Merge tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These are PM-runtime framework changes to use ktime instead of jiffies
  for accounting, new PM core flag to mark devices that don't need any
  form of power management, cpuidle updates including driver API
  documentation and a new governor, cpufreq updates including a new
  driver for Armada 8K, thermal cleanups and more, some energy-aware
  scheduling (EAS) enabling changes, new chips support in the intel_idle
  and RAPL drivers and assorted cleanups in some other places.

  Specifics:

   - Update the PM-runtime framework to use ktime instead of jiffies for
     accounting (Thara Gopinath, Vincent Guittot)

   - Optimize the autosuspend code in the PM-runtime framework somewhat
     (Ladislav Michl)

   - Add a PM core flag to mark devices that don't need any form of
     power management (Sudeep Holla)

   - Introduce driver API documentation for cpuidle and add a new
     cpuidle governor for tickless systems (Rafael Wysocki)

   - Add Jacobsville support to the intel_idle driver (Zhang Rui)

   - Clean up a cpuidle core header file and the cpuidle-dt and ACPI
     processor-idle drivers (Yangtao Li, Joseph Lo, Yazen Ghannam)

   - Add new cpufreq driver for Armada 8K (Gregory Clement)

   - Fix and clean up cpufreq core (Rafael Wysocki, Viresh Kumar, Amit
     Kucheria)

   - Add support for light-weight tear-down and bring-up of CPUs to the
     cpufreq core and use it in the cpufreq-dt driver (Viresh Kumar)

   - Fix cpu_cooling Kconfig dependencies, add support for CPU cooling
     auto-registration to the cpufreq core and use it in multiple
     cpufreq drivers (Amit Kucheria)

   - Fix some minor issues and do some cleanups in the davinci,
     e_powersaver, ap806, s5pv210, qcom and kryo cpufreq drivers
     (Bartosz Golaszewski, Gustavo Silva, Julia Lawall, Paweł Chmiel,
     Taniya Das, Viresh Kumar)

   - Add a Hisilicon CPPC quirk to the cppc_cpufreq driver (Xiongfeng
     Wang)

   - Clean up the intel_pstate and acpi-cpufreq drivers (Erwan Velu,
     Rafael Wysocki)

   - Clean up multiple cpufreq drivers (Yangtao Li)

   - Update cpufreq-related MAINTAINERS entries (Baruch Siach, Lukas
     Bulwahn)

   - Add support for exposing the Energy Model via debugfs and make
     multiple cpufreq drivers register an Energy Model to support
     energy-aware scheduling (Quentin Perret, Dietmar Eggemann, Matthias
     Kaehlcke)

   - Add Ice Lake mobile and Jacobsville support to the Intel RAPL
     power-capping driver (Gayatri Kammela, Zhang Rui)

   - Add a power estimation helper to the operating performance points
     (OPP) framework and clean up a core function in it (Quentin Perret,
     Viresh Kumar)

   - Make minor improvements in the generic power domains (genpd), OPP
     and system suspend frameworks and in the PM core (Aditya Pakki,
     Douglas Anderson, Greg Kroah-Hartman, Rafael Wysocki, Yangtao Li)"

* tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (80 commits)
  cpufreq: kryo: Release OPP tables on module removal
  cpufreq: ap806: add missing of_node_put after of_device_is_available
  cpufreq: acpi-cpufreq: Report if CPU doesn't support boost technologies
  cpufreq: Pass updated policy to driver ->setpolicy() callback
  cpufreq: Fix two debug messages in cpufreq_set_policy()
  cpufreq: Reorder and simplify cpufreq_update_policy()
  cpufreq: Add kerneldoc comments for two core functions
  PM / core: Add support to skip power management in device/driver model
  cpufreq: intel_pstate: Rework iowait boosting to be less aggressive
  cpufreq: intel_pstate: Eliminate intel_pstate_get_base_pstate()
  cpufreq: intel_pstate: Avoid redundant initialization of local vars
  powercap/intel_rapl: add Ice Lake mobile
  ACPI / processor: Set P_LVL{2,3} idle state descriptions
  cpufreq / cppc: Work around for Hisilicon CPPC cpufreq
  ACPI / CPPC: Add a helper to get desired performance
  cpufreq: davinci: move configuration to include/linux/platform_data
  cpufreq: speedstep: convert BUG() to BUG_ON()
  cpufreq: powernv: fix missing check of return value in init_powernv_pstates()
  cpufreq: longhaul: remove unneeded semicolon
  cpufreq: pcc-cpufreq: remove unneeded semicolon
  ..

27 files changed, 640 insertions, 246 deletions

diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 608af20a3494..b22e6bba71f1 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -207,8 +207,6 @@ comment "CPU frequency scaling drivers"
 config CPUFREQ_DT
 	tristate "Generic DT based cpufreq driver"
 	depends on HAVE_CLK && OF
-	# if CPU_THERMAL is on and THERMAL=m, CPUFREQ_DT cannot be =y:
-	depends on !CPU_THERMAL || THERMAL
 	select CPUFREQ_DT_PLATDEV
 	select PM_OPP
 	help
@@ -327,7 +325,6 @@ endif
 config QORIQ_CPUFREQ
 	tristate "CPU frequency scaling driver for Freescale QorIQ SoCs"
 	depends on OF && COMMON_CLK && (PPC_E500MC || ARM || ARM64)
-	depends on !CPU_THERMAL || THERMAL
 	select CLK_QORIQ
 	help
 	  This adds the CPUFreq driver support for Freescale QorIQ SoCs
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 1a6778e81f90..179a1d302f48 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -25,12 +25,21 @@ config ARM_ARMADA_37XX_CPUFREQ
 	  This adds the CPUFreq driver support for Marvell Armada 37xx SoCs.
 	  The Armada 37xx PMU supports 4 frequency and VDD levels.
 
+config ARM_ARMADA_8K_CPUFREQ
+	tristate "Armada 8K CPUFreq driver"
+	depends on ARCH_MVEBU && CPUFREQ_DT
+	help
+	  This enables the CPUFreq driver support for Marvell
+	  Armada8k SOCs.
+	  Armada8K device has the AP806 which supports scaling
+	  to any full integer divider.
+
+	  If in doubt, say N.
+
 # big LITTLE core layer and glue drivers
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
 	depends on ARM_CPU_TOPOLOGY && HAVE_CLK
-	# if CPU_THERMAL is on and THERMAL=m, ARM_BIT_LITTLE_CPUFREQ cannot be =y
-	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
@@ -38,7 +47,6 @@ config ARM_BIG_LITTLE_CPUFREQ
 config ARM_SCPI_CPUFREQ
 	tristate "SCPI based CPUfreq driver"
 	depends on ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
-	depends on !CPU_THERMAL || THERMAL
 	help
 	  This adds the CPUfreq driver support for ARM platforms using SCPI
 	  protocol for CPU power management.
@@ -93,7 +101,6 @@ config ARM_KIRKWOOD_CPUFREQ
 config ARM_MEDIATEK_CPUFREQ
 	tristate "CPU Frequency scaling support for MediaTek SoCs"
 	depends on ARCH_MEDIATEK && REGULATOR
-	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This adds the CPUFreq driver support for MediaTek SoCs.
@@ -233,7 +240,6 @@ config ARM_SA1110_CPUFREQ
 config ARM_SCMI_CPUFREQ
 	tristate "SCMI based CPUfreq driver"
 	depends on ARM_SCMI_PROTOCOL || COMPILE_TEST
-	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This adds the CPUfreq driver support for ARM platforms using SCMI
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 08c071be2491..689b26c6f949 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_X86_SFI_CPUFREQ)		+= sfi-cpufreq.o
 obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ)	+= arm_big_little.o
 
 obj-$(CONFIG_ARM_ARMADA_37XX_CPUFREQ)	+= armada-37xx-cpufreq.o
+obj-$(CONFIG_ARM_ARMADA_8K_CPUFREQ)	+= armada-8k-cpufreq.o
 obj-$(CONFIG_ARM_BRCMSTB_AVS_CPUFREQ)	+= brcmstb-avs-cpufreq.o
 obj-$(CONFIG_ACPI_CPPC_CPUFREQ)		+= cppc_cpufreq.o
 obj-$(CONFIG_ARCH_DAVINCI)		+= davinci-cpufreq.o
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index d62fd374d5c7..c72258a44ba4 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -916,8 +916,10 @@ static void __init acpi_cpufreq_boost_init(void)
 {
 	int ret;
 
-	if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)))
+	if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA))) {
+		pr_debug("Boost capabilities not present in the processor\n");
 		return;
+	}
 
 	acpi_cpufreq_driver.set_boost = set_boost;
 	acpi_cpufreq_driver.boost_enabled = boost_state(0);
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index cf62a1f64dd7..7fe52fcddcf1 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -487,6 +487,8 @@ static int bL_cpufreq_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency =
 				arm_bL_ops->get_transition_latency(cpu_dev);
 
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	if (is_bL_switching_enabled())
 		per_cpu(cpu_last_req_freq, policy->cpu) = clk_get_cpu_rate(policy->cpu);
 
diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c
new file mode 100644
index 000000000000..b3f4bd647e9b
--- /dev/null
+++ b/drivers/cpufreq/armada-8k-cpufreq.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * CPUFreq support for Armada 8K
+ *
+ * Copyright (C) 2018 Marvell
+ *
+ * Omri Itach <omrii@marvell.com>
+ * Gregory Clement <gregory.clement@bootlin.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+
+/*
+ * Setup the opps list with the divider for the max frequency, that
+ * will be filled at runtime.
+ */
+static const int opps_div[] __initconst = {1, 2, 3, 4};
+
+static struct platform_device *armada_8k_pdev;
+
+struct freq_table {
+	struct device *cpu_dev;
+	unsigned int freq[ARRAY_SIZE(opps_div)];
+};
+
+/* If the CPUs share the same clock, then they are in the same cluster. */
+static void __init armada_8k_get_sharing_cpus(struct clk *cur_clk,
+					      struct cpumask *cpumask)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct device *cpu_dev;
+		struct clk *clk;
+
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_warn("Failed to get cpu%d device\n", cpu);
+			continue;
+		}
+
+		clk = clk_get(cpu_dev, 0);
+		if (IS_ERR(clk)) {
+			pr_warn("Cannot get clock for CPU %d\n", cpu);
+		} else {
+			if (clk_is_match(clk, cur_clk))
+				cpumask_set_cpu(cpu, cpumask);
+
+			clk_put(clk);
+		}
+	}
+}
+
+static int __init armada_8k_add_opp(struct clk *clk, struct device *cpu_dev,
+				    struct freq_table *freq_tables,
+				    int opps_index)
+{
+	unsigned int cur_frequency;
+	unsigned int freq;
+	int i, ret;
+
+	/* Get nominal (current) CPU frequency. */
+	cur_frequency = clk_get_rate(clk);
+	if (!cur_frequency) {
+		dev_err(cpu_dev, "Failed to get clock rate for this CPU\n");
+		return -EINVAL;
+	}
+
+	freq_tables[opps_index].cpu_dev = cpu_dev;
+
+	for (i = 0; i < ARRAY_SIZE(opps_div); i++) {
+		freq = cur_frequency / opps_div[i];
+
+		ret = dev_pm_opp_add(cpu_dev, freq, 0);
+		if (ret)
+			return ret;
+
+		freq_tables[opps_index].freq[i] = freq;
+	}
+
+	return 0;
+}
+
+static void armada_8k_cpufreq_free_table(struct freq_table *freq_tables)
+{
+	int opps_index, nb_cpus = num_possible_cpus();
+
+	for (opps_index = 0 ; opps_index <= nb_cpus; opps_index++) {
+		int i;
+
+		/* If cpu_dev is NULL then we reached the end of the array */
+		if (!freq_tables[opps_index].cpu_dev)
+			break;
+
+		for (i = 0; i < ARRAY_SIZE(opps_div); i++) {
+			/*
+			 * A 0Hz frequency is not valid, this meant
+			 * that it was not yet initialized so there is
+			 * no more opp to free
+			 */
+			if (freq_tables[opps_index].freq[i] == 0)
+				break;
+
+			dev_pm_opp_remove(freq_tables[opps_index].cpu_dev,
+					  freq_tables[opps_index].freq[i]);
+		}
+	}
+
+	kfree(freq_tables);
+}
+
+static int __init armada_8k_cpufreq_init(void)
+{
+	int ret = 0, opps_index = 0, cpu, nb_cpus;
+	struct freq_table *freq_tables;
+	struct device_node *node;
+	struct cpumask cpus;
+
+	node = of_find_compatible_node(NULL, NULL, "marvell,ap806-cpu-clock");
+	if (!node || !of_device_is_available(node)) {
+		of_node_put(node);
+		return -ENODEV;
+	}
+
+	nb_cpus = num_possible_cpus();
+	freq_tables = kcalloc(nb_cpus, sizeof(*freq_tables), GFP_KERNEL);
+	cpumask_copy(&cpus, cpu_possible_mask);
+
+	/*
+	 * For each CPU, this loop registers the operating points
+	 * supported (which are the nominal CPU frequency and full integer
+	 * divisions of it).
+	 */
+	for_each_cpu(cpu, &cpus) {
+		struct cpumask shared_cpus;
+		struct device *cpu_dev;
+		struct clk *clk;
+
+		cpu_dev = get_cpu_device(cpu);
+
+		if (!cpu_dev) {
+			pr_err("Cannot get CPU %d\n", cpu);
+			continue;
+		}
+
+		clk = clk_get(cpu_dev, 0);
+
+		if (IS_ERR(clk)) {
+			pr_err("Cannot get clock for CPU %d\n", cpu);
+			ret = PTR_ERR(clk);
+			goto remove_opp;
+		}
+
+		ret = armada_8k_add_opp(clk, cpu_dev, freq_tables, opps_index);
+		if (ret) {
+			clk_put(clk);
+			goto remove_opp;
+		}
+
+		opps_index++;
+		cpumask_clear(&shared_cpus);
+		armada_8k_get_sharing_cpus(clk, &shared_cpus);
+		dev_pm_opp_set_sharing_cpus(cpu_dev, &shared_cpus);
+		cpumask_andnot(&cpus, &cpus, &shared_cpus);
+		clk_put(clk);
+	}
+
+	armada_8k_pdev = platform_device_register_simple("cpufreq-dt", -1,
+							 NULL, 0);
+	ret = PTR_ERR_OR_ZERO(armada_8k_pdev);
+	if (ret)
+		goto remove_opp;
+
+	platform_set_drvdata(armada_8k_pdev, freq_tables);
+
+	return 0;
+
+remove_opp:
+	armada_8k_cpufreq_free_table(freq_tables);
+	return ret;
+}
+module_init(armada_8k_cpufreq_init);
+
+static void __exit armada_8k_cpufreq_exit(void)
+{
+	struct freq_table *freq_tables = platform_get_drvdata(armada_8k_pdev);
+
+	platform_device_unregister(armada_8k_pdev);
+	armada_8k_cpufreq_free_table(freq_tables);
+}
+module_exit(armada_8k_cpufreq_exit);
+
+MODULE_AUTHOR("Gregory Clement <gregory.clement@bootlin.com>");
+MODULE_DESCRIPTION("Armada 8K cpufreq driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index fd25c21cee72..2ae978d27e61 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -42,6 +42,66 @@
  */
 static struct cppc_cpudata **all_cpu_data;
 
+struct cppc_workaround_oem_info {
+	char oem_id[ACPI_OEM_ID_SIZE +1];
+	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
+	u32 oem_revision;
+};
+
+static bool apply_hisi_workaround;
+
+static struct cppc_workaround_oem_info wa_info[] = {
+	{
+		.oem_id		= "HISI  ",
+		.oem_table_id	= "HIP07   ",
+		.oem_revision	= 0,
+	}, {
+		.oem_id		= "HISI  ",
+		.oem_table_id	= "HIP08   ",
+		.oem_revision	= 0,
+	}
+};
+
+static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu,
+					unsigned int perf);
+
+/*
+ * HISI platform does not support delivered performance counter and
+ * reference performance counter. It can calculate the performance using the
+ * platform specific mechanism. We reuse the desired performance register to
+ * store the real performance calculated by the platform.
+ */
+static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpunum)
+{
+	struct cppc_cpudata *cpudata = all_cpu_data[cpunum];
+	u64 desired_perf;
+	int ret;
+
+	ret = cppc_get_desired_perf(cpunum, &desired_perf);
+	if (ret < 0)
+		return -EIO;
+
+	return cppc_cpufreq_perf_to_khz(cpudata, desired_perf);
+}
+
+static void cppc_check_hisi_workaround(void)
+{
+	struct acpi_table_header *tbl;
+	acpi_status status = AE_OK;
+	int i;
+
+	status = acpi_get_table(ACPI_SIG_PCCT, 0, &tbl);
+	if (ACPI_FAILURE(status) || !tbl)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(wa_info); i++) {
+		if (!memcmp(wa_info[i].oem_id, tbl->oem_id, ACPI_OEM_ID_SIZE) &&
+		    !memcmp(wa_info[i].oem_table_id, tbl->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) &&
+		    wa_info[i].oem_revision == tbl->oem_revision)
+			apply_hisi_workaround = true;
+	}
+}
+
 /* Callback function used to retrieve the max frequency from DMI */
 static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
 {
@@ -334,6 +394,9 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpunum)
 	struct cppc_cpudata *cpu = all_cpu_data[cpunum];
 	int ret;
 
