block: loop: use kthread_work

The following patch will use dio/aio to submit IO to backing file,
then it needn't to schedule IO concurrently from work, so
use kthread_work for decreasing context switch cost a lot.

For non-AIO case, single thread has been used for long long time,
and it was just converted to work in v4.0, which has caused performance
regression for fedora live booting already. In discussion[1], even
though submitting I/O via work concurrently can improve random read IO
throughput, meantime it might hurt sequential read IO performance, so
better to restore to single thread behaviour.

For the following AIO support, it is better to use multi hw-queue
with per-hwq kthread than current work approach suppose there is so
high performance requirement for loop.

[1] http://marc.info/?t=143082678400002&r=1&w=2

Signed-off-by: Ming Lei <ming.lei@canonical.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 4 insertions, 6 deletions

diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 25e8997ed246..b6c7d21a453a 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -14,7 +14,7 @@
 #include <linux/blk-mq.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
+#include <linux/kthread.h>
 #include <uapi/linux/loop.h>
 
 /* Possible states of device */
@@ -54,12 +54,10 @@ struct loop_device {
 	gfp_t		old_gfp_mask;
 
 	spinlock_t		lo_lock;
-	struct workqueue_struct *wq;
-	struct list_head	write_cmd_head;
-	struct work_struct	write_work;
-	bool			write_started;
 	int			lo_state;
 	struct mutex		lo_ctl_mutex;
+	struct kthread_worker	worker;
+	struct task_struct	*worker_task;
 
 	struct request_queue	*lo_queue;
 	struct blk_mq_tag_set	tag_set;
@@ -67,7 +65,7 @@ struct loop_device {
 };
 
 struct loop_cmd {
-	struct work_struct read_work;
+	struct kthread_work work;
 	struct request *rq;
 	struct list_head list;
 };