Merge remote-tracking branch 'writeback/next'

15 files changed, 270 insertions, 159 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1a2421f908f0..3c9a03e51b62 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -44,24 +44,28 @@ inline struct block_device *I_BDEV(struct inode *inode)
 {
 	return &BDEV_I(inode)->bdev;
 }
-
 EXPORT_SYMBOL(I_BDEV);
 
 /*
- * move the inode from it's current bdi to the a new bdi. if the inode is dirty
- * we need to move it onto the dirty list of @dst so that the inode is always
- * on the right list.
+ * Move the inode from its current bdi to a new bdi. If the inode is dirty we
+ * need to move it onto the dirty list of @dst so that the inode is always on
+ * the right list.
  */
 static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
-	spin_lock(&inode_wb_list_lock);
+	struct backing_dev_info *old = inode->i_data.backing_dev_info;
+
+	if (unlikely(dst == old))		/* deadlock avoidance */
+		return;
+	bdi_lock_two(&old->wb, &dst->wb);
 	spin_lock(&inode->i_lock);
 	inode->i_data.backing_dev_info = dst;
 	if (inode->i_state & I_DIRTY)
 		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
 	spin_unlock(&inode->i_lock);
-	spin_unlock(&inode_wb_list_lock);
+	spin_unlock(&old->wb.list_lock);
+	spin_unlock(&dst->wb.list_lock);
 }
 
 static sector_t max_block(struct block_device *bdev)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e3126c051006..62f86e71f291 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2741,7 +2741,7 @@ static int write_cache_pages_da(struct address_space *mapping,
 	index = wbc->range_start >> PAGE_CACHE_SHIFT;
 	end = wbc->range_end >> PAGE_CACHE_SHIFT;
 
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag = PAGECACHE_TAG_TOWRITE;
 	else
 		tag = PAGECACHE_TAG_DIRTY;
@@ -2973,7 +2973,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	}
 
 retry:
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag_pages_for_writeback(mapping, index, end);
 
 	while (!ret && wbc->nr_to_write > 0) {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 0f015a0468de..6caa98247a5b 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -36,6 +36,7 @@ struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
 	enum writeback_sync_modes sync_mode;
+	unsigned int tagged_writepages:1;
 	unsigned int for_kupdate:1;
 	unsigned int range_cyclic:1;
 	unsigned int for_background:1;
@@ -180,12 +181,13 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
  */
 void inode_wb_list_del(struct inode *inode)
 {
-	spin_lock(&inode_wb_list_lock);
+	struct backing_dev_info *bdi = inode_to_bdi(inode);
+
+	spin_lock(&bdi->wb.list_lock);
 	list_del_init(&inode->i_wb_list);
-	spin_unlock(&inode_wb_list_lock);
+	spin_unlock(&bdi->wb.list_lock);
 }
 
-
 /*
  * Redirty an inode: set its when-it-was dirtied timestamp and move it to the
  * furthest end of its superblock's dirty-inode list.
@@ -195,11 +197,9 @@ void inode_wb_list_del(struct inode *inode)
  * the case then the inode must have been redirtied while it was being written
  * out and we don't reset its dirtied_when.
  */
-static void redirty_tail(struct inode *inode)
+static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
 {
-	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
-
-	assert_spin_locked(&inode_wb_list_lock);
+	assert_spin_locked(&wb->list_lock);
 	if (!list_empty(&wb->b_dirty)) {
 		struct inode *tail;
 
@@ -213,11 +213,9 @@ static void redirty_tail(struct inode *inode)
 /*
  * requeue inode for re-scanning after bdi->b_io list is exhausted.
  */
-static void requeue_io(struct inode *inode)
+static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
 {
-	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
-
-	assert_spin_locked(&inode_wb_list_lock);
+	assert_spin_locked(&wb->list_lock);
 	list_move(&inode->i_wb_list, &wb->b_more_io);
 }
 
@@ -225,7 +223,7 @@ static void inode_sync_complete(struct inode *inode)
 {
 	/*
 	 * Prevent speculative execution through
-	 * spin_unlock(&inode_wb_list_lock);
+	 * spin_unlock(&wb->list_lock);
 	 */
 
 	smp_mb();
@@ -250,15 +248,16 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 /*
  * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
  */
-static void move_expired_inodes(struct list_head *delaying_queue,
+static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
-				unsigned long *older_than_this)
+			       unsigned long *older_than_this)
 {
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
 	struct super_block *sb = NULL;
 	struct inode *inode;
 	int do_sb_sort = 0;
+	int moved = 0;
 
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
@@ -269,12 +268,13 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 			do_sb_sort = 1;
 		sb = inode->i_sb;
 		list_move(&inode->i_wb_list, &tmp);
+		moved++;
 	}
 
 	/* just one sb in list, splice to dispatch_queue and we're done */
 	if (!do_sb_sort) {
 		list_splice(&tmp, dispatch_queue);
-		return;
+		goto out;
 	}
 
