mm: sanitize page->mapping for tail pages

We don't define meaning of page->mapping for tail pages.  Currently it's
always NULL, which can be inconsistent with head page and potentially
lead to problems.

Let's poison the pointer to catch all illigal uses.

page_rmapping(), page_mapping() and page_anon_vma() are changed to look
on head page.

The only illegal use I've caught so far is __GPF_COMP pages from sound
subsystem, mapped with PTEs.  do_shared_fault() is changed to use
page_rmapping() instead of direct access to fault_page->mapping.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 14 insertions, 6 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f952f05..370d44a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1805,7 +1805,7 @@ static void __split_huge_page_refcount(struct page *page,
 		*/
 		page_tail->_mapcount = page->_mapcount;
 
-		BUG_ON(page_tail->mapping);
+		BUG_ON(page_tail->mapping != TAIL_MAPPING);
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
diff --git a/mm/memory.c b/mm/memory.c
index d4e4d37..f9360dd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3096,7 +3096,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
 	 * release semantics to prevent the compiler from undoing this copying.
 	 */
-	mapping = fault_page->mapping;
+	mapping = page_rmapping(fault_page);
 	unlock_page(fault_page);
 	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
 		/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ce63d60..d02d643 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -466,6 +466,7 @@ void prep_compound_page(struct page *page, unsigned int order)
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
 		set_page_count(p, 0);
+		p->mapping = TAIL_MAPPING;
 		set_compound_head(p, page);
 	}
 }
@@ -856,6 +857,10 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
 		ret = 0;
 		goto out;
 	}
+	if (page->mapping != TAIL_MAPPING) {
+		bad_page(page, "corrupted mapping in tail page", 0);
+		goto out;
+	}
 	if (unlikely(!PageTail(page))) {
 		bad_page(page, "PageTail not set", 0);
 		goto out;
@@ -866,6 +871,7 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
 	}
 	ret = 0;
 out:
+	page->mapping = NULL;
 	clear_compound_head(page);
 	return ret;
 }
diff --git a/mm/util.c b/mm/util.c
index 2d28f79..8acb936 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -386,7 +386,9 @@ struct anon_vma *page_anon_vma(struct page *page)
 
 struct address_space *page_mapping(struct page *page)
 {
-	unsigned long mapping;
+	struct address_space *mapping;
+
+	page = compound_head(page);
 
 	/* This happens if someone calls flush_dcache_page on slab page */
 	if (unlikely(PageSlab(page)))
@@ -399,10 +401,10 @@ struct address_space *page_mapping(struct page *page)
 		return swap_address_space(entry);
 	}
 
-	mapping = (unsigned long)page->mapping;
-	if (mapping & PAGE_MAPPING_FLAGS)
+	mapping = page->mapping;
+	if ((unsigned long)mapping & PAGE_MAPPING_FLAGS)
 		return NULL;
-	return page->mapping;
+	return mapping;
 }
 
 int overcommit_ratio_handler(struct ctl_table *table, int write,