diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 321f6b8..fd557a0 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -355,8 +355,15 @@
 	spin_lock_bh(&wb->work_lock);
 	if (!test_and_clear_bit(WB_registered, &wb->state)) {
 		spin_unlock_bh(&wb->work_lock);
+		/*
+		 * Wait for wb shutdown to finish if someone else is just
+		 * running wb_shutdown(). Otherwise we could proceed to wb /
+		 * bdi destruction before wb_shutdown() is finished.
+		 */
+		wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE);
 		return;
 	}
+	set_bit(WB_shutting_down, &wb->state);
 	spin_unlock_bh(&wb->work_lock);
 
 	cgwb_remove_from_bdi_list(wb);
@@ -368,6 +375,12 @@
 	mod_delayed_work(bdi_wq, &wb->dwork, 0);
 	flush_delayed_work(&wb->dwork);
 	WARN_ON(!list_empty(&wb->work_list));
+	/*
+	 * Make sure bit gets cleared after shutdown is finished. Matches with
+	 * the barrier provided by test_and_clear_bit() above.
+	 */
+	smp_wmb();
+	clear_bit(WB_shutting_down, &wb->state);
 }
 
 static void wb_exit(struct bdi_writeback *wb)
@@ -698,12 +711,21 @@
 {
 	struct radix_tree_iter iter;
 	void **slot;
+	struct bdi_writeback *wb;
 
 	WARN_ON(test_bit(WB_registered, &bdi->wb.state));
 
 	spin_lock_irq(&cgwb_lock);
 	radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
 		cgwb_kill(*slot);
+
+	while (!list_empty(&bdi->wb_list)) {
+		wb = list_first_entry(&bdi->wb_list, struct bdi_writeback,
+				      bdi_node);
+		spin_unlock_irq(&cgwb_lock);
+		wb_shutdown(wb);
+		spin_lock_irq(&cgwb_lock);
+	}
 	spin_unlock_irq(&cgwb_lock);
 
 	/*