In collapse_pte_mapped_thp(), we may modify the pte and pmd entry after
acquring the ptl, so convert it to using pte_offset_map_rw_nolock(). At
this time, the pte_same() check is not performed after the PTL held. So we
should get pgt_pmd and do pmd_same() check after the ptl held.

Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
 mm/khugepaged.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 6498721d4783a..854577f39957d 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1605,7 +1605,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED))
 		pml = pmd_lock(mm, pmd);
 
-	start_pte = pte_offset_map_nolock(mm, pmd, haddr, &ptl);
+	start_pte = pte_offset_map_rw_nolock(mm, pmd, haddr, &pgt_pmd, &ptl);
 	if (!start_pte)		/* mmap_lock + page lock should prevent this */
 		goto abort;
 	if (!pml)
@@ -1613,6 +1613,9 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	else if (ptl != pml)
 		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 
+	if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd))))
+		goto abort;
+
 	/* step 2: clear page table and adjust rmap */
 	for (i = 0, addr = haddr, pte = start_pte;
 	     i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) {
@@ -1645,7 +1648,6 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 		nr_ptes++;
 	}
 
-	pte_unmap(start_pte);
 	if (!pml)
 		spin_unlock(ptl);
 
@@ -1658,14 +1660,19 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	/* step 4: remove empty page table */
 	if (!pml) {
 		pml = pmd_lock(mm, pmd);
-		if (ptl != pml)
+		if (ptl != pml) {
 			spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
+			if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) {
+				flush_tlb_mm(mm);
+				goto unlock;
+			}
+		}
 	}
 	pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd);
 	pmdp_get_lockless_sync();
+	pte_unmap_unlock(start_pte, ptl);
 	if (ptl != pml)
-		spin_unlock(ptl);
-	spin_unlock(pml);
+		spin_unlock(pml);
 
 	mmu_notifier_invalidate_range_end(&range);
 
@@ -1685,6 +1692,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 		folio_ref_sub(folio, nr_ptes);
 		add_mm_counter(mm, mm_counter_file(folio), -nr_ptes);
 	}
+unlock:
 	if (start_pte)
 		pte_unmap_unlock(start_pte, ptl);
 	if (pml && pml != ptl)
-- 
2.20.1

> On Sep 26, 2024, at 14:46, Qi Zheng <zhengqi.arch@bytedance.com> wrote:
> 
> In collapse_pte_mapped_thp(), we may modify the pte and pmd entry after
> acquring the ptl, so convert it to using pte_offset_map_rw_nolock(). At
> this time, the pte_same() check is not performed after the PTL held. So we
> should get pgt_pmd and do pmd_same() check after the ptl held.
> 
> Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>

Reviewed-by: Muchun Song <muchun.song@linux.dev>

Thanks.