Merge tag 'pm-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael  Wysocki:
 "Again, the majority of changes go into the cpufreq subsystem, but
  there are no big features this time.  The cpufreq changes that stand
  out somewhat are the governor interface rework and improvements
  related to the handling of frequency tables.  Apart from those, there
  are fixes and new device/CPU IDs in drivers, cleanups and an
  improvement of the new schedutil governor.

  Next, there are some changes in the hibernation core, including a fix
  for a nasty problem related to the MONITOR/MWAIT usage by CPU offline
  during resume from hibernation, a few core improvements related to
  memory management during resume, a couple of additional debug features
  and cleanups.

  Finally, we have some fixes and cleanups in the devfreq subsystem,
  generic power domains framework improvements related to system
  suspend/resume, support for some new chips in intel_idle and in the
  power capping RAPL driver, a new version of the AnalyzeSuspend utility
  and some assorted fixes and cleanups.

  Specifics:

   - Rework the cpufreq governor interface to make it more
     straightforward and modify the conservative governor to avoid using
     transition notifications (Rafael Wysocki).

   - Rework the handling of frequency tables by the cpufreq core to make
     it more efficient (Viresh Kumar).

   - Modify the schedutil governor to reduce the number of wakeups it
     causes to occur in cases when the CPU frequency doesn't need to be
     changed (Steve Muckle, Viresh Kumar).

   - Fix some minor issues and clean up code in the cpufreq core and
     governors (Rafael Wysocki, Viresh Kumar).

   - Add Intel Broxton support to the intel_pstate driver (Srinivas
     Pandruvada).

   - Fix problems related to the config TDP feature and to the validity
     of the MSR_HWP_INTERRUPT register in intel_pstate (Jan Kiszka,
     Srinivas Pandruvada).

   - Make intel_pstate update the cpu_frequency tracepoint even if the
     frequency doesn't change to avoid confusing powertop (Rafael
     Wysocki).

   - Clean up the usage of __init/__initdata in intel_pstate, mark some
     of its internal variables as __read_mostly and drop an unused
     structure element from it (Jisheng Zhang, Carsten Emde).

   - Clean up the usage of some duplicate MSR symbols in intel_pstate
     and turbostat (Srinivas Pandruvada).

   - Update/fix the powernv, s3c24xx and mvebu cpufreq drivers (Akshay
     Adiga, Viresh Kumar, Ben Dooks).

   - Fix a regression (introduced during the 4.5 cycle) in the
     pcc-cpufreq driver by reverting the problematic commit (Andreas
     Herrmann).

   - Add support for Intel Denverton to intel_idle, clean up Broxton
     support in it and make it explicitly non-modular (Jacob Pan, Jan
     Beulich, Paul Gortmaker).

   - Add support for Denverton and Ivy Bridge server to the Intel RAPL
     power capping driver and make it more careful about the handing of
     MSRs that may not be present (Jacob Pan, Xiaolong Wang).

   - Fix resume from hibernation on x86-64 by making the CPU offline
     during resume avoid using MONITOR/MWAIT in the "play dead" loop
     which may lead to an inadvertent "revival" of a "dead" CPU and a
     page fault leading to a kernel crash from it (Rafael Wysocki).

   - Make memory management during resume from hibernation more
     straightforward (Rafael Wysocki).

   - Add debug features that should help to detect problems related to
     hibernation and resume from it (Rafael Wysocki, Chen Yu).

   - Clean up hibernation core somewhat (Rafael Wysocki).

   - Prevent KASAN from instrumenting the hibernation core which leads
     to large numbers of false-positives from it (James Morse).

   - Prevent PM (hibernate and suspend) notifiers from being called
     during the cleanup phase if they have not been called during the
     corresponding preparation phase which is possible if one of the
     other notifiers returns an error at that time (Lianwei Wang).

   - Improve suspend-related debug printout in the tasks freezer and
     clean up suspend-related console handling (Roger Lu, Borislav
     Petkov).

   - Update the AnalyzeSuspend script in the kernel sources to version
     4.2 (Todd Brandt).

   - Modify the generic power domains framework to make it handle system
     suspend/resume better (Ulf Hansson).

   - Make the runtime PM framework avoid resuming devices synchronously
     when user space changes the runtime PM settings for them and
     improve its error reporting (Rafael Wysocki, Linus Walleij).

   - Fix error paths in devfreq drivers (exynos, exynos-ppmu,
     exynos-bus) and in the core, make some devfreq code explicitly
     non-modular and change some of it into tristate (Bartlomiej
     Zolnierkiewicz, Peter Chen, Paul Gortmaker).

   - Add DT support to the generic PM clocks management code and make it
     export some more symbols (Jon Hunter, Paul Gortmaker).

   - Make the PCI PM core code slightly more robust against possible
     driver errors (Andy Shevchenko).

   - Make it possible to change DESTDIR and PREFIX in turbostat (Andy
     Shevchenko)"

* tag 'pm-4.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (89 commits)
  Revert "cpufreq: pcc-cpufreq: update default value of cpuinfo_transition_latency"
  PM / hibernate: Introduce test_resume mode for hibernation
  cpufreq: export cpufreq_driver_resolve_freq()
  cpufreq: Disallow ->resolve_freq() for drivers providing ->target_index()
  PCI / PM: check all fields in pci_set_platform_pm()
  cpufreq: acpi-cpufreq: use cached frequency mapping when possible
  cpufreq: schedutil: map raw required frequency to driver frequency
  cpufreq: add cpufreq_driver_resolve_freq()
  cpufreq: intel_pstate: Check cpuid for MSR_HWP_INTERRUPT
  intel_pstate: Update cpu_frequency tracepoint every time
  cpufreq: intel_pstate: clean remnant struct element
  PM / tools: scripts: AnalyzeSuspend v4.2
  x86 / hibernate: Use hlt_play_dead() when resuming from hibernation
  cpufreq: powernv: Replacing pstate_id with frequency table index
  intel_pstate: Fix MSR_CONFIG_TDP_x addressing in core_get_max_pstate()
  PM / hibernate: Image data protection during restoration
  PM / hibernate: Add missing braces in __register_nosave_region()
  PM / hibernate: Clean up comments in snapshot.c
  PM / hibernate: Clean up function headers in snapshot.c
  PM / hibernate: Add missing braces in hibernate_setup()
  ...

36 files changed, 831 insertions, 1056 deletions

diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 3657ac1cb801..8e2e4757adcb 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -121,6 +121,7 @@ int pm_clk_add(struct device *dev, const char *con_id)
 {
 	return __pm_clk_add(dev, con_id, NULL);
 }
+EXPORT_SYMBOL_GPL(pm_clk_add);
 
 /**
  * pm_clk_add_clk - Start using a device clock for power management.
@@ -136,9 +137,42 @@ int pm_clk_add_clk(struct device *dev, struct clk *clk)
 {
 	return __pm_clk_add(dev, NULL, clk);
 }
+EXPORT_SYMBOL_GPL(pm_clk_add_clk);
 
 
 /**
+ * of_pm_clk_add_clk - Start using a device clock for power management.
+ * @dev: Device whose clock is going to be used for power management.
+ * @name: Name of clock that is going to be used for power management.
+ *
+ * Add the clock described in the 'clocks' device-tree node that matches
+ * with the 'name' provided, to the list of clocks used for the power
+ * management of @dev. On success, returns 0. Returns a negative error
+ * code if the clock is not found or cannot be added.
+ */
+int of_pm_clk_add_clk(struct device *dev, const char *name)
+{
+	struct clk *clk;
+	int ret;
+
+	if (!dev || !dev->of_node || !name)
+		return -EINVAL;
+
+	clk = of_clk_get_by_name(dev->of_node, name);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	ret = pm_clk_add_clk(dev, clk);
+	if (ret) {
+		clk_put(clk);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_pm_clk_add_clk);
+
+/**
  * of_pm_clk_add_clks - Start using device clock(s) for power management.
  * @dev: Device whose clock(s) is going to be used for power management.
  *
@@ -192,6 +226,7 @@ error:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(of_pm_clk_add_clks);
 
 /**
  * __pm_clk_remove - Destroy PM clock entry.
@@ -252,6 +287,7 @@ void pm_clk_remove(struct device *dev, const char *con_id)
 
 	__pm_clk_remove(ce);
 }
+EXPORT_SYMBOL_GPL(pm_clk_remove);
 
 /**
  * pm_clk_remove_clk - Stop using a device clock for power management.
@@ -285,6 +321,7 @@ void pm_clk_remove_clk(struct device *dev, struct clk *clk)
 
 	__pm_clk_remove(ce);
 }
+EXPORT_SYMBOL_GPL(pm_clk_remove_clk);
 
 /**
  * pm_clk_init - Initialize a device's list of power management clocks.
@@ -299,6 +336,7 @@ void pm_clk_init(struct device *dev)
 	if (psd)
 		INIT_LIST_HEAD(&psd->clock_list);
 }
+EXPORT_SYMBOL_GPL(pm_clk_init);
 
 /**
  * pm_clk_create - Create and initialize a device's list of PM clocks.
@@ -311,6 +349,7 @@ int pm_clk_create(struct device *dev)
 {
 	return dev_pm_get_subsys_data(dev);
 }
+EXPORT_SYMBOL_GPL(pm_clk_create);
 
 /**
  * pm_clk_destroy - Destroy a device's list of power management clocks.
@@ -345,6 +384,7 @@ void pm_clk_destroy(struct device *dev)
 		__pm_clk_remove(ce);
 	}
 }
+EXPORT_SYMBOL_GPL(pm_clk_destroy);
 
 /**
  * pm_clk_suspend - Disable clocks in a device's PM clock list.
@@ -375,6 +415,7 @@ int pm_clk_suspend(struct device *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pm_clk_suspend);
 
 /**
  * pm_clk_resume - Enable clocks in a device's PM clock list.
@@ -400,6 +441,7 @@ int pm_clk_resume(struct device *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pm_clk_resume);
 
 /**
  * pm_clk_notify - Notify routine for device addition and removal.
@@ -480,6 +522,7 @@ int pm_clk_runtime_suspend(struct device *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pm_clk_runtime_suspend);
 
 int pm_clk_runtime_resume(struct device *dev)
 {
@@ -495,6 +538,7 @@ int pm_clk_runtime_resume(struct device *dev)
 
 	return pm_generic_runtime_resume(dev);
 }
+EXPORT_SYMBOL_GPL(pm_clk_runtime_resume);
 
 #else /* !CONFIG_PM_CLK */
 
@@ -598,3 +642,4 @@ void pm_clk_add_notifier(struct bus_type *bus,
 	clknb->nb.notifier_call = pm_clk_notify;
 	bus_register_notifier(bus, &clknb->nb);
 }
+EXPORT_SYMBOL_GPL(pm_clk_add_notifier);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index de23b648fce3..a1f2aff33997 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -187,8 +187,7 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
 	struct gpd_link *link;
 	int ret = 0;
 
-	if (genpd->status == GPD_STATE_ACTIVE
-	    || (genpd->prepared_count > 0 && genpd->suspend_power_off))
+	if (genpd->status == GPD_STATE_ACTIVE)
 		return 0;
 
 	/*
@@ -735,82 +734,24 @@ static int pm_genpd_prepare(struct device *dev)
 
 	mutex_lock(&genpd->lock);
 
-	if (genpd->prepared_count++ == 0) {
+	if (genpd->prepared_count++ == 0)
 		genpd->suspended_count = 0;
-		genpd->suspend_power_off = genpd->status == GPD_STATE_POWER_OFF;
-	}
 
 	mutex_unlock(&genpd->lock);
 
-	if (genpd->suspend_power_off)
-		return 0;
-
-	/*
-	 * The PM domain must be in the GPD_STATE_ACTIVE state at this point,
-	 * so genpd_poweron() will return immediately, but if the device
-	 * is suspended (e.g. it's been stopped by genpd_stop_dev()), we need
-	 * to make it operational.
-	 */
-	pm_runtime_resume(dev);
-	__pm_runtime_disable(dev, false);
-
 	ret = pm_generic_prepare(dev);
 	if (ret) {
 		mutex_lock(&genpd->lock);
 
-		if (--genpd->prepared_count == 0)
-			genpd->suspend_power_off = false;
+		genpd->prepared_count--;
 
 		mutex_unlock(&genpd->lock);
-		pm_runtime_enable(dev);
 	}
 
 	return ret;
 }
 
 /**
- * pm_genpd_suspend - Suspend a device belonging to an I/O PM domain.
- * @dev: Device to suspend.
- *
- * Suspend a device under the assumption that its pm_domain field points to the
- * domain member of an object of type struct generic_pm_domain representing
- * a PM domain consisting of I/O devices.
- */
-static int pm_genpd_suspend(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_suspend(dev);
-}
-
-/**
- * pm_genpd_suspend_late - Late suspend of a device from an I/O PM domain.
- * @dev: Device to suspend.
- *
- * Carry out a late suspend of a device under the assumption that its
- * pm_domain field points to the domain member of an object of type
- * struct generic_pm_domain representing a PM domain consisting of I/O devices.
- */
-static int pm_genpd_suspend_late(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_suspend_late(dev);
-}
-
-/**
  * pm_genpd_suspend_noirq - Completion of suspend of device in an I/O PM domain.
  * @dev: Device to suspend.
  *
@@ -820,6 +761,7 @@ static int pm_genpd_suspend_late(struct device *dev)
 static int pm_genpd_suspend_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
+	int ret;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -827,11 +769,14 @@ static int pm_genpd_suspend_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (genpd->suspend_power_off
-	    || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev)))
+	if (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))
 		return 0;
 
-	genpd_stop_dev(genpd, dev);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start) {
+		ret = pm_runtime_force_suspend(dev);
+		if (ret)
+			return ret;
+	}
 
 	/*
 	 * Since all of the "noirq" callbacks are executed sequentially, it is
@@ -853,6 +798,7 @@ static int pm_genpd_suspend_noirq(struct device *dev)
 static int pm_genpd_resume_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
+	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -860,8 +806,7 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	if (genpd->suspend_power_off
-	    || (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev)))
+	if (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))
 		return 0;
 
 	/*
@@ -872,93 +817,10 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	pm_genpd_sync_poweron(genpd, true);
 	genpd->suspended_count--;
 
-	return genpd_start_dev(genpd, dev);
-}
-
-/**
- * pm_genpd_resume_early - Early resume of a device in an I/O PM domain.
- * @dev: Device to resume.
- *
- * Carry out an early resume of a device under the assumption that its
- * pm_domain field points to the domain member of an object of type
- * struct generic_pm_domain representing a power domain consisting of I/O
- * devices.
- */
-static int pm_genpd_resume_early(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_resume_early(dev);
-}
-
-/**
- * pm_genpd_resume - Resume of device in an I/O PM domain.
- * @dev: Device to resume.
- *
- * Resume a device under the assumption that its pm_domain field points to the
- * domain member of an object of type struct generic_pm_domain representing
- * a power domain consisting of I/O devices.
- */
-static int pm_genpd_resume(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_resume(dev);
-}
-
-/**
- * pm_genpd_freeze - Freezing a device in an I/O PM domain.
- * @dev: Device to freeze.
- *
- * Freeze a device under the assumption that its pm_domain field points to the
- * domain member of an object of type struct generic_pm_domain representing
- * a power domain consisting of I/O devices.
- */
-static int pm_genpd_freeze(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_freeze(dev);
-}
+	if (genpd->dev_ops.stop && genpd->dev_ops.start)
+		ret = pm_runtime_force_resume(dev);
 
-/**
- * pm_genpd_freeze_late - Late freeze of a device in an I/O PM domain.
- * @dev: Device to freeze.
- *
- * Carry out a late freeze of a device under the assumption that its
- * pm_domain field points to the domain member of an object of type
- * struct generic_pm_domain representing a power domain consisting of I/O
- * devices.
- */
-static int pm_genpd_freeze_late(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_freeze_late(dev);
+	return ret;
 }
 
 /**
@@ -973,6 +835,7 @@ static int pm_genpd_freeze_late(struct device *dev)
 static int pm_genpd_freeze_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
+	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -980,7 +843,10 @@ static int pm_genpd_freeze_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_stop_dev(genpd, dev);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start)
+		ret = pm_runtime_force_suspend(dev);
+
+	return ret;
 }
 
