Re: [PATCH v2 3/4] cpufreq: s5pv210: Defer probe if getting regulators fail

From: PaweÅ Chmiel
Date: Fri Jan 11 2019 - 04:53:59 EST


pt., 11 sty 2019 o 10:46 Krzysztof Kozlowski <krzk@xxxxxxxxxx> napisaÅ(a):
>
> On Thu, 10 Jan 2019 at 21:53, PaweÅ Chmiel
> <pawel.mikolaj.chmiel@xxxxxxxxx> wrote:
> >
> > There is possibility, that when probing driver, regulators are not yet
> > initialized. In this case we should return EPROBE_DEFER and wait till
> > they're initialized, since they're required currently for cpufreq driver
> > to work. Also move regulator initialization code at beginning of probe,
> > so we can defer as fast as posibble.
> >
> > Signed-off-by: PaweÅ Chmiel <pawel.mikolaj.chmiel@xxxxxxxxx>
> > ---
> > Changes from v1:
> > - Fix compilation error
> > - Reorganize code so it's smaller
> > ---
> > drivers/cpufreq/s5pv210-cpufreq.c | 32 ++++++++++++++++++-------------
> > 1 file changed, 19 insertions(+), 13 deletions(-)
> >
> > diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
> > index f51697f1e0b3..6df95941ba96 100644
> > --- a/drivers/cpufreq/s5pv210-cpufreq.c
> > +++ b/drivers/cpufreq/s5pv210-cpufreq.c
> > @@ -594,6 +594,25 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev)
> > * this whole driver as soon as S5PV210 gets migrated to use
> > * cpufreq-dt driver.
> > */
> > + arm_regulator = regulator_get(NULL, "vddarm");
> > + if (IS_ERR(arm_regulator)) {
> > + if (PTR_ERR(arm_regulator) == -EPROBE_DEFER)
> > + pr_debug("vddarm regulator not ready, defer\n");
> > + else
> > + pr_err("failed to get regulator vddarm\n");
> > + return PTR_ERR(arm_regulator);
> > + }
> > +
> > + int_regulator = regulator_get(NULL, "vddint");
> > + if (IS_ERR(int_regulator)) {
> > + if (PTR_ERR(int_regulator) == -EPROBE_DEFER)
> > + pr_debug("vddint regulator not ready, defer\n");
> > + else
> > + pr_err("failed to get regulator vddint\n");
> > + regulator_put(arm_regulator);
> > + return PTR_ERR(int_regulator);
> > + }
> > +
>
> Error paths are now not correct. You should put the regulators when
> returning later. The previous code had these error paths wrong as well
> - not iounmapping - but if you move things around, maybe let's fix
> things.
Ok, will fix this in new version and will resend it (only this one
patch, since all other looks ok/applied).
Also will add missing iounmapping/etc to fix all other error paths.

Thanks
>
> Best regards,
> Krzysztof