Merge branch 'pm-cpufreq'

* pm-cpufreq: (24 commits)
  cpufreq: intel_pstate: Fix EPP setting via sysfs in active mode
  cpufreq: intel_pstate: Rearrange the storing of new EPP values
  cpufreq: intel_pstate: Avoid enabling HWP if EPP is not supported
  cpufreq: intel_pstate: Clean up aperf_mperf_shift description
  cpufreq: powernv: Make some symbols static
  cpufreq: amd_freq_sensitivity: Mark sometimes used ID structs as __maybe_unused
  cpufreq: intel_pstate: Supply struct attribute description for get_aperf_mperf_shift()
  cpufreq: pcc-cpufreq: Mark sometimes used ID structs as __maybe_unused
  cpufreq: powernow-k8: Mark 'hi' and 'lo' dummy variables as __always_unused
  cpufreq: acpi-cpufreq: Mark sometimes used ID structs as __maybe_unused
  cpufreq: acpi-cpufreq: Mark 'dummy' variable as __always_unused
  cpufreq: powernv-cpufreq: Fix a bunch of kerneldoc related issues
  cpufreq: pasemi: Include header file for {check,restore}_astate prototypes
  cpufreq: cpufreq_governor: Demote store_sampling_rate() header to standard comment block
  cpufreq: cpufreq: Demote lots of function headers unworthy of kerneldoc status
  cpufreq: freq_table: Demote obvious misuse of kerneldoc to standard comment blocks
  cpufreq: Replace HTTP links with HTTPS ones
  cpufreq: intel_pstate: Fix static checker warning for epp variable
  cpufreq: Remove the weakly defined cpufreq_default_governor()
  cpufreq: Specify default governor on command line
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -703,6 +703,11 @@
 	cpufreq.off=1	[CPU_FREQ]
 			disable the cpufreq sub-system
 
+	cpufreq.default_governor=
+			[CPU_FREQ] Name of the default cpufreq governor or
+			policy to use. This governor must be registered in the
+			kernel before the cpufreq driver probes.
+
 	cpu_init_udelay=N
 			[X86] Delay for N microsec between assert and de-assert
 			of APIC INIT to start processors.  This delay occurs

Documentation/admin-guide/pm/cpufreq.rst

@@ -147,9 +147,9 @@ CPUs in it.
 
 The next major initialization step for a new policy object is to attach a
 scaling governor to it (to begin with, that is the default scaling governor
-determined by the kernel configuration, but it may be changed later
+determined by the kernel command line or configuration, but it may be changed
-via ``sysfs``).  First, a pointer to the new policy object is passed to the
+later via ``sysfs``).  First, a pointer to the new policy object is passed to
-governor's ``->init()`` callback which is expected to initialize all of the
+the governor's ``->init()`` callback which is expected to initialize all of the
 data structures necessary to handle the given policy and, possibly, to add
 a governor ``sysfs`` interface to it.  Next, the governor is started by
 invoking its ``->start()`` callback.

Documentation/admin-guide/pm/intel_pstate.rst

@@ -431,6 +431,17 @@ argument is passed to the kernel in the command line.
 	supported in the current configuration, writes to this attribute will
 	fail with an appropriate error.
 
+``energy_efficiency``
+	This attribute is only present on platforms, which have CPUs matching
+	Kaby Lake or Coffee Lake desktop CPU model. By default
+	energy efficiency optimizations are disabled on these CPU models in HWP
+	mode by this driver. Enabling energy efficiency may limit maximum
+	operating frequency in both HWP and non HWP mode. In non HWP mode,
+	optimizations are done only in the turbo frequency range. In HWP mode,
+	optimizations are done in the entire frequency range. Setting this
+	attribute to "1" enables energy efficiency optimizations and setting
+	to "0" disables energy efficiency optimizations.
+
 Interpretation of Policy Attributes
 -----------------------------------
 
@@ -554,7 +565,11 @@ somewhere between the two extremes:
 Strings written to the ``energy_performance_preference`` attribute are
 internally translated to integer values written to the processor's
 Energy-Performance Preference (EPP) knob (if supported) or its
-Energy-Performance Bias (EPB) knob.
+Energy-Performance Bias (EPB) knob. It is also possible to write a positive
+integer value between 0 to 255, if the EPP feature is present. If the EPP
+feature is not present, writing integer value to this attribute is not
+supported. In this case, user can use
+ "/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface.
 
 [Note that tasks may by migrated from one CPU to another by the scheduler's
 load-balancing algorithm and if different energy vs performance hints are

arch/powerpc/platforms/cell/cpufreq_spudemand.c

@@ -126,30 +126,8 @@ static struct cpufreq_governor spu_governor = {
 	.stop = spu_gov_stop,
 	.owner = THIS_MODULE,
 };
-
+cpufreq_governor_init(spu_governor);
-/*
+cpufreq_governor_exit(spu_governor);
- * module init and destoy
- */
-
-static int __init spu_gov_init(void)
-{
-	int ret;
-
-	ret = cpufreq_register_governor(&spu_governor);
-	if (ret)
-		printk(KERN_ERR "registration of governor failed\n");
-	return ret;
-}
-
-static void __exit spu_gov_exit(void)
-{
-	cpufreq_unregister_governor(&spu_governor);
-}
-
-
-module_init(spu_gov_init);
-module_exit(spu_gov_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Christian Krafft <krafft@de.ibm.com>");
-

arch/x86/include/asm/msr-index.h

@@ -149,6 +149,10 @@
 
 #define MSR_LBR_SELECT			0x000001c8
 #define MSR_LBR_TOS			0x000001c9
+
+#define MSR_IA32_POWER_CTL		0x000001fc
+#define MSR_IA32_POWER_CTL_BIT_EE	19
+
 #define MSR_LBR_NHM_FROM		0x00000680
 #define MSR_LBR_NHM_TO			0x000006c0
 #define MSR_LBR_CORE_FROM		0x00000040
@@ -253,8 +257,6 @@
 
