[PATCH v3 1/2] blk-mq: Introduce the BLK_MQ_F_NO_SCHED_BY_DEFAULT flag

[Bart Van Assche <bvanassche@acm.org>]

elevator_get_default() uses the following algorithm to select an I/O
scheduler from inside add_disk():
- In case of a single hardware queue or if sharing hardware queues across
  multiple request queues (BLK_MQ_F_TAG_HCTX_SHARED), use mq-deadline.
- Otherwise, use 'none'.

This is a good choice for most but not for all block drivers. Make it
possible to override the selection of mq-deadline with a new flag,
namely BLK_MQ_F_NO_SCHED_BY_DEFAULT.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Martijn Coenen <maco@android.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
---
 block/elevator.c       | 3 +++
 include/linux/blk-mq.h | 6 ++++++
 2 files changed, 9 insertions(+)

diff --git a/block/elevator.c b/block/elevator.c
index 52ada14cfe45..d0295e68f481 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -630,6 +630,9 @@ static inline bool elv_support_iosched(struct request_queue *q)
  */
 static struct elevator_type *elevator_get_default(struct request_queue *q)
 {
+	if (q->tag_set && q->tag_set->flags & BLK_MQ_F_NO_SCHED_BY_DEFAULT)
+		return NULL;
+
 	if (q->nr_hw_queues != 1 &&
 			!blk_mq_is_sbitmap_shared(q->tag_set->flags))
 		return NULL;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 1d18447ebebc..22215db36122 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -404,7 +404,13 @@ enum {
 	BLK_MQ_F_STACKING	= 1 << 2,
 	BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
+	/* Do not allow an I/O scheduler to be configured. */
 	BLK_MQ_F_NO_SCHED	= 1 << 6,
+	/*
+	 * Select 'none' during queue registration in case of a single hwq
+	 * or shared hwqs instead of 'mq-deadline'.
+	 */
+	BLK_MQ_F_NO_SCHED_BY_DEFAULT	= 1 << 7,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
 	BLK_MQ_F_ALLOC_POLICY_BITS = 1,