpumask *dstp = policy->cpus;
+	struct clk *clk;
 	int i;
 
-	np = cpu_to_clk_node(policy->cpu);
-	if (!np)
-		return;
-
 	for_each_present_cpu(i) {
-		clk_np = cpu_to_clk_node(i);
-		if (!clk_np)
+		clk = cpu_to_clk(i);
+		if (IS_ERR(clk)) {
+			pr_err("%s: no clock for cpu %d\n", __func__, i);
 			continue;
+		}
 
-		if (clk_np == np)
+		if (clk_is_match(policy->clk, clk))
 			cpumask_set_cpu(i, dstp);
-
-		of_node_put(clk_np);
 	}
-	of_node_put(np);
 }
 
 /* reduce the duplicated frequencies in frequency table */
@@ -198,10 +158,11 @@ static void freq_table_sort(struct cpufreq_frequency_table *freq_table,
 
 static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	struct device_node *np, *pnode;
+	struct device_node *np;
 	int i, count, ret;
-	u32 freq, mask;
+	u32 freq;
 	struct clk *clk;
+	const struct clk_hw *hwclk;
 	struct cpufreq_frequency_table *table;
 	struct cpu_data *data;
 	unsigned int cpu = policy->cpu;
@@ -221,17 +182,13 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_nomem2;
 	}
 
-	pnode = of_parse_phandle(np, "clocks", 0);
-	if (!pnode) {
-		pr_err("%s: could not get clock information\n", __func__);
-		goto err_nomem2;
-	}
+	hwclk = __clk_get_hw(policy->clk);
+	count = clk_hw_get_num_parents(hwclk);
 
-	count = of_property_count_strings(pnode, "clock-names");
 	data->pclk = kcalloc(count, sizeof(struct clk *), GFP_KERNEL);
 	if (!data->pclk) {
 		pr_err("%s: no memory\n", __func__);
-		goto err_node;
+		goto err_nomem2;
 	}
 
 	table = kcalloc(count + 1, sizeof(*table), GFP_KERNEL);
@@ -240,23 +197,11 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_pclk;
 	}
 
-	if (fmask)
-		mask = fmask[get_cpu_physical_id(cpu)];
-	else
-		mask = 0x0;
-
 	for (i = 0; i < count; i++) {
-		clk = of_clk_get(pnode, i);
+		clk = clk_hw_get_parent_by_index(hwclk, i)->clk;
 		data->pclk[i] = clk;
 		freq = clk_get_rate(clk);
-		/*
-		 * the clock is valid if its frequency is not masked
-		 * and large than minimum allowed frequency.
-		 */
-		if (freq < min_cpufreq || (mask & (1 << i)))
-			table[i].frequency = CPUFREQ_ENTRY_INVALID;
-		else
-			table[i].frequency = freq / 1000;
+		table[i].frequency = freq / 1000;
 		table[i].driver_data = i;
 	}
 	freq_table_redup(table, count);
@@ -282,7 +227,6 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency = u64temp + 1;
 
 	of_node_put(np);
-	of_node_put(pnode);
 
 	return 0;
 
@@ -290,10 +234,7 @@ err_nomem1:
 	kfree(table);
 err_pclk:
 	kfree(data->pclk);
-err_node:
-	of_node_put(pnode);
 err_nomem2:
-	policy->driver_data = NULL;
 	kfree(data);
 err_np:
 	of_node_put(np);
@@ -357,12 +298,25 @@ static struct cpufreq_driver qoriq_cpufreq_driver = {
 	.attr		= cpufreq_generic_attr,
 };
 
+static const struct soc_data blacklist = {
+	.flags = SOC_BLACKLIST,
+};
+
 static const struct of_device_id node_matches[] __initconst = {
-	{ .compatible = "fsl,p2041-clockgen", .data = &sdata[0], },
-	{ .compatible = "fsl,p3041-clockgen", .data = &sdata[0], },
-	{ .compatible = "fsl,p5020-clockgen", .data = &sdata[1], },
-	{ .compatible = "fsl,p4080-clockgen", .data = &sdata[2], },
-	{ .compatible = "fsl,p5040-clockgen", .data = &sdata[2], },
+	/* e6500 cannot use cpufreq due to erratum A-008083 */
+	{ .compatible = "fsl,b4420-clockgen", &blacklist },
+	{ .compatible = "fsl,b4860-clockgen", &blacklist },
+	{ .compatible = "fsl,t2080-clockgen", &blacklist },
+	{ .compatible = "fsl,t4240-clockgen", &blacklist },
+
+	{ .compatible = "fsl,ls1012a-clockgen", },
+	{ .compatible = "fsl,ls1021a-clockgen", },
+	{ .compatible = "fsl,ls1043a-clockgen", },
+	{ .compatible = "fsl,ls1046a-clockgen", },
+	{ .compatible = "fsl,ls1088a-clockgen", },
+	{ .compatible = "fsl,ls2080a-clockgen", },
+	{ .compatible = "fsl,p4080-clockgen", },
+	{ .compatible = "fsl,qoriq-clockgen-1.0", },
 	{ .compatible = "fsl,qoriq-clockgen-2.0", },
 	{}
 };
@@ -380,16 +334,12 @@ static int __init qoriq_cpufreq_init(void)
 
 	match = of_match_node(node_matches, np);
 	data = match->data;
-	if (data) {
-		if (data->flag)
-			fmask = data->freq_mask;
-		min_cpufreq = get_bus_freq();
-	} else {
-		min_cpufreq = get_bus_freq() / 2;
-	}
 
 	of_node_put(np);
 
+	if (data && data->flags & SOC_BLACKLIST)
+		return -ENODEV;
+
 	ret = cpufreq_register_driver(&qoriq_cpufreq_driver);
 	if (!ret)
 		pr_info("Freescale QorIQ CPU frequency scaling driver\n");
diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c
index d6d425773fa4..5b2db3c6568f 100644
--- a/drivers/cpufreq/s3c2416-cpufreq.c
+++ b/drivers/cpufreq/s3c2416-cpufreq.c
@@ -400,7 +400,6 @@ static int s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy)
 	rate = clk_get_rate(s3c_freq->hclk);
 	if (rate < 133 * 1000 * 1000) {
 		pr_err("cpufreq: HCLK not at 133MHz\n");
-		clk_put(s3c_freq->hclk);
 		ret = -EINVAL;
 		goto err_armclk;
 	}
diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c
index b366e6d830ea..a7db9011d5fe 100644
--- a/drivers/cpufreq/sti-cpufreq.c
+++ b/drivers/cpufreq/sti-cpufreq.c
@@ -160,6 +160,7 @@ static int sti_cpufreq_set_opp_info(void)
 	int pcode, substrate, major, minor;
 	int ret;
 	char name[MAX_PCODE_NAME_LEN];
+	struct opp_table *opp_table;
 
 	reg_fields = sti_cpufreq_match();
 	if (!reg_fields) {
@@ -211,20 +212,20 @@ use_defaults:
 
 	snprintf(name, MAX_PCODE_NAME_LEN, "pcode%d", pcode);
 