 #define MSR_PEBS_FRONTEND		0x000003f7
 
-#define MSR_IA32_POWER_CTL		0x000001fc
-
 #define MSR_IA32_MC0_CTL		0x00000400
 #define MSR_IA32_MC0_STATUS		0x00000401
 #define MSR_IA32_MC0_ADDR		0x00000402

drivers/cpufreq/acpi-cpufreq.c

@@ -244,7 +244,7 @@ static unsigned extract_freq(struct cpufreq_policy *policy, u32 val)
 
 static u32 cpu_freq_read_intel(struct acpi_pct_register *not_used)
 {
-	u32 val, dummy;
+	u32 val, dummy __always_unused;
 
 	rdmsr(MSR_IA32_PERF_CTL, val, dummy);
 	return val;
@@ -261,7 +261,7 @@ static void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val)
 
 static u32 cpu_freq_read_amd(struct acpi_pct_register *not_used)
 {
-	u32 val, dummy;
+	u32 val, dummy __always_unused;
 
 	rdmsr(MSR_AMD_PERF_CTL, val, dummy);
 	return val;
@@ -612,7 +612,7 @@ static const struct dmi_system_id sw_any_bug_dmi_table[] = {
 static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c)
 {
 	/* Intel Xeon Processor 7100 Series Specification Update
-	 * http://www.intel.com/Assets/PDF/specupdate/314554.pdf
+	 * https://www.intel.com/Assets/PDF/specupdate/314554.pdf
 	 * AL30: A Machine Check Exception (MCE) Occurring during an
 	 * Enhanced Intel SpeedStep Technology Ratio Change May Cause
 	 * Both Processor Cores to Lock Up. */
@@ -993,14 +993,14 @@ MODULE_PARM_DESC(acpi_pstate_strict,
 late_initcall(acpi_cpufreq_init);
 module_exit(acpi_cpufreq_exit);
 
-static const struct x86_cpu_id acpi_cpufreq_ids[] = {
+static const struct x86_cpu_id __maybe_unused acpi_cpufreq_ids[] = {
 	X86_MATCH_FEATURE(X86_FEATURE_ACPI, NULL),
 	X86_MATCH_FEATURE(X86_FEATURE_HW_PSTATE, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, acpi_cpufreq_ids);
 
-static const struct acpi_device_id processor_device_ids[] = {
+static const struct acpi_device_id __maybe_unused processor_device_ids[] = {
 	{ACPI_PROCESSOR_OBJECT_HID, },
 	{ACPI_PROCESSOR_DEVICE_HID, },
 	{},

drivers/cpufreq/amd_freq_sensitivity.c

@@ -144,7 +144,7 @@ static void __exit amd_freq_sensitivity_exit(void)
 }
 module_exit(amd_freq_sensitivity_exit);
 
-static const struct x86_cpu_id amd_freq_sensitivity_ids[] = {
+static const struct x86_cpu_id __maybe_unused amd_freq_sensitivity_ids[] = {
 	X86_MATCH_FEATURE(X86_FEATURE_PROC_FEEDBACK, NULL),
 	{}
 };

drivers/cpufreq/cpufreq.c

@@ -50,7 +50,9 @@ static LIST_HEAD(cpufreq_governor_list);
 #define for_each_governor(__governor)				\
 	list_for_each_entry(__governor, &cpufreq_governor_list, governor_list)
 
-/**
+static char default_governor[CPUFREQ_NAME_LEN];
+
+/*
  * The "cpufreq driver" - the arch- or hardware-dependent low
  * level driver of CPUFreq support, and its spinlock. This lock
  * also protects the cpufreq_cpu_data array.
@@ -78,7 +80,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 			      struct cpufreq_governor *new_gov,
 			      unsigned int new_pol);
 
-/**
+/*
  * Two notifier lists: the "policy" list is involved in the
  * validation process for a new CPU frequency policy; the
  * "transition" list for kernel code that needs to handle
@@ -298,7 +300,7 @@ struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu)
  *            EXTERNALLY AFFECTING FREQUENCY CHANGES                 *
  *********************************************************************/
 
-/**
+/*
  * adjust_jiffies - adjust the system "loops_per_jiffy"
  *
  * This function alters the system "loops_per_jiffy" for the clock
@@ -524,6 +526,7 @@ EXPORT_SYMBOL_GPL(cpufreq_disable_fast_switch);
 /**
  * cpufreq_driver_resolve_freq - Map a target frequency to a driver-supported
  * one.
+ * @policy: associated policy to interrogate
  * @target_freq: target frequency to resolve.
  *
  * The target to driver frequency mapping is cached in the policy.
@@ -621,6 +624,24 @@ static struct cpufreq_governor *find_governor(const char *str_governor)
 	return NULL;
 }
 
+static struct cpufreq_governor *get_governor(const char *str_governor)
+{
+	struct cpufreq_governor *t;
+
+	mutex_lock(&cpufreq_governor_mutex);
+	t = find_governor(str_governor);
+	if (!t)
+		goto unlock;
+
+	if (!try_module_get(t->owner))
+		t = NULL;
+
+unlock:
+	mutex_unlock(&cpufreq_governor_mutex);
+
+	return t;
+}
+
 static unsigned int cpufreq_parse_policy(char *str_governor)
 {
 	if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN))
@@ -640,31 +661,17 @@ static struct cpufreq_governor *cpufreq_parse_governor(char *str_governor)
 {
 	struct cpufreq_governor *t;
 
