block: loop: improve performance via blk-mq

The conversion is a bit straightforward, and use work queue to
dispatch requests of loop block, and one big change is that requests
is submitted to backend file/device concurrently with work queue,
so throughput may get improved much. Given write requests over same
file are often run exclusively, so don't handle them concurrently for
avoiding extra context switch cost, possible lock contention and work
schedule cost. Also with blk-mq, there is opportunity to get loop I/O
merged before submitting to backend file/device.

In the following test:
	- base: v3.19-rc2-2041231
	- loop over file in ext4 file system on SSD disk
	- bs: 4k, libaio, io depth: 64, O_DIRECT, num of jobs: 1
	- throughput: IOPS

	------------------------------------------------------
	|            | base      | base with loop-mq | delta |
	------------------------------------------------------
	| randread   | 1740      | 25318             | +1355%|
	------------------------------------------------------
	| read       | 42196     | 51771             | +22.6%|
	-----------------------------------------------------
	| randwrite  | 35709     | 34624             | -3%   |
	-----------------------------------------------------
	| write      | 39137     | 40326             | +3%   |
	-----------------------------------------------------

So loop-mq can improve throughput for both read and randread, meantime,
performance of write and randwrite isn't hurted basically.

Another benefit is that loop driver code gets simplified
much after blk-mq conversion, and the patch can be thought as
cleanup too.
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

drivers/block/loop.h

@@ -13,6 +13,7 @@
 #include <linux/blkdev.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/workqueue.h>
 #include <uapi/linux/loop.h>
 
 /* Possible states of device */
@@ -52,19 +53,23 @@ struct loop_device {
 	gfp_t		old_gfp_mask;
 
 	spinlock_t		lo_lock;
-	struct bio_list		lo_bio_list;
-	unsigned int		lo_bio_count;
+	struct list_head	write_cmd_head;
+	struct work_struct	write_work;
+	bool			write_started;
 	int			lo_state;
 	struct mutex		lo_ctl_mutex;
-	struct task_struct	*lo_thread;
-	wait_queue_head_t	lo_event;
-	/* wait queue for incoming requests */
-	wait_queue_head_t	lo_req_wait;
 
 	struct request_queue	*lo_queue;
+	struct blk_mq_tag_set	tag_set;
 	struct gendisk		*lo_disk;
 };
 
+struct loop_cmd {
+	struct work_struct read_work;
+	struct request *rq;
+	struct list_head list;
+};
+
 /* Support for loadable transfer modules */
 struct loop_func_table {
 	int number;	/* filter type */