1 files changed, 55 insertions, 10 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index b874c4761e84..47db27f8049e 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -899,7 +899,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 	mmu_notifier_invalidate_range_start(vma->vm_mm, start, end);
 
 	while (page_vma_mapped_walk(&pvmw)) {
-		unsigned long cstart, cend;
+		unsigned long cstart;
 		int ret = 0;
 
 		cstart = address = pvmw.address;
@@ -915,7 +915,6 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 			entry = pte_wrprotect(entry);
 			entry = pte_mkclean(entry);
 			set_pte_at(vma->vm_mm, address, pte, entry);
-			cend = cstart + PAGE_SIZE;
 			ret = 1;
 		} else {
 #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
@@ -931,7 +930,6 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 			entry = pmd_mkclean(entry);
 			set_pmd_at(vma->vm_mm, address, pmd, entry);
 			cstart &= PMD_MASK;
-			cend = cstart + PMD_SIZE;
 			ret = 1;
 #else
 			/* unexpected pmd-mapped page? */
@@ -939,10 +937,15 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 #endif
 		}
 
-		if (ret) {
-			mmu_notifier_invalidate_range(vma->vm_mm, cstart, cend);
+		/*
+		 * No need to call mmu_notifier_invalidate_range() as we are
+		 * downgrading page table protection not changing it to point
+		 * to a new page.
+		 *
+		 * See Documentation/vm/mmu_notifier.txt
+		 */
+		if (ret)
 			(*cleaned)++;
-		}
 	}
 
 	mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
@@ -1318,7 +1321,7 @@ void page_remove_rmap(struct page *page, bool compound)
 	 * It would be tidy to reset the PageAnon mapping here,
 	 * but that might overwrite a racing page_add_anon_rmap
 	 * which increments mapcount after us but sets mapping
-	 * before us: so leave the reset to free_hot_cold_page,
+	 * before us: so leave the reset to free_unref_page,
 	 * and remember that it's only reliable while mapped.
 	 * Leaving it set also helps swapoff to reinstate ptes
 	 * faster for those pages still in swapcache.
@@ -1426,6 +1429,10 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
 			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
+			/*
+			 * No need to invalidate here it will synchronize on
+			 * against the special swap migration pte.
+			 */
 			goto discard;
 		}
 
@@ -1483,6 +1490,9 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * will take care of the rest.
 			 */
 			dec_mm_counter(mm, mm_counter(page));
+			/* We have to invalidate as we cleared the pte */
+			mmu_notifier_invalidate_range(mm, address,
+						      address + PAGE_SIZE);
 		} else if (IS_ENABLED(CONFIG_MIGRATION) &&
 				(flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) {
 			swp_entry_t entry;
@@ -1498,6 +1508,10 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
 			set_pte_at(mm, address, pvmw.pte, swp_pte);
+			/*
+			 * No need to invalidate here it will synchronize on
+			 * against the special swap migration pte.
+			 */
 		} else if (PageAnon(page)) {
 			swp_entry_t entry = { .val = page_private(subpage) };
 			pte_t swp_pte;
@@ -1509,6 +1523,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				WARN_ON_ONCE(1);
 				ret = false;
 				/* We have to invalidate as we cleared the pte */
+				mmu_notifier_invalidate_range(mm, address,
+							address + PAGE_SIZE);
 				page_vma_mapped_walk_done(&pvmw);
 				break;
 			}
@@ -1516,6 +1532,9 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			/* MADV_FREE page check */
 			if (!PageSwapBacked(page)) {
 				if (!PageDirty(page)) {
+					/* Invalidate as we cleared the pte */
+					mmu_notifier_invalidate_range(mm,
+						address, address + PAGE_SIZE);
 					dec_mm_counter(mm, MM_ANONPAGES);
 					goto discard;
 				}
@@ -1549,13 +1568,39 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
 			set_pte_at(mm, address, pvmw.pte, swp_pte);
-		} else
+			/* Invalidate as we cleared the pte */
+			mmu_notifier_invalidate_range(mm, address,
+						      address + PAGE_SIZE);
+		} else {
+			/*
+			 * We should not need to notify here as we reach this
+			 * case only from freeze_page() itself only call from
+			 * split_huge_page_to_list() so everything below must
+			 * be true:
+			 *   - page is not anonymous
+			 *   - page is locked
+			 *
+			 * So as it is a locked file back page thus it can not
+			 * be remove from the page cache and replace by a new
+			 * page before mmu_notifier_invalidate_range_end so no
+			 * concurrent thread might update its page table to
+			 * point at new page while a device still is using this
+			 * page.
+			 *
+			 * See Documentation/vm/mmu_notifier.txt
+			 */
 			dec_mm_counter(mm, mm_counter_file(page));
+		}
 discard:
+		/*
+		 * No need to call mmu_notifier_invalidate_range() it has be
+		 * done above for all cases requiring it to happen under page
+		 * table lock before mmu_notifier_invalidate_range_end()
+		 *
+		 * See Documentation/vm/mmu_notifier.txt
+		 */
 		page_remove_rmap(subpage, PageHuge(page));
 		put_page(page);
-		mmu_notifier_invalidate_range(mm, address,
-					      address + PAGE_SIZE);
 	}
 
 	mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);