[RFC PATCH 1/3] arm64/hugetlb: Introduce new huge_ptep_get_access_flags() interface

[nh26223 at qq.com]

On 2022年5月8日星期日 CST 下午4:58:52 Baolin Wang wrote:
> Now we use huge_ptep_get() to get the pte value of a hugetlb page,
> however it will only return one specific pte value for the CONT-PTE
> or CONT-PMD size hugetlb on ARM64 system, which can contain seravel
> continuous pte or pmd entries with same page table attributes. And it
> will not take into account the subpages' dirty or young bits of a
> CONT-PTE/PMD size hugetlb page.
> 
> So the huge_ptep_get() is inconsistent with huge_ptep_get_and_clear(),
> which already takes account the dirty or young bits for any subpages
> in this CONT-PTE/PMD size hugetlb [1]. Meanwhile we can miss dirty or
> young flags statistics for hugetlb pages with current huge_ptep_get(),
> such as the gather_hugetlb_stats() function.
> 
> Thus introduce a new huge_ptep_get_access_flags() interface and define
> an ARM64 specific implementation, that will take into account any subpages'
> dirty or young bits for CONT-PTE/PMD size hugetlb page, for those functions
> that want to check the dirty and young flags of a hugetlb page.
> 
> [1]
> https://lore.kernel.org/linux-mm/85bd80b4-b4fd-0d3f-a2e5-149559f2f387@oracl
> e.com/
> 
> Signed-off-by: Baolin Wang <baolin.wang at linux.alibaba.com>
> ---
>  arch/arm64/include/asm/hugetlb.h |  2 ++
>  arch/arm64/mm/hugetlbpage.c      | 24 ++++++++++++++++++++++++
>  include/asm-generic/hugetlb.h    |  7 +++++++
>  3 files changed, 33 insertions(+)
> 
> diff --git a/arch/arm64/include/asm/hugetlb.h
> b/arch/arm64/include/asm/hugetlb.h index 616b2ca..a473544 100644
> --- a/arch/arm64/include/asm/hugetlb.h
> +++ b/arch/arm64/include/asm/hugetlb.h
> @@ -44,6 +44,8 @@ extern pte_t huge_ptep_clear_flush(struct vm_area_struct
> *vma, #define __HAVE_ARCH_HUGE_PTE_CLEAR
>  extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
>  			   pte_t *ptep, unsigned long sz);
> +#define __HAVE_ARCH_HUGE_PTEP_GET_ACCESS_FLAGS
> +extern pte_t huge_ptep_get_access_flags(pte_t *ptep, unsigned long sz);
>  extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
>  				 pte_t *ptep, pte_t pte, unsigned long 
sz);
>  #define set_huge_swap_pte_at set_huge_swap_pte_at
> diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
> index ca8e65c..ce39699 100644
> --- a/arch/arm64/mm/hugetlbpage.c
> +++ b/arch/arm64/mm/hugetlbpage.c
> @@ -158,6 +158,30 @@ static inline int num_contig_ptes(unsigned long size,
> size_t *pgsize) return contig_ptes;
>  }
> 
> +pte_t huge_ptep_get_access_flags(pte_t *ptep, unsigned long sz)
The function name looks to me that it returns access flags of PTE.

> +{
> +	int ncontig, i;
> +	size_t pgsize;
> +	pte_t orig_pte = ptep_get(ptep);
> +
> +	if (!pte_cont(orig_pte))
> +		return orig_pte;
> +
> +	ncontig = num_contig_ptes(sz, &pgsize);
> +
> +	for (i = 0; i < ncontig; i++, ptep++) {
> +		pte_t pte = ptep_get(ptep);
> +
> +		if (pte_dirty(pte))
> +			orig_pte = pte_mkdirty(orig_pte);
> +
> +		if (pte_young(pte))
> +			orig_pte = pte_mkyoung(orig_pte);
> +	}
> +
> +	return orig_pte;
> +}
Not sure whether it's worthy being changed to:

        bool dirty = false, young = false;

        for (i = 0; i < ncontig; i++, ptep++) {
                pte_t pte = ptep_get(ptep);

                if (pte_dirty(pte))
                        dirty = true;

                if (pte_young(pte))
                        young = true;

                if (dirty && young)
                        break;
        }

        if (dirty)
                orig_pte = pte_mkdirty(orig_pte);

        if (young)
                orig_pte = pte_mkyoung(orit_pte);

        return orig_pte;

> +
>  /*
>   * Changing some bits of contiguous entries requires us to follow a
>   * Break-Before-Make approach, breaking the whole contiguous set
> diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
> index a57d667..bb77fb0 100644
> --- a/include/asm-generic/hugetlb.h
> +++ b/include/asm-generic/hugetlb.h
> @@ -150,6 +150,13 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
>  }
>  #endif
> 
> +#ifndef __HAVE_ARCH_HUGE_PTEP_GET_ACCESS_FLAGS
> +static inline pte_t huge_ptep_get_access_flags(pte_t *ptep, unsigned long
> sz) +{
> +	return ptep_get(ptep);
Should be:
	return huge_ptep_get(ptep) ?


Regards
Yin, Fengwei

> +}
> +#endif
> +
>  #ifndef __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
>  static inline bool gigantic_page_runtime_supported(void)
>  {