 	/* Move inodes from one superblock together */
@@ -286,6 +286,8 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 				list_move(&inode->i_wb_list, dispatch_queue);
 		}
 	}
+out:
+	return moved;
 }
 
 /*
@@ -301,9 +303,11 @@ static void move_expired_inodes(struct list_head *delaying_queue,
  */
 static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
 {
-	assert_spin_locked(&inode_wb_list_lock);
+	int moved;
+	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
+	trace_writeback_queue_io(wb, older_than_this, moved);
 }
 
 static int write_inode(struct inode *inode, struct writeback_control *wbc)
@@ -316,7 +320,8 @@ static int write_inode(struct inode *inode, struct writeback_control *wbc)
 /*
  * Wait for writeback on an inode to complete.
  */
-static void inode_wait_for_writeback(struct inode *inode)
+static void inode_wait_for_writeback(struct inode *inode,
+				     struct bdi_writeback *wb)
 {
 	DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
 	wait_queue_head_t *wqh;
@@ -324,15 +329,15 @@ static void inode_wait_for_writeback(struct inode *inode)
 	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
 	while (inode->i_state & I_SYNC) {
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&inode_wb_list_lock);
+		spin_unlock(&wb->list_lock);
 		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
-		spin_lock(&inode_wb_list_lock);
+		spin_lock(&wb->list_lock);
 		spin_lock(&inode->i_lock);
 	}
 }
 
 /*
- * Write out an inode's dirty pages.  Called under inode_wb_list_lock and
+ * Write out an inode's dirty pages.  Called under wb->list_lock and
  * inode->i_lock.  Either the caller has an active reference on the inode or
  * the inode has I_WILL_FREE set.
  *
@@ -343,13 +348,15 @@ static void inode_wait_for_writeback(struct inode *inode)
  * livelocks, etc.
  */
 static int
-writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
+writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
+		       struct writeback_control *wbc)
 {
 	struct address_space *mapping = inode->i_mapping;
+	long nr_to_write = wbc->nr_to_write;
 	unsigned dirty;
 	int ret;
 
-	assert_spin_locked(&inode_wb_list_lock);
+	assert_spin_locked(&wb->list_lock);
 	assert_spin_locked(&inode->i_lock);
 
 	if (!atomic_read(&inode->i_count))
@@ -367,14 +374,16 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 		 * completed a full scan of b_io.
 		 */
 		if (wbc->sync_mode != WB_SYNC_ALL) {
-			requeue_io(inode);
+			requeue_io(inode, wb);
+			trace_writeback_single_inode_requeue(inode, wbc,
+							     nr_to_write);
 			return 0;
 		}
 
 		/*
 		 * It's a data-integrity sync.  We must wait.
 		 */
-		inode_wait_for_writeback(inode);
+		inode_wait_for_writeback(inode, wb);
 	}
 
 	BUG_ON(inode->i_state & I_SYNC);
@@ -383,7 +392,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	inode->i_state |= I_SYNC;
 	inode->i_state &= ~I_DIRTY_PAGES;
 	spin_unlock(&inode->i_lock);
-	spin_unlock(&inode_wb_list_lock);
+	spin_unlock(&wb->list_lock);
 
 	ret = do_writepages(mapping, wbc);
 
@@ -414,10 +423,19 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 			ret = err;
 	}
 
-	spin_lock(&inode_wb_list_lock);
+	spin_lock(&wb->list_lock);
 	spin_lock(&inode->i_lock);
 	inode->i_state &= ~I_SYNC;
 	if (!(inode->i_state & I_FREEING)) {
+		/*
+		 * Sync livelock prevention. Each inode is tagged and synced in
+		 * one shot. If still dirty, it will be redirty_tail()'ed below.
+		 * Update the dirty time to prevent enqueue and sync it again.
+		 */
+		if ((inode->i_state & I_DIRTY) &&
+		    (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages))
+			inode->dirtied_when = jiffies;
+
 		if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
 			/*
 			 * We didn't write back all the pages.  nfs_writepages()
@@ -428,7 +446,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 				/*
 				 * slice used up: queue for next turn
 				 */
-				requeue_io(inode);
+				requeue_io(inode, wb);
 			} else {
 				/*
 				 * Writeback blocked by something other than
@@ -437,7 +455,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 				 * retrying writeback of the dirty page/inode
 				 * that cannot be performed immediately.
 				 */
-				redirty_tail(inode);
+				redirty_tail(inode, wb);
 			}
 		} else if (inode->i_state & I_DIRTY) {
 			/*
@@ -446,7 +464,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 			 * submission or metadata updates after data IO
 			 * completion.
 			 */
-			redirty_tail(inode);
+			redirty_tail(inode, wb);
 		} else {
 			/*
 			 * The inode is clean.  At this point we either have
@@ -454,9 +472,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 			 * No need to add it back to the LRU.
 			 */
 			list_del_init(&inode->i_wb_list);
+			wbc->inodes_written++;
 		}
 	}
 	inode_sync_complete(inode);
+	trace_writeback_single_inode(inode, wbc, nr_to_write);
 	return ret;
 }
 
