[PATCH v8 24/24] gpio/omap: handle set_dataout reg capable IP on restore

Kevin Hilman khilman at ti.com
Wed Nov 23 14:54:15 EST 2011


"DebBarma, Tarun Kanti" <tarun.kanti at ti.com> writes:

> On Mon, Nov 7, 2011 at 5:35 PM, DebBarma, Tarun Kanti
> <tarun.kanti at ti.com> wrote:
>> On Fri, Nov 4, 2011 at 10:23 PM, Kevin Hilman <khilman at ti.com> wrote:
>>> Tarun Kanti DebBarma <tarun.kanti at ti.com> writes:
>>>
>>>> From: Nishanth Menon <nm at ti.com>
>>>>
>>>> GPIO IP revisions such as those used in OMAP4 have a set_dataout
>>>> while the previous revisions used a single dataout register.
>>>> Depending on what is available restore the dataout settings
>>>> to the right register.
>>>>
>>>> Signed-off-by: Nishanth Menon <nm at ti.com>
>>>> Signed-off-by: Tarun Kanti DebBarma <tarun.kanti at ti.com>
>>>> Reviewed-by: Santosh Shilimkar <santosh.shilimkar at ti.com>
>>>> ---
>>>>  drivers/gpio/gpio-omap.c |    9 +++++++--
>>>>  1 files changed, 7 insertions(+), 2 deletions(-)
>>>>
>>>> diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
>>>> index 4009446..3df7a98 100644
>>>> --- a/drivers/gpio/gpio-omap.c
>>>> +++ b/drivers/gpio/gpio-omap.c
>>>> @@ -1073,7 +1073,7 @@ static int __devinit omap_gpio_probe(struct platform_device *pdev)
>>>>       bank->get_context_loss_count = pdata->get_context_loss_count;
>>>>       bank->regs = pdata->regs;
>>>>
>>>> -     if (bank->regs->set_dataout && bank->regs->clr_dataout)
>>>> +     if (bank->regs->set_dataout)
>>>
>>> This change isn't right.
>>>
>>> The _set_gpio_dataout_reg function depends on the existence of
>>> ->clr_dataout too.
>> Ok, I will add the clr_dataout condtion as well.
>
>>
>>>
>>>>               bank->set_dataout = _set_gpio_dataout_reg;
>>>>       else
>>>>               bank->set_dataout = _set_gpio_dataout_mask;
>>>> @@ -1351,7 +1351,12 @@ static void omap_gpio_restore_context(struct gpio_bank *bank)
>>>>                               bank->base + bank->regs->risingdetect);
>>>>       __raw_writel(bank->context.fallingdetect,
>>>>                               bank->base + bank->regs->fallingdetect);
>>>> -     __raw_writel(bank->context.dataout, bank->base + bank->regs->dataout);
>>>> +     if (bank->regs->set_dataout)
>>>
>>> Why the check again?  The check has already been done in probe.
>>>
>>> Just use bank->set_dataout() here.
>> Sure, i will make the change.
>
> When I look at the signature of set_dataout(), it does not seem
> straight forward to be used here. It expects (struct gpio_bank *bank,
> int gpio, int enable) to be passed to it.

IOW, it expects to only set 1 bit, where the context restore needs to
set the value for the whole register.

OK, then keep the original version, but make sure the if statement
matches is checking for ->set_dataout and ->clr_dataout like the other one.

Kevin




More information about the linux-arm-kernel mailing list