Re: [PATCH v4 01/11] mm: x86: move _PAGE_SWP_SOFT_DIRTY from bit 7 to bit 1

From: Tim Chen
Date: Fri Mar 24 2017 - 14:24:59 EST


On Mon, 2017-03-13 at 11:44 -0400, Zi Yan wrote:
> From: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
>
> pmd_present() checks _PAGE_PSE along with _PAGE_PRESENT to avoid
> false negative return when it races with thp spilt
> (during which _PAGE_PRESENT is temporary cleared.) I don't think that
> dropping _PAGE_PSE check in pmd_present() works well because it can
> hurt optimization of tlb handling in thp split.
> In the current kernel, bits 1-4 are not used in non-present format
> since commit 00839ee3b299 ("x86/mm: Move swap offset/type up in PTE to
> work around erratum"). So let's move _PAGE_SWP_SOFT_DIRTY to bit 1.
> Bit 7 is used as reserved (always clear), so please don't use it for
> other purpose.
>
> Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
> Signed-off-by: Zi Yan <zi.yan@xxxxxxxxxxxxxx>
> ---
> Âarch/x86/include/asm/pgtable_64.hÂÂÂÂ| 12 +++++++++---
> Âarch/x86/include/asm/pgtable_types.h | 10 +++++-----
> Â2 files changed, 14 insertions(+), 8 deletions(-)
>
> diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
> index 73c7ccc38912..a5c4fc62e078 100644
> --- a/arch/x86/include/asm/pgtable_64.h
> +++ b/arch/x86/include/asm/pgtable_64.h
> @@ -157,15 +157,21 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
> Â/*
> Â * Encode and de-code a swap entry
> Â *
> - * |ÂÂÂÂÂ...ÂÂÂÂÂÂÂÂÂÂÂÂ| 11| 10|ÂÂ9|8|7|6|5| 4| 3|2|1|0| <- bit number
> - * |ÂÂÂÂÂ...ÂÂÂÂÂÂÂÂÂÂÂÂ|SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names
> - * | OFFSET (14->63) | TYPE (9-13)ÂÂ|0|X|X|X| X| X|X|X|0| <- swp entry
> + * |ÂÂÂÂÂ...ÂÂÂÂÂÂÂÂÂÂÂÂ| 11| 10|ÂÂ9|8|7|6|5| 4| 3|2| 1|0| <- bit number
> + * |ÂÂÂÂÂ...ÂÂÂÂÂÂÂÂÂÂÂÂ|SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
> + * | OFFSET (14->63) | TYPE (9-13)ÂÂ|0|0|X|X| X| X|X|SD|0| <- swp entry
> Â *
> Â * G (8) is aliased and used as a PROT_NONE indicator for
> Â * !present ptes.ÂÂWe need to start storing swap entries above
> Â * there.ÂÂWe also need to avoid using A and D because of an
> Â * erratum where they can be incorrectly set by hardware on
> Â * non-present PTEs.
> + *
> + * SD (1) in swp entry is used to store soft dirty bit, which helps us
> + * remember soft dirty over page migration
> + *
> + * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
> + * but also G.

but also L and G.