Re: [PATCH v1 15/39] mm/huge_memory: batch rmap operations in __split_huge_pmd_locked()

[Ryan Roberts <ryan.roberts@arm.com>]

On 11/12/2023 15:56, David Hildenbrand wrote:
> Let's use folio_add_anon_rmap_ptes(), batching the rmap operations.
> 
> While at it, use more folio operations (but only in the code branch we're
> touching), use VM_WARN_ON_FOLIO(), and pass RMAP_EXCLUSIVE instead of
> manually setting PageAnonExclusive.
> 
> We should never see non-anon pages on that branch: otherwise, the
> existing page_add_anon_rmap() call would have been flawed already.
> 
> Signed-off-by: David Hildenbrand <david@redhat.com>
> ---
>  mm/huge_memory.c | 23 +++++++++++++++--------
>  1 file changed, 15 insertions(+), 8 deletions(-)
> 
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 1f5634b2f374..82ad68fe0d12 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2398,6 +2398,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
>  		unsigned long haddr, bool freeze)
>  {
>  	struct mm_struct *mm = vma->vm_mm;
> +	struct folio *folio;
>  	struct page *page;
>  	pgtable_t pgtable;
>  	pmd_t old_pmd, _pmd;
> @@ -2493,16 +2494,18 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
>  		uffd_wp = pmd_swp_uffd_wp(old_pmd);
>  	} else {
>  		page = pmd_page(old_pmd);
> +		folio = page_folio(page);
>  		if (pmd_dirty(old_pmd)) {
>  			dirty = true;
> -			SetPageDirty(page);
> +			folio_set_dirty(folio);
>  		}
>  		write = pmd_write(old_pmd);
>  		young = pmd_young(old_pmd);
>  		soft_dirty = pmd_soft_dirty(old_pmd);
>  		uffd_wp = pmd_uffd_wp(old_pmd);
>  
> -		VM_BUG_ON_PAGE(!page_count(page), page);
> +		VM_WARN_ON_FOLIO(!folio_ref_count(folio), folio);
> +		VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);

Is this warning really correct? file-backed memory can be PMD-mapped with
CONFIG_READ_ONLY_THP_FOR_FS, so presumably it can also have the need to be
remapped as pte? Although I guess if we did have a file-backed folio, it
definitely wouldn't be correct to call page_add_anon_rmap() /
folio_add_anon_rmap_ptes()...

>  
>  		/*
>  		 * Without "freeze", we'll simply split the PMD, propagating the
> @@ -2519,11 +2522,18 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
>  		 *
>  		 * See page_try_share_anon_rmap(): invalidate PMD first.
>  		 */
> -		anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
> +		anon_exclusive = PageAnonExclusive(page);
>  		if (freeze && anon_exclusive && page_try_share_anon_rmap(page))
>  			freeze = false;
> -		if (!freeze)
> -			page_ref_add(page, HPAGE_PMD_NR - 1);
> +		if (!freeze) {
> +			rmap_t rmap_flags = RMAP_NONE;
> +
> +			folio_ref_add(folio, HPAGE_PMD_NR - 1);
> +			if (anon_exclusive)
> +				rmap_flags |= RMAP_EXCLUSIVE;
> +			folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR,
> +						 vma, haddr, rmap_flags);
> +		}
>  	}
>  
>  	/*
> @@ -2566,8 +2576,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
>  			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
>  			if (write)
>  				entry = pte_mkwrite(entry, vma);
> -			if (anon_exclusive)
> -				SetPageAnonExclusive(page + i);
>  			if (!young)
>  				entry = pte_mkold(entry);
>  			/* NOTE: this may set soft-dirty too on some archs */
> @@ -2577,7 +2585,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
>  				entry = pte_mksoft_dirty(entry);
>  			if (uffd_wp)
>  				entry = pte_mkuffd_wp(entry);
> -			page_add_anon_rmap(page + i, vma, addr, RMAP_NONE);
>  		}
>  		VM_BUG_ON(!pte_none(ptep_get(pte)));
>  		set_pte_at(mm, addr, pte, entry);