+	if (apply_hisi_workaround)
+		return hisi_cppc_cpufreq_get_rate(cpunum);
+
 	ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t0);
 	if (ret)
 		return ret;
@@ -386,6 +449,8 @@ static int __init cppc_cpufreq_init(void)
 		goto out;
 	}
 
+	cppc_check_hisi_workaround();
+
 	ret = cpufreq_register_driver(&cppc_cpufreq_driver);
 	if (ret)
 		goto out;
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index e58bfcb1169e..bde28878725b 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -13,7 +13,6 @@
 
 #include <linux/clk.h>
 #include <linux/cpu.h>
-#include <linux/cpu_cooling.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
 #include <linux/err.h>
@@ -30,7 +29,6 @@
 struct private_data {
 	struct opp_table *opp_table;
 	struct device *cpu_dev;
-	struct thermal_cooling_device *cdev;
 	const char *reg_name;
 	bool have_static_opps;
 };
@@ -280,6 +278,8 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency = transition_latency;
 	policy->dvfs_possible_from_any_cpu = true;
 
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	return 0;
 
 out_free_cpufreq_table:
@@ -297,11 +297,25 @@ out_put_clk:
 	return ret;
 }
 
+static int cpufreq_online(struct cpufreq_policy *policy)
+{
+	/* We did light-weight tear down earlier, nothing to do here */
+	return 0;
+}
+
+static int cpufreq_offline(struct cpufreq_policy *policy)
+{
+	/*
+	 * Preserve policy->driver_data and don't free resources on light-weight
+	 * tear down.
+	 */
+	return 0;
+}
+
 static int cpufreq_exit(struct cpufreq_policy *policy)
 {
 	struct private_data *priv = policy->driver_data;
 
-	cpufreq_cooling_unregister(priv->cdev);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	if (priv->have_static_opps)
 		dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
@@ -314,21 +328,16 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void cpufreq_ready(struct cpufreq_policy *policy)
-{
-	struct private_data *priv = policy->driver_data;
-
-	priv->cdev = of_cpufreq_cooling_register(policy);
-}
-
 static struct cpufreq_driver dt_cpufreq_driver = {
-	.flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK |
+		 CPUFREQ_IS_COOLING_DEV,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = set_target,
 	.get = cpufreq_generic_get,
 	.init = cpufreq_init,
 	.exit = cpufreq_exit,
-	.ready = cpufreq_ready,
+	.online = cpufreq_online,
+	.offline = cpufreq_offline,
 	.name = "cpufreq-dt",
 	.attr = cpufreq_dt_attr,
 	.suspend = cpufreq_generic_suspend,
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index e35a886e00bc..0e626b00053b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -19,6 +19,7 @@
 
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_cooling.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/init.h>
@@ -545,13 +546,13 @@ EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us);
  *                          SYSFS INTERFACE                          *
  *********************************************************************/
 static ssize_t show_boost(struct kobject *kobj,
-				 struct attribute *attr, char *buf)
+			  struct kobj_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled);
 }
 
-static ssize_t store_boost(struct kobject *kobj, struct attribute *attr,
-				  const char *buf, size_t count)
+static ssize_t store_boost(struct kobject *kobj, struct kobj_attribute *attr,
+			   const char *buf, size_t count)
 {
 	int ret, enable;
 
@@ -1200,28 +1201,39 @@ static int cpufreq_online(unsigned int cpu)
 			return -ENOMEM;
 	}
 
-	cpumask_copy(policy->cpus, cpumask_of(cpu));
+	if (!new_policy && cpufreq_driver->online) {
+		ret = cpufreq_driver->online(policy);
+		if (ret) {
+			pr_debug("%s: %d: initialization failed\n", __func__,
+				 __LINE__);
+			goto out_exit_policy;
+		}
 
-	/* call driver. From then on the cpufreq must be able
-	 * to accept all calls to ->verify and ->setpolicy for this CPU
-	 */
-	ret = cpufreq_driver->init(policy);
-	if (ret) {
-		pr_debug("initialization failed\n");
-		goto out_free_policy;
-	}
+		/* Recover policy->cpus using related_cpus */
+		cpumask_copy(policy->cpus, policy->related_cpus);
+	} else {
+		cpumask_copy(policy->cpus, cpumask_of(cpu));
 
-	ret = cpufreq_table_validate_and_sort(policy);
-	if (ret)
-		goto out_exit_policy;
+		/*
+		 * Call driver. From then on the cpufreq must be able
+		 * to accept all calls to ->verify and ->setpolicy for this CPU.
+		 */
+		ret = cpufreq_driver->init(policy);
+		if (ret) {
+			pr_debug("%s: %d: initialization failed\n", __func__,
+				 __LINE__);
+			goto out_free_policy;
+		}
 
-	down_write(&policy->rwsem);
+		ret = cpufreq_table_validate_and_sort(policy);
+		if (ret)
+			goto out_exit_policy;
 
-	if (new_policy) {
 		/* related_cpus should at least include policy->cpus. */
 		cpumask_copy(policy->related_cpus, policy->cpus);
 	}
 
+	down_write(&policy->rwsem);
 	/*
 	 * affected cpus must always be the one, which are online. We aren't
 	 * managing offline cpus here.
@@ -1305,8 +1317,6 @@ static int cpufreq_online(unsigned int cpu)
 	if (ret) {
 		pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n",
 		       __func__, cpu, ret);
-		/* cpufreq_policy_free() will notify based on this */
-		new_policy = false;
 		goto out_destroy_policy;
 	}
 
@@ -1318,6 +1328,10 @@ static int cpufreq_online(unsigned int cpu)
 	if (cpufreq_driver->ready)
 		cpufreq_driver->ready(policy);
 
+	if (IS_ENABLED(CONFIG_CPU_THERMAL) &&
+	    cpufreq_driver->flags & CPUFREQ_IS_COOLING_DEV)
+		policy->cdev = of_cpufreq_cooling_register(policy);
+
 	pr_debug("initialization complete\n");
 
 	return 0;
@@ -1405,6 +1419,12 @@ static int cpufreq_offline(unsigned int cpu)
 		goto unlock;
 	}
 
+	if (IS_ENABLED(CONFIG_CPU_THERMAL) &&
+	    cpufreq_driver->flags & CPUFREQ_IS_COOLING_DEV) {
+		cpufreq_cooling_unregister(policy->cdev);
+		policy->cdev = NULL;
+	}
+
 	if (cpufreq_driver->stop_cpu)
 		cpufreq_driver->stop_cpu(policy);
 
@@ -1412,11 +1432,12 @@ static int cpufreq_offline(unsigned int cpu)
 		cpufreq_exit_governor(policy);
 
 	/*
-	 * Perform the ->exit() even during light-weight tear-down,
-	 * since this is a core component, and is essential for the
-	 * subsequent light-weight ->init() to succeed.
+	 * Perform the ->offline() during light-weight tear-down, as
+	 * that allows fast recovery when the CPU comes back.
 	 */
-	if (cpufreq_driver->exit) {
+	if (cpufreq_driver->offline) {
+		cpufreq_driver->offline(policy);
+	} else if (cpufreq_driver->exit) {
 		cpufreq_driver->exit(policy);
 		policy->freq_table = NULL;
 	}
@@ -1445,8 +1466,13 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	cpumask_clear_cpu(cpu, policy->real_cpus);
 	remove_cpu_dev_symlink(policy, dev);
 
-	if (cpumask_empty(policy->real_cpus))
+	if (cpumask_empty(policy->real_cpus)) {
+		/* We did light-weight exit earlier, do full tear down now */
+		if (cpufreq_driver->offline)
+			cpufreq_driver->exit(policy);
+
 		cpufreq_policy_free(policy);
+	}
 }
 
 /**
@@ -2192,12 +2218,25 @@ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu)
 }
 EXPORT_SYMBOL(cpufreq_get_policy);
 
