Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/writeback

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/writeback: (27 commits)
  mm: properly reflect task dirty limits in dirty_exceeded logic
  writeback: don't busy retry writeback on new/freeing inodes
  writeback: scale IO chunk size up to half device bandwidth
  writeback: trace global_dirty_state
  writeback: introduce max-pause and pass-good dirty limits
  writeback: introduce smoothed global dirty limit
  writeback: consolidate variable names in balance_dirty_pages()
  writeback: show bdi write bandwidth in debugfs
  writeback: bdi write bandwidth estimation
  writeback: account per-bdi accumulated written pages
  writeback: make writeback_control.nr_to_write straight
  writeback: skip tmpfs early in balance_dirty_pages_ratelimited_nr()
  writeback: trace event writeback_queue_io
  writeback: trace event writeback_single_inode
  writeback: remove .nonblocking and .encountered_congestion
  writeback: remove writeback_control.more_io
  writeback: skip balance_dirty_pages() for in-memory fs
  writeback: add bdi_dirty_limit() kernel-doc
  writeback: avoid extra sync work at enqueue time
  writeback: elevate queue_io() into wb_writeback()
  ...

Fix up trivial conflicts in fs/fs-writeback.c and mm/filemap.c

6 files changed, 223 insertions, 180 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index c62fb84944d5..f55aad4d1611 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/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 7055d11c1efd..561262d35689 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2551,7 +2551,6 @@ int extent_write_full_page(struct extent_io_tree *tree, struct page *page,
 	};
 	struct writeback_control wbc_writepages = {
 		.sync_mode	= wbc->sync_mode,
-		.older_than_this = NULL,
 		.nr_to_write	= 64,
 		.range_start	= page_offset(page) + PAGE_CACHE_SIZE,
 		.range_end	= (loff_t)-1,
@@ -2584,7 +2583,6 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
 	};
 	struct writeback_control wbc_writepages = {
 		.sync_mode	= mode,
-		.older_than_this = NULL,
 		.nr_to_write	= nr_pages * 2,
 		.range_start	= start,
 		.range_end	= end + 1,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 678cde834f19..3e5191f9f398 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 b8c507ca42f7..1599aa985fe2 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -35,7 +35,9 @@
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
+	unsigned long *older_than_this;
 	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 +182,13 @@ 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 +198,9 @@ 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 +214,9 @@ 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 +224,7 @@ 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 +249,16 @@ 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 +269,13 @@ 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 +287,8 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 				list_move(&inode->i_wb_list, dispatch_queue);
 		}
 	}
+out:
+	return moved;
 }
 
 /*
@@ -301,9 +304,11 @@ 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 +321,8 @@ 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 +330,15 @@ 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 +349,15 @@ 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 +375,16 @@ 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 +393,7 @@ 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 +424,19 @@ 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 +447,7 @@ 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 +456,7 @@ 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 +465,7 @@ 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
@@ -457,9 +476,41 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 		}
 	}
 	inode_sync_complete(inode);
+	trace_writeback_single_inode(inode, wbc, nr_to_write);
 	return ret;
 }
 
+static long writeback_chunk_size(struct backing_dev_info *bdi,
+				 struct wb_writeback_work *work)
+{
+	long pages;
+
+	/*
+	 * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
+	 * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
+	 * here avoids calling into writeback_inodes_wb() more than once.
+	 *
+	 * The intended call sequence for WB_SYNC_ALL writeback is:
+	 *
+	 *      wb_writeback()
+	 *          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 (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages)
+		pages = LONG_MAX;
+	else {
+		pages = min(bdi->avg_write_bandwidth / 2,
+			    global_dirty_limit / DIRTY_SCOPE);
+		pages = min(pages, work->nr_pages);
+		pages = round_down(pages + MIN_WRITEBACK_PAGES,
+				   MIN_WRITEBACK_PAGES);
+	}
+
+	return pages;
+}
+
 /*
  * Write a portion of b_io inodes which belong to @sb.
  *
@@ -467,24 +518,36 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
  * inodes. Otherwise write only ones which go sequentially
  * in reverse order.
  *
- * Return 1, if the caller writeback routine should be
- * interrupted. Otherwise return 0.
+ * Return the number of pages and/or inodes written.
  */
-static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
-		struct writeback_control *wbc, bool only_this_sb)
+static long writeback_sb_inodes(struct super_block *sb,
+				struct bdi_writeback *wb,
+				struct wb_writeback_work *work)
 {
+	struct writeback_control wbc = {
+		.sync_mode		= work->sync_mode,
+		.tagged_writepages	= work->tagged_writepages,
+		.for_kupdate		= work->for_kupdate,
+		.for_background		= work->for_background,
+		.range_cyclic		= work->range_cyclic,
+		.range_start		= 0,
+		.range_end		= LLONG_MAX,
+	};
+	unsigned long start_time = jiffies;
+	long write_chunk;
+	long wrote = 0;  /* count both pages and inodes */
+
 	while (!list_empty(&wb->b_io)) {
-		long pages_skipped;
 		struct inode *inode = wb_inode(wb->b_io.prev);
 