 /**
@@ -993,6 +859,7 @@ static int pm_genpd_freeze_noirq(struct device *dev)
 static int pm_genpd_thaw_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
+	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -1000,51 +867,10 @@ static int pm_genpd_thaw_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ?
-		0 : genpd_start_dev(genpd, dev);
-}
-
-/**
- * pm_genpd_thaw_early - Early thaw of device in an I/O PM domain.
- * @dev: Device to thaw.
- *
- * Carry out an early thaw of a device under the assumption that its
- * pm_domain field points to the domain member of an object of type
- * struct generic_pm_domain representing a power domain consisting of I/O
- * devices.
- */
-static int pm_genpd_thaw_early(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_thaw_early(dev);
-}
-
-/**
- * pm_genpd_thaw - Thaw a device belonging to an I/O power domain.
- * @dev: Device to thaw.
- *
- * Thaw a device under the assumption that its pm_domain field points to the
- * domain member of an object of type struct generic_pm_domain representing
- * a power domain consisting of I/O devices.
- */
-static int pm_genpd_thaw(struct device *dev)
-{
-	struct generic_pm_domain *genpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start)
+		ret = pm_runtime_force_resume(dev);
 
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
-		return -EINVAL;
-
-	return genpd->suspend_power_off ? 0 : pm_generic_thaw(dev);
+	return ret;
 }
 
 /**
@@ -1057,6 +883,7 @@ static int pm_genpd_thaw(struct device *dev)
 static int pm_genpd_restore_noirq(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
+	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -1072,30 +899,20 @@ static int pm_genpd_restore_noirq(struct device *dev)
 	 * At this point suspended_count == 0 means we are being run for the
 	 * first time for the given domain in the present cycle.
 	 */
-	if (genpd->suspended_count++ == 0) {
+	if (genpd->suspended_count++ == 0)
 		/*
 		 * The boot kernel might put the domain into arbitrary state,
 		 * so make it appear as powered off to pm_genpd_sync_poweron(),
 		 * so that it tries to power it on in case it was really off.
 		 */
 		genpd->status = GPD_STATE_POWER_OFF;
-		if (genpd->suspend_power_off) {
-			/*
-			 * If the domain was off before the hibernation, make
-			 * sure it will be off going forward.
-			 */
-			genpd_power_off(genpd, true);
-
-			return 0;
-		}
-	}
-
-	if (genpd->suspend_power_off)
-		return 0;
 
 	pm_genpd_sync_poweron(genpd, true);
 
-	return genpd_start_dev(genpd, dev);
+	if (genpd->dev_ops.stop && genpd->dev_ops.start)
+		ret = pm_runtime_force_resume(dev);
+
+	return ret;
 }
 
 /**
@@ -1110,7 +927,6 @@ static int pm_genpd_restore_noirq(struct device *dev)
 static void pm_genpd_complete(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	bool run_complete;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -1118,20 +934,15 @@ static void pm_genpd_complete(struct device *dev)
 	if (IS_ERR(genpd))
 		return;
 
+	pm_generic_complete(dev);
+
 	mutex_lock(&genpd->lock);
 
-	run_complete = !genpd->suspend_power_off;
-	if (--genpd->prepared_count == 0)
-		genpd->suspend_power_off = false;
+	genpd->prepared_count--;
+	if (!genpd->prepared_count)
+		genpd_queue_power_off_work(genpd);
 
 	mutex_unlock(&genpd->lock);
-
-	if (run_complete) {
-		pm_generic_complete(dev);
-		pm_runtime_set_active(dev);
-		pm_runtime_enable(dev);
-		pm_request_idle(dev);
-	}
 }
 
 /**
@@ -1173,18 +984,10 @@ EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
 #else /* !CONFIG_PM_SLEEP */
 
 #define pm_genpd_prepare		NULL
-#define pm_genpd_suspend		NULL
-#define pm_genpd_suspend_late		NULL
 #define pm_genpd_suspend_noirq		NULL
-#define pm_genpd_resume_early		NULL
 #define pm_genpd_resume_noirq		NULL
-#define pm_genpd_resume			NULL
-#define pm_genpd_freeze			NULL
-#define pm_genpd_freeze_late		NULL
 #define pm_genpd_freeze_noirq		NULL
-#define pm_genpd_thaw_early		NULL
 #define pm_genpd_thaw_noirq		NULL
-#define pm_genpd_thaw			NULL
 #define pm_genpd_restore_noirq		NULL
 #define pm_genpd_complete		NULL
 
@@ -1455,12 +1258,14 @@ EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain);
  * @genpd: PM domain object to initialize.
  * @gov: PM domain governor to associate with the domain (may be NULL).
  * @is_off: Initial value of the domain's power_is_off field.
+ *
+ * Returns 0 on successful initialization, else a negative error code.
  */
-void pm_genpd_init(struct generic_pm_domain *genpd,
-		   struct dev_power_governor *gov, bool is_off)
+int pm_genpd_init(struct generic_pm_domain *genpd,
+		  struct dev_power_governor *gov, bool is_off)
 {
 	if (IS_ERR_OR_NULL(genpd))
-		return;
+		return -EINVAL;
 
 	INIT_LIST_HEAD(&genpd->master_links);
 	INIT_LIST_HEAD(&genpd->slave_links);
@@ -1476,24 +1281,24 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->domain.ops.runtime_suspend = genpd_runtime_suspend;
 	genpd->domain.ops.runtime_resume = genpd_runtime_resume;
 	genpd->domain.ops.prepare = pm_genpd_prepare;
-	genpd->domain.ops.suspend = pm_genpd_suspend;
-	genpd->domain.ops.suspend_late = pm_genpd_suspend_late;
+	genpd->domain.ops.suspend = pm_generic_suspend;
+	genpd->domain.ops.suspend_late = pm_generic_suspend_late;
 	genpd->domain.ops.suspend_noirq = pm_genpd_suspend_noirq;
 	genpd->domain.ops.resume_noirq = pm_genpd_resume_noirq;
-	genpd->domain.ops.resume_early = pm_genpd_resume_early;
-	genpd->domain.ops.resume = pm_genpd_resume;
-	genpd->domain.ops.freeze = pm_genpd_freeze;
-	genpd->domain.ops.freeze_late = pm_genpd_freeze_late;
+	genpd->domain.ops.resume_early = pm_generic_resume_early;
+	genpd->domain.ops.resume = pm_generic_resume;
+	genpd->domain.ops.freeze = pm_generic_freeze;
+	genpd->domain.ops.freeze_late = pm_generic_freeze_late;
 	genpd->domain.ops.freeze_noirq = pm_genpd_freeze_noirq;
 	genpd->domain.ops.thaw_noirq = pm_genpd_thaw_noirq;
-	genpd->domain.ops.thaw_early = pm_genpd_thaw_early;
-	genpd->domain.ops.thaw = pm_genpd_thaw;
-	genpd->domain.ops.poweroff = pm_genpd_suspend;
-	genpd->domain.ops.poweroff_late = pm_genpd_suspend_late;
+	genpd->domain.ops.thaw_early = pm_generic_thaw_early;
+	genpd->domain.ops.thaw = pm_generic_thaw;
+	genpd->domain.ops.poweroff = pm_generic_poweroff;
+	genpd->domain.ops.poweroff_late = pm_generic_poweroff_late;
 	genpd->domain.ops.poweroff_noirq = pm_genpd_suspend_noirq;
 	genpd->domain.ops.restore_noirq = pm_genpd_restore_noirq;
-	genpd->domain.ops.restore_early = pm_genpd_resume_early;
-	genpd->domain.ops.restore = pm_genpd_resume;
+	genpd->domain.ops.restore_early = pm_generic_restore_early;
+	genpd->domain.ops.restore = pm_generic_restore;
 	genpd->domain.ops.complete = pm_genpd_complete;
 
 	if (genpd->flags & GENPD_FLAG_PM_CLK) {
@@ -1518,6 +1323,8 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(pm_genpd_init);
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index b74690418504..e097d355cc04 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1045,10 +1045,14 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status)
 		 */
 		if (!parent->power.disable_depth
 		    && !parent->power.ignore_children
-		    && parent->power.runtime_status != RPM_ACTIVE)
+		    && parent->power.runtime_status != RPM_ACTIVE) {
+			dev_err(dev, "runtime PM trying to activate child device %s but parent (%s) is not active\n",
+				dev_name(dev),
+				dev_name(parent));
 			error = -EBUSY;
-		else if (dev->power.runtime_status == RPM_SUSPENDED)
+		} else if (dev->power.runtime_status == RPM_SUSPENDED) {
 			atomic_inc(&parent->power.child_count);
+		}
 
 		spin_unlock(&parent->power.lock);
 
@@ -1256,7 +1260,7 @@ void pm_runtime_allow(struct device *dev)
 
 	dev->power.runtime_auto = true;
 	if (atomic_dec_and_test(&dev->power.usage_count))
-		rpm_idle(dev, RPM_AUTO);
+		rpm_idle(dev, RPM_AUTO | RPM_ASYNC);
 
  out:
 	spin_unlock_irq(&dev->power.lock);
@@ -1506,6 +1510,9 @@ int pm_runtime_force_resume(struct device *dev)
 		goto out;
 	}
 
+	if (!pm_runtime_status_suspended(dev))
+		goto out;
+
 	ret = pm_runtime_set_active(dev);
 	if (ret)
 		goto out;
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index b7445b6ae5a4..c822d72629d5 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -31,23 +31,18 @@ config CPU_FREQ_BOOST_SW
 	depends on THERMAL
 
 config CPU_FREQ_STAT
-	tristate "CPU frequency translation statistics"
+	bool "CPU frequency transition statistics"
 	default y
 	help
-	  This driver exports CPU frequency statistics information through sysfs
-	  file system.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called cpufreq_stats.
+	  Export CPU frequency statistics information through sysfs.
 
 	  If in doubt, say N.
 
 config CPU_FREQ_STAT_DETAILS
-	bool "CPU frequency translation statistics details"
+	bool "CPU frequency transition statistics details"
 	depends on CPU_FREQ_STAT
 	help
-	  This will show detail CPU frequency translation table in sysfs file
-	  system.
+	  Show detailed CPU frequency transition table in sysfs.
 
 	  If in doubt, say N.
 
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 32a15052f363..297e9128fe9f 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -468,20 +468,17 @@ unsigned int acpi_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	struct acpi_cpufreq_data *data = policy->driver_data;
 	struct acpi_processor_performance *perf;
 	struct cpufreq_frequency_table *entry;
-	unsigned int next_perf_state, next_freq, freq;
+	unsigned int next_perf_state, next_freq, index;
 
 	/*
 	 * Find the closest frequency above target_freq.
-	 *
-	 * The table is sorted in the reverse order with respect to the
-	 * frequency and all of the entries are valid (see the initialization).
 	 */
-	entry = policy->freq_table;
-	do {
-		entry++;
-		freq = entry->frequency;
-	} while (freq >= target_freq && freq != CPUFREQ_TABLE_END);
-	entry--;
+	if (policy->cached_target_freq == target_freq)
+		index = policy->cached_resolved_idx;
+	else
+		index = cpufreq_table_find_index_dl(policy, target_freq);
+
+	entry = &policy->freq_table[index];
 	next_freq = entry->frequency;
 	next_perf_state = entry->driver_data;
 
diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c
index 404360cad25c..042023bbbf62 100644
--- a/drivers/cpufreq/amd_freq_sensitivity.c
+++ b/drivers/cpufreq/amd_freq_sensitivity.c
@@ -48,9 +48,8 @@ static unsigned int amd_powersave_bias_target(struct cpufreq_policy *policy,
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
 	struct dbs_data *od_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = od_data->tuners;
-	struct od_policy_dbs_info *od_info = to_dbs_info(policy_dbs);
 
-	if (!od_info->freq_table)
+	if (!policy->freq_table)
 		return freq_next;
 
 	rdmsr_on_cpu(policy->cpu, MSR_AMD64_FREQ_SENSITIVITY_ACTUAL,
@@ -92,10 +91,9 @@ static unsigned int amd_powersave_bias_target(struct cpufreq_policy *policy,
 		else {
 			unsigned int index;
 
-			cpufreq_frequency_table_target(policy,
-				od_info->freq_table, policy->cur - 1,
-				CPUFREQ_RELATION_H, &index);
-			freq_next = od_info->freq_table[index].frequency;
+			index = cpufreq_table_find_index_h(policy,
+							   policy->cur - 1);
+			freq_next = policy->freq_table[index].frequency;
 		}
 
 		data->freq_prev = freq_next;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 5617c7087d77..3dd4884c6f9e 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -74,19 +74,12 @@ static inline bool has_target(void)
 }
 
 /* internal prototypes */
-static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
 static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
+static int cpufreq_init_governor(struct cpufreq_policy *policy);
+static void cpufreq_exit_governor(struct cpufreq_policy *policy);
 static int cpufreq_start_governor(struct cpufreq_policy *policy);
-
-static inline void cpufreq_exit_governor(struct cpufreq_policy *policy)
-{
-	(void)cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-}
-
-static inline void cpufreq_stop_governor(struct cpufreq_policy *policy)
-{
-	(void)cpufreq_governor(policy, CPUFREQ_GOV_STOP);
-}
+static void cpufreq_stop_governor(struct cpufreq_policy *policy);
+static void cpufreq_governor_limits(struct cpufreq_policy *policy);
 
 /**
  * Two notifier lists: the "policy" list is involved in the
@@ -133,15 +126,6 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(get_governor_parent_kobj);
 
-struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
-
-	return policy && !policy_is_inactive(policy) ?
-		policy->freq_table : NULL;
-}
-EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
-
 static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
 	u64 idle_time;
@@ -354,6 +338,7 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
 		pr_debug("FREQ: %lu - CPU: %lu\n",
 			 (unsigned long)freqs->new, (unsigned long)freqs->cpu);
 		trace_cpu_frequency(freqs->new, freqs->cpu);
+		cpufreq_stats_record_transition(policy, freqs->new);
 		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
 				CPUFREQ_POSTCHANGE, freqs);
 		if (likely(policy) && likely(policy->cpu == freqs->cpu))
@@ -507,6 +492,38 @@ void cpufreq_disable_fast_switch(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch);
 
+/**
+ * cpufreq_driver_resolve_freq - Map a target frequency to a driver-supported
+ * one.
+ * @target_freq: target frequency to resolve.
+ *
+ * The target to driver frequency mapping is cached in the policy.
+ *
+ * Return: Lowest driver-supported frequency greater than or equal to the
+ * given target_freq, subject to policy (min/max) and driver limitations.
+ */
+unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
+					 unsigned int target_freq)
+{
+	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	policy->cached_target_freq = target_freq;
+
+	if (cpufreq_driver->target_index) {
+		int idx;
+
+		idx = cpufreq_frequency_table_target(policy, target_freq,
+						     CPUFREQ_RELATION_L);
+		policy->cached_resolved_idx = idx;
+		return policy->freq_table[idx].frequency;
+	}
+
+	if (cpufreq_driver->resolve_freq)
+		return cpufreq_driver->resolve_freq(policy, target_freq);
+
+	return target_freq;
+}
+EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq);
+
 /*********************************************************************
  *                          SYSFS INTERFACE                          *
  *********************************************************************/
@@ -1115,6 +1132,7 @@ static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify)
 					     CPUFREQ_REMOVE_POLICY, policy);
 
 	down_write(&policy->rwsem);
+	cpufreq_stats_free_table(policy);
 	cpufreq_remove_dev_symlink(policy);
 	kobj = &policy->kobj;
 	cmp = &policy->kobj_unregister;
@@ -1265,13 +1283,12 @@ static int cpufreq_online(unsigned int cpu)
 		}
 	}
 
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-				     CPUFREQ_START, policy);
-
 	if (new_policy) {
 		ret = cpufreq_add_dev_interface(policy);
 		if (ret)
 			goto out_exit_policy;
+
+		cpufreq_stats_create_table(policy);
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				CPUFREQ_CREATE_POLICY, policy);
 
@@ -1280,6 +1297,9 @@ static int cpufreq_online(unsigned int cpu)
 		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",
@@ -1556,9 +1576,6 @@ static unsigned int cpufreq_update_current_freq(struct cpufreq_policy *policy)
 {
 	unsigned int new_freq;
 
