Re: 3.10-rc4: mtrr_cleanup: can not find optimal value, pleasespecify mtrr_gran_size/mtrr_chunk_size
From: Sergey Meirovich
Date: Mon Jun 10 2013 - 15:01:08 EST
Hi,
On 10 June 2013 21:28, Yinghai Lu <yinghai@xxxxxxxxxx> wrote:
> On Mon, Jun 10, 2013 at 11:00 AM, Sergey Meirovich
> <rathamahata@xxxxxxxxx> wrote:
>
>> 3.10-rc5 with patches has curred error messages in dmesg but MTRRs
>> still do not cover my entire memory (7748Mb) or anything close to it
>> ("total RAM covered: 2936M").Unfortunately, I don't have anything
>> other to compare to because this system started straight with 3.9.X
>
> Your system is AMD 64bit, so there is TOM2.
>
>>
>> rathamahata@piledriver ~ $ free -m
>> total used free shared buffers cached
>> Mem: 7748 1264 6483 0 56 513
>> -/+ buffers/cache: 695 7053
>> Swap: 3659 0 3659
>> rathamahata@piledriver ~ $
>>
>> ...
>> [ 0.000000] e820: last_pfn = 0x23f000 max_arch_pfn = 0x400000000
>> [ 0.000000] MTRR default type: uncachable
>> [ 0.000000] MTRR fixed ranges enabled:
>> [ 0.000000] 00000-9FFFF write-back
>> [ 0.000000] A0000-BFFFF write-through
>> [ 0.000000] C0000-D2FFF write-protect
>> [ 0.000000] D3000-DFFFF uncachable
>> [ 0.000000] E0000-FFFFF write-protect
>> [ 0.000000] MTRR variable ranges enabled:
>> [ 0.000000] 0 base 000000000000 mask FFFF80000000 write-back
>> [ 0.000000] 1 base 000080000000 mask FFFFC0000000 write-back
>> [ 0.000000] 2 base 0000B7800000 mask FFFFFF800000 uncachable
>> [ 0.000000] 3 base 0000B8000000 mask FFFFF8000000 uncachable
>> [ 0.000000] 4 disabled
>> [ 0.000000] 5 disabled
>> [ 0.000000] 6 disabled
>> [ 0.000000] 7 disabled
>> [ 0.000000] TOM2: 000000023f000000 aka 9200M
>> [ 0.000000] x86 PAT enabled: cpu 0, old 0x7040600070406, new 0x7010600070106
>> [ 0.000000] original variable MTRRs
>> [ 0.000000] reg 0, base: 0GB, range: 2GB, type WB
>> [ 0.000000] reg 1, base: 2GB, range: 1GB, type WB
>> [ 0.000000] reg 2, base: 2936MB, range: 8MB, type UC
>> [ 0.000000] reg 3, base: 2944MB, range: 128MB, type UC
>> [ 0.000000] total RAM covered: 2936M
>> [ 0.000000] Found optimal setting for mtrr clean up
>> [ 0.000000] gran_size: 64K chunk_size: 256M num_reg: 4
>> lose cover RAM: 0G
>> [ 0.000000] New variable MTRRs
>> [ 0.000000] reg 0, base: 0GB, range: 2GB, type WB
>> [ 0.000000] reg 1, base: 2GB, range: 1GB, type WB
>> [ 0.000000] reg 2, base: 2936MB, range: 8MB, type UC
>> [ 0.000000] reg 3, base: 2944MB, range: 128MB, type UC
>> [ 0.000000] e820: update [mem 0xb7800000-0xffffffff] usable ==> reserved
>> [ 0.000000] e820: last_pfn = 0xb7800 max_arch_pfn = 0x400000000
>> [ 0.000000] Base memory trampoline at [ffff880000099000] 99000 size 24576
>> [ 0.000000] Using GB pages for direct mapping
>> [ 0.000000] init_memory_mapping: [mem 0x00000000-0x000fffff]20:
>> last_pfn = 0x23f000 max_arch_pfn = 0x400000000
>> [ 0.000000] MTRR default type: uncachable
>> [ 0.000000] MTRR fixed ranges enabled:
>> [ 0.000000] 00000-9FFFF write-back
>> [ 0.000000] A0000-BFFFF write-through
>> [ 0.000000] C0000-D2FFF write-protect
>> [ 0.000000] D3000-DFFFF uncachable
>> [ 0.000000] E0000-FFFFF write-protect
>> [ 0.000000] MTRR variable ranges enabled:
>> [ 0.000000] 0 base 000000000000 mask FFFF80000000 write-back
>> [ 0.000000] 1 base 000080000000 mask FFFFC0000000 write-back
>> [ 0.000000] 2 base 0000B7800000 mask FFFFFF800000 uncachable
>> [ 0.000000] 3 base 0000B8000000 mask FFFFF8000000 uncachable
>> [ 0.000000] 4 disabled
>> [ 0.000000] 5 disabled
>> [ 0.000000] 6 disabled
>> [ 0.000000] 7 disabled
>> [ 0.000000] TOM2: 000000023f000000 aka 9200M
>
> [4G, 9200M) is write-back automatically, there is no need to cover them
> again with VAR mtrr.
>
>> [ 0.000000] x86 PAT enabled: cpu 0, old 0x7040600070406, new 0x7010600070106
>> [ 0.000000] original variable MTRRs
>> [ 0.000000] reg 0, base: 0GB, range: 2GB, type WB
>> [ 0.000000] reg 1, base: 2GB, range: 1GB, type WB
>> [ 0.000000] reg 2, base: 2936MB, range: 8MB, type UC
>> [ 0.000000] reg 3, base: 2944MB, range: 128MB, type UC
>> [ 0.000000] total RAM covered: 2936M
>
> It only count var really.
>
>> [ 0.000000] Found optimal setting for mtrr clean up
>> [ 0.000000] gran_size: 64K chunk_size: 256M num_reg: 4
>> lose cover RAM: 0G
>> [ 0.000000] New variable MTRRs
>> [ 0.000000] reg 0, base: 0GB, range: 2GB, type WB
>> [ 0.000000] reg 1, base: 2GB, range: 1GB, type WB
>> [ 0.000000] reg 2, base: 2936MB, range: 8MB, type UC
>> [ 0.000000] reg 3, base: 2944MB, range: 128MB, type UC
>> [ 0.000000] e820: update [mem 0xb7800000-0xffffffff] usable ==> reserved
>> [ 0.000000] e820: last_pfn = 0xb7800 max_arch_pfn = 0x400000000
>> [ 0.000000] Base memory trampoline at [ffff880000099000] 99000 size 24576
>> [ 0.000000] Using GB pages for direct mapping
>> [ 0.000000] init_memory_mapping: [mem 0x00000000-0x000fffff]
>> ...
>
> so there is no problem with your system...
Thanks a lot for confirming this!
>
> Thanks
>
> Yinghai
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/