@@ -510,7 +530,7 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 				 * superblock, move all inodes not belonging
 				 * to it back onto the dirty list.
 				 */
-				redirty_tail(inode);
+				redirty_tail(inode, wb);
 				continue;
 			}
 
@@ -530,63 +550,44 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
 			spin_unlock(&inode->i_lock);
-			requeue_io(inode);
+			requeue_io(inode, wb);
 			continue;
 		}
 
-		/*
-		 * Was this inode dirtied after sync_sb_inodes was called?
-		 * This keeps sync from extra jobs and livelock.
-		 */
-		if (inode_dirtied_after(inode, wbc->wb_start)) {
-			spin_unlock(&inode->i_lock);
-			return 1;
-		}
-
 		__iget(inode);
 
 		pages_skipped = wbc->pages_skipped;
-		writeback_single_inode(inode, wbc);
+		writeback_single_inode(inode, wb, wbc);
 		if (wbc->pages_skipped != pages_skipped) {
 			/*
 			 * writeback is not making progress due to locked
 			 * buffers.  Skip this inode for now.
 			 */
-			redirty_tail(inode);
+			redirty_tail(inode, wb);
 		}
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&inode_wb_list_lock);
+		spin_unlock(&wb->list_lock);
 		iput(inode);
 		cond_resched();
-		spin_lock(&inode_wb_list_lock);
-		if (wbc->nr_to_write <= 0) {
-			wbc->more_io = 1;
+		spin_lock(&wb->list_lock);
+		if (wbc->nr_to_write <= 0)
 			return 1;
-		}
-		if (!list_empty(&wb->b_more_io))
-			wbc->more_io = 1;
 	}
 	/* b_io is empty */
 	return 1;
 }
 
-void writeback_inodes_wb(struct bdi_writeback *wb,
-		struct writeback_control *wbc)
+static void __writeback_inodes_wb(struct bdi_writeback *wb,
+				  struct writeback_control *wbc)
 {
 	int ret = 0;
 
-	if (!wbc->wb_start)
-		wbc->wb_start = jiffies; /* livelock avoidance */
-	spin_lock(&inode_wb_list_lock);
-	if (!wbc->for_kupdate || list_empty(&wb->b_io))
-		queue_io(wb, wbc->older_than_this);
-
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
 		struct super_block *sb = inode->i_sb;
 
 		if (!pin_sb_for_writeback(sb)) {
-			requeue_io(inode);
+			requeue_io(inode, wb);
 			continue;
 		}
 		ret = writeback_sb_inodes(sb, wb, wbc, false);
@@ -595,20 +596,17 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
 		if (ret)
 			break;
 	}
-	spin_unlock(&inode_wb_list_lock);
 	/* Leave any unwritten inodes on b_io */
 }
 
-static void __writeback_inodes_sb(struct super_block *sb,
-		struct bdi_writeback *wb, struct writeback_control *wbc)
+void writeback_inodes_wb(struct bdi_writeback *wb,
+		struct writeback_control *wbc)
 {
-	WARN_ON(!rwsem_is_locked(&sb->s_umount));
-
-	spin_lock(&inode_wb_list_lock);
-	if (!wbc->for_kupdate || list_empty(&wb->b_io))
+	spin_lock(&wb->list_lock);
+	if (list_empty(&wb->b_io))
 		queue_io(wb, wbc->older_than_this);
-	writeback_sb_inodes(sb, wb, wbc, true);
-	spin_unlock(&inode_wb_list_lock);
+	__writeback_inodes_wb(wb, wbc);
+	spin_unlock(&wb->list_lock);
 }
 
 /*
@@ -650,6 +648,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 {
 	struct writeback_control wbc = {
 		.sync_mode		= work->sync_mode,
+		.tagged_writepages	= work->tagged_writepages,
 		.older_than_this	= NULL,
 		.for_kupdate		= work->for_kupdate,
 		.for_background		= work->for_background,
@@ -657,14 +656,9 @@ static long wb_writeback(struct bdi_writeback *wb,
 	};
 	unsigned long oldest_jif;
 	long wrote = 0;
-	long write_chunk;
+	long write_chunk = MAX_WRITEBACK_PAGES;
 	struct inode *inode;
 
