From mboxrd@z Thu Jan 1 00:00:00 1970 From: Mike Waychison Subject: Re: [PATCH v1 2/5] firmware: Basic dmi-sysfs support Date: Tue, 22 Feb 2011 15:31:02 -0800 Message-ID: <4D644736.9050109@google.com> References: <20110217212754.3967.98648.stgit@mike.mtv.corp.google.com> <20110217212805.3967.47547.stgit@mike.mtv.corp.google.com> <20110217215608.GA2451@kroah.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20110217215608.GA2451-U8xfFu+wG4EAvxtiuMwx3w@public.gmane.org> Sender: linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Greg KH Cc: Olof Johansson , Andi Kleen , Alan Cox , Robert Lippert , Jon Mayer , Duncan Laurie , Aaron Durbin , linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Tim Hockin , David Hendrix , linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Tony Luck List-Id: linux-api@vger.kernel.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