-	ret = dev_pm_opp_set_prop_name(dev, name);
-	if (ret) {
+	opp_table = dev_pm_opp_set_prop_name(dev, name);
+	if (IS_ERR(opp_table)) {
 		dev_err(dev, "Failed to set prop name\n");
-		return ret;
+		return PTR_ERR(opp_table);
 	}
 
 	version[0] = BIT(major);
 	version[1] = BIT(minor);
 	version[2] = BIT(substrate);
 
-	ret = dev_pm_opp_set_supported_hw(dev, version, VERSION_ELEMENTS);
-	if (ret) {
+	opp_table = dev_pm_opp_set_supported_hw(dev, version, VERSION_ELEMENTS);
+	if (IS_ERR(opp_table)) {
 		dev_err(dev, "Failed to set supported hardware\n");
-		return ret;
+		return PTR_ERR(opp_table);
 	}
 
 	dev_dbg(dev, "pcode: %d major: %d minor: %d substrate: %d\n",
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
new file mode 100644
index 000000000000..a7b5658c0460
--- /dev/null
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -0,0 +1,268 @@
+/*
+ * TI CPUFreq/OPP hw-supported driver
+ *
+ * Copyright (C) 2016-2017 Texas Instruments, Inc.
+ *	 Dave Gerlach <d-gerlach@ti.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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/pm_opp.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#define REVISION_MASK				0xF
+#define REVISION_SHIFT				28
+
+#define AM33XX_800M_ARM_MPU_MAX_FREQ		0x1E2F
+#define AM43XX_600M_ARM_MPU_MAX_FREQ		0xFFA
+
+#define DRA7_EFUSE_HAS_OD_MPU_OPP		11
+#define DRA7_EFUSE_HAS_HIGH_MPU_OPP		15
+#define DRA7_EFUSE_HAS_ALL_MPU_OPP		23
+
+#define DRA7_EFUSE_NOM_MPU_OPP			BIT(0)
+#define DRA7_EFUSE_OD_MPU_OPP			BIT(1)
+#define DRA7_EFUSE_HIGH_MPU_OPP			BIT(2)
+
+#define VERSION_COUNT				2
+
+struct ti_cpufreq_data;
+
+struct ti_cpufreq_soc_data {
+	unsigned long (*efuse_xlate)(struct ti_cpufreq_data *opp_data,
+				     unsigned long efuse);
+	unsigned long efuse_fallback;
+	unsigned long efuse_offset;
+	unsigned long efuse_mask;
+	unsigned long efuse_shift;
+	unsigned long rev_offset;
+};
+
+struct ti_cpufreq_data {
+	struct device *cpu_dev;
+	struct device_node *opp_node;
+	struct regmap *syscon;
+	const struct ti_cpufreq_soc_data *soc_data;
+};
+
+static unsigned long amx3_efuse_xlate(struct ti_cpufreq_data *opp_data,
+				      unsigned long efuse)
+{
+	if (!efuse)
+		efuse = opp_data->soc_data->efuse_fallback;
+	/* AM335x and AM437x use "OPP disable" bits, so invert */
+	return ~efuse;
+}
+
+static unsigned long dra7_efuse_xlate(struct ti_cpufreq_data *opp_data,
+				      unsigned long efuse)
+{
+	unsigned long calculated_efuse = DRA7_EFUSE_NOM_MPU_OPP;
+
+	/*
+	 * The efuse on dra7 and am57 parts contains a specific
+	 * value indicating the highest available OPP.
+	 */
+
+	switch (efuse) {
+	case DRA7_EFUSE_HAS_ALL_MPU_OPP:
+	case DRA7_EFUSE_HAS_HIGH_MPU_OPP:
+		calculated_efuse |= DRA7_EFUSE_HIGH_MPU_OPP;
+	case DRA7_EFUSE_HAS_OD_MPU_OPP:
+		calculated_efuse |= DRA7_EFUSE_OD_MPU_OPP;
+	}
+
+	return calculated_efuse;
+}
+
+static struct ti_cpufreq_soc_data am3x_soc_data = {
+	.efuse_xlate = amx3_efuse_xlate,
+	.efuse_fallback = AM33XX_800M_ARM_MPU_MAX_FREQ,
+	.efuse_offset = 0x07fc,
+	.efuse_mask = 0x1fff,
+	.rev_offset = 0x600,
+};
+
+static struct ti_cpufreq_soc_data am4x_soc_data = {
+	.efuse_xlate = amx3_efuse_xlate,
+	.efuse_fallback = AM43XX_600M_ARM_MPU_MAX_FREQ,
+	.efuse_offset = 0x0610,
+	.efuse_mask = 0x3f,
+	.rev_offset = 0x600,
+};
+
+static struct ti_cpufreq_soc_data dra7_soc_data = {
+	.efuse_xlate = dra7_efuse_xlate,
+	.efuse_offset = 0x020c,
+	.efuse_mask = 0xf80000,
+	.efuse_shift = 19,
+	.rev_offset = 0x204,
+};
+
+/**
+ * ti_cpufreq_get_efuse() - Parse and return efuse value present on SoC
+ * @opp_data: pointer to ti_cpufreq_data context
+ * @efuse_value: Set to the value parsed from efuse
+ *
+ * Returns error code if efuse not read properly.
+ */
+static int ti_cpufreq_get_efuse(struct ti_cpufreq_data *opp_data,
+				u32 *efuse_value)
+{
+	struct device *dev = opp_data->cpu_dev;
+	u32 efuse;
+	int ret;
+
+	ret = regmap_read(opp_data->syscon, opp_data->soc_data->efuse_offset,
+			  &efuse);
+	if (ret) {
+		dev_err(dev,
+			"Failed to read the efuse value from syscon: %d\n",
+			ret);
+		return ret;
+	}
+
+	efuse = (efuse & opp_data->soc_data->efuse_mask);
+	efuse >>= opp_data->soc_data->efuse_shift;
+
+	*efuse_value = opp_data->soc_data->efuse_xlate(opp_data, efuse);
+
+	return 0;
+}
+
+/**
+ * ti_cpufreq_get_rev() - Parse and return rev value present on SoC
+ * @opp_data: pointer to ti_cpufreq_data context
+ * @revision_value: Set to the value parsed from revision register
+ *
+ * Returns error code if revision not read properly.
+ */
+static int ti_cpufreq_get_rev(struct ti_cpufreq_data *opp_data,
+			      u32 *revision_value)
+{
+	struct device *dev = opp_data->cpu_dev;
+	u32 revision;
+	int ret;
+
+	ret = regmap_read(opp_data->syscon, opp_data->soc_data->rev_offset,
+			  &revision);
+	if (ret) {
+		dev_err(dev,
+			"Failed to read the revision number from syscon: %d\n",
+			ret);
+		return ret;
+	}
+
+	*revision_value = BIT((revision >> REVISION_SHIFT) & REVISION_MASK);
+
+	return 0;
+}
+
+static int ti_cpufreq_setup_syscon_register(struct ti_cpufreq_data *opp_data)
+{
+	struct device *dev = opp_data->cpu_dev;
+	struct device_node *np = opp_data->opp_node;
+
+	opp_data->syscon = syscon_regmap_lookup_by_phandle(np,
+							"syscon");
+	if (IS_ERR(opp_data->syscon)) {
+		dev_err(dev,
+			"\"syscon\" is missing, cannot use OPPv2 table.\n");
+		return PTR_ERR(opp_data->syscon);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id ti_cpufreq_of_match[] = {
+	{ .compatible = "ti,am33xx", .data = &am3x_soc_data, },
+	{ .compatible = "ti,am4372", .data = &am4x_soc_data, },
+	{ .compatible = "ti,dra7", .data = &dra7_soc_data },
+	{},
+};
+
+static int ti_cpufreq_init(void)
+{
+	u32 version[VERSION_COUNT];
+	struct device_node *np;
+	const struct of_device_id *match;
+	struct ti_cpufreq_data *opp_data;
+	int ret;
+
+	np = of_find_node_by_path("/");
+	match = of_match_node(ti_cpufreq_of_match, np);
+	if (!match)
+		return -ENODEV;
+
+	opp_data = kzalloc(sizeof(*opp_data), GFP_KERNEL);
+	if (!opp_data)
+		return -ENOMEM;
+
+	opp_data->soc_data = match->data;
+
+	opp_data->cpu_dev = get_cpu_device(0);
+	if (!opp_data->cpu_dev) {
+		pr_err("%s: Failed to get device for CPU0\n", __func__);
+		return -ENODEV;
+	}
+
+	opp_data->opp_node = dev_pm_opp_of_get_opp_desc_node(opp_data->cpu_dev);
+	if (!opp_data->opp_node) {
+		dev_info(opp_data->cpu_dev,
+			 "OPP-v2 not supported, cpufreq-dt will attempt to use legacy tables.\n");
+		goto register_cpufreq_dt;
+	}
+
+	ret = ti_cpufreq_setup_syscon_register(opp_data);
+	if (ret)
+		goto fail_put_node;
+
+	/*
+	 * OPPs determine whether or not they are supported based on
+	 * two metrics:
+	 *	0 - SoC Revision
+	 *	1 - eFuse value
+	 */
+	ret = ti_cpufreq_get_rev(opp_data, &version[0]);
+	if (ret)
+		goto fail_put_node;
+
+	ret = ti_cpufreq_get_efuse(opp_data, &version[1]);
+	if (ret)
+		goto fail_put_node;
+
+	of_node_put(opp_data->opp_node);
+
+	ret = PTR_ERR_OR_ZERO(dev_pm_opp_set_supported_hw(opp_data->cpu_dev,
+							  version, VERSION_COUNT));
+	if (ret) {
+		dev_err(opp_data->cpu_dev,
+			"Failed to set supported hardware\n");
+		goto fail_put_node;
+	}
+
+register_cpufreq_dt:
+	platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
+
+	return 0;
+
+fail_put_node:
+	of_node_put(opp_data->opp_node);
+
+	return ret;
+}
+device_initcall(ti_cpufreq_init);
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index d9b5b9398a0f..8d6d25c38c02 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -19,6 +19,7 @@
 #include <linux/tick.h>
 #include <linux/sched.h>
 #include <linux/math64.h>
+#include <linux/cpu.h>
 
