bdi: reimplement bdev_inode_switch_bdi()

A block_device may be attached to different gendisks and thus
different bdis over time.  bdev_inode_switch_bdi() is used to switch
the associated bdi.  The function assumes that the inode could be
dirty and transfers it between bdis if so.  This is a bit nasty in
that it reaches into bdi internals.

This patch reimplements the function so that it writes out the inode
if dirty.  This is a lot simpler and can be implemented without
exposing bdi internals.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jens Axboe <axboe@fb.com>

fs/block_dev.c

@@ -50,32 +50,22 @@ inline struct block_device *I_BDEV(struct inode *inode)
 EXPORT_SYMBOL(I_BDEV);
 
 /*
- * 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.
+ * Move the inode from its current bdi to a new bdi.  Make sure the inode
+ * is clean before moving so that it doesn't linger on the old bdi.
  */
 static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
-	struct backing_dev_info *old = inode->i_data.backing_dev_info;
-	bool wakeup_bdi = false;
-
-	if (unlikely(dst == old))		/* deadlock avoidance */
-		return;
-	bdi_lock_two(&old->wb, &dst->wb);
+	while (true) {
 		spin_lock(&inode->i_lock);
+		if (!(inode->i_state & I_DIRTY)) {
 			inode->i_data.backing_dev_info = dst;
-	if (inode->i_state & I_DIRTY) {
-		if (bdi_cap_writeback_dirty(dst) && !wb_has_dirty_io(&dst->wb))
-			wakeup_bdi = true;
-		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
+			spin_unlock(&inode->i_lock);
+			return;
 		}
 		spin_unlock(&inode->i_lock);
-	spin_unlock(&old->wb.list_lock);
-	spin_unlock(&dst->wb.list_lock);
-
-	if (wakeup_bdi)
-		bdi_wakeup_thread_delayed(dst);
+		WARN_ON_ONCE(write_inode_now(inode, true));
+	}
 }
 
 /* Kill _all_ buffers and pagecache , dirty or not.. */

include/linux/backing-dev.h

@@ -121,7 +121,6 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi);
 void bdi_writeback_workfn(struct work_struct *work);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
 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;

mm/backing-dev.c

@@ -40,7 +40,7 @@ LIST_HEAD(bdi_list);
 /* bdi_wq serves all asynchronous writeback tasks */
 struct workqueue_struct *bdi_wq;
 
-void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+static void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
 {
 	if (wb1 < wb2) {
 		spin_lock(&wb1->list_lock);