Re: [PATCH v1 2/5] firmware: Basic dmi-sysfs support

[Mike Waychison <mikew-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>]

On 02/17/11 13:56, Greg KH wrote:
> Overall, this looks great, just a few minor comments below:
>
> On Thu, Feb 17, 2011 at 01:28:05PM -0800, Mike Waychison wrote:
>> +config DMI_SYSFS
>> +	tristate "DMI table support in sysfs"
>> +	depends on SYSFS&&  DMI
>> +	default X86
>
> Huh?  Default should be 'N' for any new feature, unless it keeps your
> machine from booting.
>
> I think you want this option to depend on X86 though, right?

Looks to be supported on ia64 as well, though I don't have any hardware 
to test this code on for that arch.  Tony: I think this DMI exporting 
code should just work on ia64 as all it is using is dmi_walk() and 
parsing the entries as returned as dmi_headers in the callback.  Does 
this sound sane to you?

>
>> +	help
>> +	  Say Y or M here to enable the exporting of the raw DMI table
>> +	  data via sysfs.  This is useful for consuming the data without
>> +	  requiring any access to /dev/mem at all.  Tables are found
>> +	  under /sys/firmware/dmi when this option is enabled and
>> +	  loaded.
>
> I just realized (due to other work I'm doing on a laptop) that we have a
> bunch of entries today in /sys/class/dmi/id which is a pointer to the
> dmi "device".
>
> Now I think this really is different (these are the raw DMI tables), but
> this doesn't have anything to do with that code, right?

Ya, it is similar, though the primary goal I have is to export these raw 
bytes.  The data comes from the same place, however the dmi-id code is 
just exporting the in-kernel copies of the strings parsed at boot.

These could probably be better exported under 
/sys/firmware/dmi/entries/[0123]-*/ files imo.

Mike Waychison