Messages in this thread | | | Subject | RE: [git head] Should X86_PAT really default to yes? | Date | Fri, 2 May 2008 12:37:32 -0700 | From | "Pallipadi, Venkatesh" <> |
| |
>-----Original Message----- >From: Frans Pop [mailto:elendil@planet.nl] >Sent: Friday, May 02, 2008 12:22 PM >To: linux-kernel@vger.kernel.org >Cc: Pallipadi, Venkatesh; Ingo Molnar >Subject: [git head] Should X86_PAT really default to yes? > >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) >
Copying the X-guys. The messages all look like debug messages from X and should not cause any side-effects other than little annoyance. I am not sure why band of 2 cm is there... Do you see any performance difference with or without PAT.
Thanks, Venki
| |