* use of scratchpad registers
@ 2013-03-25 10:07 Jan Beulich
2013-03-25 14:12 ` Konrad Rzeszutek Wilk
0 siblings, 1 reply; 2+ messages in thread
From: Jan Beulich @ 2013-03-25 10:07 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk; +Cc: xen-devel
Konrad,
in a response on thread "High CPU temp, suspend problem - xen
4.1.5-pre, linux 3.7.x", you say
"There are some BIOSes out there that I know that use the
scratchpad registers in IOH (so depending on the platform that
can be 0:0e.1 , Reg 0x84). If Xen or Linux touch it then the
P-states and C-states that the BIOS generates are buggy",
which makes me assume you have knowledge on why and where
Xen or Linux would touch these registers. It is my understanding
that these registers should be left alone by Xen, and be used by
Linux only in ways consistent between native and running on top
of Xen (i.e. through the same specific driver).
However, we've been having a report of there being a difference
in behavior, which so far we weren't able to narrow down the
origin of. Hence, if you know details here, I'd very much
appreciate if you could share them.
Thanks, Jan
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: use of scratchpad registers
2013-03-25 10:07 use of scratchpad registers Jan Beulich
@ 2013-03-25 14:12 ` Konrad Rzeszutek Wilk
0 siblings, 0 replies; 2+ messages in thread
From: Konrad Rzeszutek Wilk @ 2013-03-25 14:12 UTC (permalink / raw)
To: Jan Beulich; +Cc: xen-devel
On Mon, Mar 25, 2013 at 10:07:22AM +0000, Jan Beulich wrote:
> Konrad,
>
> in a response on thread "High CPU temp, suspend problem - xen
> 4.1.5-pre, linux 3.7.x", you say
>
> "There are some BIOSes out there that I know that use the
> scratchpad registers in IOH (so depending on the platform that
> can be 0:0e.1 , Reg 0x84). If Xen or Linux touch it then the
> P-states and C-states that the BIOS generates are buggy",
>
> which makes me assume you have knowledge on why and where
> Xen or Linux would touch these registers. It is my understanding
> that these registers should be left alone by Xen, and be used by
> Linux only in ways consistent between native and running on top
> of Xen (i.e. through the same specific driver).
>
> However, we've been having a report of there being a difference
> in behavior, which so far we weren't able to narrow down the
> origin of. Hence, if you know details here, I'd very much
> appreciate if you could share them.
Of course. Let me email the group that had let me know about this
scratchpad registers and see if they narrowed down _who_ was
poking at that. Once I get that information - or if they are
comfortable responding in a public forum, I will post it
here ASAP.
>
> Thanks, Jan
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> http://lists.xen.org/xen-devel
>
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2013-03-25 14:12 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2013-03-25 10:07 use of scratchpad registers Jan Beulich
2013-03-25 14:12 ` Konrad Rzeszutek Wilk
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).