-/*
- * policy : current policy.
- * new_policy: policy to be set.
+/**
+ * cpufreq_set_policy - Modify cpufreq policy parameters.
+ * @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.
+ *
+ * The cpuinfo part of @policy is not updated by this function.
  */
 static int cpufreq_set_policy(struct cpufreq_policy *policy,
-				struct cpufreq_policy *new_policy)
+			      struct cpufreq_policy *new_policy)
 {
 	struct cpufreq_governor *old_gov;
 	int ret;
@@ -2247,11 +2286,11 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	if (cpufreq_driver->setpolicy) {
 		policy->policy = new_policy->policy;
 		pr_debug("setting range\n");
-		return cpufreq_driver->setpolicy(new_policy);
+		return cpufreq_driver->setpolicy(policy);
 	}
 
 	if (new_policy->governor == policy->governor) {
-		pr_debug("cpufreq: governor limits update\n");
+		pr_debug("governor limits update\n");
 		cpufreq_governor_limits(policy);
 		return 0;
 	}
@@ -2272,7 +2311,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	if (!ret) {
 		ret = cpufreq_start_governor(policy);
 		if (!ret) {
-			pr_debug("cpufreq: governor change\n");
+			pr_debug("governor change\n");
 			sched_cpufreq_governor_change(policy, old_gov);
 			return 0;
 		}
@@ -2293,11 +2332,14 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 }
 
 /**
- *	cpufreq_update_policy - re-evaluate an existing cpufreq policy
- *	@cpu: CPU which shall be re-evaluated
+ * cpufreq_update_policy - Re-evaluate an existing cpufreq policy.
+ * @cpu: CPU to re-evaluate the policy for.
  *
- *	Useful for policy notifiers which have different necessities
- *	at different times.
+ * Update the current frequency for the cpufreq policy of @cpu and use
+ * cpufreq_set_policy() to re-apply the min and max limits saved in the
+ * user_policy sub-structure of that policy, which triggers the evaluation
+ * of policy notifiers and the cpufreq driver's ->verify() callback for the
+ * policy in question, among other things.
  */
 void cpufreq_update_policy(unsigned int cpu)
 {
@@ -2312,23 +2354,18 @@ void cpufreq_update_policy(unsigned int cpu)
 	if (policy_is_inactive(policy))
 		goto unlock;
 
-	pr_debug("updating policy for CPU %u\n", cpu);
-	memcpy(&new_policy, policy, sizeof(*policy));
-	new_policy.min = policy->user_policy.min;
-	new_policy.max = policy->user_policy.max;
-
 	/*
 	 * BIOS might change freq behind our back
 	 * -> ask driver for current freq and notify governors about a change
 	 */
-	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
-		if (cpufreq_suspended)
-			goto unlock;
+	if (cpufreq_driver->get && !cpufreq_driver->setpolicy &&
+	    (cpufreq_suspended || WARN_ON(!cpufreq_update_current_freq(policy))))
+		goto unlock;
 
-		new_policy.cur = cpufreq_update_current_freq(policy);
-		if (WARN_ON(!new_policy.cur))
-			goto unlock;
-	}
+	pr_debug("updating policy for CPU %u\n", cpu);
+	memcpy(&new_policy, policy, sizeof(*policy));
+	new_policy.min = policy->user_policy.min;
+	new_policy.max = policy->user_policy.max;
 
 	cpufreq_set_policy(policy, &new_policy);
 
@@ -2479,7 +2516,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 		    driver_data->target) ||
 	     (driver_data->setpolicy && (driver_data->target_index ||
 		    driver_data->target)) ||
-	     (!!driver_data->get_intermediate != !!driver_data->target_intermediate))
+	     (!driver_data->get_intermediate != !driver_data->target_intermediate) ||
+	     (!driver_data->online != !driver_data->offline))
 		return -EINVAL;
 
 	pr_debug("trying to register driver %s\n", driver_data->name);
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 1572129844a5..e2db5581489a 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -31,26 +31,27 @@ static void cpufreq_stats_update(struct cpufreq_stats *stats)
 {
 	unsigned long long cur_time = get_jiffies_64();
 
-	spin_lock(&cpufreq_stats_lock);
 	stats->time_in_state[stats->last_index] += cur_time - stats->last_time;
 	stats->last_time = cur_time;
-	spin_unlock(&cpufreq_stats_lock);
 }
 
 static void cpufreq_stats_clear_table(struct cpufreq_stats *stats)
 {
 	unsigned int count = stats->max_state;
 
+	spin_lock(&cpufreq_stats_lock);
 	memset(stats->time_in_state, 0, count * sizeof(u64));
 	memset(stats->trans_table, 0, count * count * sizeof(int));
 	stats->last_time = get_jiffies_64();
 	stats->total_trans = 0;
+	spin_unlock(&cpufreq_stats_lock);
 }
 
 static ssize_t show_total_trans(struct cpufreq_policy *policy, char *buf)
 {
 	return sprintf(buf, "%d\n", policy->stats->total_trans);
 }
+cpufreq_freq_attr_ro(total_trans);
 
 static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 {
@@ -61,7 +62,10 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 	if (policy->fast_switch_enabled)
 		return 0;
 
+	spin_lock(&cpufreq_stats_lock);
 	cpufreq_stats_update(stats);
+	spin_unlock(&cpufreq_stats_lock);
+
 	for (i = 0; i < stats->state_num; i++) {
 		len += sprintf(buf + len, "%u %llu\n", stats->freq_table[i],
 			(unsigned long long)
@@ -69,6 +73,7 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 	}
 	return len;
 }
+cpufreq_freq_attr_ro(time_in_state);
 
 static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf,
 			   size_t count)
@@ -77,6 +82,7 @@ static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf,
 	cpufreq_stats_clear_table(policy->stats);
 	return count;
 }
+cpufreq_freq_attr_wo(reset);
 
 static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 {
@@ -126,10 +132,6 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 }
 cpufreq_freq_attr_ro(trans_table);
 
-cpufreq_freq_attr_ro(total_trans);
-cpufreq_freq_attr_ro(time_in_state);
-cpufreq_freq_attr_wo(reset);
-
 static struct attribute *default_attrs[] = {
 	&total_trans.attr,
 	&time_in_state.attr,
@@ -240,9 +242,11 @@ void cpufreq_stats_record_transition(struct cpufreq_policy *policy,
 	if (old_index == -1 || new_index == -1 || old_index == new_index)
 		return;
 
+	spin_lock(&cpufreq_stats_lock);
 	cpufreq_stats_update(stats);
 
 	stats->last_index = new_index;
 	stats->trans_table[old_index * stats->max_state + new_index]++;
 	stats->total_trans++;
+	spin_unlock(&cpufreq_stats_lock);
 }
diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c
index d54a27c99121..940fe85db97a 100644
--- a/drivers/cpufreq/davinci-cpufreq.c
+++ b/drivers/cpufreq/davinci-cpufreq.c
@@ -23,13 +23,10 @@
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/clk.h>
+#include <linux/platform_data/davinci-cpufreq.h>
 #include <linux/platform_device.h>
 #include <linux/export.h>
 
-#include <mach/hardware.h>
-#include <mach/cpufreq.h>
-#include <mach/common.h>
-
 struct davinci_cpufreq {
 	struct device *dev;
 	struct clk *armclk;
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index 60bea302abbe..2d3ef208dd70 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -323,9 +323,8 @@ static int eps_cpu_init(struct cpufreq_policy *policy)
 		states = 2;
 
 	/* Allocate private data and frequency table for current cpu */
-	centaur = kzalloc(sizeof(*centaur)
-		    + (states + 1) * sizeof(struct cpufreq_frequency_table),
-		    GFP_KERNEL);
+	centaur = kzalloc(struct_size(centaur, freq_table, states + 1),
+			  GFP_KERNEL);
 	if (!centaur)
 		return -ENOMEM;
 	eps_cpu[0] = centaur;
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 9fedf627e000..a4ff09f91c8f 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -9,7 +9,6 @@
 #include <linux/clk.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
-#include <linux/cpu_cooling.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/nvmem-consumer.h>
@@ -52,7 +51,6 @@ static struct clk_bulk_data clks[] = {
 };
 
 static struct device *cpu_dev;
-static struct thermal_cooling_device *cdev;
 static bool free_opp;
 static struct cpufreq_frequency_table *freq_table;
 static unsigned int max_freq;
@@ -193,16 +191,6 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 	return 0;
 }
 