-	if (wbc.for_kupdate) {
-		wbc.older_than_this = &oldest_jif;
-		oldest_jif = jiffies -
-				msecs_to_jiffies(dirty_expire_interval * 10);
-	}
 	if (!wbc.range_cyclic) {
 		wbc.range_start = 0;
 		wbc.range_end = LLONG_MAX;
@@ -678,17 +672,18 @@ static long wb_writeback(struct bdi_writeback *wb,
 	 * The intended call sequence for WB_SYNC_ALL writeback is:
 	 *
 	 *      wb_writeback()
-	 *          __writeback_inodes_sb()     <== called only once
+	 *          writeback_sb_inodes()       <== called only once
 	 *              write_cache_pages()     <== called once for each inode
 	 *                   (quickly) tag currently dirty pages
 	 *                   (maybe slowly) sync all tagged pages
 	 */
-	if (wbc.sync_mode == WB_SYNC_NONE)
-		write_chunk = MAX_WRITEBACK_PAGES;
-	else
+	if (wbc.sync_mode == WB_SYNC_ALL || wbc.tagged_writepages)
 		write_chunk = LONG_MAX;
 
-	wbc.wb_start = jiffies; /* livelock avoidance */
+	oldest_jif = jiffies;
+	wbc.older_than_this = &oldest_jif;
+
+	spin_lock(&wb->list_lock);
 	for (;;) {
 		/*
 		 * Stop writeback when nr_pages has been consumed
@@ -713,50 +708,59 @@ static long wb_writeback(struct bdi_writeback *wb,
 		if (work->for_background && !over_bground_thresh())
 			break;
 
-		wbc.more_io = 0;
+		if (work->for_kupdate) {
+			oldest_jif = jiffies -
+				msecs_to_jiffies(dirty_expire_interval * 10);
+			wbc.older_than_this = &oldest_jif;
+		}
+
 		wbc.nr_to_write = write_chunk;
 		wbc.pages_skipped = 0;
+		wbc.inodes_written = 0;
 
 		trace_wbc_writeback_start(&wbc, wb->bdi);
+		if (list_empty(&wb->b_io))
+			queue_io(wb, wbc.older_than_this);
 		if (work->sb)
-			__writeback_inodes_sb(work->sb, wb, &wbc);
+			writeback_sb_inodes(work->sb, wb, &wbc, true);
 		else
-			writeback_inodes_wb(wb, &wbc);
+			__writeback_inodes_wb(wb, &wbc);
 		trace_wbc_writeback_written(&wbc, wb->bdi);
 
 		work->nr_pages -= write_chunk - wbc.nr_to_write;
 		wrote += write_chunk - wbc.nr_to_write;
 
 		/*
-		 * If we consumed everything, see if we have more
+		 * Did we write something? Try for more
+		 *
+		 * Dirty inodes are moved to b_io for writeback in batches.
+		 * The completion of the current batch does not necessarily
+		 * mean the overall work is done. So we keep looping as long
+		 * as made some progress on cleaning pages or inodes.
 		 */
-		if (wbc.nr_to_write <= 0)
+		if (wbc.nr_to_write < write_chunk)
+			continue;
+		if (wbc.inodes_written)
 			continue;
 		/*
-		 * Didn't write everything and we don't have more IO, bail
+		 * No more inodes for IO, bail
 		 */
-		if (!wbc.more_io)
+		if (list_empty(&wb->b_more_io))
 			break;
 		/*
-		 * Did we write something? Try for more
-		 */
-		if (wbc.nr_to_write < write_chunk)
-			continue;
-		/*
 		 * Nothing written. Wait for some inode to
 		 * become available for writeback. Otherwise
 		 * we'll just busyloop.
 		 */
-		spin_lock(&inode_wb_list_lock);
 		if (!list_empty(&wb->b_more_io))  {
 			inode = wb_inode(wb->b_more_io.prev);
 			trace_wbc_writeback_wait(&wbc, wb->bdi);
 			spin_lock(&inode->i_lock);
-			inode_wait_for_writeback(inode);
+			inode_wait_for_writeback(inode, wb);
 			spin_unlock(&inode->i_lock);
 		}
-		spin_unlock(&inode_wb_list_lock);
 	}
+	spin_unlock(&wb->list_lock);
 
 	return wrote;
 }
@@ -1089,10 +1093,10 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			}
 
 			spin_unlock(&inode->i_lock);
-			spin_lock(&inode_wb_list_lock);
+			spin_lock(&bdi->wb.list_lock);
 			inode->dirtied_when = jiffies;
 			list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
-			spin_unlock(&inode_wb_list_lock);
+			spin_unlock(&bdi->wb.list_lock);
 
 			if (wakeup_bdi)
 				bdi_wakeup_thread_delayed(bdi);
@@ -1188,10 +1192,11 @@ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct wb_writeback_work work = {
-		.sb		= sb,
-		.sync_mode	= WB_SYNC_NONE,
-		.done		= &done,
-		.nr_pages	= nr,
+		.sb			= sb,
+		.sync_mode		= WB_SYNC_NONE,
+		.tagged_writepages	= 1,
+		.done			= &done,
+		.nr_pages		= nr,
 	};
 