-	if (cpufreq_suspended)
-		return 0;
-
 	new_freq = cpufreq_driver->get(policy->cpu);
 	if (!new_freq)
 		return 0;
@@ -1864,14 +1881,17 @@ static int __target_intermediate(struct cpufreq_policy *policy,
 	return ret;
 }
 
-static int __target_index(struct cpufreq_policy *policy,
-			  struct cpufreq_frequency_table *freq_table, int index)
+static int __target_index(struct cpufreq_policy *policy, int index)
 {
 	struct cpufreq_freqs freqs = {.old = policy->cur, .flags = 0};
 	unsigned int intermediate_freq = 0;
+	unsigned int newfreq = policy->freq_table[index].frequency;
 	int retval = -EINVAL;
 	bool notify;
 
+	if (newfreq == policy->cur)
+		return 0;
+
 	notify = !(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION);
 	if (notify) {
 		/* Handle switching to intermediate frequency */
@@ -1886,7 +1906,7 @@ static int __target_index(struct cpufreq_policy *policy,
 				freqs.old = freqs.new;
 		}
 
-		freqs.new = freq_table[index].frequency;
+		freqs.new = newfreq;
 		pr_debug("%s: cpu: %d, oldfreq: %u, new freq: %u\n",
 			 __func__, policy->cpu, freqs.old, freqs.new);
 
@@ -1923,17 +1943,13 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 			    unsigned int relation)
 {
 	unsigned int old_target_freq = target_freq;
-	struct cpufreq_frequency_table *freq_table;
-	int index, retval;
+	int index;
 
 	if (cpufreq_disabled())
 		return -ENODEV;
 
 	/* Make sure that target_freq is within supported range */
-	if (target_freq > policy->max)
-		target_freq = policy->max;
-	if (target_freq < policy->min)
-		target_freq = policy->min;
+	target_freq = clamp_val(target_freq, policy->min, policy->max);
 
 	pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
 		 policy->cpu, target_freq, relation, old_target_freq);
@@ -1956,23 +1972,9 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	if (!cpufreq_driver->target_index)
 		return -EINVAL;
 
-	freq_table = cpufreq_frequency_get_table(policy->cpu);
-	if (unlikely(!freq_table)) {
-		pr_err("%s: Unable to find freq_table\n", __func__);
-		return -EINVAL;
-	}
-
-	retval = cpufreq_frequency_table_target(policy, freq_table, target_freq,
-						relation, &index);
-	if (unlikely(retval)) {
-		pr_err("%s: Unable to find matching freq\n", __func__);
-		return retval;
-	}
-
-	if (freq_table[index].frequency == policy->cur)
-		return 0;
+	index = cpufreq_frequency_table_target(policy, target_freq, relation);
 
-	return __target_index(policy, freq_table, index);
+	return __target_index(policy, index);
 }
 EXPORT_SYMBOL_GPL(__cpufreq_driver_target);
 
@@ -1997,7 +1999,7 @@ __weak struct cpufreq_governor *cpufreq_fallback_governor(void)
 	return NULL;
 }
 
-static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event)
+static int cpufreq_init_governor(struct cpufreq_policy *policy)
 {
 	int ret;
 
@@ -2025,36 +2027,82 @@ static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event)
 		}
 	}
 
-	if (event == CPUFREQ_GOV_POLICY_INIT)
-		if (!try_module_get(policy->governor->owner))
-			return -EINVAL;
-
-	pr_debug("%s: for CPU %u, event %u\n", __func__, policy->cpu, event);
+	if (!try_module_get(policy->governor->owner))
+		return -EINVAL;
 
-	ret = policy->governor->governor(policy, event);
+	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);
 
-	if (event == CPUFREQ_GOV_POLICY_INIT) {
-		if (ret)
+	if (policy->governor->init) {
+		ret = policy->governor->init(policy);
+		if (ret) {
 			module_put(policy->governor->owner);
-		else
-			policy->governor->initialized++;
-	} else if (event == CPUFREQ_GOV_POLICY_EXIT) {
-		policy->governor->initialized--;
-		module_put(policy->governor->owner);
+			return ret;
+		}
 	}
 
-	return ret;
+	return 0;
+}
+
+static void cpufreq_exit_governor(struct cpufreq_policy *policy)
+{
+	if (cpufreq_suspended || !policy->governor)
+		return;
+
+	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);
+
+	if (policy->governor->exit)
+		policy->governor->exit(policy);
+
+	module_put(policy->governor->owner);
 }
 
 static int cpufreq_start_governor(struct cpufreq_policy *policy)
 {
 	int ret;
 
+	if (cpufreq_suspended)
+		return 0;
+
+	if (!policy->governor)
+		return -EINVAL;
+
+	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);
+
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy)
 		cpufreq_update_current_freq(policy);
 
-	ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
-	return ret ? ret : cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+	if (policy->governor->start) {
+		ret = policy->governor->start(policy);
+		if (ret)
+			return ret;
+	}
+
+	if (policy->governor->limits)
+		policy->governor->limits(policy);
+
+	return 0;
+}
+
+static void cpufreq_stop_governor(struct cpufreq_policy *policy)
+{
+	if (cpufreq_suspended || !policy->governor)
+		return;
+
+	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);
+
+	if (policy->governor->stop)
+		policy->governor->stop(policy);
+}
+
+static void cpufreq_governor_limits(struct cpufreq_policy *policy)
+{
+	if (cpufreq_suspended || !policy->governor)
+		return;
+
+	pr_debug("%s: for CPU %u\n", __func__, policy->cpu);
+
+	if (policy->governor->limits)
+		policy->governor->limits(policy);
 }
 
 int cpufreq_register_governor(struct cpufreq_governor *governor)
@@ -2069,7 +2117,6 @@ int cpufreq_register_governor(struct cpufreq_governor *governor)
 
 	mutex_lock(&cpufreq_governor_mutex);
 
-	governor->initialized = 0;
 	err = -EBUSY;
 	if (!find_governor(governor->name)) {
 		err = 0;
@@ -2184,6 +2231,8 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	policy->min = new_policy->min;
 	policy->max = new_policy->max;
 
+	policy->cached_target_freq = UINT_MAX;
+
 	pr_debug("new min and max freqs are %u - %u kHz\n",
 		 policy->min, policy->max);
 
@@ -2195,7 +2244,8 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	if (new_policy->governor == policy->governor) {
 		pr_debug("cpufreq: governor limits update\n");
-		return cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+		cpufreq_governor_limits(policy);
+		return 0;
 	}
 
 	pr_debug("governor switch\n");
@@ -2210,7 +2260,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	/* start new governor */
 	policy->governor = new_policy->governor;
-	ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
+	ret = cpufreq_init_governor(policy);
 	if (!ret) {
 		ret = cpufreq_start_governor(policy);
 		if (!ret) {
@@ -2224,7 +2274,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	pr_debug("starting governor %s failed\n", policy->governor->name);
 	if (old_gov) {
 		policy->governor = old_gov;
-		if (cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
+		if (cpufreq_init_governor(policy))
 			policy->governor = NULL;
 		else
 			cpufreq_start_governor(policy);
@@ -2309,26 +2359,25 @@ static struct notifier_block __refdata cpufreq_cpu_notifier = {
  *********************************************************************/
 static int cpufreq_boost_set_sw(int state)
 {
-	struct cpufreq_frequency_table *freq_table;
 	struct cpufreq_policy *policy;
 	int ret = -EINVAL;
 
 	for_each_active_policy(policy) {
-		freq_table = cpufreq_frequency_get_table(policy->cpu);
-		if (freq_table) {
-			ret = cpufreq_frequency_table_cpuinfo(policy,
-							freq_table);
-			if (ret) {
-				pr_err("%s: Policy frequency update failed\n",
-				       __func__);
-				break;
-			}
-
-			down_write(&policy->rwsem);
-			policy->user_policy.max = policy->max;
-			cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
-			up_write(&policy->rwsem);
+		if (!policy->freq_table)
+			continue;
+
+		ret = cpufreq_frequency_table_cpuinfo(policy,
+						      policy->freq_table);
+		if (ret) {
+			pr_err("%s: Policy frequency update failed\n",
+			       __func__);
+			break;
 		}
+
+		down_write(&policy->rwsem);
+		policy->user_policy.max = policy->max;
+		cpufreq_governor_limits(policy);
+		up_write(&policy->rwsem);
 	}
 
 	return ret;
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 316df247e00d..18da4f8051d3 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -17,7 +17,6 @@
 struct cs_policy_dbs_info {
 	struct policy_dbs_info policy_dbs;
 	unsigned int down_skip;
-	unsigned int requested_freq;
 };
 
 static inline struct cs_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs)
@@ -75,19 +74,17 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 
 	/* Check for frequency increase */
 	if (load > dbs_data->up_threshold) {
+		unsigned int requested_freq = policy->cur;
+
 		dbs_info->down_skip = 0;
 
 		/* if we are already at full speed then break out early */
-		if (dbs_info->requested_freq == policy->max)
+		if (requested_freq == policy->max)
 			goto out;
 
-		dbs_info->requested_freq += get_freq_target(cs_tuners, policy);
-
-		if (dbs_info->requested_freq > policy->max)
-			dbs_info->requested_freq = policy->max;
+		requested_freq += get_freq_target(cs_tuners, policy);
 
-		__cpufreq_driver_target(policy, dbs_info->requested_freq,
-			CPUFREQ_RELATION_H);
+		__cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_H);
 		goto out;
 	}
 
@@ -98,36 +95,27 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 
 	/* Check for frequency decrease */
 	if (load < cs_tuners->down_threshold) {
-		unsigned int freq_target;
+		unsigned int freq_target, requested_freq = policy->cur;
 		/*
 		 * if we cannot reduce the frequency anymore, break out early
 		 */
-		if (policy->cur == policy->min)
+		if (requested_freq == policy->min)
 			goto out;
 
 		freq_target = get_freq_target(cs_tuners, policy);
-		if (dbs_info->requested_freq > freq_target)
-			dbs_info->requested_freq -= freq_target;
+		if (requested_freq > freq_target)
+			requested_freq -= freq_target;
 		else
-			dbs_info->requested_freq = policy->min;
+			requested_freq = policy->min;
 
-		__cpufreq_driver_target(policy, dbs_info->requested_freq,
-				CPUFREQ_RELATION_L);
+		__cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_L);
 	}
 
  out:
 	return dbs_data->sampling_rate;
 }
 
-static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-				void *data);
-
-static struct notifier_block cs_cpufreq_notifier_block = {
-	.notifier_call = dbs_cpufreq_notifier,
-};
-
 /************************** sysfs interface ************************/
-static struct dbs_governor cs_dbs_gov;
 
 static ssize_t store_sampling_down_factor(struct gov_attr_set *attr_set,
 					  const char *buf, size_t count)
@@ -268,15 +256,13 @@ static void cs_free(struct policy_dbs_info *policy_dbs)
 	kfree(to_dbs_info(policy_dbs));
 }
 
-static int cs_init(struct dbs_data *dbs_data, bool notify)
+static int cs_init(struct dbs_data *dbs_data)
 {
 	struct cs_dbs_tuners *tuners;
 
 	tuners = kzalloc(sizeof(*tuners), GFP_KERNEL);
-	if (!tuners) {
-		pr_err("%s: kzalloc failed\n", __func__);
+	if (!tuners)
 		return -ENOMEM;
-	}
 
 	tuners->down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD;
 	tuners->freq_step = DEF_FREQUENCY_STEP;
@@ -288,19 +274,11 @@ static int cs_init(struct dbs_data *dbs_data, bool notify)
 	dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
 		jiffies_to_usecs(10);
 
-	if (notify)
-		cpufreq_register_notifier(&cs_cpufreq_notifier_block,
-					  CPUFREQ_TRANSITION_NOTIFIER);
-
 	return 0;
 }
 
-static void cs_exit(struct dbs_data *dbs_data, bool notify)
+static void cs_exit(struct dbs_data *dbs_data)
 {
-	if (notify)
-		cpufreq_unregister_notifier(&cs_cpufreq_notifier_block,
-					    CPUFREQ_TRANSITION_NOTIFIER);
-
 	kfree(dbs_data->tuners);
 }
 
@@ -309,16 +287,10 @@ static void cs_start(struct cpufreq_policy *policy)
 	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
 
 	dbs_info->down_skip = 0;
-	dbs_info->requested_freq = policy->cur;
 }
 
-static struct dbs_governor cs_dbs_gov = {
-	.gov = {
-		.name = "conservative",
-		.governor = cpufreq_governor_dbs,
-		.max_transition_latency = TRANSITION_LATENCY_LIMIT,
-		.owner = THIS_MODULE,
-	},
+static struct dbs_governor cs_governor = {
+	.gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("conservative"),
 	.kobj_type = { .default_attrs = cs_attributes },
 	.gov_dbs_timer = cs_dbs_timer,
 	.alloc = cs_alloc,
@@ -328,33 +300,7 @@ static struct dbs_governor cs_dbs_gov = {
 	.start = cs_start,
 };
 
-#define CPU_FREQ_GOV_CONSERVATIVE	(&cs_dbs_gov.gov)
-
-static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-				void *data)
-{
-	struct cpufreq_freqs *freq = data;
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu);
-	struct cs_policy_dbs_info *dbs_info;
-
-	if (!policy)
-		return 0;
-
-	/* policy isn't governed by conservative governor */
-	if (policy->governor != CPU_FREQ_GOV_CONSERVATIVE)
-		return 0;
-
-	dbs_info = to_dbs_info(policy->governor_data);
-	/*
-	 * we only care if our internally tracked freq moves outside the 'valid'
-	 * ranges of frequency available to us otherwise we do not change it
-	*/
-	if (dbs_info->requested_freq > policy->max
-			|| dbs_info->requested_freq < policy->min)
-		dbs_info->requested_freq = freq->new;
-
-	return 0;
-}
+#define CPU_FREQ_GOV_CONSERVATIVE	(&cs_governor.gov)
 
 static int __init cpufreq_gov_dbs_init(void)
 {
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index be498d56dd69..e415349ab31b 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -336,17 +336,6 @@ static inline void gov_clear_update_util(struct cpufreq_policy *policy)
 	synchronize_sched();
 }
 
-static void gov_cancel_work(struct cpufreq_policy *policy)
-{
-	struct policy_dbs_info *policy_dbs = policy->governor_data;
-
-	gov_clear_update_util(policy_dbs->policy);
-	irq_work_sync(&policy_dbs->irq_work);
-	cancel_work_sync(&policy_dbs->work);
-	atomic_set(&policy_dbs->work_count, 0);
-	policy_dbs->work_in_progress = false;
-}
-
 static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *policy,
 						     struct dbs_governor *gov)
 {
@@ -389,7 +378,7 @@ static void free_policy_dbs_info(struct policy_dbs_info *policy_dbs,
 	gov->free(policy_dbs);
 }
 
-static int cpufreq_governor_init(struct cpufreq_policy *policy)
+int cpufreq_dbs_governor_init(struct cpufreq_policy *policy)
 {
 	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct dbs_data *dbs_data;
@@ -429,7 +418,7 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy)
 
 	gov_attr_set_init(&dbs_data->attr_set, &policy_dbs->list);
 
-	ret = gov->init(dbs_data, !policy->governor->initialized);
+	ret = gov->init(dbs_data);
 	if (ret)
 		goto free_policy_dbs_info;
 
@@ -458,13 +447,13 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy)
 		goto out;
 
 	/* Failure, so roll back. */
-	pr_err("cpufreq: Governor initialization failed (dbs_data kobject init error %d)\n", ret);
+	pr_err("initialization failed (dbs_data kobject init error %d)\n", ret);
 
 	policy->governor_data = NULL;
 
 	if (!have_governor_per_policy())
 		gov->gdbs_data = NULL;
-	gov->exit(dbs_data, !policy->governor->initialized);
+	gov->exit(dbs_data);
 	kfree(dbs_data);
 
 free_policy_dbs_info:
@@ -474,8 +463,9 @@ out:
 	mutex_unlock(&gov_dbs_data_mutex);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_init);
 
-static int cpufreq_governor_exit(struct cpufreq_policy *policy)
+void cpufreq_dbs_governor_exit(struct cpufreq_policy *policy)
 {
 	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
@@ -493,17 +483,17 @@ static int cpufreq_governor_exit(struct cpufreq_policy *policy)
 		if (!have_governor_per_policy())
 			gov->gdbs_data = NULL;
 
