Re: configuration x86/Kconfig bug? or AMD feature request

[Randy Dunlap]

Hi--

On 8/31/22 16:54, Steven J Abner wrote:
> Hi
> I am tailoring a kernel for AMD 2400g on ASRock B450 using 5.18.12 as base.
> I found a feature I don't believe I need, and the system seems to work just
> fine without it. A quick glance at the code seems like I'll be just fine, too.
> In /drivers/platform/x86/Kconfig:1159  I altered the text to:
> 
> config PMC_ATOM
>      bool "Intel Atom SOC Power Management Controller Driver"
>      default y
>      depends on PCI
>      select COMMON_CLK

I can't tell what you changed it to.

> Please have a look and decide if x86 must include this code to function properly.
> Nothing but being x86 selects this. 'default y' was chosen only because forced y before.
> Steve
> 
> I wish to be personally CC'ed the answers/comments posted to the list
> in response to my posting, please. I not part of the list.


That kconfig option has been deleted:
commit 3cd8cc98d634
Author: Hans de Goede <hdegoede@xxxxxxxxxx>
Date:   Tue May 3 16:02:07 2022 +0200

    platform/x86: Drop the PMC_ATOM Kconfig option
    
    The def_bool y PMC_ATOM Kconfig option provides a couple of symbols used
    by the code enabled by the X86_INTEL_LPSS option and it registers some
    clocks. These clocks are only registered on Bay Trail, Cherry Trail and
    Brasswell Intel SoCs and kernels targeting these SoCs must always have
    the X86_INTEL_LPSS option enabled otherwise many things will not work.
    
    Building the PMC_ATOM code on kernels which are not targeting the
    mentioned SoCs and which do not have the X86_INTEL_LPSS enabled is
    not useful.
    
    This means that we can simplify things by replacing the PMC_ATOM Kconfig
    option in Makefiles with X86_INTEL_LPSS and then drop the option.


Maybe that commit should be backported?

-- 
~Randy