 /*
  * Please note when changing the tuning values:
@@ -280,17 +281,23 @@ again:
 static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
+	struct device *device = get_cpu_device(dev->cpu);
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	int i;
 	unsigned int interactivity_req;
 	unsigned int expected_interval;
 	unsigned long nr_iowaiters, cpu_load;
+	int resume_latency = dev_pm_qos_read_value(device);
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
 		data->needs_update = 0;
 	}
 
+	/* resume_latency is 0 means no restriction */
+	if (resume_latency && resume_latency < latency_req)
+		latency_req = resume_latency;
+
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0))
 		return 0;
@@ -357,9 +364,9 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		if (s->disabled || su->disable)
 			continue;
 		if (s->target_residency > data->predicted_us)
-			continue;
+			break;
 		if (s->exit_latency > latency_req)
-			continue;
+			break;
 
 		data->last_state_idx = i;
 	}
diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c
index 9aea2c7ecbe6..8648b32ebc89 100644
--- a/drivers/devfreq/devfreq-event.c
+++ b/drivers/devfreq/devfreq-event.c
@@ -306,7 +306,7 @@ struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev,
 						struct devfreq_event_desc *desc)
 {
 	struct devfreq_event_dev *edev;
-	static atomic_t event_no = ATOMIC_INIT(0);
+	static atomic_t event_no = ATOMIC_INIT(-1);
 	int ret;
 
 	if (!dev || !desc)
@@ -329,7 +329,7 @@ struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev,
 	edev->dev.class = devfreq_event_class;
 	edev->dev.release = devfreq_event_release_edev;
 
-	dev_set_name(&edev->dev, "event.%d", atomic_inc_return(&event_no) - 1);
+	dev_set_name(&edev->dev, "event%d", atomic_inc_return(&event_no));
 	ret = device_register(&edev->dev);
 	if (ret < 0) {
 		put_device(&edev->dev);
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 47206a21bb90..551a271353d2 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -111,18 +111,16 @@ static void devfreq_set_freq_table(struct devfreq *devfreq)
 		return;
 	}
 
-	rcu_read_lock();
 	for (i = 0, freq = 0; i < profile->max_state; i++, freq++) {
 		opp = dev_pm_opp_find_freq_ceil(devfreq->dev.parent, &freq);
 		if (IS_ERR(opp)) {
 			devm_kfree(devfreq->dev.parent, profile->freq_table);
 			profile->max_state = 0;
-			rcu_read_unlock();
 			return;
 		}
+		dev_pm_opp_put(opp);
 		profile->freq_table[i] = freq;
 	}
-	rcu_read_unlock();
 }
 
 /**
@@ -130,7 +128,7 @@ static void devfreq_set_freq_table(struct devfreq *devfreq)
  * @devfreq:	the devfreq instance
  * @freq:	the update target frequency
  */
-static int devfreq_update_status(struct devfreq *devfreq, unsigned long freq)
+int devfreq_update_status(struct devfreq *devfreq, unsigned long freq)
 {
 	int lev, prev_lev, ret = 0;
 	unsigned long cur_time;
@@ -166,6 +164,7 @@ out:
 	devfreq->last_stat_updated = cur_time;
 	return ret;
 }
+EXPORT_SYMBOL(devfreq_update_status);
 
 /**
  * find_devfreq_governor() - find devfreq governor from name
@@ -474,11 +473,15 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type,
 }
 
 /**
- * _remove_devfreq() - Remove devfreq from the list and release its resources.
- * @devfreq:	the devfreq struct
+ * devfreq_dev_release() - Callback for struct device to release the device.
+ * @dev:	the devfreq device
+ *
+ * Remove devfreq from the list and release its resources.
  */
-static void _remove_devfreq(struct devfreq *devfreq)
+static void devfreq_dev_release(struct device *dev)
 {
+	struct devfreq *devfreq = to_devfreq(dev);
+
 	mutex_lock(&devfreq_list_lock);
 	if (IS_ERR(find_device_devfreq(devfreq->dev.parent))) {
 		mutex_unlock(&devfreq_list_lock);
@@ -500,19 +503,6 @@ static void _remove_devfreq(struct devfreq *devfreq)
 }
 
