Merge branch 'pm-cpufreq'

* pm-cpufreq: (36 commits)
  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
  sched/cpufreq: Align trace event behavior of fast switching
  ACPI: cpufreq: Switch to QoS requests instead of cpufreq notifier
  video: pxafb: Remove cpufreq policy notifier
  video: sa1100fb: Remove cpufreq policy notifier
  arch_topology: Use CPUFREQ_CREATE_POLICY instead of CPUFREQ_NOTIFY
  cpufreq: powerpc_cbe: Switch to QoS requests for freq limits
  cpufreq: powerpc: macintosh: Switch to QoS requests for freq limits
  cpufreq: Print driver name if cpufreq_suspend() fails
  cpufreq: mediatek: Add support for mt8183
  cpufreq: mediatek: change to regulator_get_optional
  cpufreq: imx-cpufreq-dt: Add i.MX8MN support
  cpufreq: Use imx-cpufreq-dt for i.MX8MN's speed grading
  ...

Documentation/cpu-freq/core.txt

@@ -57,19 +57,11 @@ transition notifiers.
 2.1 CPUFreq policy notifiers
 ----------------------------
 
-These are notified when a new policy is intended to be set. Each
-CPUFreq policy notifier is called twice for a policy transition:
+These are notified when a new policy is created or removed.
 
-1.) During CPUFREQ_ADJUST all CPUFreq notifiers may change the limit if
-    they see a need for this - may it be thermal considerations or
-    hardware limitations.
-
-2.) And during CPUFREQ_NOTIFY all notifiers are informed of the new policy
-   - if two hardware drivers failed to agree on a new policy before this
-   stage, the incompatible hardware shall be shut down, and the user
-   informed of this.
-
-The phase is specified in the second argument to the notifier.
+The phase is specified in the second argument to the notifier.  The phase is
+CPUFREQ_CREATE_POLICY when the policy is first created and it is
+CPUFREQ_REMOVE_POLICY when the policy is removed.
 
 The third argument, a void *pointer, points to a struct cpufreq_policy
 consisting of several values, including min, max (the lower and upper

Documentation/devicetree/bindings/opp/kryo-cpufreq.txt → Documentation/devicetree/bindings/opp/qcom-nvmem-cpufreq.txt

-Qualcomm Technologies, Inc. KRYO CPUFreq and OPP bindings
+Qualcomm Technologies, Inc. NVMEM CPUFreq and OPP bindings
 ===================================
 
-In Certain Qualcomm Technologies, Inc. SoCs like apq8096 and msm8996
-that have KRYO processors, the CPU ferequencies subset and voltage value
-of each OPP varies based on the silicon variant in use.
+In Certain Qualcomm Technologies, Inc. SoCs like apq8096 and msm8996,
+the CPU frequencies subset and voltage value of each OPP varies based on
+the silicon variant in use.
 Qualcomm Technologies, Inc. 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
+The qcom-cpufreq-nvmem driver reads the msm-id and efuse value from the SoC
 to provide the OPP framework with required information (existing HW bitmap).
 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.
 
 Required properties:
 --------------------
-In 'cpus' nodes:
+In 'cpu' nodes:
 - operating-points-v2: Phandle to the operating-points-v2 table to use.
 
