[PATCH 14/14] mm: khugepaged: retract_page_tables() use pte_offset_map_maywrite_nolock()

[Qi Zheng <zhengqi.arch@bytedance.com>]

In retract_page_tables(), we may modify the pmd entry after acquiring the
pml and ptl, so we should also check whether the pmd entry is stable.
Using pte_offset_map_maywrite_nolock() + pmd_same() to do it.

Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
 mm/khugepaged.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 8fcad0b368a08..821c840b5b593 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1721,6 +1721,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		spinlock_t *pml;
 		spinlock_t *ptl;
 		bool skipped_uffd = false;
+		pte_t *pte;
 
 		/*
 		 * Check vma->anon_vma to exclude MAP_PRIVATE mappings that
@@ -1756,11 +1757,25 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 					addr, addr + HPAGE_PMD_SIZE);
 		mmu_notifier_invalidate_range_start(&range);
 
+		pte = pte_offset_map_maywrite_nolock(mm, pmd, addr, &pgt_pmd, &ptl);
+		if (!pte) {
+			mmu_notifier_invalidate_range_end(&range);
+			continue;
+		}
+
 		pml = pmd_lock(mm, pmd);
-		ptl = pte_lockptr(mm, pmd);
 		if (ptl != pml)
 			spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 
+		if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) {
+			pte_unmap_unlock(pte, ptl);
+			if (ptl != pml)
+				spin_unlock(pml);
+			mmu_notifier_invalidate_range_end(&range);
+			continue;
+		}
+		pte_unmap(pte);
+
 		/*
 		 * Huge page lock is still held, so normally the page table
 		 * must remain empty; and we have already skipped anon_vma
-- 
2.20.1