 /**
- * devfreq_dev_release() - Callback for struct device to release the device.
- * @dev:	the devfreq device
- *
- * This calls _remove_devfreq() if _remove_devfreq() is not called.
- */
-static void devfreq_dev_release(struct device *dev)
-{
-	struct devfreq *devfreq = to_devfreq(dev);
-
-	_remove_devfreq(devfreq);
-}
-
-/**
  * devfreq_add_device() - Add devfreq feature to the device
  * @dev:	the device to add devfreq feature.
  * @profile:	device-specific profile to run devfreq.
@@ -527,6 +517,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 {
 	struct devfreq *devfreq;
 	struct devfreq_governor *governor;
+	static atomic_t devfreq_no = ATOMIC_INIT(-1);
 	int err = 0;
 
 	if (!dev || !profile || !governor_name) {
@@ -538,15 +529,14 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq = find_device_devfreq(dev);
 	mutex_unlock(&devfreq_list_lock);
 	if (!IS_ERR(devfreq)) {
-		dev_err(dev, "%s: Unable to create devfreq for the device. It already has one.\n", __func__);
+		dev_err(dev, "%s: Unable to create devfreq for the device.\n",
+			__func__);
 		err = -EINVAL;
 		goto err_out;
 	}
 
 	devfreq = kzalloc(sizeof(struct devfreq), GFP_KERNEL);
 	if (!devfreq) {
-		dev_err(dev, "%s: Unable to create devfreq for the device\n",
-			__func__);
 		err = -ENOMEM;
 		goto err_out;
 	}
@@ -569,18 +559,21 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		mutex_lock(&devfreq->lock);
 	}
 
-	dev_set_name(&devfreq->dev, "%s", dev_name(dev));
+	dev_set_name(&devfreq->dev, "devfreq%d",
+				atomic_inc_return(&devfreq_no));
 	err = device_register(&devfreq->dev);
 	if (err) {
 		mutex_unlock(&devfreq->lock);
 		goto err_out;
 	}
 
-	devfreq->trans_table =	devm_kzalloc(&devfreq->dev, sizeof(unsigned int) *
+	devfreq->trans_table =	devm_kzalloc(&devfreq->dev,
+						sizeof(unsigned int) *
 						devfreq->profile->max_state *
 						devfreq->profile->max_state,
 						GFP_KERNEL);
-	devfreq->time_in_state = devm_kzalloc(&devfreq->dev, sizeof(unsigned long) *
+	devfreq->time_in_state = devm_kzalloc(&devfreq->dev,
+						sizeof(unsigned long) *
 						devfreq->profile->max_state,
 						GFP_KERNEL);
 	devfreq->last_stat_updated = jiffies;
@@ -939,6 +932,9 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr,
 	if (df->governor == governor) {
 		ret = 0;
 		goto out;
+	} else if (df->governor->immutable || governor->immutable) {
+		ret = -EINVAL;
+		goto out;
 	}
 
 	if (df->governor) {
@@ -968,13 +964,33 @@ static ssize_t available_governors_show(struct device *d,
 					struct device_attribute *attr,
 					char *buf)
 {
-	struct devfreq_governor *tmp_governor;
+	struct devfreq *df = to_devfreq(d);
 	ssize_t count = 0;
 
 	mutex_lock(&devfreq_list_lock);
-	list_for_each_entry(tmp_governor, &devfreq_governor_list, node)
-		count += scnprintf(&buf[count], (PAGE_SIZE - count - 2),
-				   "%s ", tmp_governor->name);
+
+	/*
+	 * The devfreq with immutable governor (e.g., passive) shows
+	 * only own governor.
+	 */
+	if (df->governor->immutable) {
+		count = scnprintf(&buf[count], DEVFREQ_NAME_LEN,
+				   "%s ", df->governor_name);
+	/*
+	 * The devfreq device shows the registered governor except for
+	 * immutable governors such as passive governor .
+	 */
+	} else {
+		struct devfreq_governor *governor;
+
+		list_for_each_entry(governor, &devfreq_governor_list, node) {
+			if (governor->immutable)
+				continue;
+			count += scnprintf(&buf[count], (PAGE_SIZE - count - 2),
+					   "%s ", governor->name);
+		}
+	}
+
 	mutex_unlock(&devfreq_list_lock);
 
 	/* Truncate the trailing space */
@@ -995,7 +1011,7 @@ static ssize_t cur_freq_show(struct device *dev, struct device_attribute *attr,
 
 	if (devfreq->profile->get_cur_freq &&
 		!devfreq->profile->get_cur_freq(devfreq->dev.parent, &freq))
-			return sprintf(buf, "%lu\n", freq);
+		return sprintf(buf, "%lu\n", freq);
 
 	return sprintf(buf, "%lu\n", devfreq->previous_freq);
 }
@@ -1112,17 +1128,16 @@ static ssize_t available_frequencies_show(struct device *d,
 	ssize_t count = 0;
 	unsigned long freq = 0;
 
-	rcu_read_lock();
 	do {
 		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
 		if (IS_ERR(opp))
 			break;
 
+		dev_pm_opp_put(opp);
 		count += scnprintf(&buf[count], (PAGE_SIZE - count - 2),
 				   "%lu ", freq);
 		freq++;
 	} while (1);
-	rcu_read_unlock();
 
 	/* Truncate the trailing space */
 	if (count)
@@ -1224,11 +1239,8 @@ subsys_initcall(devfreq_init);
  * @freq:	The frequency given to target function
  * @flags:	Flags handed from devfreq framework.
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *devfreq_recommended_opp(struct device *dev,
 					   unsigned long *freq,
@@ -1265,18 +1277,7 @@ EXPORT_SYMBOL(devfreq_recommended_opp);
  */
 int devfreq_register_opp_notifier(struct device *dev, struct devfreq *devfreq)
 {
-	struct srcu_notifier_head *nh;
-	int ret = 0;
-
-	rcu_read_lock();
-	nh = dev_pm_opp_get_notifier(dev);
-	if (IS_ERR(nh))
-		ret = PTR_ERR(nh);
-	rcu_read_unlock();
-	if (!ret)
-		ret = srcu_notifier_chain_register(nh, &devfreq->nb);
-
-	return ret;
+	return dev_pm_opp_register_notifier(dev, &devfreq->nb);
 }
 EXPORT_SYMBOL(devfreq_register_opp_notifier);
 
@@ -1292,18 +1293,7 @@ EXPORT_SYMBOL(devfreq_register_opp_notifier);
  */
 int devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq)
 {
-	struct srcu_notifier_head *nh;
-	int ret = 0;
-
-	rcu_read_lock();
-	nh = dev_pm_opp_get_notifier(dev);
-	if (IS_ERR(nh))
-		ret = PTR_ERR(nh);
-	rcu_read_unlock();
-	if (!ret)
-		ret = srcu_notifier_chain_unregister(nh, &devfreq->nb);
-
-	return ret;
+	return dev_pm_opp_unregister_notifier(dev, &devfreq->nb);
 }
 EXPORT_SYMBOL(devfreq_unregister_opp_notifier);
 
