> On Fri, Aug 23, 2013 at 11:18 AM, Andreas Werner
> wrote:
>> Hi,
>>
>> why are you curious?
>>
>> I have never heard about movntdqa. Have you ever tried it?
>> May be it is a good idea to try i out.
>
> I've never tried it, but in theory it should be comparably fast as
> compared to WT.
>
>
On Fri, Aug 23, 2013 at 11:18 AM, Andreas Werner wrote:
> Hi,
>
> why are you curious?
>
> I have never heard about movntdqa. Have you ever tried it?
> May be it is a good idea to try i out.
I've never tried it, but in theory it should be comparably fast as
compared to WT.
--Andy
--
To
_PAGE_CACHE_WB;
>>> + else
>>> return _PAGE_CACHE_UC_MINUS;
>>> -
>>> - return _PAGE_CACHE_WB;
>>> +
>>> }
>>>
>>> return req_type;
>>>
>>
>> That seems more or less reasonable to me. If you want it incl
t;>
>
> That seems more or less reasonable to me. If you want it included,
> send it to x...@kernel.org (cc lkml) and see what they say.
>
> It would be prettier if you combined the conditions into a single
> if/else, though.
>
>>
>> Best regards.
>>
t; return req_type;
>
That seems more or less reasonable to me. If you want it included,
send it to x...@kernel.org (cc lkml) and see what they say.
It would be prettier if you combined the conditions into a single
if/else, though.
>
> Best regards.
>
>
> Gesendet: Montag, 12.
E_CACHE_WB;
+ else
return _PAGE_CACHE_UC_MINUS;
-
- return _PAGE_CACHE_WB;
+
}
return req_type;
Best regards.
Gesendet: Montag, 12. August 2013 um 19:53 Uhr
Von: "Andy Lutomirski"
An: "Andreas Werner"
Cc: linux-kernel@vger.kernel.org
Betreff: Re: question about
return _PAGE_CACHE_UC_MINUS;
-
- return _PAGE_CACHE_WB;
+
}
return req_type;
Best regards.
Gesendet: Montag, 12. August 2013 um 19:53 Uhr
Von: Andy Lutomirski l...@amacapital.net
An: Andreas Werner wernera...@gmx.de
Cc: linux-kernel@vger.kernel.org
Betreff: Re: question about
.
Best regards.
Gesendet: Montag, 12. August 2013 um 19:53 Uhr
Von: Andy Lutomirski l...@amacapital.net
An: Andreas Werner wernera...@gmx.de
Cc: linux-kernel@vger.kernel.org
Betreff: Re: question about ioremap_cache and PAT
On 08/11/2013 09:50 AM, Andreas Werner wrote:
Hi i have a question
.
Best regards.
Gesendet: Montag, 12. August 2013 um 19:53 Uhr
Von: Andy Lutomirski l...@amacapital.net
An: Andreas Werner wernera...@gmx.de
Cc: linux-kernel@vger.kernel.org
Betreff: Re: question about ioremap_cache and PAT
On 08/11/2013 09:50 AM, Andreas Werner wrote:
Hi i have a question
Lutomirski l...@amacapital.net
An: Andreas Werner wernera...@gmx.de
Cc: linux-kernel@vger.kernel.org
Betreff: Re: question about ioremap_cache and PAT
On 08/11/2013 09:50 AM, Andreas Werner wrote:
Hi i have a question about ioremap_cache and the resulting PAT
attribute on X86 system. If I configure
On Fri, Aug 23, 2013 at 11:18 AM, Andreas Werner wernera...@gmx.de wrote:
Hi,
why are you curious?
I have never heard about movntdqa. Have you ever tried it?
May be it is a good idea to try i out.
I've never tried it, but in theory it should be comparably fast as
compared to WT.
--Andy
--
On Fri, Aug 23, 2013 at 11:18 AM, Andreas Werner wernera...@gmx.de
wrote:
Hi,
why are you curious?
I have never heard about movntdqa. Have you ever tried it?
May be it is a good idea to try i out.
I've never tried it, but in theory it should be comparably fast as
compared to WT.
On 08/11/2013 09:50 AM, Andreas Werner wrote:
> Hi i have a question about ioremap_cache and the resulting PAT attribute on
> X86 system. If I configure the mtrr to Write-Through for an adress range, and
> call ioremap_cache to map the mmio, the resulting PAT attribute is set to UC.
> If I check
On 08/11/2013 09:50 AM, Andreas Werner wrote:
Hi i have a question about ioremap_cache and the resulting PAT attribute on
X86 system. If I configure the mtrr to Write-Through for an adress range, and
call ioremap_cache to map the mmio, the resulting PAT attribute is set to UC.
If I check the
Hi i have a question about ioremap_cache and the resulting PAT attribute on X86
system. If I configure the mtrr to Write-Through for an adress range, and call
ioremap_cache to map the mmio, the resulting PAT attribute is set to UC.
If I check the Intel document IA-32 SDM vol 3a, the resulting
Hi i have a question about ioremap_cache and the resulting PAT attribute on X86
system. If I configure the mtrr to Write-Through for an adress range, and call
ioremap_cache to map the mmio, the resulting PAT attribute is set to UC.
If I check the Intel document IA-32 SDM vol 3a, the resulting
16 matches
Mail list logo
