Athlon adv speculative caching fix removed from 2.4.20?

Athlon adv speculative caching fix removed from 2.4.20?

[Oliver Feiler]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Hi,

in patch-2.4.20 'static void amd_adv_spec_cache_disable(void)' was removed 
from arch/i386/kernel/setup.c.

I haven't found any patch on lkml posted that did this and it wasn't mentioned 
in 2.4.20's changelog.

Can someone point to a why this was removed, maybe a different fix since the 
one mentioned says "Short-term fix" or is it not needed anymore for some 
reason?

Bye,
Oliver

- -- 
Oliver Feiler  <kiza@(kcore.de|lionking.org|gmx(pro).net)>
http://kiza.kcore.de/    <--    homepage
PGP-key      -->    /pgpkey.shtml
http://kiza.kcore.de/journal/
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.1 (GNU/Linux)

iD8DBQE+SCXqOpifZVYdT9IRAlpTAKDRjsbgPJDj6MhjnrjuCnXzKaoODACg4f8/
w8NSN6QG9K+ULPaB9/AVRDU=
=xj4v
-----END PGP SIGNATURE-----

Re: Athlon adv speculative caching fix removed from 2.4.20?

[Dave Jones]

On Mon, Feb 10, 2003 at 11:21:24PM +0100, Oliver Feiler wrote:

 > Can someone point to a why this was removed, maybe a different fix since the 
 > one mentioned says "Short-term fix" or is it not needed anymore for some 
 > reason?

A better fix went in. See the changes to agpgart.

		Dave
 
-- 
| Dave Jones.        http://www.codemonkey.org.uk
| SuSE Labs

Re: Athlon adv speculative caching fix removed from 2.4.20?

[Andi Kleen]

Oliver Feiler <kiza@gmx.net> writes:
> 
> Can someone point to a why this was removed, maybe a different fix since the 
> one mentioned says "Short-term fix" or is it not needed anymore for some 
> reason?

The "long term" fix for it went in instead (arch/i386/mm/pageattr.c)
The kernel is careful now to not create conflicting cache attributes
for AGP and other mappings.  This makes the linux kernel x86
conformant in this area.  It also increases performance on
Athlon XP/MP because they can now use large pages in kernel space again.

-Andi

Re: Athlon adv speculative caching fix removed from 2.4.20?

[Oliver Feiler]

On Monday 10 February 2003 23:36, Andi Kleen wrote:
>
> The "long term" fix for it went in instead (arch/i386/mm/pageattr.c)
> The kernel is careful now to not create conflicting cache attributes
> for AGP and other mappings.  This makes the linux kernel x86
> conformant in this area.  It also increases performance on
> Athlon XP/MP because they can now use large pages in kernel space again.

Ah yes, indeed. I must have missed that. :)

Thanks for the quick answers everyone.

-Oliver

-- 
Oliver Feiler  <kiza@(kcore.de|lionking.org|gmx(pro).net)>
http://kiza.kcore.de/    <--    homepage
PGP-key      -->    /pgpkey.shtml
http://kiza.kcore.de/journal/