Messages in this thread | | | Date | Tue, 22 Feb 2011 15:31:02 -0800 | From | Mike Waychison <> | Subject | Re: [PATCH v1 2/5] firmware: Basic dmi-sysfs support |
| |
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
| |