Merge tag 'pm-5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These include a rework of the main suspend-to-idle code flow (related
  to the handling of spurious wakeups), a switch over of several users
  of cpufreq notifiers to QoS-based limits, a new devfreq driver for
  Tegra20, a new cpuidle driver and governor for virtualized guests, an
  extension of the wakeup sources framework to expose wakeup sources as
  device objects in sysfs, and more.

  Specifics:

   - Rework the main suspend-to-idle control flow to avoid repeating
     "noirq" device resume and suspend operations in case of spurious
     wakeups from the ACPI EC and decouple the ACPI EC wakeups support
     from the LPS0 _DSM support (Rafael Wysocki).

   - Extend the wakeup sources framework to expose wakeup sources as
     device objects in sysfs (Tri Vo, Stephen Boyd).

   - Expose system suspend statistics in sysfs (Kalesh Singh).

   - Introduce a new haltpoll cpuidle driver and a new matching governor
     for virtualized guests wanting to do guest-side polling in the idle
     loop (Marcelo Tosatti, Joao Martins, Wanpeng Li, Stephen Rothwell).

   - Fix the menu and teo cpuidle governors to allow the scheduler tick
     to be stopped if PM QoS is used to limit the CPU idle state exit
     latency in some cases (Rafael Wysocki).

   - Increase the resolution of the play_idle() argument to microseconds
     for more fine-grained injection of CPU idle cycles (Daniel
     Lezcano).

   - Switch over some users of cpuidle notifiers to the new QoS-based
     frequency limits and drop the CPUFREQ_ADJUST and CPUFREQ_NOTIFY
     policy notifier events (Viresh Kumar).

   - Add new cpufreq driver based on nvmem for sun50i (Yangtao Li).

   - Add support for MT8183 and MT8516 to the mediatek cpufreq driver
     (Andrew-sh.Cheng, Fabien Parent).

   - Add i.MX8MN support to the imx-cpufreq-dt cpufreq driver (Anson
     Huang).

   - Add qcs404 to cpufreq-dt-platdev blacklist (Jorge Ramirez-Ortiz).

   - Update the qcom cpufreq driver (among other things, to make it
     easier to extend and to use kryo cpufreq for other nvmem-based
     SoCs) and add qcs404 support to it (Niklas Cassel, Douglas
     RAILLARD, Sibi Sankar, Sricharan R).

   - Fix assorted issues and make assorted minor improvements in the
     cpufreq code (Colin Ian King, Douglas RAILLARD, Florian Fainelli,
     Gustavo Silva, Hariprasad Kelam).

   - Add new devfreq driver for NVidia Tegra20 (Dmitry Osipenko, Arnd
     Bergmann).

   - Add new Exynos PPMU events to devfreq events and extend that
     mechanism (Lukasz Luba).

   - Fix and clean up the exynos-bus devfreq driver (Kamil Konieczny).

   - Improve devfreq documentation and governor code, fix spelling typos
     in devfreq (Ezequiel Garcia, Krzysztof Kozlowski, Leonard Crestez,
     MyungJoo Ham, Gaël PORTAY).

   - Add regulators enable and disable to the OPP (operating performance
     points) framework (Kamil Konieczny).

   - Update the OPP framework to support multiple opp-suspend properties
     (Anson Huang).

   - Fix assorted issues and make assorted minor improvements in the OPP
     code (Niklas Cassel, Viresh Kumar, Yue Hu).

   - Clean up the generic power domains (genpd) framework (Ulf Hansson).

   - Clean up assorted pieces of power management code and documentation
     (Akinobu Mita, Amit Kucheria, Chuhong Yuan).

   - Update the pm-graph tool to version 5.5 including multiple fixes
     and improvements (Todd Brandt).

   - Update the cpupower utility (Benjamin Weis, Geert Uytterhoeven,
     Sébastien Szymanski)"

* tag 'pm-5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (126 commits)
  cpuidle-haltpoll: Enable kvm guest polling when dedicated physical CPUs are available
  cpuidle-haltpoll: do not set an owner to allow modunload
  cpuidle-haltpoll: return -ENODEV on modinit failure
  cpuidle-haltpoll: set haltpoll as preferred governor
  cpuidle: allow governor switch on cpuidle_register_driver()
  PM: runtime: Documentation: add runtime_status ABI document
  pm-graph: make setVal unbuffered again for python2 and python3
  powercap: idle_inject: Use higher resolution for idle injection
  cpuidle: play_idle: Increase the resolution to usec
  cpuidle-haltpoll: vcpu hotplug support
  cpufreq: Add qcs404 to cpufreq-dt-platdev blacklist
  cpufreq: qcom: Add support for qcs404 on nvmem driver
  cpufreq: qcom: Refactor the driver to make it easier to extend
  cpufreq: qcom: Re-organise kryo cpufreq to use it for other nvmem based qcom socs
  dt-bindings: opp: Add qcom-opp bindings with properties needed for CPR
  dt-bindings: opp: qcom-nvmem: Support pstates provided by a power domain
  Documentation: cpufreq: Update policy notifier documentation
  cpufreq: Remove CPUFREQ_ADJUST and CPUFREQ_NOTIFY policy notifier events
  PM / Domains: Verify PM domain type in dev_pm_genpd_set_performance_state()
  PM / Domains: Simplify genpd_lookup_dev()
  ...

67 files changed, 2548 insertions, 1259 deletions

diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index 710488ec59e9..04a40d563dd6 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -644,17 +644,17 @@ ACPI_EXPORT_SYMBOL(acpi_get_gpe_status)
  * PARAMETERS:  gpe_device          - Parent GPE Device. NULL for GPE0/GPE1
  *              gpe_number          - GPE level within the GPE block
  *
- * RETURN:      None
+ * RETURN:      INTERRUPT_HANDLED or INTERRUPT_NOT_HANDLED
  *
  * DESCRIPTION: Detect and dispatch a General Purpose Event to either a function
  *              (e.g. EC) or method (e.g. _Lxx/_Exx) handler.
  *
  ******************************************************************************/
-void acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number)
+u32 acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number)
 {
 	ACPI_FUNCTION_TRACE(acpi_dispatch_gpe);
 
-	acpi_ev_detect_gpe(gpe_device, NULL, gpe_number);
+	return acpi_ev_detect_gpe(gpe_device, NULL, gpe_number);
 }
 
 ACPI_EXPORT_SYMBOL(acpi_dispatch_gpe)
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index f616b16c1f0b..08bb9f2f2d23 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -166,6 +166,10 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 	    || (state < ACPI_STATE_D0) || (state > ACPI_STATE_D3_COLD))
 		return -EINVAL;
 
+	acpi_handle_debug(device->handle, "Power state change: %s -> %s\n",
+			  acpi_power_state_string(device->power.state),
+			  acpi_power_state_string(state));
+
 	/* Make sure this is a valid target state */
 
 	/* There is a special case for D0 addressed below. */
@@ -497,7 +501,8 @@ acpi_status acpi_add_pm_notifier(struct acpi_device *adev, struct device *dev,
 		goto out;
 
 	mutex_lock(&acpi_pm_notifier_lock);
-	adev->wakeup.ws = wakeup_source_register(dev_name(&adev->dev));
+	adev->wakeup.ws = wakeup_source_register(&adev->dev,
+						 dev_name(&adev->dev));
 	adev->wakeup.context.dev = dev;
 	adev->wakeup.context.func = func;
 	adev->wakeup.flags.notifier_present = true;
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index c33756ed3304..da1e5c5ce150 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -25,6 +25,7 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
+#include <linux/suspend.h>
 #include <linux/acpi.h>
 #include <linux/dmi.h>
 #include <asm/io.h>
@@ -1048,24 +1049,6 @@ void acpi_ec_unblock_transactions(void)
 		acpi_ec_start(first_ec, true);
 }
 
-void acpi_ec_mark_gpe_for_wake(void)
-{
-	if (first_ec && !ec_no_wakeup)
-		acpi_mark_gpe_for_wake(NULL, first_ec->gpe);
-}
-
-void acpi_ec_set_gpe_wake_mask(u8 action)
-{
-	if (first_ec && !ec_no_wakeup)
-		acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action);
-}
-
-void acpi_ec_dispatch_gpe(void)
-{
-	if (first_ec)
-		acpi_dispatch_gpe(NULL, first_ec->gpe);
-}
-
 /* --------------------------------------------------------------------------
                                 Event Management
    -------------------------------------------------------------------------- */
@@ -1931,7 +1914,7 @@ static int acpi_ec_suspend(struct device *dev)
 	struct acpi_ec *ec =
 		acpi_driver_data(to_acpi_device(dev));
 
-	if (acpi_sleep_no_ec_events() && ec_freeze_events)
+	if (!pm_suspend_no_platform() && ec_freeze_events)
 		acpi_ec_disable_event(ec);
 	return 0;
 }
@@ -1948,8 +1931,7 @@ static int acpi_ec_suspend_noirq(struct device *dev)
 	    ec->reference_count >= 1)
 		acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE);
 
-	if (acpi_sleep_no_ec_events())
-		acpi_ec_enter_noirq(ec);
+	acpi_ec_enter_noirq(ec);
 
 	return 0;
 }
@@ -1958,8 +1940,7 @@ static int acpi_ec_resume_noirq(struct device *dev)
 {
 	struct acpi_ec *ec = acpi_driver_data(to_acpi_device(dev));
 
-	if (acpi_sleep_no_ec_events())
-		acpi_ec_leave_noirq(ec);
+	acpi_ec_leave_noirq(ec);
 
 	if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) &&
 	    ec->reference_count >= 1)
@@ -1976,7 +1957,35 @@ static int acpi_ec_resume(struct device *dev)
 	acpi_ec_enable_event(ec);
 	return 0;
 }
-#endif
+
+void acpi_ec_mark_gpe_for_wake(void)
+{
+	if (first_ec && !ec_no_wakeup)
+		acpi_mark_gpe_for_wake(NULL, first_ec->gpe);
+}
+EXPORT_SYMBOL_GPL(acpi_ec_mark_gpe_for_wake);
+
+void acpi_ec_set_gpe_wake_mask(u8 action)
+{
+	if (pm_suspend_no_platform() && first_ec && !ec_no_wakeup)
+		acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action);
+}
+
+bool acpi_ec_dispatch_gpe(void)
+{
+	u32 ret;
+
+	if (!first_ec)
+		return false;
+
+	ret = acpi_dispatch_gpe(NULL, first_ec->gpe);
+	if (ret == ACPI_INTERRUPT_HANDLED) {
+		pm_pr_dbg("EC GPE dispatched\n");
+		return true;
+	}
+	return false;
+}
+#endif /* CONFIG_PM_SLEEP */
 
 static const struct dev_pm_ops acpi_ec_pm = {
 	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend_noirq, acpi_ec_resume_noirq)
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index f4c2fe6be4f2..afe6636f9ad3 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -194,9 +194,6 @@ void acpi_ec_ecdt_probe(void);
 void acpi_ec_dsdt_probe(void);
 void acpi_ec_block_transactions(void);
 void acpi_ec_unblock_transactions(void);
-void acpi_ec_mark_gpe_for_wake(void);
-void acpi_ec_set_gpe_wake_mask(u8 action);
-void acpi_ec_dispatch_gpe(void);
 int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
 			      acpi_handle handle, acpi_ec_query_func func,
 			      void *data);
@@ -204,6 +201,7 @@ void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit);
 
 #ifdef CONFIG_PM_SLEEP
 void acpi_ec_flush_work(void);
+bool acpi_ec_dispatch_gpe(void);
 #endif
 
 
@@ -212,11 +210,9 @@ void acpi_ec_flush_work(void);
   -------------------------------------------------------------------------- */
 #ifdef CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT
 extern bool acpi_s2idle_wakeup(void);
-extern bool acpi_sleep_no_ec_events(void);
 extern int acpi_sleep_init(void);
 #else
 static inline bool acpi_s2idle_wakeup(void) { return false; }
-static inline bool acpi_sleep_no_ec_events(void) { return true; }
 static inline int acpi_sleep_init(void) { return -ENXIO; }
 #endif
 
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index aea8d674a33d..08da9c29f1e9 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -284,6 +284,29 @@ static int acpi_processor_stop(struct device *dev)
 	return 0;
 }
 
+bool acpi_processor_cpufreq_init;
+
+static int acpi_processor_notifier(struct notifier_block *nb,
+				   unsigned long event, void *data)
+{
+	struct cpufreq_policy *policy = data;
+	int cpu = policy->cpu;
+
+	if (event == CPUFREQ_CREATE_POLICY) {
+		acpi_thermal_cpufreq_init(cpu);
+		acpi_processor_ppc_init(cpu);
+	} else if (event == CPUFREQ_REMOVE_POLICY) {
+		acpi_processor_ppc_exit(cpu);
+		acpi_thermal_cpufreq_exit(cpu);
+	}
+
+	return 0;
+}
+
+static struct notifier_block acpi_processor_notifier_block = {
+	.notifier_call = acpi_processor_notifier,
+};
+
 /*
  * We keep the driver loaded even when ACPI is not running.
  * This is needed for the powernow-k8 driver, that works even without
@@ -310,8 +333,12 @@ static int __init acpi_processor_driver_init(void)
 	cpuhp_setup_state_nocalls(CPUHP_ACPI_CPUDRV_DEAD, "acpi/cpu-drv:dead",
 				  NULL, acpi_soft_cpu_dead);
 
-	acpi_thermal_cpufreq_init();
-	acpi_processor_ppc_init();
+	if (!cpufreq_register_notifier(&acpi_processor_notifier_block,
+				       CPUFREQ_POLICY_NOTIFIER)) {
+		acpi_processor_cpufreq_init = true;
+		acpi_processor_ignore_ppc_init();
+	}
+
 	acpi_processor_throttling_init();
 	return 0;
 err:
@@ -324,8 +351,12 @@ static void __exit acpi_processor_driver_exit(void)
 	if (acpi_disabled)
 		return;
 
-	acpi_processor_ppc_exit();
-	acpi_thermal_cpufreq_exit();
+	if (acpi_processor_cpufreq_init) {
+		cpufreq_unregister_notifier(&acpi_processor_notifier_block,
+					    CPUFREQ_POLICY_NOTIFIER);
+		acpi_processor_cpufreq_init = false;
+	}
+
 	cpuhp_remove_state_nocalls(hp_online);
 	cpuhp_remove_state_nocalls(CPUHP_ACPI_CPUDRV_DEAD);
 	driver_unregister(&acpi_processor_driver);
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index ee87cb6f6e59..2261713d1aec 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -50,57 +50,13 @@ module_param(ignore_ppc, int, 0644);
 MODULE_PARM_DESC(ignore_ppc, "If the frequency of your machine gets wrongly" \
 		 "limited by BIOS, this should help");
 
-#define PPC_REGISTERED   1
-#define PPC_IN_USE       2
-
-static int acpi_processor_ppc_status;
-
-static int acpi_processor_ppc_notifier(struct notifier_block *nb,
-				       unsigned long event, void *data)
-{
-	struct cpufreq_policy *policy = data;
-	struct acpi_processor *pr;
-	unsigned int ppc = 0;
-
-	if (ignore_ppc < 0)
-		ignore_ppc = 0;
-
-	if (ignore_ppc)
-		return 0;
-
-	if (event != CPUFREQ_ADJUST)
-		return 0;
-
-	mutex_lock(&performance_mutex);
-
-	pr = per_cpu(processors, policy->cpu);
-	if (!pr || !pr->performance)
-		goto out;
-
-	ppc = (unsigned int)pr->performance_platform_limit;
-
-	if (ppc >= pr->performance->state_count)
-		goto out;
-
-	cpufreq_verify_within_limits(policy, 0,
-				     pr->performance->states[ppc].
-				     core_frequency * 1000);
-
-      out:
-	mutex_unlock(&performance_mutex);
-
-	return 0;
-}
-
-static struct notifier_block acpi_ppc_notifier_block = {
-	.notifier_call = acpi_processor_ppc_notifier,
-};
+static bool acpi_processor_ppc_in_use;
 
 static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 {
 	acpi_status status = 0;
 	unsigned long long ppc = 0;
-
+	int ret;
 
 	if (!pr)
 		return -EINVAL;
@@ -112,7 +68,7 @@ static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 	status = acpi_evaluate_integer(pr->handle, "_PPC", NULL, &ppc);
 
 	if (status != AE_NOT_FOUND)
-		acpi_processor_ppc_status |= PPC_IN_USE;
+		acpi_processor_ppc_in_use = true;
 
 	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
 		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PPC"));
@@ -124,6 +80,17 @@ static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 
 	pr->performance_platform_limit = (int)ppc;
 
+	if (ppc >= pr->performance->state_count ||
+	    unlikely(!dev_pm_qos_request_active(&pr->perflib_req)))
+		return 0;
+
+	ret = dev_pm_qos_update_request(&pr->perflib_req,
+			pr->performance->states[ppc].core_frequency * 1000);
+	if (ret < 0) {
+		pr_warn("Failed to update perflib freq constraint: CPU%d (%d)\n",
+			pr->id, ret);
+	}
+
 	return 0;
 }
 
@@ -184,23 +151,32 @@ int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
 }
 EXPORT_SYMBOL(acpi_processor_get_bios_limit);
 
-void acpi_processor_ppc_init(void)
+void acpi_processor_ignore_ppc_init(void)
 {
-	if (!cpufreq_register_notifier
-	    (&acpi_ppc_notifier_block, CPUFREQ_POLICY_NOTIFIER))
-		acpi_processor_ppc_status |= PPC_REGISTERED;
-	else
-		printk(KERN_DEBUG
-		       "Warning: Processor Platform Limit not supported.\n");
+	if (ignore_ppc < 0)
+		ignore_ppc = 0;
+}
+
+void acpi_processor_ppc_init(int cpu)
+{
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+	int ret;
+
+	ret = dev_pm_qos_add_request(get_cpu_device(cpu),
+				     &pr->perflib_req, DEV_PM_QOS_MAX_FREQUENCY,
+				     INT_MAX);
+	if (ret < 0) {
+		pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu,
+		       ret);
+		return;
+	}
 }
 
-void acpi_processor_ppc_exit(void)
+void acpi_processor_ppc_exit(int cpu)
 {
-	if (acpi_processor_ppc_status & PPC_REGISTERED)
-		cpufreq_unregister_notifier(&acpi_ppc_notifier_block,
-					    CPUFREQ_POLICY_NOTIFIER);
+	struct acpi_processor *pr = per_cpu(processors, cpu);
 
-	acpi_processor_ppc_status &= ~PPC_REGISTERED;
+	dev_pm_qos_remove_request(&pr->perflib_req);
 }
 
 static int acpi_processor_get_performance_control(struct acpi_processor *pr)
@@ -477,7 +453,7 @@ int acpi_processor_notify_smm(struct module *calling_module)
 	static int is_done = 0;
 	int result;
 
-	if (!(acpi_processor_ppc_status & PPC_REGISTERED))
+	if (!acpi_processor_cpufreq_init)
 		return -EBUSY;
 
 	if (!try_module_get(calling_module))
@@ -513,7 +489,7 @@ int acpi_processor_notify_smm(struct module *calling_module)
 	 * we can allow the cpufreq driver to be rmmod'ed. */
 	is_done = 1;
 
-	if (!(acpi_processor_ppc_status & PPC_IN_USE))
+	if (!acpi_processor_ppc_in_use)
 		module_put(calling_module);
 
 	return 0;
@@ -742,7 +718,7 @@ acpi_processor_register_performance(struct acpi_processor_performance
 {
 	struct acpi_processor *pr;
 
-	if (!(acpi_processor_ppc_status & PPC_REGISTERED))
+	if (!acpi_processor_cpufreq_init)
 		return -EINVAL;
 
 	mutex_lock(&performance_mutex);
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index 50fb0107375e..ec2638f1df4f 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -35,7 +35,6 @@ ACPI_MODULE_NAME("processor_thermal");
 #define CPUFREQ_THERMAL_MAX_STEP 3
 
 static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
-static unsigned int acpi_thermal_cpufreq_is_init = 0;
 
 #define reduction_pctg(cpu) \
 	per_cpu(cpufreq_thermal_reduction_pctg, phys_package_first_cpu(cpu))
@@ -61,35 +60,11 @@ static int phys_package_first_cpu(int cpu)
 static int cpu_has_cpufreq(unsigned int cpu)
 {
 	struct cpufreq_policy policy;
-	if (!acpi_thermal_cpufreq_is_init || cpufreq_get_policy(&policy, cpu))
+	if (!acpi_processor_cpufreq_init || cpufreq_get_policy(&policy, cpu))
 		return 0;
 	return 1;
 }
 
-static int acpi_thermal_cpufreq_notifier(struct notifier_block *nb,
-					 unsigned long event, void *data)
-{
-	struct cpufreq_policy *policy = data;
-	unsigned long max_freq = 0;
-
-	if (event != CPUFREQ_ADJUST)
-		goto out;
-
-	max_freq = (
-	    policy->cpuinfo.max_freq *
-	    (100 - reduction_pctg(policy->cpu) * 20)
-	) / 100;
-
-	cpufreq_verify_within_limits(policy, 0, max_freq);
-
-      out:
-	return 0;
-}
-
-static struct notifier_block acpi_thermal_cpufreq_notifier_block = {
-	.notifier_call = acpi_thermal_cpufreq_notifier,
-};
-
 static int cpufreq_get_max_state(unsigned int cpu)
 {
 	if (!cpu_has_cpufreq(cpu))
@@ -108,7 +83,10 @@ static int cpufreq_get_cur_state(unsigned int cpu)
 
 static int cpufreq_set_cur_state(unsigned int cpu, int state)
 {
-	int i;
+	struct cpufreq_policy *policy;
+	struct acpi_processor *pr;
+	unsigned long max_freq;
+	int i, ret;
 
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
@@ -121,33 +99,53 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 	 * frequency.
 	 */
 	for_each_online_cpu(i) {
-		if (topology_physical_package_id(i) ==
+		if (topology_physical_package_id(i) !=
 		    topology_physical_package_id(cpu))
-			cpufreq_update_policy(i);
+			continue;
+
+		pr = per_cpu(processors, i);
+
+		if (unlikely(!dev_pm_qos_request_active(&pr->thermal_req)))
+			continue;
+
+		policy = cpufreq_cpu_get(i);
+		if (!policy)
+			return -EINVAL;
+
+		max_freq = (policy->cpuinfo.max_freq * (100 - reduction_pctg(i) * 20)) / 100;
+
+		cpufreq_cpu_put(policy);
+
+		ret = dev_pm_qos_update_request(&pr->thermal_req, max_freq);
+		if (ret < 0) {
+			pr_warn("Failed to update thermal freq constraint: CPU%d (%d)\n",
+				pr->id, ret);
+		}
 	}
 	return 0;
 }
 
-void acpi_thermal_cpufreq_init(void)
+void acpi_thermal_cpufreq_init(int cpu)
 {
-	int i;
-
-	i = cpufreq_register_notifier(&acpi_thermal_cpufreq_notifier_block,
-				      CPUFREQ_POLICY_NOTIFIER);
-	if (!i)
-		acpi_thermal_cpufreq_is_init = 1;
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+	int ret;
+
+	ret = dev_pm_qos_add_request(get_cpu_device(cpu),
+				     &pr->thermal_req, DEV_PM_QOS_MAX_FREQUENCY,
+				     INT_MAX);
+	if (ret < 0) {
+		pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu,
+		       ret);
+		return;
+	}
 }
 
-void acpi_thermal_cpufreq_exit(void)
+void acpi_thermal_cpufreq_exit(int cpu)
 {
-	if (acpi_thermal_cpufreq_is_init)
-		cpufreq_unregister_notifier
-		    (&acpi_thermal_cpufreq_notifier_block,
-		     CPUFREQ_POLICY_NOTIFIER);
+	struct acpi_processor *pr = per_cpu(processors, cpu);
 
-	acpi_thermal_cpufreq_is_init = 0;
+	dev_pm_qos_remove_request(&pr->thermal_req);
 }
-
 #else				/* ! CONFIG_CPU_FREQ */
 static int cpufreq_get_max_state(unsigned int cpu)
 {
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index f0fe7c15d657..9fa77d72ef27 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -89,6 +89,10 @@ bool acpi_sleep_state_supported(u8 sleep_state)
 }
 
 #ifdef CONFIG_ACPI_SLEEP
+static bool sleep_no_lps0 __read_mostly;
+module_param(sleep_no_lps0, bool, 0644);
+MODULE_PARM_DESC(sleep_no_lps0, "Do not use the special LPS0 device interface");
+
 static u32 acpi_target_sleep_state = ACPI_STATE_S0;
 
 u32 acpi_target_system_state(void)
@@ -158,11 +162,11 @@ static int __init init_nvs_nosave(const struct dmi_system_id *d)
 	return 0;
 }
 
-static bool acpi_sleep_no_lps0;
+static bool acpi_sleep_default_s3;
 
-static int __init init_no_lps0(const struct dmi_system_id *d)
+static int __init init_default_s3(const struct dmi_system_id *d)
 {
-	acpi_sleep_no_lps0 = true;
+	acpi_sleep_default_s3 = true;
 	return 0;
 }
 
@@ -363,7 +367,7 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 	 * S0 Idle firmware interface.
 	 */
 	{
-	.callback = init_no_lps0,
+	.callback = init_default_s3,
 	.ident = "Dell XPS13 9360",
 	.matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -376,7 +380,7 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=199057).
 	 */
 	{
-	.callback = init_no_lps0,
+	.callback = init_default_s3,
 	.ident = "ThinkPad X1 Tablet(2016)",
 	.matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -524,8 +528,9 @@ static void acpi_pm_end(void)
 	acpi_sleep_tts_switch(acpi_target_sleep_state);
 }
 #else /* !CONFIG_ACPI_SLEEP */
+#define sleep_no_lps0	(1)
 #define acpi_target_sleep_state	ACPI_STATE_S0
-#define acpi_sleep_no_lps0	(false)
+#define acpi_sleep_default_s3	(1)
 static inline void acpi_sleep_dmi_check(void) {}
 #endif /* CONFIG_ACPI_SLEEP */
 
@@ -691,7 +696,6 @@ static const struct platform_suspend_ops acpi_suspend_ops_old = {
 	.recover = acpi_pm_finish,
 };
 
-static bool s2idle_in_progress;
 static bool s2idle_wakeup;
 
 /*
@@ -904,42 +908,43 @@ static int lps0_device_attach(struct acpi_device *adev,
 	if (lps0_device_handle)
 		return 0;
 
-	if (acpi_sleep_no_lps0) {
-		acpi_handle_info(adev->handle,
-				 "Low Power S0 Idle interface disabled\n");
-		return 0;
-	}
-
 	if (!(acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0))
 		return 0;
 
 	guid_parse(ACPI_LPS0_DSM_UUID, &lps0_dsm_guid);
 	/* Check if the _DSM is present and as expected. */
 	out_obj = acpi_evaluate_dsm(adev->handle, &lps0_dsm_guid, 1, 0, NULL);
-	if (out_obj && out_obj->type == ACPI_TYPE_BUFFER) {
-		char bitmask = *(char *)out_obj->buffer.pointer;
-
-		lps0_dsm_func_mask = bitmask;
-		lps0_device_handle = adev->handle;
-		/*
-		 * Use suspend-to-idle by default if the default
-		 * suspend mode was not set from the command line.
-		 */
-		if (mem_sleep_default > PM_SUSPEND_MEM)
-			mem_sleep_current = PM_SUSPEND_TO_IDLE;
-
-		acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n",
-				  bitmask);
-
-		acpi_ec_mark_gpe_for_wake();
-	} else {
+	if (!out_obj || out_obj->type != ACPI_TYPE_BUFFER) {
 		acpi_handle_debug(adev->handle,
 				  "_DSM function 0 evaluation failed\n");
+		return 0;
 	}
+
+	lps0_dsm_func_mask = *(char *)out_obj->buffer.pointer;
+
 	ACPI_FREE(out_obj);
 