-static void imx6q_cpufreq_ready(struct cpufreq_policy *policy)
-{
-	cdev = of_cpufreq_cooling_register(policy);
-
-	if (!cdev)
-		dev_err(cpu_dev,
-			"running cpufreq without cooling device: %ld\n",
-			PTR_ERR(cdev));
-}
-
 static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret;
@@ -210,26 +198,19 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 	policy->clk = clks[ARM].clk;
 	ret = cpufreq_generic_init(policy, freq_table, transition_latency);
 	policy->suspend_freq = max_freq;
+	dev_pm_opp_of_register_em(policy->cpus);
 
 	return ret;
 }
 
-static int imx6q_cpufreq_exit(struct cpufreq_policy *policy)
-{
-	cpufreq_cooling_unregister(cdev);
-
-	return 0;
-}
-
 static struct cpufreq_driver imx6q_cpufreq_driver = {
-	.flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK |
+		 CPUFREQ_IS_COOLING_DEV,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = imx6q_set_target,
 	.get = cpufreq_generic_get,
 	.init = imx6q_cpufreq_init,
-	.exit = imx6q_cpufreq_exit,
 	.name = "imx6q-cpufreq",
-	.ready = imx6q_cpufreq_ready,
 	.attr = cpufreq_generic_attr,
 	.suspend = cpufreq_generic_suspend,
 };
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index dd66decf2087..002f5169d4eb 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -50,6 +50,8 @@
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
 #define fp_toint(X) ((X) >> FRAC_BITS)
 
+#define ONE_EIGHTH_FP ((int64_t)1 << (FRAC_BITS - 3))
+
 #define EXT_BITS 6
 #define EXT_FRAC_BITS (EXT_BITS + FRAC_BITS)
 #define fp_ext_toint(X) ((X) >> EXT_FRAC_BITS)
@@ -895,7 +897,7 @@ static void intel_pstate_update_policies(void)
 /************************** sysfs begin ************************/
 #define show_one(file_name, object)					\
 	static ssize_t show_##file_name					\
-	(struct kobject *kobj, struct attribute *attr, char *buf)	\
+	(struct kobject *kobj, struct kobj_attribute *attr, char *buf)	\
 	{								\
 		return sprintf(buf, "%u\n", global.object);		\
 	}
@@ -904,7 +906,7 @@ static ssize_t intel_pstate_show_status(char *buf);
 static int intel_pstate_update_status(const char *buf, size_t size);
 
 static ssize_t show_status(struct kobject *kobj,
-			   struct attribute *attr, char *buf)
+			   struct kobj_attribute *attr, char *buf)
 {
 	ssize_t ret;
 
@@ -915,7 +917,7 @@ static ssize_t show_status(struct kobject *kobj,
 	return ret;
 }
 
-static ssize_t store_status(struct kobject *a, struct attribute *b,
+static ssize_t store_status(struct kobject *a, struct kobj_attribute *b,
 			    const char *buf, size_t count)
 {
 	char *p = memchr(buf, '\n', count);
@@ -929,7 +931,7 @@ static ssize_t store_status(struct kobject *a, struct attribute *b,
 }
 
 static ssize_t show_turbo_pct(struct kobject *kobj,
-				struct attribute *attr, char *buf)
+				struct kobj_attribute *attr, char *buf)
 {
 	struct cpudata *cpu;
 	int total, no_turbo, turbo_pct;
@@ -955,7 +957,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj,
 }
 
 static ssize_t show_num_pstates(struct kobject *kobj,
-				struct attribute *attr, char *buf)
+				struct kobj_attribute *attr, char *buf)
 {
 	struct cpudata *cpu;
 	int total;
@@ -976,7 +978,7 @@ static ssize_t show_num_pstates(struct kobject *kobj,
 }
 
 static ssize_t show_no_turbo(struct kobject *kobj,
-			     struct attribute *attr, char *buf)
+			     struct kobj_attribute *attr, char *buf)
 {
 	ssize_t ret;
 
@@ -998,7 +1000,7 @@ static ssize_t show_no_turbo(struct kobject *kobj,
 	return ret;
 }
 
-static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
+static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 			      const char *buf, size_t count)
 {
 	unsigned int input;
@@ -1045,7 +1047,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	return count;
 }
 
-static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
+static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b,
 				  const char *buf, size_t count)
 {
 	unsigned int input;
@@ -1075,7 +1077,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 	return count;
 }
 
-static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
+static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b,
 				  const char *buf, size_t count)
 {
 	unsigned int input;
@@ -1107,12 +1109,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 }
 
 static ssize_t show_hwp_dynamic_boost(struct kobject *kobj,
-				struct attribute *attr, char *buf)
+				struct kobj_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%u\n", hwp_boost);
 }
 
-static ssize_t store_hwp_dynamic_boost(struct kobject *a, struct attribute *b,
+static ssize_t store_hwp_dynamic_boost(struct kobject *a,
+				       struct kobj_attribute *b,
 				       const char *buf, size_t count)
 {
 	unsigned int input;
@@ -1444,12 +1447,6 @@ static int knl_get_turbo_pstate(void)
 	return ret;
 }
 
-static int intel_pstate_get_base_pstate(struct cpudata *cpu)
-{
-	return global.no_turbo || global.turbo_disabled ?
-			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
-}
-
 static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
 	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
@@ -1470,11 +1467,9 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu)
 
 static void intel_pstate_max_within_limits(struct cpudata *cpu)
 {
-	int pstate;
+	int pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio);
 
 	update_turbo_state();
-	pstate = intel_pstate_get_base_pstate(cpu);
-	pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio);
 	intel_pstate_set_pstate(cpu, pstate);
 }
 
@@ -1678,17 +1673,14 @@ static inline int32_t get_avg_pstate(struct cpudata *cpu)
 static inline int32_t get_target_pstate(struct cpudata *cpu)
 {
 	struct sample *sample = &cpu->sample;
-	int32_t busy_frac, boost;
+	int32_t busy_frac;
 	int target, avg_pstate;
 
 	busy_frac = div_fp(sample->mperf << cpu->aperf_mperf_shift,
 			   sample->tsc);
 
-	boost = cpu->iowait_boost;
-	cpu->iowait_boost >>= 1;
-
-	if (busy_frac < boost)
-		busy_frac = boost;
+	if (busy_frac < cpu->iowait_boost)
+		busy_frac = cpu->iowait_boost;
 
 	sample->busy_scaled = busy_frac * 100;
 
@@ -1715,11 +1707,9 @@ static inline int32_t get_target_pstate(struct cpudata *cpu)
 
 static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate)
 {
-	int max_pstate = intel_pstate_get_base_pstate(cpu);
-	int min_pstate;
+	int min_pstate = max(cpu->pstate.min_pstate, cpu->min_perf_ratio);
+	int max_pstate = max(min_pstate, cpu->max_perf_ratio);
 
-	min_pstate = max(cpu->pstate.min_pstate, cpu->min_perf_ratio);
-	max_pstate = max(min_pstate, cpu->max_perf_ratio);
 	return clamp_t(int, pstate, min_pstate, max_pstate);
 }
 
@@ -1767,29 +1757,30 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time,
 	if (smp_processor_id() != cpu->cpu)
 		return;
 
+	delta_ns = time - cpu->last_update;
 	if (flags & SCHED_CPUFREQ_IOWAIT) {
-		cpu->iowait_boost = int_tofp(1);
-		cpu->last_update = time;
-		/*
-		 * The last time the busy was 100% so P-state was max anyway
-		 * so avoid overhead of computation.
-		 */
-		if (fp_toint(cpu->sample.busy_scaled) == 100)
-			return;
-
-		goto set_pstate;
+		/* Start over if the CPU may have been idle. */
+		if (delta_ns > TICK_NSEC) {
+			cpu->iowait_boost = ONE_EIGHTH_FP;
+		} else if (cpu->iowait_boost) {
+			cpu->iowait_boost <<= 1;
+			if (cpu->iowait_boost > int_tofp(1))
+				cpu->iowait_boost = int_tofp(1);
+		} else {
+			cpu->iowait_boost = ONE_EIGHTH_FP;
+		}
 	} else if (cpu->iowait_boost) {
 		/* Clear iowait_boost if the CPU may have been idle. */
-		delta_ns = time - cpu->last_update;
 		if (delta_ns > TICK_NSEC)
 			cpu->iowait_boost = 0;
+		else
+			cpu->iowait_boost >>= 1;
 	}
 	cpu->last_update = time;
 	delta_ns = time - cpu->sample.time;
 	if ((s64)delta_ns < INTEL_PSTATE_SAMPLING_INTERVAL)
 		return;
 
-set_pstate:
 	if (intel_pstate_sample(cpu, time))
 		intel_pstate_adjust_pstate(cpu);
 }
@@ -1976,7 +1967,8 @@ static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
 	if (hwp_active) {
 		intel_pstate_get_hwp_max(cpu->cpu, &turbo_max, &max_state);
 	} else {
-		max_state = intel_pstate_get_base_pstate(cpu);
+		max_state = global.no_turbo || global.turbo_disabled ?
+			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 		turbo_max = cpu->pstate.turbo_pstate;
 	}
 
