[PATCH] Fix buddy list race that could lead to page lru list corruptions

Rohit found an obscure bug causing buddy list corruption.

page_is_buddy is using a non-atomic test (PagePrivate && page_count == 0)
to determine whether or not a free page's buddy is itself free and in the
buddy lists.

Each of the conjuncts may be true at different times due to unrelated
conditions, so the non-atomic page_is_buddy test may find each conjunct to
be true even if they were not both true at the same time (ie. the page was
not on the buddy lists).

Signed-off-by: Martin Bligh <mbligh@google.com>
Signed-off-by: Rohit Seth <rohitseth@google.com>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

1 files changed, 18 insertions, 13 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 234bd4895d1..61de2220231 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -153,7 +153,8 @@ static void bad_page(struct page *page)
 			1 << PG_reclaim |
 			1 << PG_slab    |
 			1 << PG_swapcache |
-			1 << PG_writeback );
+			1 << PG_writeback |
+			1 << PG_buddy );
 	set_page_count(page, 0);
 	reset_page_mapcount(page);
 	page->mapping = NULL;
@@ -224,12 +225,12 @@ static inline unsigned long page_order(struct page *page) {
 
 static inline void set_page_order(struct page *page, int order) {
 	set_page_private(page, order);
-	__SetPagePrivate(page);
+	__SetPageBuddy(page);
 }
 
 static inline void rmv_page_order(struct page *page)
 {
-	__ClearPagePrivate(page);
+	__ClearPageBuddy(page);
 	set_page_private(page, 0);
 }
 
@@ -268,11 +269,13 @@ __find_combined_index(unsigned long page_idx, unsigned int order)
  * This function checks whether a page is free && is the buddy
  * we can do coalesce a page and its buddy if
  * (a) the buddy is not in a hole &&
- * (b) the buddy is free &&
- * (c) the buddy is on the buddy system &&
- * (d) a page and its buddy have the same order.
- * for recording page's order, we use page_private(page) and PG_private.
+ * (b) the buddy is in the buddy system &&
+ * (c) a page and its buddy have the same order.
+ *
+ * For recording whether a page is in the buddy system, we use PG_buddy.
+ * Setting, clearing, and testing PG_buddy is serialized by zone->lock.
  *
+ * For recording page's order, we use page_private(page).
  */
 static inline int page_is_buddy(struct page *page, int order)
 {
@@ -281,10 +284,10 @@ static inline int page_is_buddy(struct page *page, int order)
 		return 0;
 #endif
 
-       if (PagePrivate(page)           &&
-           (page_order(page) == order) &&
-            page_count(page) == 0)
+	if (PageBuddy(page) && page_order(page) == order) {
+		BUG_ON(page_count(page) != 0);
                return 1;
+	}
        return 0;
 }
 
@@ -301,7 +304,7 @@ static inline int page_is_buddy(struct page *page, int order)
  * as necessary, plus some accounting needed to play nicely with other
  * parts of the VM system.
  * At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with PG_Private.Page's
+ * free pages of length of (1 << order) and marked with PG_buddy. Page's
  * order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
  * other.  That is, if we allocate a small block, and both were   
@@ -364,7 +367,8 @@ static inline int free_pages_check(struct page *page)
 			1 << PG_slab	|
 			1 << PG_swapcache |
 			1 << PG_writeback |
-			1 << PG_reserved ))))
+			1 << PG_reserved |
+			1 << PG_buddy ))))
 		bad_page(page);
 	if (PageDirty(page))
 		__ClearPageDirty(page);
@@ -522,7 +526,8 @@ static int prep_new_page(struct page *page, int order)
 			1 << PG_slab    |
 			1 << PG_swapcache |
 			1 << PG_writeback |
-			1 << PG_reserved ))))
+			1 << PG_reserved |
+			1 << PG_buddy ))))
 		bad_page(page);
 
 	/*