Re: [RFC 07/11] khugepaged: generalize __collapse_huge_page_* for mTHP support

[Dev Jain <dev.jain@xxxxxxx>]

On 09/01/25 5:01 am, Nico Pache wrote:
> generalize the order of the __collapse_huge_page_* functions
> to support future mTHP collapse.
>
> No functional changes in this patch.
>
> Signed-off-by: Nico Pache <npache@xxxxxxxxxx>
> ---
>   mm/khugepaged.c | 36 +++++++++++++++++++-----------------
>   1 file changed, 19 insertions(+), 17 deletions(-)
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 6daf3a943a1a..9eb161b04ee4 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -565,7 +565,8 @@ 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,
> +					u8 order)
>   {
>   	struct page *page = NULL;
>   	struct folio *folio = NULL;
> @@ -573,7 +574,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
>   	int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0;
>   	bool writable = false;
>   
> -	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
> +	for (_pte = pte; _pte < pte + (1 << order);
>   	     _pte++, address += PAGE_SIZE) {
>   		pte_t pteval = ptep_get(_pte);
>   		if (pte_none(pteval) || (pte_present(pteval) &&
> @@ -711,14 +712,15 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte,
>   						struct vm_area_struct *vma,
>   						unsigned long address,
>   						spinlock_t *ptl,
> -						struct list_head *compound_pagelist)
> +						struct list_head *compound_pagelist,
> +						u8 order)
>   {
>   	struct folio *src, *tmp;
>   	pte_t *_pte;
>   	pte_t pteval;
>   
> -	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
> -	     _pte++, address += PAGE_SIZE) {
> +	for (_pte = pte; _pte < pte + (1 << order);
> +		_pte++, address += PAGE_SIZE) {
>   		pteval = ptep_get(_pte);
>   		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
>   			add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
> @@ -764,7 +766,8 @@ static void __collapse_huge_page_copy_failed(pte_t *pte,
>   					     pmd_t *pmd,
>   					     pmd_t orig_pmd,
>   					     struct vm_area_struct *vma,
> -					     struct list_head *compound_pagelist)
> +					     struct list_head *compound_pagelist,
> +					     u8 order)
>   {
>   	spinlock_t *pmd_ptl;
>   
> @@ -781,7 +784,7 @@ static void __collapse_huge_page_copy_failed(pte_t *pte,
>   	 * Release both raw and compound pages isolated
>   	 * in __collapse_huge_page_isolate.
>   	 */
> -	release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist);
> +	release_pte_pages(pte, pte + (1 << order), compound_pagelist);
>   }
>   
>   /*
> @@ -802,7 +805,7 @@ static void __collapse_huge_page_copy_failed(pte_t *pte,
>   static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio,
>   		pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma,
>   		unsigned long address, spinlock_t *ptl,
> -		struct list_head *compound_pagelist)
> +		struct list_head *compound_pagelist, u8 order)
>   {
>   	unsigned int i;
>   	int result = SCAN_SUCCEED;
> @@ -810,7 +813,7 @@ static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio,
>   	/*
>   	 * Copying pages' contents is subject to memory poison at any iteration.
>   	 */
> -	for (i = 0; i < HPAGE_PMD_NR; i++) {
> +	for (i = 0; i < (1 << order); i++) {
>   		pte_t pteval = ptep_get(pte + i);
>   		struct page *page = folio_page(folio, i);
>   		unsigned long src_addr = address + i * PAGE_SIZE;
> @@ -829,10 +832,10 @@ static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio,
>   
>   	if (likely(result == SCAN_SUCCEED))
>   		__collapse_huge_page_copy_succeeded(pte, vma, address, ptl,
> -						    compound_pagelist);
> +						    compound_pagelist, order);
>   	else
>   		__collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma,
> -						 compound_pagelist);
> +						 compound_pagelist, order);
>   
>   	return result;
>   }
> @@ -996,11 +999,11 @@ static int check_pmd_still_valid(struct mm_struct *mm,
>   static int __collapse_huge_page_swapin(struct mm_struct *mm,
>   				       struct vm_area_struct *vma,
>   				       unsigned long haddr, pmd_t *pmd,
> -				       int referenced)
> +				       int referenced, u8 order)
>   {

I had dropped 'h' from haddr because the address won't be huge-aligned
after mTHP support.

>   	int swapped_in = 0;
>   	vm_fault_t ret = 0;
> -	unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE);
> +	unsigned long address, end = haddr + ((1 << order) * PAGE_SIZE);

Better to write PAGE_SIZE << order, as Matthew had noted in my patch :)