@@ -2475,6 +2467,7 @@ static bool __init intel_pstate_no_acpi_pss(void)
 		kfree(pss);
 	}
 
+	pr_debug("ACPI _PSS not found\n");
 	return true;
 }
 
@@ -2485,9 +2478,14 @@ static bool __init intel_pstate_no_acpi_pcch(void)
 
 	status = acpi_get_handle(NULL, "\\_SB", &handle);
 	if (ACPI_FAILURE(status))
-		return true;
+		goto not_found;
+
+	if (acpi_has_method(handle, "PCCH"))
+		return false;
 
-	return !acpi_has_method(handle, "PCCH");
+not_found:
+	pr_debug("ACPI PCCH not found\n");
+	return true;
 }
 
 static bool __init intel_pstate_has_acpi_ppc(void)
@@ -2502,6 +2500,7 @@ static bool __init intel_pstate_has_acpi_ppc(void)
 		if (acpi_has_method(pr->handle, "_PPC"))
 			return true;
 	}
+	pr_debug("ACPI _PPC not found\n");
 	return false;
 }
 
@@ -2539,8 +2538,10 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void)
 	id = x86_match_cpu(intel_pstate_cpu_oob_ids);
 	if (id) {
 		rdmsrl(MSR_MISC_PWR_MGMT, misc_pwr);
-		if ( misc_pwr & (1 << 8))
+		if (misc_pwr & (1 << 8)) {
+			pr_debug("Bit 8 in the MISC_PWR_MGMT MSR set\n");
 			return true;
+		}
 	}
 
 	idx = acpi_match_platform_list(plat_info);
@@ -2606,22 +2607,28 @@ static int __init intel_pstate_init(void)
 		}
 	} else {
 		id = x86_match_cpu(intel_pstate_cpu_ids);
-		if (!id)
+		if (!id) {
+			pr_info("CPU ID not supported\n");
 			return -ENODEV;
+		}
 
 		copy_cpu_funcs((struct pstate_funcs *)id->driver_data);
 	}
 
-	if (intel_pstate_msrs_not_valid())
+	if (intel_pstate_msrs_not_valid()) {
+		pr_info("Invalid MSRs\n");
 		return -ENODEV;
+	}
 
 hwp_cpu_matched:
 	/*
 	 * The Intel pstate driver will be ignored if the platform
 	 * firmware has its own power management modes.
 	 */
-	if (intel_pstate_platform_pwr_mgmt_exists())
+	if (intel_pstate_platform_pwr_mgmt_exists()) {
+		pr_info("P-states controlled by the platform\n");
 		return -ENODEV;
+	}
 
 	if (!hwp_active && hwp_only)
 		return -ENOTSUPP;
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index 279bd9e9fa95..fb546e0d0356 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -851,7 +851,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy)
 	case TYPE_POWERSAVER:
 		pr_cont("Powersaver supported\n");
 		break;
-	};
+	}
 
 	/* Doesn't hurt */
 	longhaul_setup_southbridge();
diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c
index eb8920d39818..48e9829274c6 100644
--- a/drivers/cpufreq/mediatek-cpufreq.c
+++ b/drivers/cpufreq/mediatek-cpufreq.c
@@ -14,7 +14,6 @@
 
 #include <linux/clk.h>
 #include <linux/cpu.h>
-#include <linux/cpu_cooling.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
 #include <linux/module.h>
@@ -48,7 +47,6 @@ struct mtk_cpu_dvfs_info {
 	struct regulator *sram_reg;
 	struct clk *cpu_clk;
 	struct clk *inter_clk;
-	struct thermal_cooling_device *cdev;
 	struct list_head list_head;
 	int intermediate_voltage;
 	bool need_voltage_tracking;
@@ -307,13 +305,6 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
 
 #define DYNAMIC_POWER "dynamic-power-coefficient"
 
-static void mtk_cpufreq_ready(struct cpufreq_policy *policy)
-{
-	struct mtk_cpu_dvfs_info *info = policy->driver_data;
-
-	info->cdev = of_cpufreq_cooling_register(policy);
-}
-
 static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
 {
 	struct device *cpu_dev;
@@ -465,6 +456,8 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy)
 	policy->driver_data = info;
 	policy->clk = info->cpu_clk;
 
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	return 0;
 }
 
@@ -472,7 +465,6 @@ static int mtk_cpufreq_exit(struct cpufreq_policy *policy)
 {
 	struct mtk_cpu_dvfs_info *info = policy->driver_data;
 
-	cpufreq_cooling_unregister(info->cdev);
 	dev_pm_opp_free_cpufreq_table(info->cpu_dev, &policy->freq_table);
 
 	return 0;
@@ -480,13 +472,13 @@ static int mtk_cpufreq_exit(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver mtk_cpufreq_driver = {
 	.flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK |
-		 CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
+		 CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+		 CPUFREQ_IS_COOLING_DEV,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = mtk_cpufreq_set_target,
 	.get = cpufreq_generic_get,
 	.init = mtk_cpufreq_init,
 	.exit = mtk_cpufreq_exit,
-	.ready = mtk_cpufreq_ready,
 	.name = "mtk-cpufreq",
 	.attr = cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 71e81bbf031b..68052b74d28f 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -133,8 +133,10 @@ static int omap_cpu_init(struct cpufreq_policy *policy)
 
 	/* FIXME: what's the actual transition time? */
 	result = cpufreq_generic_init(policy, freq_table, 300 * 1000);
-	if (!result)
+	if (!result) {
+		dev_pm_opp_of_register_em(policy->cpus);
 		return 0;
+	}
 
 	freq_table_free();
 fail:
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 099a849396f6..1e5e64643c3a 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -268,7 +268,7 @@ static int pcc_get_offset(int cpu)
 	if (!pccp || pccp->type != ACPI_TYPE_PACKAGE) {
 		ret = -ENODEV;
 		goto out_free;
-	};
+	}
 
 	offset = &(pccp->package.elements[0]);
 	if (!offset || offset->type != ACPI_TYPE_INTEGER) {
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 7e7ad3879c4e..d2230812fa4b 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -244,6 +244,7 @@ static int init_powernv_pstates(void)
 	u32 len_ids, len_freqs;
 	u32 pstate_min, pstate_max, pstate_nominal;
 	u32 pstate_turbo, pstate_ultra_turbo;
+	int rc = -ENODEV;
 
 	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
 	if (!power_mgt) {
@@ -327,8 +328,11 @@ next:
 		powernv_freqs[i].frequency = freq * 1000; /* kHz */
 		powernv_freqs[i].driver_data = id & 0xFF;
 
-		revmap_data = (struct pstate_idx_revmap_data *)
-			      kmalloc(sizeof(*revmap_data), GFP_KERNEL);
+		revmap_data = kmalloc(sizeof(*revmap_data), GFP_KERNEL);
+		if (!revmap_data) {
+			rc = -ENOMEM;
+			goto out;
+		}
 
 		revmap_data->pstate_id = id & 0xFF;
 		revmap_data->cpufreq_table_idx = i;
@@ -357,7 +361,7 @@ next:
 	return 0;
 out:
 	of_node_put(power_mgt);
-	return -ENODEV;
+	return rc;
 }
 
 /* Returns the CPU frequency corresponding to the pstate_id. */
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index d83939a1b3d4..4b0b50403901 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -10,18 +10,21 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
+#include <linux/pm_opp.h>
 #include <linux/slab.h>
 
 #define LUT_MAX_ENTRIES			40U
 #define LUT_SRC				GENMASK(31, 30)
 #define LUT_L_VAL			GENMASK(7, 0)
 #define LUT_CORE_COUNT			GENMASK(18, 16)
+#define LUT_VOLT			GENMASK(11, 0)
 #define LUT_ROW_SIZE			32
 #define CLK_HW_DIV			2
 
 /* Register offsets */
 #define REG_ENABLE			0x0
-#define REG_LUT_TABLE			0x110
+#define REG_FREQ_LUT			0x110
+#define REG_VOLT_LUT			0x114
 #define REG_PERF_STATE			0x920
 
 static unsigned long cpu_hw_rate, xo_rate;
@@ -70,11 +73,12 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
 	return policy->freq_table[index].frequency;
 }
 
-static int qcom_cpufreq_hw_read_lut(struct device *dev,
+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 volt;
 	unsigned int max_cores = cpumask_weight(policy->cpus);
 	struct cpufreq_frequency_table	*table;
 
@@ -83,23 +87,28 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev,
 		return -ENOMEM;
 
 	for (i = 0; i < LUT_MAX_ENTRIES; i++) {
-		data = readl_relaxed(base + REG_LUT_TABLE + i * LUT_ROW_SIZE);
+		data = readl_relaxed(base + REG_FREQ_LUT +
+				      i * LUT_ROW_SIZE);
 		src = FIELD_GET(LUT_SRC, data);
 		lval = FIELD_GET(LUT_L_VAL, data);
 		core_count = FIELD_GET(LUT_CORE_COUNT, data);
 
