Re: mtrr cleanup not doing anything on 2.6.33-rc7

["Carlos R. Mafra" <crmafra2@gmail.com>]

On Do 11.Feb'10 at  6:56:59 -0800, H. Peter Anvin wrote:
> On 02/11/2010 02:10 AM, Carlos R. Mafra wrote:
> > [Add people in that commit to Cc: list, just in case]
> > 
> > On Mi 10.Feb'10 at 20:48:49 -0500, Alexander Lam wrote:
> >> On Wed, Feb 10, 2010 at 3:02 PM, Alexander Lam <lambchop468@gmail.com> wrote:
> >>>
> >>> My kernel config has the following:
> >>> CONFIG_MTRR=y
> >>> CONFIG_MTRR_SANITIZER=y
> >>> CONFIG_MTRR_SANITIZER_ENABLE_DEFAULT=1
> >>> CONFIG_MTRR_SANITIZER_SPARE_REG_NR_DEFAULT=1
> >>>
> >>> With previous kernels, dmesg would show that the sanitizer was indeed
> >>> cleaning up the mtrrs [1]
> >>>
> >>> but now, with 2.6.33-rc7 there is no indication that this is occuring,
> >>
> >> For those who run across this later,
> >>
> >> Found out that commit 508d85c2c6bc8cba53d2a54d9a306ad64a0a80bf,
> >>    x86: When cleaning MTRRs, do not fold WP into UC
> >>
> >> causes mtrr cleanup not to run on my machine.
> >>
> >> Probably not worth fixing because the i915 error message is harmless.
> >> --
> 
> You're not stating what your MTRR setup looks like, and hence if there
> is anything to clean up.

I am not sure if I am being an intruder here, but I also should
have quoted Alexander's first email:

Hi all,

Please CC: me when replying.

My kernel config has the following:
CONFIG_MTRR=y
CONFIG_MTRR_SANITIZER=y
CONFIG_MTRR_SANITIZER_ENABLE_DEFAULT=1
CONFIG_MTRR_SANITIZER_SPARE_REG_NR_DEFAULT=1

With previous kernels, dmesg would show that the sanitizer was indeed
cleaning up the mtrrs [1]

but now, with 2.6.33-rc7 there is no indication that this is occuring,
and the intel i915 driver complains:
   [    0.613419] i915 0000:00:02.0: PCI INT A -> GSI 16 (level, low) -> IRQ 16
   [    0.614577] i915 0000:00:02.0: setting latency timer to 64
   [    0.625446] mtrr: no more MTRRs available
   [    0.625529] [drm] MTRR allocation failed.  Graphics performance
may suffer.

What has changed and what do I need to do to make the mtrr sanitation
work again?

[1]: dmesg from previous kernels:
[    0.000000] MTRR default type: uncachable
[    0.000000] MTRR fixed ranges enabled:
[    0.000000]   00000-9FFFF write-back
[    0.000000]   A0000-BFFFF uncachable
[    0.000000]   C0000-C7FFF write-protect
[    0.000000]   C8000-EFFFF uncachable
[    0.000000]   F0000-FFFFF write-protect
[    0.000000] MTRR variable ranges enabled:
[    0.000000]   0 base 0FFFE0000 mask 0FFFE0000 write-protect
[    0.000000]   1 base 0FFFC0000 mask 0FFFE0000 uncachable
[    0.000000]   2 base 000000000 mask 0E0000000 write-back
[    0.000000]   3 base 020000000 mask 0E0000000 write-back
[    0.000000]   4 base 03F800000 mask 0FF800000 uncachable
[    0.000000]   5 base 03F600000 mask 0FFE00000 uncachable
[    0.000000]   6 base 03F500000 mask 0FFF00000 uncachable
[    0.000000]   7 base 000000000 mask 0FFFE0000 uncachable
[    0.000000] x86 PAT enabled: cpu 0, old 0x7040600070406, new 0x7010600070106
[    0.000000] original variable MTRRs
[    0.000000] reg 0, base: 4194176KB, range: 128KB, type WP
[    0.000000] reg 1, base: 4194048KB, range: 128KB, type UC
[    0.000000] reg 2, base: 0GB, range: 512MB, type WB
[    0.000000] reg 3, base: 512MB, range: 512MB, type WB
[    0.000000] reg 4, base: 1016MB, range: 8MB, type UC
[    0.000000] reg 5, base: 1014MB, range: 2MB, type UC
[    0.000000] reg 6, base: 1013MB, range: 1MB, type UC
[    0.000000] reg 7, base: 0GB, range: 128KB, type UC
[    0.000000] WARNING: BIOS bug: VAR MTRR 7 contains strange UC entry
under 1M, check with your system vendor!
[    0.000000] total RAM coverred: 1013M
[    0.000000] Found optimal setting for mtrr clean up
[    0.000000]  gran_size: 64K  chunk_size: 16M         num_reg: 4
 lose cover RAM: 0G
[    0.000000] New variable MTRRs
[    0.000000] reg 0, base: 0GB, range: 1GB, type WB
[    0.000000] reg 1, base: 1013MB, range: 1MB, type UC
[    0.000000] reg 2, base: 1014MB, range: 2MB, type UC
[    0.000000] reg 3, base: 1016MB, range: 8MB, type UC
[    0.000000] x86 PAT enabled: cpu 0, old 0x7040600070406, new 0x7010600070106


Thanks,
-- 
Alexander Lam