-		gov->exit(dbs_data, policy->governor->initialized == 1);
+		gov->exit(dbs_data);
 		kfree(dbs_data);
 	}
 
 	free_policy_dbs_info(policy_dbs, gov);
 
 	mutex_unlock(&gov_dbs_data_mutex);
-	return 0;
 }
+EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_exit);
 
-static int cpufreq_governor_start(struct cpufreq_policy *policy)
+int cpufreq_dbs_governor_start(struct cpufreq_policy *policy)
 {
 	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
@@ -539,47 +529,28 @@ static int cpufreq_governor_start(struct cpufreq_policy *policy)
 	gov_set_update_util(policy_dbs, sampling_rate);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_start);
 
-static int cpufreq_governor_stop(struct cpufreq_policy *policy)
+void cpufreq_dbs_governor_stop(struct cpufreq_policy *policy)
 {
-	gov_cancel_work(policy);
-	return 0;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+
+	gov_clear_update_util(policy_dbs->policy);
+	irq_work_sync(&policy_dbs->irq_work);
+	cancel_work_sync(&policy_dbs->work);
+	atomic_set(&policy_dbs->work_count, 0);
+	policy_dbs->work_in_progress = false;
 }
+EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_stop);
 
-static int cpufreq_governor_limits(struct cpufreq_policy *policy)
+void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy)
 {
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
 
 	mutex_lock(&policy_dbs->timer_mutex);
-
-	if (policy->max < policy->cur)
-		__cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H);
-	else if (policy->min > policy->cur)
-		__cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L);
-
+	cpufreq_policy_apply_limits(policy);
 	gov_update_sample_delay(policy_dbs, 0);
 
 	mutex_unlock(&policy_dbs->timer_mutex);
-
-	return 0;
-}
-
-int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event)
-{
-	if (event == CPUFREQ_GOV_POLICY_INIT) {
-		return cpufreq_governor_init(policy);
-	} else if (policy->governor_data) {
-		switch (event) {
-		case CPUFREQ_GOV_POLICY_EXIT:
-			return cpufreq_governor_exit(policy);
-		case CPUFREQ_GOV_START:
-			return cpufreq_governor_start(policy);
-		case CPUFREQ_GOV_STOP:
-			return cpufreq_governor_stop(policy);
-		case CPUFREQ_GOV_LIMITS:
-			return cpufreq_governor_limits(policy);
-		}
-	}
-	return -EINVAL;
 }
-EXPORT_SYMBOL_GPL(cpufreq_governor_dbs);
+EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_limits);
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 34eb214b6d57..ef1037e9c92b 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -138,8 +138,8 @@ struct dbs_governor {
 	unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy);
 	struct policy_dbs_info *(*alloc)(void);
 	void (*free)(struct policy_dbs_info *policy_dbs);
-	int (*init)(struct dbs_data *dbs_data, bool notify);
-	void (*exit)(struct dbs_data *dbs_data, bool notify);
+	int (*init)(struct dbs_data *dbs_data);
+	void (*exit)(struct dbs_data *dbs_data);
 	void (*start)(struct cpufreq_policy *policy);
 };
 
@@ -148,6 +148,25 @@ static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy
 	return container_of(policy->governor, struct dbs_governor, gov);
 }
 
+/* Governor callback routines */
+int cpufreq_dbs_governor_init(struct cpufreq_policy *policy);
+void cpufreq_dbs_governor_exit(struct cpufreq_policy *policy);
+int cpufreq_dbs_governor_start(struct cpufreq_policy *policy);
+void cpufreq_dbs_governor_stop(struct cpufreq_policy *policy);
+void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy);
+
+#define CPUFREQ_DBS_GOVERNOR_INITIALIZER(_name_)			\
+	{								\
+		.name = _name_,						\
+		.max_transition_latency	= TRANSITION_LATENCY_LIMIT,	\
+		.owner = THIS_MODULE,					\
+		.init = cpufreq_dbs_governor_init,			\
+		.exit = cpufreq_dbs_governor_exit,			\
+		.start = cpufreq_dbs_governor_start,			\
+		.stop = cpufreq_dbs_governor_stop,			\
+		.limits = cpufreq_dbs_governor_limits,			\
+	}
+
 /* Governor specific operations */
 struct od_ops {
 	unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
@@ -155,7 +174,6 @@ struct od_ops {
 };
 
 unsigned int dbs_update(struct cpufreq_policy *policy);
-int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event);
 void od_register_powersave_bias_handler(unsigned int (*f)
 		(struct cpufreq_policy *, unsigned int, unsigned int),
 		unsigned int powersave_bias);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 300163430516..3a1f49f5f4c6 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -65,34 +65,30 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
 {
 	unsigned int freq_req, freq_reduc, freq_avg;
 	unsigned int freq_hi, freq_lo;
-	unsigned int index = 0;
+	unsigned int index;
 	unsigned int delay_hi_us;
 	struct policy_dbs_info *policy_dbs = policy->governor_data;
 	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
 	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct cpufreq_frequency_table *freq_table = policy->freq_table;
 
-	if (!dbs_info->freq_table) {
+	if (!freq_table) {
 		dbs_info->freq_lo = 0;
 		dbs_info->freq_lo_delay_us = 0;
 		return freq_next;
 	}
 
-	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_next,
-			relation, &index);
-	freq_req = dbs_info->freq_table[index].frequency;
+	index = cpufreq_frequency_table_target(policy, freq_next, relation);
+	freq_req = freq_table[index].frequency;
 	freq_reduc = freq_req * od_tuners->powersave_bias / 1000;
 	freq_avg = freq_req - freq_reduc;
 
 	/* Find freq bounds for freq_avg in freq_table */
-	index = 0;
-	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_avg,
-			CPUFREQ_RELATION_H, &index);
-	freq_lo = dbs_info->freq_table[index].frequency;
-	index = 0;
-	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_avg,
-			CPUFREQ_RELATION_L, &index);
-	freq_hi = dbs_info->freq_table[index].frequency;
+	index = cpufreq_table_find_index_h(policy, freq_avg);
+	freq_lo = freq_table[index].frequency;
+	index = cpufreq_table_find_index_l(policy, freq_avg);
+	freq_hi = freq_table[index].frequency;
 
 	/* Find out how long we have to be in hi and lo freqs */
 	if (freq_hi == freq_lo) {
@@ -113,7 +109,6 @@ static void ondemand_powersave_bias_init(struct cpufreq_policy *policy)
 {
 	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
 
-	dbs_info->freq_table = cpufreq_frequency_get_table(policy->cpu);
 	dbs_info->freq_lo = 0;
 }
 
@@ -361,17 +356,15 @@ static void od_free(struct policy_dbs_info *policy_dbs)
 	kfree(to_dbs_info(policy_dbs));
 }
 
-static int od_init(struct dbs_data *dbs_data, bool notify)
+static int od_init(struct dbs_data *dbs_data)
 {
 	struct od_dbs_tuners *tuners;
 	u64 idle_time;
 	int cpu;
 
 	tuners = kzalloc(sizeof(*tuners), GFP_KERNEL);
-	if (!tuners) {
-		pr_err("%s: kzalloc failed\n", __func__);
+	if (!tuners)
 		return -ENOMEM;
-	}
 
 	cpu = get_cpu();
 	idle_time = get_cpu_idle_time_us(cpu, NULL);
@@ -402,7 +395,7 @@ static int od_init(struct dbs_data *dbs_data, bool notify)
 	return 0;
 }
 
-static void od_exit(struct dbs_data *dbs_data, bool notify)
+static void od_exit(struct dbs_data *dbs_data)
 {
 	kfree(dbs_data->tuners);
 }
@@ -420,12 +413,7 @@ static struct od_ops od_ops = {
 };
 
 static struct dbs_governor od_dbs_gov = {
-	.gov = {
-		.name = "ondemand",
-		.governor = cpufreq_governor_dbs,
-		.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
-		.owner = THIS_MODULE,
-	},
+	.gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("ondemand"),
 	.kobj_type = { .default_attrs = od_attributes },
 	.gov_dbs_timer = od_dbs_timer,
 	.alloc = od_alloc,
diff --git a/drivers/cpufreq/cpufreq_ondemand.h b/drivers/cpufreq/cpufreq_ondemand.h
index f0121db3cd9e..640ea4e97106 100644
--- a/drivers/cpufreq/cpufreq_ondemand.h
+++ b/drivers/cpufreq/cpufreq_ondemand.h
@@ -13,7 +13,6 @@
 
 struct od_policy_dbs_info {
 	struct policy_dbs_info policy_dbs;
-	struct cpufreq_frequency_table *freq_table;
 	unsigned int freq_lo;
 	unsigned int freq_lo_delay_us;
 	unsigned int freq_hi_delay_us;
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index af9f4b96f5a8..dafb679adc58 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -16,27 +16,16 @@
 #include <linux/init.h>
 #include <linux/module.h>
 
-static int cpufreq_governor_performance(struct cpufreq_policy *policy,
-					unsigned int event)
+static void cpufreq_gov_performance_limits(struct cpufreq_policy *policy)
 {
-	switch (event) {
-	case CPUFREQ_GOV_START:
-	case CPUFREQ_GOV_LIMITS:
-		pr_debug("setting to %u kHz because of event %u\n",
-						policy->max, event);
-		__cpufreq_driver_target(policy, policy->max,
-						CPUFREQ_RELATION_H);
-		break;
-	default:
-		break;
-	}
-	return 0;
+	pr_debug("setting to %u kHz\n", policy->max);
+	__cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H);
 }
 
 static struct cpufreq_governor cpufreq_gov_performance = {
 	.name		= "performance",
-	.governor	= cpufreq_governor_performance,
 	.owner		= THIS_MODULE,
+	.limits		= cpufreq_gov_performance_limits,
 };
 
 static int __init cpufreq_gov_performance_init(void)
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index b8b400232a74..78a651038faf 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -16,26 +16,15 @@
 #include <linux/init.h>
 #include <linux/module.h>
 
-static int cpufreq_governor_powersave(struct cpufreq_policy *policy,
-					unsigned int event)
+static void cpufreq_gov_powersave_limits(struct cpufreq_policy *policy)
 {
-	switch (event) {
-	case CPUFREQ_GOV_START:
-	case CPUFREQ_GOV_LIMITS:
-		pr_debug("setting to %u kHz because of event %u\n",
-							policy->min, event);
-		__cpufreq_driver_target(policy, policy->min,
-						CPUFREQ_RELATION_L);
-		break;
-	default:
-		break;
-	}
-	return 0;
+	pr_debug("setting to %u kHz\n", policy->min);
+	__cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L);
 }
 
 static struct cpufreq_governor cpufreq_gov_powersave = {
 	.name		= "powersave",
-	.governor	= cpufreq_governor_powersave,
+	.limits		= cpufreq_gov_powersave_limits,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 5e370a30a964..06d3abdffd3a 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -15,7 +15,7 @@
 #include <linux/slab.h>
 #include <linux/cputime.h>
 
-static spinlock_t cpufreq_stats_lock;
+static DEFINE_SPINLOCK(cpufreq_stats_lock);
 
 struct cpufreq_stats {
 	unsigned int total_trans;
@@ -52,6 +52,9 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 	ssize_t len = 0;
 	int i;
 
+	if (policy->fast_switch_enabled)
+		return 0;
+
 	cpufreq_stats_update(stats);
 	for (i = 0; i < stats->state_num; i++) {
 		len += sprintf(buf + len, "%u %llu\n", stats->freq_table[i],
@@ -68,6 +71,9 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 	ssize_t len = 0;
 	int i, j;
 
+	if (policy->fast_switch_enabled)
+		return 0;
+
 	len += snprintf(buf + len, PAGE_SIZE - len, "   From  :    To\n");
 	len += snprintf(buf + len, PAGE_SIZE - len, "         : ");
 	for (i = 0; i < stats->state_num; i++) {
@@ -130,7 +136,7 @@ static int freq_table_get_index(struct cpufreq_stats *stats, unsigned int freq)
 	return -1;
 }
 
-static void __cpufreq_stats_free_table(struct cpufreq_policy *policy)
+void cpufreq_stats_free_table(struct cpufreq_policy *policy)
 {
 	struct cpufreq_stats *stats = policy->stats;
 
@@ -146,39 +152,25 @@ static void __cpufreq_stats_free_table(struct cpufreq_policy *policy)
 	policy->stats = NULL;
 }
 
-static void cpufreq_stats_free_table(unsigned int cpu)
-{
-	struct cpufreq_policy *policy;
-
-	policy = cpufreq_cpu_get(cpu);
-	if (!policy)
-		return;
-
-	__cpufreq_stats_free_table(policy);
-
-	cpufreq_cpu_put(policy);
-}
-
-static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
+void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 {
 	unsigned int i = 0, count = 0, ret = -ENOMEM;
 	struct cpufreq_stats *stats;
 	unsigned int alloc_size;
-	unsigned int cpu = policy->cpu;
 	struct cpufreq_frequency_table *pos, *table;
 
 	/* We need cpufreq table for creating stats table */
-	table = cpufreq_frequency_get_table(cpu);
+	table = policy->freq_table;
 	if (unlikely(!table))
-		return 0;
+		return;
 
 	/* stats already initialized */
 	if (policy->stats)
-		return -EEXIST;
+		return;
 
 	stats = kzalloc(sizeof(*stats), GFP_KERNEL);
 	if (!stats)
-		return -ENOMEM;
+		return;
 
 	/* Find total allocation size */
 	cpufreq_for_each_valid_entry(pos, table)
@@ -215,80 +207,32 @@ static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	policy->stats = stats;
 	ret = sysfs_create_group(&policy->kobj, &stats_attr_group);
 	if (!ret)
-		return 0;
+		return;
 
 	/* We failed, release resources */
 	policy->stats = NULL;
 	kfree(stats->time_in_state);
 free_stat:
 	kfree(stats);
-
-	return ret;
-}
-
-static void cpufreq_stats_create_table(unsigned int cpu)
-{
-	struct cpufreq_policy *policy;
-
-	/*
-	 * "likely(!policy)" because normally cpufreq_stats will be registered
-	 * before cpufreq driver
-	 */
-	policy = cpufreq_cpu_get(cpu);
-	if (likely(!policy))
-		return;
-
-	__cpufreq_stats_create_table(policy);
-
-	cpufreq_cpu_put(policy);
 }
 
-static int cpufreq_stat_notifier_policy(struct notifier_block *nb,
-		unsigned long val, void *data)
+void cpufreq_stats_record_transition(struct cpufreq_policy *policy,
+				     unsigned int new_freq)
 {
-	int ret = 0;
-	struct cpufreq_policy *policy = data;
-
-	if (val == CPUFREQ_CREATE_POLICY)
-		ret = __cpufreq_stats_create_table(policy);
-	else if (val == CPUFREQ_REMOVE_POLICY)
-		__cpufreq_stats_free_table(policy);
-
-	return ret;
-}
-
-static int cpufreq_stat_notifier_trans(struct notifier_block *nb,
-		unsigned long val, void *data)
-{
-	struct cpufreq_freqs *freq = data;
-	struct cpufreq_policy *policy = cpufreq_cpu_get(freq->cpu);
-	struct cpufreq_stats *stats;
+	struct cpufreq_stats *stats = policy->stats;
 	int old_index, new_index;
 
-	if (!policy) {
-		pr_err("%s: No policy found\n", __func__);
-		return 0;
-	}
-
-	if (val != CPUFREQ_POSTCHANGE)
-		goto put_policy;
-
-	if (!policy->stats) {
+	if (!stats) {
 		pr_debug("%s: No stats found\n", __func__);
-		goto put_policy;
+		return;
 	}
 
-	stats = policy->stats;
-
 	old_index = stats->last_index;
-	new_index = freq_table_get_index(stats, freq->new);
+	new_index = freq_table_get_index(stats, new_freq);
 
 	/* We can't do stats->time_in_state[-1]= .. */
-	if (old_index == -1 || new_index == -1)
-		goto put_policy;
-
-	if (old_index == new_index)
-		goto put_policy;
+	if (old_index == -1 || new_index == -1 || old_index == new_index)
+		return;
 
 	cpufreq_stats_update(stats);
 