-	mutex_lock(&cpufreq_governor_mutex);
+	t = get_governor(str_governor);
+	if (t)
+		return t;
 
-	t = find_governor(str_governor);
+	if (request_module("cpufreq_%s", str_governor))
-	if (!t) {
-		int ret;
-
-		mutex_unlock(&cpufreq_governor_mutex);
-
-		ret = request_module("cpufreq_%s", str_governor);
-		if (ret)
 		return NULL;
 
-		mutex_lock(&cpufreq_governor_mutex);
+	return get_governor(str_governor);
-
-		t = find_governor(str_governor);
-	}
-	if (t && !try_module_get(t->owner))
-		t = NULL;
-
-	mutex_unlock(&cpufreq_governor_mutex);
-
-	return t;
 }
 
-/**
+/*
  * cpufreq_per_cpu_attr_read() / show_##file_name() -
  * print out cpufreq information
  *
@@ -706,7 +713,7 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf)
 	return ret;
 }
 
-/**
+/*
  * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access
  */
 #define store_one(file_name, object)			\
@@ -727,7 +734,7 @@ static ssize_t store_##file_name					\
 store_one(scaling_min_freq, min);
 store_one(scaling_max_freq, max);
 
-/**
+/*
  * show_cpuinfo_cur_freq - current CPU frequency as detected by hardware
  */
 static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
@@ -741,7 +748,7 @@ static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
 	return sprintf(buf, "<unknown>\n");
 }
 
-/**
+/*
  * show_scaling_governor - show the current policy for the specified CPU
  */
 static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
@@ -756,7 +763,7 @@ static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
 	return -EINVAL;
 }
 
-/**
+/*
  * store_scaling_governor - store policy for the specified CPU
  */
 static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
@@ -793,7 +800,7 @@ static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
 	return ret ? ret : count;
 }
 
-/**
+/*
  * show_scaling_driver - show the cpufreq driver currently loaded
  */
 static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf)
@@ -801,7 +808,7 @@ static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf)
 	return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", cpufreq_driver->name);
 }
 
-/**
+/*
  * show_scaling_available_governors - show the available CPUfreq governors
  */
 static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
@@ -815,12 +822,14 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
 		goto out;
 	}
 
+	mutex_lock(&cpufreq_governor_mutex);
 	for_each_governor(t) {
 		if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char))
 		    - (CPUFREQ_NAME_LEN + 2)))
-			goto out;
+			break;
 		i += scnprintf(&buf[i], CPUFREQ_NAME_PLEN, "%s ", t->name);
 	}
+	mutex_unlock(&cpufreq_governor_mutex);
 out:
 	i += sprintf(&buf[i], "\n");
 	return i;
@@ -843,7 +852,7 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf)
 }
 EXPORT_SYMBOL_GPL(cpufreq_show_cpus);
 
-/**
+/*
  * show_related_cpus - show the CPUs affected by each transition even if
  * hw coordination is in use
  */
@@ -852,7 +861,7 @@ static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf)
 	return cpufreq_show_cpus(policy->related_cpus, buf);
 }
 
-/**
+/*
  * show_affected_cpus - show the CPUs affected by each transition
  */
 static ssize_t show_affected_cpus(struct cpufreq_policy *policy, char *buf)
@@ -886,7 +895,7 @@ static ssize_t show_scaling_setspeed(struct cpufreq_policy *policy, char *buf)
 	return policy->governor->show_setspeed(policy, buf);
 }
 
-/**
+/*
  * show_bios_limit - show the current cpufreq HW/BIOS limitation
  */
 static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
@@ -1048,36 +1057,36 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy)
 	return 0;
 }
 
-__weak struct cpufreq_governor *cpufreq_default_governor(void)
-{
-	return NULL;
-}
-
 static int cpufreq_init_policy(struct cpufreq_policy *policy)
 {
-	struct cpufreq_governor *def_gov = cpufreq_default_governor();
 	struct cpufreq_governor *gov = NULL;
 	unsigned int pol = CPUFREQ_POLICY_UNKNOWN;
+	int ret;
 
 	if (has_target()) {
 		/* Update policy governor to the one used before hotplug. */
-		gov = find_governor(policy->last_governor);
+		gov = get_governor(policy->last_governor);
 		if (gov) {
 			pr_debug("Restoring governor %s for cpu %d\n",
-				 policy->governor->name, policy->cpu);
+				 gov->name, policy->cpu);
-		} else if (def_gov) {
-			gov = def_gov;
 		} else {
-			return -ENODATA;
+			gov = get_governor(default_governor);
 		}
+
+		if (!gov) {
+			gov = cpufreq_default_governor();
+			__module_get(gov->owner);
+		}
+
 	} else {
+
 		/* Use the default policy if there is no last_policy. */
 		if (policy->last_policy) {
 			pol = policy->last_policy;
-		} else if (def_gov) {
+		} else {
-			pol = cpufreq_parse_policy(def_gov->name);
+			pol = cpufreq_parse_policy(default_governor);
 			/*
-			 * In case the default governor is neiter "performance"
+			 * In case the default governor is neither "performance"
 			 * nor "powersave", fall back to the initial policy
 			 * value set by the driver.
 			 */
@@ -1089,7 +1098,11 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy)
 			return -ENODATA;
 	}
 
-	return cpufreq_set_policy(policy, gov, pol);
+	ret = cpufreq_set_policy(policy, gov, pol);
+	if (gov)
+		module_put(gov->owner);
+
+	return ret;
 }
 
 static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
@@ -1604,7 +1617,7 @@ unlock:
 	return 0;
 }
 
