* Re: [Query] CPUFreq: Does these machines have separate clock domains for CPUs?
2013-08-29 10:15 [Query] CPUFreq: Does these machines have separate clock domains for CPUs? Viresh Kumar
@ 2013-08-29 10:23 ` Sekhar Nori
2013-08-29 10:30 ` Viresh Kumar
2013-08-29 22:41 ` Aaro Koskinen
` (3 subsequent siblings)
4 siblings, 1 reply; 11+ messages in thread
From: Sekhar Nori @ 2013-08-29 10:23 UTC (permalink / raw)
To: Viresh Kumar
Cc: linux-pm@vger.kernel.org, cpufreq@vger.kernel.org,
Linux Kernel Mailing List, linux-arm-kernel@lists.infradead.org,
Benjamin Herrenschmidt, David Miller, Eric Miao, Jesper Nilsson,
John Crispin, linux-cris-kernel, linux-sh, Mikael Starvik,
Paul Mundt, sparclinux, Miao Steven, Dave Jones
On Thursday 29 August 2013 03:45 PM, Viresh Kumar wrote:
> Hi,
>
> I have been doing some CPUFreq cleanup work and
> wanted to know if the below mentioned machines have separate
> clock domains for their CPUs or all share the same domain?
On DaVinci (DA850), there is an async domain available to keep some
peripheral clocks insulated from cpu frequency changes. But there are a
bunch of other clocks which do get affected by CPU frequency change
(they need to run at a fixed ratio to CPU frequency).
Thanks,
Sekhar
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [Query] CPUFreq: Does these machines have separate clock domains for CPUs?
2013-08-29 10:23 ` Sekhar Nori
@ 2013-08-29 10:30 ` Viresh Kumar
2013-08-29 10:27 ` Sekhar Nori
0 siblings, 1 reply; 11+ messages in thread
From: Viresh Kumar @ 2013-08-29 10:30 UTC (permalink / raw)
To: Sekhar Nori
Cc: linux-pm@vger.kernel.org, cpufreq@vger.kernel.org,
Linux Kernel Mailing List, linux-arm-kernel@lists.infradead.org,
Benjamin Herrenschmidt, David Miller, Eric Miao, Jesper Nilsson,
John Crispin, linux-cris-kernel, linux-sh, Mikael Starvik,
Paul Mundt, sparclinux, Miao Steven, Dave Jones
On 29 August 2013 15:53, Sekhar Nori <nsekhar@ti.com> wrote:
> On DaVinci (DA850), there is an async domain available to keep some
> peripheral clocks insulated from cpu frequency changes. But there are a
> bunch of other clocks which do get affected by CPU frequency change
> (they need to run at a fixed ratio to CPU frequency).
My question wasn't about how peripherals are getting clocks.. but how
CPUs are getting them..
Does all CPUs share clock line in Davinci? i.e. if we change freq of one
cpu then freq of other one also gets changed?
Or they are capable of running at different frequencies?
--
viresh
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [Query] CPUFreq: Does these machines have separate clock domains for CPUs?
2013-08-29 10:30 ` Viresh Kumar
@ 2013-08-29 10:27 ` Sekhar Nori
2013-08-29 10:33 ` Viresh Kumar
0 siblings, 1 reply; 11+ messages in thread
From: Sekhar Nori @ 2013-08-29 10:27 UTC (permalink / raw)
To: Viresh Kumar
Cc: Jesper Nilsson, Eric Miao, linux-cris-kernel,
linux-pm@vger.kernel.org, Benjamin Herrenschmidt, linux-sh,
Miao Steven, Linux Kernel Mailing List, cpufreq@vger.kernel.org,
Mikael Starvik, Paul Mundt, sparclinux, Dave Jones, David Miller,
linux-arm-kernel@lists.infradead.org, John Crispin
On Thursday 29 August 2013 04:00 PM, Viresh Kumar wrote:
> On 29 August 2013 15:53, Sekhar Nori <nsekhar@ti.com> wrote:
>> On DaVinci (DA850), there is an async domain available to keep some
>> peripheral clocks insulated from cpu frequency changes. But there are a
>> bunch of other clocks which do get affected by CPU frequency change
>> (they need to run at a fixed ratio to CPU frequency).
>
> My question wasn't about how peripherals are getting clocks.. but how
> CPUs are getting them..