 		if (inode->i_sb != sb) {
-			if (only_this_sb) {
+			if (work->sb) {
 				/*
 				 * We only want to write back data for this
 				 * superblock, move all inodes not belonging
 				 * to it back onto the dirty list.
 				 */
-				redirty_tail(inode);
+				redirty_tail(inode, wb);
 				continue;
 			}
 
@@ -493,7 +556,7 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 			 * Bounce back to the caller to unpin this and
 			 * pin the next superblock.
 			 */
-			return 0;
+			break;
 		}
 
 		/*
@@ -504,95 +567,91 @@ 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);
+			redirty_tail(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);
+		write_chunk = writeback_chunk_size(wb->bdi, work);
+		wbc.nr_to_write = write_chunk;
+		wbc.pages_skipped = 0;
 
-		pages_skipped = wbc->pages_skipped;
-		writeback_single_inode(inode, wbc);
-		if (wbc->pages_skipped != pages_skipped) {
+		writeback_single_inode(inode, wb, &wbc);
+
+		work->nr_pages -= write_chunk - wbc.nr_to_write;
+		wrote += write_chunk - wbc.nr_to_write;
+		if (!(inode->i_state & I_DIRTY))
+			wrote++;
+		if (wbc.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;
-			return 1;
+		spin_lock(&wb->list_lock);
+		/*
+		 * bail out to wb_writeback() often enough to check
+		 * background threshold and other termination conditions.
+		 */
+		if (wrote) {
+			if (time_is_before_jiffies(start_time + HZ / 10UL))
+				break;
+			if (work->nr_pages <= 0)
+				break;
 		}
-		if (!list_empty(&wb->b_more_io))
-			wbc->more_io = 1;
 	}
-	/* b_io is empty */
-	return 1;
+	return wrote;
 }
 
-void writeback_inodes_wb(struct bdi_writeback *wb,
-		struct writeback_control *wbc)
+static long __writeback_inodes_wb(struct bdi_writeback *wb,
+				  struct wb_writeback_work *work)
 {
-	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);
+	unsigned long start_time = jiffies;
+	long wrote = 0;
 
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
 		struct super_block *sb = inode->i_sb;
 
 		if (!grab_super_passive(sb)) {
-			requeue_io(inode);
+			requeue_io(inode, wb);
 			continue;
 		}
-		ret = writeback_sb_inodes(sb, wb, wbc, false);
+		wrote += writeback_sb_inodes(sb, wb, work);
 		drop_super(sb);
 
-		if (ret)
-			break;
+		/* refer to the same tests at the end of writeback_sb_inodes */
+		if (wrote) {
+			if (time_is_before_jiffies(start_time + HZ / 10UL))
+				break;
+			if (work->nr_pages <= 0)
+				break;
+		}
 	}
-	spin_unlock(&inode_wb_list_lock);
 	/* Leave any unwritten inodes on b_io */
+	return wrote;
 }
 
-static void __writeback_inodes_sb(struct super_block *sb,
-		struct bdi_writeback *wb, struct writeback_control *wbc)
+long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages)
 {
-	WARN_ON(!rwsem_is_locked(&sb->s_umount));
+	struct wb_writeback_work work = {
+		.nr_pages	= nr_pages,
+		.sync_mode	= WB_SYNC_NONE,
+		.range_cyclic	= 1,
+	};
 
-	spin_lock(&inode_wb_list_lock);
-	if (!wbc->for_kupdate || 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);
-}
+	spin_lock(&wb->list_lock);
+	if (list_empty(&wb->b_io))
+		queue_io(wb, NULL);
+	__writeback_inodes_wb(wb, &work);
+	spin_unlock(&wb->list_lock);
 