-/**
+/*
  * cpufreq_remove_dev - remove a CPU device
  *
  * Removes the cpufreq interface for a CPU device.
@@ -2361,6 +2374,7 @@ EXPORT_SYMBOL_GPL(cpufreq_unregister_governor);
  * cpufreq_get_policy - get the current cpufreq_policy
  * @policy: struct cpufreq_policy into which the current cpufreq_policy
  *	is written
+ * @cpu: CPU to find the policy for
  *
  * Reads the current cpufreq policy.
  */
@@ -2747,7 +2761,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(cpufreq_register_driver);
 
-/**
+/*
  * cpufreq_unregister_driver - unregister the current CPUFreq driver
  *
  * Unregister the current CPUFreq driver. Only call this if you have
@@ -2783,13 +2797,19 @@ EXPORT_SYMBOL_GPL(cpufreq_unregister_driver);
 
 static int __init cpufreq_core_init(void)
 {
+	struct cpufreq_governor *gov = cpufreq_default_governor();
+
 	if (cpufreq_disabled())
 		return -ENODEV;
 
 	cpufreq_global_kobject = kobject_create_and_add("cpufreq", &cpu_subsys.dev_root->kobj);
 	BUG_ON(!cpufreq_global_kobject);
 
+	if (!strlen(default_governor))
+		strncpy(default_governor, gov->name, CPUFREQ_NAME_LEN);
+
 	return 0;
 }
 module_param(off, int, 0444);
+module_param_string(default_governor, default_governor, CPUFREQ_NAME_LEN, 0444);
 core_initcall(cpufreq_core_init);

drivers/cpufreq/cpufreq_conservative.c

@@ -322,17 +322,7 @@ static struct dbs_governor cs_governor = {
 	.start = cs_start,
 };
 
-#define CPU_FREQ_GOV_CONSERVATIVE	(&cs_governor.gov)
+#define CPU_FREQ_GOV_CONSERVATIVE	(cs_governor.gov)
-
-static int __init cpufreq_gov_dbs_init(void)
-{
-	return cpufreq_register_governor(CPU_FREQ_GOV_CONSERVATIVE);
-}
-
-static void __exit cpufreq_gov_dbs_exit(void)
-{
-	cpufreq_unregister_governor(CPU_FREQ_GOV_CONSERVATIVE);
-}
 
 MODULE_AUTHOR("Alexander Clouter <alex@digriz.org.uk>");
 MODULE_DESCRIPTION("'cpufreq_conservative' - A dynamic cpufreq governor for "
@@ -343,11 +333,9 @@ MODULE_LICENSE("GPL");
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
 struct cpufreq_governor *cpufreq_default_governor(void)
 {
-	return CPU_FREQ_GOV_CONSERVATIVE;
+	return &CPU_FREQ_GOV_CONSERVATIVE;
 }
-
-core_initcall(cpufreq_gov_dbs_init);
-#else
-module_init(cpufreq_gov_dbs_init);
 #endif
-module_exit(cpufreq_gov_dbs_exit);
+
+cpufreq_governor_init(CPU_FREQ_GOV_CONSERVATIVE);
+cpufreq_governor_exit(CPU_FREQ_GOV_CONSERVATIVE);

drivers/cpufreq/cpufreq_governor.c

@@ -26,7 +26,7 @@ static DEFINE_PER_CPU(struct cpu_dbs_info, cpu_dbs);
 static DEFINE_MUTEX(gov_dbs_data_mutex);
 
 /* Common sysfs tunables */
-/**
+/*
  * store_sampling_rate - update sampling rate effective immediately if needed.
  *
  * If new rate is smaller than the old, simply updating

drivers/cpufreq/cpufreq_ondemand.c

@@ -408,7 +408,7 @@ static struct dbs_governor od_dbs_gov = {
 	.start = od_start,
 };
 
-#define CPU_FREQ_GOV_ONDEMAND	(&od_dbs_gov.gov)
+#define CPU_FREQ_GOV_ONDEMAND	(od_dbs_gov.gov)
 
 static void od_set_powersave_bias(unsigned int powersave_bias)
 {
@@ -429,7 +429,7 @@ static void od_set_powersave_bias(unsigned int powersave_bias)
 			continue;
 
 		policy = cpufreq_cpu_get_raw(cpu);
-		if (!policy || policy->governor != CPU_FREQ_GOV_ONDEMAND)
+		if (!policy || policy->governor != &CPU_FREQ_GOV_ONDEMAND)
 			continue;
 
 		policy_dbs = policy->governor_data;
@@ -461,16 +461,6 @@ void od_unregister_powersave_bias_handler(void)
 }
 EXPORT_SYMBOL_GPL(od_unregister_powersave_bias_handler);
 
-static int __init cpufreq_gov_dbs_init(void)
-{
-	return cpufreq_register_governor(CPU_FREQ_GOV_ONDEMAND);
-}
-
-static void __exit cpufreq_gov_dbs_exit(void)
-{
-	cpufreq_unregister_governor(CPU_FREQ_GOV_ONDEMAND);
-}
-
 MODULE_AUTHOR("Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>");
 MODULE_AUTHOR("Alexey Starikovskiy <alexey.y.starikovskiy@intel.com>");
 MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for "
@@ -480,11 +470,9 @@ MODULE_LICENSE("GPL");
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
 struct cpufreq_governor *cpufreq_default_governor(void)
 {
-	return CPU_FREQ_GOV_ONDEMAND;
+	return &CPU_FREQ_GOV_ONDEMAND;
 }
-
-core_initcall(cpufreq_gov_dbs_init);
-#else
-module_init(cpufreq_gov_dbs_init);
 #endif
-module_exit(cpufreq_gov_dbs_exit);
+
+cpufreq_governor_init(CPU_FREQ_GOV_ONDEMAND);
+cpufreq_governor_exit(CPU_FREQ_GOV_ONDEMAND);

drivers/cpufreq/cpufreq_performance.c

@@ -23,16 +23,6 @@ static struct cpufreq_governor cpufreq_gov_performance = {
 	.limits		= cpufreq_gov_performance_limits,
 };
 
-static int __init cpufreq_gov_performance_init(void)
-{
-	return cpufreq_register_governor(&cpufreq_gov_performance);
-}
-
-static void __exit cpufreq_gov_performance_exit(void)
-{
-	cpufreq_unregister_governor(&cpufreq_gov_performance);
-}
-
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
 struct cpufreq_governor *cpufreq_default_governor(void)
 {
@@ -50,5 +40,5 @@ MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq policy governor 'performance'");
 MODULE_LICENSE("GPL");
 
-core_initcall(cpufreq_gov_performance_init);
+cpufreq_governor_init(cpufreq_gov_performance);
-module_exit(cpufreq_gov_performance_exit);
+cpufreq_governor_exit(cpufreq_gov_performance);

drivers/cpufreq/cpufreq_powersave.c

@@ -23,16 +23,6 @@ static struct cpufreq_governor cpufreq_gov_powersave = {
 	.owner		= THIS_MODULE,
 };
 
-static int __init cpufreq_gov_powersave_init(void)
-{
-	return cpufreq_register_governor(&cpufreq_gov_powersave);
-}
-
-static void __exit cpufreq_gov_powersave_exit(void)
-{
-	cpufreq_unregister_governor(&cpufreq_gov_powersave);
-}
-
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq policy governor 'powersave'");
 MODULE_LICENSE("GPL");
@@ -42,9 +32,7 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 {
 	return &cpufreq_gov_powersave;
 }
-
-core_initcall(cpufreq_gov_powersave_init);
-#else
-module_init(cpufreq_gov_powersave_init);
 #endif
-module_exit(cpufreq_gov_powersave_exit);
+
+cpufreq_governor_init(cpufreq_gov_powersave);
+cpufreq_governor_exit(cpufreq_gov_powersave);

drivers/cpufreq/cpufreq_userspace.c

@@ -126,16 +126,6 @@ static struct cpufreq_governor cpufreq_gov_userspace = {
 	.owner		= THIS_MODULE,
 };
 
-static int __init cpufreq_gov_userspace_init(void)
-{
-	return cpufreq_register_governor(&cpufreq_gov_userspace);
-}
-
-static void __exit cpufreq_gov_userspace_exit(void)
-{
-	cpufreq_unregister_governor(&cpufreq_gov_userspace);
-}
-
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>, "
 		"Russell King <rmk@arm.linux.org.uk>");
 MODULE_DESCRIPTION("CPUfreq policy governor 'userspace'");
@@ -146,9 +136,7 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 {
 	return &cpufreq_gov_userspace;
 }
-
-core_initcall(cpufreq_gov_userspace_init);
-#else
-module_init(cpufreq_gov_userspace_init);
 #endif
-module_exit(cpufreq_gov_userspace_exit);
+
+cpufreq_governor_init(cpufreq_gov_userspace);
+cpufreq_governor_exit(cpufreq_gov_userspace);

drivers/cpufreq/davinci-cpufreq.c

@@ -2,7 +2,7 @@
 /*
  * CPU frequency scaling for DaVinci
  *
- * Copyright (C) 2009 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2009 Texas Instruments Incorporated - https://www.ti.com/
  *
  * Based on linux/arch/arm/plat-omap/cpu-omap.c. Original Copyright follows:
  *

drivers/cpufreq/freq_table.c

@@ -221,7 +221,7 @@ int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_get_index);
 
-/**
+/*
  * show_available_freqs - show available frequencies for the specified CPU
  */
 static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf,
@@ -260,7 +260,7 @@ static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf,
 struct freq_attr cpufreq_freq_attr_##_name##_freqs =     \
 __ATTR_RO(_name##_frequencies)
 
-/**
+/*
  * show_scaling_available_frequencies - show available normal frequencies for
  * the specified CPU
  */
@@ -272,7 +272,7 @@ static ssize_t scaling_available_frequencies_show(struct cpufreq_policy *policy,
 cpufreq_attr_available_freq(scaling_available);
 EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs);
 
-/**
+/*
  * show_available_boost_freqs - show available boost frequencies for
  * the specified CPU
  */

drivers/cpufreq/intel_pstate.c

@@ -201,9 +201,7 @@ struct global_params {
  * @pstate:		Stores P state limits for this CPU
  * @vid:		Stores VID limits for this CPU
  * @last_sample_time:	Last Sample time
- * @aperf_mperf_shift:	Number of clock cycles after aperf, merf is incremented
+ * @aperf_mperf_shift:	APERF vs MPERF counting frequency difference
- *			This shift is a multiplier to mperf delta to
- *			calculate CPU busy.
  * @prev_aperf:		Last APERF value read from APERF MSR
  * @prev_mperf:		Last MPERF value read from MPERF MSR
  * @prev_tsc:		Last timestamp counter (TSC) value
@@ -275,6 +273,7 @@ static struct cpudata **all_cpu_data;
  * @get_min:		Callback to get minimum P state
  * @get_turbo:		Callback to get turbo P state
  * @get_scaling:	Callback to get frequency scaling factor
+ * @get_aperf_mperf_shift: Callback to get the APERF vs MPERF frequency difference
  * @get_val:		Callback to convert P state to actual MSR write value
  * @get_vid:		Callback to get VID data for Atom platforms
  *
@@ -602,11 +601,12 @@ static const unsigned int epp_values[] = {
 	HWP_EPP_POWERSAVE
 };
 
