On Thu, 20 Jun 2013 10:31:30 +0530, Viresh Kumar wrote:
> > I'd say there needs to be a separate controller/monitor for that
> > that will know what the chip's thermal limit is and how that
> > relates to how fast the CPU core(s) may run and for how much time.
> > I'm not sure it is sufficient to "
On Thu, 20 Jun 2013 10:41:41 +0530, Viresh Kumar wrote:
> On 19 June 2013 12:46, Lukasz Majewski wrote:
> > I would like to clarify the above issue.
> >
> > When I've discussed with Viresh previous version of this patch, we
> > have agreed, that "boost" sysfs attribute [*]:
> > /sys/devices/system
On 19 June 2013 12:46, Lukasz Majewski wrote:
> I would like to clarify the above issue.
>
> When I've discussed with Viresh previous version of this patch, we have
> agreed, that "boost" sysfs attribute [*]:
> /sys/devices/system/cpu/cpufreq/boost
>
> would be only visible when boost_supported fl
On 18 June 2013 18:56, Rafael J. Wysocki wrote:
> On Tuesday, June 18, 2013 12:12:13 PM Viresh Kumar wrote:
>> On 17 June 2013 19:21, Lukasz Majewski wrote:
>> According to my understanding, boost was important for power
>> saving. In case a high load can be managed by a single cpu with
>> boost
On 18 June 2013 19:14, Lukasz Majewski wrote:
> On Tue, 18 Jun 2013 15:26:16 +0200, Rafael J. Wysocki wrote:
>> On Tuesday, June 18, 2013 12:12:13 PM Viresh Kumar wrote:
>> > On 17 June 2013 19:21, Lukasz Majewski
>> Well, that's why on x86 turbo is controlled by hardware that takes
>> care of k
On Tue, 18 Jun 2013 15:44:56 +0200, Lukasz Majewski wrote:
Dear Viesh, Rafael,
> >
> > I'd recommend you both to read Documentation/cpu-freq/boost.txt
> > now. :-)
>
>
> According to the documentation:
> "Reading the file is always supported, even if the processor does not
> support boosting
On Tue, 18 Jun 2013 15:26:16 +0200, Rafael J. Wysocki wrote:
> On Tuesday, June 18, 2013 12:12:13 PM Viresh Kumar wrote:
> > On 17 June 2013 19:21, Lukasz Majewski
> > wrote:
> > > On Mon, 17 Jun 2013 18:40:50 +0530, Viresh Kumar wrote:
> > >> >> > The core acpi-cpufreq.c code hadn't been changed
On Tuesday, June 18, 2013 12:12:13 PM Viresh Kumar wrote:
> On 17 June 2013 19:21, Lukasz Majewski wrote:
> > On Mon, 17 Jun 2013 18:40:50 +0530, Viresh Kumar wrote:
> >> >> > The core acpi-cpufreq.c code hadn't been changed by me, so I
> >> >> > assume that it will work as before.
> >> >>
> >> >>
On Tue, 18 Jun 2013 14:10:28 +0530, Viresh Kumar wrote:
> On 18 June 2013 13:54, Lukasz Majewski wrote:
> > On Tue, 18 Jun 2013 08:42:13 +0200, Viresh Kumar wrote:
>
> >> Its not about how long.. One cpu type can work longer with boost
> >> freq compared to other.
> >>
> >> What we probably need
On 18 June 2013 13:54, Lukasz Majewski wrote:
> On Tue, 18 Jun 2013 08:42:13 +0200, Viresh Kumar wrote:
>> Its not about how long.. One cpu type can work longer with boost freq
>> compared to other.
>>
>> What we probably need is:
>> - Enabled boost from sysfs if required (now below steps will co
On Tue, 18 Jun 2013 08:42:13 +0200, Viresh Kumar wrote:
> On 17 June 2013 19:21, Lukasz Majewski wrote:
> > On Mon, 17 Jun 2013 18:40:50 +0530, Viresh Kumar wrote:
> >> >> > The core acpi-cpufreq.c code hadn't been changed by me, so I
> >> >> > assume that it will work as before.
> >> >>
> >> >> T
On 17 June 2013 19:21, Lukasz Majewski wrote:
> On Mon, 17 Jun 2013 18:40:50 +0530, Viresh Kumar wrote:
>> >> > The core acpi-cpufreq.c code hadn't been changed by me, so I
>> >> > assume that it will work as before.
>> >>
>> >> That should adapt your patch in your patchset.
>
> Could you explain
On Mon, 17 Jun 2013 18:40:50 +0530, Viresh Kumar wrote:
> On 17 June 2013 15:28, Lukasz Majewski wrote:
> > Yes. But I don't want to hardcode anything. Especially starting CPU
> > number.
>
> There is nothing wrong with it. for_each_online_cpu() is good enough
> on these cases.
I've already chan
On 17 June 2013 15:28, Lukasz Majewski wrote:
> Yes. But I don't want to hardcode anything. Especially starting CPU
> number.
There is nothing wrong with it. for_each_online_cpu() is good enough
on these cases.
>> > How one can control the boost? I'm now (on my setup) using thermal
>> > subsyste
On Mon, 17 Jun 2013 14:48:51 +0530, Viresh Kumar wrote:
> On 17 June 2013 14:38, Lukasz Majewski wrote:
> > On Mon, 17 Jun 2013 09:43:27 +0200, Viresh Kumar wrote:
>
> >> Many cpus share same policy structure and so iterating over all of
> >> them isn't a very good idea. Either keep a mask of cpu
On 17 June 2013 14:38, Lukasz Majewski wrote:
> On Mon, 17 Jun 2013 09:43:27 +0200, Viresh Kumar wrote:
>> Many cpus share same policy structure and so iterating over all of
>> them isn't a very good idea. Either keep a mask of cpus already
>> iterated, copy policy->cpus to it on each iteration.
On Mon, 17 Jun 2013 09:43:27 +0200, Viresh Kumar wrote:
> On 17 June 2013 12:45, Lukasz Majewski wrote:
> > On Mon, 17 Jun 2013 11:13:18 +0530, Viresh Kumar wrote:
> >> On 14 June 2013 13:08, Lukasz Majewski
> >> wrote:
>
> >> > +int cpufreq_boost_trigger_state(int state) +{
>
> >> > + if
On 17 June 2013 12:45, Lukasz Majewski wrote:
> On Mon, 17 Jun 2013 11:13:18 +0530, Viresh Kumar wrote:
>> On 14 June 2013 13:08, Lukasz Majewski wrote:
>> > +int cpufreq_boost_trigger_state(int state) +{
>> > + if (!cpufreq_driver->boost_supported)
>> > + return -ENODEV;
>>
On Mon, 17 Jun 2013 11:13:18 +0530, Viresh Kumar wrote:
> On 14 June 2013 13:08, Lukasz Majewski wrote:
> > Changes for v2:
> > - Removal of cpufreq_boost structure and move its fields to
> > cpufreq_driver structure
> > - Flag to indicate if global boost attribute is already defined
> > - Extent
On 14 June 2013 13:08, Lukasz Majewski wrote:
> Changes for v2:
> - Removal of cpufreq_boost structure and move its fields to cpufreq_driver
> structure
> - Flag to indicate if global boost attribute is already defined
> - Extent the pr_{err|debbug} functions to show current function names
>
> C
This commit adds boost frequency support in cpufreq core (Hardware &
Software).
Some SoC (like Exynos4 - e.g. 4x12) allow setting frequency above
its normal operation limits. Such a mode shall be only used for a short
time.
Overclocking (boost) support is essentially provided by platform
dependent
21 matches
Mail list logo
