thp, mlock: do not mlock PTE-mapped file huge pages

As with anon THP, we only mlock file huge pages if we can prove that the
page is not mapped with PTE.  This way we can avoid mlock leak into
non-mlocked vma on split.

We rely on PageDoubleMap() under lock_page() to check if the the page
may be PTE mapped.  PG_double_map is set by page_add_file_rmap() when
the page mapped with PTEs.

Link: http://lkml.kernel.org/r/1466021202-61880-21-git-send-email-kirill.shutemov@linux.intel.comSigned-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/page-flags.h

@@ -581,6 +581,17 @@ static inline int PageDoubleMap(struct page *page)
 	return PageHead(page) && test_bit(PG_double_map, &page[1].flags);
 }
 
+static inline void SetPageDoubleMap(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageHead(page), page);
+	set_bit(PG_double_map, &page[1].flags);
+}
+
+static inline void ClearPageDoubleMap(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageHead(page), page);
+	clear_bit(PG_double_map, &page[1].flags);
+}
 static inline int TestSetPageDoubleMap(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHead(page), page);
@@ -598,7 +609,7 @@ TESTPAGEFLAG_FALSE(TransHuge)
 TESTPAGEFLAG_FALSE(TransCompound)
 TESTPAGEFLAG_FALSE(TransCompoundMap)
 TESTPAGEFLAG_FALSE(TransTail)
-TESTPAGEFLAG_FALSE(DoubleMap)
+PAGEFLAG_FALSE(DoubleMap)
 	TESTSETFLAG_FALSE(DoubleMap)
 	TESTCLEARFLAG_FALSE(DoubleMap)
 #endif

mm/huge_memory.c

@@ -1437,6 +1437,8 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 		 * We don't mlock() pte-mapped THPs. This way we can avoid
 		 * leaking mlocked pages into non-VM_LOCKED VMAs.
 		 *
+		 * For anon THP:
+		 *
 		 * In most cases the pmd is the only mapping of the page as we
 		 * break COW for the mlock() -- see gup_flags |= FOLL_WRITE for
 		 * writable private mappings in populate_vma_page_range().
@@ -1444,15 +1446,26 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 		 * The only scenario when we have the page shared here is if we
 		 * mlocking read-only mapping shared over fork(). We skip
 		 * mlocking such pages.
+		 *
+		 * For file THP:
+		 *
+		 * We can expect PageDoubleMap() to be stable under page lock:
+		 * for file pages we set it in page_add_file_rmap(), which
+		 * requires page to be locked.
 		 */
-		if (compound_mapcount(page) == 1 && !PageDoubleMap(page) &&
-				page->mapping && trylock_page(page)) {
+
+		if (PageAnon(page) && compound_mapcount(page) != 1)
+			goto skip_mlock;
+		if (PageDoubleMap(page) || !page->mapping)
+			goto skip_mlock;
+		if (!trylock_page(page))
+			goto skip_mlock;
 		lru_add_drain();
-			if (page->mapping)
+		if (page->mapping && !PageDoubleMap(page))
 			mlock_vma_page(page);
 		unlock_page(page);
 	}
-	}
+skip_mlock:
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 	if (flags & FOLL_GET)

mm/mmap.c

@@ -2591,6 +2591,12 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 		/* drop PG_Mlocked flag for over-mapped range */
 		for (tmp = vma; tmp->vm_start >= start + size;
 				tmp = tmp->vm_next) {
+			/*
+			 * Split pmd and munlock page on the border
+			 * of the range.
+			 */
+			vma_adjust_trans_huge(tmp, start, start + size, 0);
+
 			munlock_vma_pages_range(tmp,
 					max(tmp->vm_start, start),
 					min(tmp->vm_end, start + size));

mm/page_alloc.c

@@ -1007,6 +1007,8 @@ static __always_inline bool free_pages_prepare(struct page *page,
 
 		VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);
 
+		if (compound)
+			ClearPageDoubleMap(page);
 		for (i = 1; i < (1 << order); i++) {
 			if (compound)
 				bad += free_tail_pages_check(page, page + i);

mm/rmap.c

@@ -1284,6 +1284,12 @@ void page_add_file_rmap(struct page *page, bool compound)
 		if (!atomic_inc_and_test(compound_mapcount_ptr(page)))
 			goto out;
 	} else {
+		if (PageTransCompound(page)) {
+			VM_BUG_ON_PAGE(!PageLocked(page), page);
+			SetPageDoubleMap(compound_head(page));
+			if (PageMlocked(page))
+				clear_page_mlock(compound_head(page));
+		}
 		if (!atomic_inc_and_test(&page->_mapcount))
 			goto out;
 	}
@@ -1458,8 +1464,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	 */
 	if (!(flags & TTU_IGNORE_MLOCK)) {
 		if (vma->vm_flags & VM_LOCKED) {
-			/* Holding pte lock, we do *not* need mmap_sem here */
+			/* PTE-mapped THP are never mlocked */
+			if (!PageTransCompound(page)) {
+				/*
+				 * Holding pte lock, we do *not* need
+				 * mmap_sem here
+				 */
 				mlock_vma_page(page);
+			}
 			ret = SWAP_MLOCK;
 			goto out_unmap;
 		}