Merge back earlier 'pm-cpufreq' material.

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -200,3 +200,27 @@ Description:	address and size of the percpu note.
 		note of cpu#.
 
 		crash_notes_size: size of the note of cpu#.
+
+
+What:		/sys/devices/system/cpu/intel_pstate/max_perf_pct
+		/sys/devices/system/cpu/intel_pstate/min_perf_pct
+		/sys/devices/system/cpu/intel_pstate/no_turbo
+Date:		February 2013
+Contact:	linux-pm@vger.kernel.org
+Description:	Parameters for the Intel P-state driver
+
+		Logic for selecting the current P-state in Intel
+		Sandybridge+ processors. The three knobs control
+		limits for the P-state that will be requested by the
+		driver.
+
+		max_perf_pct: limits the maximum P state that will be requested by
+		the driver stated as a percentage of the available performance.
+
+		min_perf_pct: limits the minimum P state that will be requested by
+		the driver stated as a percentage of the available performance.
+
+		no_turbo: limits the driver to selecting P states below the turbo
+		frequency range.
+
+		More details can be found in Documentation/cpu-freq/intel-pstate.txt

Documentation/cpu-freq/intel-pstate.txt

@@ -0,0 +1,40 @@
+Intel P-state driver
+--------------------
+
+This driver implements a scaling driver with an internal governor for
+Intel Core processors.  The driver follows the same model as the
+Transmeta scaling driver (longrun.c) and implements the setpolicy()
+instead of target().  Scaling drivers that implement setpolicy() are
+assumed to implement internal governors by the cpufreq core. All the
+logic for selecting the current P state is contained within the
+driver; no external governor is used by the cpufreq core.
+
+Intel SandyBridge+ processors are supported.
+
+New sysfs files for controlling P state selection have been added to
+/sys/devices/system/cpu/intel_pstate/
+
+      max_perf_pct: limits the maximum P state that will be requested by
+      the driver stated as a percentage of the available performance.
+
+      min_perf_pct: limits the minimum P state that will be  requested by
+      the driver stated as a percentage of the available performance.
+
+      no_turbo: limits the driver to selecting P states below the turbo
+      frequency range.
+
+For contemporary Intel processors, the frequency is controlled by the
+processor itself and the P-states exposed to software are related to
+performance levels.  The idea that frequency can be set to a single
+frequency is fiction for Intel Core processors. Even if the scaling
+driver selects a single P state the actual frequency the processor
+will run at is selected by the processor itself.
+
+New debugfs files have also been added to /sys/kernel/debug/pstate_snb/
+
+      deadband
+      d_gain_pct
+      i_gain_pct
+      p_gain_pct
+      sample_rate_ms
+      setpoint

arch/arm/mach-exynos/common.c

@@ -303,6 +303,11 @@ void __init exynos_cpuidle_init(void)
 	platform_device_register(&exynos_cpuidle);
 }
 
+void __init exynos_cpufreq_init(void)
+{
+	platform_device_register_simple("exynos-cpufreq", -1, NULL, 0);
+}
+
 void __init exynos_init_late(void)
 {
 	if (of_machine_is_compatible("samsung,exynos5440"))

arch/arm/mach-exynos/common.h

@@ -22,6 +22,7 @@ void exynos_init_io(void);
 void exynos4_restart(enum reboot_mode mode, const char *cmd);
 void exynos5_restart(enum reboot_mode mode, const char *cmd);
 void exynos_cpuidle_init(void);
+void exynos_cpufreq_init(void);
 void exynos_init_late(void);
 
 void exynos_firmware_init(void);

arch/arm/mach-exynos/mach-exynos4-dt.c

@@ -22,6 +22,7 @@
 static void __init exynos4_dt_machine_init(void)
 {
 	exynos_cpuidle_init();
+	exynos_cpufreq_init();
 
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }

arch/arm/mach-exynos/mach-exynos5-dt.c

@@ -44,6 +44,7 @@ static void __init exynos5_dt_machine_init(void)
 	}
 
 	exynos_cpuidle_init();
+	exynos_cpufreq_init();
 
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }

drivers/cpufreq/Kconfig

@@ -181,7 +181,8 @@ config CPU_FREQ_GOV_CONSERVATIVE
 
 config GENERIC_CPUFREQ_CPU0
 	tristate "Generic CPU0 cpufreq driver"
-	depends on HAVE_CLK && REGULATOR && PM_OPP && OF
+	depends on HAVE_CLK && REGULATOR && OF
+	select PM_OPP
 	help
 	  This adds a generic cpufreq driver for CPU0 frequency management.
 	  It supports both uniprocessor (UP) and symmetric multiprocessor (SMP)

drivers/cpufreq/Kconfig.arm

@@ -4,7 +4,8 @@
 
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
-	depends on ARM_CPU_TOPOLOGY && PM_OPP && HAVE_CLK
+	depends on ARM && BIG_LITTLE && ARM_CPU_TOPOLOGY && HAVE_CLK
+	select PM_OPP
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
 