+	acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n",
+			  lps0_dsm_func_mask);
+
+	lps0_device_handle = adev->handle;
+
 	lpi_device_get_constraints();
 
+	/*
+	 * Use suspend-to-idle by default if the default suspend mode was not
+	 * set from the command line.
+	 */
+	if (mem_sleep_default > PM_SUSPEND_MEM && !acpi_sleep_default_s3)
+		mem_sleep_current = PM_SUSPEND_TO_IDLE;
+
+	/*
+	 * Some LPS0 systems, like ASUS Zenbook UX430UNR/i7-8550U, require the
+	 * EC GPE to be enabled while suspended for certain wakeup devices to
+	 * work, so mark it as wakeup-capable.
+	 */
+	acpi_ec_mark_gpe_for_wake();
+
 	return 0;
 }
 
@@ -951,98 +956,110 @@ static struct acpi_scan_handler lps0_handler = {
 static int acpi_s2idle_begin(void)
 {
 	acpi_scan_lock_acquire();
-	s2idle_in_progress = true;
 	return 0;
 }
 
 static int acpi_s2idle_prepare(void)
 {
-	if (lps0_device_handle) {
-		acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF);
-		acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY);
-
+	if (acpi_sci_irq_valid()) {
+		enable_irq_wake(acpi_sci_irq);
 		acpi_ec_set_gpe_wake_mask(ACPI_GPE_ENABLE);
 	}
 
-	if (acpi_sci_irq_valid())
-		enable_irq_wake(acpi_sci_irq);
-
 	acpi_enable_wakeup_devices(ACPI_STATE_S0);
 
 	/* Change the configuration of GPEs to avoid spurious wakeup. */
 	acpi_enable_all_wakeup_gpes();
 	acpi_os_wait_events_complete();
+
+	s2idle_wakeup = true;
 	return 0;
 }
 
-static void acpi_s2idle_wake(void)
+static int acpi_s2idle_prepare_late(void)
 {
-	if (!lps0_device_handle)
-		return;
+	if (!lps0_device_handle || sleep_no_lps0)
+		return 0;
 
 	if (pm_debug_messages_on)
 		lpi_check_constraints();
 
+	acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF);
+	acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY);
+
+	return 0;
+}
+
+static void acpi_s2idle_wake(void)
+{
+	/*
+	 * If IRQD_WAKEUP_ARMED is set for the SCI at this point, the SCI has
+	 * not triggered while suspended, so bail out.
+	 */
+	if (!acpi_sci_irq_valid() ||
+	    irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq)))
+		return;
+
 	/*
-	 * If IRQD_WAKEUP_ARMED is not set for the SCI at this point, it means
-	 * that the SCI has triggered while suspended, so cancel the wakeup in
-	 * case it has not been a wakeup event (the GPEs will be checked later).
+	 * If there are EC events to process, the wakeup may be a spurious one
+	 * coming from the EC.
 	 */
-	if (acpi_sci_irq_valid() &&
-	    !irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq))) {
+	if (acpi_ec_dispatch_gpe()) {
+		/*
+		 * Cancel the wakeup and process all pending events in case
+		 * there are any wakeup ones in there.
+		 *
+		 * Note that if any non-EC GPEs are active at this point, the
+		 * SCI will retrigger after the rearming below, so no events
+		 * should be missed by canceling the wakeup here.
+		 */
 		pm_system_cancel_wakeup();
-		s2idle_wakeup = true;
 		/*
-		 * On some platforms with the LPS0 _DSM device noirq resume
-		 * takes too much time for EC wakeup events to survive, so look
-		 * for them now.
+		 * The EC driver uses the system workqueue and an additional
+		 * special one, so those need to be flushed too.
 		 */
-		acpi_ec_dispatch_gpe();
+		acpi_os_wait_events_complete(); /* synchronize EC GPE processing */
+		acpi_ec_flush_work();
+		acpi_os_wait_events_complete(); /* synchronize Notify handling */
+
+		rearm_wake_irq(acpi_sci_irq);
 	}
 }
 
-static void acpi_s2idle_sync(void)
+static void acpi_s2idle_restore_early(void)
 {
-	/*
-	 * Process all pending events in case there are any wakeup ones.
-	 *
-	 * The EC driver uses the system workqueue and an additional special
-	 * one, so those need to be flushed too.
-	 */
-	acpi_os_wait_events_complete();	/* synchronize SCI IRQ handling */
-	acpi_ec_flush_work();
-	acpi_os_wait_events_complete();	/* synchronize Notify handling */
-	s2idle_wakeup = false;
+	if (!lps0_device_handle || sleep_no_lps0)
+		return;
+
+	acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT);
+	acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON);
 }
 
 static void acpi_s2idle_restore(void)
 {
+	s2idle_wakeup = false;
+
 	acpi_enable_all_runtime_gpes();
 
 	acpi_disable_wakeup_devices(ACPI_STATE_S0);
 
-	if (acpi_sci_irq_valid())
-		disable_irq_wake(acpi_sci_irq);
-
-	if (lps0_device_handle) {
+	if (acpi_sci_irq_valid()) {
 		acpi_ec_set_gpe_wake_mask(ACPI_GPE_DISABLE);
-
-		acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT);
-		acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON);
+		disable_irq_wake(acpi_sci_irq);
 	}
 }
 
 static void acpi_s2idle_end(void)
 {
-	s2idle_in_progress = false;
 	acpi_scan_lock_release();
 }
 
 static const struct platform_s2idle_ops acpi_s2idle_ops = {
 	.begin = acpi_s2idle_begin,
 	.prepare = acpi_s2idle_prepare,
+	.prepare_late = acpi_s2idle_prepare_late,
 	.wake = acpi_s2idle_wake,
-	.sync = acpi_s2idle_sync,
+	.restore_early = acpi_s2idle_restore_early,
 	.restore = acpi_s2idle_restore,
 	.end = acpi_s2idle_end,
 };
@@ -1063,7 +1080,6 @@ static void acpi_sleep_suspend_setup(void)
 }
 
 #else /* !CONFIG_SUSPEND */
-#define s2idle_in_progress	(false)
 #define s2idle_wakeup		(false)
 #define lps0_device_handle	(NULL)
 static inline void acpi_sleep_suspend_setup(void) {}
@@ -1074,11 +1090,6 @@ bool acpi_s2idle_wakeup(void)
 	return s2idle_wakeup;
 }
 
-bool acpi_sleep_no_ec_events(void)
-{
-	return !s2idle_in_progress || !lps0_device_handle;
-}
-
 #ifdef CONFIG_PM_SLEEP
 static u32 saved_bm_rld;
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index b54d241a2ff5..1eb81f113786 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -179,7 +179,7 @@ init_cpu_capacity_callback(struct notifier_block *nb,
 	if (!raw_capacity)
 		return 0;
 
-	if (val != CPUFREQ_NOTIFY)
+	if (val != CPUFREQ_CREATE_POLICY)
 		return 0;
 
 	pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index e1bb691cf8f1..ec5bb190b9d0 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o runtime.o wakeirq.o
-obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
+obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o wakeup_stats.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
 obj-$(CONFIG_PM_GENERIC_DOMAINS)	+=  domain.o domain_governor.o
 obj-$(CONFIG_HAVE_CLK)	+= clock_ops.o
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index b063bc41b0a9..cc85e87eaf05 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -149,29 +149,24 @@ static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
 	return ret;
 }
 
+static int genpd_runtime_suspend(struct device *dev);
+
 /*
  * Get the generic PM domain for a particular struct device.
  * This validates the struct device pointer, the PM domain pointer,
  * and checks that the PM domain pointer is a real generic PM domain.
  * Any failure results in NULL being returned.
  */
-static struct generic_pm_domain *genpd_lookup_dev(struct device *dev)
+static struct generic_pm_domain *dev_to_genpd_safe(struct device *dev)
 {
-	struct generic_pm_domain *genpd = NULL, *gpd;
-
 	if (IS_ERR_OR_NULL(dev) || IS_ERR_OR_NULL(dev->pm_domain))
 		return NULL;
 
-	mutex_lock(&gpd_list_lock);
-	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
-		if (&gpd->domain == dev->pm_domain) {
-			genpd = gpd;
-			break;
-		}
-	}
-	mutex_unlock(&gpd_list_lock);
+	/* A genpd's always have its ->runtime_suspend() callback assigned. */
+	if (dev->pm_domain->ops.runtime_suspend == genpd_runtime_suspend)
+		return pd_to_genpd(dev->pm_domain);
 
-	return genpd;
+	return NULL;
 }
 
 /*
@@ -385,8 +380,8 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state)
 	unsigned int prev;
 	int ret;
 
-	genpd = dev_to_genpd(dev);
-	if (IS_ERR(genpd))
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
 		return -ENODEV;
 
 	if (unlikely(!genpd->set_performance_state))
@@ -1610,7 +1605,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
  */
 int pm_genpd_remove_device(struct device *dev)
 {
-	struct generic_pm_domain *genpd = genpd_lookup_dev(dev);
+	struct generic_pm_domain *genpd = dev_to_genpd_safe(dev);
 
 	if (!genpd)
 		return -EINVAL;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 7fb2c39bc725..134a8af51511 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -716,7 +716,7 @@ static void async_resume_noirq(void *data, async_cookie_t cookie)
 	put_device(dev);
 }
 
-void dpm_noirq_resume_devices(pm_message_t state)
+static void dpm_noirq_resume_devices(pm_message_t state)
 {
 	struct device *dev;
 	ktime_t starttime = ktime_get();
@@ -760,13 +760,6 @@ void dpm_noirq_resume_devices(pm_message_t state)
 	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false);
 }
 
-void dpm_noirq_end(void)
-{
-	resume_device_irqs();
-	device_wakeup_disarm_wake_irqs();
-	cpuidle_resume();
-}
-
 /**
  * dpm_resume_noirq - Execute "noirq resume" callbacks for all devices.
  * @state: PM transition of the system being carried out.
@@ -777,7 +770,11 @@ void dpm_noirq_end(void)
 void dpm_resume_noirq(pm_message_t state)
 {
 	dpm_noirq_resume_devices(state);
-	dpm_noirq_end();
+
+	resume_device_irqs();
+	device_wakeup_disarm_wake_irqs();
+
+	cpuidle_resume();
 }
 
 static pm_callback_t dpm_subsys_resume_early_cb(struct device *dev,
@@ -1291,11 +1288,6 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a
 	if (async_error)
 		goto Complete;
 
-	if (pm_wakeup_pending()) {
-		async_error = -EBUSY;
-		goto Complete;
-	}
-
 	if (dev->power.syscore || dev->power.direct_complete)
 		goto Complete;
 
@@ -1362,14 +1354,7 @@ static int device_suspend_noirq(struct device *dev)
 	return __device_suspend_noirq(dev, pm_transition, false);
 }
 
-void dpm_noirq_begin(void)
-{
-	cpuidle_pause();
-	device_wakeup_arm_wake_irqs();
-	suspend_device_irqs();
-}
-
-int dpm_noirq_suspend_devices(pm_message_t state)
+static int dpm_noirq_suspend_devices(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 	int error = 0;
@@ -1426,7 +1411,11 @@ int dpm_suspend_noirq(pm_message_t state)
 {
 	int ret;
 
-	dpm_noirq_begin();
+	cpuidle_pause();
+
+	device_wakeup_arm_wake_irqs();
+	suspend_device_irqs();
+
 	ret = dpm_noirq_suspend_devices(state);
 	if (ret)
 		dpm_resume_noirq(resume_event(state));
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index ec33fbdb919b..39a06a0cfdaa 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -149,3 +149,21 @@ static inline void device_pm_init(struct device *dev)
 	device_pm_sleep_init(dev);
 	pm_runtime_init(dev);
 }
+
+#ifdef CONFIG_PM_SLEEP
+
+/* drivers/base/power/wakeup_stats.c */
+extern int wakeup_source_sysfs_add(struct device *parent,
+				   struct wakeup_source *ws);
+extern void wakeup_source_sysfs_remove(struct wakeup_source *ws);
+
+extern int pm_wakeup_source_sysfs_add(struct device *parent);
+
+#else /* !CONFIG_PM_SLEEP */
+
+static inline int pm_wakeup_source_sysfs_add(struct device *parent)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 1b9c281cbe41..d7d82db2e4bc 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -5,6 +5,7 @@
 #include <linux/export.h>
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_wakeup.h>
 #include <linux/atomic.h>
 #include <linux/jiffies.h>
 #include "power.h"
@@ -667,8 +668,13 @@ int dpm_sysfs_add(struct device *dev)
 		if (rc)
 			goto err_wakeup;
 	}
+	rc = pm_wakeup_source_sysfs_add(dev);
+	if (rc)
+		goto err_latency;
 	return 0;
 
+ err_latency:
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group);
  err_wakeup:
 	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
  err_runtime:
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index ee31d4f8d856..5817b51d2b15 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -72,22 +72,7 @@ static struct wakeup_source deleted_ws = {
 	.lock =  __SPIN_LOCK_UNLOCKED(deleted_ws.lock),
 };
 
-/**
- * wakeup_source_prepare - Prepare a new wakeup source for initialization.
- * @ws: Wakeup source to prepare.
- * @name: Pointer to the name of the new wakeup source.
- *
- * Callers must ensure that the @name string won't be freed when @ws is still in
- * use.
- */
-void wakeup_source_prepare(struct wakeup_source *ws, const char *name)
-{
-	if (ws) {
-		memset(ws, 0, sizeof(*ws));
-		ws->name = name;
-	}
-}
-EXPORT_SYMBOL_GPL(wakeup_source_prepare);
+static DEFINE_IDA(wakeup_ida);
 
 /**
  * wakeup_source_create - Create a struct wakeup_source object.
@@ -96,13 +81,31 @@ EXPORT_SYMBOL_GPL(wakeup_source_prepare);
 struct wakeup_source *wakeup_source_create(const char *name)
 {
 	struct wakeup_source *ws;
+	const char *ws_name;
+	int id;
 
-	ws = kmalloc(sizeof(*ws), GFP_KERNEL);
+	ws = kzalloc(sizeof(*ws), GFP_KERNEL);
 	if (!ws)
-		return NULL;
+		goto err_ws;
+
+	ws_name = kstrdup_const(name, GFP_KERNEL);
+	if (!ws_name)
+		goto err_name;
+	ws->name = ws_name;
+
+	id = ida_alloc(&wakeup_ida, GFP_KERNEL);
+	if (id < 0)
+		goto err_id;
+	ws->id = id;
 
-	wakeup_source_prepare(ws, name ? kstrdup_const(name, GFP_KERNEL) : NULL);
 	return ws;
+
+err_id:
+	kfree_const(ws->name);
+err_name:
+	kfree(ws);
+err_ws:
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(wakeup_source_create);
 
@@ -134,6 +137,13 @@ static void wakeup_source_record(struct wakeup_source *ws)
 	spin_unlock_irqrestore(&deleted_ws.lock, flags);
 }
 
+static void wakeup_source_free(struct wakeup_source *ws)
+{
+	ida_free(&wakeup_ida, ws->id);
+	kfree_const(ws->name);
+	kfree(ws);
+}
+
 /**
  * wakeup_source_destroy - Destroy a struct wakeup_source object.
  * @ws: Wakeup source to destroy.
@@ -147,8 +157,7 @@ void wakeup_source_destroy(struct wakeup_source *ws)
 
 	__pm_relax(ws);
 	wakeup_source_record(ws);
-	kfree_const(ws->name);
-	kfree(ws);
+	wakeup_source_free(ws);
 }
 EXPORT_SYMBOL_GPL(wakeup_source_destroy);
 
@@ -200,16 +209,26 @@ EXPORT_SYMBOL_GPL(wakeup_source_remove);
 
 /**
  * wakeup_source_register - Create wakeup source and add it to the list.
+ * @dev: Device this wakeup source is associated with (or NULL if virtual).
  * @name: Name of the wakeup source to register.
  */
-struct wakeup_source *wakeup_source_register(const char *name)
+struct wakeup_source *wakeup_source_register(struct device *dev,
+					     const char *name)
 {
 	struct wakeup_source *ws;
+	int ret;
 
 	ws = wakeup_source_create(name);
-	if (ws)
+	if (ws) {
+		if (!dev || device_is_registered(dev)) {
+			ret = wakeup_source_sysfs_add(dev, ws);
+			if (ret) {
+				wakeup_source_free(ws);
+				return NULL;
+			}
+		}
 		wakeup_source_add(ws);
-
+	}
 	return ws;
 }
 EXPORT_SYMBOL_GPL(wakeup_source_register);
@@ -222,6 +241,7 @@ void wakeup_source_unregister(struct wakeup_source *ws)
 {
 	if (ws) {
 		wakeup_source_remove(ws);
+		wakeup_source_sysfs_remove(ws);
 		wakeup_source_destroy(ws);
 	}
 }
@@ -265,7 +285,7 @@ int device_wakeup_enable(struct device *dev)
 	if (pm_suspend_target_state != PM_SUSPEND_ON)
 		dev_dbg(dev, "Suspicious %s() during system transition!\n", __func__);
 
-	ws = wakeup_source_register(dev_name(dev));
+	ws = wakeup_source_register(dev, dev_name(dev));
 	if (!ws)
 		return -ENOMEM;
 
@@ -859,7 +879,7 @@ EXPORT_SYMBOL_GPL(pm_system_wakeup);
 
 void pm_system_cancel_wakeup(void)
 {
-	atomic_dec(&pm_abort_suspend);
+	atomic_dec_if_positive(&pm_abort_suspend);
 }
 
 void pm_wakeup_clear(bool reset)
diff --git a/drivers/base/power/wakeup_stats.c b/drivers/base/power/wakeup_stats.c
new file mode 100644
index 000000000000..c7734914d914
--- /dev/null
+++ b/drivers/base/power/wakeup_stats.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Wakeup statistics in sysfs
+ *
+ * Copyright (c) 2019 Linux Foundation
+ * Copyright (c) 2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+ * Copyright (c) 2019 Google Inc.
+ */
+
+#include <linux/device.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/kdev_t.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/slab.h>
+#include <linux/timekeeping.h>
+
+#include "power.h"
+
+static struct class *wakeup_class;
+
+#define wakeup_attr(_name)						\
+static ssize_t _name##_show(struct device *dev,				\
+			    struct device_attribute *attr, char *buf)	\
+{									\
+	struct wakeup_source *ws = dev_get_drvdata(dev);		\
+									\
+	return sprintf(buf, "%lu\n", ws->_name);			\
+}									\
+static DEVICE_ATTR_RO(_name)
+
+wakeup_attr(active_count);
+wakeup_attr(event_count);
+wakeup_attr(wakeup_count);
+wakeup_attr(expire_count);
+
+static ssize_t active_time_ms_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+	ktime_t active_time =
+		ws->active ? ktime_sub(ktime_get(), ws->last_time) : 0;
+
+	return sprintf(buf, "%lld\n", ktime_to_ms(active_time));
+}
+static DEVICE_ATTR_RO(active_time_ms);
+
+static ssize_t total_time_ms_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+	ktime_t active_time;
+	ktime_t total_time = ws->total_time;
+
+	if (ws->active) {
+		active_time = ktime_sub(ktime_get(), ws->last_time);
+		total_time = ktime_add(total_time, active_time);
+	}
+	return sprintf(buf, "%lld\n", ktime_to_ms(total_time));
+}
+static DEVICE_ATTR_RO(total_time_ms);
+
+static ssize_t max_time_ms_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+	ktime_t active_time;
+	ktime_t max_time = ws->max_time;
+
+	if (ws->active) {
+		active_time = ktime_sub(ktime_get(), ws->last_time);
+		if (active_time > max_time)
+			max_time = active_time;
+	}
+	return sprintf(buf, "%lld\n", ktime_to_ms(max_time));
+}
+static DEVICE_ATTR_RO(max_time_ms);
+
+static ssize_t last_change_ms_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%lld\n", ktime_to_ms(ws->last_time));
+}
+static DEVICE_ATTR_RO(last_change_ms);
+
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", ws->name);
+}
+static DEVICE_ATTR_RO(name);
+
+static ssize_t prevent_suspend_time_ms_show(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct wakeup_source *ws = dev_get_drvdata(dev);
+	ktime_t prevent_sleep_time = ws->prevent_sleep_time;
+
+	if (ws->active && ws->autosleep_enabled) {
+		prevent_sleep_time = ktime_add(prevent_sleep_time,
+			ktime_sub(ktime_get(), ws->start_prevent_time));
+	}
+	return sprintf(buf, "%lld\n", ktime_to_ms(prevent_sleep_time));
+}
+static DEVICE_ATTR_RO(prevent_suspend_time_ms);
+
+static struct attribute *wakeup_source_attrs[] = {
+	&dev_attr_name.attr,
+	&dev_attr_active_count.attr,
+	&dev_attr_event_count.attr,
+	&dev_attr_wakeup_count.attr,
+	&dev_attr_expire_count.attr,
+	&dev_attr_active_time_ms.attr,
+	&dev_attr_total_time_ms.attr,
+	&dev_attr_max_time_ms.attr,
+	&dev_attr_last_change_ms.attr,
+	&dev_attr_prevent_suspend_time_ms.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(wakeup_source);
+
+static void device_create_release(struct device *dev)
+{
+	kfree(dev);
+}
+
+static struct device *wakeup_source_device_create(struct device *parent,
+						  struct wakeup_source *ws)
+{
+	struct device *dev = NULL;
+	int retval = -ENODEV;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev) {
+		retval = -ENOMEM;
+		goto error;
+	}
+
+	device_initialize(dev);
+	dev->devt = MKDEV(0, 0);
+	dev->class = wakeup_class;
+	dev->parent = parent;
+	dev->groups = wakeup_source_groups;
+	dev->release = device_create_release;
+	dev_set_drvdata(dev, ws);
+	device_set_pm_not_required(dev);
+
+	retval = kobject_set_name(&dev->kobj, "wakeup%d", ws->id);
+	if (retval)
+		goto error;
+
+	retval = device_add(dev);
+	if (retval)
+		goto error;
+
+	return dev;
+
+error:
+	put_device(dev);
+	return ERR_PTR(retval);
+}
+
+/**
+ * wakeup_source_sysfs_add - Add wakeup_source attributes to sysfs.
+ * @parent: Device given wakeup source is associated with (or NULL if virtual).
+ * @ws: Wakeup source to be added in sysfs.
+ */
+int wakeup_source_sysfs_add(struct device *parent, struct wakeup_source *ws)
+{
+	struct device *dev;
+
+	dev = wakeup_source_device_create(parent, ws);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+	ws->dev = dev;
+
+	return 0;
+}
+
+/**
+ * pm_wakeup_source_sysfs_add - Add wakeup_source attributes to sysfs
+ * for a device if they're missing.
+ * @parent: Device given wakeup source is associated with
+ */
+int pm_wakeup_source_sysfs_add(struct device *parent)
+{
+	if (!parent->power.wakeup || parent->power.wakeup->dev)
+		return 0;
+
+	return wakeup_source_sysfs_add(parent, parent->power.wakeup);
+}
+
+/**
+ * wakeup_source_sysfs_remove - Remove wakeup_source attributes from sysfs.
+ * @ws: Wakeup source to be removed from sysfs.
+ */
+void wakeup_source_sysfs_remove(struct wakeup_source *ws)
+{
+	device_unregister(ws->dev);
+}
+
+static int __init wakeup_sources_sysfs_init(void)
+{
+	wakeup_class = class_create(THIS_MODULE, "wakeup");
+
+	return PTR_ERR_OR_ZERO(wakeup_class);
+}
+postcore_initcall(wakeup_sources_sysfs_init);
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 56c31a78c692..a905796f7f85 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -19,6 +19,18 @@ config ACPI_CPPC_CPUFREQ
 
 	  If in doubt, say N.
 