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
@@ -1293,6 +1298,7 @@ EXPORT_SYMBOL(sync_inodes_sb);
  */
 int write_inode_now(struct inode *inode, int sync)
 {
+	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 	int ret;
 	struct writeback_control wbc = {
 		.nr_to_write = LONG_MAX,
@@ -1305,11 +1311,11 @@ int write_inode_now(struct inode *inode, int sync)
 		wbc.nr_to_write = 0;
 
 	might_sleep();
-	spin_lock(&inode_wb_list_lock);
+	spin_lock(&wb->list_lock);
 	spin_lock(&inode->i_lock);
-	ret = writeback_single_inode(inode, &wbc);
+	ret = writeback_single_inode(inode, wb, &wbc);
 	spin_unlock(&inode->i_lock);
-	spin_unlock(&inode_wb_list_lock);
+	spin_unlock(&wb->list_lock);
 	if (sync)
 		inode_sync_wait(inode);
 	return ret;
@@ -1329,13 +1335,14 @@ EXPORT_SYMBOL(write_inode_now);
  */
 int sync_inode(struct inode *inode, struct writeback_control *wbc)
 {
+	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 	int ret;
 
-	spin_lock(&inode_wb_list_lock);
+	spin_lock(&wb->list_lock);
 	spin_lock(&inode->i_lock);
-	ret = writeback_single_inode(inode, wbc);
+	ret = writeback_single_inode(inode, wb, wbc);
 	spin_unlock(&inode->i_lock);
-	spin_unlock(&inode_wb_list_lock);
+	spin_unlock(&wb->list_lock);
 	return ret;
 }
 EXPORT_SYMBOL(sync_inode);
diff --git a/fs/inode.c b/fs/inode.c
index e195ff89fb58..a1c36fc442e0 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -37,7 +37,7 @@
  *   inode_lru, inode->i_lru
  * inode_sb_list_lock protects:
  *   sb->s_inodes, inode->i_sb_list
- * inode_wb_list_lock protects:
+ * bdi->wb.list_lock protects:
  *   bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list
  * inode_hash_lock protects:
  *   inode_hashtable, inode->i_hash
@@ -48,7 +48,7 @@
  *   inode->i_lock
  *     inode_lru_lock
  *
- * inode_wb_list_lock
+ * bdi->wb.list_lock
  *   inode->i_lock
  *
  * inode_hash_lock
@@ -68,7 +68,6 @@ static LIST_HEAD(inode_lru);
 static DEFINE_SPINLOCK(inode_lru_lock);
 
 __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
-__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_wb_list_lock);
 
 /*
  * iprune_sem provides exclusion between the icache shrinking and the
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 574ec0e86fbd..44a9a979788b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1582,8 +1582,7 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 		int status;
 		bool sync = true;
 
-		if (wbc->sync_mode == WB_SYNC_NONE || wbc->nonblocking ||
-		    wbc->for_background)
+		if (wbc->sync_mode == WB_SYNC_NONE)
 			sync = false;
 
 		status = pnfs_layoutcommit_inode(inode, sync);
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 79ce38be15a1..7559861481aa 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -970,7 +970,7 @@ xfs_vm_writepage(
 	offset = page_offset(page);
 	type = IO_OVERWRITE;
 
-	if (wbc->sync_mode == WB_SYNC_NONE && wbc->nonblocking)
+	if (wbc->sync_mode == WB_SYNC_NONE)
 		nonblocking = 1;
 
 	do {
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 96f4094b706d..47feb2c4706a 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -57,6 +57,7 @@ struct bdi_writeback {
 	struct list_head b_dirty;	/* dirty inodes */
 	struct list_head b_io;		/* parked for writeback */
 	struct list_head b_more_io;	/* parked for more writeback */
+	spinlock_t list_lock;		/* protects the b_* lists */
 };
 
 struct backing_dev_info {
@@ -106,6 +107,7 @@ int bdi_writeback_thread(void *data);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
 void bdi_arm_supers_timer(void);
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
+void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2);
 
 extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 17e7ccc322a5..2f1b512bd6e0 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -9,8 +9,6 @@
 
 struct backing_dev_info;
 
-extern spinlock_t inode_wb_list_lock;
-
 /*
  * fs/fs-writeback.c
  */
@@ -28,12 +26,10 @@ struct writeback_control {
 	enum writeback_sync_modes sync_mode;
 	unsigned long *older_than_this;	/* If !NULL, only write back inodes
 					   older than this */
-	unsigned long wb_start;         /* Time writeback_inodes_wb was
-					   called. This is needed to avoid
-					   extra jobs and livelock */
 	long nr_to_write;		/* Write this many pages, and decrement
 					   this for each page written */
 	long pages_skipped;		/* Pages which were not written */
+	long inodes_written;		/* # of inodes written (at least) */
 
 	/*
 	 * For a_ops->writepages(): is start or end are non-zero then this is
@@ -43,13 +39,11 @@ struct writeback_control {
 	loff_t range_start;
 	loff_t range_end;
 