@@ -54,7 +55,8 @@ config ARM_EXYNOS5250_CPUFREQ
 config ARM_EXYNOS5440_CPUFREQ
 	bool "SAMSUNG EXYNOS5440"
 	depends on SOC_EXYNOS5440
-	depends on HAVE_CLK && PM_OPP && OF
+	depends on HAVE_CLK && OF
+	select PM_OPP
 	default y
 	help
 	  This adds the CPUFreq driver for Samsung EXYNOS5440
@@ -79,11 +81,11 @@ config ARM_HIGHBANK_CPUFREQ
 	  If in doubt, say N.
 
 config ARM_IMX6Q_CPUFREQ
-	tristate "Freescale i.MX6Q cpufreq support"
-	depends on SOC_IMX6Q
+	tristate "Freescale i.MX6 cpufreq support"
+	depends on ARCH_MXC
 	depends on REGULATOR_ANATOP
 	help
-	  This adds cpufreq driver support for Freescale i.MX6Q SOC.
+	  This adds cpufreq driver support for Freescale i.MX6 series SoCs.
 
 	  If in doubt, say N.
 

drivers/cpufreq/arm_big_little.c

@@ -488,7 +488,8 @@ static int bL_cpufreq_exit(struct cpufreq_policy *policy)
 static struct cpufreq_driver bL_cpufreq_driver = {
 	.name			= "arm-big-little",
 	.flags			= CPUFREQ_STICKY |
-					CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
+					CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+					CPUFREQ_NEED_INITIAL_FREQ_CHECK,
 	.verify			= cpufreq_generic_frequency_table_verify,
 	.target_index		= bL_cpufreq_set_target,
 	.get			= bL_cpufreq_get_rate,

drivers/cpufreq/cpufreq-cpu0.c

@@ -44,7 +44,7 @@ static int cpu0_set_target(struct cpufreq_policy *policy, unsigned int index)
 	int ret;
 
 	freq_Hz = clk_round_rate(cpu_clk, freq_table[index].frequency * 1000);
-	if (freq_Hz < 0)
+	if (freq_Hz <= 0)
 		freq_Hz = freq_table[index].frequency * 1000;
 
 	freq_exact = freq_Hz;

drivers/cpufreq/cpufreq.c

@@ -39,7 +39,7 @@ static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data_fallback);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
-static DEFINE_MUTEX(cpufreq_governor_lock);
+DEFINE_MUTEX(cpufreq_governor_lock);
 static LIST_HEAD(cpufreq_policy_list);
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -320,6 +320,20 @@ void cpufreq_notify_transition(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_notify_transition);
 
+/* Do post notifications when there are chances that transition has failed */
+void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
+		struct cpufreq_freqs *freqs, int transition_failed)
+{
+	cpufreq_notify_transition(policy, freqs, CPUFREQ_POSTCHANGE);
+	if (!transition_failed)
+		return;
+
+	swap(freqs->old, freqs->new);
+	cpufreq_notify_transition(policy, freqs, CPUFREQ_PRECHANGE);
+	cpufreq_notify_transition(policy, freqs, CPUFREQ_POSTCHANGE);
+}
+EXPORT_SYMBOL_GPL(cpufreq_notify_post_transition);
+
 
 /*********************************************************************
  *                          SYSFS INTERFACE                          *
@@ -1059,6 +1073,46 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
 		}
 	}
 
+	/*
+	 * Sometimes boot loaders set CPU frequency to a value outside of
+	 * frequency table present with cpufreq core. In such cases CPU might be
+	 * unstable if it has to run on that frequency for long duration of time
+	 * and so its better to set it to a frequency which is specified in
+	 * freq-table. This also makes cpufreq stats inconsistent as
+	 * cpufreq-stats would fail to register because current frequency of CPU
+	 * isn't found in freq-table.
+	 *
+	 * Because we don't want this change to effect boot process badly, we go
+	 * for the next freq which is >= policy->cur ('cur' must be set by now,
+	 * otherwise we will end up setting freq to lowest of the table as 'cur'
+	 * is initialized to zero).
+	 *
+	 * We are passing target-freq as "policy->cur - 1" otherwise
+	 * __cpufreq_driver_target() would simply fail, as policy->cur will be
+	 * equal to target-freq.
+	 */
+	if ((cpufreq_driver->flags & CPUFREQ_NEED_INITIAL_FREQ_CHECK)
+	    && has_target()) {
+		/* Are we running at unknown frequency ? */
+		ret = cpufreq_frequency_table_get_index(policy, policy->cur);
+		if (ret == -EINVAL) {
+			/* Warn user and fix it */
+			pr_warn("%s: CPU%d: Running at unlisted freq: %u KHz\n",
+				__func__, policy->cpu, policy->cur);
+			ret = __cpufreq_driver_target(policy, policy->cur - 1,
+				CPUFREQ_RELATION_L);
+
+			/*
+			 * Reaching here after boot in a few seconds may not
+			 * mean that system will remain stable at "unknown"
+			 * frequency for longer duration. Hence, a BUG_ON().
+			 */
+			BUG_ON(ret);
+			pr_warn("%s: CPU%d: Unlisted initial frequency changed to: %u KHz\n",
+				__func__, policy->cpu, policy->cur);
+		}
+	}
+
 	/* related cpus should atleast have policy->cpus */
 	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
 