 In 'operating-points-v2' table:
 - compatible: Should be
 	- 'operating-points-v2-kryo-cpu' for apq8096 and msm8996.
+
+Optional properties:
+--------------------
+In 'cpu' nodes:
+- power-domains: A phandle pointing to the PM domain specifier which provides
+		the performance states available for active state management.
+		Please refer to the power-domains bindings
+		Documentation/devicetree/bindings/power/power_domain.txt
+		and also examples below.
+- power-domain-names: Should be
+	- 'cpr' for qcs404.
+
+In 'operating-points-v2' table:
 - nvmem-cells: A phandle pointing to a nvmem-cells node representing the
 		efuse registers that has information about the
 		speedbin that is used to select the right frequency/voltage
@@ -678,3 +691,105 @@ soc {
 		};
 	};
 };
+
+Example 2:
+---------
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		CPU0: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			reg = <0x100>;
+			....
+			clocks = <&apcs_glb>;
+			operating-points-v2 = <&cpu_opp_table>;
+			power-domains = <&cpr>;
+			power-domain-names = "cpr";
+		};
+
+		CPU1: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			reg = <0x101>;
+			....
+			clocks = <&apcs_glb>;
+			operating-points-v2 = <&cpu_opp_table>;
+			power-domains = <&cpr>;
+			power-domain-names = "cpr";
+		};
+
+		CPU2: cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			reg = <0x102>;
+			....
+			clocks = <&apcs_glb>;
+			operating-points-v2 = <&cpu_opp_table>;
+			power-domains = <&cpr>;
+			power-domain-names = "cpr";
+		};
+
+		CPU3: cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53";
+			reg = <0x103>;
+			....
+			clocks = <&apcs_glb>;
+			operating-points-v2 = <&cpu_opp_table>;
+			power-domains = <&cpr>;
+			power-domain-names = "cpr";
+		};
+	};
+
+	cpu_opp_table: cpu-opp-table {
+		compatible = "operating-points-v2-kryo-cpu";
+		opp-shared;
+
+		opp-1094400000 {
+			opp-hz = /bits/ 64 <1094400000>;
+			required-opps = <&cpr_opp1>;
+		};
+		opp-1248000000 {
+			opp-hz = /bits/ 64 <1248000000>;
+			required-opps = <&cpr_opp2>;
+		};
+		opp-1401600000 {
+			opp-hz = /bits/ 64 <1401600000>;
+			required-opps = <&cpr_opp3>;
+		};
+	};
+
+	cpr_opp_table: cpr-opp-table {
+		compatible = "operating-points-v2-qcom-level";
+
+		cpr_opp1: opp1 {
+			opp-level = <1>;
+			qcom,opp-fuse-level = <1>;
+		};
+		cpr_opp2: opp2 {
+			opp-level = <2>;
+			qcom,opp-fuse-level = <2>;
+		};
+		cpr_opp3: opp3 {
+			opp-level = <3>;
+			qcom,opp-fuse-level = <3>;
+		};
+	};
+
+....
+
+soc {
+....
+	cpr: power-controller@b018000 {
+		compatible = "qcom,qcs404-cpr", "qcom,cpr";
+		reg = <0x0b018000 0x1000>;
+		....
+		vdd-apc-supply = <&pms405_s3>;
+		#power-domain-cells = <0>;
+		operating-points-v2 = <&cpr_opp_table>;
+		....
+	};
+};

Documentation/devicetree/bindings/opp/qcom-opp.txt

+Qualcomm OPP bindings to describe OPP nodes
+
+The bindings are based on top of the operating-points-v2 bindings
+described in Documentation/devicetree/bindings/opp/opp.txt
+Additional properties are described below.
+
+* OPP Table Node
+
+Required properties:
+- compatible: Allow OPPs to express their compatibility. It should be:
+  "operating-points-v2-qcom-level"
+
+* OPP Node
+
+Required properties:
+- qcom,opp-fuse-level: A positive value representing the fuse corner/level
+  associated with this OPP node. Sometimes several corners/levels shares
+  a certain fuse corner/level. A fuse corner/level contains e.g. ref uV,
+  min uV, and max uV.

