Re: [lm-sensors] coretemp: Support for Intel Atom E6XX CPU (TunnelCreek)?

[Jean Delvare <khali@linux-fr.org>]

Hi Alexander,

On Wed, 3 Aug 2011 16:40:30 +0200, Alexander Stein wrote:
> On Wednesday 03 August 2011 15:26:53 R, Durgadoss wrote:
> > Yes I checked with some Atom Guys here.
> > Apparently there is no way to know it from the OS Level.
> > 
> > > On Monday 27 June 2011 18:54:44 R, Durgadoss wrote:
> > > > > Unfortunately, looking at Alexander's /proc/cpuinfo output, it looks
> > > > > like the E6xx chips have no mention of E6xx in the CPU ID string,
> > > > > which unfortunately kills the idea.
> > > > > 
> > > > > Do you know if there is _any_ means to distinguish E6xx from E6xxT ?
> > > > 
> > > > Sorry I do not know. But I can ask some folks here and get back
> > > > to you guys. Should not take more time, once I identify the right
> > > > person to ask :-)
> 
> So, is there a possibility to add a module parameter to force a either 
> specific tjmax or the T model for E6xx?

A parameter to force the T model for E6xx would be very very specific,
while the problem at hand is much broader: the heuristics in
adjust_tjmax() are best effort but largely insufficient in many (most?)
cases. So, as we have been enable to provide a relative temperature
scale interface in the past 2 years, a module parameter letting the
user set TjMax as needed seems the best approach to me. I'll submit a
patch doing this in a moment.

-- 
Jean Delvare