block: let io_schedule() flush the plug inline

Linus correctly observes that the most important dispatch cases
are now done from kblockd, this isn't ideal for latency reasons.
The original reason for switching dispatches out-of-line was to
avoid too deep a stack, so by _only_ letting the "accidental"
flush directly in schedule() be guarded by offload to kblockd,
we should be able to get the best of both worlds.

So add a blk_schedule_flush_plug() that offloads to kblockd,
and only use that from the schedule() path.
Signed-off-by: NJens Axboe <jaxboe@fusionio.com>

include/linux/blkdev.h

@@ -871,6 +871,14 @@ static inline void blk_flush_plug(struct task_struct *tsk)
 {
 	struct blk_plug *plug = tsk->plug;
 
+	if (plug)
+		blk_flush_plug_list(plug, false);
+}
+
+static inline void blk_schedule_flush_plug(struct task_struct *tsk)
+{
+	struct blk_plug *plug = tsk->plug;
+
 	if (plug)
 		blk_flush_plug_list(plug, true);
 }
@@ -1317,6 +1325,11 @@ static inline void blk_flush_plug(struct task_struct *task)
 {
 }
 
+static inline void blk_schedule_flush_plug(struct task_struct *task)
+{
+}
+
+
 static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 {
 	return false;

kernel/sched.c

@@ -4118,7 +4118,7 @@ asmlinkage void __sched schedule(void)
 			 */
 			if (blk_needs_flush_plug(prev)) {
 				raw_spin_unlock(&rq->lock);
-				blk_flush_plug(prev);
+				blk_schedule_flush_plug(prev);
 				raw_spin_lock(&rq->lock);
 			}
 		}