Re: [RFC PATCH 05/12] khugepaged: Generalize __collapse_huge_page_isolate()

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

On 16/12/2024 16:50, Dev Jain wrote:
> Scale down the scan range and the sysfs tunables according to the scan order,
> and isolate the folios.
> 
> Signed-off-by: Dev Jain <dev.jain@arm.com>
> ---
>  mm/khugepaged.c | 19 +++++++++++--------
>  1 file changed, 11 insertions(+), 8 deletions(-)
> 
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index f52dae7d5179..de044b1f83d4 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -564,15 +564,18 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
>  					unsigned long address,
>  					pte_t *pte,
>  					struct collapse_control *cc,
> -					struct list_head *compound_pagelist)
> +					struct list_head *compound_pagelist, int order)
>  {
> -	struct page *page = NULL;
> -	struct folio *folio = NULL;
> -	pte_t *_pte;
> +	unsigned int max_ptes_shared = khugepaged_max_ptes_shared >> (HPAGE_PMD_ORDER - order);
> +	unsigned int max_ptes_none = khugepaged_max_ptes_none >> (HPAGE_PMD_ORDER - order);

This is implicitly rounding down. I think that's the right thing to do; it's
better to be conservative.

>  	int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0;
> +	struct folio *folio = NULL;
> +	struct page *page = NULL;
>  	bool writable = false;
> +	pte_t *_pte;
>  
> -	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
> +
> +	for (_pte = pte; _pte < pte + (1UL << order);
>  	     _pte++, address += PAGE_SIZE) {
>  		pte_t pteval = ptep_get(_pte);
>  		if (pte_none(pteval) || (pte_present(pteval) &&
> @@ -580,7 +583,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
>  			++none_or_zero;
>  			if (!userfaultfd_armed(vma) &&
>  			    (!cc->is_khugepaged ||
> -			     none_or_zero <= khugepaged_max_ptes_none)) {
> +			     none_or_zero <= max_ptes_none)) {
>  				continue;
>  			} else {
>  				result = SCAN_EXCEED_NONE_PTE;
> @@ -609,7 +612,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
>  		if (folio_likely_mapped_shared(folio)) {
>  			++shared;
>  			if (cc->is_khugepaged &&
> -			    shared > khugepaged_max_ptes_shared) {
> +			    shared > max_ptes_shared) {
>  				result = SCAN_EXCEED_SHARED_PTE;
>  				count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
>  				goto out;
> @@ -1200,7 +1203,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
>  	pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl);
>  	if (pte) {
>  		result = __collapse_huge_page_isolate(vma, address, pte, cc,
> -						      &compound_pagelist);
> +						      &compound_pagelist, order);
>  		spin_unlock(pte_ptl);
>  	} else {
>  		result = SCAN_PMD_NULL;