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 107eb91a9415..9b7350935b73 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -17,13 +17,13 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/suspend.h>
 #include <linux/devfreq-event.h>
 
 #include "exynos-ppmu.h"
 
 struct exynos_ppmu_data {
-	void __iomem *base;
 	struct clk *clk;
 };
 
@@ -33,6 +33,7 @@ struct exynos_ppmu {
 	unsigned int num_events;
 
 	struct device *dev;
+	struct regmap *regmap;
 
 	struct exynos_ppmu_data ppmu;
 };
@@ -107,20 +108,28 @@ static int exynos_ppmu_find_ppmu_id(struct devfreq_event_dev *edev)
 static int exynos_ppmu_disable(struct devfreq_event_dev *edev)
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	int ret;
 	u32 pmnc;
 
 	/* Disable all counters */
-	__raw_writel(PPMU_CCNT_MASK |
-		     PPMU_PMCNT0_MASK |
-		     PPMU_PMCNT1_MASK |
-		     PPMU_PMCNT2_MASK |
-		     PPMU_PMCNT3_MASK,
-		     info->ppmu.base + PPMU_CNTENC);
+	ret = regmap_write(info->regmap, PPMU_CNTENC,
+				PPMU_CCNT_MASK |
+				PPMU_PMCNT0_MASK |
+				PPMU_PMCNT1_MASK |
+				PPMU_PMCNT2_MASK |
+				PPMU_PMCNT3_MASK);
+	if (ret < 0)
+		return ret;
 
 	/* Disable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC);
+	ret = regmap_read(info->regmap, PPMU_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
-	__raw_writel(pmnc, info->ppmu.base + PPMU_PMNC);
+	ret = regmap_write(info->regmap, PPMU_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -129,29 +138,42 @@ static int exynos_ppmu_set_event(struct devfreq_event_dev *edev)
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
 	int id = exynos_ppmu_find_ppmu_id(edev);
+	int ret;
 	u32 pmnc, cntens;
 
 	if (id < 0)
 		return id;
 
 	/* Enable specific counter */
-	cntens = __raw_readl(info->ppmu.base + PPMU_CNTENS);
+	ret = regmap_read(info->regmap, PPMU_CNTENS, &cntens);
+	if (ret < 0)
+		return ret;
+
 	cntens |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
-	__raw_writel(cntens, info->ppmu.base + PPMU_CNTENS);
+	ret = regmap_write(info->regmap, PPMU_CNTENS, cntens);
+	if (ret < 0)
+		return ret;
 
 	/* Set the event of Read/Write data count  */
-	__raw_writel(PPMU_RO_DATA_CNT | PPMU_WO_DATA_CNT,
-			info->ppmu.base + PPMU_BEVTxSEL(id));
+	ret = regmap_write(info->regmap, PPMU_BEVTxSEL(id),
+				PPMU_RO_DATA_CNT | PPMU_WO_DATA_CNT);
+	if (ret < 0)
+		return ret;
 
 	/* Reset cycle counter/performance counter and enable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC);
+	ret = regmap_read(info->regmap, PPMU_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~(PPMU_PMNC_ENABLE_MASK
 			| PPMU_PMNC_COUNTER_RESET_MASK
 			| PPMU_PMNC_CC_RESET_MASK);
 	pmnc |= (PPMU_ENABLE << PPMU_PMNC_ENABLE_SHIFT);
 	pmnc |= (PPMU_ENABLE << PPMU_PMNC_COUNTER_RESET_SHIFT);
 	pmnc |= (PPMU_ENABLE << PPMU_PMNC_CC_RESET_SHIFT);
-	__raw_writel(pmnc, info->ppmu.base + PPMU_PMNC);
+	ret = regmap_write(info->regmap, PPMU_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -161,40 +183,64 @@ static int exynos_ppmu_get_event(struct devfreq_event_dev *edev,
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
 	int id = exynos_ppmu_find_ppmu_id(edev);
-	u32 pmnc, cntenc;
+	unsigned int total_count, load_count;
+	unsigned int pmcnt3_high, pmcnt3_low;
+	unsigned int pmnc, cntenc;
+	int ret;
 
 	if (id < 0)
 		return -EINVAL;
 
 	/* Disable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC);
+	ret = regmap_read(info->regmap, PPMU_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
-	__raw_writel(pmnc, info->ppmu.base + PPMU_PMNC);
+	ret = regmap_write(info->regmap, PPMU_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	/* Read cycle count */
-	edata->total_count = __raw_readl(info->ppmu.base + PPMU_CCNT);
+	ret = regmap_read(info->regmap, PPMU_CCNT, &total_count);
+	if (ret < 0)
+		return ret;
+	edata->total_count = total_count;
 
 	/* Read performance count */
 	switch (id) {
 	case PPMU_PMNCNT0:
 	case PPMU_PMNCNT1:
 	case PPMU_PMNCNT2:
-		edata->load_count
-			= __raw_readl(info->ppmu.base + PPMU_PMNCT(id));
+		ret = regmap_read(info->regmap, PPMU_PMNCT(id), &load_count);
+		if (ret < 0)
+			return ret;
+		edata->load_count = load_count;
 		break;
 	case PPMU_PMNCNT3:
-		edata->load_count =
-			((__raw_readl(info->ppmu.base + PPMU_PMCNT3_HIGH) << 8)
-			| __raw_readl(info->ppmu.base + PPMU_PMCNT3_LOW));
+		ret = regmap_read(info->regmap, PPMU_PMCNT3_HIGH, &pmcnt3_high);
+		if (ret < 0)
+			return ret;
+
+		ret = regmap_read(info->regmap, PPMU_PMCNT3_LOW, &pmcnt3_low);
+		if (ret < 0)
+			return ret;
+
+		edata->load_count = ((pmcnt3_high << 8) | pmcnt3_low);
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Disable specific counter */
-	cntenc = __raw_readl(info->ppmu.base + PPMU_CNTENC);
+	ret = regmap_read(info->regmap, PPMU_CNTENC, &cntenc);
+	if (ret < 0)
+		return ret;
+
 	cntenc |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
-	__raw_writel(cntenc, info->ppmu.base + PPMU_CNTENC);
+	ret = regmap_write(info->regmap, PPMU_CNTENC, cntenc);
+	if (ret < 0)
+		return ret;
 
 	dev_dbg(&edev->dev, "%s (event: %ld/%ld)\n", edev->desc->name,
 					edata->load_count, edata->total_count);
@@ -214,36 +260,93 @@ static const struct devfreq_event_ops exynos_ppmu_ops = {
 static int exynos_ppmu_v2_disable(struct devfreq_event_dev *edev)
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	int ret;
 	u32 pmnc, clear;
 