+		data = readl_relaxed(base + REG_VOLT_LUT +
+				      i * LUT_ROW_SIZE);
+		volt = FIELD_GET(LUT_VOLT, data) * 1000;
+
 		if (src)
 			freq = xo_rate * lval / 1000;
 		else
 			freq = cpu_hw_rate / 1000;
 
-		/* Ignore boosts in the middle of the table */
-		if (core_count != max_cores) {
-			table[i].frequency = CPUFREQ_ENTRY_INVALID;
-		} else {
+		if (freq != prev_freq && core_count == max_cores) {
 			table[i].frequency = freq;
-			dev_dbg(dev, "index=%d freq=%d, core_count %d\n", i,
+			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 {
+			table[i].frequency = CPUFREQ_ENTRY_INVALID;
 		}
 
 		/*
@@ -116,6 +125,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev,
 			if (prev_cc != max_cores) {
 				prev->frequency = prev_freq;
 				prev->flags = CPUFREQ_BOOST_FREQ;
+				dev_pm_opp_add(cpu_dev,	prev_freq * 1000, volt);
 			}
 
 			break;
@@ -127,6 +137,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev,
 
 	table[i].frequency = CPUFREQ_TABLE_END;
 	policy->freq_table = table;
+	dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
 
 	return 0;
 }
@@ -159,10 +170,18 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 	struct device *dev = &global_pdev->dev;
 	struct of_phandle_args args;
 	struct device_node *cpu_np;
+	struct device *cpu_dev;
 	struct resource *res;
 	void __iomem *base;
 	int ret, index;
 
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("%s: failed to get cpu%d device\n", __func__,
+		       policy->cpu);
+		return -ENODEV;
+	}
+
 	cpu_np = of_cpu_device_node_get(policy->cpu);
 	if (!cpu_np)
 		return -EINVAL;
@@ -199,12 +218,21 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 
 	policy->driver_data = base + REG_PERF_STATE;
 
-	ret = qcom_cpufreq_hw_read_lut(dev, policy, base);
+	ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy, base);
 	if (ret) {
 		dev_err(dev, "Domain-%d failed to read LUT\n", index);
 		goto error;
 	}
 
+	ret = dev_pm_opp_get_opp_count(cpu_dev);
+	if (ret <= 0) {
+		dev_err(cpu_dev, "Failed to add OPPs\n");
+		ret = -ENODEV;
+		goto error;
+	}
+
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	policy->fast_switch_possible = true;
 
 	return 0;
@@ -215,8 +243,10 @@ error:
 
 static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy)
 {
+	struct device *cpu_dev = get_cpu_device(policy->cpu);
 	void __iomem *base = policy->driver_data - REG_PERF_STATE;
 
+	dev_pm_opp_remove_all_dynamic(cpu_dev);
 	kfree(policy->freq_table);
 	devm_iounmap(&global_pdev->dev, base);
 
@@ -231,7 +261,8 @@ static struct freq_attr *qcom_cpufreq_hw_attr[] = {
 
 static struct cpufreq_driver cpufreq_qcom_hw_driver = {
 	.flags		= CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK |
-			  CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
+			  CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+			  CPUFREQ_IS_COOLING_DEV,
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= qcom_cpufreq_hw_target_index,
 	.get		= qcom_cpufreq_hw_get,
@@ -296,7 +327,7 @@ static int __init qcom_cpufreq_hw_init(void)
 {
 	return platform_driver_register(&qcom_cpufreq_hw_driver);
 }
-subsys_initcall(qcom_cpufreq_hw_init);
+device_initcall(qcom_cpufreq_hw_init);
 
 static void __exit qcom_cpufreq_hw_exit(void)
 {
diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
index 2a3675c24032..dd64dcf89c74 100644
--- a/drivers/cpufreq/qcom-cpufreq-kryo.c
+++ b/drivers/cpufreq/qcom-cpufreq-kryo.c
@@ -42,7 +42,7 @@ enum _msm8996_version {
 	NUM_OF_MSM8996_VERSIONS,
 };
 
-struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev;
+static struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev;
 
 static enum _msm8996_version qcom_cpufreq_kryo_get_msm_id(void)
 {
@@ -75,7 +75,7 @@ static enum _msm8996_version qcom_cpufreq_kryo_get_msm_id(void)
 
 static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 {
-	struct opp_table *opp_tables[NR_CPUS] = {0};
+	struct opp_table **opp_tables;
 	enum _msm8996_version msm8996_version;
 	struct nvmem_cell *speedbin_nvmem;
 	struct device_node *np;
@@ -133,6 +133,10 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 	}
 	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) {
@@ -151,8 +155,10 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 
 	cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1,
 							  NULL, 0);
-	if (!IS_ERR(cpufreq_dt_pdev))
+	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");
@@ -163,13 +169,23 @@ free_opp:
 			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;
 }
 
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index 3d773f64b4df..4295e5476264 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -13,7 +13,6 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/cpufreq.h>
-#include <linux/cpu_cooling.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -31,7 +30,6 @@
 struct cpu_data {
 	struct clk **pclk;
 	struct cpufreq_frequency_table *table;
-	struct thermal_cooling_device *cdev;
 };
 
 /*
@@ -239,7 +237,6 @@ static int qoriq_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
 	struct cpu_data *data = policy->driver_data;
 
-	cpufreq_cooling_unregister(data->cdev);
 	kfree(data->pclk);
 	kfree(data->table);
 	kfree(data);
@@ -258,23 +255,15 @@ static int qoriq_cpufreq_target(struct cpufreq_policy *policy,
 	return clk_set_parent(policy->clk, parent);
 }
 
-
-static void qoriq_cpufreq_ready(struct cpufreq_policy *policy)
-{
-	struct cpu_data *cpud = policy->driver_data;
-
-	cpud->cdev = of_cpufreq_cooling_register(policy);
-}
-
 static struct cpufreq_driver qoriq_cpufreq_driver = {
 	.name		= "qoriq_cpufreq",
-	.flags		= CPUFREQ_CONST_LOOPS,
+	.flags		= CPUFREQ_CONST_LOOPS |
+			  CPUFREQ_IS_COOLING_DEV,
 	.init		= qoriq_cpufreq_cpu_init,
 	.exit		= qoriq_cpufreq_cpu_exit,
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= qoriq_cpufreq_target,
 	.get		= cpufreq_generic_get,
-	.ready		= qoriq_cpufreq_ready,
 	.attr		= cpufreq_generic_attr,
 };
 
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index dbecd7667db2..5b4289460bc9 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -584,7 +584,7 @@ static struct notifier_block s5pv210_cpufreq_reboot_notifier = {
 static int s5pv210_cpufreq_probe(struct platform_device *pdev)
 {
 	struct device_node *np;
-	int id;
+	int id, result = 0;
 
 	/*
 	 * HACK: This is a temporary workaround to get access to clock
@@ -594,18 +594,39 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev)
 	 * this whole driver as soon as S5PV210 gets migrated to use
 	 * cpufreq-dt driver.
 	 */
+	arm_regulator = regulator_get(NULL, "vddarm");
+	if (IS_ERR(arm_regulator)) {
+		if (PTR_ERR(arm_regulator) == -EPROBE_DEFER)
+			pr_debug("vddarm regulator not ready, defer\n");
+		else
+			pr_err("failed to get regulator vddarm\n");
+		return PTR_ERR(arm_regulator);
+	}
+
+	int_regulator = regulator_get(NULL, "vddint");
+	if (IS_ERR(int_regulator)) {
+		if (PTR_ERR(int_regulator) == -EPROBE_DEFER)
+			pr_debug("vddint regulator not ready, defer\n");
+		else
+			pr_err("failed to get regulator vddint\n");
+		result = PTR_ERR(int_regulator);
+		goto err_int_regulator;
+	}
+
 	np = of_find_compatible_node(NULL, NULL, "samsung,s5pv210-clock");
 	if (!np) {
 		pr_err("%s: failed to find clock controller DT node\n",
 			__func__);
-		return -ENODEV;
+		result = -ENODEV;
+		goto err_clock;
 	}
 
 	clk_base = of_iomap(np, 0);
 	of_node_put(np);
 	if (!clk_base) {
 		pr_err("%s: failed to map clock registers\n", __func__);
-		return -EFAULT;
+		result = -EFAULT;
+		goto err_clock;
 	}
 
 	for_each_compatible_node(np, NULL, "samsung,s5pv210-dmc") {
@@ -614,7 +635,8 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev)
 			pr_err("%s: failed to get alias of dmc node '%pOFn'\n",
 				__func__, np);
 			of_node_put(np);
-			return id;
+			result = id;
+			goto err_clk_base;
 		}
 
 		dmc_base[id] = of_iomap(np, 0);
@@ -622,33 +644,40 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev)
 			pr_err("%s: failed to map dmc%d registers\n",
 				__func__, id);
 			of_node_put(np);
-			return -EFAULT;
+			result = -EFAULT;
+			goto err_dmc;
 		}
 	}
 
 	for (id = 0; id < ARRAY_SIZE(dmc_base); ++id) {
 		if (!dmc_base[id]) {
 			pr_err("%s: failed to find dmc%d node\n", __func__, id);
-			return -ENODEV;
+			result = -ENODEV;
+			goto err_dmc;
 		}
 	}
 
