cpufreq: Specify default governor on command line

Currently, the only way to specify the default CPUfreq governor is
via Kconfig options, which suits users who can build the kernel
themselves perfectly.

However, for those who use a distro-like kernel (such as Android,
with the Generic Kernel Image project), the only way to use a
non-default governor is to boot to userspace, and to then switch
using the sysfs interface. Being able to specify the default governor
on the command line, like is the case for cpuidle, would allow those
users to specify their governor of choice earlier on, and to simplify
the userspace boot procedure slighlty.

To support this use-case, add a kernel command line parameter
allowing the default governor for CPUfreq to be specified, which
takes precedence over the built-in default.

This implementation has one notable limitation: the default governor
must be registered before the driver. This is solved for builtin
governors and drivers using appropriate *_initcall() functions. And
in the modular case, this must be reflected as a constraint on the
module loading order.

Signed-off-by: Quentin Perret <[email protected]>
[ Viresh: Converted 'default_governor' to a string and parsing it only
	  at initcall level, and several updates to
	  cpufreq_init_policy(). ]
Signed-off-by: Viresh Kumar <[email protected]>
[ rjw: Changelog ]
Signed-off-by: Rafael J. Wysocki <[email protected]>

Author: Quentin Perret

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
-via ``sysfs``).  First, a pointer to the new policy object is passed to the
-governor's ``->init()`` callback which is expected to initialize all of the
+determined by the kernel command line or configuration, but it may be changed
+later via ``sysfs``).  First, a pointer to the new policy object is passed to
+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.

drivers/cpufreq/cpufreq.c

@@ -50,6 +50,8 @@ 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
@@ -1061,7 +1063,6 @@ __weak struct cpufreq_governor *cpufreq_default_governor(void)
 
 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;
@@ -1071,21 +1072,27 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy)
 		gov = get_governor(policy->last_governor);
 		if (gov) {
 			pr_debug("Restoring governor %s for cpu %d\n",
-				 policy->governor->name, policy->cpu);
-		} else if (def_gov) {
-			gov = def_gov;
-			__module_get(gov->owner);
+				 gov->name, policy->cpu);
 		} else {
-			return -ENODATA;
+			gov = get_governor(default_governor);
+		}
+
+		if (!gov) {
+			gov = cpufreq_default_governor();
+			if (!gov)
+				return -ENODATA;
+			__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) {
-			pol = cpufreq_parse_policy(def_gov->name);
+		} else {
+			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.
 			 */
@@ -2795,13 +2802,19 @@ 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);