Re: Another mtrr - BIOS-e820 mismatch

[Mikael Pettersson]

On Fri, 18 Jun 2004 10:51:12 +0300 (EEST), Catalin BOIE wrote:
>Yesterday I read about a mtrr - BIOS-e820 mismatch.
>So I check on a server and I think I find a mismatch:
>2048MB - 1 = 7FFFFFFF, but at 0x7ff80000 there is 512 uncacheable memory.
>Am I right?
>
>Thanks!
>
>It's a Intel MB, with 2 Pentium 4, with HT, 2GB RAM.
>(Sorry I could not get more info.)
>
>reg00: base=0x00000000 (   0MB), size=2048MB: write-back, count=1
>reg01: base=0x7ff80000 (2047MB), size= 512KB: uncachable, count=1
>
>BIOS-provided physical RAM map:
>BIOS-e820: 0000000000000000 - 000000000009b400 (usable)
>BIOS-e820: 000000000009b400 - 00000000000a0000 (reserved)
>BIOS-e820: 00000000000cc000 - 00000000000d0000 (reserved)
>BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved)
>BIOS-e820: 0000000000100000 - 000000007ff70000 (usable)
>BIOS-e820: 000000007ff70000 - 000000007ff7b000 (ACPI data)
>BIOS-e820: 000000007ff7b000 - 000000007ff80000 (ACPI NVS)
>BIOS-e820: 000000007ff80000 - 0000000080000000 (reserved)
>BIOS-e820: 00000000fec00000 - 00000000fec10000 (reserved)
>BIOS-e820: 00000000fee00000 - 00000000fee01000 (reserved)
>BIOS-e820: 00000000ff800000 - 00000000ffc00000 (reserved)
>BIOS-e820: 00000000fff00000 - 0000000100000000 (reserved)

Not a problem. All "usable" memory is cacheable, which
is what matters for performance. You did lose some RAM
in the e820 map, but that's a relatively minor issue.
-
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/