Synchronous Lumpy Reclaim V2

index d419e10..99ec7fa 100644
@@ -777,6 +777,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 			     (sc->order > PAGE_ALLOC_COSTLY_ORDER)?
 					     ISOLATE_BOTH : ISOLATE_INACTIVE);
 		nr_active = clear_active_flags(&page_list);
+		__count_vm_events(PGDEACTIVATE, nr_active);
 
 		__mod_zone_page_state(zone, NR_ACTIVE, -nr_active);
 		__mod_zone_page_state(zone, NR_INACTIVE,

index 99ec7fa..1c21714 100644
@@ -271,6 +271,12 @@ static void handle_write_error(struct address_space *mapping,
 	unlock_page(page);
 }
 
+/* Request for sync pageout. */
+typedef enum {
+	PAGEOUT_IO_ASYNC,
+	PAGEOUT_IO_SYNC,
+} pageout_io_t;
+
 /* possible outcome of pageout() */
 typedef enum {
 	/* failed to write page out, page is locked */

@@ -287,7 +293,8 @@ typedef enum {
  * pageout is called by shrink_page_list() for each dirty page.
  * Calls ->writepage().
  */
-static pageout_t pageout(struct page *page, struct address_space *mapping)
+static pageout_t pageout(struct page *page, struct address_space *mapping,
+						pageout_io_t sync_writeback)
 {
 	/*
 	 * If the page is dirty, only perform writeback if that write

@@ -346,6 +353,15 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
 			ClearPageReclaim(page);
 			return PAGE_ACTIVATE;
 		}
+
+		/*
+		 * Wait on writeback if requested to. This happens when
+		 * direct reclaiming a large contiguous area and the
+		 * first attempt to free a ranage of pages fails
+		 */
+		if (PageWriteback(page) && sync_writeback == PAGEOUT_IO_SYNC)
+			wait_on_page_writeback(page);
+
 		if (!PageWriteback(page)) {
 			/* synchronous write or broken a_ops? */
 			ClearPageReclaim(page);

@@ -423,7 +439,8 @@ cannot_free:
  * shrink_page_list() returns the number of reclaimed pages
  */
 static unsigned long shrink_page_list(struct list_head *page_list,
-					struct scan_control *sc)
+					struct scan_control *sc,
+					pageout_io_t sync_writeback)
 {
 	LIST_HEAD(ret_pages);
 	struct pagevec freed_pvec;

@@ -458,8 +475,12 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (page_mapped(page) || PageSwapCache(page))
 			sc->nr_scanned++;
 
-		if (PageWriteback(page))
-			goto keep_locked;
+		if (PageWriteback(page)) {
+			if (sync_writeback == PAGEOUT_IO_SYNC)
+				wait_on_page_writeback(page);
+			else
+				goto keep_locked;
+		}
 
 		referenced = page_referenced(page, 1);
 		/* In active use or really unfreeable?  Activate it. */

@@ -505,7 +526,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto keep_locked;
 
 			/* Page is dirty, try to write it out here */
-			switch(pageout(page, mapping)) {
+			switch (pageout(page, mapping, sync_writeback)) {
 			case PAGE_KEEP:
 				goto keep_locked;
 			case PAGE_ACTIVATE:

@@ -786,7 +807,29 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		spin_unlock_irq(&zone->lru_lock);
 
 		nr_scanned += nr_scan;
-		nr_freed = shrink_page_list(&page_list, sc);
+		nr_freed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);
+
+		/*
+		 * If we are direct reclaiming for contiguous pages and we do
+		 * not reclaim everything in the list, try again and wait
+		 * for IO to complete. This will stall high-order allocations
+		 * but that should be acceptable to the caller
+		 */
+		if (nr_freed < nr_taken && !current_is_kswapd() &&
+					sc->order > PAGE_ALLOC_COSTLY_ORDER) {
+			congestion_wait(WRITE, HZ/10);
+
+			/*
+			 * The attempt at page out may have made some
+			 * of the pages active, mark them inactive again.
+			 */
+			nr_active = clear_active_flags(&page_list);
+			count_vm_events(PGDEACTIVATE, nr_active);
+
+			nr_freed += shrink_page_list(&page_list, sc,
+							PAGEOUT_IO_SYNC);
+		}
+
 		nr_reclaimed += nr_freed;
 		local_irq_disable();
 		if (current_is_kswapd()) {