1 files changed, 46 insertions, 38 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1f4a10ece2f1..ef9bef118342 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -40,18 +40,13 @@
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
-	/*
-	 * Write only inodes dirtied before this time. Don't forget to set
-	 * older_than_this_is_set when you set this.
-	 */
-	unsigned long older_than_this;
+	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;
 	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
-	unsigned int older_than_this_is_set:1;
 	enum wb_reason reason;		/* why was writeback initiated? */
 
 	struct list_head list;		/* pending work list */
@@ -94,16 +89,31 @@ static inline struct inode *wb_inode(struct list_head *head)
 #define CREATE_TRACE_POINTS
 #include <trace/events/writeback.h>
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);
+
+static void bdi_wakeup_thread(struct backing_dev_info *bdi)
+{
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	spin_unlock_bh(&bdi->wb_lock);
+}
+
 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);
+	if (!test_bit(BDI_registered, &bdi->state)) {
+		if (work->done)
+			complete(work->done);
+		goto out_unlock;
+	}
 	list_add_tail(&work->list, &bdi->work_list);
-	spin_unlock_bh(&bdi->wb_lock);
-
 	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+out_unlock:
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
@@ -119,7 +129,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
 		trace_writeback_nowork(bdi);
-		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+		bdi_wakeup_thread(bdi);
 		return;
 	}
 
@@ -166,7 +176,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
 	 * writeback as soon as there is no other work to do.
 	 */
 	trace_writeback_wake_background(bdi);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	bdi_wakeup_thread(bdi);
 }
 
 /*
@@ -252,10 +262,10 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 	int moved = 0;
 
-	WARN_ON_ONCE(!work->older_than_this_is_set);
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (inode_dirtied_after(inode, work->older_than_this))
+		if (work->older_than_this &&
+		    inode_dirtied_after(inode, *work->older_than_this))
 			break;
 		list_move(&inode->i_wb_list, &tmp);
 		moved++;
@@ -332,7 +342,8 @@ 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);
-		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
+		__wait_on_bit(wqh, &wq, bit_wait,
+			      TASK_UNINTERRUPTIBLE);
 		spin_lock(&inode->i_lock);
 	}
 }
@@ -516,13 +527,16 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	}
 	WARN_ON(inode->i_state & I_SYNC);
 	/*
-	 * Skip inode if it is clean. We don't want to mess with writeback
-	 * lists in this function since flusher thread may be doing for example
-	 * sync in parallel and if we move the inode, it could get skipped. So
-	 * here we make sure inode is on some writeback list and leave it there
-	 * unless we have completely cleaned the inode.
+	 * Skip inode if it is clean and we have no outstanding writeback in
+	 * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this
+	 * function since flusher thread may be doing for example sync in
+	 * parallel and if we move the inode, it could get skipped. So here we
+	 * make sure inode is on some writeback list and leave it there unless
+	 * we have completely cleaned the inode.
 	 */
-	if (!(inode->i_state & I_DIRTY))
+	if (!(inode->i_state & I_DIRTY) &&
+	    (wbc->sync_mode != WB_SYNC_ALL ||
+	     !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
 		goto out;
 	inode->i_state |= I_SYNC;
 	spin_unlock(&inode->i_lock);
@@ -739,8 +753,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 		.sync_mode	= WB_SYNC_NONE,
 		.range_cyclic	= 1,
 		.reason		= reason,
-		.older_than_this = jiffies,
-		.older_than_this_is_set = 1,
 	};
 
 	spin_lock(&wb->list_lock);
@@ -799,13 +811,12 @@ static long wb_writeback(struct bdi_writeback *wb,
 {
 	unsigned long wb_start = jiffies;
 	long nr_pages = work->nr_pages;
+	unsigned long oldest_jif;
 	struct inode *inode;
 	long progress;
 
-	if (!work->older_than_this_is_set) {
-		work->older_than_this = jiffies;
-		work->older_than_this_is_set = 1;
-	}
+	oldest_jif = jiffies;
+	work->older_than_this = &oldest_jif;
 
 	spin_lock(&wb->list_lock);
 	for (;;) {
@@ -839,10 +850,10 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * safe.
 		 */
 		if (work->for_kupdate) {
-			work->older_than_this = jiffies -
+			oldest_jif = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
 		} else if (work->for_background)
-			work->older_than_this = jiffies;
+			oldest_jif = jiffies;
 
 		trace_writeback_start(wb->bdi, work);
 		if (list_empty(&wb->b_io))
@@ -1022,7 +1033,7 @@ void bdi_writeback_workfn(struct work_struct *work)
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
-		   list_empty(&bdi->bdi_list))) {
+		   !test_bit(BDI_registered, &bdi->state))) {
 		/*
 		 * The normal path.  Keep writing back @bdi until its
 		 * work_list is empty.  Note that this path is also taken
@@ -1044,10 +1055,10 @@ void bdi_writeback_workfn(struct work_struct *work)
 		trace_writeback_pages_written(pages_written);
 	}
 
-	if (!list_empty(&bdi->work_list) ||
-	    (wb_has_dirty_io(wb) && dirty_writeback_interval))
-		queue_delayed_work(bdi_wq, &wb->dwork,
-			msecs_to_jiffies(dirty_writeback_interval * 10));
+	if (!list_empty(&bdi->work_list))
+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+	else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
+		bdi_wakeup_thread_delayed(bdi);
 
 	current->flags &= ~PF_SWAPWRITE;
 }
@@ -1354,21 +1365,18 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb);
 
 /**
  * sync_inodes_sb	-	sync sb inode pages
- * @sb:			the superblock
- * @older_than_this:	timestamp
+ * @sb: the superblock
  *
  * This function writes and waits on any dirty inode belonging to this
- * superblock that has been dirtied before given timestamp.
+ * super_block.
  */
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this)
+void sync_inodes_sb(struct super_block *sb)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct wb_writeback_work work = {
 		.sb		= sb,
 		.sync_mode	= WB_SYNC_ALL,
 		.nr_pages	= LONG_MAX,
-		.older_than_this = older_than_this,
-		.older_than_this_is_set = 1,
 		.range_cyclic	= 0,
 		.done		= &done,
 		.reason		= WB_REASON_SYNC,