Documentation/devicetree/bindings/opp/sun50i-nvmem-cpufreq.txt

+Allwinner Technologies, Inc. NVMEM CPUFreq and OPP bindings
+===================================
+
+For some SoCs, the CPU frequency subset and voltage value of each OPP
+varies based on the silicon variant in use. Allwinner Process Voltage
+Scaling Tables defines the voltage and frequency value based on the
+speedbin blown in the efuse combination. The sun50i-cpufreq-nvmem driver
+reads the efuse value from the SoC to provide the OPP framework with
+required information.
+
+Required properties:
+--------------------
+In 'cpus' nodes:
+- operating-points-v2: Phandle to the operating-points-v2 table to use.
+
+In 'operating-points-v2' table:
+- compatible: Should be
+	- 'allwinner,sun50i-h6-operating-points'.
+- nvmem-cells: A phandle pointing to a nvmem-cells node representing the
+		efuse registers that has information about the speedbin
+		that is used to select the right frequency/voltage value
+		pair. Please refer the for nvmem-cells bindings
+		Documentation/devicetree/bindings/nvmem/nvmem.txt and
+		also examples below.
+
+In every OPP node:
+- opp-microvolt-<name>: Voltage in micro Volts.
+			At runtime, the platform can pick a <name> and
+			matching opp-microvolt-<name> property.
+			[See: opp.txt]
+			HW:		<name>:
+			sun50i-h6	speed0 speed1 speed2
+
+Example 1:
+---------
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			compatible = "arm,cortex-a53";
+			device_type = "cpu";
+			reg = <0>;
+			enable-method = "psci";
+			clocks = <&ccu CLK_CPUX>;
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			operating-points-v2 = <&cpu_opp_table>;
+			#cooling-cells = <2>;
+		};
+
+		cpu1: cpu@1 {
+			compatible = "arm,cortex-a53";
+			device_type = "cpu";
+			reg = <1>;
+			enable-method = "psci";
+			clocks = <&ccu CLK_CPUX>;
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			operating-points-v2 = <&cpu_opp_table>;
+			#cooling-cells = <2>;
+		};
+
+		cpu2: cpu@2 {
+			compatible = "arm,cortex-a53";
+			device_type = "cpu";
+			reg = <2>;
+			enable-method = "psci";
+			clocks = <&ccu CLK_CPUX>;
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			operating-points-v2 = <&cpu_opp_table>;
+			#cooling-cells = <2>;
+		};
+
+		cpu3: cpu@3 {
+			compatible = "arm,cortex-a53";
+			device_type = "cpu";
+			reg = <3>;
+			enable-method = "psci";
+			clocks = <&ccu CLK_CPUX>;
+			clock-latency-ns = <244144>; /* 8 32k periods */
+			operating-points-v2 = <&cpu_opp_table>;
+			#cooling-cells = <2>;
+		};
+        };
+
+        cpu_opp_table: opp_table {
+                compatible = "allwinner,sun50i-h6-operating-points";
+                nvmem-cells = <&speedbin_efuse>;
+                opp-shared;
+
+                opp@480000000 {
+                        clock-latency-ns = <244144>; /* 8 32k periods */
+                        opp-hz = /bits/ 64 <480000000>;
+
+                        opp-microvolt-speed0 = <880000>;
+                        opp-microvolt-speed1 = <820000>;
+                        opp-microvolt-speed2 = <800000>;
+                };
+
+                opp@720000000 {
+                        clock-latency-ns = <244144>; /* 8 32k periods */
+                        opp-hz = /bits/ 64 <720000000>;
+
+                        opp-microvolt-speed0 = <880000>;
+                        opp-microvolt-speed1 = <820000>;
+                        opp-microvolt-speed2 = <800000>;
+                };
+
+                opp@816000000 {
+                        clock-latency-ns = <244144>; /* 8 32k periods */
+                        opp-hz = /bits/ 64 <816000000>;
+
+                        opp-microvolt-speed0 = <880000>;
+                        opp-microvolt-speed1 = <820000>;
+                        opp-microvolt-speed2 = <800000>;
+                };
+
+                opp@888000000 {
+                        clock-latency-ns = <244144>; /* 8 32k periods */
+                        opp-hz = /bits/ 64 <888000000>;
+
+                        opp-microvolt-speed0 = <940000>;
+                        opp-microvolt-speed1 = <820000>;
+                        opp-microvolt-speed2 = <800000>;
+                };
+
+                opp@1080000000 {
+                        clock-latency-ns = <244144>; /* 8 32k periods */
+                        opp-hz = /bits/ 64 <1080000000>;
+
+                        opp-microvolt-speed0 = <1060000>;
+                        opp-microvolt-speed1 = <880000>;
+                        opp-microvolt-speed2 = <840000>;
+                };
+
+                opp@1320000000 {
+                        clock-latency-ns = <244144>; /* 8 32k periods */
+                        opp-hz = /bits/ 64 <1320000000>;
+
+                        opp-microvolt-speed0 = <1160000>;
+                        opp-microvolt-speed1 = <940000>;
+                        opp-microvolt-speed2 = <900000>;
+                };
+
+                opp@1488000000 {
+                        clock-latency-ns = <244144>; /* 8 32k periods */
+                        opp-hz = /bits/ 64 <1488000000>;
+
+                        opp-microvolt-speed0 = <1160000>;
+                        opp-microvolt-speed1 = <1000000>;
+                        opp-microvolt-speed2 = <960000>;
+                };
+        };
+....
+soc {
+....
+	sid: sid@3006000 {
+		compatible = "allwinner,sun50i-h6-sid";
+		reg = <0x03006000 0x400>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		....
+		speedbin_efuse: speed@1c {
+			reg = <0x1c 4>;
+		};
+        };
+};