@@ -297,61 +241,4 @@ static int cpufreq_stat_notifier_trans(struct notifier_block *nb,
 	stats->trans_table[old_index * stats->max_state + new_index]++;
 #endif
 	stats->total_trans++;
-
-put_policy:
-	cpufreq_cpu_put(policy);
-	return 0;
 }
-
-static struct notifier_block notifier_policy_block = {
-	.notifier_call = cpufreq_stat_notifier_policy
-};
-
-static struct notifier_block notifier_trans_block = {
-	.notifier_call = cpufreq_stat_notifier_trans
-};
-
-static int __init cpufreq_stats_init(void)
-{
-	int ret;
-	unsigned int cpu;
-
-	spin_lock_init(&cpufreq_stats_lock);
-	ret = cpufreq_register_notifier(&notifier_policy_block,
-				CPUFREQ_POLICY_NOTIFIER);
-	if (ret)
-		return ret;
-
-	for_each_online_cpu(cpu)
-		cpufreq_stats_create_table(cpu);
-
-	ret = cpufreq_register_notifier(&notifier_trans_block,
-				CPUFREQ_TRANSITION_NOTIFIER);
-	if (ret) {
-		cpufreq_unregister_notifier(&notifier_policy_block,
-				CPUFREQ_POLICY_NOTIFIER);
-		for_each_online_cpu(cpu)
-			cpufreq_stats_free_table(cpu);
-		return ret;
-	}
-
-	return 0;
-}
-static void __exit cpufreq_stats_exit(void)
-{
-	unsigned int cpu;
-
-	cpufreq_unregister_notifier(&notifier_policy_block,
-			CPUFREQ_POLICY_NOTIFIER);
-	cpufreq_unregister_notifier(&notifier_trans_block,
-			CPUFREQ_TRANSITION_NOTIFIER);
-	for_each_online_cpu(cpu)
-		cpufreq_stats_free_table(cpu);
-}
-
-MODULE_AUTHOR("Zou Nan hai <nanhai.zou@intel.com>");
-MODULE_DESCRIPTION("Export cpufreq stats via sysfs");
-MODULE_LICENSE("GPL");
-
-module_init(cpufreq_stats_init);
-module_exit(cpufreq_stats_exit);
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index 9f3dec9a3f36..bd897e3e134d 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -65,66 +65,66 @@ static int cpufreq_userspace_policy_init(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
-				   unsigned int event)
+static void cpufreq_userspace_policy_exit(struct cpufreq_policy *policy)
+{
+	mutex_lock(&userspace_mutex);
+	kfree(policy->governor_data);
+	policy->governor_data = NULL;
+	mutex_unlock(&userspace_mutex);
+}
+
+static int cpufreq_userspace_policy_start(struct cpufreq_policy *policy)
 {
 	unsigned int *setspeed = policy->governor_data;
-	unsigned int cpu = policy->cpu;
-	int rc = 0;
 
-	if (event == CPUFREQ_GOV_POLICY_INIT)
-		return cpufreq_userspace_policy_init(policy);
+	BUG_ON(!policy->cur);
+	pr_debug("started managing cpu %u\n", policy->cpu);
 
-	if (!setspeed)
-		return -EINVAL;
-
-	switch (event) {
-	case CPUFREQ_GOV_POLICY_EXIT:
-		mutex_lock(&userspace_mutex);
-		policy->governor_data = NULL;
-		kfree(setspeed);
-		mutex_unlock(&userspace_mutex);
-		break;
-	case CPUFREQ_GOV_START:
-		BUG_ON(!policy->cur);
-		pr_debug("started managing cpu %u\n", cpu);
-
-		mutex_lock(&userspace_mutex);
-		per_cpu(cpu_is_managed, cpu) = 1;
-		*setspeed = policy->cur;
-		mutex_unlock(&userspace_mutex);
-		break;
-	case CPUFREQ_GOV_STOP:
-		pr_debug("managing cpu %u stopped\n", cpu);
-
-		mutex_lock(&userspace_mutex);
-		per_cpu(cpu_is_managed, cpu) = 0;
-		*setspeed = 0;
-		mutex_unlock(&userspace_mutex);
-		break;
-	case CPUFREQ_GOV_LIMITS:
-		mutex_lock(&userspace_mutex);
-		pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz, last set to %u kHz\n",
-			cpu, policy->min, policy->max, policy->cur, *setspeed);
-
-		if (policy->max < *setspeed)
-			__cpufreq_driver_target(policy, policy->max,
-						CPUFREQ_RELATION_H);
-		else if (policy->min > *setspeed)
-			__cpufreq_driver_target(policy, policy->min,
-						CPUFREQ_RELATION_L);
-		else
-			__cpufreq_driver_target(policy, *setspeed,
-						CPUFREQ_RELATION_L);
-		mutex_unlock(&userspace_mutex);
-		break;
-	}
-	return rc;
+	mutex_lock(&userspace_mutex);
+	per_cpu(cpu_is_managed, policy->cpu) = 1;
+	*setspeed = policy->cur;
+	mutex_unlock(&userspace_mutex);
+	return 0;
+}
+
+static void cpufreq_userspace_policy_stop(struct cpufreq_policy *policy)
+{
+	unsigned int *setspeed = policy->governor_data;
+
+	pr_debug("managing cpu %u stopped\n", policy->cpu);
+
+	mutex_lock(&userspace_mutex);
+	per_cpu(cpu_is_managed, policy->cpu) = 0;
+	*setspeed = 0;
+	mutex_unlock(&userspace_mutex);
+}
+
+static void cpufreq_userspace_policy_limits(struct cpufreq_policy *policy)
+{
+	unsigned int *setspeed = policy->governor_data;
+
+	mutex_lock(&userspace_mutex);
+
+	pr_debug("limit event for cpu %u: %u - %u kHz, currently %u kHz, last set to %u kHz\n",
+		 policy->cpu, policy->min, policy->max, policy->cur, *setspeed);
+
+	if (policy->max < *setspeed)
+		__cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H);
+	else if (policy->min > *setspeed)
+		__cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L);
+	else
+		__cpufreq_driver_target(policy, *setspeed, CPUFREQ_RELATION_L);
+
+	mutex_unlock(&userspace_mutex);
 }
 
 static struct cpufreq_governor cpufreq_gov_userspace = {
 	.name		= "userspace",
-	.governor	= cpufreq_governor_userspace,
+	.init		= cpufreq_userspace_policy_init,
+	.exit		= cpufreq_userspace_policy_exit,
+	.start		= cpufreq_userspace_policy_start,
+	.stop		= cpufreq_userspace_policy_stop,
+	.limits		= cpufreq_userspace_policy_limits,
 	.store_setspeed	= cpufreq_set,
 	.show_setspeed	= show_speed,
 	.owner		= THIS_MODULE,
diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c
index 7e336d20c184..b95a872800ec 100644
--- a/drivers/cpufreq/davinci-cpufreq.c
+++ b/drivers/cpufreq/davinci-cpufreq.c
@@ -38,26 +38,6 @@ struct davinci_cpufreq {
 };
 static struct davinci_cpufreq cpufreq;
 
-static int davinci_verify_speed(struct cpufreq_policy *policy)
-{
-	struct davinci_cpufreq_config *pdata = cpufreq.dev->platform_data;
-	struct cpufreq_frequency_table *freq_table = pdata->freq_table;
-	struct clk *armclk = cpufreq.armclk;
-
-	if (freq_table)
-		return cpufreq_frequency_table_verify(policy, freq_table);
-
-	if (policy->cpu)
-		return -EINVAL;
-
-	cpufreq_verify_within_cpu_limits(policy);
-	policy->min = clk_round_rate(armclk, policy->min * 1000) / 1000;
-	policy->max = clk_round_rate(armclk, policy->max * 1000) / 1000;
-	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-						policy->cpuinfo.max_freq);
-	return 0;
-}
-
 static int davinci_target(struct cpufreq_policy *policy, unsigned int idx)
 {
 	struct davinci_cpufreq_config *pdata = cpufreq.dev->platform_data;
@@ -121,7 +101,7 @@ static int davinci_cpu_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver davinci_driver = {
 	.flags		= CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
-	.verify		= davinci_verify_speed,
+	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= davinci_target,
 	.get		= cpufreq_generic_get,
 	.init		= davinci_cpu_init,
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index a8f1daffc9bc..3bbbf9e6960c 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -63,8 +63,6 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 	else
 		return 0;
 }
-EXPORT_SYMBOL_GPL(cpufreq_frequency_table_cpuinfo);
-
 
 int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 				   struct cpufreq_frequency_table *table)
@@ -108,20 +106,16 @@ EXPORT_SYMBOL_GPL(cpufreq_frequency_table_verify);
  */
 int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy)
 {
-	struct cpufreq_frequency_table *table =
-		cpufreq_frequency_get_table(policy->cpu);
-	if (!table)
+	if (!policy->freq_table)
 		return -ENODEV;
 
-	return cpufreq_frequency_table_verify(policy, table);
+	return cpufreq_frequency_table_verify(policy, policy->freq_table);
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_frequency_table_verify);
 
-int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
-				   struct cpufreq_frequency_table *table,
-				   unsigned int target_freq,
-				   unsigned int relation,
-				   unsigned int *index)
+int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
+				 unsigned int target_freq,
+				 unsigned int relation)
 {
 	struct cpufreq_frequency_table optimal = {
 		.driver_data = ~0,
@@ -132,7 +126,9 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 		.frequency = 0,
 	};
 	struct cpufreq_frequency_table *pos;
+	struct cpufreq_frequency_table *table = policy->freq_table;
 	unsigned int freq, diff, i = 0;
+	int index;
 
 	pr_debug("request for target %u kHz (relation: %u) for cpu %u\n",
 					target_freq, relation, policy->cpu);
@@ -196,25 +192,26 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 		}
 	}
 	if (optimal.driver_data > i) {
-		if (suboptimal.driver_data > i)
-			return -EINVAL;
-		*index = suboptimal.driver_data;
-	} else
-		*index = optimal.driver_data;
+		if (suboptimal.driver_data > i) {
+			WARN(1, "Invalid frequency table: %d\n", policy->cpu);
+			return 0;
+		}
 
-	pr_debug("target index is %u, freq is:%u kHz\n", *index,
-		 table[*index].frequency);
+		index = suboptimal.driver_data;
+	} else
+		index = optimal.driver_data;
 
-	return 0;
+	pr_debug("target index is %u, freq is:%u kHz\n", index,
+		 table[index].frequency);
+	return index;
 }
-EXPORT_SYMBOL_GPL(cpufreq_frequency_table_target);
+EXPORT_SYMBOL_GPL(cpufreq_table_index_unsorted);
 
 int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy,
 		unsigned int freq)
 {
-	struct cpufreq_frequency_table *pos, *table;
+	struct cpufreq_frequency_table *pos, *table = policy->freq_table;
 
-	table = cpufreq_frequency_get_table(policy->cpu);
 	if (unlikely(!table)) {
 		pr_debug("%s: Unable to find frequency table\n", __func__);
 		return -ENOENT;
@@ -300,15 +297,72 @@ struct freq_attr *cpufreq_generic_attr[] = {
 };
 EXPORT_SYMBOL_GPL(cpufreq_generic_attr);
 
+static int set_freq_table_sorted(struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *pos, *table = policy->freq_table;
+	struct cpufreq_frequency_table *prev = NULL;
+	int ascending = 0;
+
+	policy->freq_table_sorted = CPUFREQ_TABLE_UNSORTED;
+
+	cpufreq_for_each_valid_entry(pos, table) {
+		if (!prev) {
+			prev = pos;
+			continue;
+		}
+
+		if (pos->frequency == prev->frequency) {
+			pr_warn("Duplicate freq-table entries: %u\n",
+				pos->frequency);
+			return -EINVAL;
+		}
+
+		/* Frequency increased from prev to pos */
+		if (pos->frequency > prev->frequency) {
+			/* But frequency was decreasing earlier */
+			if (ascending < 0) {
+				pr_debug("Freq table is unsorted\n");
+				return 0;
+			}
+
+			ascending++;
+		} else {
+			/* Frequency decreased from prev to pos */
+
+			/* But frequency was increasing earlier */
+			if (ascending > 0) {
+				pr_debug("Freq table is unsorted\n");
+				return 0;
+			}
+
+			ascending--;
+		}
+
+		prev = pos;
+	}
+
+	if (ascending > 0)
+		policy->freq_table_sorted = CPUFREQ_TABLE_SORTED_ASCENDING;
+	else
+		policy->freq_table_sorted = CPUFREQ_TABLE_SORTED_DESCENDING;
+
+	pr_debug("Freq table is sorted in %s order\n",
+		 ascending > 0 ? "ascending" : "descending");
+
+	return 0;
+}
+
 int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 				      struct cpufreq_frequency_table *table)
 {
-	int ret = cpufreq_frequency_table_cpuinfo(policy, table);
+	int ret;
 
-	if (!ret)
-		policy->freq_table = table;
+	ret = cpufreq_frequency_table_cpuinfo(policy, table);
+	if (ret)
+		return ret;
 
-	return ret;
+	policy->freq_table = table;
+	return set_freq_table_sorted(policy);
 }
 EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show);
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 28690b284846..9ec033b4f2d9 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -97,7 +97,6 @@ static inline u64 div_ext_fp(u64 x, u64 y)
  *			read from MPERF MSR between last and current sample
  * @tsc:		Difference of time stamp counter between last and
  *			current sample
- * @freq:		Effective frequency calculated from APERF/MPERF
  * @time:		Current time from scheduler
  *
  * This structure is used in the cpudata structure to store performance sample
@@ -109,7 +108,6 @@ struct sample {
 	u64 aperf;
 	u64 mperf;
 	u64 tsc;
-	int freq;
 	u64 time;
 };
 
@@ -282,9 +280,9 @@ struct cpu_defaults {
 static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu);
 static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu);
 
-static struct pstate_adjust_policy pid_params;
-static struct pstate_funcs pstate_funcs;
-static int hwp_active;
+static struct pstate_adjust_policy pid_params __read_mostly;
+static struct pstate_funcs pstate_funcs __read_mostly;
+static int hwp_active __read_mostly;
 
 #ifdef CONFIG_ACPI
 static bool acpi_ppc;
@@ -808,7 +806,8 @@ static void __init intel_pstate_sysfs_expose_params(void)
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
 	/* First disable HWP notification interrupt as we don't process them */
-	wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
+	if (static_cpu_has(X86_FEATURE_HWP_NOTIFY))
+		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
 
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 }
@@ -945,7 +944,7 @@ static int core_get_max_pstate(void)
 			if (err)
 				goto skip_tar;
 
-			tdp_msr = MSR_CONFIG_TDP_NOMINAL + tdp_ctrl;
+			tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x3);
 			err = rdmsrl_safe(tdp_msr, &tdp_ratio);
 			if (err)
 				goto skip_tar;
@@ -973,7 +972,7 @@ static int core_get_turbo_pstate(void)
 	u64 value;
 	int nont, ret;
 
-	rdmsrl(MSR_NHM_TURBO_RATIO_LIMIT, value);
+	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
 	nont = core_get_max_pstate();
 	ret = (value) & 255;
 	if (ret <= nont)
@@ -1002,7 +1001,7 @@ static int knl_get_turbo_pstate(void)
 	u64 value;
 	int nont, ret;
 
-	rdmsrl(MSR_NHM_TURBO_RATIO_LIMIT, value);
+	rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
 	nont = core_get_max_pstate();
 	ret = (((value) >> 8) & 0xFF);
 	if (ret <= nont)
@@ -1092,6 +1091,26 @@ static struct cpu_defaults knl_params = {
 	},
 };
 
+static struct cpu_defaults bxt_params = {
+	.pid_policy = {
+		.sample_rate_ms = 10,
+		.deadband = 0,
+		.setpoint = 60,
+		.p_gain_pct = 14,
+		.d_gain_pct = 0,
+		.i_gain_pct = 4,
+	},
+	.funcs = {
+		.get_max = core_get_max_pstate,
+		.get_max_physical = core_get_max_pstate_physical,
+		.get_min = core_get_min_pstate,
+		.get_turbo = core_get_turbo_pstate,
+		.get_scaling = core_get_scaling,
+		.get_val = core_get_val,
+		.get_target_pstate = get_target_pstate_use_cpu_load,
+	},
+};
+
 static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 {
 	int max_perf = cpu->pstate.turbo_pstate;
@@ -1114,17 +1133,12 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
-static inline void intel_pstate_record_pstate(struct cpudata *cpu, int pstate)
-{
-	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
-	cpu->pstate.current_pstate = pstate;
-}
-
 static void intel_pstate_set_min_pstate(struct cpudata *cpu)
 {
 	int pstate = cpu->pstate.min_pstate;
 