+config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM
+	tristate "Allwinner nvmem based SUN50I CPUFreq driver"
+	depends on ARCH_SUNXI
+	depends on NVMEM_SUNXI_SID
+	select PM_OPP
+	help
+	  This adds the nvmem based CPUFreq driver for Allwinner
+	  h6 SoC.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called sun50i-cpufreq-nvmem.
+
 config ARM_ARMADA_37XX_CPUFREQ
 	tristate "Armada 37xx CPUFreq support"
 	depends on ARCH_MVEBU && CPUFREQ_DT
@@ -120,8 +132,8 @@ config ARM_OMAP2PLUS_CPUFREQ
 	depends on ARCH_OMAP2PLUS
 	default ARCH_OMAP2PLUS
 
-config ARM_QCOM_CPUFREQ_KRYO
-	tristate "Qualcomm Kryo based CPUFreq"
+config ARM_QCOM_CPUFREQ_NVMEM
+	tristate "Qualcomm nvmem based CPUFreq"
 	depends on ARM64
 	depends on QCOM_QFPROM
 	depends on QCOM_SMEM
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 5a6c70d26c98..9a9f5ccd13d9 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -64,7 +64,7 @@ obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ)	+= omap-cpufreq.o
 obj-$(CONFIG_ARM_PXA2xx_CPUFREQ)	+= pxa2xx-cpufreq.o
 obj-$(CONFIG_PXA3xx)			+= pxa3xx-cpufreq.o
 obj-$(CONFIG_ARM_QCOM_CPUFREQ_HW)	+= qcom-cpufreq-hw.o
-obj-$(CONFIG_ARM_QCOM_CPUFREQ_KRYO)	+= qcom-cpufreq-kryo.o
+obj-$(CONFIG_ARM_QCOM_CPUFREQ_NVMEM)	+= qcom-cpufreq-nvmem.o
 obj-$(CONFIG_ARM_RASPBERRYPI_CPUFREQ) 	+= raspberrypi-cpufreq.o
 obj-$(CONFIG_ARM_S3C2410_CPUFREQ)	+= s3c2410-cpufreq.o
 obj-$(CONFIG_ARM_S3C2412_CPUFREQ)	+= s3c2412-cpufreq.o
@@ -80,6 +80,7 @@ obj-$(CONFIG_ARM_SCMI_CPUFREQ)		+= scmi-cpufreq.o
 obj-$(CONFIG_ARM_SCPI_CPUFREQ)		+= scpi-cpufreq.o
 obj-$(CONFIG_ARM_SPEAR_CPUFREQ)		+= spear-cpufreq.o
 obj-$(CONFIG_ARM_STI_CPUFREQ)		+= sti-cpufreq.o
+obj-$(CONFIG_ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM) += sun50i-cpufreq-nvmem.o
 obj-$(CONFIG_ARM_TANGO_CPUFREQ)		+= tango-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA20_CPUFREQ)	+= tegra20-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c
index 988ebc326bdb..39e34f5066d3 100644
--- a/drivers/cpufreq/armada-8k-cpufreq.c
+++ b/drivers/cpufreq/armada-8k-cpufreq.c
@@ -136,6 +136,8 @@ static int __init armada_8k_cpufreq_init(void)
 
 	nb_cpus = num_possible_cpus();
 	freq_tables = kcalloc(nb_cpus, sizeof(*freq_tables), GFP_KERNEL);
+	if (!freq_tables)
+		return -ENOMEM;
 	cpumask_copy(&cpus, cpu_possible_mask);
 
 	/*
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 03dc4244ab00..bca8d1f47fd2 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -101,12 +101,15 @@ static const struct of_device_id whitelist[] __initconst = {
  * platforms using "operating-points-v2" property.
  */
 static const struct of_device_id blacklist[] __initconst = {
+	{ .compatible = "allwinner,sun50i-h6", },
+
 	{ .compatible = "calxeda,highbank", },
 	{ .compatible = "calxeda,ecx-2000", },
 
 	{ .compatible = "fsl,imx7d", },
 	{ .compatible = "fsl,imx8mq", },
 	{ .compatible = "fsl,imx8mm", },
+	{ .compatible = "fsl,imx8mn", },
 
 	{ .compatible = "marvell,armadaxp", },
 
@@ -117,12 +120,14 @@ static const struct of_device_id blacklist[] __initconst = {
 	{ .compatible = "mediatek,mt817x", },
 	{ .compatible = "mediatek,mt8173", },
 	{ .compatible = "mediatek,mt8176", },
+	{ .compatible = "mediatek,mt8183", },
 
 	{ .compatible = "nvidia,tegra124", },
 	{ .compatible = "nvidia,tegra210", },
 
 	{ .compatible = "qcom,apq8096", },
 	{ .compatible = "qcom,msm8996", },
+	{ .compatible = "qcom,qcs404", },
 
 	{ .compatible = "st,stih407", },
 	{ .compatible = "st,stih410", },
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index c28ebf2810f1..c52d6fa32aac 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1266,7 +1266,17 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy)
 				   DEV_PM_QOS_MAX_FREQUENCY);
 	dev_pm_qos_remove_notifier(dev, &policy->nb_min,
 				   DEV_PM_QOS_MIN_FREQUENCY);
-	dev_pm_qos_remove_request(policy->max_freq_req);
+
+	if (policy->max_freq_req) {
+		/*
+		 * CPUFREQ_CREATE_POLICY notification is sent only after
+		 * successfully adding max_freq_req request.
+		 */
+		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+					     CPUFREQ_REMOVE_POLICY, policy);
+		dev_pm_qos_remove_request(policy->max_freq_req);
+	}
+
 	dev_pm_qos_remove_request(policy->min_freq_req);
 	kfree(policy->min_freq_req);
 
@@ -1391,6 +1401,9 @@ static int cpufreq_online(unsigned int cpu)
 				ret);
 			goto out_destroy_policy;
 		}
+
+		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+				CPUFREQ_CREATE_POLICY, policy);
 	}
 
 	if (cpufreq_driver->get && has_target()) {
@@ -1807,8 +1820,8 @@ void cpufreq_suspend(void)
 		}
 
 		if (cpufreq_driver->suspend && cpufreq_driver->suspend(policy))
-			pr_err("%s: Failed to suspend driver: %p\n", __func__,
-				policy);
+			pr_err("%s: Failed to suspend driver: %s\n", __func__,
+				cpufreq_driver->name);
 	}
 
 suspend:
@@ -2140,7 +2153,7 @@ int cpufreq_driver_target(struct cpufreq_policy *policy,
 			  unsigned int target_freq,
 			  unsigned int relation)
 {
-	int ret = -EINVAL;
+	int ret;
 
 	down_write(&policy->rwsem);
 
@@ -2347,15 +2360,13 @@ EXPORT_SYMBOL(cpufreq_get_policy);
  * @policy: Policy object to modify.
  * @new_policy: New policy data.
  *
- * Pass @new_policy to the cpufreq driver's ->verify() callback, run the
- * installed policy notifiers for it with the CPUFREQ_ADJUST value, pass it to
- * the driver's ->verify() callback again and run the notifiers for it again
- * with the CPUFREQ_NOTIFY value.  Next, copy the min and max parameters
- * of @new_policy to @policy and either invoke the driver's ->setpolicy()
- * callback (if present) or carry out a governor update for @policy.  That is,
- * run the current governor's ->limits() callback (if the governor field in
- * @new_policy points to the same object as the one in @policy) or replace the
- * governor for @policy with the new one stored in @new_policy.
+ * Pass @new_policy to the cpufreq driver's ->verify() callback. Next, copy the
+ * min and max parameters of @new_policy to @policy and either invoke the
+ * driver's ->setpolicy() callback (if present) or carry out a governor update
+ * for @policy.  That is, run the current governor's ->limits() callback (if the
+ * governor field in @new_policy points to the same object as the one in
+ * @policy) or replace the governor for @policy with the new one stored in
+ * @new_policy.
  *
  * The cpuinfo part of @policy is not updated by this function.
  */
@@ -2383,26 +2394,6 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 	if (ret)
 		return ret;
 
-	/*
-	 * The notifier-chain shall be removed once all the users of
-	 * CPUFREQ_ADJUST are moved to use the QoS framework.
-	 */
-	/* adjust if necessary - all reasons */
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_ADJUST, new_policy);
-
-	/*
-	 * verify the cpu speed can be set within this limit, which might be
-	 * different to the first one
-	 */
-	ret = cpufreq_driver->verify(new_policy);
-	if (ret)
-		return ret;
-
-	/* notification of the new policy */
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_NOTIFY, new_policy);
-
 	policy->min = new_policy->min;
 	policy->max = new_policy->max;
 	trace_cpu_frequency_limits(policy);
diff --git a/drivers/cpufreq/imx-cpufreq-dt.c b/drivers/cpufreq/imx-cpufreq-dt.c
index 4f85f3112784..35db14cf3102 100644
--- a/drivers/cpufreq/imx-cpufreq-dt.c
+++ b/drivers/cpufreq/imx-cpufreq-dt.c
@@ -16,6 +16,7 @@
 
 #define OCOTP_CFG3_SPEED_GRADE_SHIFT	8
 #define OCOTP_CFG3_SPEED_GRADE_MASK	(0x3 << 8)
+#define IMX8MN_OCOTP_CFG3_SPEED_GRADE_MASK	(0xf << 8)
 #define OCOTP_CFG3_MKT_SEGMENT_SHIFT    6
 #define OCOTP_CFG3_MKT_SEGMENT_MASK     (0x3 << 6)
 
@@ -34,7 +35,12 @@ static int imx_cpufreq_dt_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	speed_grade = (cell_value & OCOTP_CFG3_SPEED_GRADE_MASK) >> OCOTP_CFG3_SPEED_GRADE_SHIFT;
+	if (of_machine_is_compatible("fsl,imx8mn"))
+		speed_grade = (cell_value & IMX8MN_OCOTP_CFG3_SPEED_GRADE_MASK)
+			      >> OCOTP_CFG3_SPEED_GRADE_SHIFT;
+	else
+		speed_grade = (cell_value & OCOTP_CFG3_SPEED_GRADE_MASK)
+			      >> OCOTP_CFG3_SPEED_GRADE_SHIFT;
 	mkt_segment = (cell_value & OCOTP_CFG3_MKT_SEGMENT_MASK) >> OCOTP_CFG3_MKT_SEGMENT_SHIFT;
 
 	/*
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 886324041add..9f02de9a1b47 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -24,6 +24,7 @@
 #include <linux/fs.h>
 #include <linux/acpi.h>
 #include <linux/vmalloc.h>
+#include <linux/pm_qos.h>
 #include <trace/events/power.h>
 
 #include <asm/div64.h>
@@ -1085,6 +1086,47 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 	return count;
 }
 
+static struct cpufreq_driver intel_pstate;
+
+static void update_qos_request(enum dev_pm_qos_req_type type)
+{
+	int max_state, turbo_max, freq, i, perf_pct;
+	struct dev_pm_qos_request *req;
+	struct cpufreq_policy *policy;
+
+	for_each_possible_cpu(i) {
+		struct cpudata *cpu = all_cpu_data[i];
+
+		policy = cpufreq_cpu_get(i);
+		if (!policy)
+			continue;
+
+		req = policy->driver_data;
+		cpufreq_cpu_put(policy);
+
+		if (!req)
+			continue;
+
+		if (hwp_active)
+			intel_pstate_get_hwp_max(i, &turbo_max, &max_state);
+		else
+			turbo_max = cpu->pstate.turbo_pstate;
+
+		if (type == DEV_PM_QOS_MIN_FREQUENCY) {
+			perf_pct = global.min_perf_pct;
+		} else {
+			req++;
+			perf_pct = global.max_perf_pct;
+		}
+
+		freq = DIV_ROUND_UP(turbo_max * perf_pct, 100);
+		freq *= cpu->pstate.scaling;
+
+		if (dev_pm_qos_update_request(req, freq) < 0)
+			pr_warn("Failed to update freq constraint: CPU%d\n", i);
+	}
+}
+
 static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b,
 				  const char *buf, size_t count)
 {
@@ -1108,7 +1150,10 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b,
 
 	mutex_unlock(&intel_pstate_limits_lock);
 
-	intel_pstate_update_policies();
+	if (intel_pstate_driver == &intel_pstate)
+		intel_pstate_update_policies();
+	else
+		update_qos_request(DEV_PM_QOS_MAX_FREQUENCY);
 
 	mutex_unlock(&intel_pstate_driver_lock);
 
@@ -1139,7 +1184,10 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b,
 
 	mutex_unlock(&intel_pstate_limits_lock);
 
-	intel_pstate_update_policies();
+	if (intel_pstate_driver == &intel_pstate)
+		intel_pstate_update_policies();
+	else
+		update_qos_request(DEV_PM_QOS_MIN_FREQUENCY);
 
 	mutex_unlock(&intel_pstate_driver_lock);
 
@@ -2332,8 +2380,16 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 
 static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	int ret = __intel_pstate_cpu_init(policy);
+	int max_state, turbo_max, min_freq, max_freq, ret;
+	struct dev_pm_qos_request *req;
+	struct cpudata *cpu;
+	struct device *dev;
+
+	dev = get_cpu_device(policy->cpu);
+	if (!dev)
+		return -ENODEV;
 
+	ret = __intel_pstate_cpu_init(policy);
 	if (ret)
 		return ret;
 
@@ -2342,7 +2398,63 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	/* This reflects the intel_pstate_get_cpu_pstates() setting. */
 	policy->cur = policy->cpuinfo.min_freq;
 
+	req = kcalloc(2, sizeof(*req), GFP_KERNEL);
+	if (!req) {
+		ret = -ENOMEM;
+		goto pstate_exit;
+	}
+
+	cpu = all_cpu_data[policy->cpu];
+
+	if (hwp_active)
+		intel_pstate_get_hwp_max(policy->cpu, &turbo_max, &max_state);
+	else
+		turbo_max = cpu->pstate.turbo_pstate;
+
+	min_freq = DIV_ROUND_UP(turbo_max * global.min_perf_pct, 100);
+	min_freq *= cpu->pstate.scaling;
+	max_freq = DIV_ROUND_UP(turbo_max * global.max_perf_pct, 100);
+	max_freq *= cpu->pstate.scaling;
+
+	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_MIN_FREQUENCY,
+				     min_freq);
+	if (ret < 0) {
+		dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret);
+		goto free_req;
+	}
+
+	ret = dev_pm_qos_add_request(dev, req + 1, DEV_PM_QOS_MAX_FREQUENCY,
+				     max_freq);
+	if (ret < 0) {
+		dev_err(dev, "Failed to add max-freq constraint (%d)\n", ret);
+		goto remove_min_req;
+	}
+
+	policy->driver_data = req;
+
 	return 0;
+
+remove_min_req:
+	dev_pm_qos_remove_request(req);
+free_req:
+	kfree(req);
+pstate_exit:
+	intel_pstate_exit_perf_limits(policy);
+
+	return ret;
+}
+
+static int intel_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+	struct dev_pm_qos_request *req;
+
+	req = policy->driver_data;
+
+	dev_pm_qos_remove_request(req + 1);
+	dev_pm_qos_remove_request(req);
+	kfree(req);
+
+	return intel_pstate_cpu_exit(policy);
 }
 
 static struct cpufreq_driver intel_cpufreq = {
@@ -2351,7 +2463,7 @@ static struct cpufreq_driver intel_cpufreq = {
 	.target		= intel_cpufreq_target,
 	.fast_switch	= intel_cpufreq_fast_switch,
 	.init		= intel_cpufreq_cpu_init,
-	.exit		= intel_pstate_cpu_exit,
+	.exit		= intel_cpufreq_cpu_exit,
 	.stop_cpu	= intel_cpufreq_stop_cpu,
 	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_cpufreq",
diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c
index f14f3a85f2f7..0c98dd08273d 100644
--- a/drivers/cpufreq/mediatek-cpufreq.c
+++ b/drivers/cpufreq/mediatek-cpufreq.c
@@ -338,7 +338,7 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
 		goto out_free_resources;
 	}
 
-	proc_reg = regulator_get_exclusive(cpu_dev, "proc");
+	proc_reg = regulator_get_optional(cpu_dev, "proc");
 	if (IS_ERR(proc_reg)) {
 		if (PTR_ERR(proc_reg) == -EPROBE_DEFER)
 			pr_warn("proc regulator for cpu%d not ready, retry.\n",
@@ -535,6 +535,8 @@ static const struct of_device_id mtk_cpufreq_machines[] __initconst = {
 	{ .compatible = "mediatek,mt817x", },
 	{ .compatible = "mediatek,mt8173", },
 	{ .compatible = "mediatek,mt8176", },
+	{ .compatible = "mediatek,mt8183", },
+	{ .compatible = "mediatek,mt8516", },
 
 	{ }
 };
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c
index b83f36febf03..c58abb4cca3a 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq.c
@@ -110,6 +110,13 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy)
 #endif
 
 	policy->freq_table = cbe_freqs;
+	cbe_cpufreq_pmi_policy_init(policy);
+	return 0;
+}
+
+static int cbe_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+	cbe_cpufreq_pmi_policy_exit(policy);
 	return 0;
 }
 
@@ -129,6 +136,7 @@ static struct cpufreq_driver cbe_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= cbe_cpufreq_target,
 	.init		= cbe_cpufreq_cpu_init,
+	.exit		= cbe_cpufreq_cpu_exit,
 	.name		= "cbe-cpufreq",
 	.flags		= CPUFREQ_CONST_LOOPS,
 };
@@ -139,15 +147,24 @@ static struct cpufreq_driver cbe_cpufreq_driver = {
 
 static int __init cbe_cpufreq_init(void)
 {
+	int ret;
+
 	if (!machine_is(cell))
 		return -ENODEV;
 
-	return cpufreq_register_driver(&cbe_cpufreq_driver);
+	cbe_cpufreq_pmi_init();
+
+	ret = cpufreq_register_driver(&cbe_cpufreq_driver);
+	if (ret)
+		cbe_cpufreq_pmi_exit();
+
+	return ret;
 }
 
 static void __exit cbe_cpufreq_exit(void)
 {
 	cpufreq_unregister_driver(&cbe_cpufreq_driver);
+	cbe_cpufreq_pmi_exit();
 }
 
 module_init(cbe_cpufreq_init);
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.h b/drivers/cpufreq/ppc_cbe_cpufreq.h
index 9d973519d669..00cd8633b0d9 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq.h
+++ b/drivers/cpufreq/ppc_cbe_cpufreq.h
@@ -20,6 +20,14 @@ int cbe_cpufreq_set_pmode_pmi(int cpu, unsigned int pmode);
 
 #if IS_ENABLED(CONFIG_CPU_FREQ_CBE_PMI)
 extern bool cbe_cpufreq_has_pmi;
+void cbe_cpufreq_pmi_policy_init(struct cpufreq_policy *policy);
+void cbe_cpufreq_pmi_policy_exit(struct cpufreq_policy *policy);
+void cbe_cpufreq_pmi_init(void);
+void cbe_cpufreq_pmi_exit(void);
 #else
 #define cbe_cpufreq_has_pmi (0)
+static inline void cbe_cpufreq_pmi_policy_init(struct cpufreq_policy *policy) {}
+static inline void cbe_cpufreq_pmi_policy_exit(struct cpufreq_policy *policy) {}
+static inline void cbe_cpufreq_pmi_init(void) {}
+static inline void cbe_cpufreq_pmi_exit(void) {}
 #endif
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index 97c8ee4614b7..bc9dd30395c4 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -12,6 +12,7 @@
 #include <linux/timer.h>
 #include <linux/init.h>
 #include <linux/of_platform.h>
+#include <linux/pm_qos.h>
 
 #include <asm/processor.h>
 #include <asm/prom.h>
@@ -24,8 +25,6 @@
 
 #include "ppc_cbe_cpufreq.h"
 
-static u8 pmi_slow_mode_limit[MAX_CBE];
-
 bool cbe_cpufreq_has_pmi = false;
 EXPORT_SYMBOL_GPL(cbe_cpufreq_has_pmi);
 
@@ -65,64 +64,89 @@ EXPORT_SYMBOL_GPL(cbe_cpufreq_set_pmode_pmi);
 
 static void cbe_cpufreq_handle_pmi(pmi_message_t pmi_msg)
 {
+	struct cpufreq_policy *policy;
+	struct dev_pm_qos_request *req;
 	u8 node, slow_mode;
+	int cpu, ret;
 
 	BUG_ON(pmi_msg.type != PMI_TYPE_FREQ_CHANGE);
 
 	node = pmi_msg.data1;
 	slow_mode = pmi_msg.data2;
 
-	pmi_slow_mode_limit[node] = slow_mode;
+	cpu = cbe_node_to_cpu(node);
 
 	pr_debug("cbe_handle_pmi: node: %d max_freq: %d\n", node, slow_mode);
-}
-
-static int pmi_notifier(struct notifier_block *nb,
-				       unsigned long event, void *data)
-{
-	struct cpufreq_policy *policy = data;
-	struct cpufreq_frequency_table *cbe_freqs = policy->freq_table;
-	u8 node;
-
-	/* Should this really be called for CPUFREQ_ADJUST and CPUFREQ_NOTIFY
-	 * policy events?)
-	 */
-	node = cbe_cpu_to_node(policy->cpu);
-
-	pr_debug("got notified, event=%lu, node=%u\n", event, node);
 
-	if (pmi_slow_mode_limit[node] != 0) {
-		pr_debug("limiting node %d to slow mode %d\n",
-			 node, pmi_slow_mode_limit[node]);
+	policy = cpufreq_cpu_get(cpu);
+	if (!policy) {
+		pr_warn("cpufreq policy not found cpu%d\n", cpu);
+		return;
+	}
 
-		cpufreq_verify_within_limits(policy, 0,
+	req = policy->driver_data;
 
-			cbe_freqs[pmi_slow_mode_limit[node]].frequency);
-	}
+	ret = dev_pm_qos_update_request(req,
+			policy->freq_table[slow_mode].frequency);
+	if (ret < 0)
+		pr_warn("Failed to update freq constraint: %d\n", ret);
+	else
+		pr_debug("limiting node %d to slow mode %d\n", node, slow_mode);
 
-	return 0;
+	cpufreq_cpu_put(policy);
 }
 
-static struct notifier_block pmi_notifier_block = {
-	.notifier_call = pmi_notifier,
-};
-
 static struct pmi_handler cbe_pmi_handler = {
 	.type			= PMI_TYPE_FREQ_CHANGE,
 	.handle_pmi_message	= cbe_cpufreq_handle_pmi,
 };
 
+void cbe_cpufreq_pmi_policy_init(struct cpufreq_policy *policy)
+{
+	struct dev_pm_qos_request *req;
+	int ret;
+
+	if (!cbe_cpufreq_has_pmi)
+		return;
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return;
+
+	ret = dev_pm_qos_add_request(get_cpu_device(policy->cpu), req,
+				     DEV_PM_QOS_MAX_FREQUENCY,
+				     policy->freq_table[0].frequency);
+	if (ret < 0) {
+		pr_err("Failed to add freq constraint (%d)\n", ret);
+		kfree(req);
+		return;
+	}
 
+	policy->driver_data = req;
+}
+EXPORT_SYMBOL_GPL(cbe_cpufreq_pmi_policy_init);
 
-static int __init cbe_cpufreq_pmi_init(void)
+void cbe_cpufreq_pmi_policy_exit(struct cpufreq_policy *policy)
 {
-	cbe_cpufreq_has_pmi = pmi_register_handler(&cbe_pmi_handler) == 0;
+	struct dev_pm_qos_request *req = policy->driver_data;
 
-	if (!cbe_cpufreq_has_pmi)
-		return -ENODEV;
+	if (cbe_cpufreq_has_pmi) {
+		dev_pm_qos_remove_request(req);
+		kfree(req);
+	}
+}
+EXPORT_SYMBOL_GPL(cbe_cpufreq_pmi_policy_exit);
 
-	cpufreq_register_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER);
+void cbe_cpufreq_pmi_init(void)
+{
+	if (!pmi_register_handler(&cbe_pmi_handler))
+		cbe_cpufreq_has_pmi = true;
+}
+EXPORT_SYMBOL_GPL(cbe_cpufreq_pmi_init);
 
-	return 0;
+void cbe_cpufreq_pmi_exit(void)
+{
+	pmi_unregister_handler(&cbe_pmi_handler);
+	cbe_cpufreq_has_pmi = false;
 }
-device_initcall(cbe_cpufreq_pmi_init);
+EXPORT_SYMBOL_GPL(cbe_cpufreq_pmi_exit);
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 4b0b50403901..a9ae2f84a4ef 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -20,6 +20,7 @@
 #define LUT_VOLT			GENMASK(11, 0)
 #define LUT_ROW_SIZE			32
 #define CLK_HW_DIV			2
+#define LUT_TURBO_IND			1
 
 /* Register offsets */
 #define REG_ENABLE			0x0
@@ -34,9 +35,12 @@ static int qcom_cpufreq_hw_target_index(struct cpufreq_policy *policy,
 					unsigned int index)
 {
 	void __iomem *perf_state_reg = policy->driver_data;
+	unsigned long freq = policy->freq_table[index].frequency;
 
 	writel_relaxed(index, perf_state_reg);
 
+	arch_set_freq_scale(policy->related_cpus, freq,
+			    policy->cpuinfo.max_freq);
 	return 0;
 }
 
@@ -63,6 +67,7 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
 {
 	void __iomem *perf_state_reg = policy->driver_data;
 	int index;
+	unsigned long freq;
 
 	index = policy->cached_resolved_idx;
 	if (index < 0)
@@ -70,16 +75,19 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
 
 	writel_relaxed(index, perf_state_reg);
 
-	return policy->freq_table[index].frequency;
+	freq = policy->freq_table[index].frequency;
+	arch_set_freq_scale(policy->related_cpus, freq,
+			    policy->cpuinfo.max_freq);
+
+	return freq;
 }
 
 static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
 				    struct cpufreq_policy *policy,
 				    void __iomem *base)
 {
-	u32 data, src, lval, i, core_count, prev_cc = 0, prev_freq = 0, freq;
+	u32 data, src, lval, i, core_count, prev_freq = 0, freq;
 	u32 volt;
-	unsigned int max_cores = cpumask_weight(policy->cpus);
 	struct cpufreq_frequency_table	*table;
 
 	table = kcalloc(LUT_MAX_ENTRIES + 1, sizeof(*table), GFP_KERNEL);
@@ -102,12 +110,12 @@ static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
 		else
 			freq = cpu_hw_rate / 1000;
 
-		if (freq != prev_freq && core_count == max_cores) {
+		if (freq != prev_freq && core_count != LUT_TURBO_IND) {
 			table[i].frequency = freq;
 			dev_pm_opp_add(cpu_dev, freq * 1000, volt);
 			dev_dbg(cpu_dev, "index=%d freq=%d, core_count %d\n", i,
 				freq, core_count);
-		} else {
+		} else if (core_count == LUT_TURBO_IND) {
 			table[i].frequency = CPUFREQ_ENTRY_INVALID;
 		}
 
@@ -115,14 +123,14 @@ static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
 		 * Two of the same frequencies with the same core counts means
 		 * end of table
 		 */
-		if (i > 0 && prev_freq == freq && prev_cc == core_count) {
+		if (i > 0 && prev_freq == freq) {
 			struct cpufreq_frequency_table *prev = &table[i - 1];
 
 			/*
 			 * Only treat the last frequency that might be a boost
 			 * as the boost frequency
 			 */
-			if (prev_cc != max_cores) {
+			if (prev->frequency == CPUFREQ_ENTRY_INVALID) {
 				prev->frequency = prev_freq;
 				prev->flags = CPUFREQ_BOOST_FREQ;
 				dev_pm_opp_add(cpu_dev,	prev_freq * 1000, volt);
@@ -131,7 +139,6 @@ static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
 			break;
 		}
 
