Re: Linux 2.6.38.4 : regression due to x86 AMD ARAT feature

[Borislav Petkov <bp@amd64.org>]

On Fri, Apr 29, 2011 at 02:34:41PM -0400, Jiri Slaby wrote:
> On 04/24/2011 09:44 PM, Ostrovsky, Boris wrote:
> > Borislav Petkov wrote, on 04/24/11 20:20:
> >> On Sun, Apr 24, 2011 at 10:06:36AM +0200, Jörg-Volker Peetz wrote:
> >>> With 2.6.38.4 the clock slows down and the affected laptop sometimes, e.g. for
> >>> the output of "ps axuw" to appear, needs an input from the keyboard or the
> >>> touchpad. Please find attached the kernel config file and the output of dmesg.
> >>>
> >>> Commenting out the the lines
> >>>
> >>>      if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400))
> >>>              set_cpu_cap(c, X86_FEATURE_ARAT);
> >>>
> >>> in arch/x86/kernel/cpu/amd.c makes this laptop work as before with kernel
> >>> 2.6.38.3. I think these lines came with commit
> >>> d7b7f0c401303dd7eafcff11752fe74d3b75c766.
> 
> > It's an old family fh processor (CPUID 00020F42) that
> cpu_has_amd_erratum(amd_erratum_400) apparently hasn't picked up. Since
> all fh processors are affected by this erratum I'll replace "c->x86 >=
> 0xf" with "c->x86 > 0xf" (and probably fix erratum formula anyway).
> 
> Hi, what's the status of this please?
> 
> I don't see the fix neither in the -next tree.

Boris O will be coming up with a patch soon. We wanted to clarify the
details first.

Thanks.

-- 
Regards/Gruss,
Boris.

Advanced Micro Devices GmbH
Einsteinring 24, 85609 Dornach
General Managers: Alberto Bozzo, Andrew Bowd
Registration: Dornach, Gemeinde Aschheim, Landkreis Muenchen
Registergericht Muenchen, HRB Nr. 43632