 	/* Disable all counters */
 	clear = (PPMU_CCNT_MASK | PPMU_PMCNT0_MASK | PPMU_PMCNT1_MASK
 		| PPMU_PMCNT2_MASK | PPMU_PMCNT3_MASK);
+	ret = regmap_write(info->regmap, PPMU_V2_FLAG, clear);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_INTENC, clear);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CNTENC, clear);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CNT_RESET, clear);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CIG_CFG0, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CIG_CFG1, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CIG_CFG2, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CIG_RESULT, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CNT_AUTO, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CH_EV0_TYPE, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CH_EV1_TYPE, 0x0);
+	if (ret < 0)
+		return ret;
 
-	__raw_writel(clear, info->ppmu.base + PPMU_V2_FLAG);
-	__raw_writel(clear, info->ppmu.base + PPMU_V2_INTENC);
-	__raw_writel(clear, info->ppmu.base + PPMU_V2_CNTENC);
-	__raw_writel(clear, info->ppmu.base + PPMU_V2_CNT_RESET);
-
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_CFG0);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_CFG1);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_CFG2);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_RESULT);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CNT_AUTO);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV0_TYPE);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV1_TYPE);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV2_TYPE);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV3_TYPE);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_ID_V);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_ID_A);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_OTHERS_V);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_OTHERS_A);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_INTERRUPT_RESET);
+	ret = regmap_write(info->regmap, PPMU_V2_CH_EV2_TYPE, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CH_EV3_TYPE, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_SM_ID_V, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_SM_ID_A, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_SM_OTHERS_V, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_SM_OTHERS_A, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_INTERRUPT_RESET, 0x0);
+	if (ret < 0)
+		return ret;
 
 	/* Disable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_V2_PMNC);
+	ret = regmap_read(info->regmap, PPMU_V2_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
-	__raw_writel(pmnc, info->ppmu.base + PPMU_V2_PMNC);
+	ret = regmap_write(info->regmap, PPMU_V2_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -251,30 +354,43 @@ static int exynos_ppmu_v2_disable(struct devfreq_event_dev *edev)
 static int exynos_ppmu_v2_set_event(struct devfreq_event_dev *edev)
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	unsigned int pmnc, cntens;
 	int id = exynos_ppmu_find_ppmu_id(edev);
-	u32 pmnc, cntens;
+	int ret;
 
 	/* Enable all counters */
-	cntens = __raw_readl(info->ppmu.base + PPMU_V2_CNTENS);
+	ret = regmap_read(info->regmap, PPMU_V2_CNTENS, &cntens);
+	if (ret < 0)
+		return ret;
+
 	cntens |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
-	__raw_writel(cntens, info->ppmu.base + PPMU_V2_CNTENS);
+	ret = regmap_write(info->regmap, PPMU_V2_CNTENS, cntens);
+	if (ret < 0)
+		return ret;
 
 	/* Set the event of Read/Write data count  */
 	switch (id) {
 	case PPMU_PMNCNT0:
 	case PPMU_PMNCNT1:
 	case PPMU_PMNCNT2:
-		__raw_writel(PPMU_V2_RO_DATA_CNT | PPMU_V2_WO_DATA_CNT,
-				info->ppmu.base + PPMU_V2_CH_EVx_TYPE(id));
+		ret = regmap_write(info->regmap, PPMU_V2_CH_EVx_TYPE(id),
+				PPMU_V2_RO_DATA_CNT | PPMU_V2_WO_DATA_CNT);
+		if (ret < 0)
+			return ret;
 		break;
 	case PPMU_PMNCNT3:
-		__raw_writel(PPMU_V2_EVT3_RW_DATA_CNT,
-				info->ppmu.base + PPMU_V2_CH_EVx_TYPE(id));
+		ret = regmap_write(info->regmap, PPMU_V2_CH_EVx_TYPE(id),
+				PPMU_V2_EVT3_RW_DATA_CNT);
+		if (ret < 0)
+			return ret;
 		break;
 	}
 
 	/* Reset cycle counter/performance counter and enable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_V2_PMNC);
+	ret = regmap_read(info->regmap, PPMU_V2_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~(PPMU_PMNC_ENABLE_MASK
 			| PPMU_PMNC_COUNTER_RESET_MASK
 			| PPMU_PMNC_CC_RESET_MASK
@@ -284,7 +400,10 @@ static int exynos_ppmu_v2_set_event(struct devfreq_event_dev *edev)
 	pmnc |= (PPMU_ENABLE << PPMU_PMNC_COUNTER_RESET_SHIFT);
 	pmnc |= (PPMU_ENABLE << PPMU_PMNC_CC_RESET_SHIFT);
 	pmnc |= (PPMU_V2_MODE_MANUAL << PPMU_V2_PMNC_START_MODE_SHIFT);
-	__raw_writel(pmnc, info->ppmu.base + PPMU_V2_PMNC);
+
+	ret = regmap_write(info->regmap, PPMU_V2_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -294,37 +413,61 @@ static int exynos_ppmu_v2_get_event(struct devfreq_event_dev *edev,
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
 	int id = exynos_ppmu_find_ppmu_id(edev);
-	u32 pmnc, cntenc;
-	u32 pmcnt_high, pmcnt_low;
-	u64 load_count = 0;
+	int ret;
+	unsigned int pmnc, cntenc;
+	unsigned int pmcnt_high, pmcnt_low;
+	unsigned int total_count, count;
+	unsigned long load_count = 0;
 
 	/* Disable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_V2_PMNC);
+	ret = regmap_read(info->regmap, PPMU_V2_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
-	__raw_writel(pmnc, info->ppmu.base + PPMU_V2_PMNC);
+	ret = regmap_write(info->regmap, PPMU_V2_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	/* Read cycle count and performance count */
-	edata->total_count = __raw_readl(info->ppmu.base + PPMU_V2_CCNT);
+	ret = regmap_read(info->regmap, PPMU_V2_CCNT, &total_count);
+	if (ret < 0)
+		return ret;
+	edata->total_count = total_count;
 
 	switch (id) {
 	case PPMU_PMNCNT0:
 	case PPMU_PMNCNT1:
 	case PPMU_PMNCNT2:
-		load_count = __raw_readl(info->ppmu.base + PPMU_V2_PMNCT(id));
+		ret = regmap_read(info->regmap, PPMU_V2_PMNCT(id), &count);
+		if (ret < 0)
+			return ret;
+		load_count = count;
 		break;
 	case PPMU_PMNCNT3:
-		pmcnt_high = __raw_readl(info->ppmu.base + PPMU_V2_PMCNT3_HIGH);
-		pmcnt_low = __raw_readl(info->ppmu.base + PPMU_V2_PMCNT3_LOW);
-		load_count = ((u64)((pmcnt_high & 0xff)) << 32)
-			   + (u64)pmcnt_low;
+		ret = regmap_read(info->regmap, PPMU_V2_PMCNT3_HIGH,
+						&pmcnt_high);
+		if (ret < 0)
+			return ret;
+
+		ret = regmap_read(info->regmap, PPMU_V2_PMCNT3_LOW, &pmcnt_low);
+		if (ret < 0)
+			return ret;
+
+		load_count = ((u64)((pmcnt_high & 0xff)) << 32)+ (u64)pmcnt_low;
 		break;
 	}
 	edata->load_count = load_count;
 
