2 files changed, 49 insertions, 4 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 2cb01f6ec5d..b437fe6257b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1211,6 +1211,17 @@ int set_page_dirty(struct page *page)
 
 	if (likely(mapping)) {
 		int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
+		/*
+		 * readahead/lru_deactivate_page could remain
+		 * PG_readahead/PG_reclaim due to race with end_page_writeback
+		 * About readahead, if the page is written, the flags would be
+		 * reset. So no problem.
+		 * About lru_deactivate_page, if the page is redirty, the flag
+		 * will be reset. So no problem. but if the page is used by readahead
+		 * it will confuse readahead and make it restart the size rampup
+		 * process. But it's a trivial problem.
+		 */
+		ClearPageReclaim(page);
 #ifdef CONFIG_BLOCK
 		if (!spd)
 			spd = __set_page_dirty_buffers;
@@ -1266,7 +1277,6 @@ int clear_page_dirty_for_io(struct page *page)
 
 	BUG_ON(!PageLocked(page));
 
-	ClearPageReclaim(page);
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		/*
 		 * Yes, Virginia, this is indeed insane.
diff --git a/mm/swap.c b/mm/swap.c
index 1b9e4ebaffc..0a33714a7cb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -354,26 +354,61 @@ void add_page_to_unevictable_list(struct page *page)
  * head of the list, rather than the tail, to give the flusher
  * threads some time to write it out, as this is much more
  * effective than the single-page writeout from reclaim.
+ *
+ * If the page isn't page_mapped and dirty/writeback, the page
+ * could reclaim asap using PG_reclaim.
+ *
+ * 1. active, mapped page -> none
+ * 2. active, dirty/writeback page -> inactive, head, PG_reclaim
+ * 3. inactive, mapped page -> none
+ * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim
+ * 5. inactive, clean -> inactive, tail
+ * 6. Others -> none
+ *
+ * In 4, why it moves inactive's head, the VM expects the page would
+ * be write it out by flusher threads as this is much more effective
+ * than the single-page writeout from reclaim.
  */
 static void lru_deactivate(struct page *page, struct zone *zone)
 {
 	int lru, file;
+	bool active;
 
-	if (!PageLRU(page) || !PageActive(page))
+	if (!PageLRU(page))
 		return;
 
 	/* Some processes are using the page */
 	if (page_mapped(page))
 		return;
 
+	active = PageActive(page);
+
 	file = page_is_file_cache(page);
 	lru = page_lru_base_type(page);
-	del_page_from_lru_list(zone, page, lru + LRU_ACTIVE);
+	del_page_from_lru_list(zone, page, lru + active);
 	ClearPageActive(page);
 	ClearPageReferenced(page);
 	add_page_to_lru_list(zone, page, lru);
-	__count_vm_event(PGDEACTIVATE);
 
+	if (PageWriteback(page) || PageDirty(page)) {
+		/*
+		 * PG_reclaim could be raced with end_page_writeback
+		 * It can make readahead confusing.  But race window
+		 * is _really_ small and  it's non-critical problem.
+		 */
+		SetPageReclaim(page);
+	} else {
+		/*
+		 * The page's writeback ends up during pagevec
+		 * We moves tha page into tail of inactive.
+		 */
+		list_move_tail(&page->lru, &zone->lru[lru].list);
+		mem_cgroup_rotate_reclaimable_page(page);
+		__count_vm_event(PGROTATED);
+	}
+
+	if (active)
+		__count_vm_event(PGDEACTIVATE);
 	update_page_reclaim_stat(zone, page, file, 0);
 }