-static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data)
+static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data, int *raw_epp)
 {
 	s16 epp;
 	int index = -EINVAL;
 
+	*raw_epp = 0;
 	epp = intel_pstate_get_epp(cpu_data, 0);
 	if (epp < 0)
 		return epp;
@@ -614,12 +614,14 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data)
 	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		if (epp == HWP_EPP_PERFORMANCE)
 			return 1;
-		if (epp <= HWP_EPP_BALANCE_PERFORMANCE)
+		if (epp == HWP_EPP_BALANCE_PERFORMANCE)
 			return 2;
-		if (epp <= HWP_EPP_BALANCE_POWERSAVE)
+		if (epp == HWP_EPP_BALANCE_POWERSAVE)
 			return 3;
-		else
+		if (epp == HWP_EPP_POWERSAVE)
 			return 4;
+		*raw_epp = epp;
+		return 0;
 	} else if (boot_cpu_has(X86_FEATURE_EPB)) {
 		/*
 		 * Range:
@@ -638,7 +640,8 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data)
 }
 
 static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
-					      int pref_index)
+					      int pref_index, bool use_raw,
+					      u32 raw_epp)
 {
 	int epp = -EINVAL;
 	int ret;
@@ -646,29 +649,34 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
 	if (!pref_index)
 		epp = cpu_data->epp_default;
 
-	mutex_lock(&intel_pstate_limits_lock);
-
 	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
-		u64 value;
+		/*
-
+		 * Use the cached HWP Request MSR value, because the register
-		ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, &value);
+		 * itself may be updated by intel_pstate_hwp_boost_up() or
-		if (ret)
+		 * intel_pstate_hwp_boost_down() at any time.
-			goto return_pref;
+		 */
+		u64 value = READ_ONCE(cpu_data->hwp_req_cached);
 
 		value &= ~GENMASK_ULL(31, 24);
 
-		if (epp == -EINVAL)
+		if (use_raw)
+			epp = raw_epp;
+		else if (epp == -EINVAL)
 			epp = epp_values[pref_index - 1];
 
 		value |= (u64)epp << 24;
+		/*
+		 * The only other updater of hwp_req_cached in the active mode,
+		 * intel_pstate_hwp_set(), is called under the same lock as this
+		 * function, so it cannot run in parallel with the update below.
+		 */
+		WRITE_ONCE(cpu_data->hwp_req_cached, value);
 		ret = wrmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, value);
 	} else {
 		if (epp == -EINVAL)
 			epp = (pref_index - 1) << 2;
 		ret = intel_pstate_set_epb(cpu_data->cpu, epp);
 	}
-return_pref:
-	mutex_unlock(&intel_pstate_limits_lock);
 
 	return ret;
 }
@@ -694,30 +702,53 @@ static ssize_t store_energy_performance_preference(
 {
 	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
 	char str_preference[21];
-	int ret;
+	bool raw = false;
+	ssize_t ret;
+	u32 epp = 0;
 
 	ret = sscanf(buf, "%20s", str_preference);
 	if (ret != 1)
 		return -EINVAL;
 
 	ret = match_string(energy_perf_strings, -1, str_preference);
-	if (ret < 0)
+	if (ret < 0) {
+		if (!boot_cpu_has(X86_FEATURE_HWP_EPP))
 			return ret;
 
-	intel_pstate_set_energy_pref_index(cpu_data, ret);
+		ret = kstrtouint(buf, 10, &epp);
-	return count;
+		if (ret)
+			return ret;
+
+		if (epp > 255)
+			return -EINVAL;
+
+		raw = true;
+	}
+
+	mutex_lock(&intel_pstate_limits_lock);
+
+	ret = intel_pstate_set_energy_pref_index(cpu_data, ret, raw, epp);
+	if (!ret)
+		ret = count;
+
+	mutex_unlock(&intel_pstate_limits_lock);
+
+	return ret;
 }
 
 static ssize_t show_energy_performance_preference(
 				struct cpufreq_policy *policy, char *buf)
 {
 	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
-	int preference;
+	int preference, raw_epp;
 
-	preference = intel_pstate_get_energy_pref_index(cpu_data);
+	preference = intel_pstate_get_energy_pref_index(cpu_data, &raw_epp);
 	if (preference < 0)
 		return preference;
 
+	if (raw_epp)
+		return  sprintf(buf, "%d\n", raw_epp);
+	else
 		return  sprintf(buf, "%s\n", energy_perf_strings[preference]);
 }
 
@@ -866,10 +897,39 @@ static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy)
 	return 0;
 }
 
+#define POWER_CTL_EE_ENABLE	1
+#define POWER_CTL_EE_DISABLE	2
+
+static int power_ctl_ee_state;
+
+static void set_power_ctl_ee_state(bool input)
+{
+	u64 power_ctl;
+
+	mutex_lock(&intel_pstate_driver_lock);
+	rdmsrl(MSR_IA32_POWER_CTL, power_ctl);
+	if (input) {
+		power_ctl &= ~BIT(MSR_IA32_POWER_CTL_BIT_EE);
+		power_ctl_ee_state = POWER_CTL_EE_ENABLE;
+	} else {
+		power_ctl |= BIT(MSR_IA32_POWER_CTL_BIT_EE);
+		power_ctl_ee_state = POWER_CTL_EE_DISABLE;
+	}
+	wrmsrl(MSR_IA32_POWER_CTL, power_ctl);
+	mutex_unlock(&intel_pstate_driver_lock);
+}
+
 static void intel_pstate_hwp_enable(struct cpudata *cpudata);
 
 static int intel_pstate_resume(struct cpufreq_policy *policy)
 {
+
+	/* Only restore if the system default is changed */
+	if (power_ctl_ee_state == POWER_CTL_EE_ENABLE)
+		set_power_ctl_ee_state(true);
+	else if (power_ctl_ee_state == POWER_CTL_EE_DISABLE)
+		set_power_ctl_ee_state(false);
+
 	if (!hwp_active)
 		return 0;
 
