[PATCH 7/7] blk-mq-sched: allow setting of default IO scheduler

[Jens Axboe <axboe@fb.com>]

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/Kconfig.iosched   | 43 +++++++++++++++++++++++++++++++++++++------
 block/blk-mq-sched.c    | 19 +++++++++++++++++++
 block/blk-mq-sched.h    |  1 +
 block/blk-mq.c          |  3 +++
 block/elevator.c        |  5 ++++-
 drivers/nvme/host/pci.c |  1 +
 include/linux/blk-mq.h  |  1 +
 7 files changed, 66 insertions(+), 7 deletions(-)

diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 490ef2850fae..00502a3d76b7 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -32,12 +32,6 @@ config IOSCHED_CFQ
 
 	  This is the default I/O scheduler.
 
-config MQ_IOSCHED_DEADLINE
-	tristate "MQ deadline I/O scheduler"
-	default y
-	---help---
-	  MQ version of the deadline IO scheduler.
-
 config CFQ_GROUP_IOSCHED
 	bool "CFQ Group Scheduling support"
 	depends on IOSCHED_CFQ && BLK_CGROUP
@@ -69,6 +63,43 @@ config DEFAULT_IOSCHED
 	default "cfq" if DEFAULT_CFQ
 	default "noop" if DEFAULT_NOOP
 
+config MQ_IOSCHED_DEADLINE
+	tristate "MQ deadline I/O scheduler"
+	default y
+	---help---
+	  MQ version of the deadline IO scheduler.
+
+config MQ_IOSCHED_NONE
+	bool
+	default y
+
+choice
+	prompt "Default MQ I/O scheduler"
+	default MQ_IOSCHED_NONE
+	help
+	  Select the I/O scheduler which will be used by default for all
+	  blk-mq managed block devices.
+
+	config DEFAULT_MQ_DEADLINE
+		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
+
+	config DEFAULT_MQ_NONE
+		bool "None"
+
+endchoice
+
+config DEFAULT_MQ_IOSCHED
+	string
+	default "mq-deadline" if DEFAULT_MQ_DEADLINE
+	default "none" if DEFAULT_MQ_NONE
+
 endmenu
 
+config MQ_IOSCHED_ONLY_SQ
+	bool "Enable blk-mq IO scheduler only for single queue devices"
+	default y
+	help
+	  Say Y here, if you only want to enable IO scheduling on block
+	  devices that have a single queue registered.
+
 endif
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 9213366e67d1..bcab84d325c2 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -244,3 +244,22 @@ void __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 
 	blk_mq_dispatch_rq_list(hctx, &rq_list);
 }
+
+int blk_mq_sched_init(struct request_queue *q)
+{
+	int ret;
+
+#if defined(CONFIG_DEFAULT_MQ_NONE)
+	return 0;
+#endif
+#if defined(CONFIG_MQ_IOSCHED_ONLY_SQ)
+	if (q->nr_hw_queues > 1)
+		return 0;
+#endif
+
+	mutex_lock(&q->sysfs_lock);
+	ret = elevator_init(q, NULL);
+	mutex_unlock(&q->sysfs_lock);
+
+	return ret;
+}
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 609c80506cfc..391ecc00f520 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -25,6 +25,7 @@ struct request *
 blk_mq_sched_request_from_shadow(struct blk_mq_hw_ctx *hctx,
 				 struct request *(*get_sched_rq)(struct blk_mq_hw_ctx *));
 
+int blk_mq_sched_init(struct request_queue *q);
 
 struct blk_mq_alloc_data {
 	/* input parameter */
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 019de6f0fd06..9eeffd76f729 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2141,6 +2141,9 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	INIT_LIST_HEAD(&q->requeue_list);
 	spin_lock_init(&q->requeue_lock);
 
+	if (!(set->flags & BLK_MQ_F_NO_SCHED))
+		blk_mq_sched_init(q);
+
 	if (q->nr_hw_queues > 1)
 		blk_queue_make_request(q, blk_mq_make_request);
 	else
diff --git a/block/elevator.c b/block/elevator.c
index f1191b3b0ff3..368976d05f0a 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -219,7 +219,10 @@ int elevator_init(struct request_queue *q, char *name)
 	}
 
 	if (!e) {
-		e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
+		if (q->mq_ops)
+			e = elevator_get(CONFIG_DEFAULT_MQ_IOSCHED, false);
+		else
+			e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
 		if (!e) {
 			printk(KERN_ERR
 				"Default I/O scheduler not found. " \
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 82b9b3f1f21d..7777ec58252f 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1186,6 +1186,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
 		dev->admin_tagset.numa_node = dev_to_node(dev->dev);
 		dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
+		dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
 		dev->admin_tagset.driver_data = dev;
 
 		if (blk_mq_alloc_tag_set(&dev->admin_tagset))
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index c86b314dde97..7c470bf4d7bf 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -152,6 +152,7 @@ enum {
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
 	BLK_MQ_F_DEFER_ISSUE	= 1 << 4,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
+	BLK_MQ_F_NO_SCHED	= 1 << 6,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
 	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
 
-- 
2.7.4