Re: [PATCH] x86: mtrr cleanup for converting continuous to discrete - auto detect v2

From: Yinghai Lu
Date: Thu May 01 2008 - 19:11:33 EST


On Thu, May 1, 2008 at 3:57 PM, H. Peter Anvin <hpa@xxxxxxxxx> wrote:
> Yinghai Lu wrote:
>
> >
> > only search 78
> > 2g, 1g, ...1m, and half matrix 13 * 6..
> >
> > and don't need to search than 78.
> >
> >
>
> Again, it's not clear to me why there is an inherent limit at 2 GB.

above 2g, we will use 4g (chunk size, because if use 4g gran_size will
trim too much RAM). it will get the continous layout like
0-4g WB
3.5g-4G UC

instead of discrete that we want. (chunk_size=2g, gran_size=512M)
0-2g WB
2g-4g WB
3.5g-4g UC

YH
--
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/