[PATCH v4 04/34] pgtable: Create struct ptdesc

[Mike Rapoport]

On Mon, Jun 12, 2023 at 02:03:53PM -0700, Vishal Moola (Oracle) wrote:
> Currently, page table information is stored within struct page. As part
> of simplifying struct page, create struct ptdesc for page table
> information.
> 
> Signed-off-by: Vishal Moola (Oracle) <vishal.moola at gmail.com>

Acked-by: Mike Rapoport (IBM) <rppt at kernel.org>

> ---
>  include/linux/pgtable.h | 51 +++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 51 insertions(+)
> 
> diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
> index c5a51481bbb9..330de96ebfd6 100644
> --- a/include/linux/pgtable.h
> +++ b/include/linux/pgtable.h
> @@ -975,6 +975,57 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
>  #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
>  #endif /* CONFIG_MMU */
>  
> +
> +/**
> + * struct ptdesc - Memory descriptor for page tables.
> + * @__page_flags: Same as page flags. Unused for page tables.
> + * @pt_list: List of used page tables. Used for s390 and x86.
> + * @_pt_pad_1: Padding that aliases with page's compound head.
> + * @pmd_huge_pte: Protected by ptdesc->ptl, used for THPs.
> + * @_pt_s390_gaddr: Aliases with page's mapping. Used for s390 gmap only.
> + * @pt_mm: Used for x86 pgds.
> + * @pt_frag_refcount: For fragmented page table tracking. Powerpc and s390 only.
> + * @ptl: Lock for the page table.

Do you mind aligning the descriptions by @pt_frag_refcount? I think it'll
be more readable.

> + *
> + * This struct overlays struct page for now. Do not modify without a good
> + * understanding of the issues.
> + */
> +struct ptdesc {
> +	unsigned long __page_flags;
> +
> +	union {
> +		struct list_head pt_list;
> +		struct {
> +			unsigned long _pt_pad_1;
> +			pgtable_t pmd_huge_pte;
> +		};
> +	};
> +	unsigned long _pt_s390_gaddr;
> +
> +	union {
> +		struct mm_struct *pt_mm;
> +		atomic_t pt_frag_refcount;
> +	};
> +
> +#if ALLOC_SPLIT_PTLOCKS
> +	spinlock_t *ptl;
> +#else
> +	spinlock_t ptl;
> +#endif
> +};
> +
> +#define TABLE_MATCH(pg, pt)						\
> +	static_assert(offsetof(struct page, pg) == offsetof(struct ptdesc, pt))
> +TABLE_MATCH(flags, __page_flags);
> +TABLE_MATCH(compound_head, pt_list);
> +TABLE_MATCH(compound_head, _pt_pad_1);
> +TABLE_MATCH(pmd_huge_pte, pmd_huge_pte);
> +TABLE_MATCH(mapping, _pt_s390_gaddr);
> +TABLE_MATCH(pt_mm, pt_mm);
> +TABLE_MATCH(ptl, ptl);
> +#undef TABLE_MATCH
> +static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
> +
>  /*
>   * No-op macros that just return the current protection value. Defined here
>   * because these macros can be used even if CONFIG_MMU is not defined.
> -- 
> 2.40.1
> 
> 

-- 
Sincerely yours,
Mike.