 	/* Disable all counters */
-	cntenc = __raw_readl(info->ppmu.base + PPMU_V2_CNTENC);
+	ret = regmap_read(info->regmap, PPMU_V2_CNTENC, &cntenc);
+	if (ret < 0)
+		return 0;
+
 	cntenc |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
-	__raw_writel(cntenc, info->ppmu.base + PPMU_V2_CNTENC);
+	ret = regmap_write(info->regmap, PPMU_V2_CNTENC, cntenc);
+	if (ret < 0)
+		return ret;
 
 	dev_dbg(&edev->dev, "%25s (load: %ld / %ld)\n", edev->desc->name,
 					edata->load_count, edata->total_count);
@@ -411,10 +554,19 @@ static int of_get_devfreq_events(struct device_node *np,
 	return 0;
 }
 
-static int exynos_ppmu_parse_dt(struct exynos_ppmu *info)
+static struct regmap_config exynos_ppmu_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+};
+
+static int exynos_ppmu_parse_dt(struct platform_device *pdev,
+				struct exynos_ppmu *info)
 {
 	struct device *dev = info->dev;
 	struct device_node *np = dev->of_node;
+	struct resource *res;
+	void __iomem *base;
 	int ret = 0;
 
 	if (!np) {
@@ -423,10 +575,17 @@ static int exynos_ppmu_parse_dt(struct exynos_ppmu *info)
 	}
 
 	/* Maps the memory mapped IO to control PPMU register */
-	info->ppmu.base = of_iomap(np, 0);
-	if (IS_ERR_OR_NULL(info->ppmu.base)) {
-		dev_err(dev, "failed to map memory region\n");
-		return -ENOMEM;
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	exynos_ppmu_regmap_config.max_register = resource_size(res) - 4;
+	info->regmap = devm_regmap_init_mmio(dev, base,
+					&exynos_ppmu_regmap_config);
+	if (IS_ERR(info->regmap)) {
+		dev_err(dev, "failed to initialize regmap\n");
+		return PTR_ERR(info->regmap);
 	}
 
 	info->ppmu.clk = devm_clk_get(dev, "ppmu");
@@ -438,15 +597,10 @@ static int exynos_ppmu_parse_dt(struct exynos_ppmu *info)
 	ret = of_get_devfreq_events(np, info);
 	if (ret < 0) {
 		dev_err(dev, "failed to parse exynos ppmu dt node\n");
-		goto err;
+		return ret;
 	}
 
 	return 0;
-
-err:
-	iounmap(info->ppmu.base);
-
-	return ret;
 }
 
 static int exynos_ppmu_probe(struct platform_device *pdev)
@@ -463,7 +617,7 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 	info->dev = &pdev->dev;
 
 	/* Parse dt data to get resource */
-	ret = exynos_ppmu_parse_dt(info);
+	ret = exynos_ppmu_parse_dt(pdev, info);
 	if (ret < 0) {
 		dev_err(&pdev->dev,
 			"failed to parse devicetree for resource\n");
@@ -476,8 +630,7 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 	if (!info->edev) {
 		dev_err(&pdev->dev,
 			"failed to allocate memory devfreq-event devices\n");
-		ret = -ENOMEM;
-		goto err;
+		return -ENOMEM;
 	}
 	edev = info->edev;
 	platform_set_drvdata(pdev, info);
@@ -488,17 +641,16 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 			ret = PTR_ERR(edev[i]);
 			dev_err(&pdev->dev,
 				"failed to add devfreq-event device\n");
-			goto err;
+			return PTR_ERR(edev[i]);
 		}
+
+		pr_info("exynos-ppmu: new PPMU device registered %s (%s)\n",
+			dev_name(&pdev->dev), desc[i].name);
 	}
 
 	clk_prepare_enable(info->ppmu.clk);
 
 	return 0;
-err:
-	iounmap(info->ppmu.base);
-
-	return ret;
 }
 
 static int exynos_ppmu_remove(struct platform_device *pdev)
@@ -506,7 +658,6 @@ static int exynos_ppmu_remove(struct platform_device *pdev)
 	struct exynos_ppmu *info = platform_get_drvdata(pdev);
 
 	clk_disable_unprepare(info->ppmu.clk);
-	iounmap(info->ppmu.base);
 
 	return 0;
 }
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index 9af86f46fbec..49f68929e024 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -103,18 +103,17 @@ static int exynos_bus_target(struct device *dev, unsigned long *freq, u32 flags)
 	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);
+	dev_pm_opp_put(new_opp);
+
 	old_freq = bus->curr_freq;
-	rcu_read_unlock();
 
 	if (old_freq == new_freq)
 		return 0;
@@ -147,8 +146,8 @@ static int exynos_bus_target(struct device *dev, unsigned long *freq, u32 flags)
 	}
 	bus->curr_freq = new_freq;
 
-	dev_dbg(dev, "Set the frequency of bus (%lukHz -> %lukHz)\n",
-			old_freq/1000, new_freq/1000);
+	dev_dbg(dev, "Set the frequency of bus (%luHz -> %luHz, %luHz)\n",
+			old_freq, new_freq, clk_get_rate(bus->clk));
 out:
 	mutex_unlock(&bus->lock);
 
@@ -214,17 +213,16 @@ static int exynos_bus_passive_target(struct device *dev, unsigned long *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);
+	dev_pm_opp_put(new_opp);
+
 	old_freq = bus->curr_freq;
-	rcu_read_unlock();
 
 	if (old_freq == new_freq)
 		return 0;
@@ -241,8 +239,8 @@ static int exynos_bus_passive_target(struct device *dev, unsigned long *freq,
 	*freq = new_freq;
 	bus->curr_freq = new_freq;
 
-	dev_dbg(dev, "Set the frequency of bus (%lukHz -> %lukHz)\n",
-			old_freq/1000, new_freq/1000);
+	dev_dbg(dev, "Set the frequency of bus (%luHz -> %luHz, %luHz)\n",
+			old_freq, new_freq, clk_get_rate(bus->clk));
 out:
 	mutex_unlock(&bus->lock);
 
@@ -358,16 +356,14 @@ static int exynos_bus_parse_of(struct device_node *np,
 
 	rate = clk_get_rate(bus->clk);
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, &rate, 0);
 	if (IS_ERR(opp)) {
 		dev_err(dev, "failed to find dev_pm_opp\n");
-		rcu_read_unlock();
 		ret = PTR_ERR(opp);
 		goto err_opp;
 	}
 	bus->curr_freq = dev_pm_opp_get_freq(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	return 0;
 
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index fad7d6321978..71576b8bdfef 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -38,4 +38,6 @@ extern void devfreq_interval_update(struct devfreq *devfreq,
 extern int devfreq_add_governor(struct devfreq_governor *governor);
 extern int devfreq_remove_governor(struct devfreq_governor *governor);
 
