[lm-sensors] [patch 1/1] applesmc for Mac Pro 2 x Quad-Core

[Jean Delvare]

On Tue, 23 Oct 2007 20:40:55 -0400, Mark M. Hoffman wrote:
> Hi Jean:
> 
> * Jean Delvare <khali at linux-fr.org> [2007-10-23 23:01:36 +0200]:
> > On Tue, 23 Oct 2007 08:02:39 -0400, Mark M. Hoffman wrote:
> > > René: there is a series of patches for the f75375s hwmon driver that allow fans
> > > to be initialized with platform data.  Although I haven't reviewed the series
> > > in detail yet, IMO the concept looks OK and it may be appropriate for the Macs
> > > also.
> > > 
> > > http://lists.lm-sensors.org/pipermail/lm-sensors/2007-October/021597.html
> > > http://lists.lm-sensors.org/pipermail/lm-sensors/2007-October/021598.html
> > > http://lists.lm-sensors.org/pipermail/lm-sensors/2007-October/021599.html
> > 
> > I still need to be convinced why this has to be hard-coded in the
> > kernel when the same can be done, and fine-tuned, in user-space just
> > fine.
> 
> For the same reasons that it would be better still if it were done by the BIOS.
> 
> When the machine's safety is at stake, you initialize the hardware into a sane,
> safe state as early as possible.  Fine tuning is not the issue here.  When you
> *know* that the hardware does not come up into a safe state, you should correct
> that ASAP.
> 
> Say fsck fails out to a shell during early inits... so the fans run full-on,
> big deal the machine needs attention anyway.  That sure beats having some
> unrelated early userspace problem cause your power supply to catch fire.
> 
> Is that good hardware design?  No, but that's irrelevant.
> 
> You are going to have to convince *me* why that patch series is a bad idea.

OK, you're right.

-- 
Jean Delvare