-		prev_cc = core_count;
 		prev_freq = freq;
 	}
 
diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
deleted file mode 100644
index dd64dcf89c74..000000000000
--- a/drivers/cpufreq/qcom-cpufreq-kryo.c
+++ /dev/null
@@ -1,249 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2018, The Linux Foundation. All rights reserved.
- */
-
-/*
- * In Certain QCOM SoCs like apq8096 and msm8996 that have KRYO processors,
- * the CPU frequency subset and voltage value of each OPP varies
- * based on the silicon variant in use. Qualcomm Process Voltage Scaling Tables
- * defines the voltage and frequency value based on the msm-id in SMEM
- * and speedbin blown in the efuse combination.
- * The qcom-cpufreq-kryo driver reads the msm-id and efuse value from the SoC
- * to provide the OPP framework with required information.
- * This is used to determine the voltage and frequency value for each OPP of
- * operating-points-v2 table when it is parsed by the OPP framework.
- */
-
-#include <linux/cpu.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/nvmem-consumer.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/pm_opp.h>
-#include <linux/slab.h>
-#include <linux/soc/qcom/smem.h>
-
-#define MSM_ID_SMEM	137
-
-enum _msm_id {
-	MSM8996V3 = 0xF6ul,
-	APQ8096V3 = 0x123ul,
-	MSM8996SG = 0x131ul,
-	APQ8096SG = 0x138ul,
-};
-
-enum _msm8996_version {
-	MSM8996_V3,
-	MSM8996_SG,
-	NUM_OF_MSM8996_VERSIONS,
-};
-
-static struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev;
-
-static enum _msm8996_version qcom_cpufreq_kryo_get_msm_id(void)
-{
-	size_t len;
-	u32 *msm_id;
-	enum _msm8996_version version;
-
-	msm_id = qcom_smem_get(QCOM_SMEM_HOST_ANY, MSM_ID_SMEM, &len);
-	if (IS_ERR(msm_id))
-		return NUM_OF_MSM8996_VERSIONS;
-
-	/* The first 4 bytes are format, next to them is the actual msm-id */
-	msm_id++;
-
-	switch ((enum _msm_id)*msm_id) {
-	case MSM8996V3:
-	case APQ8096V3:
-		version = MSM8996_V3;
-		break;
-	case MSM8996SG:
-	case APQ8096SG:
-		version = MSM8996_SG;
-		break;
-	default:
-		version = NUM_OF_MSM8996_VERSIONS;
-	}
-
-	return version;
-}
-
-static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
-{
-	struct opp_table **opp_tables;
-	enum _msm8996_version msm8996_version;
-	struct nvmem_cell *speedbin_nvmem;
-	struct device_node *np;
-	struct device *cpu_dev;
-	unsigned cpu;
-	u8 *speedbin;
-	u32 versions;
-	size_t len;
-	int ret;
-
-	cpu_dev = get_cpu_device(0);
-	if (!cpu_dev)
-		return -ENODEV;
-
-	msm8996_version = qcom_cpufreq_kryo_get_msm_id();
-	if (NUM_OF_MSM8996_VERSIONS == msm8996_version) {
-		dev_err(cpu_dev, "Not Snapdragon 820/821!");
-		return -ENODEV;
-	}
-
-	np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
-	if (!np)
-		return -ENOENT;
-
-	ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu");
-	if (!ret) {
-		of_node_put(np);
-		return -ENOENT;
-	}
-
-	speedbin_nvmem = of_nvmem_cell_get(np, NULL);
-	of_node_put(np);
-	if (IS_ERR(speedbin_nvmem)) {
-		if (PTR_ERR(speedbin_nvmem) != -EPROBE_DEFER)
-			dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
-				PTR_ERR(speedbin_nvmem));
-		return PTR_ERR(speedbin_nvmem);
-	}
-
-	speedbin = nvmem_cell_read(speedbin_nvmem, &len);
-	nvmem_cell_put(speedbin_nvmem);
-	if (IS_ERR(speedbin))
-		return PTR_ERR(speedbin);
-
-	switch (msm8996_version) {
-	case MSM8996_V3:
-		versions = 1 << (unsigned int)(*speedbin);
-		break;
-	case MSM8996_SG:
-		versions = 1 << ((unsigned int)(*speedbin) + 4);
-		break;
-	default:
-		BUG();
-		break;
-	}
-	kfree(speedbin);
-
-	opp_tables = kcalloc(num_possible_cpus(), sizeof(*opp_tables), GFP_KERNEL);
-	if (!opp_tables)
-		return -ENOMEM;
-
-	for_each_possible_cpu(cpu) {
-		cpu_dev = get_cpu_device(cpu);
-		if (NULL == cpu_dev) {
-			ret = -ENODEV;
-			goto free_opp;
-		}
-
-		opp_tables[cpu] = dev_pm_opp_set_supported_hw(cpu_dev,
-							      &versions, 1);
-		if (IS_ERR(opp_tables[cpu])) {
-			ret = PTR_ERR(opp_tables[cpu]);
-			dev_err(cpu_dev, "Failed to set supported hardware\n");
-			goto free_opp;
-		}
-	}
-
-	cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1,
-							  NULL, 0);
-	if (!IS_ERR(cpufreq_dt_pdev)) {
-		platform_set_drvdata(pdev, opp_tables);
-		return 0;
-	}
-
-	ret = PTR_ERR(cpufreq_dt_pdev);
-	dev_err(cpu_dev, "Failed to register platform device\n");
-
-free_opp:
-	for_each_possible_cpu(cpu) {
-		if (IS_ERR_OR_NULL(opp_tables[cpu]))
-			break;
-		dev_pm_opp_put_supported_hw(opp_tables[cpu]);
-	}
-	kfree(opp_tables);
-
-	return ret;
-}
-
-static int qcom_cpufreq_kryo_remove(struct platform_device *pdev)
-{
-	struct opp_table **opp_tables = platform_get_drvdata(pdev);
-	unsigned int cpu;
-
-	platform_device_unregister(cpufreq_dt_pdev);
-
-	for_each_possible_cpu(cpu)
-		dev_pm_opp_put_supported_hw(opp_tables[cpu]);
-
-	kfree(opp_tables);
-
-	return 0;
-}
-
-static struct platform_driver qcom_cpufreq_kryo_driver = {
-	.probe = qcom_cpufreq_kryo_probe,
-	.remove = qcom_cpufreq_kryo_remove,
-	.driver = {
-		.name = "qcom-cpufreq-kryo",
-	},
-};
-
-static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = {
-	{ .compatible = "qcom,apq8096", },
-	{ .compatible = "qcom,msm8996", },
-	{}
-};
-
-/*
- * Since the driver depends on smem and nvmem drivers, which may
- * return EPROBE_DEFER, all the real activity is done in the probe,
- * which may be defered as well. The init here is only registering
- * the driver and the platform device.
- */
-static int __init qcom_cpufreq_kryo_init(void)
-{
-	struct device_node *np = of_find_node_by_path("/");
-	const struct of_device_id *match;
-	int ret;
-
-	if (!np)
-		return -ENODEV;
-
-	match = of_match_node(qcom_cpufreq_kryo_match_list, np);
-	of_node_put(np);
-	if (!match)
-		return -ENODEV;
-
-	ret = platform_driver_register(&qcom_cpufreq_kryo_driver);
-	if (unlikely(ret < 0))
-		return ret;
-
-	kryo_cpufreq_pdev = platform_device_register_simple(
-		"qcom-cpufreq-kryo", -1, NULL, 0);
-	ret = PTR_ERR_OR_ZERO(kryo_cpufreq_pdev);
-	if (0 == ret)
-		return 0;
-
-	platform_driver_unregister(&qcom_cpufreq_kryo_driver);
-	return ret;
-}
-module_init(qcom_cpufreq_kryo_init);
-
-static void __exit qcom_cpufreq_kryo_exit(void)
-{
-	platform_device_unregister(kryo_cpufreq_pdev);
-	platform_driver_unregister(&qcom_cpufreq_kryo_driver);
-}
-module_exit(qcom_cpufreq_kryo_exit);
-
-MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Kryo CPUfreq driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c
new file mode 100644
index 000000000000..f0d2d5035413
--- /dev/null
+++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+/*
+ * In Certain QCOM SoCs like apq8096 and msm8996 that have KRYO processors,
+ * the CPU frequency subset and voltage value of each OPP varies
+ * based on the silicon variant in use. Qualcomm Process Voltage Scaling Tables
+ * defines the voltage and frequency value based on the msm-id in SMEM
+ * and speedbin blown in the efuse combination.
+ * The qcom-cpufreq-nvmem driver reads the msm-id and efuse value from the SoC
+ * to provide the OPP framework with required information.
+ * This is used to determine the voltage and frequency value for each OPP of
+ * operating-points-v2 table when it is parsed by the OPP framework.
+ */
+
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+#include <linux/soc/qcom/smem.h>
+
+#define MSM_ID_SMEM	137
+
+enum _msm_id {
+	MSM8996V3 = 0xF6ul,
+	APQ8096V3 = 0x123ul,
+	MSM8996SG = 0x131ul,
+	APQ8096SG = 0x138ul,
+};
+
+enum _msm8996_version {
+	MSM8996_V3,
+	MSM8996_SG,
+	NUM_OF_MSM8996_VERSIONS,
+};
+
+struct qcom_cpufreq_drv;
+
+struct qcom_cpufreq_match_data {
+	int (*get_version)(struct device *cpu_dev,
+			   struct nvmem_cell *speedbin_nvmem,
+			   struct qcom_cpufreq_drv *drv);
+	const char **genpd_names;
+};
+
+struct qcom_cpufreq_drv {
+	struct opp_table **opp_tables;
+	struct opp_table **genpd_opp_tables;
+	u32 versions;
+	const struct qcom_cpufreq_match_data *data;
+};
+
+static struct platform_device *cpufreq_dt_pdev, *cpufreq_pdev;
+
+static enum _msm8996_version qcom_cpufreq_get_msm_id(void)
+{
+	size_t len;
+	u32 *msm_id;
+	enum _msm8996_version version;
+
+	msm_id = qcom_smem_get(QCOM_SMEM_HOST_ANY, MSM_ID_SMEM, &len);
+	if (IS_ERR(msm_id))
+		return NUM_OF_MSM8996_VERSIONS;
+
+	/* The first 4 bytes are format, next to them is the actual msm-id */
+	msm_id++;
+
+	switch ((enum _msm_id)*msm_id) {
+	case MSM8996V3:
+	case APQ8096V3:
+		version = MSM8996_V3;
+		break;
+	case MSM8996SG:
+	case APQ8096SG:
+		version = MSM8996_SG;
+		break;
+	default:
+		version = NUM_OF_MSM8996_VERSIONS;
+	}
+
+	return version;
+}
+
+static int qcom_cpufreq_kryo_name_version(struct device *cpu_dev,
+					  struct nvmem_cell *speedbin_nvmem,
+					  struct qcom_cpufreq_drv *drv)
+{
+	size_t len;
+	u8 *speedbin;
+	enum _msm8996_version msm8996_version;
+
+	msm8996_version = qcom_cpufreq_get_msm_id();
+	if (NUM_OF_MSM8996_VERSIONS == msm8996_version) {
+		dev_err(cpu_dev, "Not Snapdragon 820/821!");
+		return -ENODEV;
+	}
+
+	speedbin = nvmem_cell_read(speedbin_nvmem, &len);
+	if (IS_ERR(speedbin))
+		return PTR_ERR(speedbin);
+
+	switch (msm8996_version) {
+	case MSM8996_V3:
+		drv->versions = 1 << (unsigned int)(*speedbin);
+		break;
+	case MSM8996_SG:
+		drv->versions = 1 << ((unsigned int)(*speedbin) + 4);
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	kfree(speedbin);
+	return 0;
+}
+
+static const struct qcom_cpufreq_match_data match_data_kryo = {
+	.get_version = qcom_cpufreq_kryo_name_version,
+};
+
+static const char *qcs404_genpd_names[] = { "cpr", NULL };
+
+static const struct qcom_cpufreq_match_data match_data_qcs404 = {
+	.genpd_names = qcs404_genpd_names,
+};
+
+static int qcom_cpufreq_probe(struct platform_device *pdev)
+{
+	struct qcom_cpufreq_drv *drv;
+	struct nvmem_cell *speedbin_nvmem;
+	struct device_node *np;
+	struct device *cpu_dev;
+	unsigned cpu;
+	const struct of_device_id *match;
+	int ret;
+
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev)
+		return -ENODEV;
+
+	np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
+	if (!np)
+		return -ENOENT;
+
+	ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu");
+	if (!ret) {
+		of_node_put(np);
+		return -ENOENT;
+	}
+
+	drv = kzalloc(sizeof(*drv), GFP_KERNEL);
+	if (!drv)
+		return -ENOMEM;
+
+	match = pdev->dev.platform_data;
+	drv->data = match->data;
+	if (!drv->data) {
+		ret = -ENODEV;
+		goto free_drv;
+	}
+
+	if (drv->data->get_version) {
+		speedbin_nvmem = of_nvmem_cell_get(np, NULL);
+		if (IS_ERR(speedbin_nvmem)) {
+			if (PTR_ERR(speedbin_nvmem) != -EPROBE_DEFER)
+				dev_err(cpu_dev,
+					"Could not get nvmem cell: %ld\n",
+					PTR_ERR(speedbin_nvmem));
+			ret = PTR_ERR(speedbin_nvmem);
+			goto free_drv;
+		}
+
+		ret = drv->data->get_version(cpu_dev, speedbin_nvmem, drv);
+		if (ret) {
+			nvmem_cell_put(speedbin_nvmem);
+			goto free_drv;
+		}
+		nvmem_cell_put(speedbin_nvmem);
+	}
+	of_node_put(np);
+
+	drv->opp_tables = kcalloc(num_possible_cpus(), sizeof(*drv->opp_tables),
+				  GFP_KERNEL);
+	if (!drv->opp_tables) {
+		ret = -ENOMEM;
+		goto free_drv;
+	}
+
+	drv->genpd_opp_tables = kcalloc(num_possible_cpus(),
+					sizeof(*drv->genpd_opp_tables),
+					GFP_KERNEL);
+	if (!drv->genpd_opp_tables) {
+		ret = -ENOMEM;
+		goto free_opp;
+	}
+
+	for_each_possible_cpu(cpu) {
+		cpu_dev = get_cpu_device(cpu);
+		if (NULL == cpu_dev) {
+			ret = -ENODEV;
+			goto free_genpd_opp;
+		}
+
+		if (drv->data->get_version) {
+			drv->opp_tables[cpu] =
+				dev_pm_opp_set_supported_hw(cpu_dev,
+							    &drv->versions, 1);
+			if (IS_ERR(drv->opp_tables[cpu])) {
+				ret = PTR_ERR(drv->opp_tables[cpu]);
+				dev_err(cpu_dev,
+					"Failed to set supported hardware\n");
+				goto free_genpd_opp;
+			}
+		}
+
+		if (drv->data->genpd_names) {
+			drv->genpd_opp_tables[cpu] =
+				dev_pm_opp_attach_genpd(cpu_dev,
+							drv->data->genpd_names,
+							NULL);
+			if (IS_ERR(drv->genpd_opp_tables[cpu])) {
+				ret = PTR_ERR(drv->genpd_opp_tables[cpu]);
+				if (ret != -EPROBE_DEFER)
+					dev_err(cpu_dev,
+						"Could not attach to pm_domain: %d\n",
+						ret);
+				goto free_genpd_opp;
+			}
+		}
+	}
+
+	cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1,
+							  NULL, 0);
+	if (!IS_ERR(cpufreq_dt_pdev)) {
+		platform_set_drvdata(pdev, drv);
+		return 0;
+	}
+
+	ret = PTR_ERR(cpufreq_dt_pdev);
+	dev_err(cpu_dev, "Failed to register platform device\n");
+
+free_genpd_opp:
+	for_each_possible_cpu(cpu) {
+		if (IS_ERR_OR_NULL(drv->genpd_opp_tables[cpu]))
+			break;
+		dev_pm_opp_detach_genpd(drv->genpd_opp_tables[cpu]);
+	}
+	kfree(drv->genpd_opp_tables);
+free_opp:
+	for_each_possible_cpu(cpu) {
+		if (IS_ERR_OR_NULL(drv->opp_tables[cpu]))
+			break;
+		dev_pm_opp_put_supported_hw(drv->opp_tables[cpu]);
+	}
+	kfree(drv->opp_tables);
+free_drv:
+	kfree(drv);
+
+	return ret;
+}
+
+static int qcom_cpufreq_remove(struct platform_device *pdev)
+{
+	struct qcom_cpufreq_drv *drv = platform_get_drvdata(pdev);
+	unsigned int cpu;
+
+	platform_device_unregister(cpufreq_dt_pdev);
+
+	for_each_possible_cpu(cpu) {
+		if (drv->opp_tables[cpu])
+			dev_pm_opp_put_supported_hw(drv->opp_tables[cpu]);
+		if (drv->genpd_opp_tables[cpu])
+			dev_pm_opp_detach_genpd(drv->genpd_opp_tables[cpu]);
+	}
+
+	kfree(drv->opp_tables);
+	kfree(drv->genpd_opp_tables);
+	kfree(drv);
+
+	return 0;
+}
+
+static struct platform_driver qcom_cpufreq_driver = {
+	.probe = qcom_cpufreq_probe,
+	.remove = qcom_cpufreq_remove,
+	.driver = {
+		.name = "qcom-cpufreq-nvmem",
+	},
+};
+
+static const struct of_device_id qcom_cpufreq_match_list[] __initconst = {
+	{ .compatible = "qcom,apq8096", .data = &match_data_kryo },
+	{ .compatible = "qcom,msm8996", .data = &match_data_kryo },
+	{ .compatible = "qcom,qcs404", .data = &match_data_qcs404 },
+	{},
+};
+
+/*
+ * Since the driver depends on smem and nvmem drivers, which may
+ * return EPROBE_DEFER, all the real activity is done in the probe,
+ * which may be defered as well. The init here is only registering
+ * the driver and the platform device.
+ */
+static int __init qcom_cpufreq_init(void)
+{
+	struct device_node *np = of_find_node_by_path("/");
+	const struct of_device_id *match;
+	int ret;
+
+	if (!np)
+		return -ENODEV;
+
+	match = of_match_node(qcom_cpufreq_match_list, np);
+	of_node_put(np);
+	if (!match)
+		return -ENODEV;
+
+	ret = platform_driver_register(&qcom_cpufreq_driver);
+	if (unlikely(ret < 0))
+		return ret;
+
+	cpufreq_pdev = platform_device_register_data(NULL, "qcom-cpufreq-nvmem",
+						     -1, match, sizeof(*match));
+	ret = PTR_ERR_OR_ZERO(cpufreq_pdev);
+	if (0 == ret)
+		return 0;
+
+	platform_driver_unregister(&qcom_cpufreq_driver);
+	return ret;
+}
+module_init(qcom_cpufreq_init);
+
+static void __exit qcom_cpufreq_exit(void)
+{
+	platform_device_unregister(cpufreq_pdev);
+	platform_driver_unregister(&qcom_cpufreq_driver);
+}
+module_exit(qcom_cpufreq_exit);
+
+MODULE_DESCRIPTION("Qualcomm Technologies, Inc. CPUfreq driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
new file mode 100644
index 000000000000..eca32e443716
--- /dev/null
+++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Allwinner CPUFreq nvmem based driver
+ *
+ * The sun50i-cpufreq-nvmem driver reads the efuse value from the SoC to
+ * provide the OPP framework with required information.
+ *
+ * Copyright (C) 2019 Yangtao Li <tiny.windzz@gmail.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+
+#define MAX_NAME_LEN	7
+
+#define NVMEM_MASK	0x7
+#define NVMEM_SHIFT	5
+
+static struct platform_device *cpufreq_dt_pdev, *sun50i_cpufreq_pdev;
+
+/**
+ * sun50i_cpufreq_get_efuse() - Parse and return efuse value present on SoC
+ * @versions: Set to the value parsed from efuse
+ *
+ * Returns 0 if success.
+ */
+static int sun50i_cpufreq_get_efuse(u32 *versions)
+{
+	struct nvmem_cell *speedbin_nvmem;
+	struct device_node *np;
+	struct device *cpu_dev;
+	u32 *speedbin, efuse_value;
+	size_t len;
+	int ret;
+
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev)
+		return -ENODEV;
+
+	np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
+	if (!np)
+		return -ENOENT;
+
+	ret = of_device_is_compatible(np,
+				      "allwinner,sun50i-h6-operating-points");
+	if (!ret) {
+		of_node_put(np);
+		return -ENOENT;
+	}
+
+	speedbin_nvmem = of_nvmem_cell_get(np, NULL);
+	of_node_put(np);
+	if (IS_ERR(speedbin_nvmem)) {
+		if (PTR_ERR(speedbin_nvmem) != -EPROBE_DEFER)
+			pr_err("Could not get nvmem cell: %ld\n",
+			       PTR_ERR(speedbin_nvmem));
+		return PTR_ERR(speedbin_nvmem);
+	}
+
+	speedbin = nvmem_cell_read(speedbin_nvmem, &len);
+	nvmem_cell_put(speedbin_nvmem);
+	if (IS_ERR(speedbin))
+		return PTR_ERR(speedbin);
+
+	efuse_value = (*speedbin >> NVMEM_SHIFT) & NVMEM_MASK;
+	switch (efuse_value) {
+	case 0b0001:
+		*versions = 1;
+		break;
+	case 0b0011:
+		*versions = 2;
+		break;
+	default:
+		/*
+		 * For other situations, we treat it as bin0.
+		 * This vf table can be run for any good cpu.
+		 */
+		*versions = 0;
+		break;
+	}
+
+	kfree(speedbin);
+	return 0;
+};
+
+static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev)
+{
+	struct opp_table **opp_tables;
+	char name[MAX_NAME_LEN];
+	unsigned int cpu;
+	u32 speed = 0;
+	int ret;
+
+	opp_tables = kcalloc(num_possible_cpus(), sizeof(*opp_tables),
+			     GFP_KERNEL);
+	if (!opp_tables)
+		return -ENOMEM;
+
+	ret = sun50i_cpufreq_get_efuse(&speed);
+	if (ret)
+		return ret;
+
+	snprintf(name, MAX_NAME_LEN, "speed%d", speed);
+
+	for_each_possible_cpu(cpu) {
+		struct device *cpu_dev = get_cpu_device(cpu);
+
+		if (!cpu_dev) {
+			ret = -ENODEV;
+			goto free_opp;
+		}
+
+		opp_tables[cpu] = dev_pm_opp_set_prop_name(cpu_dev, name);
+		if (IS_ERR(opp_tables[cpu])) {
+			ret = PTR_ERR(opp_tables[cpu]);
+			pr_err("Failed to set prop name\n");
+			goto free_opp;
+		}
+	}
+
+	cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1,
+							  NULL, 0);
+	if (!IS_ERR(cpufreq_dt_pdev)) {
+		platform_set_drvdata(pdev, opp_tables);
+		return 0;
+	}
+
+	ret = PTR_ERR(cpufreq_dt_pdev);
+	pr_err("Failed to register platform device\n");
+
+free_opp:
+	for_each_possible_cpu(cpu) {
+		if (IS_ERR_OR_NULL(opp_tables[cpu]))
+			break;
+		dev_pm_opp_put_prop_name(opp_tables[cpu]);
+	}
+	kfree(opp_tables);
+
+	return ret;
+}
+
+static int sun50i_cpufreq_nvmem_remove(struct platform_device *pdev)
+{
+	struct opp_table **opp_tables = platform_get_drvdata(pdev);
+	unsigned int cpu;
+
+	platform_device_unregister(cpufreq_dt_pdev);
+
+	for_each_possible_cpu(cpu)
+		dev_pm_opp_put_prop_name(opp_tables[cpu]);
+
+	kfree(opp_tables);
+
+	return 0;
+}
+
+static struct platform_driver sun50i_cpufreq_driver = {
+	.probe = sun50i_cpufreq_nvmem_probe,
+	.remove = sun50i_cpufreq_nvmem_remove,
+	.driver = {
+		.name = "sun50i-cpufreq-nvmem",
+	},
+};
+
+static const struct of_device_id sun50i_cpufreq_match_list[] = {
+	{ .compatible = "allwinner,sun50i-h6" },
+	{}
+};
+
+static const struct of_device_id *sun50i_cpufreq_match_node(void)
+{
+	const struct of_device_id *match;
+	struct device_node *np;
+
+	np = of_find_node_by_path("/");
+	match = of_match_node(sun50i_cpufreq_match_list, np);
+	of_node_put(np);
+
+	return match;
+}
+
+/*
+ * Since the driver depends on nvmem drivers, which may return EPROBE_DEFER,
+ * all the real activity is done in the probe, which may be defered as well.
+ * The init here is only registering the driver and the platform device.
+ */
+static int __init sun50i_cpufreq_init(void)
+{
+	const struct of_device_id *match;
+	int ret;
+
+	match = sun50i_cpufreq_match_node();
+	if (!match)
+		return -ENODEV;
+
+	ret = platform_driver_register(&sun50i_cpufreq_driver);
+	if (unlikely(ret < 0))
+		return ret;
+
+	sun50i_cpufreq_pdev =
+		platform_device_register_simple("sun50i-cpufreq-nvmem",
+						-1, NULL, 0);
+	ret = PTR_ERR_OR_ZERO(sun50i_cpufreq_pdev);
+	if (ret == 0)
+		return 0;
+
+	platform_driver_unregister(&sun50i_cpufreq_driver);
+	return ret;
+}
+module_init(sun50i_cpufreq_init);
+
+static void __exit sun50i_cpufreq_exit(void)
+{
+	platform_device_unregister(sun50i_cpufreq_pdev);
+	platform_driver_unregister(&sun50i_cpufreq_driver);
+}
+module_exit(sun50i_cpufreq_exit);
+
+MODULE_DESCRIPTION("Sun50i-h6 cpufreq driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
index 2ad1ae17932d..aeaa883a8c9d 100644
--- a/drivers/cpufreq/ti-cpufreq.c
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -77,6 +77,7 @@ static unsigned long dra7_efuse_xlate(struct ti_cpufreq_data *opp_data,
 	case DRA7_EFUSE_HAS_ALL_MPU_OPP:
 	case DRA7_EFUSE_HAS_HIGH_MPU_OPP:
 		calculated_efuse |= DRA7_EFUSE_HIGH_MPU_OPP;
+		/* Fall through */
 	case DRA7_EFUSE_HAS_OD_MPU_OPP:
 		calculated_efuse |= DRA7_EFUSE_OD_MPU_OPP;
 	}
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index a4ac31e4a58c..88727b7c0d59 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -33,6 +33,17 @@ config CPU_IDLE_GOV_TEO
 	  Some workloads benefit from using it and it generally should be safe
 	  to use.  Say Y here if you are not happy with the alternatives.
 
