1 files changed, 32 insertions, 49 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 2f76c4a081a2..7d9d06ba184b 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -68,7 +68,7 @@ int nr_pdflush_threads;
  */
 int writeback_in_progress(struct backing_dev_info *bdi)
 {
-	return !list_empty(&bdi->work_list);
+	return test_bit(BDI_writeback_running, &bdi->state);
 }
 
 static void bdi_queue_work(struct backing_dev_info *bdi,
@@ -249,10 +249,18 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 
 /*
  * Queue all expired dirty inodes for io, eldest first.
+ * Before
+ *         newly dirtied     b_dirty    b_io    b_more_io
+ *         =============>    gf         edc     BA
+ * After
+ *         newly dirtied     b_dirty    b_io    b_more_io
+ *         =============>    g          fBAedc
+ *                                           |
+ *                                           +--> dequeue for IO
  */
 static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
 {
-	list_splice_init(&wb->b_more_io, wb->b_io.prev);
+	list_splice_init(&wb->b_more_io, &wb->b_io);
 	move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
 }
 
@@ -363,62 +371,35 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	spin_lock(&inode_lock);
 	inode->i_state &= ~I_SYNC;
 	if (!(inode->i_state & I_FREEING)) {
-		if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) {
-			/*
-			 * More pages get dirtied by a fast dirtier.
-			 */
-			goto select_queue;
-		} else if (inode->i_state & I_DIRTY) {
-			/*
-			 * At least XFS will redirty the inode during the
-			 * writeback (delalloc) and on io completion (isize).
-			 */
-			redirty_tail(inode);
-		} else if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+		if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
 			/*
 			 * We didn't write back all the pages.  nfs_writepages()
-			 * sometimes bales out without doing anything. Redirty
-			 * the inode; Move it from b_io onto b_more_io/b_dirty.
+			 * sometimes bales out without doing anything.
 			 */
-			/*
-			 * akpm: if the caller was the kupdate function we put
-			 * this inode at the head of b_dirty so it gets first
-			 * consideration.  Otherwise, move it to the tail, for
-			 * the reasons described there.  I'm not really sure
-			 * how much sense this makes.  Presumably I had a good
-			 * reasons for doing it this way, and I'd rather not
-			 * muck with it at present.
-			 */
-			if (wbc->for_kupdate) {
+			inode->i_state |= I_DIRTY_PAGES;
+			if (wbc->nr_to_write <= 0) {
 				/*
-				 * For the kupdate function we move the inode
-				 * to b_more_io so it will get more writeout as
-				 * soon as the queue becomes uncongested.
+				 * slice used up: queue for next turn
 				 */
-				inode->i_state |= I_DIRTY_PAGES;
-select_queue:
-				if (wbc->nr_to_write <= 0) {
-					/*
-					 * slice used up: queue for next turn
-					 */
-					requeue_io(inode);
-				} else {
-					/*
-					 * somehow blocked: retry later
-					 */
-					redirty_tail(inode);
-				}
+				requeue_io(inode);
 			} else {
 				/*
-				 * Otherwise fully redirty the inode so that
-				 * other inodes on this superblock will get some
-				 * writeout.  Otherwise heavy writing to one
-				 * file would indefinitely suspend writeout of
-				 * all the other files.
+				 * Writeback blocked by something other than
+				 * congestion. Delay the inode for some time to
+				 * avoid spinning on the CPU (100% iowait)
+				 * retrying writeback of the dirty page/inode
+				 * that cannot be performed immediately.
 				 */
-				inode->i_state |= I_DIRTY_PAGES;
 				redirty_tail(inode);
 			}
+		} else if (inode->i_state & I_DIRTY) {
+			/*
+			 * Filesystems can dirty the inode during writeback
+			 * operations, such as delayed allocation during
+			 * submission or metadata updates after data IO
+			 * completion.
+			 */
+			redirty_tail(inode);
 		} else if (atomic_read(&inode->i_count)) {
 			/*
 			 * The inode is clean, inuse
@@ -590,7 +571,7 @@ static inline bool over_bground_thresh(void)
 {
 	unsigned long background_thresh, dirty_thresh;
 
-	get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+	global_dirty_limits(&background_thresh, &dirty_thresh);
 
 	return (global_page_state(NR_FILE_DIRTY) +
 		global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
@@ -759,6 +740,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 	struct wb_writeback_work *work;
 	long wrote = 0;
 
+	set_bit(BDI_writeback_running, &wb->bdi->state);
 	while ((work = get_next_work_item(bdi)) != NULL) {
 		/*
 		 * Override sync mode, in case we must wait for completion
@@ -785,6 +767,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 	 * Check for periodic writeback, kupdated() style
 	 */
 	wrote += wb_check_old_data_flush(wb);
+	clear_bit(BDI_writeback_running, &wb->bdi->state);
 
 	return wrote;
 }