-	unsigned nonblocking:1;		/* Don't get stuck on request queues */
-	unsigned encountered_congestion:1; /* An output: a queue is full */
 	unsigned for_kupdate:1;		/* A kupdate writeback */
 	unsigned for_background:1;	/* A background writeback */
+	unsigned tagged_writepages:1;	/* tag-and-write to avoid livelock */
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
-	unsigned more_io:1;		/* more io to be dispatched */
 };
 
 /*
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 4114129f0794..b31702ac15be 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -284,7 +284,6 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 		__field(	long,   pages_skipped		)
 		__field(	loff_t, range_start		)
 		__field(	loff_t, range_end		)
-		__field(	char,   nonblocking		)
 		__field(	char,   for_kupdate		)
 		__field(	char,   for_reclaim		)
 		__field(	char,   range_cyclic		)
@@ -299,7 +298,6 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 		__entry->pages_skipped	= wbc->pages_skipped;
 		__entry->range_start	= wbc->range_start;
 		__entry->range_end	= wbc->range_end;
-		__entry->nonblocking	= wbc->nonblocking;
 		__entry->for_kupdate	= wbc->for_kupdate;
 		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
@@ -310,13 +308,13 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 
 	TP_printk("root = %llu(%s), ino = %lu, page_index = %lu, "
 		  "nr_to_write = %ld, pages_skipped = %ld, range_start = %llu, "
-		  "range_end = %llu, nonblocking = %d, for_kupdate = %d, "
+		  "range_end = %llu, for_kupdate = %d, "
 		  "for_reclaim = %d, range_cyclic = %d, writeback_index = %lu",
 		  show_root_type(__entry->root_objectid),
 		  (unsigned long)__entry->ino, __entry->index,
 		  __entry->nr_to_write, __entry->pages_skipped,
 		  __entry->range_start, __entry->range_end,
-		  __entry->nonblocking, __entry->for_kupdate,
+		  __entry->for_kupdate,
 		  __entry->for_reclaim, __entry->range_cyclic,
 		  (unsigned long)__entry->writeback_index)
 );
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 5ce2b2f5f524..6363193a3418 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -380,7 +380,6 @@ TRACE_EVENT(ext4_da_writepages_result,
 		__field(	int,	pages_written		)
 		__field(	long,	pages_skipped		)
 		__field(	int,	sync_mode		)
-		__field(	char,	more_io			)	
 		__field(       pgoff_t,	writeback_index		)
 	),
 
@@ -391,16 +390,15 @@ TRACE_EVENT(ext4_da_writepages_result,
 		__entry->pages_written	= pages_written;
 		__entry->pages_skipped	= wbc->pages_skipped;
 		__entry->sync_mode	= wbc->sync_mode;
-		__entry->more_io	= wbc->more_io;
 		__entry->writeback_index = inode->i_mapping->writeback_index;
 	),
 
 	TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld "
-		  " more_io %d sync_mode %d writeback_index %lu",
+		  "sync_mode %d writeback_index %lu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino, __entry->ret,
 		  __entry->pages_written, __entry->pages_skipped,
-		  __entry->more_io, __entry->sync_mode,
+		  __entry->sync_mode,
 		  (unsigned long) __entry->writeback_index)
 );
 
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 4e249b927eaa..205d14919ef2 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -8,6 +8,19 @@
 #include <linux/device.h>
 #include <linux/writeback.h>
 
+#define show_inode_state(state)					\
+	__print_flags(state, "|",				\
+		{I_DIRTY_SYNC,		"I_DIRTY_SYNC"},	\
+		{I_DIRTY_DATASYNC,	"I_DIRTY_DATASYNC"},	\
+		{I_DIRTY_PAGES,		"I_DIRTY_PAGES"},	\
+		{I_NEW,			"I_NEW"},		\
+		{I_WILL_FREE,		"I_WILL_FREE"},		\
+		{I_FREEING,		"I_FREEING"},		\
+		{I_CLEAR,		"I_CLEAR"},		\
+		{I_SYNC,		"I_SYNC"},		\
+		{I_REFERENCED,		"I_REFERENCED"}		\
+	)
+
 struct wb_writeback_work;
 
 DECLARE_EVENT_CLASS(writeback_work_class,
@@ -101,7 +114,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__field(int, for_background)
 		__field(int, for_reclaim)
 		__field(int, range_cyclic)
-		__field(int, more_io)
 		__field(unsigned long, older_than_this)
 		__field(long, range_start)
 		__field(long, range_end)
@@ -116,7 +128,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->for_background	= wbc->for_background;
 		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
-		__entry->more_io	= wbc->more_io;
 		__entry->older_than_this = wbc->older_than_this ?
 						*wbc->older_than_this : 0;
 		__entry->range_start	= (long)wbc->range_start;
@@ -124,7 +135,7 @@ DECLARE_EVENT_CLASS(wbc_class,
 	),
 
