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:
quoted
+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?
quoted
+ 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