Messages in this thread | | | Date | Tue, 29 Apr 2008 15:18:34 -0700 | From | "Yinghai Lu" <> | Subject | Re: [PATCH] x86: mtrr cleanup for converting continuous to discrete layout v5 |
| |
On Tue, Apr 29, 2008 at 3:09 PM, Ingo Molnar <mingo@elte.hu> wrote: > > * Yinghai Lu <yhlu.kernel@gmail.com> wrote: > > > agreed. so that feature is compiled in but disable by default. > > > > BTW: is any chance for OS to disable SMI etc? to verify is the > > unstatbility is caused by SMI? > > i dont think there's any documented way for that. SMI might be the > mechanism that ensures blue-smoke type of system reliability (CPU fan, > temperature, etc.) so it would be extremely dangerous to mess with it.
then that is bad and sick HW design.
for example. cpu fan is supposed to full speed, if SW send insane instruction and lose connection. also, CPU should shutdown by thermal strip is FAN is stopped.
when we were working on LinuxBIOS, found one MB cpu fan need to be started by BIOS, and another one is auto full speed if BIOS don't touch it. We always like the second design.
YH
| |