 	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
-		"bgrd=%d reclm=%d cyclic=%d more=%d older=0x%lx "
+		"bgrd=%d reclm=%d cyclic=%d older=0x%lx "
 		"start=0x%lx end=0x%lx",
 		__entry->name,
 		__entry->nr_to_write,
@@ -134,7 +145,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->for_background,
 		__entry->for_reclaim,
 		__entry->range_cyclic,
-		__entry->more_io,
 		__entry->older_than_this,
 		__entry->range_start,
 		__entry->range_end)
@@ -152,6 +162,31 @@ DEFINE_WBC_EVENT(wbc_balance_dirty_written);
 DEFINE_WBC_EVENT(wbc_balance_dirty_wait);
 DEFINE_WBC_EVENT(wbc_writepage);
 
+TRACE_EVENT(writeback_queue_io,
+	TP_PROTO(struct bdi_writeback *wb,
+		 unsigned long *older_than_this,
+		 int moved),
+	TP_ARGS(wb, older_than_this, moved),
+	TP_STRUCT__entry(
+		__array(char,		name, 32)
+		__field(unsigned long,	older)
+		__field(long,		age)
+		__field(int,		moved)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
+		__entry->older	= older_than_this ?  *older_than_this : 0;
+		__entry->age	= older_than_this ?
+				  (jiffies - *older_than_this) * 1000 / HZ : -1;
+		__entry->moved	= moved;
+	),
+	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d",
+		__entry->name,
+		__entry->older,	/* older_than_this in jiffies */
+		__entry->age,	/* older_than_this in relative milliseconds */
+		__entry->moved)
+);
+
 DECLARE_EVENT_CLASS(writeback_congest_waited_template,
 
 	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),
@@ -187,6 +222,63 @@ DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested,
 	TP_ARGS(usec_timeout, usec_delayed)
 );
 
+DECLARE_EVENT_CLASS(writeback_single_inode_template,
+
+	TP_PROTO(struct inode *inode,
+		 struct writeback_control *wbc,
+		 unsigned long nr_to_write
+	),
+
+	TP_ARGS(inode, wbc, nr_to_write),
+
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(unsigned long, ino)
+		__field(unsigned long, state)
+		__field(unsigned long, age)
+		__field(unsigned long, writeback_index)
+		__field(long, nr_to_write)
+		__field(unsigned long, wrote)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name,
+			dev_name(inode->i_mapping->backing_dev_info->dev), 32);
+		__entry->ino		= inode->i_ino;
+		__entry->state		= inode->i_state;
+		__entry->age		= (jiffies - inode->dirtied_when) *
+								1000 / HZ;
+		__entry->writeback_index = inode->i_mapping->writeback_index;
+		__entry->nr_to_write	= nr_to_write;
+		__entry->wrote		= nr_to_write - wbc->nr_to_write;
+	),
+
+	TP_printk("bdi %s: ino=%lu state=%s age=%lu "
+		  "index=%lu to_write=%ld wrote=%lu",
+		  __entry->name,
+		  __entry->ino,
+		  show_inode_state(__entry->state),
+		  __entry->age,
+		  __entry->writeback_index,
+		  __entry->nr_to_write,
+		  __entry->wrote
+	)
+);
+
+DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_requeue,
+	TP_PROTO(struct inode *inode,
+		 struct writeback_control *wbc,
+		 unsigned long nr_to_write),
+	TP_ARGS(inode, wbc, nr_to_write)
+);
+
+DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode,
+	TP_PROTO(struct inode *inode,
+		 struct writeback_control *wbc,
+		 unsigned long nr_to_write),
+	TP_ARGS(inode, wbc, nr_to_write)
+);
+
 #endif /* _TRACE_WRITEBACK_H */
 
 /* This part must be outside protection */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f032e6e1e09a..5f6553ef1ba7 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -45,6 +45,17 @@ static struct timer_list sync_supers_timer;
 static int bdi_sync_supers(void *);
 static void sync_supers_timer_fn(unsigned long);
 
+void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+{
+	if (wb1 < wb2) {
+		spin_lock(&wb1->list_lock);
+		spin_lock_nested(&wb2->list_lock, 1);
+	} else {
+		spin_lock(&wb2->list_lock);
+		spin_lock_nested(&wb1->list_lock, 1);
+	}
+}
+
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -67,14 +78,14 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 	struct inode *inode;
 
 	nr_dirty = nr_io = nr_more_io = 0;
-	spin_lock(&inode_wb_list_lock);
+	spin_lock(&wb->list_lock);
 	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
 		nr_dirty++;
 	list_for_each_entry(inode, &wb->b_io, i_wb_list)
 		nr_io++;
 	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
 		nr_more_io++;
-	spin_unlock(&inode_wb_list_lock);
+	spin_unlock(&wb->list_lock);
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);
 	bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
@@ -628,6 +639,7 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&wb->b_dirty);
 	INIT_LIST_HEAD(&wb->b_io);
 	INIT_LIST_HEAD(&wb->b_more_io);
+	spin_lock_init(&wb->list_lock);
 	setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
 }
 
