Re: CPU MTRRs and linux kernel

[Stefan Bader]

On 12.06.2012 15:48, Mahmood Naderan wrote:
> Thanks Borislav,
> I want to know, should I upgrade to the latest kernel or it is possible to download the source of 2.6.32-24 from repository and modify cleanup.c and then recompile?
> 
Just update to the latest kernel. 2.6.32-24.39 is way old. The fix Boris
mentioned was in 2.6.32-27.49. And the latest kernel is 2.6.32-41.89 by now...

-Stefan

> ~MN
> 
> ----- Original Message -----
> From: Borislav Petkov <bp@xxxxxxxxx>
> To: Mahmood Naderan <nt_mahmood@xxxxxxxxx>
> Cc: "linux-kernel@xxxxxxxxxxxxxxx" <linux-kernel@xxxxxxxxxxxxxxx>; Andreas Herrmann <andreas.herrmann3@xxxxxxx>
> Sent: Tuesday, June 12, 2012 3:09 PM
> Subject: Re: CPU MTRRs and linux kernel
> 
> On Tue, Jun 12, 2012 at 02:37:40AM -0700, Mahmood Naderan wrote:
>> Hi everybody,
>> Abour rhis warnning in boot log:
>>
>> WARNING: BIOS bug: CPU MTRRs don't cover all of memory, losing 61952MB of RAM
>>
>>  
>> I
>>   searched a lot however didn't find a clear solution. Does AMD new 
>> processors (62XX) have problems with new kernels or old kernels??
>> Mine is:
>>
>> Linux n1 2.6.32-24-server #39-Ubuntu SMP Wed Jul 28 06:21:40 UTC 2010 x86_64 GNU/Linux
>>
>> Should I upgrade?
> 
> Yes, fix is below and it got backported to -stable AFAICT but obviously
> the ubuntus don't have it in the kernel you cite above.
> 
> 
> commit 3fdbf004c1706480a7c7fac3c9d836fa6df20d7d
> Author: Andreas Herrmann <andreas.herrmann3@xxxxxxx>
> Date:   Thu Sep 30 14:32:35 2010 +0200
> 
>     x86, mtrr: Assume SYS_CFG[Tom2ForceMemTypeWB] exists on all future AMD CPUs
>     
>     Instead of adapting the CPU family check in amd_special_default_mtrr()
>     for each new CPU family assume that all new AMD CPUs support the
>     necessary bits in SYS_CFG MSR.
>     
>     Tom2Enabled is architectural (defined in APM Vol.2).
>     Tom2ForceMemTypeWB is defined in all BKDGs starting with K8 NPT.
>     In pre K8-NPT BKDG this bit is reserved (read as zero).
>     
>     W/o this adaption Linux would unnecessarily complain about bad MTRR
>     settings on every new AMD CPU family, e.g.
>     
>     [    0.000000] WARNING: BIOS bug: CPU MTRRs don't cover all of memory, losing 4863MB of RAM.
>     
>     Cc: stable@xxxxxxxxxx # .32.x, .35.x
>     Signed-off-by: Andreas Herrmann <andreas.herrmann3@xxxxxxx>
>     LKML-Reference: <20100930123235.GB20545@xxxxxxxxxxxx>
>     Signed-off-by: H. Peter Anvin <hpa@xxxxxxxxxxxxxxx>
> 
> diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
> index c5f59d071425..ac140c7be396 100644
> --- a/arch/x86/kernel/cpu/mtrr/cleanup.c
> +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
> @@ -827,7 +827,7 @@ int __init amd_special_default_mtrr(void)
> 
>         if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
>                 return 0;
> -       if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11)
> +       if (boot_cpu_data.x86 < 0xf)
>                 return 0;
>         /* In case some hypervisor doesn't pass SYSCFG through: */
>         if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0)
>

Attachment: signature.asc
Description: OpenPGP digital signature