1 files changed, 35 insertions, 40 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 700f5160f3e4..b52bd46ad146 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -431,7 +431,7 @@ static void insert_to_mm_slots_hash(struct mm_struct *mm,
 
 static inline int khugepaged_test_exit(struct mm_struct *mm)
 {
-	return atomic_read(&mm->mm_users) == 0;
+	return atomic_read(&mm->mm_users) == 0 || !mmget_still_valid(mm);
 }
 
 static bool hugepage_vma_check(struct vm_area_struct *vma,
@@ -1100,9 +1100,6 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * handled by the anon_vma lock + PG_lock.
 	 */
 	mmap_write_lock(mm);
-	result = SCAN_ANY_PROCESS;
-	if (!mmget_still_valid(mm))
-		goto out;
 	result = hugepage_vma_revalidate(mm, address, &vma);
 	if (result)
 		goto out;
@@ -1412,7 +1409,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 {
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
 	struct vm_area_struct *vma = find_vma(mm, haddr);
-	struct page *hpage = NULL;
+	struct page *hpage;
 	pte_t *start_pte, *pte;
 	pmd_t *pmd, _pmd;
 	spinlock_t *ptl;
@@ -1432,9 +1429,17 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 	if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE))
 		return;
 
+	hpage = find_lock_page(vma->vm_file->f_mapping,
+			       linear_page_index(vma, haddr));
+	if (!hpage)
+		return;
+
+	if (!PageHead(hpage))
+		goto drop_hpage;
+
 	pmd = mm_find_pmd(mm, haddr);
 	if (!pmd)
-		return;
+		goto drop_hpage;
 
 	start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
 
@@ -1453,30 +1458,11 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 
 		page = vm_normal_page(vma, addr, *pte);
 
-		if (!page || !PageCompound(page))
-			goto abort;
-
-		if (!hpage) {
-			hpage = compound_head(page);
-			/*
-			 * The mapping of the THP should not change.
-			 *
-			 * Note that uprobe, debugger, or MAP_PRIVATE may
-			 * change the page table, but the new page will
-			 * not pass PageCompound() check.
-			 */
-			if (WARN_ON(hpage->mapping != vma->vm_file->f_mapping))
-				goto abort;
-		}
-
 		/*
-		 * Confirm the page maps to the correct subpage.
-		 *
-		 * Note that uprobe, debugger, or MAP_PRIVATE may change
-		 * the page table, but the new page will not pass
-		 * PageCompound() check.
+		 * Note that uprobe, debugger, or MAP_PRIVATE may change the
+		 * page table, but the new page will not be a subpage of hpage.
 		 */
-		if (WARN_ON(hpage + i != page))
+		if (hpage + i != page)
 			goto abort;
 		count++;
 	}
@@ -1495,21 +1481,26 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 	pte_unmap_unlock(start_pte, ptl);
 
 	/* step 3: set proper refcount and mm_counters. */
-	if (hpage) {
+	if (count) {
 		page_ref_sub(hpage, count);
 		add_mm_counter(vma->vm_mm, mm_counter_file(hpage), -count);
 	}
 
 	/* step 4: collapse pmd */
 	ptl = pmd_lock(vma->vm_mm, pmd);
-	_pmd = pmdp_collapse_flush(vma, addr, pmd);
+	_pmd = pmdp_collapse_flush(vma, haddr, pmd);
 	spin_unlock(ptl);
 	mm_dec_nr_ptes(mm);
 	pte_free(mm, pmd_pgtable(_pmd));
+
+drop_hpage:
+	unlock_page(hpage);
+	put_page(hpage);
 	return;
 
 abort:
 	pte_unmap_unlock(start_pte, ptl);
+	goto drop_hpage;
 }
 
 static int khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot)
@@ -1538,6 +1529,7 @@ out:
 static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 {
 	struct vm_area_struct *vma;
+	struct mm_struct *mm;
 	unsigned long addr;
 	pmd_t *pmd, _pmd;
 
@@ -1566,7 +1558,8 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 			continue;
 		if (vma->vm_end < addr + HPAGE_PMD_SIZE)
 			continue;
-		pmd = mm_find_pmd(vma->vm_mm, addr);
+		mm = vma->vm_mm;
+		pmd = mm_find_pmd(mm, addr);
 		if (!pmd)
 			continue;
 		/*
@@ -1576,17 +1569,19 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		 * mmap_lock while holding page lock. Fault path does it in
 		 * reverse order. Trylock is a way to avoid deadlock.
 		 */
-		if (mmap_write_trylock(vma->vm_mm)) {
-			spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd);
-			/* assume page table is clear */
-			_pmd = pmdp_collapse_flush(vma, addr, pmd);
-			spin_unlock(ptl);
-			mmap_write_unlock(vma->vm_mm);
-			mm_dec_nr_ptes(vma->vm_mm);
-			pte_free(vma->vm_mm, pmd_pgtable(_pmd));
+		if (mmap_write_trylock(mm)) {
+			if (!khugepaged_test_exit(mm)) {
+				spinlock_t *ptl = pmd_lock(mm, pmd);
+				/* assume page table is clear */
+				_pmd = pmdp_collapse_flush(vma, addr, pmd);
+				spin_unlock(ptl);
+				mm_dec_nr_ptes(mm);
+				pte_free(mm, pmd_pgtable(_pmd));
+			}
+			mmap_write_unlock(mm);
 		} else {
 			/* Try again later */
-			khugepaged_add_pte_mapped_thp(vma->vm_mm, addr);
+			khugepaged_add_pte_mapped_thp(mm, addr);
 		}
 	}
 	i_mmap_unlock_write(mapping);