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()
  ...

8 files changed, 566 insertions, 855 deletions

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 =