@@ -1218,6 +1278,32 @@ static ssize_t store_hwp_dynamic_boost(struct kobject *a,
 	return count;
 }
 
+static ssize_t show_energy_efficiency(struct kobject *kobj, struct kobj_attribute *attr,
+				      char *buf)
+{
+	u64 power_ctl;
+	int enable;
+
+	rdmsrl(MSR_IA32_POWER_CTL, power_ctl);
+	enable = !!(power_ctl & BIT(MSR_IA32_POWER_CTL_BIT_EE));
+	return sprintf(buf, "%d\n", !enable);
+}
+
+static ssize_t store_energy_efficiency(struct kobject *a, struct kobj_attribute *b,
+				       const char *buf, size_t count)
+{
+	bool input;
+	int ret;
+
+	ret = kstrtobool(buf, &input);
+	if (ret)
+		return ret;
+
+	set_power_ctl_ee_state(input);
+
+	return count;
+}
+
 show_one(max_perf_pct, max_perf_pct);
 show_one(min_perf_pct, min_perf_pct);
 
@@ -1228,6 +1314,7 @@ define_one_global_rw(min_perf_pct);
 define_one_global_ro(turbo_pct);
 define_one_global_ro(num_pstates);
 define_one_global_rw(hwp_dynamic_boost);
+define_one_global_rw(energy_efficiency);
 
 static struct attribute *intel_pstate_attributes[] = {
 	&status.attr,
@@ -1241,6 +1328,8 @@ static const struct attribute_group intel_pstate_attr_group = {
 	.attrs = intel_pstate_attributes,
 };
 
+static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[];
+
 static void __init intel_pstate_sysfs_expose_params(void)
 {
 	struct kobject *intel_pstate_kobject;
@@ -1273,6 +1362,11 @@ static void __init intel_pstate_sysfs_expose_params(void)
 				       &hwp_dynamic_boost.attr);
 		WARN_ON(rc);
 	}
+
+	if (x86_match_cpu(intel_pstate_cpu_ee_disable_ids)) {
+		rc = sysfs_create_file(intel_pstate_kobject, &energy_efficiency.attr);
+		WARN_ON(rc);
+	}
 }
 /************************** sysfs end ************************/
 
@@ -1288,25 +1382,6 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 		cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
 }
 
-#define MSR_IA32_POWER_CTL_BIT_EE	19
-
-/* Disable energy efficiency optimization */
-static void intel_pstate_disable_ee(int cpu)
-{
-	u64 power_ctl;
-	int ret;
-
-	ret = rdmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, &power_ctl);
-	if (ret)
-		return;
-
-	if (!(power_ctl & BIT(MSR_IA32_POWER_CTL_BIT_EE))) {
-		pr_info("Disabling energy efficiency optimization\n");
-		power_ctl |= BIT(MSR_IA32_POWER_CTL_BIT_EE);
-		wrmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, power_ctl);
-	}
-}
-
 static int atom_get_min_pstate(void)
 {
 	u64 value;
@@ -1982,10 +2057,6 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	if (hwp_active) {
 		const struct x86_cpu_id *id;
 
-		id = x86_match_cpu(intel_pstate_cpu_ee_disable_ids);
-		if (id)
-			intel_pstate_disable_ee(cpunum);
-
 		intel_pstate_hwp_enable(cpu);
 
 		id = x86_match_cpu(intel_pstate_hwp_boost_ids);
@@ -2754,7 +2825,12 @@ static int __init intel_pstate_init(void)
 	id = x86_match_cpu(hwp_support_ids);
 	if (id) {
 		copy_cpu_funcs(&core_funcs);
-		if (!no_hwp) {
+		/*
+		 * Avoid enabling HWP for processors without EPP support,
+		 * because that means incomplete HWP implementation which is a
+		 * corner case and supporting it is generally problematic.
+		 */
+		if (!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 			hwp_active++;
 			hwp_mode_bdw = id->driver_data;
 			intel_pstate.attr = hwp_cpufreq_attrs;
@@ -2808,8 +2884,17 @@ hwp_cpu_matched:
 	if (rc)
 		return rc;
 
-	if (hwp_active)
+	if (hwp_active) {
+		const struct x86_cpu_id *id;
+
+		id = x86_match_cpu(intel_pstate_cpu_ee_disable_ids);
+		if (id) {
+			set_power_ctl_ee_state(false);
+			pr_info("Disabling energy efficiency optimization\n");
+		}
+
 		pr_info("HWP enabled\n");
+	}
 
 	return 0;
 }

drivers/cpufreq/pasemi-cpufreq.c

@@ -22,6 +22,8 @@
 #include <asm/time.h>
 #include <asm/smp.h>
 
+#include <platforms/pasemi/pasemi.h>
+
 #define SDCASR_REG		0x0100
 #define SDCASR_REG_STRIDE	0x1000
 #define SDCPWR_CFGA0_REG	0x0100

drivers/cpufreq/pcc-cpufreq.c

@@ -616,7 +616,7 @@ static void __exit pcc_cpufreq_exit(void)
 	free_percpu(pcc_cpu_info);
 }
 
