Merge branch 'master'; commit 'v2.6.38-rc7' into next

1 files changed, 83 insertions, 22 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3d06ccc953aa..59c6e4956786 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -84,13 +84,9 @@ 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)
+/* Wakeup flusher thread or forker thread to fork it. Requires bdi->wb_lock. */
+static void bdi_wakeup_flusher(struct backing_dev_info *bdi)
 {
-	trace_writeback_queue(bdi, work);
-
-	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 {
@@ -98,15 +94,26 @@ static void bdi_queue_work(struct backing_dev_info *bdi,
 		 * 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);
 	}
+}
+
+static void bdi_queue_work(struct backing_dev_info *bdi,
+			   struct wb_writeback_work *work)
+{
+	trace_writeback_queue(bdi, work);
+
+	spin_lock_bh(&bdi->wb_lock);
+	list_add_tail(&work->list, &bdi->work_list);
+	if (!bdi->wb.task)
+		trace_writeback_nothread(bdi, work);
+	bdi_wakeup_flusher(bdi);
 	spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
 __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
-		bool range_cyclic, bool for_background)
+		      bool range_cyclic)
 {
 	struct wb_writeback_work *work;
 
@@ -126,7 +133,6 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	work->sync_mode	= WB_SYNC_NONE;
 	work->nr_pages	= nr_pages;
 	work->range_cyclic = range_cyclic;
-	work->for_background = for_background;
 
 	bdi_queue_work(bdi, work);
 }
@@ -144,7 +150,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
  */
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
 {
-	__bdi_start_writeback(bdi, nr_pages, true, false);
+	__bdi_start_writeback(bdi, nr_pages, true);
 }
 
 /**
@@ -152,13 +158,21 @@ void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
  * @bdi: the backing device to write from
  *
  * Description:
- *   This does WB_SYNC_NONE background writeback. The IO is only
- *   started when this function returns, we make no guarentees on
- *   completion. Caller need not hold sb s_umount semaphore.
+ *   This makes sure WB_SYNC_NONE background writeback happens. When
+ *   this function returns, it is only guaranteed that for given BDI
+ *   some IO is happening if we are over background dirty threshold.
+ *   Caller need not hold sb s_umount semaphore.
  */
 void bdi_start_background_writeback(struct backing_dev_info *bdi)
 {
-	__bdi_start_writeback(bdi, LONG_MAX, true, true);
+	/*
+	 * We just wake up the flusher thread. It will perform background
+	 * writeback as soon as there is no other work to do.
+	 */
+	trace_writeback_wake_background(bdi);
+	spin_lock_bh(&bdi->wb_lock);
+	bdi_wakeup_flusher(bdi);
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 /*
@@ -616,6 +630,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 	};
 	unsigned long oldest_jif;
 	long wrote = 0;
+	long write_chunk;
 	struct inode *inode;
 
 	if (wbc.for_kupdate) {
@@ -628,6 +643,24 @@ static long wb_writeback(struct bdi_writeback *wb,
 		wbc.range_end = LLONG_MAX;
 	}
 
+	/*
+	 * 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 */
 	for (;;) {
 		/*
@@ -637,6 +670,16 @@ static long wb_writeback(struct bdi_writeback *wb,
 			break;
 
 		/*
+		 * Background writeout and kupdate-style writeback may
+		 * run forever. Stop them if there is other work to do
+		 * so that e.g. sync can proceed. They'll be restarted
+		 * after the other works are all done.
+		 */
+		if ((work->for_background || work->for_kupdate) &&
+		    !list_empty(&wb->bdi->work_list))
+			break;
+
+		/*
 		 * For background writeout, stop when we are below the
 		 * background dirty threshold
 		 */
@@ -644,7 +687,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 			break;
 
 		wbc.more_io = 0;
-		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+		wbc.nr_to_write = write_chunk;
 		wbc.pages_skipped = 0;
 
 		trace_wbc_writeback_start(&wbc, wb->bdi);
@@ -654,8 +697,8 @@ static long wb_writeback(struct bdi_writeback *wb,
 			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;
+		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
@@ -670,7 +713,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		/*
 		 * Did we write something? Try for more
 		 */
-		if (wbc.nr_to_write < MAX_WRITEBACK_PAGES)
+		if (wbc.nr_to_write < write_chunk)
 			continue;
 		/*
 		 * Nothing written. Wait for some inode to
@@ -718,6 +761,23 @@ static unsigned long get_nr_dirty_pages(void)
 		get_nr_dirty_inodes();
 }
 
+static long wb_check_background_flush(struct bdi_writeback *wb)
+{
+	if (over_bground_thresh()) {
+
+		struct wb_writeback_work work = {
+			.nr_pages	= LONG_MAX,
+			.sync_mode	= WB_SYNC_NONE,
+			.for_background	= 1,
+			.range_cyclic	= 1,
+		};
+
+		return wb_writeback(wb, &work);
+	}
+
+	return 0;
+}
+
 static long wb_check_old_data_flush(struct bdi_writeback *wb)
 {
 	unsigned long expired;
@@ -787,6 +847,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 	 * Check for periodic writeback, kupdated() style
 	 */
 	wrote += wb_check_old_data_flush(wb);
+	wrote += wb_check_background_flush(wb);
 	clear_bit(BDI_writeback_running, &wb->bdi->state);
 
 	return wrote;
@@ -873,7 +934,7 @@ void wakeup_flusher_threads(long nr_pages)
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
 		if (!bdi_has_dirty_io(bdi))
 			continue;
-		__bdi_start_writeback(bdi, nr_pages, false, false);
+		__bdi_start_writeback(bdi, nr_pages, false);
 	}
 	rcu_read_unlock();
 }
@@ -1164,7 +1225,7 @@ EXPORT_SYMBOL(writeback_inodes_sb_nr_if_idle);
  * @sb: the superblock
  *
  * This function writes and waits on any dirty inode belonging to this
- * super_block. The number of pages synced is returned.
+ * super_block.
  */
 void sync_inodes_sb(struct super_block *sb)
 {
@@ -1242,11 +1303,11 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc)
 EXPORT_SYMBOL(sync_inode);
 
 /**
- * sync_inode - write an inode to disk
+ * sync_inode_metadata - 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.
+ * Write an inode to disk and adjust its dirty state after completion.
  *
  * Note: only writes the actual inode, no associated data or other metadata.
  */