@@ -676,11 +688,12 @@ void bdi_destroy(struct backing_dev_info *bdi)
 	if (bdi_has_dirty_io(bdi)) {
 		struct bdi_writeback *dst = &default_backing_dev_info.wb;
 
-		spin_lock(&inode_wb_list_lock);
+		bdi_lock_two(&bdi->wb, dst);
 		list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
 		list_splice(&bdi->wb.b_io, &dst->b_io);
 		list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
-		spin_unlock(&inode_wb_list_lock);
+		spin_unlock(&bdi->wb.list_lock);
+		spin_unlock(&dst->list_lock);
 	}
 
 	bdi_unregister(bdi);
diff --git a/mm/filemap.c b/mm/filemap.c
index cfac89d95ec1..2a2f5e8880ae 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -81,7 +81,7 @@
  *  ->i_mutex
  *    ->i_alloc_sem             (various)
  *
- *  inode_wb_list_lock
+ *  bdi->wb.list_lock
  *    sb_lock			(fs/fs-writeback.c)
  *    ->mapping->tree_lock	(__sync_single_inode)
  *
@@ -99,9 +99,9 @@
  *    ->zone.lru_lock		(check_pte_range->isolate_lru_page)
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->tree_lock		(page_remove_rmap->set_page_dirty)
- *    inode_wb_list_lock	(page_remove_rmap->set_page_dirty)
+ *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
  *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
- *    inode_wb_list_lock	(zap_pte_range->set_page_dirty)
+ *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 31f698862420..b2529f8f8be0 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -244,13 +244,8 @@ void task_dirty_inc(struct task_struct *tsk)
 static void bdi_writeout_fraction(struct backing_dev_info *bdi,
 		long *numerator, long *denominator)
 {
-	if (bdi_cap_writeback_dirty(bdi)) {
-		prop_fraction_percpu(&vm_completions, &bdi->completions,
+	prop_fraction_percpu(&vm_completions, &bdi->completions,
 				numerator, denominator);
-	} else {
-		*numerator = 0;
-		*denominator = 1;
-	}
 }
 
 static inline void task_dirties_fraction(struct task_struct *tsk,
@@ -437,10 +432,17 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
 	*pdirty = dirty;
 }
 
-/*
+/**
  * bdi_dirty_limit - @bdi's share of dirty throttling threshold
+ * @bdi: the backing_dev_info to query
+ * @dirty: global dirty limit in pages
  *
- * Allocate high/low dirty limits to fast/slow devices, in order to prevent
+ * Returns @bdi's dirty limit in pages. The term "dirty" in the context of
+ * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages.
+ * And the "limit" in the name is not seriously taken as hard limit in
+ * balance_dirty_pages().
+ *
+ * It allocates high/low dirty limits to fast/slow devices, in order to prevent
  * - starving fast devices
  * - piling up dirty pages (that will take long time to sync) on slow devices
  *
@@ -488,6 +490,9 @@ static void balance_dirty_pages(struct address_space *mapping,
 	bool dirty_exceeded = false;
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 
+	if (!bdi_cap_account_dirty(bdi))
+		return;
+
 	for (;;) {
 		struct writeback_control wbc = {
 			.sync_mode	= WB_SYNC_NONE,
@@ -892,12 +897,12 @@ int write_cache_pages(struct address_space *mapping,
 			range_whole = 1;
 		cycled = 1; /* ignore range_cyclic tests */
 	}
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag = PAGECACHE_TAG_TOWRITE;
 	else
 		tag = PAGECACHE_TAG_DIRTY;
 retry:
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag_pages_for_writeback(mapping, index, end);
 	done_index = index;
 	while (!done && (index <= end)) {
diff --git a/mm/rmap.c b/mm/rmap.c
index 23295f65ae43..67528a2661b8 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -32,11 +32,11 @@
  *               mmlist_lock (in mmput, drain_mmlist and others)
  *               mapping->private_lock (in __set_page_dirty_buffers)
  *               inode->i_lock (in set_page_dirty's __mark_inode_dirty)
- *               inode_wb_list_lock (in set_page_dirty's __mark_inode_dirty)
+ *               bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
  *                 sb_lock (within inode_lock in fs/fs-writeback.c)
  *                 mapping->tree_lock (widely used, in set_page_dirty,
  *                           in arch-dependent flush_dcache_mmap_lock,
- *                           within inode_wb_list_lock in __sync_single_inode)
+ *                           within bdi.wb->list_lock in __sync_single_inode)
  *
  * anon_vma->mutex,mapping->i_mutex      (memory_failure, collect_procs_anon)
  *   ->tasklist_lock