From: "Vishal Moola (Oracle)" vishal.moola@gmail.com
mainline inclusion from mainline-6.7-rc1 commit 98b32d296d95d7aa0516c36b72406277412268cd category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9CESE CVE: NA
-------------------------------------------------
This removes 2 calls to compound_head() and helps convert khugepaged to use folios throughout.
Previously, if the address passed to collapse_pte_mapped_thp() corresponded to a tail page, the scan would fail immediately. Using filemap_lock_folio() we get the corresponding folio back and try to operate on the folio instead.
Link: https://lkml.kernel.org/r/20231020183331.10770-6-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) vishal.moola@gmail.com Reviewed-by: Rik van Riel riel@surriel.com Reviewed-by: Yang Shi shy828301@gmail.com Cc: Kefeng Wang wangkefeng.wang@huawei.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit 98b32d296d95d7aa0516c36b72406277412268cd) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- mm/khugepaged.c | 45 ++++++++++++++++++++------------------------- 1 file changed, 20 insertions(+), 25 deletions(-)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c index c60baa5fcb8a..37ff3679043c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1500,7 +1500,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = vma_lookup(mm, haddr); - struct page *hpage; + struct folio *folio; pte_t *start_pte, *pte; pmd_t *pmd, pgt_pmd; spinlock_t *pml = NULL, *ptl; @@ -1534,19 +1534,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP;
- hpage = find_lock_page(vma->vm_file->f_mapping, + folio = filemap_lock_folio(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); - if (!hpage) + if (IS_ERR(folio)) return SCAN_PAGE_NULL;
- if (!PageHead(hpage)) { - result = SCAN_FAIL; - goto drop_hpage; - } - - if (compound_order(hpage) != HPAGE_PMD_ORDER) { + if (folio_order(folio) != HPAGE_PMD_ORDER) { result = SCAN_PAGE_COMPOUND; - goto drop_hpage; + goto drop_folio; }
result = find_pmd_or_thp_or_none(mm, haddr, &pmd); @@ -1560,13 +1555,13 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, */ goto maybe_install_pmd; default: - goto drop_hpage; + goto drop_folio; }
result = SCAN_FAIL; start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ - goto drop_hpage; + goto drop_folio;
/* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; @@ -1591,7 +1586,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ - if (hpage + i != page) + if (folio_page(folio, i) != page) goto abort; }
@@ -1606,7 +1601,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * page_table_lock) ptl nests inside pml. The less time we hold pml, * the better; but userfaultfd's mfill_atomic_pte() on a private VMA * inserts a valid as-if-COWed PTE without even looking up page cache. - * So page lock of hpage does not protect from it, so we must not drop + * So page lock of folio does not protect from it, so we must not drop * ptl before pgt_pmd is removed, so uffd private needs pml taken now. */ if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) @@ -1630,7 +1625,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, continue; /* * We dropped ptl after the first scan, to do the mmu_notifier: - * page lock stops more PTEs of the hpage being faulted in, but + * page lock stops more PTEs of the folio being faulted in, but * does not stop write faults COWing anon copies from existing * PTEs; and does not stop those being swapped out or migrated. */ @@ -1639,7 +1634,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, goto abort; } page = vm_normal_page(vma, addr, ptent); - if (hpage + i != page) + if (folio_page(folio, i) != page) goto abort;
/* @@ -1659,8 +1654,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
/* step 3: set proper refcount and mm_counters. */ if (nr_ptes) { - page_ref_sub(hpage, nr_ptes); - add_mm_counter(mm, mm_counter_file(hpage), -nr_ptes); + folio_ref_sub(folio, nr_ptes); + add_mm_counter(mm, mm_counter_file(&folio->page), -nr_ptes); }
/* step 4: remove empty page table */ @@ -1684,14 +1679,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd - ? set_huge_pmd(vma, haddr, pmd, hpage) + ? set_huge_pmd(vma, haddr, pmd, &folio->page) : SCAN_SUCCEED; - goto drop_hpage; + goto drop_folio; abort: if (nr_ptes) { flush_tlb_mm(mm); - page_ref_sub(hpage, nr_ptes); - add_mm_counter(mm, mm_counter_file(hpage), -nr_ptes); + folio_ref_sub(folio, nr_ptes); + add_mm_counter(mm, mm_counter_file(&folio->page), -nr_ptes); } if (start_pte) pte_unmap_unlock(start_pte, ptl); @@ -1699,9 +1694,9 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, spin_unlock(pml); if (notified) mmu_notifier_invalidate_range_end(&range); -drop_hpage: - unlock_page(hpage); - put_page(hpage); +drop_folio: + folio_unlock(folio); + folio_put(folio); return result; }