+extern int devfreq_update_status(struct devfreq *devfreq, unsigned long freq);
+
 #endif /* _GOVERNOR_H */
diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c
index 9ef46e2592c4..673ad8cc9a1d 100644
--- a/drivers/devfreq/governor_passive.c
+++ b/drivers/devfreq/governor_passive.c
@@ -59,14 +59,14 @@ static int devfreq_passive_get_target_freq(struct devfreq *devfreq,
 	 * 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;
 	}
 
+	dev_pm_opp_put(opp);
+
 	/*
 	 * Get the OPP table's index of decided freqeuncy by governor
 	 * of parent device.
@@ -112,6 +112,11 @@ static int update_devfreq_passive(struct devfreq *devfreq, unsigned long freq)
 	if (ret < 0)
 		goto out;
 
+	if (devfreq->profile->freq_table
+		&& (devfreq_update_status(devfreq, freq)))
+		dev_err(&devfreq->dev,
+			"Couldn't update frequency transition information.\n");
+
 	devfreq->previous_freq = freq;
 
 out:
@@ -179,6 +184,7 @@ static int devfreq_passive_event_handler(struct devfreq *devfreq,
 
 static struct devfreq_governor devfreq_passive = {
 	.name = "passive",
+	.immutable = 1,
 	.get_target_freq = devfreq_passive_get_target_freq,
 	.event_handler = devfreq_passive_event_handler,
 };
diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c
index 35de6e83c1fe..176976068bcd 100644
--- a/drivers/devfreq/governor_userspace.c
+++ b/drivers/devfreq/governor_userspace.c
@@ -1,5 +1,5 @@
 /*
- *  linux/drivers/devfreq/governor_simpleondemand.c
+ *  linux/drivers/devfreq/governor_userspace.c
  *
  *  Copyright (C) 2011 Samsung Electronics
  *	MyungJoo Ham <myungjoo.ham@samsung.com>
@@ -50,7 +50,6 @@ static ssize_t store_freq(struct device *dev, struct device_attribute *attr,
 	unsigned long wanted;
 	int err = 0;
 
-
 	mutex_lock(&devfreq->lock);
 	data = devfreq->data;
 
@@ -112,7 +111,13 @@ out:
 
 static void userspace_exit(struct devfreq *devfreq)
 {
-	sysfs_remove_group(&devfreq->dev.kobj, &dev_attr_group);
+	/*
+	 * Remove the sysfs entry, unless this is being called after
+	 * device_del(), which should have done this already via kobject_del().
+	 */
+	if (devfreq->dev.kobj.sd)
+		sysfs_remove_group(&devfreq->dev.kobj, &dev_attr_group);
+
 	kfree(devfreq->data);
 	devfreq->data = NULL;
 }
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 27d2f349b53c..40a2499730fc 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -91,17 +91,13 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 	unsigned long target_volt, target_rate;
 	int err;
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, freq, flags);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp))
 		return PTR_ERR(opp);
-	}
 
 	target_rate = dev_pm_opp_get_freq(opp);
 	target_volt = dev_pm_opp_get_voltage(opp);
-
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	if (dmcfreq->rate == target_rate)
 		return 0;
@@ -422,15 +418,13 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 
 	data->rate = clk_get_rate(data->dmc_clk);
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, &data->rate, 0);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp))
 		return PTR_ERR(opp);
-	}
+
 	data->rate = dev_pm_opp_get_freq(opp);
 	data->volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	rk3399_devfreq_dmc_profile.initial_freq = data->rate;
 
diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c
index fe9dce0245bf..214fff96fa4a 100644
--- a/drivers/devfreq/tegra-devfreq.c
+++ b/drivers/devfreq/tegra-devfreq.c
@@ -487,15 +487,13 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
 	struct dev_pm_opp *opp;
 	unsigned long rate = *freq * KHZ;
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, &rate, flags);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		dev_err(dev, "Failed to find opp for %lu KHz\n", *freq);
 		return PTR_ERR(opp);
 	}
 	rate = dev_pm_opp_get_freq(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	clk_set_min_rate(tegra->emc_clock, rate);
 	clk_set_rate(tegra->emc_clock, 0);
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 9ce0e9eef923..85fdbf762fa0 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -297,8 +297,6 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 	if (!power_table)
 		return -ENOMEM;
 
-	rcu_read_lock();
-
 	for (freq = 0, i = 0;
 	     opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
 	     freq++, i++) {
@@ -306,13 +304,13 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		u64 power;
 
 		if (i >= num_opps) {
-			rcu_read_unlock();
 			ret = -EAGAIN;
 			goto free_power_table;
 		}
 
 		freq_mhz = freq / 1000000;
 		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
+		dev_pm_opp_put(opp);
 
 		/*
 		 * Do the multiplication with MHz and millivolt so as
@@ -328,8 +326,6 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		power_table[i].power = power;
 	}
 
-	rcu_read_unlock();
-
 	if (i != num_opps) {
 		ret = PTR_ERR(opp);
 		goto free_power_table;
@@ -433,13 +429,10 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
 		return 0;
 	}
 
-	rcu_read_lock();
-
 	opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz,
 					 true);
 	voltage = dev_pm_opp_get_voltage(opp);
-
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	if (voltage == 0) {
 		dev_warn_ratelimited(cpufreq_device->cpu_dev,
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index 5a737fd5f1aa..ba7a5cd994dc 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -113,15 +113,15 @@ static int partition_enable_opps(struct devfreq_cooling_device *dfc,
 		unsigned int freq = dfc->freq_table[i];
 		bool want_enable = i >= cdev_state ? true : false;
 
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_exact(dev, freq, !want_enable);
-		rcu_read_unlock();
 
 		if (PTR_ERR(opp) == -ERANGE)
 			continue;
 		else if (IS_ERR(opp))
 			return PTR_ERR(opp);
 
+		dev_pm_opp_put(opp);
+
 		if (want_enable)
 			ret = dev_pm_opp_enable(dev, freq);
 		else
@@ -221,15 +221,12 @@ get_static_power(struct devfreq_cooling_device *dfc, unsigned long freq)
 	if (!dfc->power_ops->get_static_power)
 		return 0;
 
-	rcu_read_lock();
-
 	opp = dev_pm_opp_find_freq_exact(dev, freq, true);
 	if (IS_ERR(opp) && (PTR_ERR(opp) == -ERANGE))
 		opp = dev_pm_opp_find_freq_exact(dev, freq, false);
 
 	voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
-
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	if (voltage == 0) {
 		dev_warn_ratelimited(dev,
@@ -412,18 +409,14 @@ static int devfreq_cooling_gen_tables(struct devfreq_cooling_device *dfc)
 		unsigned long power_dyn, voltage;
 		struct dev_pm_opp *opp;
 
-		rcu_read_lock();
-
 		opp = dev_pm_opp_find_freq_floor(dev, &freq);
 		if (IS_ERR(opp)) {
-			rcu_read_unlock();
 			ret = PTR_ERR(opp);
 			goto free_tables;
 		}
 
 		voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
-
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 
 		if (dfc->power_ops) {
 			power_dyn = get_dynamic_power(dfc, freq, voltage);