+config CPU_IDLE_GOV_HALTPOLL
+	bool "Haltpoll governor (for virtualized systems)"
+	depends on KVM_GUEST
+	help
+	  This governor implements haltpoll idle state selection, to be
+	  used in conjunction with the haltpoll cpuidle driver, allowing
+	  for polling for a certain amount of time before entering idle
+	  state.
+
+	  Some virtualized workloads benefit from using it.
+
 config DT_IDLE_STATES
 	bool
 
@@ -51,6 +62,15 @@ depends on PPC
 source "drivers/cpuidle/Kconfig.powerpc"
 endmenu
 
+config HALTPOLL_CPUIDLE
+       tristate "Halt poll cpuidle driver"
+       depends on X86 && KVM_GUEST
+       default y
+       help
+         This option enables halt poll cpuidle driver, which allows to poll
+         before halting in the guest (more efficient than polling in the
+         host via halt_poll_ns for some scenarios).
+
 endif
 
 config ARCH_NEEDS_CPU_IDLE_COUPLED
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index 40d016339b29..ee70d5cc5b99 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -7,6 +7,7 @@ obj-y += cpuidle.o driver.o governor.o sysfs.o governors/
 obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
 obj-$(CONFIG_DT_IDLE_STATES)		  += dt_idle_states.o
 obj-$(CONFIG_ARCH_HAS_CPU_RELAX)	  += poll_state.o
+obj-$(CONFIG_HALTPOLL_CPUIDLE)		  += cpuidle-haltpoll.o
 
 ##################################################################################
 # ARM SoC drivers
diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c
new file mode 100644
index 000000000000..932390b028f1
--- /dev/null
+++ b/drivers/cpuidle/cpuidle-haltpoll.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * cpuidle driver for haltpoll governor.
+ *
+ * Copyright 2019 Red Hat, Inc. and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Authors: Marcelo Tosatti <mtosatti@redhat.com>
+ */
+
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/cpuidle.h>
+#include <linux/module.h>
+#include <linux/sched/idle.h>
+#include <linux/kvm_para.h>
+#include <linux/cpuidle_haltpoll.h>
+
+static struct cpuidle_device __percpu *haltpoll_cpuidle_devices;
+static enum cpuhp_state haltpoll_hp_state;
+
+static int default_enter_idle(struct cpuidle_device *dev,
+			      struct cpuidle_driver *drv, int index)
+{
+	if (current_clr_polling_and_test()) {
+		local_irq_enable();
+		return index;
+	}
+	default_idle();
+	return index;
+}
+
+static struct cpuidle_driver haltpoll_driver = {
+	.name = "haltpoll",
+	.governor = "haltpoll",
+	.states = {
+		{ /* entry 0 is for polling */ },
+		{
+			.enter			= default_enter_idle,
+			.exit_latency		= 1,
+			.target_residency	= 1,
+			.power_usage		= -1,
+			.name			= "haltpoll idle",
+			.desc			= "default architecture idle",
+		},
+	},
+	.safe_state_index = 0,
+	.state_count = 2,
+};
+
+static int haltpoll_cpu_online(unsigned int cpu)
+{
+	struct cpuidle_device *dev;
+
+	dev = per_cpu_ptr(haltpoll_cpuidle_devices, cpu);
+	if (!dev->registered) {
+		dev->cpu = cpu;
+		if (cpuidle_register_device(dev)) {
+			pr_notice("cpuidle_register_device %d failed!\n", cpu);
+			return -EIO;
+		}
+		arch_haltpoll_enable(cpu);
+	}
+
+	return 0;
+}
+
+static int haltpoll_cpu_offline(unsigned int cpu)
+{
+	struct cpuidle_device *dev;
+
+	dev = per_cpu_ptr(haltpoll_cpuidle_devices, cpu);
+	if (dev->registered) {
+		arch_haltpoll_disable(cpu);
+		cpuidle_unregister_device(dev);
+	}
+
+	return 0;
+}
+
+static void haltpoll_uninit(void)
+{
+	if (haltpoll_hp_state)
+		cpuhp_remove_state(haltpoll_hp_state);
+	cpuidle_unregister_driver(&haltpoll_driver);
+
+	free_percpu(haltpoll_cpuidle_devices);
+	haltpoll_cpuidle_devices = NULL;
+}
+
+static int __init haltpoll_init(void)
+{
+	int ret;
+	struct cpuidle_driver *drv = &haltpoll_driver;
+
+	cpuidle_poll_state_init(drv);
+
+	if (!kvm_para_available() ||
+		!kvm_para_has_hint(KVM_HINTS_REALTIME))
+		return -ENODEV;
+
+	ret = cpuidle_register_driver(drv);
+	if (ret < 0)
+		return ret;
+
+	haltpoll_cpuidle_devices = alloc_percpu(struct cpuidle_device);
+	if (haltpoll_cpuidle_devices == NULL) {
+		cpuidle_unregister_driver(drv);
+		return -ENOMEM;
+	}
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "cpuidle/haltpoll:online",
+				haltpoll_cpu_online, haltpoll_cpu_offline);
+	if (ret < 0) {
+		haltpoll_uninit();
+	} else {
+		haltpoll_hp_state = ret;
+		ret = 0;
+	}
+
+	return ret;
+}
+
+static void __exit haltpoll_exit(void)
+{
+	haltpoll_uninit();
+}
+
+module_init(haltpoll_init);
+module_exit(haltpoll_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Marcelo Tosatti <mtosatti@redhat.com>");
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 0f4b7c45df3e..0895b988fa92 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -362,6 +362,36 @@ void cpuidle_reflect(struct cpuidle_device *dev, int index)
 }
 
 /**
+ * cpuidle_poll_time - return amount of time to poll for,
+ * governors can override dev->poll_limit_ns if necessary
+ *
+ * @drv:   the cpuidle driver tied with the cpu
+ * @dev:   the cpuidle device
+ *
+ */
+u64 cpuidle_poll_time(struct cpuidle_driver *drv,
+		      struct cpuidle_device *dev)
+{
+	int i;
+	u64 limit_ns;
+
+	if (dev->poll_limit_ns)
+		return dev->poll_limit_ns;
+
+	limit_ns = TICK_NSEC;
+	for (i = 1; i < drv->state_count; i++) {
+		if (drv->states[i].disabled || dev->states_usage[i].disable)
+			continue;
+
+		limit_ns = (u64)drv->states[i].target_residency * NSEC_PER_USEC;
+	}
+
+	dev->poll_limit_ns = limit_ns;
+
+	return dev->poll_limit_ns;
+}
+
+/**
  * cpuidle_install_idle_handler - installs the cpuidle idle loop handler
  */
 void cpuidle_install_idle_handler(void)
diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h
index d6613101af92..9f336af17fa6 100644
--- a/drivers/cpuidle/cpuidle.h
+++ b/drivers/cpuidle/cpuidle.h
@@ -9,6 +9,7 @@
 /* For internal use only */
 extern char param_governor[];
 extern struct cpuidle_governor *cpuidle_curr_governor;
+extern struct cpuidle_governor *cpuidle_prev_governor;
 extern struct list_head cpuidle_governors;
 extern struct list_head cpuidle_detected_devices;
 extern struct mutex cpuidle_lock;
@@ -22,6 +23,7 @@ extern void cpuidle_install_idle_handler(void);
 extern void cpuidle_uninstall_idle_handler(void);
 
 /* governors */
+extern struct cpuidle_governor *cpuidle_find_governor(const char *str);
 extern int cpuidle_switch_governor(struct cpuidle_governor *gov);
 
 /* sysfs */
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index dc32f34e68d9..80c1a830d991 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -254,12 +254,25 @@ static void __cpuidle_unregister_driver(struct cpuidle_driver *drv)
  */
 int cpuidle_register_driver(struct cpuidle_driver *drv)
 {
+	struct cpuidle_governor *gov;
 	int ret;
 
 	spin_lock(&cpuidle_driver_lock);
 	ret = __cpuidle_register_driver(drv);
 	spin_unlock(&cpuidle_driver_lock);
 
+	if (!ret && !strlen(param_governor) && drv->governor &&
+	    (cpuidle_get_driver() == drv)) {
+		mutex_lock(&cpuidle_lock);
+		gov = cpuidle_find_governor(drv->governor);
+		if (gov) {
+			cpuidle_prev_governor = cpuidle_curr_governor;
+			if (cpuidle_switch_governor(gov) < 0)
+				cpuidle_prev_governor = NULL;
+		}
+		mutex_unlock(&cpuidle_lock);
+	}
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(cpuidle_register_driver);
@@ -274,9 +287,21 @@ EXPORT_SYMBOL_GPL(cpuidle_register_driver);
  */
 void cpuidle_unregister_driver(struct cpuidle_driver *drv)
 {
+	bool enabled = (cpuidle_get_driver() == drv);
+
 	spin_lock(&cpuidle_driver_lock);
 	__cpuidle_unregister_driver(drv);
 	spin_unlock(&cpuidle_driver_lock);
+
+	if (!enabled)
+		return;
+
+	mutex_lock(&cpuidle_lock);
+	if (cpuidle_prev_governor) {
+		if (!cpuidle_switch_governor(cpuidle_prev_governor))
+			cpuidle_prev_governor = NULL;
+	}
+	mutex_unlock(&cpuidle_lock);
 }
 EXPORT_SYMBOL_GPL(cpuidle_unregister_driver);
 
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index 2e3e14192bee..e9801f26c732 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -20,14 +20,15 @@ char param_governor[CPUIDLE_NAME_LEN];
 
 LIST_HEAD(cpuidle_governors);
 struct cpuidle_governor *cpuidle_curr_governor;
+struct cpuidle_governor *cpuidle_prev_governor;
 
 /**
- * __cpuidle_find_governor - finds a governor of the specified name
+ * cpuidle_find_governor - finds a governor of the specified name
  * @str: the name
  *
  * Must be called with cpuidle_lock acquired.
  */
-static struct cpuidle_governor * __cpuidle_find_governor(const char *str)
+struct cpuidle_governor *cpuidle_find_governor(const char *str)
 {
 	struct cpuidle_governor *gov;
 
@@ -87,7 +88,7 @@ int cpuidle_register_governor(struct cpuidle_governor *gov)
 		return -ENODEV;
 
 	mutex_lock(&cpuidle_lock);
-	if (__cpuidle_find_governor(gov->name) == NULL) {
+	if (cpuidle_find_governor(gov->name) == NULL) {
 		ret = 0;
 		list_add_tail(&gov->governor_list, &cpuidle_governors);
 		if (!cpuidle_curr_governor ||
diff --git a/drivers/cpuidle/governors/Makefile b/drivers/cpuidle/governors/Makefile
index 42f44cc610dd..63abb5393a4d 100644
--- a/drivers/cpuidle/governors/Makefile
+++ b/drivers/cpuidle/governors/Makefile
@@ -6,3 +6,4 @@
 obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o
 obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o
 obj-$(CONFIG_CPU_IDLE_GOV_TEO) += teo.o
+obj-$(CONFIG_CPU_IDLE_GOV_HALTPOLL) += haltpoll.o
diff --git a/drivers/cpuidle/governors/haltpoll.c b/drivers/cpuidle/governors/haltpoll.c
new file mode 100644
index 000000000000..7a703d2e0064
--- /dev/null
+++ b/drivers/cpuidle/governors/haltpoll.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * haltpoll.c - haltpoll idle governor
+ *
+ * Copyright 2019 Red Hat, Inc. and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Authors: Marcelo Tosatti <mtosatti@redhat.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/cpuidle.h>
+#include <linux/time.h>
+#include <linux/ktime.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/kvm_para.h>
+
+static unsigned int guest_halt_poll_ns __read_mostly = 200000;
+module_param(guest_halt_poll_ns, uint, 0644);
+
+/* division factor to shrink halt_poll_ns */
+static unsigned int guest_halt_poll_shrink __read_mostly = 2;
+module_param(guest_halt_poll_shrink, uint, 0644);
+
+/* multiplication factor to grow per-cpu poll_limit_ns */
+static unsigned int guest_halt_poll_grow __read_mostly = 2;
+module_param(guest_halt_poll_grow, uint, 0644);
+
+/* value in us to start growing per-cpu halt_poll_ns */
+static unsigned int guest_halt_poll_grow_start __read_mostly = 50000;
+module_param(guest_halt_poll_grow_start, uint, 0644);
+
+/* allow shrinking guest halt poll */
+static bool guest_halt_poll_allow_shrink __read_mostly = true;
+module_param(guest_halt_poll_allow_shrink, bool, 0644);
+
+/**
+ * haltpoll_select - selects the next idle state to enter
+ * @drv: cpuidle driver containing state data
+ * @dev: the CPU
+ * @stop_tick: indication on whether or not to stop the tick
+ */
+static int haltpoll_select(struct cpuidle_driver *drv,
+			   struct cpuidle_device *dev,
+			   bool *stop_tick)
+{
+	int latency_req = cpuidle_governor_latency_req(dev->cpu);
+
+	if (!drv->state_count || latency_req == 0) {
+		*stop_tick = false;
+		return 0;
+	}
+
+	if (dev->poll_limit_ns == 0)
+		return 1;
+
+	/* Last state was poll? */
+	if (dev->last_state_idx == 0) {
+		/* Halt if no event occurred on poll window */
+		if (dev->poll_time_limit == true)
+			return 1;
+
+		*stop_tick = false;
+		/* Otherwise, poll again */
+		return 0;
+	}
+
+	*stop_tick = false;
+	/* Last state was halt: poll */
+	return 0;
+}
+
+static void adjust_poll_limit(struct cpuidle_device *dev, unsigned int block_us)
+{
+	unsigned int val;
+	u64 block_ns = block_us*NSEC_PER_USEC;
+
+	/* Grow cpu_halt_poll_us if
+	 * cpu_halt_poll_us < block_ns < guest_halt_poll_us
+	 */
+	if (block_ns > dev->poll_limit_ns && block_ns <= guest_halt_poll_ns) {
+		val = dev->poll_limit_ns * guest_halt_poll_grow;
+
+		if (val < guest_halt_poll_grow_start)
+			val = guest_halt_poll_grow_start;
+		if (val > guest_halt_poll_ns)
+			val = guest_halt_poll_ns;
+
+		dev->poll_limit_ns = val;
+	} else if (block_ns > guest_halt_poll_ns &&
+		   guest_halt_poll_allow_shrink) {
+		unsigned int shrink = guest_halt_poll_shrink;
+
+		val = dev->poll_limit_ns;
+		if (shrink == 0)
+			val = 0;
+		else
+			val /= shrink;
+		dev->poll_limit_ns = val;
+	}
+}
+
+/**
+ * haltpoll_reflect - update variables and update poll time
+ * @dev: the CPU
+ * @index: the index of actual entered state
+ */
+static void haltpoll_reflect(struct cpuidle_device *dev, int index)
+{
+	dev->last_state_idx = index;
+
+	if (index != 0)
+		adjust_poll_limit(dev, dev->last_residency);
+}
+
+/**
+ * haltpoll_enable_device - scans a CPU's states and does setup
+ * @drv: cpuidle driver
+ * @dev: the CPU
+ */
+static int haltpoll_enable_device(struct cpuidle_driver *drv,
+				  struct cpuidle_device *dev)
+{
+	dev->poll_limit_ns = 0;
+
+	return 0;
+}
+
+static struct cpuidle_governor haltpoll_governor = {
+	.name =			"haltpoll",
+	.rating =		9,
+	.enable =		haltpoll_enable_device,
+	.select =		haltpoll_select,
+	.reflect =		haltpoll_reflect,
+};
+
+static int __init init_haltpoll(void)
+{
+	if (kvm_para_available())
+		return cpuidle_register_governor(&haltpoll_governor);
+
+	return 0;
+}
+
+postcore_initcall(init_haltpoll);
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index f0dddc66af26..428eeb832fe7 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -38,7 +38,6 @@ struct ladder_device_state {
 
 struct ladder_device {
 	struct ladder_device_state states[CPUIDLE_STATE_MAX];
-	int last_state_idx;
 };
 
 static DEFINE_PER_CPU(struct ladder_device, ladder_devices);
@@ -49,12 +48,13 @@ static DEFINE_PER_CPU(struct ladder_device, ladder_devices);
  * @old_idx: the current state index
  * @new_idx: the new target state index
  */
-static inline void ladder_do_selection(struct ladder_device *ldev,
+static inline void ladder_do_selection(struct cpuidle_device *dev,
+				       struct ladder_device *ldev,
 				       int old_idx, int new_idx)
 {
 	ldev->states[old_idx].stats.promotion_count = 0;
 	ldev->states[old_idx].stats.demotion_count = 0;
-	ldev->last_state_idx = new_idx;
+	dev->last_state_idx = new_idx;
 }
 
 /**
@@ -68,13 +68,13 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 {
 	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	struct ladder_device_state *last_state;
-	int last_residency, last_idx = ldev->last_state_idx;
+	int last_residency, last_idx = dev->last_state_idx;
 	int first_idx = drv->states[0].flags & CPUIDLE_FLAG_POLLING ? 1 : 0;
 	int latency_req = cpuidle_governor_latency_req(dev->cpu);
 
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0)) {
-		ladder_do_selection(ldev, last_idx, 0);
+		ladder_do_selection(dev, ldev, last_idx, 0);
 		return 0;
 	}
 
@@ -91,7 +91,7 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 		last_state->stats.promotion_count++;
 		last_state->stats.demotion_count = 0;
 		if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) {
-			ladder_do_selection(ldev, last_idx, last_idx + 1);
+			ladder_do_selection(dev, ldev, last_idx, last_idx + 1);
 			return last_idx + 1;
 		}
 	}
@@ -107,7 +107,7 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 			if (drv->states[i].exit_latency <= latency_req)
 				break;
 		}
-		ladder_do_selection(ldev, last_idx, i);
+		ladder_do_selection(dev, ldev, last_idx, i);
 		return i;
 	}
 
@@ -116,7 +116,7 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 		last_state->stats.demotion_count++;
 		last_state->stats.promotion_count = 0;
 		if (last_state->stats.demotion_count >= last_state->threshold.demotion_count) {
-			ladder_do_selection(ldev, last_idx, last_idx - 1);
+			ladder_do_selection(dev, ldev, last_idx, last_idx - 1);
 			return last_idx - 1;
 		}
 	}
@@ -139,7 +139,7 @@ static int ladder_enable_device(struct cpuidle_driver *drv,
 	struct ladder_device_state *lstate;
 	struct cpuidle_state *state;
 
-	ldev->last_state_idx = first_idx;
+	dev->last_state_idx = first_idx;
 
 	for (i = first_idx; i < drv->state_count; i++) {
 		state = &drv->states[i];
@@ -167,9 +167,8 @@ static int ladder_enable_device(struct cpuidle_driver *drv,
  */
 static void ladder_reflect(struct cpuidle_device *dev, int index)
 {
-	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	if (index > 0)
-		ldev->last_state_idx = index;
+		dev->last_state_idx = index;
 }
 
 static struct cpuidle_governor ladder_governor = {
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index e9a28c7846d6..e5a5d0c8d66b 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -117,7 +117,6 @@
  */
 
 struct menu_device {
-	int		last_state_idx;
 	int             needs_update;
 	int             tick_wakeup;
 
@@ -302,9 +301,10 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	     !drv->states[0].disabled && !dev->states_usage[0].disable)) {
 		/*
 		 * In this case state[0] will be used no matter what, so return
-		 * it right away and keep the tick running.
+		 * it right away and keep the tick running if state[0] is a
+		 * polling one.
 		 */
-		*stop_tick = false;
+		*stop_tick = !(drv->states[0].flags & CPUIDLE_FLAG_POLLING);
 		return 0;
 	}
 
@@ -395,16 +395,9 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 
 			return idx;
 		}
-		if (s->exit_latency > latency_req) {
-			/*
-			 * If we break out of the loop for latency reasons, use
-			 * the target residency of the selected state as the
-			 * expected idle duration so that the tick is retained
-			 * as long as that target residency is low enough.
-			 */
-			predicted_us = drv->states[idx].target_residency;
+		if (s->exit_latency > latency_req)
 			break;
-		}
+
 		idx = i;
 	}
 
@@ -455,7 +448,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
 
-	data->last_state_idx = index;
+	dev->last_state_idx = index;
 	data->needs_update = 1;
 	data->tick_wakeup = tick_nohz_idle_got_tick();
 }
@@ -468,7 +461,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index)
 static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
-	int last_idx = data->last_state_idx;
+	int last_idx = dev->last_state_idx;
 	struct cpuidle_state *target = &drv->states[last_idx];
 	unsigned int measured_us;
 	unsigned int new_factor;
diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c
index 7d05efdbd3c6..b5a0e498f798 100644
--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -96,7 +96,6 @@ struct teo_idle_state {
  * @time_span_ns: Time between idle state selection and post-wakeup update.
  * @sleep_length_ns: Time till the closest timer event (at the selection time).
  * @states: Idle states data corresponding to this CPU.
- * @last_state: Idle state entered by the CPU last time.
  * @interval_idx: Index of the most recent saved idle interval.
  * @intervals: Saved idle duration values.
  */
@@ -104,7 +103,6 @@ struct teo_cpu {
 	u64 time_span_ns;
 	u64 sleep_length_ns;
 	struct teo_idle_state states[CPUIDLE_STATE_MAX];
-	int last_state;
 	int interval_idx;
 	unsigned int intervals[INTERVALS];
 };
@@ -125,12 +123,15 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 	if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) {
 		/*
-		 * One of the safety nets has triggered or this was a timer
-		 * wakeup (or equivalent).
+		 * One of the safety nets has triggered or the wakeup was close
+		 * enough to the closest timer event expected at the idle state
+		 * selection time to be discarded.
 		 */
-		measured_us = sleep_length_us;
+		measured_us = UINT_MAX;
 	} else {
-		unsigned int lat = drv->states[cpu_data->last_state].exit_latency;
+		unsigned int lat;
+
+		lat = drv->states[dev->last_state_idx].exit_latency;
 
 		measured_us = ktime_to_us(cpu_data->time_span_ns);
 		/*
@@ -189,15 +190,6 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	}
 
 	/*
-	 * If the total time span between idle state selection and the "reflect"
-	 * callback is greater than or equal to the sleep length determined at
-	 * the idle state selection time, the wakeup is likely to be due to a
-	 * timer event.
-	 */
-	if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns)
-		measured_us = UINT_MAX;
-
-	/*
 	 * Save idle duration values corresponding to non-timer wakeups for
 	 * pattern detection.
 	 */
@@ -242,12 +234,12 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
 	int latency_req = cpuidle_governor_latency_req(dev->cpu);
 	unsigned int duration_us, count;
-	int max_early_idx, idx, i;
+	int max_early_idx, constraint_idx, idx, i;
 	ktime_t delta_tick;
 
-	if (cpu_data->last_state >= 0) {
+	if (dev->last_state_idx >= 0) {
 		teo_update(drv, dev);
-		cpu_data->last_state = -1;
+		dev->last_state_idx = -1;
 	}
 
 	cpu_data->time_span_ns = local_clock();
@@ -257,6 +249,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 
 	count = 0;
 	max_early_idx = -1;
+	constraint_idx = drv->state_count;
 	idx = -1;
 
 	for (i = 0; i < drv->state_count; i++) {
@@ -286,16 +279,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		if (s->target_residency > duration_us)
 			break;
 
-		if (s->exit_latency > latency_req) {
-			/*
-			 * If we break out of the loop for latency reasons, use
-			 * the target residency of the selected state as the
-			 * expected idle duration to avoid stopping the tick
-			 * as long as that target residency is low enough.
-			 */
-			duration_us = drv->states[idx].target_residency;
-			goto refine;
-		}
+		if (s->exit_latency > latency_req && constraint_idx > i)
+			constraint_idx = i;
 
 		idx = i;
 
@@ -321,7 +306,13 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		duration_us = drv->states[idx].target_residency;
 	}
 
-refine:
+	/*
+	 * If there is a latency constraint, it may be necessary to use a
+	 * shallower idle state than the one selected so far.
+	 */
+	if (constraint_idx < idx)
+		idx = constraint_idx;
+
 	if (idx < 0) {
 		idx = 0; /* No states enabled. Must use 0. */
 	} else if (idx > 0) {
@@ -331,13 +322,12 @@ refine:
 
 		/*
 		 * Count and sum the most recent idle duration values less than
-		 * the target residency of the state selected so far, find the
-		 * max.
+		 * the current expected idle duration value.
 		 */
 		for (i = 0; i < INTERVALS; i++) {
 			unsigned int val = cpu_data->intervals[i];
 
-			if (val >= drv->states[idx].target_residency)
+			if (val >= duration_us)
 				continue;
 
 			count++;
@@ -356,8 +346,10 @@ refine:
 			 * would be too shallow.
 			 */
 			if (!(tick_nohz_tick_stopped() && avg_us < TICK_USEC)) {
-				idx = teo_find_shallower_state(drv, dev, idx, avg_us);
 				duration_us = avg_us;
+				if (drv->states[idx].target_residency > avg_us)
+					idx = teo_find_shallower_state(drv, dev,
+								       idx, avg_us);
 			}
 		}
 	}
@@ -394,7 +386,7 @@ static void teo_reflect(struct cpuidle_device *dev, int state)
 {
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
 
-	cpu_data->last_state = state;
+	dev->last_state_idx = state;
 	/*
 	 * If the wakeup was not "natural", but triggered by one of the safety
 	 * nets, assume that the CPU might have been idle for the entire sleep
diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c
index 02b9315a9e96..c8fa5f41dfc4 100644
--- a/drivers/cpuidle/poll_state.c
+++ b/drivers/cpuidle/poll_state.c
@@ -20,16 +20,9 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
 	local_irq_enable();
 	if (!current_set_polling_and_test()) {
 		unsigned int loop_count = 0;
-		u64 limit = TICK_NSEC;
-		int i;
+		u64 limit;
 
-		for (i = 1; i < drv->state_count; i++) {
-			if (drv->states[i].disabled || dev->states_usage[i].disable)
-				continue;
-
-			limit = (u64)drv->states[i].target_residency * NSEC_PER_USEC;
-			break;
-		}
+		limit = cpuidle_poll_time(drv, dev);
 
 		while (!need_resched()) {
 			cpu_relax();
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index eb20adb5de23..2bb2683b493c 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -334,6 +334,7 @@ struct cpuidle_state_kobj {
 	struct cpuidle_state_usage *state_usage;
 	struct completion kobj_unregister;
 	struct kobject kobj;
+	struct cpuidle_device *device;
 };
 
 #ifdef CONFIG_SUSPEND
@@ -391,6 +392,7 @@ static inline void cpuidle_remove_s2idle_attr_group(struct cpuidle_state_kobj *k
 #define kobj_to_state_obj(k) container_of(k, struct cpuidle_state_kobj, kobj)
 #define kobj_to_state(k) (kobj_to_state_obj(k)->state)
 #define kobj_to_state_usage(k) (kobj_to_state_obj(k)->state_usage)
+#define kobj_to_device(k) (kobj_to_state_obj(k)->device)
 #define attr_to_stateattr(a) container_of(a, struct cpuidle_state_attr, attr)
 
 static ssize_t cpuidle_state_show(struct kobject *kobj, struct attribute *attr,
@@ -414,10 +416,14 @@ static ssize_t cpuidle_state_store(struct kobject *kobj, struct attribute *attr,
 	struct cpuidle_state *state = kobj_to_state(kobj);
 	struct cpuidle_state_usage *state_usage = kobj_to_state_usage(kobj);
 	struct cpuidle_state_attr *cattr = attr_to_stateattr(attr);
+	struct cpuidle_device *dev = kobj_to_device(kobj);
 
 	if (cattr->store)
 		ret = cattr->store(state, state_usage, buf, size);
 
+	/* reset poll time cache */
+	dev->poll_limit_ns = 0;
+
 	return ret;
 }
 
@@ -468,6 +474,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device)
 		}
 		kobj->state = &drv->states[i];
 		kobj->state_usage = &device->states_usage[i];
+		kobj->device = device;
 		init_completion(&kobj->kobj_unregister);
 
 		ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle,
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index ba98a4e3ad33..defe1d438710 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -93,15 +93,28 @@ config ARM_EXYNOS_BUS_DEVFREQ
 	  This does not yet operate with optimal voltages.
 
 config ARM_TEGRA_DEVFREQ
-	tristate "Tegra DEVFREQ Driver"
-	depends on ARCH_TEGRA_124_SOC
-	select DEVFREQ_GOV_SIMPLE_ONDEMAND
+	tristate "NVIDIA Tegra30/114/124/210 DEVFREQ Driver"
+	depends on ARCH_TEGRA_3x_SOC || ARCH_TEGRA_114_SOC || \
+		ARCH_TEGRA_132_SOC || ARCH_TEGRA_124_SOC || \
+		ARCH_TEGRA_210_SOC || \
+		COMPILE_TEST
 	select PM_OPP
 	help
 	  This adds the DEVFREQ driver for the Tegra family of SoCs.
 	  It reads ACTMON counters of memory controllers and adjusts the
 	  operating frequencies and voltages with OPP support.
 
