Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/…

…davej/cpufreq

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/davej/cpufreq:
  [ACPI/CPUFREQ] Introduce bios_limit per cpu cpufreq sysfs interface
  [CPUFREQ] make internal cpufreq_add_dev_* static
  [CPUFREQ] use an enum for speedstep processor identification
  [CPUFREQ] Document units for transition latency
  [CPUFREQ] Use global sysfs cpufreq structure for conservative governor tunings
  [CPUFREQ] Documentation: ABI: /sys/devices/system/cpu/cpu#/cpufreq/
  [CPUFREQ] powernow-k6: set transition latency value so ondemand governor can be used
  [CPUFREQ] cpumask: don't put a cpumask on the stack in x86...cpufreq/powernow-k8.c

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

@@ -136,6 +136,24 @@ Description:	Discover cpuidle policy and mechanism
 		See files in Documentation/cpuidle/ for more information.
 
 
+What:		/sys/devices/system/cpu/cpu#/cpufreq/*
+Date:		pre-git history
+Contact:	cpufreq@vger.kernel.org
+Description:	Discover and change clock speed of CPUs
+
+		Clock scaling allows you to change the clock speed of the
+		CPUs on the fly. This is a nice method to save battery
+		power, because the lower the clock speed, the less power
+		the CPU consumes.
+
+		There are many knobs to tweak in this directory.
+
+		See files in Documentation/cpu-freq/ for more information.
+
+		In particular, read Documentation/cpu-freq/user-guide.txt
+		to learn how to control the knobs.
+
+
 What:      /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
 Date:      August 2008
 KernelVersion:	2.6.27

Documentation/cpu-freq/cpu-drivers.txt

@@ -92,9 +92,9 @@ policy->cpuinfo.max_freq -	the minimum and maximum frequency
 				(in kHz) which is supported by 
 				this CPU
 policy->cpuinfo.transition_latency   the time it takes on this CPU to
-				switch between two frequencies (if
-				appropriate, else specify
-				CPUFREQ_ETERNAL)
+				switch between two frequencies in
+				nanoseconds (if appropriate, else
+				specify CPUFREQ_ETERNAL)
 
 policy->cur			The current operating frequency of
 				this CPU (if appropriate)

Documentation/cpu-freq/user-guide.txt

@@ -203,6 +203,17 @@ scaling_cur_freq :		Current frequency of the CPU as determined by
 				the frequency the kernel thinks the CPU runs
 				at.
 
+bios_limit :			If the BIOS tells the OS to limit a CPU to
+				lower frequencies, the user can read out the
+				maximum available frequency from this file.
+				This typically can happen through (often not
+				intended) BIOS settings, restrictions
+				triggered through a service processor or other
+				BIOS/HW based implementations.
+				This does not cover thermal ACPI limitations
+				which can be detected through the generic
+				thermal driver.
+
 If you have selected the "userspace" governor which allows you to
 set the CPU operating frequency to a specific value, you can read out
 the current frequency in

arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c

@@ -764,14 +764,15 @@ static struct freq_attr *acpi_cpufreq_attr[] = {
 };
 
 static struct cpufreq_driver acpi_cpufreq_driver = {
-	.verify = acpi_cpufreq_verify,
-	.target = acpi_cpufreq_target,
-	.init = acpi_cpufreq_cpu_init,
-	.exit = acpi_cpufreq_cpu_exit,
-	.resume = acpi_cpufreq_resume,
-	.name = "acpi-cpufreq",
-	.owner = THIS_MODULE,
-	.attr = acpi_cpufreq_attr,
+	.verify		= acpi_cpufreq_verify,
+	.target		= acpi_cpufreq_target,
+	.bios_limit	= acpi_processor_get_bios_limit,
+	.init		= acpi_cpufreq_cpu_init,
+	.exit		= acpi_cpufreq_cpu_exit,
+	.resume		= acpi_cpufreq_resume,
+	.name		= "acpi-cpufreq",
+	.owner		= THIS_MODULE,
+	.attr		= acpi_cpufreq_attr,
 };
 
 static int __init acpi_cpufreq_init(void)

