From e71335bfdcb68b91921f3b1ee04dc5816568f78b Mon Sep 17 00:00:00 2001 From: Lance Yang Date: Wed, 1 Oct 2025 11:22:51 +0800 Subject: [PATCH] mm/khugepaged: abort collapse scan on non-swap entries MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Currently, special non-swap entries (like migration, hwpoison, or PTE markers) are not caught early in hpage_collapse_scan_pmd(), leading to failures deep in the swap-in logic. hpage_collapse_scan_pmd() `- collapse_huge_page() `- __collapse_huge_page_swapin() -> fails! As David suggested[1], this patch skips any such non-swap entries early. If any one is found, the scan is aborted immediately with the SCAN_PTE_NON_PRESENT result, as Lorenzo suggested[2], avoiding wasted work. Link: https://lkml.kernel.org/r/20251001032251.85888-1-lance.yang@linux.dev Link: https://lore.kernel.org/linux-mm/7840f68e-7580-42cb-a7c8-1ba64fd6df69@redhat.com [1] Link: https://lore.kernel.org/linux-mm/7df49fe7-c6b7-426a-8680-dcd55219c8bd@lucifer.local [2] Signed-off-by: Lance Yang Suggested-by: David Hildenbrand Suggested-by: Lorenzo Stoakes Acked-by: David Hildenbrand Reviewed-by: Wei Yang Reviewed-by: Dev Jain Cc: Baolin Wang Cc: Barry Song Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Liam Howlett Cc: Mariano Pache Cc: Mika Penttilä Cc: Ryan Roberts Cc: Zi Yan Signed-off-by: Andrew Morton --- mm/khugepaged.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index abe54f0043c7..f4f57ba69d72 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1281,7 +1281,23 @@ 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))) { + result = SCAN_PTE_NON_PRESENT; + goto out_unmap; + } + ++unmapped; if (!cc->is_khugepaged || unmapped <= khugepaged_max_ptes_swap) { @@ -1290,7 +1306,7 @@ 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)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } @@ -1301,18 +1317,6 @@ 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 -- 2.51.0