MAINTAINERS

@@ -676,6 +676,13 @@ L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	drivers/staging/media/allegro-dvt/
 
+ALLWINNER CPUFREQ DRIVER
+M:	Yangtao Li <tiny.windzz@gmail.com>
+L:	linux-pm@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/opp/sun50i-nvmem-cpufreq.txt
+F:	drivers/cpufreq/sun50i-cpufreq-nvmem.c
+
 ALLWINNER SECURITY SYSTEM
 M:	Corentin Labbe <clabbe.montjoie@gmail.com>
 L:	linux-crypto@vger.kernel.org
@@ -13308,8 +13315,8 @@ QUALCOMM CPUFREQ DRIVER MSM8996/APQ8096
 M:	Ilia Lin <ilia.lin@kernel.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
-F:	Documentation/devicetree/bindings/opp/kryo-cpufreq.txt
-F:	drivers/cpufreq/qcom-cpufreq-kryo.c
+F:	Documentation/devicetree/bindings/opp/qcom-nvmem-cpufreq.txt
+F:	drivers/cpufreq/qcom-cpufreq-nvmem.c
 
 QUALCOMM EMAC GIGABIT ETHERNET DRIVER
 M:	Timur Tabi <timur@kernel.org>

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);

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);

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)
 {

drivers/base/arch_topology.c

@@ -174,7 +174,7 @@ 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",

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

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

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);
 
 	/*

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", },

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);

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;
 
 	/*

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",

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", },
 
 	{ }
 };

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);

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

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);

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;
 	}
 

drivers/cpufreq/sun50i-cpufreq-nvmem.c

+// 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");

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;
 	}

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);
+	}
 }
 
 

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)
 {
@@ -1771,6 +1819,7 @@ 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 +1833,16 @@ 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 +1868,6 @@ 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 +1888,12 @@ 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;

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);
@@ -118,59 +117,6 @@ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev,
 	return level - 1;
 }
 
-/**
- * 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
@@ -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);

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
 
 	/*

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;

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 */

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;

include/acpi/processor.h

@@ -4,6 +4,8 @@
 
 #include <linux/kernel.h>
 #include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/pm_qos.h>
 #include <linux/thermal.h>
 #include <asm/acpi.h>
 
@@ -230,6 +232,8 @@ struct acpi_processor {
 	struct acpi_processor_limit limit;
 	struct thermal_cooling_device *cdev;
 	struct device *dev; /* Processor device. */
+	struct dev_pm_qos_request perflib_req;
+	struct dev_pm_qos_request thermal_req;
 };
 
 struct acpi_processor_errata {
@@ -296,16 +300,22 @@ static inline void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx
 /* in processor_perflib.c */
 