>
> Does all CPUs share clock line in Davinci? i.e. if we change freq of one
> cpu then freq of other one also gets changed?
>
> Or they are capable of running at different frequencies?
I get it now. All DaVinci devices are UP only.
Thanks,
Sekhar
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [Query] CPUFreq: Does these machines have separate clock domains for CPUs?
2013-08-29 10:27 ` Sekhar Nori
@ 2013-08-29 10:33 ` Viresh Kumar
0 siblings, 0 replies; 11+ messages in thread
From: Viresh Kumar @ 2013-08-29 10:33 UTC (permalink / raw)
To: Sekhar Nori
Cc: linux-pm@vger.kernel.org, cpufreq@vger.kernel.org,
Linux Kernel Mailing List, linux-arm-kernel@lists.infradead.org,
Benjamin Herrenschmidt, David Miller, Eric Miao, Jesper Nilsson,
John Crispin, linux-cris-kernel, linux-sh, Mikael Starvik,
Paul Mundt, sparclinux, Miao Steven, Dave Jones
On 29 August 2013 15:57, Sekhar Nori <nsekhar@ti.com> wrote:
> I get it now. All DaVinci devices are UP only.
Thanks..
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [Query] CPUFreq: Does these machines have separate clock domains for CPUs?
2013-08-29 10:15 [Query] CPUFreq: Does these machines have separate clock domains for CPUs? Viresh Kumar
2013-08-29 10:23 ` Sekhar Nori
@ 2013-08-29 22:41 ` Aaro Koskinen
2013-08-30 4:21 ` Mikael Starvik
` (2 subsequent siblings)
4 siblings, 0 replies; 11+ messages in thread
From: Aaro Koskinen @ 2013-08-29 22:41 UTC (permalink / raw)
To: Viresh Kumar
Cc: linux-pm@vger.kernel.org, cpufreq@vger.kernel.org,
Linux Kernel Mailing List, linux-arm-kernel@lists.infradead.org,
Benjamin Herrenschmidt, David Miller, Eric Miao, Jesper Nilsson,
John Crispin, linux-cris-kernel, linux-sh, Mikael Starvik,
Paul Mundt, Sekhar Nori, sparclinux, Miao Steven, Dave Jones
Hi,
On Thu, Aug 29, 2013 at 03:45:58PM +0530, Viresh Kumar wrote:
> I have been doing some CPUFreq cleanup work and
> wanted to know if the below mentioned machines have separate
> clock domains for their CPUs or all share the same domain?
[...]
> drivers/cpufreq/loongson2_cpufreq.c
Loongson2 is UP only.
A.
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [Query] CPUFreq: Does these machines have separate clock domains for CPUs?
2013-08-29 10:15 [Query] CPUFreq: Does these machines have separate clock domains for CPUs? Viresh Kumar
2013-08-29 10:23 ` Sekhar Nori
2013-08-29 22:41 ` Aaro Koskinen
@ 2013-08-30 4:21 ` Mikael Starvik
2013-08-30 6:48 ` Magnus Damm
2013-08-30 8:49 ` Benjamin Herrenschmidt
4 siblings, 0 replies; 11+ messages in thread
From: Mikael Starvik @ 2013-08-30 4:21 UTC (permalink / raw)
To: Viresh Kumar
Cc: Eric Miao, linux-cris-kernel, linux-pm@vger.kernel.org,
Benjamin Herrenschmidt, linux-sh@vger.kernel.org, Sekhar Nori,
Linux Kernel Mailing List, cpufreq@vger.kernel.org,
Jesper Nilsson, Miao Steven, Paul Mundt,
sparclinux@vger.kernel.org, Dave Jones, David Miller,
linux-arm-kernel@lists.infradead.org, John Crispin
Cris are also UP
29 aug 2013 kl. 12:16 skrev "Viresh Kumar" <viresh.kumar@linaro.org>:
> Hi,
>
> I have been doing some CPUFreq cleanup work and
> wanted to know if the below mentioned machines have separate
> clock domains for their CPUs or all share the same domain?
>
> So, that we can use some generic routines for these drivers which
> would eventually do:
>
> cpumask_setall(policy->cpus);
>
> And I wanted to make sure that this doesn't break them.. :)
>
> ......
