Re: [PATCH mm-new v3 1/1] mm/khugepaged: abort collapse scan on non-swap entries

[Lorenzo Stoakes <lorenzo.stoakes@oracle.com>]

On Wed, Oct 08, 2025 at 11:26:57AM +0800, Lance Yang wrote:
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index abe54f0043c7..bec3e268dc76 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -1020,6 +1020,11 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm,
>  		if (!is_swap_pte(vmf.orig_pte))
>  			continue;
>
> +		if (non_swap_entry(pte_to_swp_entry(vmf.orig_pte))) {
> +			result = SCAN_PTE_NON_PRESENT;
> +			goto out;
> +		}

OK seems in line with what we were discussing before...

> +
>  		vmf.pte = pte;
>  		vmf.ptl = ptl;
>  		ret = do_swap_page(&vmf);
> @@ -1281,7 +1286,23 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
>  	for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
>  	     _pte++, addr += PAGE_SIZE) {
>  		pte_t pteval = ptep_get(_pte);
> -		if (is_swap_pte(pteval)) {
> +		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
> +			++none_or_zero;
> +			if (!userfaultfd_armed(vma) &&
> +			    (!cc->is_khugepaged ||
> +			     none_or_zero <= khugepaged_max_ptes_none)) {
> +				continue;
> +			} else {
> +				result = SCAN_EXCEED_NONE_PTE;
> +				count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
> +				goto out_unmap;
> +			}
> +		} else if (!pte_present(pteval)) {
> +			if (non_swap_entry(pte_to_swp_entry(pteval))) {

Hm but can't this be pte_protnone() at this stage (or something else)? And then
we're just assuming pte_to_swp_entry() is operating on a swap entry when it in
fact might not be?

Couldn't we end up with false positives here?

> +				result = SCAN_PTE_NON_PRESENT;
> +				goto out_unmap;
> +			}
> +
>  			++unmapped;
>  			if (!cc->is_khugepaged ||
>  			    unmapped <= khugepaged_max_ptes_swap) {
> @@ -1290,7 +1311,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
>  				 * enabled swap entries.  Please see
>  				 * comment below for pte_uffd_wp().
>  				 */
> -				if (pte_swp_uffd_wp_any(pteval)) {
> +				if (pte_swp_uffd_wp(pteval)) {

Again you're assuming it's a swap entry but you're not asserting this is a swap
entry in this branch?

Also an aside - I hate, hate, hate how this uffd wp stuff has infiltrated all
kinds of open-coded stuff. It's so gross (not your fault, just a general
comment...)

>  					result = SCAN_PTE_UFFD_WP;
>  					goto out_unmap;
>  				}
> @@ -1301,18 +1322,6 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
>  				goto out_unmap;
>  			}
>  		}
> -		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
> -			++none_or_zero;
> -			if (!userfaultfd_armed(vma) &&
> -			    (!cc->is_khugepaged ||
> -			     none_or_zero <= khugepaged_max_ptes_none)) {
> -				continue;
> -			} else {
> -				result = SCAN_EXCEED_NONE_PTE;
> -				count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
> -				goto out_unmap;
> -			}
> -		}
>  		if (pte_uffd_wp(pteval)) {
>  			/*
>  			 * Don't collapse the page if any of the small
> --
> 2.49.0
>

Cheers, Lorenzo