arch/x86/kernel/cpu/cpufreq/powernow-k6.c

@@ -164,7 +164,7 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	/* cpuinfo and default policy values */
-	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
+	policy->cpuinfo.transition_latency = 200000;
 	policy->cur = busfreq * max_multiplier;
 
 	result = cpufreq_frequency_table_cpuinfo(policy, clock_ratio);

arch/x86/kernel/cpu/cpufreq/powernow-k7.c

@@ -714,14 +714,17 @@ static struct freq_attr *powernow_table_attr[] = {
 };
 
 static struct cpufreq_driver powernow_driver = {
-	.verify	= powernow_verify,
-	.target	= powernow_target,
-	.get	= powernow_get,
-	.init	= powernow_cpu_init,
-	.exit	= powernow_cpu_exit,
-	.name	= "powernow-k7",
-	.owner	= THIS_MODULE,
-	.attr	= powernow_table_attr,
+	.verify		= powernow_verify,
+	.target		= powernow_target,
+	.get		= powernow_get,
+#ifdef CONFIG_X86_POWERNOW_K7_ACPI
+	.bios_limit	= acpi_processor_get_bios_limit,
+#endif
+	.init		= powernow_cpu_init,
+	.exit		= powernow_cpu_exit,
+	.name		= "powernow-k7",
+	.owner		= THIS_MODULE,
+	.attr		= powernow_table_attr,
 };
 
 static int __init powernow_init(void)

arch/x86/kernel/cpu/cpufreq/powernow-k8.c

@@ -1118,7 +1118,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data,
 static int powernowk8_target(struct cpufreq_policy *pol,
 		unsigned targfreq, unsigned relation)
 {
-	cpumask_t oldmask;
+	cpumask_var_t oldmask;
 	struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
 	u32 checkfid;
 	u32 checkvid;
@@ -1131,9 +1131,13 @@ static int powernowk8_target(struct cpufreq_policy *pol,
 	checkfid = data->currfid;
 	checkvid = data->currvid;
 
-	/* only run on specific CPU from here on */
-	oldmask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu));
+	/* only run on specific CPU from here on. */
+	/* This is poor form: use a workqueue or smp_call_function_single */
+	if (!alloc_cpumask_var(&oldmask, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_copy(oldmask, tsk_cpumask(current));
+	set_cpus_allowed_ptr(current, cpumask_of(pol->cpu));
 
 	if (smp_processor_id() != pol->cpu) {
 		printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu);
@@ -1193,7 +1197,8 @@ static int powernowk8_target(struct cpufreq_policy *pol,
 	ret = 0;
 
 err_out:
-	set_cpus_allowed_ptr(current, &oldmask);
+	set_cpus_allowed_ptr(current, oldmask);
+	free_cpumask_var(oldmask);
 	return ret;
 }
 
@@ -1393,14 +1398,15 @@ static struct freq_attr *powernow_k8_attr[] = {
 };
 
 static struct cpufreq_driver cpufreq_amd64_driver = {
-	.verify = powernowk8_verify,
-	.target = powernowk8_target,
-	.init = powernowk8_cpu_init,
-	.exit = __devexit_p(powernowk8_cpu_exit),
-	.get = powernowk8_get,
-	.name = "powernow-k8",
-	.owner = THIS_MODULE,
-	.attr = powernow_k8_attr,
+	.verify		= powernowk8_verify,
+	.target		= powernowk8_target,
+	.bios_limit	= acpi_processor_get_bios_limit,
+	.init		= powernowk8_cpu_init,
+	.exit		= __devexit_p(powernowk8_cpu_exit),
+	.get		= powernowk8_get,
+	.name		= "powernow-k8",
+	.owner		= THIS_MODULE,
+	.attr		= powernow_k8_attr,
 };
 
 /* driver entry point for init */

arch/x86/kernel/cpu/cpufreq/speedstep-ich.c

@@ -39,7 +39,7 @@ static struct pci_dev *speedstep_chipset_dev;
 
 /* speedstep_processor
  */
-static unsigned int speedstep_processor;
+static enum speedstep_processor speedstep_processor;
 
 static u32 pmbase;
 

arch/x86/kernel/cpu/cpufreq/speedstep-lib.c

@@ -34,7 +34,7 @@ static int relaxed_check;
  *                   GET PROCESSOR CORE SPEED IN KHZ                 *
  *********************************************************************/
 
