Re: [Xen-devel] Is: drivers/cpufreq/cpufreq-xen.c Was:Re: [PATCH 2 of 2] linux-xencommons: Load processor-passthru

[Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>]

On Wed, Mar 07, 2012 at 09:12:00PM -0500, Konrad Rzeszutek Wilk wrote:
> >  > I think what you are suggesting is that to write a driver in 
> > drivers/cpufreq/
> >  > that gets either started before the other ones (if built-in) or if as
> >  > a module gets
> >  > loaded from xencommons. That driver would then make the call
> >  > to acpi_processor_preregister_performance(),
> >  > acpi_processor_register_performance() and acpi_processor_notify_smm().
> >  > It would function as a cpufreq-scaling driver but
> >  > in reality all calls to it from cpufreq gov-* drivers would end up with 
> > nop.
> >  >
> >  > Dave, would you be Ok with a driver like that in your tree?
> >
> > I joined this thread half-way through, so I'm not sure what the original 
> > problem was.
> > How is a driver that does nothing better than just masking out the cpufreq 
> > capabilities to guests ?
> Hey Dave,
> 
> The problem statement is three-fold:
>  1). Parse and upload ACPI0007 (or PROCESSOR_TYPE) information to the
>      hypervisor - aka P-states.
>  2). Upload the  Cx state information.
>  3). Inhibit CPU frequency scaling drivers from loading.
.. snip..
> So my big question is whether could be a 'cpufreq.off=1' API, similar
> to the "disable_cpuidle()"
> call that inhibit the cpuidle drivers?

Which would look like this (compile tested, but not extensivly):

diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1236623..1ba8dff 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -10,6 +10,7 @@
 #include <linux/pm.h>
 #include <linux/memblock.h>
 #include <linux/cpuidle.h>
+#include <linux/cpufreq.h>
 
 #include <asm/elf.h>
 #include <asm/vdso.h>
@@ -420,6 +421,7 @@ void __init xen_arch_setup(void)
        boot_cpu_data.hlt_works_ok = 1;
 #endif
        disable_cpuidle();
+       disable_cpufreq();
        WARN_ON(set_pm_idle_to_default());
        fiddle_vdso();
 }
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 622013f..7f2f149 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -126,6 +126,15 @@ static int __init 
init_cpufreq_transition_notifier_list(void)
 }
 pure_initcall(init_cpufreq_transition_notifier_list);
 
+static int off __read_mostly;
+int cpufreq_disabled(void)
+{
+       return off;
+}
+void disable_cpufreq(void)
+{
+       off = 1;
+}
 static LIST_HEAD(cpufreq_governor_list);
 static DEFINE_MUTEX(cpufreq_governor_mutex);
 
@@ -1441,6 +1450,9 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 {
        int retval = -EINVAL;
 
+       if (cpufreq_disabled())
+               return -ENODEV;
+
        pr_debug("target for CPU %u: %u kHz, relation %u\n", policy->cpu,
                target_freq, relation);
        if (cpu_online(policy->cpu) && cpufreq_driver->target)
@@ -1549,6 +1561,9 @@ int cpufreq_register_governor(struct cpufreq_governor 
*governor)
        if (!governor)
                return -EINVAL;
 
+       if (cpufreq_disabled())
+               return -ENODEV;
+
        mutex_lock(&cpufreq_governor_mutex);
 
        err = -EBUSY;
@@ -1572,6 +1587,9 @@ void cpufreq_unregister_governor(struct cpufreq_governor 
*governor)
        if (!governor)
                return;
 
+       if (cpufreq_disabled())
+               return;
+
 #ifdef CONFIG_HOTPLUG_CPU
        for_each_present_cpu(cpu) {
                if (cpu_online(cpu))
@@ -1814,6 +1832,9 @@ int cpufreq_register_driver(struct cpufreq_driver 
*driver_data)
        unsigned long flags;
        int ret;
 
+       if (cpufreq_disabled())
+               return -ENODEV;
+
        if (!driver_data || !driver_data->verify || !driver_data->init ||
            ((!driver_data->setpolicy) && (!driver_data->target)))
                return -EINVAL;
@@ -1901,6 +1922,9 @@ static int __init cpufreq_core_init(void)
 {
        int cpu;
 
+       if (cpufreq_disabled())
+               return -ENODEV;
+
        for_each_possible_cpu(cpu) {
                per_cpu(cpufreq_policy_cpu, cpu) = -1;
                init_rwsem(&per_cpu(cpu_policy_rwsem, cpu));
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 6216115..8ff4427 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -35,6 +35,7 @@
 #ifdef CONFIG_CPU_FREQ
 int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list);
 int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list);
+extern void disable_cpufreq(void);
 #else          /* CONFIG_CPU_FREQ */
 static inline int cpufreq_register_notifier(struct notifier_block *nb,
                                                unsigned int list)
@@ -46,6 +47,7 @@ static inline int cpufreq_unregister_notifier(struct 
notifier_block *nb,
 {
        return 0;
 }
+static inline void disable_cpufreq(void) { }
 #endif         /* CONFIG_CPU_FREQ */
 
 /* if (cpufreq_driver->target) exists, the ->governor decides what frequency

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel