Re: [PATCH v1 1/5] ASoC: Intel: bytcht_cx2072x: Replace open coded acpi_dev_put()

From: Pierre-Louis Bossart
Date: Wed Jan 04 2023 - 11:13:54 EST




On 1/4/23 04:29, Andy Shevchenko wrote:
> On Tue, Jan 03, 2023 at 09:08:20AM -0600, Pierre-Louis Bossart wrote:
>> On 1/2/23 14:30, Andy Shevchenko wrote:
>>> Instead of calling put_device(&adev->dev) where adev is a pointer
>>> to an ACPI device, use specific call, i.e. acpi_dev_put().
>>>
>>> Also move it out of the conditional to make it more visible in case
>>> some other code will be added which may use that pointer. We need
>>> to keep a reference as long as we use the pointer.
>>>
>>> Signed-off-by: Andy Shevchenko <andriy.shevchenko@xxxxxxxxxxxxxxx>
>>
>> Answering for the series: we should make the change across all Intel
>> machine drivers. I see at least four cases that were missed
>>
>> bytcr_rt5640.c: put_device(&adev->dev);
>> bytcr_rt5651.c: put_device(&adev->dev);
>> bytcr_wm5102.c: put_device(&adev->dev);
>> sof_es8336.c: put_device(&adev->dev);
>
> Aren't they (they all problematic, btw) covered by the fixes series
> https://lore.kernel.org/r/20230102203014.16041-1-andriy.shevchenko@xxxxxxxxxxxxxxx?

They are indeed, but if you group AMD-related patches with Intel ones,
it's only human for reviewers to skip the thread entirely, even more so
when catching up with email on January 3 :-)

For this series

Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@xxxxxxxxxxxxxxx>