-static unsigned int pentium3_get_frequency(unsigned int processor)
+static unsigned int pentium3_get_frequency(enum speedstep_processor processor)
 {
 	/* See table 14 of p3_ds.pdf and table 22 of 29834003.pdf */
 	struct {
@@ -227,7 +227,7 @@ static unsigned int pentium4_get_frequency(void)
 
 
 /* Warning: may get called from smp_call_function_single. */
-unsigned int speedstep_get_frequency(unsigned int processor)
+unsigned int speedstep_get_frequency(enum speedstep_processor processor)
 {
 	switch (processor) {
 	case SPEEDSTEP_CPU_PCORE:
@@ -380,7 +380,7 @@ EXPORT_SYMBOL_GPL(speedstep_detect_processor);
  *                     DETECT SPEEDSTEP SPEEDS                       *
  *********************************************************************/
 
-unsigned int speedstep_get_freqs(unsigned int processor,
+unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 				  unsigned int *low_speed,
 				  unsigned int *high_speed,
 				  unsigned int *transition_latency,

arch/x86/kernel/cpu/cpufreq/speedstep-lib.h

@@ -11,18 +11,18 @@
 
 
 /* processors */
-
-#define SPEEDSTEP_CPU_PIII_C_EARLY	0x00000001  /* Coppermine core */
-#define SPEEDSTEP_CPU_PIII_C		0x00000002  /* Coppermine core */
-#define SPEEDSTEP_CPU_PIII_T		0x00000003  /* Tualatin core */
-#define SPEEDSTEP_CPU_P4M		0x00000004  /* P4-M  */
-
+enum speedstep_processor {
+	SPEEDSTEP_CPU_PIII_C_EARLY = 0x00000001,  /* Coppermine core */
+	SPEEDSTEP_CPU_PIII_C	   = 0x00000002,  /* Coppermine core */
+	SPEEDSTEP_CPU_PIII_T	   = 0x00000003,  /* Tualatin core */
+	SPEEDSTEP_CPU_P4M	   = 0x00000004,  /* P4-M  */
 /* the following processors are not speedstep-capable and are not auto-detected
  * in speedstep_detect_processor(). However, their speed can be detected using
  * the speedstep_get_frequency() call. */
-#define SPEEDSTEP_CPU_PM		0xFFFFFF03  /* Pentium M  */
-#define SPEEDSTEP_CPU_P4D		0xFFFFFF04  /* desktop P4  */
-#define SPEEDSTEP_CPU_PCORE		0xFFFFFF05  /* Core */
+	SPEEDSTEP_CPU_PM	   = 0xFFFFFF03,  /* Pentium M  */
+	SPEEDSTEP_CPU_P4D	   = 0xFFFFFF04,  /* desktop P4  */
+	SPEEDSTEP_CPU_PCORE	   = 0xFFFFFF05,  /* Core */
+};
 
 /* speedstep states -- only two of them */
 
@@ -31,18 +31,18 @@
 
 
 /* detect a speedstep-capable processor */
-extern unsigned int speedstep_detect_processor (void);
+extern enum speedstep_processor speedstep_detect_processor(void);
 
 /* detect the current speed (in khz) of the processor */
-extern unsigned int speedstep_get_frequency(unsigned int processor);
+extern unsigned int speedstep_get_frequency(enum speedstep_processor processor);
 
 
 /* detect the low and high speeds of the processor. The callback
  * set_state"'s first argument is either SPEEDSTEP_HIGH or
  * SPEEDSTEP_LOW; the second argument is zero so that no
  * cpufreq_notify_transition calls are initiated.
  */
-extern unsigned int speedstep_get_freqs(unsigned int processor,
+extern unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 	unsigned int *low_speed,
 	unsigned int *high_speed,
 	unsigned int *transition_latency,

arch/x86/kernel/cpu/cpufreq/speedstep-smi.c

@@ -35,7 +35,7 @@ static int smi_cmd;
 static unsigned int smi_sig;
 
 /* info about the processor */
-static unsigned int speedstep_processor;
+static enum speedstep_processor speedstep_processor;
 
