[Linux-ia64] Itanium 2 flaw detection

[Linux-ia64] Itanium 2 flaw detection

[Bruno Cornec]

Hello,

Concerning the recent problem announced by Intel on some I2 chips, do anyone
of you have a pointer to a script/C Code/whatever code which could give a
clear answer for the processor on which we are running ?
(I didn't had customer requests up yo now, but I prefer to be early :-)

Would it be also possible to include it in the result of /proc/cpuinfo as
it was done for pentium processor bugs some time ago:

[bruno@morley ~/Download]$ cat /proc/cpuinfo 
[...]
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
[...]

Of course in case of answer for point 1, I could try to propose a patch for 
point 2 (even if I never made kernel patches up to now).

TIA for any feedback,
Bruno.
-- 
Linux Solution Consultant         Tél: +33 476 143 278 - Fax: +33 476 146 105
HP/Intel Solution Center http://hpintelco.net Hewlett-Packard Grenoble/France
Des infos sur Linux?  http://www.HyPer-Linux.org      http://www.hp.com/linux
La musique ancienne?  http://www.musique-ancienne.org http://www.medieval.org

Re: [Linux-ia64] Itanium 2 flaw detection

[David Mosberger]

>>>>> On Thu, 15 May 2003 10:37:40 +0200, Bruno Cornec <Bruno.Cornec@hp.com> said:

  Bruno> Hello, Concerning the recent problem announced by Intel on
  Bruno> some I2 chips, do anyone of you have a pointer to a script/C
  Bruno> Code/whatever code which could give a clear answer for the
  Bruno> processor on which we are running ?  (I didn't had customer
  Bruno> requests up yo now, but I prefer to be early :-)

I don't, but I'd like to have it, too. ;-/

  Bruno> Would it be also possible to include it in the result of
  Bruno> /proc/cpuinfo as it was done for pentium processor bugs some
  Bruno> time ago:

  Bruno> [bruno@morley ~/Download]$ cat /proc/cpuinfo [...]  fdiv_bug
  Bruno> : no hlt_bug : no f00f_bug : no coma_bug : no [...]

That only makes sense for bugs for which the kernel can do something
about.  That's not the case here because there is no way for the
kernel to force the clock frequency down to 800MHz.

	--david