Re: [PATCH v2] cpufreq: qcom-hw: Set dvfs_possible_from_any_cpu cpufreq driver flag

[Viresh Kumar]

On 18-08-21, 15:33, Taniya Das wrote:
> Hi Doug,
> 
> Thanks for your review.
> 
> On 8/13/2021 2:03 AM, Doug Anderson wrote:
> > Hi,
> > 
> > On Thu, Aug 12, 2021 at 7:19 AM Taniya Das <tdas@xxxxxxxxxxxxxx> wrote:
> > > 
> > > As remote cpufreq updates are supported on QCOM platforms, set
> > > dvfs_possible_from_any_cpu cpufreq driver flag.
> > > 
> > > Signed-off-by: Taniya Das <tdas@xxxxxxxxxxxxxx>
> > > ---
> > > 
> > > [v2]
> > >    * update the dvfs_possible_from_any_cpu always.
> > > 
> > >   drivers/cpufreq/qcom-cpufreq-hw.c | 2 ++
> > >   1 file changed, 2 insertions(+)
> > > 
> > > diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
> > > index f86859b..53d3898 100644
> > > --- a/drivers/cpufreq/qcom-cpufreq-hw.c
> > > +++ b/drivers/cpufreq/qcom-cpufreq-hw.c
> > > @@ -223,6 +223,8 @@ static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
> > > 
> > >          table[i].frequency = CPUFREQ_TABLE_END;
> > >          policy->freq_table = table;
> > > +       policy->dvfs_possible_from_any_cpu = true;
> > > +
> > 
> > Why is this in the qcom_cpufreq_hw_read_lut() function? Shouldn't it
> > be straight in qcom_cpufreq_hw_cpu_init()?
> > 
> All CPU policy related data is updated here, thus wanted to keep it
> together.

This function should only be updating freq table, please do it in
qcom_cpufreq_hw_cpu_init() itself, around where you set
policy->driver_data.

-- 
viresh