 /*
  * There are only two frequency states for each processor. Values

drivers/acpi/processor_perflib.c

@@ -167,6 +167,19 @@ int acpi_processor_ppc_has_changed(struct acpi_processor *pr)
 		return cpufreq_update_policy(pr->id);
 }
 
+int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
+{
+	struct acpi_processor *pr;
+
+	pr = per_cpu(processors, cpu);
+	if (!pr || !pr->performance || !pr->performance->state_count)
+		return -ENODEV;
+	*limit = pr->performance->states[pr->performance_platform_limit].
+		core_frequency * 1000;
+	return 0;
+}
+EXPORT_SYMBOL(acpi_processor_get_bios_limit);
+
 void acpi_processor_ppc_init(void)
 {
 	if (!cpufreq_register_notifier

drivers/cpufreq/cpufreq.c

@@ -647,6 +647,21 @@ static ssize_t show_scaling_setspeed(struct cpufreq_policy *policy, char *buf)
 	return policy->governor->show_setspeed(policy, buf);
 }
 
+/**
+ * show_scaling_driver - show the current cpufreq HW/BIOS limitation
+ */
+static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
+{
+	unsigned int limit;
+	int ret;
+	if (cpufreq_driver->bios_limit) {
+		ret = cpufreq_driver->bios_limit(policy->cpu, &limit);
+		if (!ret)
+			return sprintf(buf, "%u\n", limit);
+	}
+	return sprintf(buf, "%u\n", policy->cpuinfo.max_freq);
+}
+
 #define define_one_ro(_name) \
 static struct freq_attr _name = \
 __ATTR(_name, 0444, show_##_name, NULL)
@@ -666,6 +681,7 @@ define_one_ro(cpuinfo_transition_latency);
 define_one_ro(scaling_available_governors);
 define_one_ro(scaling_driver);
 define_one_ro(scaling_cur_freq);
+define_one_ro(bios_limit);
 define_one_ro(related_cpus);
 define_one_ro(affected_cpus);
 define_one_rw(scaling_min_freq);
@@ -767,8 +783,9 @@ static struct kobj_type ktype_cpufreq = {
  *   0:        Success
  *   Positive: When we have a managed CPU and the sysfs got symlinked
  */
-int cpufreq_add_dev_policy(unsigned int cpu, struct cpufreq_policy *policy,
-		struct sys_device *sys_dev)
+static int cpufreq_add_dev_policy(unsigned int cpu,
+				  struct cpufreq_policy *policy,
+				  struct sys_device *sys_dev)
 {
 	int ret = 0;
 #ifdef CONFIG_SMP
@@ -842,7 +859,8 @@ int cpufreq_add_dev_policy(unsigned int cpu, struct cpufreq_policy *policy,
 
 
 /* symlink affected CPUs */
-int cpufreq_add_dev_symlink(unsigned int cpu, struct cpufreq_policy *policy)
+static int cpufreq_add_dev_symlink(unsigned int cpu,
+				   struct cpufreq_policy *policy)
 {
 	unsigned int j;
 	int ret = 0;
@@ -869,8 +887,9 @@ int cpufreq_add_dev_symlink(unsigned int cpu, struct cpufreq_policy *policy)
 	return ret;
 }
 
-int cpufreq_add_dev_interface(unsigned int cpu, struct cpufreq_policy *policy,
-		struct sys_device *sys_dev)
+static int cpufreq_add_dev_interface(unsigned int cpu,
+				     struct cpufreq_policy *policy,
+				     struct sys_device *sys_dev)
 {
 	struct cpufreq_policy new_policy;
 	struct freq_attr **drv_attr;
@@ -902,6 +921,11 @@ int cpufreq_add_dev_interface(unsigned int cpu, struct cpufreq_policy *policy,
 		if (ret)
 			goto err_out_kobj_put;
 	}
+	if (cpufreq_driver->bios_limit) {
+		ret = sysfs_create_file(&policy->kobj, &bios_limit.attr);
+		if (ret)
+			goto err_out_kobj_put;
+	}
 
 	spin_lock_irqsave(&cpufreq_driver_lock, flags);
 	for_each_cpu(j, policy->cpus) {