-/*
- * The maximum number of pages to writeout in a single bdi flush/kupdate
- * operation.  We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode.  Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES     1024
+	return nr_pages - work.nr_pages;
+}
 
 static inline bool over_bground_thresh(void)
 {
@@ -605,6 +664,16 @@ static inline bool over_bground_thresh(void)
 }
 
 /*
+ * Called under wb->list_lock. If there are multiple wb per bdi,
+ * only the flusher working on the first wb should do it.
+ */
+static void wb_update_bandwidth(struct bdi_writeback *wb,
+				unsigned long start_time)
+{
+	__bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, start_time);
+}
+
+/*
  * Explicit flushing or periodic writeback of "old" data.
  *
  * Define "old": the first time one of an inode's pages is dirtied, we mark the
@@ -622,47 +691,16 @@ static inline bool over_bground_thresh(void)
 static long wb_writeback(struct bdi_writeback *wb,
 			 struct wb_writeback_work *work)
 {
-	struct writeback_control wbc = {
-		.sync_mode		= work->sync_mode,
-		.older_than_this	= NULL,
-		.for_kupdate		= work->for_kupdate,
-		.for_background		= work->for_background,
-		.range_cyclic		= work->range_cyclic,
-	};
+	unsigned long wb_start = jiffies;
+	long nr_pages = work->nr_pages;
 	unsigned long oldest_jif;
-	long wrote = 0;
-	long write_chunk;
 	struct inode *inode;
+	long progress;
 
-	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;
-	}
+	oldest_jif = jiffies;
+	work->older_than_this = &oldest_jif;
 
-	/*
-	 * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
-	 * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
-	 * here avoids calling into writeback_inodes_wb() more than once.
-	 *
-	 * The intended call sequence for WB_SYNC_ALL writeback is:
-	 *
-	 *      wb_writeback()
-	 *          __writeback_inodes_sb()     <== 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
-		write_chunk = LONG_MAX;
-
-	wbc.wb_start = jiffies; /* livelock avoidance */
+	spin_lock(&wb->list_lock);
 	for (;;) {
 		/*
 		 * Stop writeback when nr_pages has been consumed
@@ -687,52 +725,54 @@ static long wb_writeback(struct bdi_writeback *wb,
 		if (work->for_background && !over_bground_thresh())
 			break;
 
-		wbc.more_io = 0;
-		wbc.nr_to_write = write_chunk;
-		wbc.pages_skipped = 0;
+		if (work->for_kupdate) {
+			oldest_jif = jiffies -
+				msecs_to_jiffies(dirty_expire_interval * 10);
+			work->older_than_this = &oldest_jif;
+		}
 
-		trace_wbc_writeback_start(&wbc, wb->bdi);
+		trace_writeback_start(wb->bdi, work);
+		if (list_empty(&wb->b_io))
+			queue_io(wb, work->older_than_this);
 		if (work->sb)
-			__writeback_inodes_sb(work->sb, wb, &wbc);
+			progress = writeback_sb_inodes(work->sb, wb, work);
 		else
-			writeback_inodes_wb(wb, &wbc);
-		trace_wbc_writeback_written(&wbc, wb->bdi);
+			progress = __writeback_inodes_wb(wb, work);
+		trace_writeback_written(wb->bdi, work);
 
-		work->nr_pages -= write_chunk - wbc.nr_to_write;
-		wrote += write_chunk - wbc.nr_to_write;
+		wb_update_bandwidth(wb, wb_start);
 
 		/*
-		 * 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 (progress)
 			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))  {
+			trace_writeback_wait(wb->bdi, work);
 			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;
+	return nr_pages - work->nr_pages;
 }
 
 /*
@@ -1063,10 +1103,10 @@ 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);
@@ -1162,10 +1202,11 @@ 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));
@@ -1267,6 +1308,7 @@ 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,
@@ -1279,11 +1321,11 @@ 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;
@@ -1303,13 +1345,14 @@ 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 96c77b81167c..a48fa5355fb4 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -37,7 +37,7 @@
  *   inode->i_sb->s_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->i_sb->s_inode_lru_lock
  *
- * inode_wb_list_lock
+ * bdi->wb.list_lock
  *   inode->i_lock
  *
  * inode_hash_lock
@@ -65,7 +65,6 @@ static struct hlist_head *inode_hashtable __read_mostly;
 static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
 
 __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
-__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_wb_list_lock);
 
 /*
  * Empty aops. Can be used for the cases where the user does not
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 08579312c57b..00e37501fa3b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1566,8 +1566,7 @@ 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);