@@ -1725,17 +1779,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 			pr_err("%s: Failed to change cpu frequency: %d\n",
 					__func__, retval);
 
-		if (notify) {
-			/*
-			 * Notify with old freq in case we failed to change
-			 * frequency
-			 */
-			if (retval)
-				freqs.new = freqs.old;
-
-			cpufreq_notify_transition(policy, &freqs,
-					CPUFREQ_POSTCHANGE);
-		}
+		if (notify)
+			cpufreq_notify_post_transition(policy, &freqs, retval);
 	}
 
 out:

drivers/cpufreq/cpufreq_governor.c

@@ -119,8 +119,9 @@ void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
 {
 	int i;
 
+	mutex_lock(&cpufreq_governor_lock);
 	if (!policy->governor_enabled)
-		return;
+		goto out_unlock;
 
 	if (!all_cpus) {
 		/*
@@ -135,6 +136,9 @@ void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
 		for_each_cpu(i, policy->cpus)
 			__gov_queue_work(i, dbs_data, delay);
 	}
+
+out_unlock:
+	mutex_unlock(&cpufreq_governor_lock);
 }
 EXPORT_SYMBOL_GPL(gov_queue_work);
 

drivers/cpufreq/cpufreq_governor.h

@@ -257,6 +257,8 @@ static ssize_t show_sampling_rate_min_gov_pol				\
 	return sprintf(buf, "%u\n", dbs_data->min_sampling_rate);	\
 }
 
+extern struct mutex cpufreq_governor_lock;
+
 void dbs_check_cpu(struct dbs_data *dbs_data, int cpu);
 bool need_load_eval(struct cpu_dbs_common_info *cdbs,
 		unsigned int sampling_rate);

drivers/cpufreq/davinci-cpufreq.c

@@ -126,7 +126,7 @@ static int davinci_cpu_init(struct cpufreq_policy *policy)
 }
 
 static struct cpufreq_driver davinci_driver = {
-	.flags		= CPUFREQ_STICKY,
+	.flags		= CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
 	.verify		= davinci_verify_speed,
 	.target_index	= davinci_target,
 	.get		= davinci_getspeed,

drivers/cpufreq/dbx500-cpufreq.c

@@ -48,7 +48,8 @@ static int dbx500_cpufreq_init(struct cpufreq_policy *policy)
 }
 
 static struct cpufreq_driver dbx500_cpufreq_driver = {
-	.flags  = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS,
+	.flags  = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS |
+			CPUFREQ_NEED_INITIAL_FREQ_CHECK,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = dbx500_cpufreq_target,
 	.get    = dbx500_cpufreq_getspeed,

drivers/cpufreq/exynos-cpufreq.c

@@ -17,6 +17,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/cpufreq.h>
 #include <linux/suspend.h>
+#include <linux/platform_device.h>
 
 #include <plat/cpu.h>
 
@@ -218,7 +219,7 @@ static int exynos_cpufreq_cpu_init(struct cpufreq_policy *policy)
 }
 
 static struct cpufreq_driver exynos_driver = {
-	.flags		= CPUFREQ_STICKY,
+	.flags		= CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= exynos_target,
 	.get		= exynos_getspeed,
@@ -232,7 +233,7 @@ static struct cpufreq_driver exynos_driver = {
 #endif
 };
 
-static int __init exynos_cpufreq_init(void)
+static int exynos_cpufreq_probe(struct platform_device *pdev)
 {
 	int ret = -EINVAL;
 
@@ -281,4 +282,12 @@ static int __init exynos_cpufreq_init(void)
 	kfree(exynos_info);
 	return -EINVAL;
 }
-late_initcall(exynos_cpufreq_init);
+
+static struct platform_driver exynos_cpufreq_platdrv = {
+	.driver = {
+		.name	= "exynos-cpufreq",
+		.owner	= THIS_MODULE,
+	},
+	.probe = exynos_cpufreq_probe,
+};
+module_platform_driver(exynos_cpufreq_platdrv);