SHM_UNLOCK: fix Unevictable pages stranded after swap

Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in
find_get_pages") correctly fixed an infinite loop; but left a problem
that find_get_pages() on shmem would return 0 (appearing to callers to
mean end of tree) when it meets a run of nr_pages swap entries.

The only uses of find_get_pages() on shmem are via pagevec_lookup(),
called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's
scan_mapping_unevictable_pages().  The first is already commented, and
not worth worrying about; but the second can leave pages on the
Unevictable list after an unusual sequence of swapping and locking.

Fix that by using shmem_find_get_pages_and_swap() (then ignoring the
swap) instead of pagevec_lookup().

But I don't want to contaminate vmscan.c with shmem internals, nor
shmem.c with LRU locking.  So move scan_mapping_unevictable_pages() into
shmem.c, renaming it shmem_unlock_mapping(); and rename
check_move_unevictable_page() to check_move_unevictable_pages(), looping
down an array of pages, oftentimes under the same lock.

Leave out the "rotate unevictable list" block: that's a leftover from
when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed
handling involved looking at pages at tail of LRU.

Was there significance to the sequence first ClearPageUnevictable, then
test page_evictable, then SetPageUnevictable here? I think not, we're
under LRU lock, and have no barriers between those.

Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shaohua.li@intel.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 80 insertions, 94 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 4aaa53abe302..269d049294ab 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -379,7 +379,7 @@ static int shmem_free_swap(struct address_space *mapping,
 /*
  * Pagevec may contain swap entries, so shuffle up pages before releasing.
  */
-static void shmem_pagevec_release(struct pagevec *pvec)
+static void shmem_deswap_pagevec(struct pagevec *pvec)
 {
 	int i, j;
 
@@ -389,7 +389,36 @@ static void shmem_pagevec_release(struct pagevec *pvec)
 			pvec->pages[j++] = page;
 	}
 	pvec->nr = j;
-	pagevec_release(pvec);
+}
+
+/*
+ * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
+ */
+void shmem_unlock_mapping(struct address_space *mapping)
+{
+	struct pagevec pvec;
+	pgoff_t indices[PAGEVEC_SIZE];
+	pgoff_t index = 0;
+
+	pagevec_init(&pvec, 0);
+	/*
+	 * Minor point, but we might as well stop if someone else SHM_LOCKs it.
+	 */
+	while (!mapping_unevictable(mapping)) {
+		/*
+		 * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
+		 * has finished, if it hits a row of PAGEVEC_SIZE swap entries.
+		 */
+		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+					PAGEVEC_SIZE, pvec.pages, indices);
+		if (!pvec.nr)
+			break;
+		index = indices[pvec.nr - 1] + 1;
+		shmem_deswap_pagevec(&pvec);
+		check_move_unevictable_pages(pvec.pages, pvec.nr);
+		pagevec_release(&pvec);
+		cond_resched();
+	}
 }
 
 /*
@@ -440,7 +469,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 			}
 			unlock_page(page);
 		}
-		shmem_pagevec_release(&pvec);
+		shmem_deswap_pagevec(&pvec);
+		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
 		index++;
@@ -470,7 +500,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 			continue;
 		}
 		if (index == start && indices[0] > end) {
-			shmem_pagevec_release(&pvec);
+			shmem_deswap_pagevec(&pvec);
+			pagevec_release(&pvec);
 			break;
 		}
 		mem_cgroup_uncharge_start();
@@ -494,7 +525,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 			}
 			unlock_page(page);
 		}
-		shmem_pagevec_release(&pvec);
+		shmem_deswap_pagevec(&pvec);
+		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		index++;
 	}
@@ -2438,6 +2470,10 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	return 0;
 }
 
+void shmem_unlock_mapping(struct address_space *mapping)
+{
+}
+
 void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 {
 	truncate_inode_pages_range(inode->i_mapping, lstart, lend);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e097c1026b58..c52b23552659 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -26,7 +26,6 @@
 #include <linux/buffer_head.h>	/* for try_to_release_page(),
 					buffer_heads_over_limit */
 #include <linux/mm_inline.h>
-#include <linux/pagevec.h>
 #include <linux/backing-dev.h>
 #include <linux/rmap.h>
 #include <linux/topology.h>
@@ -661,7 +660,7 @@ redo:
 		 * When racing with an mlock or AS_UNEVICTABLE clearing
 		 * (page is unlocked) make sure that if the other thread
 		 * does not observe our setting of PG_lru and fails
-		 * isolation/check_move_unevictable_page,
+		 * isolation/check_move_unevictable_pages,
 		 * we see PG_mlocked/AS_UNEVICTABLE cleared below and move
 		 * the page back to the evictable list.
 		 *
@@ -3501,107 +3500,58 @@ int page_evictable(struct page *page, struct vm_area_struct *vma)
 