+config ARM_TEGRA20_DEVFREQ
+	tristate "NVIDIA Tegra20 DEVFREQ Driver"
+	depends on (TEGRA_MC && TEGRA20_EMC) || COMPILE_TEST
+	depends on COMMON_CLK
+	select DEVFREQ_GOV_SIMPLE_ONDEMAND
+	select PM_OPP
+	help
+	  This adds the DEVFREQ driver for the Tegra20 family of SoCs.
+	  It reads Memory Controller counters and adjusts the operating
+	  frequencies and voltages with OPP support.
+
 config ARM_RK3399_DMC_DEVFREQ
 	tristate "ARM RK3399 DMC DEVFREQ Driver"
 	depends on ARCH_ROCKCHIP
diff --git a/drivers/devfreq/Makefile b/drivers/devfreq/Makefile
index 32b8d4d3f12c..338ae8440db6 100644
--- a/drivers/devfreq/Makefile
+++ b/drivers/devfreq/Makefile
@@ -10,7 +10,8 @@ obj-$(CONFIG_DEVFREQ_GOV_PASSIVE)	+= governor_passive.o
 # DEVFREQ Drivers
 obj-$(CONFIG_ARM_EXYNOS_BUS_DEVFREQ)	+= exynos-bus.o
 obj-$(CONFIG_ARM_RK3399_DMC_DEVFREQ)	+= rk3399_dmc.o
-obj-$(CONFIG_ARM_TEGRA_DEVFREQ)		+= tegra-devfreq.o
+obj-$(CONFIG_ARM_TEGRA_DEVFREQ)		+= tegra30-devfreq.o
+obj-$(CONFIG_ARM_TEGRA20_DEVFREQ)	+= tegra20-devfreq.o
 
 # DEVFREQ Event Drivers
 obj-$(CONFIG_PM_DEVFREQ_EVENT)		+= event/
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index ab22bf8a12d6..446490c9d635 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -254,7 +254,7 @@ static struct devfreq_governor *try_then_request_governor(const char *name)
 		/* Restore previous state before return */
 		mutex_lock(&devfreq_list_lock);
 		if (err)
-			return ERR_PTR(err);
+			return (err < 0) ? ERR_PTR(err) : ERR_PTR(-EINVAL);
 
 		governor = find_devfreq_governor(name);
 	}
@@ -402,7 +402,7 @@ static void devfreq_monitor(struct work_struct *work)
  * devfreq_monitor_start() - Start load monitoring of devfreq instance
  * @devfreq:	the devfreq instance.
  *
- * Helper function for starting devfreq device load monitoing. By
+ * Helper function for starting devfreq device load monitoring. By
  * default delayed work based monitoring is supported. Function
  * to be called from governor in response to DEVFREQ_GOV_START
  * event when device is added to devfreq framework.
@@ -420,7 +420,7 @@ EXPORT_SYMBOL(devfreq_monitor_start);
  * devfreq_monitor_stop() - Stop load monitoring of a devfreq instance
  * @devfreq:	the devfreq instance.
  *
- * Helper function to stop devfreq device load monitoing. Function
+ * Helper function to stop devfreq device load monitoring. Function
  * to be called from governor in response to DEVFREQ_GOV_STOP
  * event when device is removed from devfreq framework.
  */
@@ -434,7 +434,7 @@ EXPORT_SYMBOL(devfreq_monitor_stop);
  * devfreq_monitor_suspend() - Suspend load monitoring of a devfreq instance
  * @devfreq:	the devfreq instance.
  *
- * Helper function to suspend devfreq device load monitoing. Function
+ * Helper function to suspend devfreq device load monitoring. Function
  * to be called from governor in response to DEVFREQ_GOV_SUSPEND
  * event or when polling interval is set to zero.
  *
@@ -461,7 +461,7 @@ EXPORT_SYMBOL(devfreq_monitor_suspend);
  * devfreq_monitor_resume() - Resume load monitoring of a devfreq instance
  * @devfreq:    the devfreq instance.
  *
- * Helper function to resume devfreq device load monitoing. Function
+ * Helper function to resume devfreq device load monitoring. Function
  * to be called from governor in response to DEVFREQ_GOV_RESUME
  * event or when polling interval is set to non-zero.
  */
@@ -867,7 +867,7 @@ EXPORT_SYMBOL_GPL(devfreq_get_devfreq_by_phandle);
 
 /**
  * devm_devfreq_remove_device() - Resource-managed devfreq_remove_device()
- * @dev:	the device to add devfreq feature.
+ * @dev:	the device from which to remove devfreq feature.
  * @devfreq:	the devfreq instance to be removed
  */
 void devm_devfreq_remove_device(struct device *dev, struct devfreq *devfreq)
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 3ee3dd5653aa..87b42055e6bc 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/suspend.h>
@@ -20,6 +21,11 @@
 
 #include "exynos-ppmu.h"
 
+enum exynos_ppmu_type {
+	EXYNOS_TYPE_PPMU,
+	EXYNOS_TYPE_PPMU_V2,
+};
+
 struct exynos_ppmu_data {
 	struct clk *clk;
 };
@@ -33,6 +39,7 @@ struct exynos_ppmu {
 	struct regmap *regmap;
 
 	struct exynos_ppmu_data ppmu;
+	enum exynos_ppmu_type ppmu_type;
 };
 
 #define PPMU_EVENT(name)			\
@@ -86,6 +93,12 @@ static struct __exynos_ppmu_events {
 	PPMU_EVENT(d1-cpu),
 	PPMU_EVENT(d1-general),
 	PPMU_EVENT(d1-rt),
+
+	/* For Exynos5422 SoC */
+	PPMU_EVENT(dmc0_0),
+	PPMU_EVENT(dmc0_1),
+	PPMU_EVENT(dmc1_0),
+	PPMU_EVENT(dmc1_1),
 };
 
 static int exynos_ppmu_find_ppmu_id(struct devfreq_event_dev *edev)
@@ -151,9 +164,9 @@ static int exynos_ppmu_set_event(struct devfreq_event_dev *edev)
 	if (ret < 0)
 		return ret;
 
-	/* Set the event of Read/Write data count  */
+	/* Set the event of proper data type monitoring */
 	ret = regmap_write(info->regmap, PPMU_BEVTxSEL(id),
-				PPMU_RO_DATA_CNT | PPMU_WO_DATA_CNT);
+			   edev->desc->event_type);
 	if (ret < 0)
 		return ret;
 
@@ -365,23 +378,11 @@ static int exynos_ppmu_v2_set_event(struct devfreq_event_dev *edev)
 	if (ret < 0)
 		return ret;
 
-	/* Set the event of Read/Write data count  */
-	switch (id) {
-	case PPMU_PMNCNT0:
-	case PPMU_PMNCNT1:
-	case PPMU_PMNCNT2:
-		ret = regmap_write(info->regmap, PPMU_V2_CH_EVx_TYPE(id),
-				PPMU_V2_RO_DATA_CNT | PPMU_V2_WO_DATA_CNT);
-		if (ret < 0)
-			return ret;
-		break;
-	case PPMU_PMNCNT3:
-		ret = regmap_write(info->regmap, PPMU_V2_CH_EVx_TYPE(id),
-				PPMU_V2_EVT3_RW_DATA_CNT);
-		if (ret < 0)
-			return ret;
-		break;
-	}
+	/* Set the event of proper data type monitoring */
+	ret = regmap_write(info->regmap, PPMU_V2_CH_EVx_TYPE(id),
+			   edev->desc->event_type);
+	if (ret < 0)
+		return ret;
 
 	/* Reset cycle counter/performance counter and enable PPMU */
 	ret = regmap_read(info->regmap, PPMU_V2_PMNC, &pmnc);
@@ -480,31 +481,24 @@ static const struct devfreq_event_ops exynos_ppmu_v2_ops = {
 static const struct of_device_id exynos_ppmu_id_match[] = {
 	{
 		.compatible = "samsung,exynos-ppmu",
-		.data = (void *)&exynos_ppmu_ops,
+		.data = (void *)EXYNOS_TYPE_PPMU,
 	}, {
 		.compatible = "samsung,exynos-ppmu-v2",
-		.data = (void *)&exynos_ppmu_v2_ops,
+		.data = (void *)EXYNOS_TYPE_PPMU_V2,
 	},
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, exynos_ppmu_id_match);
 
-static struct devfreq_event_ops *exynos_bus_get_ops(struct device_node *np)
-{
-	const struct of_device_id *match;
-
-	match = of_match_node(exynos_ppmu_id_match, np);
-	return (struct devfreq_event_ops *)match->data;
-}
-
 static int of_get_devfreq_events(struct device_node *np,
 				 struct exynos_ppmu *info)
 {
 	struct devfreq_event_desc *desc;
-	struct devfreq_event_ops *event_ops;
 	struct device *dev = info->dev;
 	struct device_node *events_np, *node;
 	int i, j, count;
+	const struct of_device_id *of_id;
+	int ret;
 
 	events_np = of_get_child_by_name(np, "events");
 	if (!events_np) {
@@ -512,7 +506,6 @@ static int of_get_devfreq_events(struct device_node *np,
 			"failed to get child node of devfreq-event devices\n");
 		return -EINVAL;
 	}
-	event_ops = exynos_bus_get_ops(np);
 
 	count = of_get_child_count(events_np);
 	desc = devm_kcalloc(dev, count, sizeof(*desc), GFP_KERNEL);
@@ -520,6 +513,12 @@ static int of_get_devfreq_events(struct device_node *np,
 		return -ENOMEM;
 	info->num_events = count;
 
+	of_id = of_match_device(exynos_ppmu_id_match, dev);
+	if (of_id)
+		info->ppmu_type = (enum exynos_ppmu_type)of_id->data;
+	else
+		return -EINVAL;
+
 	j = 0;
 	for_each_child_of_node(events_np, node) {
 		for (i = 0; i < ARRAY_SIZE(ppmu_events); i++) {
@@ -537,10 +536,51 @@ static int of_get_devfreq_events(struct device_node *np,
 			continue;
 		}
 
-		desc[j].ops = event_ops;
+		switch (info->ppmu_type) {
+		case EXYNOS_TYPE_PPMU:
+			desc[j].ops = &exynos_ppmu_ops;
+			break;
+		case EXYNOS_TYPE_PPMU_V2:
+			desc[j].ops = &exynos_ppmu_v2_ops;
+			break;
+		}
+
 		desc[j].driver_data = info;
 
 		of_property_read_string(node, "event-name", &desc[j].name);
+		ret = of_property_read_u32(node, "event-data-type",
+					   &desc[j].event_type);
+		if (ret) {
+			/* Set the event of proper data type counting.
+			 * Check if the data type has been defined in DT,
+			 * use default if not.
+			 */
+			if (info->ppmu_type == EXYNOS_TYPE_PPMU_V2) {
+				struct devfreq_event_dev edev;
+				int id;
+				/* Not all registers take the same value for
+				 * read+write data count.
+				 */
+				edev.desc = &desc[j];
+				id = exynos_ppmu_find_ppmu_id(&edev);
+
+				switch (id) {
+				case PPMU_PMNCNT0:
+				case PPMU_PMNCNT1:
+				case PPMU_PMNCNT2:
+					desc[j].event_type = PPMU_V2_RO_DATA_CNT
+						| PPMU_V2_WO_DATA_CNT;
+					break;
+				case PPMU_PMNCNT3:
+					desc[j].event_type =
+						PPMU_V2_EVT3_RW_DATA_CNT;
+					break;
+				}
+			} else {
+				desc[j].event_type = PPMU_RO_DATA_CNT |
+					PPMU_WO_DATA_CNT;
+			}
+		}
 
 		j++;
 	}
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index d9f377912c10..c832673273a2 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -22,7 +22,6 @@
 #include <linux/slab.h>
 
 #define DEFAULT_SATURATION_RATIO	40
-#define DEFAULT_VOLTAGE_TOLERANCE	2
 
 struct exynos_bus {
 	struct device *dev;
@@ -34,9 +33,8 @@ struct exynos_bus {
 
 	unsigned long curr_freq;
 
-	struct regulator *regulator;
+	struct opp_table *opp_table;
 	struct clk *clk;
-	unsigned int voltage_tolerance;
 	unsigned int ratio;
 };
 
@@ -90,62 +88,29 @@ static int exynos_bus_get_event(struct exynos_bus *bus,
 }
 
 /*
- * Must necessary function for devfreq simple-ondemand governor
+ * devfreq function for both simple-ondemand and passive governor
  */
 static int exynos_bus_target(struct device *dev, unsigned long *freq, u32 flags)
 {
 	struct exynos_bus *bus = dev_get_drvdata(dev);
 	struct dev_pm_opp *new_opp;
-	unsigned long old_freq, new_freq, new_volt, tol;
 	int ret = 0;
 
-	/* Get new opp-bus instance according to new bus clock */
+	/* Get correct frequency for bus. */
 	new_opp = devfreq_recommended_opp(dev, freq, flags);
 	if (IS_ERR(new_opp)) {
 		dev_err(dev, "failed to get recommended opp instance\n");
 		return PTR_ERR(new_opp);
 	}
 
-	new_freq = dev_pm_opp_get_freq(new_opp);
-	new_volt = dev_pm_opp_get_voltage(new_opp);
 	dev_pm_opp_put(new_opp);
 
-	old_freq = bus->curr_freq;
-
-	if (old_freq == new_freq)
-		return 0;
-	tol = new_volt * bus->voltage_tolerance / 100;
-
 	/* Change voltage and frequency according to new OPP level */
 	mutex_lock(&bus->lock);
+	ret = dev_pm_opp_set_rate(dev, *freq);
+	if (!ret)
+		bus->curr_freq = *freq;
 
-	if (old_freq < new_freq) {
-		ret = regulator_set_voltage_tol(bus->regulator, new_volt, tol);
-		if (ret < 0) {
-			dev_err(bus->dev, "failed to set voltage\n");
-			goto out;
-		}
-	}
-
-	ret = clk_set_rate(bus->clk, new_freq);
-	if (ret < 0) {
-		dev_err(dev, "failed to change clock of bus\n");
-		clk_set_rate(bus->clk, old_freq);
-		goto out;
-	}
-
-	if (old_freq > new_freq) {
-		ret = regulator_set_voltage_tol(bus->regulator, new_volt, tol);
-		if (ret < 0) {
-			dev_err(bus->dev, "failed to set voltage\n");
-			goto out;
-		}
-	}
-	bus->curr_freq = new_freq;
-
-	dev_dbg(dev, "Set the frequency of bus (%luHz -> %luHz, %luHz)\n",
-			old_freq, new_freq, clk_get_rate(bus->clk));
-out:
 	mutex_unlock(&bus->lock);
 
 	return ret;
@@ -191,57 +156,12 @@ static void exynos_bus_exit(struct device *dev)
 	if (ret < 0)
 		dev_warn(dev, "failed to disable the devfreq-event devices\n");
 
-	if (bus->regulator)
-		regulator_disable(bus->regulator);
-
 	dev_pm_opp_of_remove_table(dev);
 	clk_disable_unprepare(bus->clk);
-}
-
-/*
- * Must necessary function for devfreq passive governor
- */
-static int exynos_bus_passive_target(struct device *dev, unsigned long *freq,
-					u32 flags)
-{
-	struct exynos_bus *bus = dev_get_drvdata(dev);
-	struct dev_pm_opp *new_opp;
-	unsigned long old_freq, new_freq;
-	int ret = 0;
-
-	/* Get new opp-bus instance according to new bus clock */
-	new_opp = devfreq_recommended_opp(dev, freq, flags);
-	if (IS_ERR(new_opp)) {
-		dev_err(dev, "failed to get recommended opp instance\n");
-		return PTR_ERR(new_opp);
+	if (bus->opp_table) {
+		dev_pm_opp_put_regulators(bus->opp_table);
+		bus->opp_table = NULL;
 	}
-
-	new_freq = dev_pm_opp_get_freq(new_opp);
-	dev_pm_opp_put(new_opp);
-
-	old_freq = bus->curr_freq;
-
-	if (old_freq == new_freq)
-		return 0;
-
-	/* Change the frequency according to new OPP level */
-	mutex_lock(&bus->lock);
-
-	ret = clk_set_rate(bus->clk, new_freq);
-	if (ret < 0) {
-		dev_err(dev, "failed to set the clock of bus\n");
-		goto out;
-	}
-
-	*freq = new_freq;
-	bus->curr_freq = new_freq;
-
-	dev_dbg(dev, "Set the frequency of bus (%luHz -> %luHz, %luHz)\n",
-			old_freq, new_freq, clk_get_rate(bus->clk));
-out:
-	mutex_unlock(&bus->lock);
-
-	return ret;
 }
 
 static void exynos_bus_passive_exit(struct device *dev)
@@ -256,21 +176,19 @@ static int exynos_bus_parent_parse_of(struct device_node *np,
 					struct exynos_bus *bus)
 {
 	struct device *dev = bus->dev;
+	struct opp_table *opp_table;
+	const char *vdd = "vdd";
 	int i, ret, count, size;
 
-	/* Get the regulator to provide each bus with the power */
-	bus->regulator = devm_regulator_get(dev, "vdd");
-	if (IS_ERR(bus->regulator)) {
-		dev_err(dev, "failed to get VDD regulator\n");
-		return PTR_ERR(bus->regulator);
-	}
-
-	ret = regulator_enable(bus->regulator);
-	if (ret < 0) {
-		dev_err(dev, "failed to enable VDD regulator\n");
+	opp_table = dev_pm_opp_set_regulators(dev, &vdd, 1);
+	if (IS_ERR(opp_table)) {
+		ret = PTR_ERR(opp_table);
+		dev_err(dev, "failed to set regulators %d\n", ret);
 		return ret;
 	}
 
+	bus->opp_table = opp_table;
+
 	/*
 	 * Get the devfreq-event devices to get the current utilization of
 	 * buses. This raw data will be used in devfreq ondemand governor.
@@ -311,14 +229,11 @@ static int exynos_bus_parent_parse_of(struct device_node *np,
 	if (of_property_read_u32(np, "exynos,saturation-ratio", &bus->ratio))
 		bus->ratio = DEFAULT_SATURATION_RATIO;
 
-	if (of_property_read_u32(np, "exynos,voltage-tolerance",
-					&bus->voltage_tolerance))
-		bus->voltage_tolerance = DEFAULT_VOLTAGE_TOLERANCE;
-
 	return 0;
 
 err_regulator:
-	regulator_disable(bus->regulator);
+	dev_pm_opp_put_regulators(bus->opp_table);
+	bus->opp_table = NULL;
 
 	return ret;
 }
@@ -383,6 +298,7 @@ static int exynos_bus_probe(struct platform_device *pdev)
 	struct exynos_bus *bus;
 	int ret, max_state;
 	unsigned long min_freq, max_freq;
+	bool passive = false;
 
 	if (!np) {
 		dev_err(dev, "failed to find devicetree node\n");
@@ -396,27 +312,27 @@ static int exynos_bus_probe(struct platform_device *pdev)
 	bus->dev = &pdev->dev;
 	platform_set_drvdata(pdev, bus);
 
-	/* Parse the device-tree to get the resource information */
-	ret = exynos_bus_parse_of(np, bus);
-	if (ret < 0)
-		return ret;
-
 	profile = devm_kzalloc(dev, sizeof(*profile), GFP_KERNEL);
-	if (!profile) {
-		ret = -ENOMEM;
-		goto err;
-	}
+	if (!profile)
+		return -ENOMEM;
 
 	node = of_parse_phandle(dev->of_node, "devfreq", 0);
 	if (node) {
 		of_node_put(node);
-		goto passive;
+		passive = true;
 	} else {
 		ret = exynos_bus_parent_parse_of(np, bus);
+		if (ret < 0)
+			return ret;
 	}
 
+	/* Parse the device-tree to get the resource information */
+	ret = exynos_bus_parse_of(np, bus);
 	if (ret < 0)
-		goto err;
+		goto err_reg;
+
+	if (passive)
+		goto passive;
 
 	/* Initialize the struct profile and governor data for parent device */
 	profile->polling_ms = 50;
@@ -468,7 +384,7 @@ static int exynos_bus_probe(struct platform_device *pdev)
 	goto out;
 passive:
 	/* Initialize the struct profile and governor data for passive device */
-	profile->target = exynos_bus_passive_target;
+	profile->target = exynos_bus_target;
 	profile->exit = exynos_bus_passive_exit;
 
 	/* Get the instance of parent devfreq device */
@@ -507,6 +423,11 @@ out:
 err:
 	dev_pm_opp_of_remove_table(dev);
 	clk_disable_unprepare(bus->clk);
+err_reg:
+	if (!passive) {
+		dev_pm_opp_put_regulators(bus->opp_table);
+		bus->opp_table = NULL;
+	}
 
 	return ret;
 }
diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c
index 58308948b863..be6eeab9c814 100644
--- a/drivers/devfreq/governor_passive.c
+++ b/drivers/devfreq/governor_passive.c
@@ -149,7 +149,6 @@ static int devfreq_passive_notifier_call(struct notifier_block *nb,
 static int devfreq_passive_event_handler(struct devfreq *devfreq,
 				unsigned int event, void *data)
 {
-	struct device *dev = devfreq->dev.parent;
 	struct devfreq_passive_data *p_data
 			= (struct devfreq_passive_data *)devfreq->data;
 	struct devfreq *parent = (struct devfreq *)p_data->parent;
@@ -165,12 +164,12 @@ static int devfreq_passive_event_handler(struct devfreq *devfreq,
 			p_data->this = devfreq;
 
 		nb->notifier_call = devfreq_passive_notifier_call;
-		ret = devm_devfreq_register_notifier(dev, parent, nb,
+		ret = devfreq_register_notifier(parent, nb,
 					DEVFREQ_TRANSITION_NOTIFIER);
 		break;
 	case DEVFREQ_GOV_STOP:
-		devm_devfreq_unregister_notifier(dev, parent, nb,
-					DEVFREQ_TRANSITION_NOTIFIER);
+		WARN_ON(devfreq_unregister_notifier(parent, nb,
+					DEVFREQ_TRANSITION_NOTIFIER));
 		break;
 	default:
 		break;
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 682465fa57e1..2e65d7279d79 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -351,7 +351,7 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 
 	/*
 	 * Get dram timing and pass it to arm trust firmware,
-	 * the dram drvier in arm trust firmware will get these
+	 * the dram driver in arm trust firmware will get these
 	 * timing and to do dram initial.
 	 */
 	if (!of_get_ddr_timings(&data->timing, np)) {
diff --git a/drivers/devfreq/tegra20-devfreq.c b/drivers/devfreq/tegra20-devfreq.c
new file mode 100644
index 000000000000..ff82bac9ee4e
--- /dev/null
+++ b/drivers/devfreq/tegra20-devfreq.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVIDIA Tegra20 devfreq driver
+ *
+ * Copyright (C) 2019 GRATE-DRIVER project
+ */
+
+#include <linux/clk.h>
+#include <linux/devfreq.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+
+#include <soc/tegra/mc.h>
+
+#include "governor.h"
+
+#define MC_STAT_CONTROL				0x90
+#define MC_STAT_EMC_CLOCK_LIMIT			0xa0
+#define MC_STAT_EMC_CLOCKS			0xa4
+#define MC_STAT_EMC_CONTROL			0xa8
+#define MC_STAT_EMC_COUNT			0xb8
+
+#define EMC_GATHER_CLEAR			(1 << 8)
+#define EMC_GATHER_ENABLE			(3 << 8)
+
+struct tegra_devfreq {
+	struct devfreq *devfreq;
+	struct clk *emc_clock;
+	void __iomem *regs;
+};
+
+static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
+				u32 flags)
+{
+	struct tegra_devfreq *tegra = dev_get_drvdata(dev);
+	struct devfreq *devfreq = tegra->devfreq;
+	struct dev_pm_opp *opp;
+	unsigned long rate;
+	int err;
+
+	opp = devfreq_recommended_opp(dev, freq, flags);
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
+
+	rate = dev_pm_opp_get_freq(opp);
+	dev_pm_opp_put(opp);
+
+	err = clk_set_min_rate(tegra->emc_clock, rate);
+	if (err)
+		return err;
+
+	err = clk_set_rate(tegra->emc_clock, 0);
+	if (err)
+		goto restore_min_rate;
+
+	return 0;
+
+restore_min_rate:
+	clk_set_min_rate(tegra->emc_clock, devfreq->previous_freq);
+
+	return err;
+}
+
+static int tegra_devfreq_get_dev_status(struct device *dev,
+					struct devfreq_dev_status *stat)
+{
+	struct tegra_devfreq *tegra = dev_get_drvdata(dev);
+
+	/*
+	 * EMC_COUNT returns number of memory events, that number is lower
+	 * than the number of clocks. Conversion ratio of 1/8 results in a
+	 * bit higher bandwidth than actually needed, it is good enough for
+	 * the time being because drivers don't support requesting minimum
+	 * needed memory bandwidth yet.
+	 *
+	 * TODO: adjust the ratio value once relevant drivers will support
+	 * memory bandwidth management.
+	 */
+	stat->busy_time = readl_relaxed(tegra->regs + MC_STAT_EMC_COUNT);
+	stat->total_time = readl_relaxed(tegra->regs + MC_STAT_EMC_CLOCKS) / 8;
+	stat->current_frequency = clk_get_rate(tegra->emc_clock);
+
+	writel_relaxed(EMC_GATHER_CLEAR, tegra->regs + MC_STAT_CONTROL);
+	writel_relaxed(EMC_GATHER_ENABLE, tegra->regs + MC_STAT_CONTROL);
+
+	return 0;
+}
+
+static struct devfreq_dev_profile tegra_devfreq_profile = {
+	.polling_ms	= 500,
+	.target		= tegra_devfreq_target,
+	.get_dev_status	= tegra_devfreq_get_dev_status,
+};
+
+static struct tegra_mc *tegra_get_memory_controller(void)
+{
+	struct platform_device *pdev;
+	struct device_node *np;
+	struct tegra_mc *mc;
+
+	np = of_find_compatible_node(NULL, NULL, "nvidia,tegra20-mc-gart");
+	if (!np)
+		return ERR_PTR(-ENOENT);
+
+	pdev = of_find_device_by_node(np);
+	of_node_put(np);
+	if (!pdev)
+		return ERR_PTR(-ENODEV);
+
+	mc = platform_get_drvdata(pdev);
+	if (!mc)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	return mc;
+}
+
+static int tegra_devfreq_probe(struct platform_device *pdev)
+{
+	struct tegra_devfreq *tegra;
+	struct tegra_mc *mc;
+	unsigned long max_rate;
+	unsigned long rate;
+	int err;
+
+	mc = tegra_get_memory_controller();
+	if (IS_ERR(mc)) {
+		err = PTR_ERR(mc);
+		dev_err(&pdev->dev, "failed to get memory controller: %d\n",
+			err);
+		return err;
+	}
+
+	tegra = devm_kzalloc(&pdev->dev, sizeof(*tegra), GFP_KERNEL);
+	if (!tegra)
+		return -ENOMEM;
+
+	/* EMC is a system-critical clock that is always enabled */
+	tegra->emc_clock = devm_clk_get(&pdev->dev, "emc");
+	if (IS_ERR(tegra->emc_clock)) {
+		err = PTR_ERR(tegra->emc_clock);
+		dev_err(&pdev->dev, "failed to get emc clock: %d\n", err);
+		return err;
+	}
+
+	tegra->regs = mc->regs;
+
+	max_rate = clk_round_rate(tegra->emc_clock, ULONG_MAX);
+
+	for (rate = 0; rate <= max_rate; rate++) {
+		rate = clk_round_rate(tegra->emc_clock, rate);
+
+		err = dev_pm_opp_add(&pdev->dev, rate, 0);
+		if (err) {
+			dev_err(&pdev->dev, "failed to add opp: %d\n", err);
+			goto remove_opps;
+		}
+	}
+
+	/*
+	 * Reset statistic gathers state, select global bandwidth for the
+	 * statistics collection mode and set clocks counter saturation
+	 * limit to maximum.
+	 */
+	writel_relaxed(0x00000000, tegra->regs + MC_STAT_CONTROL);
+	writel_relaxed(0x00000000, tegra->regs + MC_STAT_EMC_CONTROL);
+	writel_relaxed(0xffffffff, tegra->regs + MC_STAT_EMC_CLOCK_LIMIT);
+
+	platform_set_drvdata(pdev, tegra);
+
+	tegra->devfreq = devfreq_add_device(&pdev->dev, &tegra_devfreq_profile,
+					    DEVFREQ_GOV_SIMPLE_ONDEMAND, NULL);
+	if (IS_ERR(tegra->devfreq)) {
+		err = PTR_ERR(tegra->devfreq);
+		goto remove_opps;
+	}
+
+	return 0;
+
+remove_opps:
+	dev_pm_opp_remove_all_dynamic(&pdev->dev);
+
+	return err;
+}
+
+static int tegra_devfreq_remove(struct platform_device *pdev)
+{
+	struct tegra_devfreq *tegra = platform_get_drvdata(pdev);
+
+	devfreq_remove_device(tegra->devfreq);
+	dev_pm_opp_remove_all_dynamic(&pdev->dev);
+
+	return 0;
+}
+
+static struct platform_driver tegra_devfreq_driver = {
+	.probe		= tegra_devfreq_probe,
+	.remove		= tegra_devfreq_remove,
+	.driver		= {
+		.name	= "tegra20-devfreq",
+	},
+};
+module_platform_driver(tegra_devfreq_driver);
+
+MODULE_ALIAS("platform:tegra20-devfreq");
+MODULE_AUTHOR("Dmitry Osipenko <digetx@gmail.com>");
+MODULE_DESCRIPTION("NVIDIA Tegra20 devfreq driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra30-devfreq.c
index 35c38aad8b4f..a6ba75f4106d 100644
--- a/drivers/devfreq/tegra-devfreq.c
+++ b/drivers/devfreq/tegra30-devfreq.c
@@ -132,7 +132,6 @@ static struct tegra_devfreq_device_config actmon_device_configs[] = {
 struct tegra_devfreq_device {
 	const struct tegra_devfreq_device_config *config;
 	void __iomem *regs;
-	spinlock_t lock;
 
