Home » Mailing list archives » linux-kernel » 2008 » May » 2

[git head] Should X86_PAT really default to yes?

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
[view in full thread]
From: Frans Pop <elendil@...>
To: <linux-kernel@...>
Cc: Venki Pallipadi <venkatesh.pallipadi@...>, Ingo Molnar <mingo@...>
Subject: [git head] Should X86_PAT really default to yes?
Date: Friday, May 2, 2008 - 3:22 pm

With X86_PAT enabled, when X is started I get about 40 lines (with varying 
addresses) like:
kernel: Xorg:3358 /dev/mem expected mapping type write-back for 
807bf000-81000000, got uncached-minus

And when X exits I get a bunch of lines like:
kernel: Xorg:3349 freeing invalid memtype 80020000-8002a000

I also noticed artifacts (a band of about 2 cm high across the screen) after 
X goes to black but before the switch to VT1.

When I unset X86_PAT all this disappeared.

Apparently this has been seen before:
http://lkml.org/lkml/2008/5/2/139

The author of that mail also points to:
http://marc.info/?l=linux-kernel&m=120612742217604&w=2

Is this a bug in PAT or not. If it is, should PAT really be recommended to 
be enabled by default?

System: Intel desktop with D945GCZ mainboard
        Intel(R) Pentium(R) D CPU 3.20GHz
        x86_64 kernel; Debian unstable
Video:  00:02.0 VGA compatible controller [0300]:
        Intel Corporation 82945G/GZ Integrated Graphics Controller
        [8086:2772] (rev 02)

Cheers,
FJP
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
Messages in current thread:
[git head] Should X86_PAT really default to yes?, Frans Pop, (Fri May 2, 3:22 pm)
RE: [git head] Should X86_PAT really default to yes?, Pallipadi, Venkatesh, (Fri May 2, 3:37 pm)
Re: [git head] Should X86_PAT really default to yes?, Jesse Barnes, (Fri May 2, 4:40 pm)
Re: [git head] Should X86_PAT really default to yes?, Frans Pop, (Sun May 4, 3:10 am)
Re: [git head] Should X86_PAT really default to yes?, Jesse Barnes, (Mon May 5, 11:57 am)
Re: [git head] Should X86_PAT really default to yes?, Frans Pop, (Mon May 5, 1:32 pm)
Re: [git head] Should X86_PAT really default to yes?, Venki Pallipadi, (Tue May 6, 6:42 pm)
Re: [git head] Should X86_PAT really default to yes?, Frans Pop, (Sun May 25, 11:08 am)
Re: [git head] X86_PAT &amp; mprotect, Ingo Molnar, (Wed May 7, 3:02 am)
Re: [git head] X86_PAT &amp; mprotect, Venki Pallipadi, (Wed May 7, 6:36 pm)
Re: [git head] X86_PAT &amp; mprotect, Hugh Dickins, (Wed May 7, 3:18 pm)
Re: [git head] X86_PAT &amp; mprotect, Venki Pallipadi, (Wed May 7, 7:23 pm)
Re: [git head] X86_PAT &amp; mprotect, Ingo Molnar, (Fri May 9, 6:08 am)
Re: [git head] X86_PAT &amp; mprotect, Venki Pallipadi, (Fri May 9, 4:05 pm)
Re: [git head] X86_PAT &amp; mprotect, Dave Airlie, (Fri May 9, 6:11 pm)
Re: [git head] X86_PAT &amp; mprotect, Keith Packard, (Sat May 10, 1:45 am)
RE: [git head] X86_PAT &amp; mprotect, Pallipadi, Venkatesh, (Fri May 9, 6:20 pm)
Re: [git head] X86_PAT &amp; mprotect, Dave Airlie, (Sat May 10, 2:19 am)
Re: [git head] X86_PAT &amp; mprotect, Keith Packard, (Sat May 10, 2:29 am)
Re: [git head] X86_PAT &amp; mprotect, Venki Pallipadi, (Fri May 9, 4:09 pm)
Re: [git head] X86_PAT &amp; mprotect, Hugh Dickins, (Fri May 9, 4:48 pm)
Re: [git head] Should X86_PAT really default to yes?, Jesse Barnes, (Mon May 5, 1:45 pm)
Re: [git head] Should X86_PAT really default to yes?, Frans Pop, (Mon May 5, 2:59 pm)
Re: fb layer &amp; ioremap_wc, Jesse Barnes, (Mon May 5, 3:04 pm)
Re: fb layer &amp; ioremap_wc, Frans Pop, (Fri Jun 13, 12:42 pm)
RE: [git head] Should X86_PAT really default to yes?, Pallipadi, Venkatesh, (Mon May 5, 1:59 pm)
Re: [git head] Should X86_PAT really default to yes?, Yinghai Lu, (Sun May 4, 4:23 pm)
Re: [git head] Should X86_PAT really default to yes?, Frans Pop, (Mon May 5, 12:55 pm)
RE: [git head] Should X86_PAT really default to yes?, Pallipadi, Venkatesh, (Mon May 5, 1:00 pm)
Re: [git head] Should X86_PAT really default to yes?, Frans Pop, (Mon May 5, 2:56 pm)
Re: [git head] Should X86_PAT really default to yes?, Yinghai Lu, (Mon May 5, 1:42 pm)
Re: [git head] Should X86_PAT really default to yes?, Ingo Molnar, (Sun May 4, 5:04 am)
RE: [git head] Should X86_PAT really default to yes?, Pallipadi, Venkatesh, (Fri May 2, 5:55 pm)
Re: [git head] Should X86_PAT really default to yes?, Jesse Barnes, (Fri May 2, 6:07 pm)