Re: [PATCH] x86: mm: accurate the comments for STEP_SIZE_SHIFT macro
From: Yinghai Lu
Date: Mon Mar 18 2013 - 17:20:08 EST
On Mon, Mar 18, 2013 at 12:14 PM, H. Peter Anvin <hpa@xxxxxxxxx> wrote:
> Instead, try to explain why 5 is the correct value in the current code
> and how it is (or should be!) derived.
initial mapped size is PMD_SIZE, aka 2M.
if we use step_size to be PUD_SIZE aka 1G, as most worse case
that 1G is cross the 1G boundary, and PG_LEVEL_2M is not set,
we will need 1+1+512 pages (aka 2M + 8k) to map 1G range with PTE.
So i picked (30-21)/2 to get 5.
Please check attached patch.
Description: Binary data