>
> The drivers are:
>
> drivers/cpufreq/at32ap-cpufreq.c
> drivers/cpufreq/blackfin-cpufreq.c
> drivers/cpufreq/cris-artpec3-cpufreq.c
> drivers/cpufreq/cris-etraxfs-cpufreq.c
> drivers/cpufreq/davinci-cpufreq.c
> drivers/cpufreq/e_powersaver.c
> drivers/cpufreq/elanfreq.c
> drivers/cpufreq/longhaul.c
> drivers/cpufreq/loongson2_cpufreq.c
> drivers/cpufreq/pmac32-cpufreq.c
> drivers/cpufreq/powernow-k6.c
> drivers/cpufreq/powernow-k7.c
> drivers/cpufreq/pxa2xx-cpufreq.c
> drivers/cpufreq/pxa3xx-cpufreq.c
> drivers/cpufreq/sc520_freq.c
> drivers/cpufreq/sh-cpufreq.c
> drivers/cpufreq/sparc-us2e-cpufreq.c
> drivers/cpufreq/sparc-us3-cpufreq.c
>
> --
> Viresh
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [Query] CPUFreq: Does these machines have separate clock domains for CPUs?
2013-08-29 10:15 [Query] CPUFreq: Does these machines have separate clock domains for CPUs? Viresh Kumar
` (2 preceding siblings ...)
2013-08-30 4:21 ` Mikael Starvik
@ 2013-08-30 6:48 ` Magnus Damm
2013-08-30 7:33 ` Viresh Kumar
2013-08-30 8:49 ` Benjamin Herrenschmidt
4 siblings, 1 reply; 11+ messages in thread
From: Magnus Damm @ 2013-08-30 6:48 UTC (permalink / raw)
To: Viresh Kumar
Cc: linux-pm@vger.kernel.org, cpufreq@vger.kernel.org,
Linux Kernel Mailing List, linux-arm-kernel@lists.infradead.org,
Jesper Nilsson, Eric Miao, linux-cris-kernel, SH-Linux,
Benjamin Herrenschmidt, Miao Steven, Sekhar Nori, Mikael Starvik,
Paul Mundt, sparclinux, Dave Jones, David Miller, John Crispin
Hi Viresh,
On Thu, Aug 29, 2013 at 7:15 PM, Viresh Kumar <viresh.kumar@linaro.org> wrote:
> Hi,
>
> I have been doing some CPUFreq cleanup work and
> wanted to know if the below mentioned machines have separate
> clock domains for their CPUs or all share the same domain?
>
> So, that we can use some generic routines for these drivers which
> would eventually do:
>
> cpumask_setall(policy->cpus);
>
> And I wanted to make sure that this doesn't break them.. :)
>
> ......
>
> The drivers are:
...
> drivers/cpufreq/sh-cpufreq.c
...
The above SH cpufreq driver seems to be written with SMP in mind, but
I would say SMP is a very rare case for SH. So I believe it can be
considered as UP-only at this point. If Paul disagrees I'm quite sure
he will tell us.
Cheers,
/ magnus
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [Query] CPUFreq: Does these machines have separate clock domains for CPUs?
2013-08-30 6:48 ` Magnus Damm
@ 2013-08-30 7:33 ` Viresh Kumar
2013-09-04 7:27 ` Magnus Damm
0 siblings, 1 reply; 11+ messages in thread
From: Viresh Kumar @ 2013-08-30 7:33 UTC (permalink / raw)
To: Magnus Damm
Cc: linux-pm@vger.kernel.org, cpufreq@vger.kernel.org,
Linux Kernel Mailing List, linux-arm-kernel@lists.infradead.org,
Jesper Nilsson, Eric Miao, linux-cris-kernel, SH-Linux,
Benjamin Herrenschmidt, Miao Steven, Sekhar Nori, Mikael Starvik,
Paul Mundt, sparclinux, Dave Jones, David Miller, John Crispin
On 30 August 2013 12:18, Magnus Damm <magnus.damm@gmail.com> wrote:
> Hi Viresh,
>
> On Thu, Aug 29, 2013 at 7:15 PM, Viresh Kumar <viresh.kumar@linaro.org> wrote:
>> Hi,
>>
>> I have been doing some CPUFreq cleanup work and
>> wanted to know if the below mentioned machines have separate
>> clock domains for their CPUs or all share the same domain?
