[PATCH] vmscan: ignore swap token when in trouble

The token-based thrashing control patches introduced a problem: when a task
which doesn't hold the token tries to run direct-reclaim, that task is told
that pages which belong to the token-holding mm are referenced, even though
they are not.  This means that it is possible for a huge number of a
non-token-holding mm's pages to be scanned to no effect.  Eventually, we give
up and go and oom-kill something.

So the patch arranges for the thrashing control logic to be defeated if the
caller has reached the highest level of scanning priority.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/linux/rmap.h

@@ -89,7 +89,7 @@ static inline void page_dup_rmap(struct page *page)
 /*
  * Called from mm/vmscan.c to handle paging out
  */
-int page_referenced(struct page *, int is_locked);
+int page_referenced(struct page *, int is_locked, int ignore_token);
 int try_to_unmap(struct page *);
 
 /*
@@ -103,7 +103,7 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
 #define anon_vma_prepare(vma)	(0)
 #define anon_vma_link(vma)	do {} while (0)
 
-#define page_referenced(page,l)	TestClearPageReferenced(page)
+#define page_referenced(page,l,i) TestClearPageReferenced(page)
 #define try_to_unmap(page)	SWAP_FAIL
 
 #endif	/* CONFIG_MMU */

mm/rmap.c

@@ -254,7 +254,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
  * repeatedly from either page_referenced_anon or page_referenced_file.
  */
 static int page_referenced_one(struct page *page,
-	struct vm_area_struct *vma, unsigned int *mapcount)
+	struct vm_area_struct *vma, unsigned int *mapcount, int ignore_token)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -289,7 +289,7 @@ static int page_referenced_one(struct page *page,
 	if (ptep_clear_flush_young(vma, address, pte))
 		referenced++;
 
-	if (mm != current->mm && has_swap_token(mm))
+	if (mm != current->mm && !ignore_token && has_swap_token(mm))
 		referenced++;
 
 	(*mapcount)--;
@@ -302,7 +302,7 @@ static int page_referenced_one(struct page *page,
 	return referenced;
 }
 
-static int page_referenced_anon(struct page *page)
+static int page_referenced_anon(struct page *page, int ignore_token)
 {
 	unsigned int mapcount;
 	struct anon_vma *anon_vma;
@@ -315,7 +315,8 @@ static int page_referenced_anon(struct page *page)
 
 	mapcount = page_mapcount(page);
 	list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
-		referenced += page_referenced_one(page, vma, &mapcount);
+		referenced += page_referenced_one(page, vma, &mapcount,
+							ignore_token);
 		if (!mapcount)
 			break;
 	}
@@ -334,7 +335,7 @@ static int page_referenced_anon(struct page *page)
  *
  * This function is only called from page_referenced for object-based pages.
  */
-static int page_referenced_file(struct page *page)
+static int page_referenced_file(struct page *page, int ignore_token)
 {
 	unsigned int mapcount;
 	struct address_space *mapping = page->mapping;
@@ -372,7 +373,8 @@ static int page_referenced_file(struct page *page)
 			referenced++;
 			break;
 		}
-		referenced += page_referenced_one(page, vma, &mapcount);
+		referenced += page_referenced_one(page, vma, &mapcount,
+							ignore_token);
 		if (!mapcount)
 			break;
 	}
@@ -389,7 +391,7 @@ static int page_referenced_file(struct page *page)
  * Quick test_and_clear_referenced for all mappings to a page,
  * returns the number of ptes which referenced the page.
  */
-int page_referenced(struct page *page, int is_locked)
+int page_referenced(struct page *page, int is_locked, int ignore_token)
 {
 	int referenced = 0;
 
@@ -401,14 +403,15 @@ int page_referenced(struct page *page, int is_locked)
 
 	if (page_mapped(page) && page->mapping) {
 		if (PageAnon(page))
-			referenced += page_referenced_anon(page);
+			referenced += page_referenced_anon(page, ignore_token);
 		else if (is_locked)
-			referenced += page_referenced_file(page);
+			referenced += page_referenced_file(page, ignore_token);
 		else if (TestSetPageLocked(page))
 			referenced++;
 		else {
 			if (page->mapping)
-				referenced += page_referenced_file(page);
+				referenced += page_referenced_file(page,
+								ignore_token);
 			unlock_page(page);
 		}
 	}

mm/vmscan.c

@@ -377,7 +377,7 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc)
 		if (page_mapped(page) || PageSwapCache(page))
 			sc->nr_scanned++;
 
-		referenced = page_referenced(page, 1);
+		referenced = page_referenced(page, 1, sc->priority <= 0);
 		/* In active use or really unfreeable?  Activate it. */
 		if (referenced && page_mapping_inuse(page))
 			goto activate_locked;
@@ -715,7 +715,7 @@ refill_inactive_zone(struct zone *zone, struct scan_control *sc)
 		if (page_mapped(page)) {
 			if (!reclaim_mapped ||
 			    (total_swap_pages == 0 && PageAnon(page)) ||
-			    page_referenced(page, 0)) {
+			    page_referenced(page, 0, sc->priority <= 0)) {
 				list_add(&page->lru, &l_active);
 				continue;
 			}