 	/* Average event count sampled in the last interrupt */
 	u32 avg_count;
@@ -160,6 +159,8 @@ struct tegra_devfreq {
 	struct notifier_block	rate_change_nb;
 
 	struct tegra_devfreq_device devices[ARRAY_SIZE(actmon_device_configs)];
+
+	int irq;
 };
 
 struct tegra_actmon_emc_ratio {
@@ -179,23 +180,23 @@ static struct tegra_actmon_emc_ratio actmon_emc_ratios[] = {
 
 static u32 actmon_readl(struct tegra_devfreq *tegra, u32 offset)
 {
-	return readl(tegra->regs + offset);
+	return readl_relaxed(tegra->regs + offset);
 }
 
 static void actmon_writel(struct tegra_devfreq *tegra, u32 val, u32 offset)
 {
-	writel(val, tegra->regs + offset);
+	writel_relaxed(val, tegra->regs + offset);
 }
 
 static u32 device_readl(struct tegra_devfreq_device *dev, u32 offset)
 {
-	return readl(dev->regs + offset);
+	return readl_relaxed(dev->regs + offset);
 }
 
 static void device_writel(struct tegra_devfreq_device *dev, u32 val,
 			  u32 offset)
 {
-	writel(val, dev->regs + offset);
+	writel_relaxed(val, dev->regs + offset);
 }
 
 static unsigned long do_percent(unsigned long val, unsigned int pct)
@@ -231,18 +232,14 @@ static void tegra_devfreq_update_wmark(struct tegra_devfreq *tegra,
 static void actmon_write_barrier(struct tegra_devfreq *tegra)
 {
 	/* ensure the update has reached the ACTMON */
-	wmb();
-	actmon_readl(tegra, ACTMON_GLB_STATUS);
+	readl(tegra->regs + ACTMON_GLB_STATUS);
 }
 
 static void actmon_isr_device(struct tegra_devfreq *tegra,
 			      struct tegra_devfreq_device *dev)
 {
-	unsigned long flags;
 	u32 intr_status, dev_ctrl;
 
-	spin_lock_irqsave(&dev->lock, flags);
-
 	dev->avg_count = device_readl(dev, ACTMON_DEV_AVG_COUNT);
 	tegra_devfreq_update_avg_wmark(tegra, dev);
 
@@ -291,26 +288,6 @@ static void actmon_isr_device(struct tegra_devfreq *tegra,
 	device_writel(dev, ACTMON_INTR_STATUS_CLEAR, ACTMON_DEV_INTR_STATUS);
 
 	actmon_write_barrier(tegra);
-
-	spin_unlock_irqrestore(&dev->lock, flags);
-}
-
-static irqreturn_t actmon_isr(int irq, void *data)
-{
-	struct tegra_devfreq *tegra = data;
-	bool handled = false;
-	unsigned int i;
-	u32 val;
-
-	val = actmon_readl(tegra, ACTMON_GLB_STATUS);
-	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) {
-		if (val & tegra->devices[i].config->irq_mask) {
-			actmon_isr_device(tegra, tegra->devices + i);
-			handled = true;
-		}
-	}
-
-	return handled ? IRQ_WAKE_THREAD : IRQ_NONE;
 }
 
 static unsigned long actmon_cpu_to_emc_rate(struct tegra_devfreq *tegra,
@@ -337,15 +314,12 @@ static void actmon_update_target(struct tegra_devfreq *tegra,
 	unsigned long cpu_freq = 0;
 	unsigned long static_cpu_emc_freq = 0;
 	unsigned int avg_sustain_coef;
-	unsigned long flags;
 
 	if (dev->config->avg_dependency_threshold) {
 		cpu_freq = cpufreq_get(0);
 		static_cpu_emc_freq = actmon_cpu_to_emc_rate(tegra, cpu_freq);
 	}
 
-	spin_lock_irqsave(&dev->lock, flags);
-
 	dev->target_freq = dev->avg_count / ACTMON_SAMPLING_PERIOD;
 	avg_sustain_coef = 100 * 100 / dev->config->boost_up_threshold;
 	dev->target_freq = do_percent(dev->target_freq, avg_sustain_coef);
@@ -353,19 +327,31 @@ static void actmon_update_target(struct tegra_devfreq *tegra,
 
 	if (dev->avg_count >= dev->config->avg_dependency_threshold)
 		dev->target_freq = max(dev->target_freq, static_cpu_emc_freq);
-
-	spin_unlock_irqrestore(&dev->lock, flags);
 }
 
 static irqreturn_t actmon_thread_isr(int irq, void *data)
 {
 	struct tegra_devfreq *tegra = data;
+	bool handled = false;
+	unsigned int i;
+	u32 val;
 
 	mutex_lock(&tegra->devfreq->lock);
-	update_devfreq(tegra->devfreq);
+
+	val = actmon_readl(tegra, ACTMON_GLB_STATUS);
+	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) {
+		if (val & tegra->devices[i].config->irq_mask) {
+			actmon_isr_device(tegra, tegra->devices + i);
+			handled = true;
+		}
+	}
+
+	if (handled)
+		update_devfreq(tegra->devfreq);
+
 	mutex_unlock(&tegra->devfreq->lock);
 
-	return IRQ_HANDLED;
+	return handled ? IRQ_HANDLED : IRQ_NONE;
 }
 
 static int tegra_actmon_rate_notify_cb(struct notifier_block *nb,
@@ -375,7 +361,6 @@ static int tegra_actmon_rate_notify_cb(struct notifier_block *nb,
 	struct tegra_devfreq *tegra;
 	struct tegra_devfreq_device *dev;
 	unsigned int i;
-	unsigned long flags;
 
 	if (action != POST_RATE_CHANGE)
 		return NOTIFY_OK;
@@ -387,9 +372,7 @@ static int tegra_actmon_rate_notify_cb(struct notifier_block *nb,
 	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) {
 		dev = &tegra->devices[i];
 
-		spin_lock_irqsave(&dev->lock, flags);
 		tegra_devfreq_update_wmark(tegra, dev);
-		spin_unlock_irqrestore(&dev->lock, flags);
 	}
 
 	actmon_write_barrier(tegra);
@@ -397,48 +380,6 @@ static int tegra_actmon_rate_notify_cb(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static void tegra_actmon_enable_interrupts(struct tegra_devfreq *tegra)
-{
-	struct tegra_devfreq_device *dev;
-	u32 val;
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) {
-		dev = &tegra->devices[i];
-
-		val = device_readl(dev, ACTMON_DEV_CTRL);
-		val |= ACTMON_DEV_CTRL_AVG_ABOVE_WMARK_EN;
-		val |= ACTMON_DEV_CTRL_AVG_BELOW_WMARK_EN;
-		val |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
-		val |= ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
-
-		device_writel(dev, val, ACTMON_DEV_CTRL);
-	}
-
-	actmon_write_barrier(tegra);
-}
-
-static void tegra_actmon_disable_interrupts(struct tegra_devfreq *tegra)
-{
-	struct tegra_devfreq_device *dev;
-	u32 val;
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) {
-		dev = &tegra->devices[i];
-
-		val = device_readl(dev, ACTMON_DEV_CTRL);
-		val &= ~ACTMON_DEV_CTRL_AVG_ABOVE_WMARK_EN;
-		val &= ~ACTMON_DEV_CTRL_AVG_BELOW_WMARK_EN;
-		val &= ~ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
-		val &= ~ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
-
-		device_writel(dev, val, ACTMON_DEV_CTRL);
-	}
-
-	actmon_write_barrier(tegra);
-}
-
 static void tegra_actmon_configure_device(struct tegra_devfreq *tegra,
 					  struct tegra_devfreq_device *dev)
 {
@@ -462,34 +403,80 @@ static void tegra_actmon_configure_device(struct tegra_devfreq *tegra,
 		<< ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_NUM_SHIFT;
 	val |= (ACTMON_ABOVE_WMARK_WINDOW - 1)
 		<< ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_NUM_SHIFT;
+	val |= ACTMON_DEV_CTRL_AVG_ABOVE_WMARK_EN;
+	val |= ACTMON_DEV_CTRL_AVG_BELOW_WMARK_EN;
+	val |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
+	val |= ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
 	val |= ACTMON_DEV_CTRL_ENB;
 
 	device_writel(dev, val, ACTMON_DEV_CTRL);
+}
+
+static void tegra_actmon_start(struct tegra_devfreq *tegra)
+{
+	unsigned int i;
+
+	disable_irq(tegra->irq);
+
+	actmon_writel(tegra, ACTMON_SAMPLING_PERIOD - 1,
+		      ACTMON_GLB_PERIOD_CTRL);
+
+	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++)
+		tegra_actmon_configure_device(tegra, &tegra->devices[i]);
+
+	actmon_write_barrier(tegra);
+
+	enable_irq(tegra->irq);
+}
+
+static void tegra_actmon_stop(struct tegra_devfreq *tegra)
+{
+	unsigned int i;
+
+	disable_irq(tegra->irq);
+
+	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) {
+		device_writel(&tegra->devices[i], 0x00000000, ACTMON_DEV_CTRL);
+		device_writel(&tegra->devices[i], ACTMON_INTR_STATUS_CLEAR,
+			      ACTMON_DEV_INTR_STATUS);
+	}
 
 	actmon_write_barrier(tegra);
+
+	enable_irq(tegra->irq);
 }
 
 static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
 				u32 flags)
 {
 	struct tegra_devfreq *tegra = dev_get_drvdata(dev);
+	struct devfreq *devfreq = tegra->devfreq;
 	struct dev_pm_opp *opp;
-	unsigned long rate = *freq * KHZ;
+	unsigned long rate;
+	int err;
 
-	opp = devfreq_recommended_opp(dev, &rate, flags);
+	opp = devfreq_recommended_opp(dev, freq, flags);
 	if (IS_ERR(opp)) {
-		dev_err(dev, "Failed to find opp for %lu KHz\n", *freq);
+		dev_err(dev, "Failed to find opp for %lu Hz\n", *freq);
 		return PTR_ERR(opp);
 	}
 	rate = dev_pm_opp_get_freq(opp);
 	dev_pm_opp_put(opp);
 
-	clk_set_min_rate(tegra->emc_clock, rate);
-	clk_set_rate(tegra->emc_clock, 0);
+	err = clk_set_min_rate(tegra->emc_clock, rate);
+	if (err)
+		return err;
 
-	*freq = rate;
+	err = clk_set_rate(tegra->emc_clock, 0);
+	if (err)
+		goto restore_min_rate;
 
 	return 0;
+
+restore_min_rate:
+	clk_set_min_rate(tegra->emc_clock, devfreq->previous_freq);
+
+	return err;
 }
 
 static int tegra_devfreq_get_dev_status(struct device *dev,
@@ -497,13 +484,15 @@ static int tegra_devfreq_get_dev_status(struct device *dev,
 {
 	struct tegra_devfreq *tegra = dev_get_drvdata(dev);
 	struct tegra_devfreq_device *actmon_dev;
+	unsigned long cur_freq;
 
-	stat->current_frequency = tegra->cur_freq;
+	cur_freq = READ_ONCE(tegra->cur_freq);
 
 	/* To be used by the tegra governor */
 	stat->private_data = tegra;
 
 	/* The below are to be used by the other governors */
+	stat->current_frequency = cur_freq * KHZ;
 
 	actmon_dev = &tegra->devices[MCALL];
 
@@ -514,7 +503,7 @@ static int tegra_devfreq_get_dev_status(struct device *dev,
 	stat->busy_time *= 100 / BUS_SATURATION_RATIO;
 
 	/* Number of cycles in a sampling period */
-	stat->total_time = ACTMON_SAMPLING_PERIOD * tegra->cur_freq;
+	stat->total_time = ACTMON_SAMPLING_PERIOD * cur_freq;
 
 	stat->busy_time = min(stat->busy_time, stat->total_time);
 
@@ -553,7 +542,7 @@ static int tegra_governor_get_target(struct devfreq *devfreq,
 		target_freq = max(target_freq, dev->target_freq);
 	}
 
-	*freq = target_freq;
+	*freq = target_freq * KHZ;
 
 	return 0;
 }
@@ -566,22 +555,22 @@ static int tegra_governor_event_handler(struct devfreq *devfreq,
 	switch (event) {
 	case DEVFREQ_GOV_START:
 		devfreq_monitor_start(devfreq);
-		tegra_actmon_enable_interrupts(tegra);
+		tegra_actmon_start(tegra);
 		break;
 
 	case DEVFREQ_GOV_STOP:
-		tegra_actmon_disable_interrupts(tegra);
+		tegra_actmon_stop(tegra);
 		devfreq_monitor_stop(devfreq);
 		break;
 
 	case DEVFREQ_GOV_SUSPEND:
-		tegra_actmon_disable_interrupts(tegra);
+		tegra_actmon_stop(tegra);
 		devfreq_monitor_suspend(devfreq);
 		break;
 
 	case DEVFREQ_GOV_RESUME:
 		devfreq_monitor_resume(devfreq);
-		tegra_actmon_enable_interrupts(tegra);
+		tegra_actmon_start(tegra);
 		break;
 	}
 
@@ -592,25 +581,22 @@ static struct devfreq_governor tegra_devfreq_governor = {
 	.name = "tegra_actmon",
 	.get_target_freq = tegra_governor_get_target,
 	.event_handler = tegra_governor_event_handler,
+	.immutable = true,
 };
 
 static int tegra_devfreq_probe(struct platform_device *pdev)
 {
 	struct tegra_devfreq *tegra;
 	struct tegra_devfreq_device *dev;
-	struct resource *res;
 	unsigned int i;
 	unsigned long rate;
-	int irq;
 	int err;
 
 	tegra = devm_kzalloc(&pdev->dev, sizeof(*tegra), GFP_KERNEL);
 	if (!tegra)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
-	tegra->regs = devm_ioremap_resource(&pdev->dev, res);
+	tegra->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(tegra->regs))
 		return PTR_ERR(tegra->regs);
 
@@ -632,13 +618,10 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
 		return PTR_ERR(tegra->emc_clock);
 	}
 
-	clk_set_rate(tegra->emc_clock, ULONG_MAX);
-
-	tegra->rate_change_nb.notifier_call = tegra_actmon_rate_notify_cb;
-	err = clk_notifier_register(tegra->emc_clock, &tegra->rate_change_nb);
-	if (err) {
-		dev_err(&pdev->dev,
-			"Failed to register rate change notifier\n");
+	tegra->irq = platform_get_irq(pdev, 0);
+	if (tegra->irq < 0) {
+		err = tegra->irq;
+		dev_err(&pdev->dev, "Failed to get IRQ: %d\n", err);
 		return err;
 	}
 
@@ -656,73 +639,94 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
 	tegra->max_freq = clk_round_rate(tegra->emc_clock, ULONG_MAX) / KHZ;
 	tegra->cur_freq = clk_get_rate(tegra->emc_clock) / KHZ;
 
-	actmon_writel(tegra, ACTMON_SAMPLING_PERIOD - 1,
-		      ACTMON_GLB_PERIOD_CTRL);
-
 	for (i = 0; i < ARRAY_SIZE(actmon_device_configs); i++) {
 		dev = tegra->devices + i;
 		dev->config = actmon_device_configs + i;
 		dev->regs = tegra->regs + dev->config->offset;
-		spin_lock_init(&dev->lock);
-
-		tegra_actmon_configure_device(tegra, dev);
 	}
 
 	for (rate = 0; rate <= tegra->max_freq * KHZ; rate++) {
 		rate = clk_round_rate(tegra->emc_clock, rate);
-		dev_pm_opp_add(&pdev->dev, rate, 0);
-	}
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "Failed to get IRQ: %d\n", irq);
-		return irq;
+		err = dev_pm_opp_add(&pdev->dev, rate, 0);
+		if (err) {
+			dev_err(&pdev->dev, "Failed to add OPP: %d\n", err);
+			goto remove_opps;
+		}
 	}
 
 	platform_set_drvdata(pdev, tegra);
 
-	err = devm_request_threaded_irq(&pdev->dev, irq, actmon_isr,
-					actmon_thread_isr, IRQF_SHARED,
-					"tegra-devfreq", tegra);
+	tegra->rate_change_nb.notifier_call = tegra_actmon_rate_notify_cb;
+	err = clk_notifier_register(tegra->emc_clock, &tegra->rate_change_nb);
 	if (err) {
-		dev_err(&pdev->dev, "Interrupt request failed\n");
-		return err;
+		dev_err(&pdev->dev,
+			"Failed to register rate change notifier\n");
+		goto remove_opps;
+	}
+
+	err = devfreq_add_governor(&tegra_devfreq_governor);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to add governor: %d\n", err);
+		goto unreg_notifier;
 	}
 
 	tegra_devfreq_profile.initial_freq = clk_get_rate(tegra->emc_clock);
-	tegra->devfreq = devm_devfreq_add_device(&pdev->dev,
-						 &tegra_devfreq_profile,
-						 "tegra_actmon",
-						 NULL);
+	tegra->devfreq = devfreq_add_device(&pdev->dev,
+					    &tegra_devfreq_profile,
+					    "tegra_actmon",
+					    NULL);
+	if (IS_ERR(tegra->devfreq)) {
+		err = PTR_ERR(tegra->devfreq);
+		goto remove_governor;
+	}
+
+	err = devm_request_threaded_irq(&pdev->dev, tegra->irq, NULL,
+					actmon_thread_isr, IRQF_ONESHOT,
+					"tegra-devfreq", tegra);
+	if (err) {
+		dev_err(&pdev->dev, "Interrupt request failed: %d\n", err);
+		goto remove_devfreq;
+	}
 
 	return 0;
+
+remove_devfreq:
+	devfreq_remove_device(tegra->devfreq);
+
+remove_governor:
+	devfreq_remove_governor(&tegra_devfreq_governor);
+
+unreg_notifier:
+	clk_notifier_unregister(tegra->emc_clock, &tegra->rate_change_nb);
+
+remove_opps:
+	dev_pm_opp_remove_all_dynamic(&pdev->dev);
+
+	reset_control_reset(tegra->reset);
+	clk_disable_unprepare(tegra->clock);
+
+	return err;
 }
 
 static int tegra_devfreq_remove(struct platform_device *pdev)
 {
 	struct tegra_devfreq *tegra = platform_get_drvdata(pdev);
-	int irq = platform_get_irq(pdev, 0);
-	u32 val;
-	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(actmon_device_configs); i++) {
-		val = device_readl(&tegra->devices[i], ACTMON_DEV_CTRL);
-		val &= ~ACTMON_DEV_CTRL_ENB;
-		device_writel(&tegra->devices[i], val, ACTMON_DEV_CTRL);
-	}
-
-	actmon_write_barrier(tegra);
-
-	devm_free_irq(&pdev->dev, irq, tegra);
+	devfreq_remove_device(tegra->devfreq);
+	devfreq_remove_governor(&tegra_devfreq_governor);
 
 	clk_notifier_unregister(tegra->emc_clock, &tegra->rate_change_nb);
+	dev_pm_opp_remove_all_dynamic(&pdev->dev);
 
+	reset_control_reset(tegra->reset);
 	clk_disable_unprepare(tegra->clock);
 
 	return 0;
 }
 
 static const struct of_device_id tegra_devfreq_of_match[] = {
+	{ .compatible = "nvidia,tegra30-actmon" },
 	{ .compatible = "nvidia,tegra124-actmon" },
 	{ },
 };
@@ -737,36 +741,7 @@ static struct platform_driver tegra_devfreq_driver = {
 		.of_match_table = tegra_devfreq_of_match,
 	},
 };
-
-static int __init tegra_devfreq_init(void)
-{
-	int ret = 0;
-
-	ret = devfreq_add_governor(&tegra_devfreq_governor);
-	if (ret) {
-		pr_err("%s: failed to add governor: %d\n", __func__, ret);
-		return ret;
-	}
-
-	ret = platform_driver_register(&tegra_devfreq_driver);
-	if (ret)
-		devfreq_remove_governor(&tegra_devfreq_governor);
-
-	return ret;
-}
-module_init(tegra_devfreq_init)
-
-static void __exit tegra_devfreq_exit(void)
-{
-	int ret = 0;
-
-	platform_driver_unregister(&tegra_devfreq_driver);
-
-	ret = devfreq_remove_governor(&tegra_devfreq_governor);
-	if (ret)
-		pr_err("%s: failed to remove governor: %d\n", __func__, ret);
-}
-module_exit(tegra_devfreq_exit)
+module_platform_driver(tegra_devfreq_driver);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Tegra devfreq driver");
diff --git a/drivers/macintosh/windfarm_cpufreq_clamp.c b/drivers/macintosh/windfarm_cpufreq_clamp.c
index 52fd5fca89a0..705c6200814b 100644
--- a/drivers/macintosh/windfarm_cpufreq_clamp.c
+++ b/drivers/macintosh/windfarm_cpufreq_clamp.c
@@ -3,9 +3,11 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
+#include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/wait.h>
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 
 #include <asm/prom.h>
@@ -16,36 +18,24 @@
 
 static int clamped;
 static struct wf_control *clamp_control;
-
-static int clamp_notifier_call(struct notifier_block *self,
-			       unsigned long event, void *data)
-{
-	struct cpufreq_policy *p = data;
-	unsigned long max_freq;
-
-	if (event != CPUFREQ_ADJUST)
-		return 0;
-
-	max_freq = clamped ? (p->cpuinfo.min_freq) : (p->cpuinfo.max_freq);
-	cpufreq_verify_within_limits(p, 0, max_freq);
-
-	return 0;
-}
-
-static struct notifier_block clamp_notifier = {
-	.notifier_call = clamp_notifier_call,
-};
+static struct dev_pm_qos_request qos_req;
+static unsigned int min_freq, max_freq;
 
 static int clamp_set(struct wf_control *ct, s32 value)
 {
-	if (value)
+	unsigned int freq;
+
+	if (value) {
+		freq = min_freq;
 		printk(KERN_INFO "windfarm: Clamping CPU frequency to "
 		       "minimum !\n");
-	else
+	} else {
+		freq = max_freq;
 		printk(KERN_INFO "windfarm: CPU frequency unclamped !\n");
+	}
 	clamped = value;
-	cpufreq_update_policy(0);
-	return 0;
+
+	return dev_pm_qos_update_request(&qos_req, freq);
 }
 
 static int clamp_get(struct wf_control *ct, s32 *value)
@@ -74,27 +64,60 @@ static const struct wf_control_ops clamp_ops = {
 
 static int __init wf_cpufreq_clamp_init(void)
 {
+	struct cpufreq_policy *policy;
 	struct wf_control *clamp;
+	struct device *dev;
+	int ret;
+
+	policy = cpufreq_cpu_get(0);
+	if (!policy) {
+		pr_warn("%s: cpufreq policy not found cpu0\n", __func__);
+		return -EPROBE_DEFER;
+	}
+
+	min_freq = policy->cpuinfo.min_freq;
+	max_freq = policy->cpuinfo.max_freq;
+	cpufreq_cpu_put(policy);
+
+	dev = get_cpu_device(0);
+	if (unlikely(!dev)) {
+		pr_warn("%s: No cpu device for cpu0\n", __func__);
+		return -ENODEV;
+	}
 
 	clamp = kmalloc(sizeof(struct wf_control), GFP_KERNEL);
 	if (clamp == NULL)
 		return -ENOMEM;
-	cpufreq_register_notifier(&clamp_notifier, CPUFREQ_POLICY_NOTIFIER);
+
+	ret = dev_pm_qos_add_request(dev, &qos_req, DEV_PM_QOS_MAX_FREQUENCY,
+				     max_freq);
+	if (ret < 0) {
+		pr_err("%s: Failed to add freq constraint (%d)\n", __func__,
+		       ret);
+		goto free;
+	}
+
 	clamp->ops = &clamp_ops;
 	clamp->name = "cpufreq-clamp";
-	if (wf_register_control(clamp))
+	ret = wf_register_control(clamp);
+	if (ret)
 		goto fail;
 	clamp_control = clamp;
 	return 0;
  fail:
+	dev_pm_qos_remove_request(&qos_req);
+
+ free:
 	kfree(clamp);
-	return -ENODEV;
+	return ret;
 }
 
 static void __exit wf_cpufreq_clamp_exit(void)
 {
-	if (clamp_control)
+	if (clamp_control) {
 		wf_unregister_control(clamp_control);
+		dev_pm_qos_remove_request(&qos_req);
+	}
 }
 
 
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index c094d5d20fd7..3b7ffd0234e9 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -401,6 +401,54 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
 
+/**
+ * dev_pm_opp_find_level_exact() - search for an exact level
+ * @dev:		device for which we do this operation
+ * @level:		level to search for
+ *
+ * Return: Searches for exact match in the opp table and returns pointer to the
+ * matching opp if found, else returns ERR_PTR in case of error and should
+ * be handled using IS_ERR. Error return values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev,
+					       unsigned int level)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		int r = PTR_ERR(opp_table);
+
+		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
+		return ERR_PTR(r);
+	}
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->level == level) {
+			opp = temp_opp;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
+			break;
+		}
+	}
+
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_exact);
+
 static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
 						   unsigned long *freq)
 {
@@ -940,6 +988,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index)
 	BLOCKING_INIT_NOTIFIER_HEAD(&opp_table->head);
 	INIT_LIST_HEAD(&opp_table->opp_list);
 	kref_init(&opp_table->kref);
+	kref_init(&opp_table->list_kref);
 
 	/* Secure the device table modification */
 	list_add(&opp_table->node, &opp_tables);
@@ -1577,6 +1626,12 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 			goto free_regulators;
 		}
 
+		ret = regulator_enable(reg);
+		if (ret < 0) {
+			regulator_put(reg);
+			goto free_regulators;
+		}
+
 		opp_table->regulators[i] = reg;
 	}
 