>>
>> So, that we can use some generic routines for these drivers which
>> would eventually do:
>>
>> cpumask_setall(policy->cpus);
>>
>> And I wanted to make sure that this doesn't break them.. :)
>>
>> ......
>>
>> The drivers are:
> ...
>> drivers/cpufreq/sh-cpufreq.c
> ...
>
> The above SH cpufreq driver seems to be written with SMP in mind, but
> I would say SMP is a very rare case for SH. So I believe it can be
> considered as UP-only at this point. If Paul disagrees I'm quite sure
> he will tell us.
Okay.. The problem isn't really SMP but different clock domains for CPUs
in a SMP system..
So, even if we have a SMP SH machine, will it have same clock line for
all CPUs?
I will go with the change anyway..
Thanks.
--
viresh
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [Query] CPUFreq: Does these machines have separate clock domains for CPUs?
2013-08-30 7:33 ` Viresh Kumar
@ 2013-09-04 7:27 ` Magnus Damm
0 siblings, 0 replies; 11+ messages in thread
From: Magnus Damm @ 2013-09-04 7:27 UTC (permalink / raw)
To: Viresh Kumar
Cc: linux-pm@vger.kernel.org, cpufreq@vger.kernel.org,
Linux Kernel Mailing List, linux-arm-kernel@lists.infradead.org,
Jesper Nilsson, Eric Miao, linux-cris-kernel, SH-Linux,
Benjamin Herrenschmidt, Miao Steven, Sekhar Nori, Mikael Starvik,
Paul Mundt, sparclinux, Dave Jones, David Miller, John Crispin
Hi Viresh,
On Fri, Aug 30, 2013 at 4:33 PM, Viresh Kumar <viresh.kumar@linaro.org> wrote:
> On 30 August 2013 12:18, Magnus Damm <magnus.damm@gmail.com> wrote:
>> Hi Viresh,
>>
>> On Thu, Aug 29, 2013 at 7:15 PM, Viresh Kumar <viresh.kumar@linaro.org> wrote:
>>> Hi,
>>>
>>> I have been doing some CPUFreq cleanup work and
>>> wanted to know if the below mentioned machines have separate
>>> clock domains for their CPUs or all share the same domain?
>>>
>>> So, that we can use some generic routines for these drivers which
>>> would eventually do:
>>>
>>> cpumask_setall(policy->cpus);
>>>
>>> And I wanted to make sure that this doesn't break them.. :)
>>>
>>> ......
>>>
>>> The drivers are:
>> ...
>>> drivers/cpufreq/sh-cpufreq.c
>> ...
>>
>> The above SH cpufreq driver seems to be written with SMP in mind, but
>> I would say SMP is a very rare case for SH. So I believe it can be
>> considered as UP-only at this point. If Paul disagrees I'm quite sure
>> he will tell us.
>
> Okay.. The problem isn't really SMP but different clock domains for CPUs
> in a SMP system..
>
> So, even if we have a SMP SH machine, will it have same clock line for
> all CPUs?
Yeah, I understand your question but I'm afraid that I don't know the
answer myself.
> I will go with the change anyway..
Good plan. Thanks for cleaning up the cpufreq bits.
Cheers,
/ magnus
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [Query] CPUFreq: Does these machines have separate clock domains for CPUs?
2013-08-29 10:15 [Query] CPUFreq: Does these machines have separate clock domains for CPUs? Viresh Kumar
` (3 preceding siblings ...)
2013-08-30 6:48 ` Magnus Damm
@ 2013-08-30 8:49 ` Benjamin Herrenschmidt
4 siblings, 0 replies; 11+ messages in thread
From: Benjamin Herrenschmidt @ 2013-08-30 8:49 UTC (permalink / raw)
To: Viresh Kumar
Cc: Jesper Nilsson, Eric Miao, linux-cris-kernel,
linux-pm@vger.kernel.org, Miao Steven, linux-sh, Sekhar Nori,
Linux Kernel Mailing List, cpufreq@vger.kernel.org,
Mikael Starvik, Paul Mundt, sparclinux, Dave Jones, David Miller,
linux-arm-kernel@lists.infradead.org, John Crispin
On Thu, 2013-08-29 at 15:45 +0530, Viresh Kumar wrote:
> drivers/cpufreq/pmac32-cpufreq.c
This is always UP.
Cheers,
Ben.
^ permalink raw reply [flat|nested] 11+ messages in thread