-	intel_pstate_record_pstate(cpu, pstate);
+	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
+	cpu->pstate.current_pstate = pstate;
 	/*
 	 * Generally, there is no guarantee that this code will always run on
 	 * the CPU being updated, so force the register update to run on the
@@ -1284,10 +1298,11 @@ static inline void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
 
 	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
 	pstate = clamp_t(int, pstate, min_perf, max_perf);
+	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 	if (pstate == cpu->pstate.current_pstate)
 		return;
 
-	intel_pstate_record_pstate(cpu, pstate);
+	cpu->pstate.current_pstate = pstate;
 	wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate));
 }
 
@@ -1352,11 +1367,12 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(INTEL_FAM6_SKYLAKE_DESKTOP,	core_params),
 	ICPU(INTEL_FAM6_BROADWELL_XEON_D,	core_params),
 	ICPU(INTEL_FAM6_XEON_PHI_KNL,		knl_params),
+	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		bxt_params),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
 
-static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] = {
+static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
 	ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params),
 	{}
 };
@@ -1576,12 +1592,12 @@ static struct cpufreq_driver intel_pstate_driver = {
 	.name		= "intel_pstate",
 };
 
-static int __initdata no_load;
-static int __initdata no_hwp;
-static int __initdata hwp_only;
-static unsigned int force_load;
+static int no_load __initdata;
+static int no_hwp __initdata;
+static int hwp_only __initdata;
+static unsigned int force_load __initdata;
 
-static int intel_pstate_msrs_not_valid(void)
+static int __init intel_pstate_msrs_not_valid(void)
 {
 	if (!pstate_funcs.get_max() ||
 	    !pstate_funcs.get_min() ||
@@ -1591,7 +1607,7 @@ static int intel_pstate_msrs_not_valid(void)
 	return 0;
 }
 
-static void copy_pid_params(struct pstate_adjust_policy *policy)
+static void __init copy_pid_params(struct pstate_adjust_policy *policy)
 {
 	pid_params.sample_rate_ms = policy->sample_rate_ms;
 	pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
@@ -1602,7 +1618,7 @@ static void copy_pid_params(struct pstate_adjust_policy *policy)
 	pid_params.setpoint = policy->setpoint;
 }
 
-static void copy_cpu_funcs(struct pstate_funcs *funcs)
+static void __init copy_cpu_funcs(struct pstate_funcs *funcs)
 {
 	pstate_funcs.get_max   = funcs->get_max;
 	pstate_funcs.get_max_physical = funcs->get_max_physical;
@@ -1617,7 +1633,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
 
 #ifdef CONFIG_ACPI
 
-static bool intel_pstate_no_acpi_pss(void)
+static bool __init intel_pstate_no_acpi_pss(void)
 {
 	int i;
 
@@ -1646,7 +1662,7 @@ static bool intel_pstate_no_acpi_pss(void)
 	return true;
 }
 
-static bool intel_pstate_has_acpi_ppc(void)
+static bool __init intel_pstate_has_acpi_ppc(void)
 {
 	int i;
 
@@ -1674,7 +1690,7 @@ struct hw_vendor_info {
 };
 
 /* Hardware vendor-specific info that has its own power management modes */
-static struct hw_vendor_info vendor_info[] = {
+static struct hw_vendor_info vendor_info[] __initdata = {
 	{1, "HP    ", "ProLiant", PSS},
 	{1, "ORACLE", "X4-2    ", PPC},
 	{1, "ORACLE", "X4-2L   ", PPC},
@@ -1693,7 +1709,7 @@ static struct hw_vendor_info vendor_info[] = {
 	{0, "", ""},
 };
 
-static bool intel_pstate_platform_pwr_mgmt_exists(void)
+static bool __init intel_pstate_platform_pwr_mgmt_exists(void)
 {
 	struct acpi_table_header hdr;
 	struct hw_vendor_info *v_info;
diff --git a/drivers/cpufreq/mvebu-cpufreq.c b/drivers/cpufreq/mvebu-cpufreq.c
index e920889b9ac2..ed915ee85dd9 100644
--- a/drivers/cpufreq/mvebu-cpufreq.c
+++ b/drivers/cpufreq/mvebu-cpufreq.c
@@ -70,7 +70,7 @@ static int __init armada_xp_pmsu_cpufreq_init(void)
 			continue;
 		}
 
-		clk = clk_get(cpu_dev, 0);
+		clk = clk_get(cpu_dev, NULL);
 		if (IS_ERR(clk)) {
 			pr_err("Cannot get clock for CPU %d\n", cpu);
 			return PTR_ERR(clk);
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index a7ecb9a84c15..3f0ce2ae35ee 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -555,8 +555,6 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->min = policy->cpuinfo.min_freq =
 		ioread32(&pcch_hdr->minimum_frequency) * 1000;
 
-	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
-
 	pr_debug("init: policy->max is %d, policy->min is %d\n",
 		policy->max, policy->min);
 out:
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 6bd715b7f11c..87796e0864e9 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -64,12 +64,14 @@
 /**
  * struct global_pstate_info -	Per policy data structure to maintain history of
  *				global pstates
- * @highest_lpstate:		The local pstate from which we are ramping down
+ * @highest_lpstate_idx:	The local pstate index from which we are
+ *				ramping down
  * @elapsed_time:		Time in ms spent in ramping down from
- *				highest_lpstate
+ *				highest_lpstate_idx
  * @last_sampled_time:		Time from boot in ms when global pstates were
  *				last set
- * @last_lpstate,last_gpstate:	Last set values for local and global pstates
+ * @last_lpstate_idx,		Last set value of local pstate and global
+ * last_gpstate_idx		pstate in terms of cpufreq table index
  * @timer:			Is used for ramping down if cpu goes idle for
  *				a long time with global pstate held high
  * @gpstate_lock:		A spinlock to maintain synchronization between
@@ -77,11 +79,11 @@
  *				governer's target_index calls
  */
 struct global_pstate_info {
-	int highest_lpstate;
+	int highest_lpstate_idx;
 	unsigned int elapsed_time;
 	unsigned int last_sampled_time;
-	int last_lpstate;
-	int last_gpstate;
+	int last_lpstate_idx;
+	int last_gpstate_idx;
 	spinlock_t gpstate_lock;
 	struct timer_list timer;
 };
@@ -124,29 +126,47 @@ static int nr_chips;
 static DEFINE_PER_CPU(struct chip *, chip_info);
 
 /*
- * Note: The set of pstates consists of contiguous integers, the
- * smallest of which is indicated by powernv_pstate_info.min, the
- * largest of which is indicated by powernv_pstate_info.max.
+ * Note:
+ * The set of pstates consists of contiguous integers.
+ * powernv_pstate_info stores the index of the frequency table for
+ * max, min and nominal frequencies. It also stores number of
+ * available frequencies.
  *
- * The nominal pstate is the highest non-turbo pstate in this
- * platform. This is indicated by powernv_pstate_info.nominal.
+ * powernv_pstate_info.nominal indicates the index to the highest
+ * non-turbo frequency.
  */
 static struct powernv_pstate_info {
-	int min;
-	int max;
-	int nominal;
-	int nr_pstates;
+	unsigned int min;
+	unsigned int max;
+	unsigned int nominal;
+	unsigned int nr_pstates;
 } powernv_pstate_info;
 
+/* Use following macros for conversions between pstate_id and index */
+static inline int idx_to_pstate(unsigned int i)
+{
+	return powernv_freqs[i].driver_data;
+}
+
+static inline unsigned int pstate_to_idx(int pstate)
+{
+	/*
+	 * abs() is deliberately used so that is works with
+	 * both monotonically increasing and decreasing
+	 * pstate values
+	 */
+	return abs(pstate - idx_to_pstate(powernv_pstate_info.max));
+}
+
 static inline void reset_gpstates(struct cpufreq_policy *policy)
 {
 	struct global_pstate_info *gpstates = policy->driver_data;
 
-	gpstates->highest_lpstate = 0;
+	gpstates->highest_lpstate_idx = 0;
 	gpstates->elapsed_time = 0;
 	gpstates->last_sampled_time = 0;
-	gpstates->last_lpstate = 0;
-	gpstates->last_gpstate = 0;
+	gpstates->last_lpstate_idx = 0;
+	gpstates->last_gpstate_idx = 0;
 }
 
 /*
@@ -156,9 +176,10 @@ static inline void reset_gpstates(struct cpufreq_policy *policy)
 static int init_powernv_pstates(void)
 {
 	struct device_node *power_mgt;
-	int i, pstate_min, pstate_max, pstate_nominal, nr_pstates = 0;
+	int i, nr_pstates = 0;
 	const __be32 *pstate_ids, *pstate_freqs;
 	u32 len_ids, len_freqs;
+	u32 pstate_min, pstate_max, pstate_nominal;
 
 	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
 	if (!power_mgt) {
@@ -208,6 +229,7 @@ static int init_powernv_pstates(void)
 		return -ENODEV;
 	}
 
+	powernv_pstate_info.nr_pstates = nr_pstates;
 	pr_debug("NR PStates %d\n", nr_pstates);
 	for (i = 0; i < nr_pstates; i++) {
 		u32 id = be32_to_cpu(pstate_ids[i]);
@@ -216,15 +238,17 @@ static int init_powernv_pstates(void)
 		pr_debug("PState id %d freq %d MHz\n", id, freq);
 		powernv_freqs[i].frequency = freq * 1000; /* kHz */
 		powernv_freqs[i].driver_data = id;
+
+		if (id == pstate_max)
+			powernv_pstate_info.max = i;
+		else if (id == pstate_nominal)
+			powernv_pstate_info.nominal = i;
+		else if (id == pstate_min)
+			powernv_pstate_info.min = i;
 	}
+
 	/* End of list marker entry */
 	powernv_freqs[i].frequency = CPUFREQ_TABLE_END;
-
-	powernv_pstate_info.min = pstate_min;
-	powernv_pstate_info.max = pstate_max;
-	powernv_pstate_info.nominal = pstate_nominal;
-	powernv_pstate_info.nr_pstates = nr_pstates;
-
 	return 0;
 }
 
@@ -233,12 +257,12 @@ static unsigned int pstate_id_to_freq(int pstate_id)
 {
 	int i;
 
-	i = powernv_pstate_info.max - pstate_id;
+	i = pstate_to_idx(pstate_id);
 	if (i >= powernv_pstate_info.nr_pstates || i < 0) {
 		pr_warn("PState id %d outside of PState table, "
 			"reporting nominal id %d instead\n",
-			pstate_id, powernv_pstate_info.nominal);
-		i = powernv_pstate_info.max - powernv_pstate_info.nominal;
+			pstate_id, idx_to_pstate(powernv_pstate_info.nominal));
+		i = powernv_pstate_info.nominal;
 	}
 
 	return powernv_freqs[i].frequency;
@@ -252,7 +276,7 @@ static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy,
 					char *buf)
 {
 	return sprintf(buf, "%u\n",
-		pstate_id_to_freq(powernv_pstate_info.nominal));
+		powernv_freqs[powernv_pstate_info.nominal].frequency);
 }
 
 struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq =
@@ -426,7 +450,7 @@ static void set_pstate(void *data)
  */
 static inline unsigned int get_nominal_index(void)
 {
-	return powernv_pstate_info.max - powernv_pstate_info.nominal;
+	return powernv_pstate_info.nominal;
 }
 
 static void powernv_cpufreq_throttle_check(void *data)
@@ -435,20 +459,22 @@ static void powernv_cpufreq_throttle_check(void *data)
 	unsigned int cpu = smp_processor_id();
 	unsigned long pmsr;
 	int pmsr_pmax;
+	unsigned int pmsr_pmax_idx;
 
 	pmsr = get_pmspr(SPRN_PMSR);
 	chip = this_cpu_read(chip_info);
 
 	/* Check for Pmax Capping */
 	pmsr_pmax = (s8)PMSR_MAX(pmsr);
-	if (pmsr_pmax != powernv_pstate_info.max) {
+	pmsr_pmax_idx = pstate_to_idx(pmsr_pmax);
+	if (pmsr_pmax_idx != powernv_pstate_info.max) {
 		if (chip->throttled)
 			goto next;
 		chip->throttled = true;
-		if (pmsr_pmax < powernv_pstate_info.nominal) {
-			pr_warn_once("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
+		if (pmsr_pmax_idx > powernv_pstate_info.nominal) {
+			pr_warn_once("CPU %d on Chip %u has Pmax(%d) reduced below nominal frequency(%d)\n",
 				     cpu, chip->id, pmsr_pmax,
-				     powernv_pstate_info.nominal);
+				     idx_to_pstate(powernv_pstate_info.nominal));
 			chip->throttle_sub_turbo++;
 		} else {
 			chip->throttle_turbo++;
@@ -484,34 +510,35 @@ next:
 
 /**
  * calc_global_pstate - Calculate global pstate
- * @elapsed_time:	Elapsed time in milliseconds
- * @local_pstate:	New local pstate
- * @highest_lpstate:	pstate from which its ramping down
+ * @elapsed_time:		Elapsed time in milliseconds
+ * @local_pstate_idx:		New local pstate
+ * @highest_lpstate_idx:	pstate from which its ramping down
  *
  * Finds the appropriate global pstate based on the pstate from which its
  * ramping down and the time elapsed in ramping down. It follows a quadratic
  * equation which ensures that it reaches ramping down to pmin in 5sec.
  */
 static inline int calc_global_pstate(unsigned int elapsed_time,
-				     int highest_lpstate, int local_pstate)
+				     int highest_lpstate_idx,
+				     int local_pstate_idx)
 {
-	int pstate_diff;
+	int index_diff;
 
 	/*
 	 * Using ramp_down_percent we get the percentage of rampdown
 	 * that we are expecting to be dropping. Difference between
-	 * highest_lpstate and powernv_pstate_info.min will give a absolute
+	 * highest_lpstate_idx and powernv_pstate_info.min will give a absolute
 	 * number of how many pstates we will drop eventually by the end of
 	 * 5 seconds, then just scale it get the number pstates to be dropped.
 	 */
-	pstate_diff =  ((int)ramp_down_percent(elapsed_time) *
-			(highest_lpstate - powernv_pstate_info.min)) / 100;
+	index_diff =  ((int)ramp_down_percent(elapsed_time) *
+			(powernv_pstate_info.min - highest_lpstate_idx)) / 100;
 
 	/* Ensure that global pstate is >= to local pstate */
-	if (highest_lpstate - pstate_diff < local_pstate)
-		return local_pstate;
+	if (highest_lpstate_idx + index_diff >= local_pstate_idx)
+		return local_pstate_idx;
 	else
-		return highest_lpstate - pstate_diff;
+		return highest_lpstate_idx + index_diff;
 }
 
 static inline void  queue_gpstate_timer(struct global_pstate_info *gpstates)
@@ -546,7 +573,7 @@ void gpstate_timer_handler(unsigned long data)
 {
 	struct cpufreq_policy *policy = (struct cpufreq_policy *)data;
 	struct global_pstate_info *gpstates = policy->driver_data;
-	int gpstate_id;
+	int gpstate_idx;
 	unsigned int time_diff = jiffies_to_msecs(jiffies)
 					- gpstates->last_sampled_time;
 	struct powernv_smp_call_data freq_data;
@@ -556,29 +583,29 @@ void gpstate_timer_handler(unsigned long data)
 
 	gpstates->last_sampled_time += time_diff;
 	gpstates->elapsed_time += time_diff;
-	freq_data.pstate_id = gpstates->last_lpstate;
+	freq_data.pstate_id = idx_to_pstate(gpstates->last_lpstate_idx);
 