-	arm_regulator = regulator_get(NULL, "vddarm");
-	if (IS_ERR(arm_regulator)) {
-		pr_err("failed to get regulator vddarm\n");
-		return PTR_ERR(arm_regulator);
-	}
-
-	int_regulator = regulator_get(NULL, "vddint");
-	if (IS_ERR(int_regulator)) {
-		pr_err("failed to get regulator vddint\n");
-		regulator_put(arm_regulator);
-		return PTR_ERR(int_regulator);
-	}
-
 	register_reboot_notifier(&s5pv210_cpufreq_reboot_notifier);
 
 	return cpufreq_register_driver(&s5pv210_driver);
+
+err_dmc:
+	for (id = 0; id < ARRAY_SIZE(dmc_base); ++id)
+		if (dmc_base[id]) {
+			iounmap(dmc_base[id]);
+			dmc_base[id] = NULL;
+		}
+
+err_clk_base:
+	iounmap(clk_base);
+
+err_clock:
+	regulator_put(int_regulator);
+
+err_int_regulator:
+	regulator_put(arm_regulator);
+
+	return result;
 }
 
 static struct platform_driver s5pv210_cpufreq_platdrv = {
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index 9ed46d188cb5..e6182c89df79 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -11,7 +11,7 @@
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
-#include <linux/cpu_cooling.h>
+#include <linux/energy_model.h>
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/pm_opp.h>
@@ -22,7 +22,6 @@
 struct scmi_data {
 	int domain_id;
 	struct device *cpu_dev;
-	struct thermal_cooling_device *cdev;
 };
 
 static const struct scmi_handle *handle;
@@ -103,13 +102,42 @@ scmi_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 	return 0;
 }
 
+static int __maybe_unused
+scmi_get_cpu_power(unsigned long *power, unsigned long *KHz, int cpu)
+{
+	struct device *cpu_dev = get_cpu_device(cpu);
+	unsigned long Hz;
+	int ret, domain;
+
+	if (!cpu_dev) {
+		pr_err("failed to get cpu%d device\n", cpu);
+		return -ENODEV;
+	}
+
+	domain = handle->perf_ops->device_domain_id(cpu_dev);
+	if (domain < 0)
+		return domain;
+
+	/* Get the power cost of the performance domain. */
+	Hz = *KHz * 1000;
+	ret = handle->perf_ops->est_power_get(handle, domain, &Hz, power);
+	if (ret)
+		return ret;
+
+	/* The EM framework specifies the frequency in KHz. */
+	*KHz = Hz / 1000;
+
+	return 0;
+}
+
 static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 {
-	int ret;
+	int ret, nr_opp;
 	unsigned int latency;
 	struct device *cpu_dev;
 	struct scmi_data *priv;
 	struct cpufreq_frequency_table *freq_table;
+	struct em_data_callback em_cb = EM_DATA_CB(scmi_get_cpu_power);
 
 	cpu_dev = get_cpu_device(policy->cpu);
 	if (!cpu_dev) {
@@ -136,8 +164,8 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 		return ret;
 	}
 
-	ret = dev_pm_opp_get_opp_count(cpu_dev);
-	if (ret <= 0) {
+	nr_opp = dev_pm_opp_get_opp_count(cpu_dev);
+	if (nr_opp <= 0) {
 		dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n");
 		ret = -EPROBE_DEFER;
 		goto out_free_opp;
@@ -171,6 +199,9 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency = latency;
 
 	policy->fast_switch_possible = true;
+
+	em_register_perf_domain(policy->cpus, nr_opp, &em_cb);
+
 	return 0;
 
 out_free_priv:
@@ -185,7 +216,6 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy)
 {
 	struct scmi_data *priv = policy->driver_data;
 
-	cpufreq_cooling_unregister(priv->cdev);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	dev_pm_opp_remove_all_dynamic(priv->cpu_dev);
 	kfree(priv);
@@ -193,17 +223,11 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void scmi_cpufreq_ready(struct cpufreq_policy *policy)
-{
-	struct scmi_data *priv = policy->driver_data;
-
-	priv->cdev = of_cpufreq_cooling_register(policy);
-}
-
 static struct cpufreq_driver scmi_cpufreq_driver = {
 	.name	= "scmi",
 	.flags	= CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
-		  CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+		  CPUFREQ_NEED_INITIAL_FREQ_CHECK |
+		  CPUFREQ_IS_COOLING_DEV,
 	.verify	= cpufreq_generic_frequency_table_verify,
 	.attr	= cpufreq_generic_attr,
 	.target_index	= scmi_cpufreq_set_target,
@@ -211,7 +235,6 @@ static struct cpufreq_driver scmi_cpufreq_driver = {
 	.get	= scmi_cpufreq_get_rate,
 	.init	= scmi_cpufreq_init,
 	.exit	= scmi_cpufreq_exit,
-	.ready	= scmi_cpufreq_ready,
 };
 
 static int scmi_cpufreq_probe(struct scmi_device *sdev)
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 99449738faa4..3f49427766b8 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -22,7 +22,6 @@
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
-#include <linux/cpu_cooling.h>
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/of_platform.h>
@@ -34,7 +33,6 @@
 struct scpi_data {
 	struct clk *clk;
 	struct device *cpu_dev;
-	struct thermal_cooling_device *cdev;
 };
 
 static struct scpi_ops *scpi_ops;
@@ -170,6 +168,9 @@ static int scpi_cpufreq_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency = latency;
 
 	policy->fast_switch_possible = false;
+
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	return 0;
 
 out_free_cpufreq_table:
@@ -186,7 +187,6 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy)
 {
 	struct scpi_data *priv = policy->driver_data;
 
-	cpufreq_cooling_unregister(priv->cdev);
 	clk_put(priv->clk);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	kfree(priv);
@@ -195,23 +195,16 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void scpi_cpufreq_ready(struct cpufreq_policy *policy)
-{
-	struct scpi_data *priv = policy->driver_data;
-
-	priv->cdev = of_cpufreq_cooling_register(policy);
-}
-
 static struct cpufreq_driver scpi_cpufreq_driver = {
 	.name	= "scpi-cpufreq",
 	.flags	= CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
-		  CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+		  CPUFREQ_NEED_INITIAL_FREQ_CHECK |
+		  CPUFREQ_IS_COOLING_DEV,
 	.verify	= cpufreq_generic_frequency_table_verify,
 	.attr	= cpufreq_generic_attr,
 	.get	= scpi_cpufreq_get_rate,
 	.init	= scpi_cpufreq_init,
 	.exit	= scpi_cpufreq_exit,
-	.ready	= scpi_cpufreq_ready,
 	.target_index	= scpi_cpufreq_set_target,
 };
 
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index fbbcb88db061..5d8a09b82efb 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -243,8 +243,7 @@ static unsigned int speedstep_get(unsigned int cpu)
 	unsigned int speed;
 
 	/* You're supposed to ensure CPU is online. */
-	if (smp_call_function_single(cpu, get_freq_data, &speed, 1) != 0)
-		BUG();
+	BUG_ON(smp_call_function_single(cpu, get_freq_data, &speed, 1));
 
 	pr_debug("detected %u kHz as current frequency\n", speed);
 	return speed;
diff --git a/drivers/cpufreq/tegra124-cpufreq.c b/drivers/cpufreq/tegra124-cpufreq.c
index ba3795e13ac6..5e748c8a5c9a 100644
--- a/drivers/cpufreq/tegra124-cpufreq.c
+++ b/drivers/cpufreq/tegra124-cpufreq.c
@@ -118,6 +118,8 @@ static int tegra124_cpufreq_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, priv);
 
+	of_node_put(np);
+
 	return 0;
 
 out_put_pllp_clk: