1 files changed, 249 insertions, 148 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index d5be1693ac93..3d06ccc953aa 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -26,15 +26,9 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
+#include <linux/tracepoint.h>
 #include "internal.h"
 
-#define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)
-
-/*
- * We don't actually have pdflush, but this one is exported though /proc...
- */
-int nr_pdflush_threads;
-
 /*
  * Passed into wb_writeback(), essentially a subset of writeback_control
  */
@@ -50,6 +44,19 @@ struct wb_writeback_work {
 	struct completion *done;	/* set if the caller waits */
 };
 
+/*
+ * Include the creation of the trace points after defining the
+ * wb_writeback_work structure so that the definition remains local to this
+ * file.
+ */
+#define CREATE_TRACE_POINTS
+#include <trace/events/writeback.h>
+
+/*
+ * We don't actually have pdflush, but this one is exported though /proc...
+ */
+int nr_pdflush_threads;
+
 /**
  * writeback_in_progress - determine whether there is writeback in progress
  * @bdi: the device's backing_dev_info structure.
@@ -59,28 +66,42 @@ struct wb_writeback_work {
  */
 int writeback_in_progress(struct backing_dev_info *bdi)
 {
-	return !list_empty(&bdi->work_list);
+	return test_bit(BDI_writeback_running, &bdi->state);
+}
+
+static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+
+	if (strcmp(sb->s_type->name, "bdev") == 0)
+		return inode->i_mapping->backing_dev_info;
+
+	return sb->s_bdi;
+}
+
+static inline struct inode *wb_inode(struct list_head *head)
+{
+	return list_entry(head, struct inode, i_wb_list);
 }
 
 static void bdi_queue_work(struct backing_dev_info *bdi,
 		struct wb_writeback_work *work)
 {
-	spin_lock(&bdi->wb_lock);
-	list_add_tail(&work->list, &bdi->work_list);
-	spin_unlock(&bdi->wb_lock);
+	trace_writeback_queue(bdi, work);
 
-	/*
-	 * If the default thread isn't there, make sure we add it. When
-	 * it gets created and wakes up, we'll run this work.
-	 */
-	if (unlikely(list_empty_careful(&bdi->wb_list)))
+	spin_lock_bh(&bdi->wb_lock);
+	list_add_tail(&work->list, &bdi->work_list);
+	if (bdi->wb.task) {
+		wake_up_process(bdi->wb.task);
+	} else {
+		/*
+		 * The bdi thread isn't there, wake up the forker thread which
+		 * will create and run it.
+		 */
+		trace_writeback_nothread(bdi, work);
 		wake_up_process(default_backing_dev_info.wb.task);
-	else {
-		struct bdi_writeback *wb = &bdi->wb;
-
-		if (wb->task)
-			wake_up_process(wb->task);
 	}
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
@@ -95,8 +116,10 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	 */
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
-		if (bdi->wb.task)
+		if (bdi->wb.task) {
+			trace_writeback_nowork(bdi);
 			wake_up_process(bdi->wb.task);
+		}
 		return;
 	}
 
@@ -154,11 +177,11 @@ static void redirty_tail(struct inode *inode)
 	if (!list_empty(&wb->b_dirty)) {
 		struct inode *tail;
 
-		tail = list_entry(wb->b_dirty.next, struct inode, i_list);
+		tail = wb_inode(wb->b_dirty.next);
 		if (time_before(inode->dirtied_when, tail->dirtied_when))
 			inode->dirtied_when = jiffies;
 	}
-	list_move(&inode->i_list, &wb->b_dirty);
+	list_move(&inode->i_wb_list, &wb->b_dirty);
 }
 
 /*
@@ -168,7 +191,7 @@ static void requeue_io(struct inode *inode)
 {
 	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 
-	list_move(&inode->i_list, &wb->b_more_io);
+	list_move(&inode->i_wb_list, &wb->b_more_io);
 }
 
 static void inode_sync_complete(struct inode *inode)
@@ -209,14 +232,14 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 
 	while (!list_empty(delaying_queue)) {
-		inode = list_entry(delaying_queue->prev, struct inode, i_list);
+		inode = wb_inode(delaying_queue->prev);
 		if (older_than_this &&
 		    inode_dirtied_after(inode, *older_than_this))
 			break;
 		if (sb && sb != inode->i_sb)
 			do_sb_sort = 1;
 		sb = inode->i_sb;
-		list_move(&inode->i_list, &tmp);
+		list_move(&inode->i_wb_list, &tmp);
 	}
 
 	/* just one sb in list, splice to dispatch_queue and we're done */
@@ -227,22 +250,29 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 
 	/* Move inodes from one superblock together */
 	while (!list_empty(&tmp)) {
-		inode = list_entry(tmp.prev, struct inode, i_list);
-		sb = inode->i_sb;
+		sb = wb_inode(tmp.prev)->i_sb;
 		list_for_each_prev_safe(pos, node, &tmp) {
-			inode = list_entry(pos, struct inode, i_list);
+			inode = wb_inode(pos);
 			if (inode->i_sb == sb)
-				list_move(&inode->i_list, dispatch_queue);
+				list_move(&inode->i_wb_list, dispatch_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);
 }
 
@@ -352,73 +382,43 @@ 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 | I_CLEAR))) {
-		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 (!(inode->i_state & I_FREEING)) {
+		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 (atomic_read(&inode->i_count)) {
+		} else if (inode->i_state & I_DIRTY) {
 			/*
-			 * The inode is clean, inuse
+			 * Filesystems can dirty the inode during writeback
+			 * operations, such as delayed allocation during
+			 * submission or metadata updates after data IO
+			 * completion.
 			 */
-			list_move(&inode->i_list, &inode_in_use);
+			redirty_tail(inode);
 		} else {
 			/*
-			 * The inode is clean, unused
+			 * The inode is clean.  At this point we either have
+			 * a reference to the inode or it's on it's way out.
+			 * No need to add it back to the LRU.
 			 */
-			list_move(&inode->i_list, &inode_unused);
+			list_del_init(&inode->i_wb_list);
 		}
 	}
 	inode_sync_complete(inode);
@@ -466,8 +466,7 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 {
 	while (!list_empty(&wb->b_io)) {
 		long pages_skipped;
-		struct inode *inode = list_entry(wb->b_io.prev,
-						 struct inode, i_list);
+		struct inode *inode = wb_inode(wb->b_io.prev);
 
 		if (inode->i_sb != sb) {
 			if (only_this_sb) {
@@ -488,10 +487,16 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 			return 0;
 		}
 
-		if (inode->i_state & (I_NEW | I_WILL_FREE)) {
+		/*
+		 * Don't bother with new inodes or inodes beeing freed, first
+		 * kind does not need peridic writeout yet, and for the latter
+		 * kind writeout is handled by the freer.
+		 */
+		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
 			requeue_io(inode);
 			continue;
 		}
+
 		/*
 		 * Was this inode dirtied after sync_sb_inodes was called?
 		 * This keeps sync from extra jobs and livelock.
@@ -499,7 +504,6 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 		if (inode_dirtied_after(inode, wbc->wb_start))
 			return 1;
 
-		BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
 		__iget(inode);
 		pages_skipped = wbc->pages_skipped;
 		writeback_single_inode(inode, wbc);
@@ -530,14 +534,14 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
 {
 	int ret = 0;
 
-	wbc->wb_start = jiffies; /* livelock avoidance */
+	if (!wbc->wb_start)
+		wbc->wb_start = jiffies; /* livelock avoidance */
 	spin_lock(&inode_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 = list_entry(wb->b_io.prev,
-						 struct inode, i_list);
+		struct inode *inode = wb_inode(wb->b_io.prev);
 		struct super_block *sb = inode->i_sb;
 
 		if (!pin_sb_for_writeback(sb)) {
@@ -559,7 +563,6 @@ static void __writeback_inodes_sb(struct super_block *sb,
 {
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
-	wbc->wb_start = jiffies; /* livelock avoidance */
 	spin_lock(&inode_lock);
 	if (!wbc->for_kupdate || list_empty(&wb->b_io))
 		queue_io(wb, wbc->older_than_this);
@@ -580,10 +583,10 @@ 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);
+		global_page_state(NR_UNSTABLE_NFS) > background_thresh);
 }
 
 /*
@@ -625,6 +628,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		wbc.range_end = LLONG_MAX;
 	}
 
+	wbc.wb_start = jiffies; /* livelock avoidance */
 	for (;;) {
 		/*
 		 * Stop writeback when nr_pages has been consumed
@@ -642,10 +646,14 @@ static long wb_writeback(struct bdi_writeback *wb,
 		wbc.more_io = 0;
 		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
 		wbc.pages_skipped = 0;
+
+		trace_wbc_writeback_start(&wbc, wb->bdi);
 		if (work->sb)
 			__writeback_inodes_sb(work->sb, wb, &wbc);
 		else
 			writeback_inodes_wb(wb, &wbc);
+		trace_wbc_writeback_written(&wbc, wb->bdi);
+
 		work->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 		wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 
@@ -671,8 +679,8 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 */
 		spin_lock(&inode_lock);
 		if (!list_empty(&wb->b_more_io))  {
-			inode = list_entry(wb->b_more_io.prev,
-						struct inode, i_list);
+			inode = wb_inode(wb->b_more_io.prev);
+			trace_wbc_writeback_wait(&wbc, wb->bdi);
 			inode_wait_for_writeback(inode);
 		}
 		spin_unlock(&inode_lock);
@@ -685,20 +693,31 @@ static long wb_writeback(struct bdi_writeback *wb,
  * Return the next wb_writeback_work struct that hasn't been processed yet.
  */
 static struct wb_writeback_work *
-get_next_work_item(struct backing_dev_info *bdi, struct bdi_writeback *wb)
+get_next_work_item(struct backing_dev_info *bdi)
 {
 	struct wb_writeback_work *work = NULL;
 
-	spin_lock(&bdi->wb_lock);
+	spin_lock_bh(&bdi->wb_lock);
 	if (!list_empty(&bdi->work_list)) {
 		work = list_entry(bdi->work_list.next,
 				  struct wb_writeback_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock(&bdi->wb_lock);
+	spin_unlock_bh(&bdi->wb_lock);
 	return work;
 }
 
+/*
+ * Add in the number of potentially dirty inodes, because each inode
+ * write can dirty pagecache in the underlying blockdev.
+ */
+static unsigned long get_nr_dirty_pages(void)
+{
+	return global_page_state(NR_FILE_DIRTY) +
+		global_page_state(NR_UNSTABLE_NFS) +
+		get_nr_dirty_inodes();
+}
+
 static long wb_check_old_data_flush(struct bdi_writeback *wb)
 {
 	unsigned long expired;
@@ -716,9 +735,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb)
 		return 0;
 
 	wb->last_old_flush = jiffies;
-	nr_pages = global_page_state(NR_FILE_DIRTY) +
-			global_page_state(NR_UNSTABLE_NFS) +
-			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
+	nr_pages = get_nr_dirty_pages();
 
 	if (nr_pages) {
 		struct wb_writeback_work work = {
@@ -743,7 +760,8 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 	struct wb_writeback_work *work;
 	long wrote = 0;
 
-	while ((work = get_next_work_item(bdi, wb)) != NULL) {
+	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
 		 * because this thread is exiting now.
@@ -751,6 +769,8 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 		if (force_wait)
 			work->sync_mode = WB_SYNC_ALL;
 
+		trace_writeback_exec(bdi, work);
+
 		wrote += wb_writeback(wb, work);
 
 		/*
@@ -767,6 +787,7 @@ 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;
 }
@@ -775,47 +796,66 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
  * Handle writeback of dirty data for the device backed by this bdi. Also
  * wakes up periodically and does kupdated style flushing.
  */
-int bdi_writeback_task(struct bdi_writeback *wb)
+int bdi_writeback_thread(void *data)
 {
-	unsigned long last_active = jiffies;
-	unsigned long wait_jiffies = -1UL;
+	struct bdi_writeback *wb = data;
+	struct backing_dev_info *bdi = wb->bdi;
 	long pages_written;
 
+	current->flags |= PF_SWAPWRITE;
+	set_freezable();
+	wb->last_active = jiffies;
+
+	/*
+	 * Our parent may run at a different priority, just set us to normal
+	 */
+	set_user_nice(current, 0);
+
+	trace_writeback_thread_start(bdi);
+
 	while (!kthread_should_stop()) {
+		/*
+		 * Remove own delayed wake-up timer, since we are already awake
+		 * and we'll take care of the preriodic write-back.
+		 */
+		del_timer(&wb->wakeup_timer);
+
 		pages_written = wb_do_writeback(wb, 0);
 
+		trace_writeback_pages_written(pages_written);
+
 		if (pages_written)
-			last_active = jiffies;
-		else if (wait_jiffies != -1UL) {
-			unsigned long max_idle;
+			wb->last_active = jiffies;
 
-			/*
-			 * Longest period of inactivity that we tolerate. If we
-			 * see dirty data again later, the task will get
-			 * recreated automatically.
-			 */
-			max_idle = max(5UL * 60 * HZ, wait_jiffies);
-			if (time_after(jiffies, max_idle + last_active))
-				break;
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (!list_empty(&bdi->work_list) || kthread_should_stop()) {
+			__set_current_state(TASK_RUNNING);
+			continue;
 		}
 
-		if (dirty_writeback_interval) {
-			wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
-			schedule_timeout_interruptible(wait_jiffies);
-		} else {
-			set_current_state(TASK_INTERRUPTIBLE);
-			if (list_empty_careful(&wb->bdi->work_list) &&
-			    !kthread_should_stop())
-				schedule();
-			__set_current_state(TASK_RUNNING);
+		if (wb_has_dirty_io(wb) && dirty_writeback_interval)
+			schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
+		else {
+			/*
+			 * We have nothing to do, so can go sleep without any
+			 * timeout and save power. When a work is queued or
+			 * something is made dirty - we will be woken up.
+			 */
+			schedule();
 		}
 
 		try_to_freeze();
 	}
 
+	/* Flush any work that raced with us exiting */
+	if (!list_empty(&bdi->work_list))
+		wb_do_writeback(wb, 1);
+
+	trace_writeback_thread_stop(bdi);
 	return 0;
 }
 
+
 /*
  * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
  * the whole world.
@@ -890,6 +930,8 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
 void __mark_inode_dirty(struct inode *inode, int flags)
 {
 	struct super_block *sb = inode->i_sb;
+	struct backing_dev_info *bdi = NULL;
+	bool wakeup_bdi = false;
 
 	/*
 	 * Don't do this for I_DIRTY_PAGES - that doesn't actually
@@ -932,10 +974,10 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		 * dirty list.  Add blockdev inodes as well.
 		 */
 		if (!S_ISBLK(inode->i_mode)) {
-			if (hlist_unhashed(&inode->i_hash))
+			if (inode_unhashed(inode))
 				goto out;
 		}
-		if (inode->i_state & (I_FREEING|I_CLEAR))
+		if (inode->i_state & I_FREEING)
 			goto out;
 
 		/*
@@ -943,22 +985,31 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		 * reposition it (that would break b_dirty time-ordering).
 		 */
 		if (!was_dirty) {
-			struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
-			struct backing_dev_info *bdi = wb->bdi;
-
-			if (bdi_cap_writeback_dirty(bdi) &&
-			    !test_bit(BDI_registered, &bdi->state)) {
-				WARN_ON(1);
-				printk(KERN_ERR "bdi-%s not registered\n",
-								bdi->name);
+			bdi = inode_to_bdi(inode);
+
+			if (bdi_cap_writeback_dirty(bdi)) {
+				WARN(!test_bit(BDI_registered, &bdi->state),
+				     "bdi-%s not registered\n", bdi->name);
+
+				/*
+				 * If this is the first dirty inode for this
+				 * bdi, we have to wake-up the corresponding
+				 * bdi thread to make sure background
+				 * write-back happens later.
+				 */
+				if (!wb_has_dirty_io(&bdi->wb))
+					wakeup_bdi = true;
 			}
 
 			inode->dirtied_when = jiffies;
-			list_move(&inode->i_list, &wb->b_dirty);
+			list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
 		}
 	}
 out:
 	spin_unlock(&inode_lock);
+
+	if (wakeup_bdi)
+		bdi_wakeup_thread_delayed(bdi);
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
 
@@ -1001,7 +1052,7 @@ static void wait_sb_inodes(struct super_block *sb)
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		struct address_space *mapping;
 
-		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
 			continue;
 		mapping = inode->i_mapping;
 		if (mapping->nrpages == 0)
@@ -1030,33 +1081,42 @@ static void wait_sb_inodes(struct super_block *sb)
 }
 
 /**
- * writeback_inodes_sb	-	writeback dirty inodes from given super_block
+ * writeback_inodes_sb_nr -	writeback dirty inodes from given super_block
  * @sb: the superblock
+ * @nr: the number of pages to write
  *
  * Start writeback on some inodes on this super_block. No guarantees are made
  * on how many (if any) will be written, and this function does not wait
- * for IO completion of submitted IO. The number of pages submitted is
- * returned.
+ * for IO completion of submitted IO.
  */
-void writeback_inodes_sb(struct super_block *sb)
+void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr)
 {
-	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
-	unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct wb_writeback_work work = {
 		.sb		= sb,
 		.sync_mode	= WB_SYNC_NONE,
 		.done		= &done,
+		.nr_pages	= nr,
 	};
 
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
-
-	work.nr_pages = nr_dirty + nr_unstable +
-			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
-
 	bdi_queue_work(sb->s_bdi, &work);
 	wait_for_completion(&done);
 }
+EXPORT_SYMBOL(writeback_inodes_sb_nr);
+
+/**
+ * writeback_inodes_sb	-	writeback dirty inodes from given super_block
+ * @sb: the superblock
+ *
+ * Start writeback on some inodes on this super_block. No guarantees are made
+ * on how many (if any) will be written, and this function does not wait
+ * for IO completion of submitted IO.
+ */
+void writeback_inodes_sb(struct super_block *sb)
+{
+	return writeback_inodes_sb_nr(sb, get_nr_dirty_pages());
+}
 EXPORT_SYMBOL(writeback_inodes_sb);
 
 /**
@@ -1079,6 +1139,27 @@ int writeback_inodes_sb_if_idle(struct super_block *sb)
 EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
 
 /**
+ * writeback_inodes_sb_if_idle	-	start writeback if none underway
+ * @sb: the superblock
+ * @nr: the number of pages to write
+ *
+ * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Returns 1 if writeback was started, 0 if not.
+ */
+int writeback_inodes_sb_nr_if_idle(struct super_block *sb,
+				   unsigned long nr)
+{
+	if (!writeback_in_progress(sb->s_bdi)) {
+		down_read(&sb->s_umount);
+		writeback_inodes_sb_nr(sb, nr);
+		up_read(&sb->s_umount);
+		return 1;
+	} else
+		return 0;
+}
+EXPORT_SYMBOL(writeback_inodes_sb_nr_if_idle);
+
+/**
  * sync_inodes_sb	-	sync sb inode pages
  * @sb: the superblock
  *
@@ -1159,3 +1240,23 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc)
 	return ret;
 }
 EXPORT_SYMBOL(sync_inode);
+
+/**
+ * sync_inode - write an inode to disk
+ * @inode: the inode to sync
+ * @wait: wait for I/O to complete.
+ *
+ * Write an inode to disk and adjust it's dirty state after completion.
+ *
+ * Note: only writes the actual inode, no associated data or other metadata.
+ */
+int sync_inode_metadata(struct inode *inode, int wait)
+{
+	struct writeback_control wbc = {
+		.sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
+		.nr_to_write = 0, /* metadata-only */
+	};
+
+	return sync_inode(inode, &wbc);
+}
+EXPORT_SYMBOL(sync_inode_metadata);