-static const struct acpi_device_id processor_device_ids[] = {
+static const struct acpi_device_id __maybe_unused processor_device_ids[] = {
 	{ACPI_PROCESSOR_OBJECT_HID, },
 	{ACPI_PROCESSOR_DEVICE_HID, },
 	{},

drivers/cpufreq/powernow-k8.c

@@ -86,7 +86,7 @@ static u32 convert_fid_to_vco_fid(u32 fid)
  */
 static int pending_bit_stuck(void)
 {
-	u32 lo, hi;
+	u32 lo, hi __always_unused;
 
 	rdmsr(MSR_FIDVID_STATUS, lo, hi);
 	return lo & MSR_S_LO_CHANGE_PENDING ? 1 : 0;
@@ -282,7 +282,7 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data,
 {
 	u32 rvosteps = data->rvo;
 	u32 savefid = data->currfid;
-	u32 maxvid, lo, rvomult = 1;
+	u32 maxvid, lo __always_unused, rvomult = 1;
 
 	pr_debug("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, reqvid 0x%x, rvo 0x%x\n",
 		smp_processor_id(),

drivers/cpufreq/powernv-cpufreq.c

@@ -64,13 +64,14 @@
  *				highest_lpstate_idx
  * @last_sampled_time:		Time from boot in ms when global pstates were
  *				last set
- * @last_lpstate_idx,		Last set value of local pstate and global
+ * @last_lpstate_idx:		Last set value of local pstate and global
- * last_gpstate_idx		pstate in terms of cpufreq table index
+ * @last_gpstate_idx:		pstate in terms of cpufreq table index
  * @timer:			Is used for ramping down if cpu goes idle for
  *				a long time with global pstate held high
  * @gpstate_lock:		A spinlock to maintain synchronization between
  *				routines called by the timer handler and
  *				governer's target_index calls
+ * @policy:			Associated CPUFreq policy
  */
 struct global_pstate_info {
 	int highest_lpstate_idx;
@@ -85,7 +86,7 @@ struct global_pstate_info {
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
 
-DEFINE_HASHTABLE(pstate_revmap, POWERNV_MAX_PSTATES_ORDER);
+static DEFINE_HASHTABLE(pstate_revmap, POWERNV_MAX_PSTATES_ORDER);
 /**
  * struct pstate_idx_revmap_data: Entry in the hashmap pstate_revmap
  *				  indexed by a function of pstate id.
@@ -170,7 +171,7 @@ static inline u8 extract_pstate(u64 pmsr_val, unsigned int shift)
 
 /* Use following functions for conversions between pstate_id and index */
 
-/**
+/*
  * idx_to_pstate : Returns the pstate id corresponding to the
  *		   frequency in the cpufreq frequency table
  *		   powernv_freqs indexed by @i.
@@ -188,7 +189,7 @@ static inline u8 idx_to_pstate(unsigned int i)
 	return powernv_freqs[i].driver_data;
 }
 
-/**
+/*
  * pstate_to_idx : Returns the index in the cpufreq frequencytable
  *		   powernv_freqs for the frequency whose corresponding
  *		   pstate id is @pstate.
@@ -380,7 +381,7 @@ static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy,
 		powernv_freqs[powernv_pstate_info.nominal].frequency);
 }
 
-struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq =
+static struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq =
 	__ATTR_RO(cpuinfo_nominal_freq);
 
 #define SCALING_BOOST_FREQS_ATTR_INDEX		2
@@ -660,13 +661,13 @@ static inline void  queue_gpstate_timer(struct global_pstate_info *gpstates)
 /**
  * gpstate_timer_handler
  *
- * @data: pointer to cpufreq_policy on which timer was queued
+ * @t: Timer context used to fetch global pstate info struct
  *
  * This handler brings down the global pstate closer to the local pstate
  * according quadratic equation. Queues a new timer if it is still not equal
  * to local pstate
  */
-void gpstate_timer_handler(struct timer_list *t)
+static void gpstate_timer_handler(struct timer_list *t)
 {
 	struct global_pstate_info *gpstates = from_timer(gpstates, t, timer);
 	struct cpufreq_policy *policy = gpstates->policy;
@@ -899,7 +900,7 @@ static struct notifier_block powernv_cpufreq_reboot_nb = {
 	.notifier_call = powernv_cpufreq_reboot_notifier,
 };
 
-void powernv_cpufreq_work_fn(struct work_struct *work)
+static void powernv_cpufreq_work_fn(struct work_struct *work)
 {
 	struct chip *chip = container_of(work, struct chip, throttle);
 	struct cpufreq_policy *policy;

include/linux/cpufreq.h

@@ -577,6 +577,20 @@ unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy);
 int cpufreq_register_governor(struct cpufreq_governor *governor);
 void cpufreq_unregister_governor(struct cpufreq_governor *governor);
 
+#define cpufreq_governor_init(__governor)			\
+static int __init __governor##_init(void)			\
+{								\
+	return cpufreq_register_governor(&__governor);	\
+}								\
+core_initcall(__governor##_init)
+
+#define cpufreq_governor_exit(__governor)			\
+static void __exit __governor##_exit(void)			\
+{								\
+	return cpufreq_unregister_governor(&__governor);	\
+}								\
+module_exit(__governor##_exit)
+
 struct cpufreq_governor *cpufreq_default_governor(void);
 struct cpufreq_governor *cpufreq_fallback_governor(void);
 

kernel/sched/cpufreq_schedutil.c

@@ -909,11 +909,7 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 }
 #endif
 
-static int __init sugov_register(void)
+cpufreq_governor_init(schedutil_gov);
-{
-	return cpufreq_register_governor(&schedutil_gov);
-}
-core_initcall(sugov_register);
 
 #ifdef CONFIG_ENERGY_MODEL
 extern bool sched_energy_update;