 #ifdef CONFIG_SHMEM
 /**
- * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list
- * @page: page to check evictability and move to appropriate lru list
- * @zone: zone page is in
+ * check_move_unevictable_pages - check pages for evictability and move to appropriate zone lru list
+ * @pages:	array of pages to check
+ * @nr_pages:	number of pages to check
  *
- * Checks a page for evictability and moves the page to the appropriate
- * zone lru list.
- *
- * Restrictions: zone->lru_lock must be held, page must be on LRU and must
- * have PageUnevictable set.
+ * Checks pages for evictability and moves them to the appropriate lru list.
  *
  * This function is only used for SysV IPC SHM_UNLOCK.
  */
-static void check_move_unevictable_page(struct page *page, struct zone *zone)
+void check_move_unevictable_pages(struct page **pages, int nr_pages)
 {
 	struct lruvec *lruvec;
+	struct zone *zone = NULL;
+	int pgscanned = 0;
+	int pgrescued = 0;
+	int i;
 
-	VM_BUG_ON(PageActive(page));
-retry:
-	ClearPageUnevictable(page);
-	if (page_evictable(page, NULL)) {
-		enum lru_list l = page_lru_base_type(page);
-
-		__dec_zone_state(zone, NR_UNEVICTABLE);
-		lruvec = mem_cgroup_lru_move_lists(zone, page,
-						   LRU_UNEVICTABLE, l);
-		list_move(&page->lru, &lruvec->lists[l]);
-		__inc_zone_state(zone, NR_INACTIVE_ANON + l);
-		__count_vm_event(UNEVICTABLE_PGRESCUED);
-	} else {
-		/*
-		 * rotate unevictable list
-		 */
-		SetPageUnevictable(page);
-		lruvec = mem_cgroup_lru_move_lists(zone, page, LRU_UNEVICTABLE,
-						   LRU_UNEVICTABLE);
-		list_move(&page->lru, &lruvec->lists[LRU_UNEVICTABLE]);
-		if (page_evictable(page, NULL))
-			goto retry;
-	}
-}
-
-/**
- * scan_mapping_unevictable_pages - scan an address space for evictable pages
- * @mapping: struct address_space to scan for evictable pages
- *
- * Scan all pages in mapping.  Check unevictable pages for
- * evictability and move them to the appropriate zone lru list.
- *
- * This function is only used for SysV IPC SHM_UNLOCK.
- */
-void scan_mapping_unevictable_pages(struct address_space *mapping)
-{
-	pgoff_t next = 0;
-	pgoff_t end   = (i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1) >>
-			 PAGE_CACHE_SHIFT;
-	struct zone *zone;
-	struct pagevec pvec;
-
-	if (mapping->nrpages == 0)
-		return;
-
-	pagevec_init(&pvec, 0);
-	while (next < end &&
-		pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
-		int i;
-		int pg_scanned = 0;
-
-		zone = NULL;
-
-		for (i = 0; i < pagevec_count(&pvec); i++) {
-			struct page *page = pvec.pages[i];
-			pgoff_t page_index = page->index;
-			struct zone *pagezone = page_zone(page);
+	for (i = 0; i < nr_pages; i++) {
+		struct page *page = pages[i];
+		struct zone *pagezone;
 
-			pg_scanned++;
-			if (page_index > next)
-				next = page_index;
-			next++;
+		pgscanned++;
+		pagezone = page_zone(page);
+		if (pagezone != zone) {
+			if (zone)
+				spin_unlock_irq(&zone->lru_lock);
+			zone = pagezone;
+			spin_lock_irq(&zone->lru_lock);
+		}
 
-			if (pagezone != zone) {
-				if (zone)
-					spin_unlock_irq(&zone->lru_lock);
-				zone = pagezone;
-				spin_lock_irq(&zone->lru_lock);
-			}
+		if (!PageLRU(page) || !PageUnevictable(page))
+			continue;
 
-			if (PageLRU(page) && PageUnevictable(page))
-				check_move_unevictable_page(page, zone);
+		if (page_evictable(page, NULL)) {
+			enum lru_list lru = page_lru_base_type(page);
+
+			VM_BUG_ON(PageActive(page));
+			ClearPageUnevictable(page);
+			__dec_zone_state(zone, NR_UNEVICTABLE);
+			lruvec = mem_cgroup_lru_move_lists(zone, page,
+						LRU_UNEVICTABLE, lru);
+			list_move(&page->lru, &lruvec->lists[lru]);
+			__inc_zone_state(zone, NR_INACTIVE_ANON + lru);
+			pgrescued++;
 		}
-		if (zone)
-			spin_unlock_irq(&zone->lru_lock);
-		pagevec_release(&pvec);
+	}
 
-		count_vm_events(UNEVICTABLE_PGSCANNED, pg_scanned);
-		cond_resched();
+	if (zone) {
+		__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
+		__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
+		spin_unlock_irq(&zone->lru_lock);
 	}
 }
-#else
-void scan_mapping_unevictable_pages(struct address_space *mapping)
-{
-}
 #endif /* CONFIG_SHMEM */
 
 static void warn_scan_unevictable_pages(void)