-	if ((gpstates->last_gpstate == freq_data.pstate_id) ||
+	if ((gpstates->last_gpstate_idx == gpstates->last_lpstate_idx) ||
 	    (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME)) {
-		gpstate_id = freq_data.pstate_id;
+		gpstate_idx = pstate_to_idx(freq_data.pstate_id);
 		reset_gpstates(policy);
-		gpstates->highest_lpstate = freq_data.pstate_id;
+		gpstates->highest_lpstate_idx = gpstate_idx;
 	} else {
-		gpstate_id = calc_global_pstate(gpstates->elapsed_time,
-						gpstates->highest_lpstate,
-						freq_data.pstate_id);
+		gpstate_idx = calc_global_pstate(gpstates->elapsed_time,
+						 gpstates->highest_lpstate_idx,
+						 freq_data.pstate_id);
 	}
 
 	/*
 	 * If local pstate is equal to global pstate, rampdown is over
 	 * So timer is not required to be queued.
 	 */
-	if (gpstate_id != freq_data.pstate_id)
+	if (gpstate_idx != gpstates->last_lpstate_idx)
 		queue_gpstate_timer(gpstates);
 
-	freq_data.gpstate_id = gpstate_id;
-	gpstates->last_gpstate = freq_data.gpstate_id;
-	gpstates->last_lpstate = freq_data.pstate_id;
+	freq_data.gpstate_id = idx_to_pstate(gpstate_idx);
+	gpstates->last_gpstate_idx = pstate_to_idx(freq_data.gpstate_id);
+	gpstates->last_lpstate_idx = pstate_to_idx(freq_data.pstate_id);
 
 	spin_unlock(&gpstates->gpstate_lock);
 
@@ -595,7 +622,7 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 					unsigned int new_index)
 {
 	struct powernv_smp_call_data freq_data;
-	unsigned int cur_msec, gpstate_id;
+	unsigned int cur_msec, gpstate_idx;
 	struct global_pstate_info *gpstates = policy->driver_data;
 
 	if (unlikely(rebooting) && new_index != get_nominal_index())
@@ -607,15 +634,15 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 	cur_msec = jiffies_to_msecs(get_jiffies_64());
 
 	spin_lock(&gpstates->gpstate_lock);
-	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
+	freq_data.pstate_id = idx_to_pstate(new_index);
 
 	if (!gpstates->last_sampled_time) {
-		gpstate_id = freq_data.pstate_id;
-		gpstates->highest_lpstate = freq_data.pstate_id;
+		gpstate_idx = new_index;
+		gpstates->highest_lpstate_idx = new_index;
 		goto gpstates_done;
 	}
 
-	if (gpstates->last_gpstate > freq_data.pstate_id) {
+	if (gpstates->last_gpstate_idx < new_index) {
 		gpstates->elapsed_time += cur_msec -
 						 gpstates->last_sampled_time;
 
@@ -626,34 +653,34 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 		 */
 		if (gpstates->elapsed_time > MAX_RAMP_DOWN_TIME) {
 			reset_gpstates(policy);
-			gpstates->highest_lpstate = freq_data.pstate_id;
-			gpstate_id = freq_data.pstate_id;
+			gpstates->highest_lpstate_idx = new_index;
+			gpstate_idx = new_index;
 		} else {
 		/* Elaspsed_time is less than 5 seconds, continue to rampdown */
-			gpstate_id = calc_global_pstate(gpstates->elapsed_time,
-							gpstates->highest_lpstate,
-							freq_data.pstate_id);
+			gpstate_idx = calc_global_pstate(gpstates->elapsed_time,
+							 gpstates->highest_lpstate_idx,
+							 new_index);
 		}
 	} else {
 		reset_gpstates(policy);
-		gpstates->highest_lpstate = freq_data.pstate_id;
-		gpstate_id = freq_data.pstate_id;
+		gpstates->highest_lpstate_idx = new_index;
+		gpstate_idx = new_index;
 	}
 
 	/*
 	 * If local pstate is equal to global pstate, rampdown is over
 	 * So timer is not required to be queued.
 	 */
-	if (gpstate_id != freq_data.pstate_id)
+	if (gpstate_idx != new_index)
 		queue_gpstate_timer(gpstates);
 	else
 		del_timer_sync(&gpstates->timer);
 
 gpstates_done:
-	freq_data.gpstate_id = gpstate_id;
+	freq_data.gpstate_id = idx_to_pstate(gpstate_idx);
 	gpstates->last_sampled_time = cur_msec;
-	gpstates->last_gpstate = freq_data.gpstate_id;
-	gpstates->last_lpstate = freq_data.pstate_id;
+	gpstates->last_gpstate_idx = gpstate_idx;
+	gpstates->last_lpstate_idx = new_index;
 
 	spin_unlock(&gpstates->gpstate_lock);
 
@@ -759,9 +786,7 @@ void powernv_cpufreq_work_fn(struct work_struct *work)
 		struct cpufreq_policy policy;
 
 		cpufreq_get_policy(&policy, cpu);
-		cpufreq_frequency_table_target(&policy, policy.freq_table,
-					       policy.cur,
-					       CPUFREQ_RELATION_C, &index);
+		index = cpufreq_table_find_index_c(&policy, policy.cur);
 		powernv_cpufreq_target_index(&policy, index);
 		cpumask_andnot(&mask, &mask, policy.cpus);
 	}
@@ -847,8 +872,8 @@ static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 	struct powernv_smp_call_data freq_data;
 	struct global_pstate_info *gpstates = policy->driver_data;
 
-	freq_data.pstate_id = powernv_pstate_info.min;
-	freq_data.gpstate_id = powernv_pstate_info.min;
+	freq_data.pstate_id = idx_to_pstate(powernv_pstate_info.min);
+	freq_data.gpstate_id = idx_to_pstate(powernv_pstate_info.min);
 	smp_call_function_single(policy->cpu, set_pstate, &freq_data, 1);
 	del_timer_sync(&gpstates->timer);
 }
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index 7c4cd5c634f2..dc112481a408 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -94,7 +94,7 @@ static int pmi_notifier(struct notifier_block *nb,
 				       unsigned long event, void *data)
 {
 	struct cpufreq_policy *policy = data;
-	struct cpufreq_frequency_table *cbe_freqs;
+	struct cpufreq_frequency_table *cbe_freqs = policy->freq_table;
 	u8 node;
 
 	/* Should this really be called for CPUFREQ_ADJUST and CPUFREQ_NOTIFY
@@ -103,7 +103,6 @@ static int pmi_notifier(struct notifier_block *nb,
 	if (event == CPUFREQ_START)
 		return 0;
 
-	cbe_freqs = cpufreq_frequency_get_table(policy->cpu);
 	node = cbe_cpu_to_node(policy->cpu);
 
 	pr_debug("got notified, event=%lu, node=%u\n", event, node);
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index ae8eaed77b70..7b596fa38ad2 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -293,12 +293,8 @@ static int s3c_cpufreq_target(struct cpufreq_policy *policy,
 		     __func__, policy, target_freq, relation);
 
 	if (ftab) {
-		if (cpufreq_frequency_table_target(policy, ftab,
-						   target_freq, relation,
-						   &index)) {
-			s3c_freq_dbg("%s: table failed\n", __func__);
-			return -EINVAL;
-		}
+		index = cpufreq_frequency_table_target(policy, target_freq,
+						       relation);
 
 		s3c_freq_dbg("%s: adjust %d to entry %d (%u)\n", __func__,
 			     target_freq, index, ftab[index].frequency);
@@ -315,7 +311,6 @@ static int s3c_cpufreq_target(struct cpufreq_policy *policy,
 		pll = NULL;
 	} else {
 		struct cpufreq_policy tmp_policy;
-		int ret;
 
 		/* we keep the cpu pll table in Hz, to ensure we get an
 		 * accurate value for the PLL output. */
@@ -323,20 +318,14 @@ static int s3c_cpufreq_target(struct cpufreq_policy *policy,
 		tmp_policy.min = policy->min * 1000;
 		tmp_policy.max = policy->max * 1000;
 		tmp_policy.cpu = policy->cpu;
+		tmp_policy.freq_table = pll_reg;
 
-		/* cpufreq_frequency_table_target uses a pointer to 'index'
-		 * which is the number of the table entry, not the value of
+		/* cpufreq_frequency_table_target returns the index
+		 * of the table entry, not the value of
 		 * the table entry's index field. */
 
-		ret = cpufreq_frequency_table_target(&tmp_policy, pll_reg,
-						     target_freq, relation,
-						     &index);
-
-		if (ret < 0) {
-			pr_err("%s: no PLL available\n", __func__);
-			goto err_notpossible;
-		}
-
+		index = cpufreq_frequency_table_target(&tmp_policy, target_freq,
+						       relation);
 		pll = pll_reg + index;
 
 		s3c_freq_dbg("%s: target %u => %u\n",
@@ -346,10 +335,6 @@ static int s3c_cpufreq_target(struct cpufreq_policy *policy,
 	}
 
 	return s3c_cpufreq_settarget(policy, target_freq, pll);
-
- err_notpossible:
-	pr_err("no compatible settings for %d\n", target_freq);
-	return -EINVAL;
 }
 
 struct clk *s3c_cpufreq_clk_get(struct device *dev, const char *name)
@@ -571,11 +556,7 @@ static int s3c_cpufreq_build_freq(void)
 {
 	int size, ret;
 
-	if (!cpu_cur.info->calc_freqtable)
-		return -EINVAL;
-
 	kfree(ftab);
-	ftab = NULL;
 
 	size = cpu_cur.info->calc_freqtable(&cpu_cur, NULL, 0);
 	size++;
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index 06d85917b6d5..9e07588ea9f5 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -246,12 +246,7 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 	new_freq = s5pv210_freq_table[index].frequency;
 
 	/* Finding current running level index */
-	if (cpufreq_frequency_table_target(policy, s5pv210_freq_table,
-					   old_freq, CPUFREQ_RELATION_H,
-					   &priv_index)) {
-		ret = -EINVAL;
-		goto exit;
-	}
+	priv_index = cpufreq_table_find_index_h(policy, old_freq);
 
 	arm_volt = dvs_conf[index].arm_volt;
 	int_volt = dvs_conf[index].int_volt;
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index 78dac0e9da11..a5be56ec57f2 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -75,7 +75,7 @@ config DEVFREQ_GOV_PASSIVE
 comment "DEVFREQ Drivers"
 
 config ARM_EXYNOS_BUS_DEVFREQ
-	bool "ARM EXYNOS Generic Memory Bus DEVFREQ Driver"
+	tristate "ARM EXYNOS Generic Memory Bus DEVFREQ Driver"
 	depends on ARCH_EXYNOS
 	select DEVFREQ_GOV_SIMPLE_ONDEMAND
 	select DEVFREQ_GOV_PASSIVE
diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c
index 39b048eda2ce..9aea2c7ecbe6 100644
--- a/drivers/devfreq/devfreq-event.c
+++ b/drivers/devfreq/devfreq-event.c
@@ -15,7 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/err.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/of.h>
@@ -481,13 +481,3 @@ static int __init devfreq_event_init(void)
 	return 0;
 }
 subsys_initcall(devfreq_event_init);
-
-static void __exit devfreq_event_exit(void)
-{
-	class_destroy(devfreq_event_class);
-}
-module_exit(devfreq_event_exit);
-
-MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>");
-MODULE_DESCRIPTION("DEVFREQ-Event class support");
-MODULE_LICENSE("GPL");
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index e92418facc92..478006b7764a 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -15,7 +15,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/pm_opp.h>
@@ -707,10 +707,12 @@ struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
 		if (devfreq->dev.parent
 			&& devfreq->dev.parent->of_node == node) {
 			mutex_unlock(&devfreq_list_lock);
+			of_node_put(node);
 			return devfreq;
 		}
 	}
 	mutex_unlock(&devfreq_list_lock);
+	of_node_put(node);
 
 	return ERR_PTR(-EPROBE_DEFER);
 }
@@ -1199,13 +1201,6 @@ static int __init devfreq_init(void)
 }
 subsys_initcall(devfreq_init);
 
-static void __exit devfreq_exit(void)
-{
-	class_destroy(devfreq_class);
-	destroy_workqueue(devfreq_wq);
-}
-module_exit(devfreq_exit);
-
 /*
  * The followings are helper functions for devfreq user device drivers with
  * OPP framework.
@@ -1471,7 +1466,3 @@ void devm_devfreq_unregister_notifier(struct device *dev,
 			       devm_devfreq_dev_match, devfreq));
 }
 EXPORT_SYMBOL(devm_devfreq_unregister_notifier);
-
-MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
-MODULE_DESCRIPTION("devfreq class support");
-MODULE_LICENSE("GPL");
diff --git a/drivers/devfreq/event/Kconfig b/drivers/devfreq/event/Kconfig
index 1e8b4f469f38..eb6f74a2b6b9 100644
--- a/drivers/devfreq/event/Kconfig
+++ b/drivers/devfreq/event/Kconfig
@@ -14,7 +14,7 @@ menuconfig PM_DEVFREQ_EVENT
 if PM_DEVFREQ_EVENT
 
 config DEVFREQ_EVENT_EXYNOS_NOCP
-	bool "EXYNOS NoC (Network On Chip) Probe DEVFREQ event Driver"
+	tristate "EXYNOS NoC (Network On Chip) Probe DEVFREQ event Driver"
 	depends on ARCH_EXYNOS
 	select PM_OPP
 	help
@@ -22,7 +22,7 @@ config DEVFREQ_EVENT_EXYNOS_NOCP
 	  (Network on Chip) Probe counters to measure the bandwidth of AXI bus.
 
 config DEVFREQ_EVENT_EXYNOS_PPMU
-	bool "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver"
+	tristate "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver"
 	depends on ARCH_EXYNOS
 	select PM_OPP
 	help
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index f312485f1451..845bf25fb9fb 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -482,7 +482,8 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 	if (!info->edev) {
 		dev_err(&pdev->dev,
 			"failed to allocate memory devfreq-event devices\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err;
 	}
 	edev = info->edev;
 	platform_set_drvdata(pdev, info);
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index 2363d0a189b7..29866f7e6d7e 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -383,7 +383,7 @@ err_clk:
 static int exynos_bus_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct device_node *np = dev->of_node;
+	struct device_node *np = dev->of_node, *node;
 	struct devfreq_dev_profile *profile;
 	struct devfreq_simple_ondemand_data *ondemand_data;
 	struct devfreq_passive_data *passive_data;
@@ -407,7 +407,7 @@ static int exynos_bus_probe(struct platform_device *pdev)
 	/* Parse the device-tree to get the resource information */
 	ret = exynos_bus_parse_of(np, bus);
 	if (ret < 0)
-		goto err;
+		return ret;
 
 	profile = devm_kzalloc(dev, sizeof(*profile), GFP_KERNEL);
 	if (!profile) {
@@ -415,10 +415,13 @@ static int exynos_bus_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	if (of_parse_phandle(dev->of_node, "devfreq", 0))
+	node = of_parse_phandle(dev->of_node, "devfreq", 0);
+	if (node) {
+		of_node_put(node);
 		goto passive;
-	else
+	} else {
 		ret = exynos_bus_parent_parse_of(np, bus);
+	}
 
 	if (ret < 0)
 		goto err;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index 252edba16e36..892d60fb225b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -421,29 +421,6 @@ static int acp_suspend(void *handle)
 
 static int acp_resume(void *handle)
 {
-	int i, ret;
-	struct acp_pm_domain *apd;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	/* return early if no ACP */
-	if (!adev->acp.acp_genpd)
-		return 0;
-
-	/* SMU block will power on ACP irrespective of ACP runtime status.
-	 * Power off explicitly based on genpd ACP runtime status so that ACP
-	 * hw and ACP-genpd status are in sync.
-	 * 'suspend_power_off' represents "Power status before system suspend"
-	*/
-	if (adev->acp.acp_genpd->gpd.suspend_power_off == true) {
-		apd = container_of(&adev->acp.acp_genpd->gpd,
-					struct acp_pm_domain, gpd);
-
-		for (i = 4; i >= 0 ; i--) {
-			ret = acp_suspend_tile(apd->cgs_dev, ACP_TILE_P1 + i);
-			if (ret)
-				pr_err("ACP tile %d tile suspend failed\n", i);
-		}
-	}
 	return 0;
 }
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index b5dd41d13d3d..9b2ef248788d 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -46,8 +46,6 @@
  * to avoid complications with the lapic timer workaround.
  * Have not seen issues with suspend, but may need same workaround here.
  *
- * There is currently no kernel-based automatic probing/loading mechanism
- * if the driver is built as a module.
  */
 