 #ifdef CONFIG_CPU_FREQ
-void acpi_processor_ppc_init(void);
-void acpi_processor_ppc_exit(void);
+extern bool acpi_processor_cpufreq_init;
+void acpi_processor_ignore_ppc_init(void);
+void acpi_processor_ppc_init(int cpu);
+void acpi_processor_ppc_exit(int cpu);
 void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag);
 extern int acpi_processor_get_bios_limit(int cpu, unsigned int *limit);
 #else
-static inline void acpi_processor_ppc_init(void)
+static inline void acpi_processor_ignore_ppc_init(void)
 {
 	return;
 }
-static inline void acpi_processor_ppc_exit(void)
+static inline void acpi_processor_ppc_init(int cpu)
+{
+	return;
+}
+static inline void acpi_processor_ppc_exit(int cpu)
 {
 	return;
 }
@@ -421,14 +431,14 @@ static inline int acpi_processor_hotplug(struct acpi_processor *pr)
 int acpi_processor_get_limit_info(struct acpi_processor *pr);
 extern const struct thermal_cooling_device_ops processor_cooling_ops;
 #if defined(CONFIG_ACPI_CPU_FREQ_PSS) & defined(CONFIG_CPU_FREQ)
-void acpi_thermal_cpufreq_init(void);
-void acpi_thermal_cpufreq_exit(void);
+void acpi_thermal_cpufreq_init(int cpu);
+void acpi_thermal_cpufreq_exit(int cpu);
 #else
-static inline void acpi_thermal_cpufreq_init(void)
+static inline void acpi_thermal_cpufreq_init(int cpu)
 {
 	return;
 }
-static inline void acpi_thermal_cpufreq_exit(void)
+static inline void acpi_thermal_cpufreq_exit(int cpu)
 {
 	return;
 }

include/linux/cpufreq.h

@@ -456,8 +456,8 @@ static inline void cpufreq_resume(void) {}
 #define CPUFREQ_POSTCHANGE		(1)
 
 /* Policy Notifiers  */
-#define CPUFREQ_ADJUST			(0)
-#define CPUFREQ_NOTIFY			(1)
+#define CPUFREQ_CREATE_POLICY		(0)
+#define CPUFREQ_REMOVE_POLICY		(1)
 
 #ifdef CONFIG_CPU_FREQ
 int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list);

include/linux/pm_opp.h

@@ -96,6 +96,8 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev);
 struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					      unsigned long freq,
 					      bool available);
+struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev,
+					       unsigned int level);
 
 struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					      unsigned long *freq);
@@ -128,7 +130,7 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name);
 void dev_pm_opp_put_clkname(struct opp_table *opp_table);
 struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data));
 void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table);
-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);
 void dev_pm_opp_detach_genpd(struct opp_table *opp_table);
 int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate);
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
@@ -200,6 +202,12 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 	return ERR_PTR(-ENOTSUPP);
 }
 
+static inline struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev,
+					unsigned int level)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+
 static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					unsigned long *freq)
 {
@@ -292,7 +300,7 @@ static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const
 
 static inline void dev_pm_opp_put_clkname(struct opp_table *opp_table) {}
 
-static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names)
+static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs)
 {
 	return ERR_PTR(-ENOTSUPP);
 }

kernel/sched/cpufreq_schedutil.c

@@ -117,6 +117,7 @@ static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time,
 			      unsigned int next_freq)
 {
 	struct cpufreq_policy *policy = sg_policy->policy;
+	int cpu;
 
 	if (!sugov_update_next_freq(sg_policy, time, next_freq))
 		return;
@@ -126,7 +127,11 @@ static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time,
 		return;
 
 	policy->cur = next_freq;
-	trace_cpu_frequency(next_freq, smp_processor_id());
+
+	if (trace_cpu_frequency_enabled()) {
+		for_each_cpu(cpu, policy->cpus)
+			trace_cpu_frequency(next_freq, cpu);
+	}
 }
 
 static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time,