@@ -1590,8 +1645,10 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 	return opp_table;
 
 free_regulators:
-	while (i != 0)
-		regulator_put(opp_table->regulators[--i]);
+	while (i--) {
+		regulator_disable(opp_table->regulators[i]);
+		regulator_put(opp_table->regulators[i]);
+	}
 
 	kfree(opp_table->regulators);
 	opp_table->regulators = NULL;
@@ -1617,8 +1674,10 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	for (i = opp_table->regulator_count - 1; i >= 0; i--)
+	for (i = opp_table->regulator_count - 1; i >= 0; i--) {
+		regulator_disable(opp_table->regulators[i]);
 		regulator_put(opp_table->regulators[i]);
+	}
 
 	_free_set_opp_data(opp_table);
 
@@ -1771,6 +1830,7 @@ static void _opp_detach_genpd(struct opp_table *opp_table)
  * dev_pm_opp_attach_genpd - Attach genpd(s) for the device and save virtual device pointer
  * @dev: Consumer device for which the genpd is getting attached.
  * @names: Null terminated array of pointers containing names of genpd to attach.
+ * @virt_devs: Pointer to return the array of virtual devices.
  *
  * Multiple generic power domains for a device are supported with the help of
  * virtual genpd devices, which are created for each consumer device - genpd
@@ -1784,12 +1844,16 @@ static void _opp_detach_genpd(struct opp_table *opp_table)
  *
  * This helper needs to be called once with a list of all genpd to attach.
  * Otherwise the original device structure will be used instead by the OPP core.
+ *
+ * The order of entries in the names array must match the order in which
+ * "required-opps" are added in DT.
  */
-struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names)
+struct opp_table *dev_pm_opp_attach_genpd(struct device *dev,
+		const char **names, struct device ***virt_devs)
 {
 	struct opp_table *opp_table;
 	struct device *virt_dev;
-	int index, ret = -EINVAL;
+	int index = 0, ret = -EINVAL;
 	const char **name = names;
 
 	opp_table = dev_pm_opp_get_opp_table(dev);
@@ -1815,14 +1879,6 @@ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names
 		goto unlock;
 
 	while (*name) {
-		index = of_property_match_string(dev->of_node,
-						 "power-domain-names", *name);
-		if (index < 0) {
-			dev_err(dev, "Failed to find power domain: %s (%d)\n",
-				*name, index);
-			goto err;
-		}
-
 		if (index >= opp_table->required_opp_count) {
 			dev_err(dev, "Index can't be greater than required-opp-count - 1, %s (%d : %d)\n",
 				*name, opp_table->required_opp_count, index);
@@ -1843,9 +1899,12 @@ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names
 		}
 
 		opp_table->genpd_virt_devs[index] = virt_dev;
+		index++;
 		name++;
 	}
 
+	if (virt_devs)
+		*virt_devs = opp_table->genpd_virt_devs;
 	mutex_unlock(&opp_table->genpd_virt_dev_lock);
 
 	return opp_table;
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index b313aca9894f..1813f5ad5fa2 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -617,9 +617,12 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table,
 	/* OPP to select on device suspend */
 	if (of_property_read_bool(np, "opp-suspend")) {
 		if (opp_table->suspend_opp) {
-			dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n",
-				 __func__, opp_table->suspend_opp->rate,
-				 new_opp->rate);
+			/* Pick the OPP with higher rate as suspend OPP */
+			if (new_opp->rate > opp_table->suspend_opp->rate) {
+				opp_table->suspend_opp->suspend = false;
+				new_opp->suspend = true;
+				opp_table->suspend_opp = new_opp;
+			}
 		} else {
 			new_opp->suspend = true;
 			opp_table->suspend_opp = new_opp;
@@ -662,8 +665,6 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table)
 		return 0;
 	}
 
-	kref_init(&opp_table->list_kref);
-
 	/* We have opp-table node now, iterate over it and add OPPs */
 	for_each_available_child_of_node(opp_table->np, np) {
 		opp = _opp_add_static_v2(opp_table, dev, np);
@@ -672,17 +673,15 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table)
 			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
 				ret);
 			of_node_put(np);
-			goto put_list_kref;
+			return ret;
 		} else if (opp) {
 			count++;
 		}
 	}
 
 	/* There should be one of more OPP defined */
-	if (WARN_ON(!count)) {
-		ret = -ENOENT;
-		goto put_list_kref;
-	}
+	if (WARN_ON(!count))
+		return -ENOENT;
 
 	list_for_each_entry(opp, &opp_table->opp_list, node)
 		pstate_count += !!opp->pstate;
@@ -691,8 +690,7 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table)
 	if (pstate_count && pstate_count != count) {
 		dev_err(dev, "Not all nodes have performance state set (%d: %d)\n",
 			count, pstate_count);
-		ret = -ENOENT;
-		goto put_list_kref;
+		return -ENOENT;
 	}
 
 	if (pstate_count)
@@ -701,11 +699,6 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table)
 	opp_table->parsed_static_opps = true;
 
 	return 0;
-
-put_list_kref:
-	_put_opp_list_kref(opp_table);
-
-	return ret;
 }
 
 /* Initializes OPP tables based on old-deprecated bindings */
@@ -731,8 +724,6 @@ static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table)
 		return -EINVAL;
 	}
 
-	kref_init(&opp_table->list_kref);
-
 	val = prop->value;
 	while (nr) {
 		unsigned long freq = be32_to_cpup(val++) * 1000;
@@ -742,7 +733,6 @@ static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table)
 		if (ret) {
 			dev_err(dev, "%s: Failed to add OPP %ld (%d)\n",
 				__func__, freq, ret);
-			_put_opp_list_kref(opp_table);
 			return ret;
 		}
 		nr -= 2;
diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index bc0d55a59015..ef6d4bd77b1a 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -253,35 +253,45 @@ static void intel_button_array_enable(struct device *device, bool enable)
 
 static int intel_hid_pm_prepare(struct device *device)
 {
-	struct intel_hid_priv *priv = dev_get_drvdata(device);
+	if (device_may_wakeup(device)) {
+		struct intel_hid_priv *priv = dev_get_drvdata(device);
 
-	priv->wakeup_mode = true;
+		priv->wakeup_mode = true;
+	}
 	return 0;
 }
 
+static void intel_hid_pm_complete(struct device *device)
+{
+	struct intel_hid_priv *priv = dev_get_drvdata(device);
+
+	priv->wakeup_mode = false;
+}
+
 static int intel_hid_pl_suspend_handler(struct device *device)
 {
-	if (pm_suspend_via_firmware()) {
+	intel_button_array_enable(device, false);
+
+	if (!pm_suspend_no_platform())
 		intel_hid_set_enable(device, false);
-		intel_button_array_enable(device, false);
-	}
+
 	return 0;
 }
 
 static int intel_hid_pl_resume_handler(struct device *device)
 {
-	struct intel_hid_priv *priv = dev_get_drvdata(device);
+	intel_hid_pm_complete(device);
 
-	priv->wakeup_mode = false;
-	if (pm_resume_via_firmware()) {
+	if (!pm_suspend_no_platform())
 		intel_hid_set_enable(device, true);
-		intel_button_array_enable(device, true);
-	}
+
+	intel_button_array_enable(device, true);
 	return 0;
 }
 
 static const struct dev_pm_ops intel_hid_pl_pm_ops = {
 	.prepare = intel_hid_pm_prepare,
+	.complete = intel_hid_pm_complete,
 	.freeze  = intel_hid_pl_suspend_handler,
 	.thaw  = intel_hid_pl_resume_handler,
 	.restore  = intel_hid_pl_resume_handler,
@@ -491,6 +501,12 @@ static int intel_hid_probe(struct platform_device *device)
 	}
 
 	device_init_wakeup(&device->dev, true);
+	/*
+	 * In order for system wakeup to work, the EC GPE has to be marked as
+	 * a wakeup one, so do that here (this setting will persist, but it has
+	 * no effect until the wakeup mask is set for the EC GPE).
+	 */
+	acpi_ec_mark_gpe_for_wake();
 	return 0;
 
 err_remove_notify:
diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c
index a0d0cecff55f..b74932307d69 100644
--- a/drivers/platform/x86/intel-vbtn.c
+++ b/drivers/platform/x86/intel-vbtn.c
@@ -176,6 +176,12 @@ static int intel_vbtn_probe(struct platform_device *device)
 		return -EBUSY;
 
 	device_init_wakeup(&device->dev, true);
+	/*
+	 * In order for system wakeup to work, the EC GPE has to be marked as
+	 * a wakeup one, so do that here (this setting will persist, but it has
+	 * no effect until the wakeup mask is set for the EC GPE).
+	 */
+	acpi_ec_mark_gpe_for_wake();
 	return 0;
 }
 
@@ -195,22 +201,30 @@ static int intel_vbtn_remove(struct platform_device *device)
 
 static int intel_vbtn_pm_prepare(struct device *dev)
 {
-	struct intel_vbtn_priv *priv = dev_get_drvdata(dev);
+	if (device_may_wakeup(dev)) {
+		struct intel_vbtn_priv *priv = dev_get_drvdata(dev);
 
-	priv->wakeup_mode = true;
+		priv->wakeup_mode = true;
+	}
 	return 0;
 }
 
-static int intel_vbtn_pm_resume(struct device *dev)
+static void intel_vbtn_pm_complete(struct device *dev)
 {
 	struct intel_vbtn_priv *priv = dev_get_drvdata(dev);
 
 	priv->wakeup_mode = false;
+}
+
+static int intel_vbtn_pm_resume(struct device *dev)
+{
+	intel_vbtn_pm_complete(dev);
 	return 0;
 }
 
 static const struct dev_pm_ops intel_vbtn_pm_ops = {
 	.prepare = intel_vbtn_pm_prepare,
+	.complete = intel_vbtn_pm_complete,
 	.resume = intel_vbtn_pm_resume,
 	.restore = intel_vbtn_pm_resume,
 	.thaw = intel_vbtn_pm_resume,
diff --git a/drivers/powercap/idle_inject.c b/drivers/powercap/idle_inject.c
index 24ff2a068978..cd1270614cc6 100644
--- a/drivers/powercap/idle_inject.c
+++ b/drivers/powercap/idle_inject.c
@@ -59,14 +59,14 @@ struct idle_inject_thread {
 /**
  * struct idle_inject_device - idle injection data
  * @timer: idle injection period timer
- * @idle_duration_ms: duration of CPU idle time to inject
- * @run_duration_ms: duration of CPU run time to allow
+ * @idle_duration_us: duration of CPU idle time to inject
+ * @run_duration_us: duration of CPU run time to allow
  * @cpumask: mask of CPUs affected by idle injection
  */
 struct idle_inject_device {
 	struct hrtimer timer;
-	unsigned int idle_duration_ms;
-	unsigned int run_duration_ms;
+	unsigned int idle_duration_us;
+	unsigned int run_duration_us;
 	unsigned long int cpumask[0];
 };
 
@@ -104,16 +104,16 @@ static void idle_inject_wakeup(struct idle_inject_device *ii_dev)
  */
 static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
 {
-	unsigned int duration_ms;
+	unsigned int duration_us;
 	struct idle_inject_device *ii_dev =
 		container_of(timer, struct idle_inject_device, timer);
 
-	duration_ms = READ_ONCE(ii_dev->run_duration_ms);
-	duration_ms += READ_ONCE(ii_dev->idle_duration_ms);
+	duration_us = READ_ONCE(ii_dev->run_duration_us);
+	duration_us += READ_ONCE(ii_dev->idle_duration_us);
 
 	idle_inject_wakeup(ii_dev);
 
-	hrtimer_forward_now(timer, ms_to_ktime(duration_ms));
+	hrtimer_forward_now(timer, ns_to_ktime(duration_us * NSEC_PER_USEC));
 
 	return HRTIMER_RESTART;
 }
@@ -138,35 +138,35 @@ static void idle_inject_fn(unsigned int cpu)
 	 */
 	iit->should_run = 0;
 
-	play_idle(READ_ONCE(ii_dev->idle_duration_ms));
+	play_idle(READ_ONCE(ii_dev->idle_duration_us));
 }
 
 /**
  * idle_inject_set_duration - idle and run duration update helper
- * @run_duration_ms: CPU run time to allow in milliseconds
- * @idle_duration_ms: CPU idle time to inject in milliseconds
+ * @run_duration_us: CPU run time to allow in microseconds
+ * @idle_duration_us: CPU idle time to inject in microseconds
  */
 void idle_inject_set_duration(struct idle_inject_device *ii_dev,
-			      unsigned int run_duration_ms,
-			      unsigned int idle_duration_ms)
+			      unsigned int run_duration_us,
+			      unsigned int idle_duration_us)
 {
-	if (run_duration_ms && idle_duration_ms) {
-		WRITE_ONCE(ii_dev->run_duration_ms, run_duration_ms);
-		WRITE_ONCE(ii_dev->idle_duration_ms, idle_duration_ms);
+	if (run_duration_us && idle_duration_us) {
+		WRITE_ONCE(ii_dev->run_duration_us, run_duration_us);
+		WRITE_ONCE(ii_dev->idle_duration_us, idle_duration_us);
 	}
 }
 
 /**
  * idle_inject_get_duration - idle and run duration retrieval helper
- * @run_duration_ms: memory location to store the current CPU run time
- * @idle_duration_ms: memory location to store the current CPU idle time
+ * @run_duration_us: memory location to store the current CPU run time
+ * @idle_duration_us: memory location to store the current CPU idle time
  */
 void idle_inject_get_duration(struct idle_inject_device *ii_dev,
-			      unsigned int *run_duration_ms,
-			      unsigned int *idle_duration_ms)
+			      unsigned int *run_duration_us,
+			      unsigned int *idle_duration_us)
 {
-	*run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
-	*idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+	*run_duration_us = READ_ONCE(ii_dev->run_duration_us);
+	*idle_duration_us = READ_ONCE(ii_dev->idle_duration_us);
 }
 
 /**
@@ -181,10 +181,10 @@ void idle_inject_get_duration(struct idle_inject_device *ii_dev,
  */
 int idle_inject_start(struct idle_inject_device *ii_dev)
 {
-	unsigned int idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
-	unsigned int run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	unsigned int idle_duration_us = READ_ONCE(ii_dev->idle_duration_us);
+	unsigned int run_duration_us = READ_ONCE(ii_dev->run_duration_us);
 
-	if (!idle_duration_ms || !run_duration_ms)
+	if (!idle_duration_us || !run_duration_us)
 		return -EINVAL;
 
 	pr_debug("Starting injecting idle cycles on CPUs '%*pbl'\n",
@@ -193,7 +193,8 @@ int idle_inject_start(struct idle_inject_device *ii_dev)
 	idle_inject_wakeup(ii_dev);
 
 	hrtimer_start(&ii_dev->timer,
-		      ms_to_ktime(idle_duration_ms + run_duration_ms),
+		      ns_to_ktime((idle_duration_us + run_duration_us) *
+				  NSEC_PER_USEC),
 		      HRTIMER_MODE_REL);
 
 	return 0;
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 4c5db59a619b..391f39776c6a 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -16,6 +16,7 @@
 #include <linux/err.h>
 #include <linux/idr.h>
 #include <linux/pm_opp.h>
+#include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/cpu_cooling.h>
@@ -66,8 +67,6 @@ struct time_in_idle {
  * @last_load: load measured by the latest call to cpufreq_get_requested_power()
  * @cpufreq_state: integer value representing the current state of cpufreq
  *	cooling	devices.
- * @clipped_freq: integer value representing the absolute value of the clipped
- *	frequency.
  * @max_level: maximum cooling level. One less than total number of valid
  *	cpufreq frequencies.
  * @freq_table: Freq table in descending order of frequencies
@@ -84,12 +83,12 @@ struct cpufreq_cooling_device {
 	int id;
 	u32 last_load;
 	unsigned int cpufreq_state;
-	unsigned int clipped_freq;
 	unsigned int max_level;
 	struct freq_table *freq_table;	/* In descending order */
 	struct cpufreq_policy *policy;
 	struct list_head node;
 	struct time_in_idle *idle_time;
+	struct dev_pm_qos_request qos_req;
 };
 
 static DEFINE_IDA(cpufreq_ida);
@@ -119,59 +118,6 @@ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev,
 }
 
 /**
- * cpufreq_thermal_notifier - notifier callback for cpufreq policy change.
- * @nb:	struct notifier_block * with callback info.
- * @event: value showing cpufreq event for which this function invoked.
- * @data: callback-specific data
- *
- * Callback to hijack the notification on cpufreq policy transition.
- * Every time there is a change in policy, we will intercept and
- * update the cpufreq policy with thermal constraints.
- *
- * Return: 0 (success)
- */
-static int cpufreq_thermal_notifier(struct notifier_block *nb,
-				    unsigned long event, void *data)
-{
-	struct cpufreq_policy *policy = data;
-	unsigned long clipped_freq;
-	struct cpufreq_cooling_device *cpufreq_cdev;
-
-	if (event != CPUFREQ_ADJUST)
-		return NOTIFY_DONE;
-
-	mutex_lock(&cooling_list_lock);
-	list_for_each_entry(cpufreq_cdev, &cpufreq_cdev_list, node) {
-		/*
-		 * A new copy of the policy is sent to the notifier and can't
-		 * compare that directly.
-		 */
-		if (policy->cpu != cpufreq_cdev->policy->cpu)
-			continue;
-
-		/*
-		 * policy->max is the maximum allowed frequency defined by user
-		 * and clipped_freq is the maximum that thermal constraints
-		 * allow.
-		 *
-		 * If clipped_freq is lower than policy->max, then we need to
-		 * readjust policy->max.
-		 *
-		 * But, if clipped_freq is greater than policy->max, we don't
-		 * need to do anything.
-		 */
-		clipped_freq = cpufreq_cdev->clipped_freq;
-
-		if (policy->max > clipped_freq)
-			cpufreq_verify_within_limits(policy, 0, clipped_freq);
-		break;
-	}
-	mutex_unlock(&cooling_list_lock);
-
-	return NOTIFY_OK;
-}
-
-/**
  * update_freq_table() - Update the freq table with power numbers
  * @cpufreq_cdev:	the cpufreq cooling device in which to update the table
  * @capacitance: dynamic power coefficient for these cpus
@@ -374,7 +320,6 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 				 unsigned long state)
 {
 	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
-	unsigned int clip_freq;
 
 	/* Request state should be less than max_level */
 	if (WARN_ON(state > cpufreq_cdev->max_level))
@@ -384,13 +329,10 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 	if (cpufreq_cdev->cpufreq_state == state)
 		return 0;
 
-	clip_freq = cpufreq_cdev->freq_table[state].frequency;
 	cpufreq_cdev->cpufreq_state = state;
-	cpufreq_cdev->clipped_freq = clip_freq;
-
-	cpufreq_update_policy(cpufreq_cdev->policy->cpu);
 
-	return 0;
+	return dev_pm_qos_update_request(&cpufreq_cdev->qos_req,
+				cpufreq_cdev->freq_table[state].frequency);
 }
 
 /**
@@ -554,11 +496,6 @@ static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = {
 	.power2state		= cpufreq_power2state,
 };
 
-/* Notifier for cpufreq policy change */
-static struct notifier_block thermal_cpufreq_notifier_block = {
-	.notifier_call = cpufreq_thermal_notifier,
-};
-
 static unsigned int find_next_max(struct cpufreq_frequency_table *table,
 				  unsigned int prev_max)
 {
@@ -596,9 +533,16 @@ __cpufreq_cooling_register(struct device_node *np,
 	struct cpufreq_cooling_device *cpufreq_cdev;
 	char dev_name[THERMAL_NAME_LENGTH];
 	unsigned int freq, i, num_cpus;
+	struct device *dev;
 	int ret;
 	struct thermal_cooling_device_ops *cooling_ops;
-	bool first;
+
+	dev = get_cpu_device(policy->cpu);
+	if (unlikely(!dev)) {
+		pr_warn("No cpu device for cpu %d\n", policy->cpu);
+		return ERR_PTR(-ENODEV);
+	}
+
 
 	if (IS_ERR_OR_NULL(policy)) {
 		pr_err("%s: cpufreq policy isn't valid: %p\n", __func__, policy);
@@ -671,25 +615,29 @@ __cpufreq_cooling_register(struct device_node *np,
 		cooling_ops = &cpufreq_cooling_ops;
 	}
 
+	ret = dev_pm_qos_add_request(dev, &cpufreq_cdev->qos_req,
+				     DEV_PM_QOS_MAX_FREQUENCY,
+				     cpufreq_cdev->freq_table[0].frequency);
+	if (ret < 0) {
+		pr_err("%s: Failed to add freq constraint (%d)\n", __func__,
+		       ret);
+		cdev = ERR_PTR(ret);
+		goto remove_ida;
+	}
+
 	cdev = thermal_of_cooling_device_register(np, dev_name, cpufreq_cdev,
 						  cooling_ops);
 	if (IS_ERR(cdev))
-		goto remove_ida;
-
-	cpufreq_cdev->clipped_freq = cpufreq_cdev->freq_table[0].frequency;
+		goto remove_qos_req;
 
 	mutex_lock(&cooling_list_lock);
-	/* Register the notifier for first cpufreq cooling device */
-	first = list_empty(&cpufreq_cdev_list);
 	list_add(&cpufreq_cdev->node, &cpufreq_cdev_list);
 	mutex_unlock(&cooling_list_lock);
 
-	if (first)
-		cpufreq_register_notifier(&thermal_cpufreq_notifier_block,
-					  CPUFREQ_POLICY_NOTIFIER);
-
 	return cdev;
 
+remove_qos_req:
+	dev_pm_qos_remove_request(&cpufreq_cdev->qos_req);
 remove_ida:
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
 free_table:
@@ -777,7 +725,6 @@ EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
 void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 {
 	struct cpufreq_cooling_device *cpufreq_cdev;
-	bool last;
 
 	if (!cdev)
 		return;
@@ -786,15 +733,10 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 
 	mutex_lock(&cooling_list_lock);
 	list_del(&cpufreq_cdev->node);
-	/* Unregister the notifier for the last cpufreq cooling device */
-	last = list_empty(&cpufreq_cdev_list);
 	mutex_unlock(&cooling_list_lock);
 
-	if (last)
-		cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block,
-					    CPUFREQ_POLICY_NOTIFIER);
-
 	thermal_cooling_device_unregister(cdev);
+	dev_pm_qos_remove_request(&cpufreq_cdev->qos_req);
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
 	kfree(cpufreq_cdev->idle_time);
 	kfree(cpufreq_cdev->freq_table);
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index 5149a817456b..53216dcbe173 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -430,7 +430,7 @@ static void clamp_idle_injection_func(struct kthread_work *work)
 	if (should_skip)
 		goto balance;
 
-	play_idle(jiffies_to_msecs(w_data->duration_jiffies));
+	play_idle(jiffies_to_usecs(w_data->duration_jiffies));
 
 balance:
 	if (clamping && w_data->clamping && cpu_online(w_data->cpu))
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index 4282cb117b92..f70c9f79622e 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -1678,24 +1678,6 @@ pxafb_freq_transition(struct notifier_block *nb, unsigned long val, void *data)
 	}
 	return 0;
 }
-
-static int
-pxafb_freq_policy(struct notifier_block *nb, unsigned long val, void *data)
-{
-	struct pxafb_info *fbi = TO_INF(nb, freq_policy);
-	struct fb_var_screeninfo *var = &fbi->fb.var;
-	struct cpufreq_policy *policy = data;
-
-	switch (val) {
-	case CPUFREQ_ADJUST:
-		pr_debug("min dma period: %d ps, "
-			"new clock %d kHz\n", pxafb_display_dma_period(var),
-			policy->max);
-		/* TODO: fill in min/max values */
-		break;
-	}
-	return 0;
-}
 #endif
 
 #ifdef CONFIG_PM
@@ -2400,11 +2382,8 @@ static int pxafb_probe(struct platform_device *dev)
 
 #ifdef CONFIG_CPU_FREQ
 	fbi->freq_transition.notifier_call = pxafb_freq_transition;
-	fbi->freq_policy.notifier_call = pxafb_freq_policy;
 	cpufreq_register_notifier(&fbi->freq_transition,
 				CPUFREQ_TRANSITION_NOTIFIER);
-	cpufreq_register_notifier(&fbi->freq_policy,
-				CPUFREQ_POLICY_NOTIFIER);
 #endif
 
 	/*
diff --git a/drivers/video/fbdev/pxafb.h b/drivers/video/fbdev/pxafb.h
index b641289c8a99..86b1e9ab1a38 100644
--- a/drivers/video/fbdev/pxafb.h
+++ b/drivers/video/fbdev/pxafb.h
@@ -162,7 +162,6 @@ struct pxafb_info {
 
 #ifdef CONFIG_CPU_FREQ
 	struct notifier_block	freq_transition;
-	struct notifier_block	freq_policy;
 #endif
 
 	struct regulator *lcd_supply;
diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c
index f7f8dee044b1..ae2bcfee338a 100644
--- a/drivers/video/fbdev/sa1100fb.c
+++ b/drivers/video/fbdev/sa1100fb.c
@@ -1005,31 +1005,6 @@ sa1100fb_freq_transition(struct notifier_block *nb, unsigned long val,
 	}
 	return 0;
 }
-
-static int
-sa1100fb_freq_policy(struct notifier_block *nb, unsigned long val,
-		     void *data)
-{
-	struct sa1100fb_info *fbi = TO_INF(nb, freq_policy);
-	struct cpufreq_policy *policy = data;
-
-	switch (val) {
-	case CPUFREQ_ADJUST:
-		dev_dbg(fbi->dev, "min dma period: %d ps, "
-			"new clock %d kHz\n", sa1100fb_min_dma_period(fbi),
-			policy->max);
-		/* todo: fill in min/max values */
-		break;
-	case CPUFREQ_NOTIFY:
-		do {} while(0);
-		/* todo: panic if min/max values aren't fulfilled 
-		 * [can't really happen unless there's a bug in the
-		 * CPU policy verififcation process *
-		 */
-		break;
-	}
-	return 0;
-}
 #endif
 
 #ifdef CONFIG_PM
@@ -1242,9 +1217,7 @@ static int sa1100fb_probe(struct platform_device *pdev)
 
 #ifdef CONFIG_CPU_FREQ
 	fbi->freq_transition.notifier_call = sa1100fb_freq_transition;
-	fbi->freq_policy.notifier_call = sa1100fb_freq_policy;
 	cpufreq_register_notifier(&fbi->freq_transition, CPUFREQ_TRANSITION_NOTIFIER);
-	cpufreq_register_notifier(&fbi->freq_policy, CPUFREQ_POLICY_NOTIFIER);
 #endif
 
 	/* This driver cannot be unloaded at the moment */
diff --git a/drivers/video/fbdev/sa1100fb.h b/drivers/video/fbdev/sa1100fb.h
index 7a1a9ca33cec..d0aa33b0b88a 100644
--- a/drivers/video/fbdev/sa1100fb.h
+++ b/drivers/video/fbdev/sa1100fb.h
@@ -64,7 +64,6 @@ struct sa1100fb_info {
 
 #ifdef CONFIG_CPU_FREQ
 	struct notifier_block	freq_transition;
-	struct notifier_block	freq_policy;
 #endif
 
 	const struct sa1100fb_mach_info *inf;