 /* un-comment DEBUG to enable pr_debug() statements */
@@ -60,7 +58,7 @@
 #include <linux/sched.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
 #include <asm/mwait.h>
@@ -828,6 +826,35 @@ static struct cpuidle_state bxt_cstates[] = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state dnv_cstates[] = {
+	{
+		.name = "C1-DNV",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00),
+		.exit_latency = 2,
+		.target_residency = 2,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.name = "C1E-DNV",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01),
+		.exit_latency = 10,
+		.target_residency = 20,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.name = "C6-DNV",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 50,
+		.target_residency = 500,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
+		.enter = NULL }
+};
+
 /**
  * intel_idle
  * @dev: cpuidle_device
@@ -1017,6 +1044,11 @@ static const struct idle_cpu idle_cpu_bxt = {
 	.disable_promotion_to_c1e = true,
 };
 
+static const struct idle_cpu idle_cpu_dnv = {
+	.state_table = dnv_cstates,
+	.disable_promotion_to_c1e = true,
+};
+
 #define ICPU(model, cpu) \
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (unsigned long)&cpu }
 
@@ -1053,9 +1085,9 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	ICPU(INTEL_FAM6_SKYLAKE_X,		idle_cpu_skx),
 	ICPU(INTEL_FAM6_XEON_PHI_KNL,		idle_cpu_knl),
 	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		idle_cpu_bxt),
+	ICPU(INTEL_FAM6_ATOM_DENVERTON,		idle_cpu_dnv),
 	{}
 };
-MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
 
 /*
  * intel_idle_probe()
@@ -1155,7 +1187,10 @@ static unsigned long long irtl_2_usec(unsigned long long irtl)
 {
 	unsigned long long ns;
 
-	ns = irtl_ns_units[(irtl >> 10) & 0x3];
+	if (!irtl)
+		return 0;
+
+	ns = irtl_ns_units[(irtl >> 10) & 0x7];
 
 	return div64_u64((irtl & 0x3FF) * ns, 1000);
 }
@@ -1168,43 +1203,39 @@ static unsigned long long irtl_2_usec(unsigned long long irtl)
 static void bxt_idle_state_table_update(void)
 {
 	unsigned long long msr;
+	unsigned int usec;
 
 	rdmsrl(MSR_PKGC6_IRTL, msr);
-	if (msr) {
-		unsigned int usec = irtl_2_usec(msr);
-
+	usec = irtl_2_usec(msr);
+	if (usec) {
 		bxt_cstates[2].exit_latency = usec;
 		bxt_cstates[2].target_residency = usec;
 	}
 
 	rdmsrl(MSR_PKGC7_IRTL, msr);
-	if (msr) {
-		unsigned int usec = irtl_2_usec(msr);
-
+	usec = irtl_2_usec(msr);
+	if (usec) {
 		bxt_cstates[3].exit_latency = usec;
 		bxt_cstates[3].target_residency = usec;
 	}
 
 	rdmsrl(MSR_PKGC8_IRTL, msr);
-	if (msr) {
-		unsigned int usec = irtl_2_usec(msr);
-
+	usec = irtl_2_usec(msr);
+	if (usec) {
 		bxt_cstates[4].exit_latency = usec;
 		bxt_cstates[4].target_residency = usec;
 	}
 
 	rdmsrl(MSR_PKGC9_IRTL, msr);
-	if (msr) {
-		unsigned int usec = irtl_2_usec(msr);
-
+	usec = irtl_2_usec(msr);
+	if (usec) {
 		bxt_cstates[5].exit_latency = usec;
 		bxt_cstates[5].target_residency = usec;
 	}
 
 	rdmsrl(MSR_PKGC10_IRTL, msr);
-	if (msr) {
-		unsigned int usec = irtl_2_usec(msr);
-
+	usec = irtl_2_usec(msr);
+	if (usec) {
 		bxt_cstates[6].exit_latency = usec;
 		bxt_cstates[6].target_residency = usec;
 	}
@@ -1416,34 +1447,12 @@ static int __init intel_idle_init(void)
 
 	return 0;
 }
+device_initcall(intel_idle_init);
 
-static void __exit intel_idle_exit(void)
-{
-	struct cpuidle_device *dev;
-	int i;
-
-	cpu_notifier_register_begin();
-
-	if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE)
-		on_each_cpu(__setup_broadcast_timer, (void *)false, 1);
-	__unregister_cpu_notifier(&cpu_hotplug_notifier);
-
-	for_each_possible_cpu(i) {
-		dev = per_cpu_ptr(intel_idle_cpuidle_devices, i);
-		cpuidle_unregister_device(dev);
-	}
-
-	cpu_notifier_register_done();
-
-	cpuidle_unregister_driver(&intel_idle_driver);
-	free_percpu(intel_idle_cpuidle_devices);
-}
-
-module_init(intel_idle_init);
-module_exit(intel_idle_exit);
-
+/*
+ * We are not really modular, but we used to support that.  Meaning we also
+ * support "intel_idle.max_cstate=..." at boot and also a read-only export of
+ * it at /sys/module/intel_idle/parameters/max_cstate -- so using module_param
+ * is the easiest way (currently) to continue doing that.
+ */
 module_param(max_cstate, int, 0444);
-
-MODULE_AUTHOR("Len Brown <len.brown@intel.com>");
-MODULE_DESCRIPTION("Cpuidle driver for Intel Hardware v" INTEL_IDLE_VERSION);
-MODULE_LICENSE("GPL");
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index c8b4dbdd1bdd..badbddc683f0 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -530,8 +530,8 @@ static const struct pci_platform_pm_ops *pci_platform_pm;
 
 int pci_set_platform_pm(const struct pci_platform_pm_ops *ops)
 {
-	if (!ops->is_manageable || !ops->set_state || !ops->choose_state
-	    || !ops->sleep_wake)
+	if (!ops->is_manageable || !ops->set_state || !ops->choose_state ||
+	    !ops->sleep_wake || !ops->run_wake || !ops->need_resume)
 		return -EINVAL;
 	pci_platform_pm = ops;
 	return 0;
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index 2e8f2be5b6f9..fbab29dfa793 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -336,14 +336,14 @@ static int release_zone(struct powercap_zone *power_zone)
 
 static int find_nr_power_limit(struct rapl_domain *rd)
 {
-	int i;
+	int i, nr_pl = 0;
 
 	for (i = 0; i < NR_POWER_LIMITS; i++) {
-		if (rd->rpl[i].name == NULL)
-			break;
+		if (rd->rpl[i].name)
+			nr_pl++;
 	}
 
-	return i;
+	return nr_pl;
 }
 
 static int set_domain_enable(struct powercap_zone *power_zone, bool mode)
@@ -426,15 +426,38 @@ static const struct powercap_zone_ops zone_ops[] = {
 	},
 };
 
-static int set_power_limit(struct powercap_zone *power_zone, int id,
+
+/*
+ * Constraint index used by powercap can be different than power limit (PL)
+ * index in that some  PLs maybe missing due to non-existant MSRs. So we
+ * need to convert here by finding the valid PLs only (name populated).
+ */
+static int contraint_to_pl(struct rapl_domain *rd, int cid)
+{
+	int i, j;
+
+	for (i = 0, j = 0; i < NR_POWER_LIMITS; i++) {
+		if ((rd->rpl[i].name) && j++ == cid) {
+			pr_debug("%s: index %d\n", __func__, i);
+			return i;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int set_power_limit(struct powercap_zone *power_zone, int cid,
 			u64 power_limit)
 {
 	struct rapl_domain *rd;
 	struct rapl_package *rp;
 	int ret = 0;
+	int id;
 
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
+	id = contraint_to_pl(rd, cid);
+
 	rp = rd->rp;
 
 	if (rd->state & DOMAIN_STATE_BIOS_LOCKED) {
@@ -461,16 +484,18 @@ set_exit:
 	return ret;
 }
 
-static int get_current_power_limit(struct powercap_zone *power_zone, int id,
+static int get_current_power_limit(struct powercap_zone *power_zone, int cid,
 					u64 *data)
 {
 	struct rapl_domain *rd;
 	u64 val;
 	int prim;
 	int ret = 0;
+	int id;
 
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
+	id = contraint_to_pl(rd, cid);
 	switch (rd->rpl[id].prim_id) {
 	case PL1_ENABLE:
 		prim = POWER_LIMIT1;
@@ -492,14 +517,17 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int id,
 	return ret;
 }
 
-static int set_time_window(struct powercap_zone *power_zone, int id,
+static int set_time_window(struct powercap_zone *power_zone, int cid,
 								u64 window)
 {
 	struct rapl_domain *rd;
 	int ret = 0;
+	int id;
 
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
+	id = contraint_to_pl(rd, cid);
+
 	switch (rd->rpl[id].prim_id) {
 	case PL1_ENABLE:
 		rapl_write_data_raw(rd, TIME_WINDOW1, window);
@@ -514,14 +542,17 @@ static int set_time_window(struct powercap_zone *power_zone, int id,
 	return ret;
 }
 
-static int get_time_window(struct powercap_zone *power_zone, int id, u64 *data)
+static int get_time_window(struct powercap_zone *power_zone, int cid, u64 *data)
 {
 	struct rapl_domain *rd;
 	u64 val;
 	int ret = 0;
+	int id;
 
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
+	id = contraint_to_pl(rd, cid);
+
 	switch (rd->rpl[id].prim_id) {
 	case PL1_ENABLE:
 		ret = rapl_read_data_raw(rd, TIME_WINDOW1, true, &val);
@@ -540,15 +571,17 @@ static int get_time_window(struct powercap_zone *power_zone, int id, u64 *data)
 	return ret;
 }
 
-static const char *get_constraint_name(struct powercap_zone *power_zone, int id)
+static const char *get_constraint_name(struct powercap_zone *power_zone, int cid)
 {
-	struct rapl_power_limit *rpl;
 	struct rapl_domain *rd;
+	int id;
 
 	rd = power_zone_to_rapl_domain(power_zone);
-	rpl = (struct rapl_power_limit *) &rd->rpl[id];
+	id = contraint_to_pl(rd, cid);
+	if (id >= 0)
+		return rd->rpl[id].name;
 
-	return rpl->name;
+	return NULL;
 }
 
 
@@ -1101,6 +1134,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	RAPL_CPU(INTEL_FAM6_SANDYBRIDGE_X,	rapl_defaults_core),
 
 	RAPL_CPU(INTEL_FAM6_IVYBRIDGE,		rapl_defaults_core),
+	RAPL_CPU(INTEL_FAM6_IVYBRIDGE_X,	rapl_defaults_core),
 
 	RAPL_CPU(INTEL_FAM6_HASWELL_CORE,	rapl_defaults_core),
 	RAPL_CPU(INTEL_FAM6_HASWELL_ULT,	rapl_defaults_core),
@@ -1123,6 +1157,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	RAPL_CPU(INTEL_FAM6_ATOM_MERRIFIELD1,	rapl_defaults_tng),
 	RAPL_CPU(INTEL_FAM6_ATOM_MERRIFIELD2,	rapl_defaults_ann),
 	RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT,	rapl_defaults_core),
+	RAPL_CPU(INTEL_FAM6_ATOM_DENVERTON,	rapl_defaults_core),
 
 	RAPL_CPU(INTEL_FAM6_XEON_PHI_KNL,	rapl_defaults_hsw_server),
 	{}
@@ -1381,6 +1416,37 @@ static int rapl_check_domain(int cpu, int domain)
 	return 0;
 }
 
+
+/*
+ * Check if power limits are available. Two cases when they are not available:
+ * 1. Locked by BIOS, in this case we still provide read-only access so that
+ *    users can see what limit is set by the BIOS.
+ * 2. Some CPUs make some domains monitoring only which means PLx MSRs may not
+ *    exist at all. In this case, we do not show the contraints in powercap.
+ *
+ * Called after domains are detected and initialized.
+ */
+static void rapl_detect_powerlimit(struct rapl_domain *rd)
+{
+	u64 val64;
+	int i;
+
+	/* check if the domain is locked by BIOS, ignore if MSR doesn't exist */
+	if (!rapl_read_data_raw(rd, FW_LOCK, false, &val64)) {
+		if (val64) {
+			pr_info("RAPL package %d domain %s locked by BIOS\n",
+				rd->rp->id, rd->name);
+			rd->state |= DOMAIN_STATE_BIOS_LOCKED;
+		}
+	}
+	/* check if power limit MSRs exists, otherwise domain is monitoring only */
+	for (i = 0; i < NR_POWER_LIMITS; i++) {
+		int prim = rd->rpl[i].prim_id;
+		if (rapl_read_data_raw(rd, prim, false, &val64))
+			rd->rpl[i].name = NULL;
+	}
+}
+
 /* Detect active and valid domains for the given CPU, caller must
  * ensure the CPU belongs to the targeted package and CPU hotlug is disabled.
  */
@@ -1389,7 +1455,6 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu)
 	int i;
 	int ret = 0;
 	struct rapl_domain *rd;
-	u64 locked;
 
 	for (i = 0; i < RAPL_DOMAIN_MAX; i++) {
 		/* use physical package id to read counters */
@@ -1400,7 +1465,7 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu)
 	}
 	rp->nr_domains = bitmap_weight(&rp->domain_map,	RAPL_DOMAIN_MAX);
 	if (!rp->nr_domains) {
-		pr_err("no valid rapl domains found in package %d\n", rp->id);
+		pr_debug("no valid rapl domains found in package %d\n", rp->id);
 		ret = -ENODEV;
 		goto done;
 	}
@@ -1414,17 +1479,9 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu)
 	}
 	rapl_init_domains(rp);
 
-	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
-		/* check if the domain is locked by BIOS */
-		ret = rapl_read_data_raw(rd, FW_LOCK, false, &locked);
-		if (ret)
-			return ret;
-		if (locked) {
-			pr_info("RAPL package %d domain %s locked by BIOS\n",
-				rp->id, rd->name);
-			rd->state |= DOMAIN_STATE_BIOS_LOCKED;
-		}
-	}
+	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++)
+		rapl_detect_powerlimit(rd);
+
 
 
 done:
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 5b4b47ed948b..3788ed74c9ab 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -787,22 +787,34 @@ __cpufreq_cooling_register(struct device_node *np,
 			const struct cpumask *clip_cpus, u32 capacitance,
 			get_static_t plat_static_func)
 {
+	struct cpufreq_policy *policy;
 	struct thermal_cooling_device *cool_dev;
 	struct cpufreq_cooling_device *cpufreq_dev;
 	char dev_name[THERMAL_NAME_LENGTH];
 	struct cpufreq_frequency_table *pos, *table;
+	struct cpumask temp_mask;
 	unsigned int freq, i, num_cpus;
 	int ret;
 
-	table = cpufreq_frequency_get_table(cpumask_first(clip_cpus));
+	cpumask_and(&temp_mask, clip_cpus, cpu_online_mask);
+	policy = cpufreq_cpu_get(cpumask_first(&temp_mask));
+	if (!policy) {
+		pr_debug("%s: CPUFreq policy not found\n", __func__);
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	table = policy->freq_table;
 	if (!table) {
 		pr_debug("%s: CPUFreq table not found\n", __func__);
-		return ERR_PTR(-EPROBE_DEFER);
+		cool_dev = ERR_PTR(-ENODEV);
+		goto put_policy;
 	}
 
 	cpufreq_dev = kzalloc(sizeof(*cpufreq_dev), GFP_KERNEL);
-	if (!cpufreq_dev)
-		return ERR_PTR(-ENOMEM);
+	if (!cpufreq_dev) {
+		cool_dev = ERR_PTR(-ENOMEM);
+		goto put_policy;
+	}
 
 	num_cpus = cpumask_weight(clip_cpus);
 	cpufreq_dev->time_in_idle = kcalloc(num_cpus,
@@ -892,7 +904,7 @@ __cpufreq_cooling_register(struct device_node *np,
 					  CPUFREQ_POLICY_NOTIFIER);
 	mutex_unlock(&cooling_cpufreq_lock);
 
-	return cool_dev;
+	goto put_policy;
 
 remove_idr:
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
@@ -906,6 +918,8 @@ free_time_in_idle:
 	kfree(cpufreq_dev->time_in_idle);
 free_cdev:
 	kfree(cpufreq_dev);
+put_policy:
+	cpufreq_cpu_put(policy);
 
 	return cool_dev;
 }