[PATCHSET v3] blk-mq scheduling framework

[PATCHSET v3] blk-mq scheduling framework

[Jens Axboe]

This is version 3 of the blk-mq scheduling framework. Version 2
was posted here:

https://marc.info/?l=linux-block&m=148122805026762&w=2

It's fully stable. In fact I'm running it on my laptop [1]. That may
or may not have been part of a dare. In any case, it's been stable
on that too, and has survived lengthy testing on dedicated test
boxes.

[1] $ cat /sys/block/nvme0n1/queue/scheduler
[mq-deadline] none

I'm still mentally debating whether to shift this over to have
duplicate request tags, one for the scheduler and one for the issue
side. We run into various issues if we do that, but we also get
rid of the shadow request field copying. I think both approaches
have their downsides. I originally considered both, and though that
the shadow request would potentially be the cleanest.

I've rebased this against Linus master branch, since a bunch of
the prep patches are now in, and the general block changes are in
as well.

The patches can be pulled here:

git://git.kernel.dk/linux-block blk-mq-sched.3

Changes since v2:

- Fix the Kconfig single/multi queue sched entry. Suggested by Bart.

- Move the queue ref put into the failure path of the request getting,
  so the caller doesn't have to know about it. Suggested by Bart.

- Add support for IO context management. Needed for the BFQ port.

- Change the anonymous elevator ops union to a named one, since
  old (looking at you, gcc 4.4) compilers don't support named
  initialization of anon unions.

- Constify the blk_mq_ops structure pointers.

- Add generic merging code, so mq-deadline (and others) don't have to
  handle/duplicate that.

- Switched the dispatch hook to list based, so we can move more entries
  at the time, if we want/need to. From Omar.

- Add support for schedulers to continue using the software queues.
  From Omar.

- Ensure that it works with blk-wbt.

- Fix a failure case if we fail registering the MQ elevator. We'd
  fall back to trying noop, which we'd find, but that would not
  work for MQ devices. Fall back to 'none' instead.

- Verified queue ref management.

- Fixed a bunch of bugs, and added a bunch of cleanups.

 block/Kconfig.iosched    |   37 ++
 block/Makefile           |    3 
 block/blk-core.c         |   23 -
 block/blk-exec.c         |    3 
 block/blk-flush.c        |    7 
 block/blk-ioc.c          |    8 
 block/blk-merge.c        |    4 
 block/blk-mq-sched.c     |  394 +++++++++++++++++++++++++++++
 block/blk-mq-sched.h     |  192 ++++++++++++++
 block/blk-mq-tag.c       |    1 
 block/blk-mq.c           |  226 +++++++---------
 block/blk-mq.h           |   28 ++
 block/blk.h              |   26 +
 block/cfq-iosched.c      |    2 
 block/deadline-iosched.c |    2 
 block/elevator.c         |  229 ++++++++++++----
 block/mq-deadline.c      |  638 +++++++++++++++++++++++++++++++++++++++++++++++
 block/noop-iosched.c     |    2 
 drivers/nvme/host/pci.c  |    1 
 include/linux/blk-mq.h   |    6 
 include/linux/blkdev.h   |    2 
 include/linux/elevator.h |   33 ++
 22 files changed, 1635 insertions(+), 232 deletions(-)

-- 
Jens Axboe

[PATCH 1/7] block: move existing elevator ops to union

[Jens Axboe]

Prep patch for adding MQ ops as well, since doing anon unions with
named initializers doesn't work on older compilers.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-ioc.c          |  8 +++----
 block/blk-merge.c        |  4 ++--
 block/blk.h              | 10 ++++----
 block/cfq-iosched.c      |  2 +-
 block/deadline-iosched.c |  2 +-
 block/elevator.c         | 60 ++++++++++++++++++++++++------------------------
 block/noop-iosched.c     |  2 +-
 include/linux/elevator.h |  4 +++-
 8 files changed, 47 insertions(+), 45 deletions(-)

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 381cb50a673c..ab372092a57d 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -43,8 +43,8 @@ static void ioc_exit_icq(struct io_cq *icq)
 	if (icq->flags & ICQ_EXITED)
 		return;
 
-	if (et->ops.elevator_exit_icq_fn)
-		et->ops.elevator_exit_icq_fn(icq);
+	if (et->ops.sq.elevator_exit_icq_fn)
+		et->ops.sq.elevator_exit_icq_fn(icq);
 
 	icq->flags |= ICQ_EXITED;
 }
@@ -383,8 +383,8 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
 	if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) {
 		hlist_add_head(&icq->ioc_node, &ioc->icq_list);
 		list_add(&icq->q_node, &q->icq_list);
-		if (et->ops.elevator_init_icq_fn)
-			et->ops.elevator_init_icq_fn(icq);
+		if (et->ops.sq.elevator_init_icq_fn)
+			et->ops.sq.elevator_init_icq_fn(icq);
 	} else {
 		kmem_cache_free(et->icq_cache, icq);
 		icq = ioc_lookup_icq(ioc, q);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 182398cb1524..480570b691dc 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -763,8 +763,8 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_allow_rq_merge_fn)
-		if (!e->type->ops.elevator_allow_rq_merge_fn(q, rq, next))
+	if (e->type->ops.sq.elevator_allow_rq_merge_fn)
+		if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next))
 			return 0;
 
 	return attempt_merge(q, rq, next);
diff --git a/block/blk.h b/block/blk.h
index 041185e5f129..f46c0ac8ae3d 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -167,7 +167,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			return NULL;
 		}
 		if (unlikely(blk_queue_bypass(q)) ||
-		    !q->elevator->type->ops.elevator_dispatch_fn(q, 0))
+		    !q->elevator->type->ops.sq.elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
 }
@@ -176,16 +176,16 @@ static inline void elv_activate_rq(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_activate_req_fn)
-		e->type->ops.elevator_activate_req_fn(q, rq);
+	if (e->type->ops.sq.elevator_activate_req_fn)
+		e->type->ops.sq.elevator_activate_req_fn(q, rq);
 }
 
 static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_deactivate_req_fn)
-		e->type->ops.elevator_deactivate_req_fn(q, rq);
+	if (e->type->ops.sq.elevator_deactivate_req_fn)
+		e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
 }
 
 #ifdef CONFIG_FAIL_IO_TIMEOUT
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index c73a6fcaeb9d..37aeb20fa454 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -4837,7 +4837,7 @@ static struct elv_fs_entry cfq_attrs[] = {
 };
 
 static struct elevator_type iosched_cfq = {
-	.ops = {
+	.ops.sq = {
 		.elevator_merge_fn = 		cfq_merge,
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index 55e0bb6d7da7..05fc0ea25a98 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -439,7 +439,7 @@ static struct elv_fs_entry deadline_attrs[] = {
 };
 
 static struct elevator_type iosched_deadline = {
-	.ops = {
+	.ops.sq = {
 		.elevator_merge_fn = 		deadline_merge,
 		.elevator_merged_fn =		deadline_merged_request,
 		.elevator_merge_req_fn =	deadline_merged_requests,
diff --git a/block/elevator.c b/block/elevator.c
index 40f0c04e5ad3..022a26830297 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -58,8 +58,8 @@ static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_allow_bio_merge_fn)
-		return e->type->ops.elevator_allow_bio_merge_fn(q, rq, bio);
+	if (e->type->ops.sq.elevator_allow_bio_merge_fn)
+		return e->type->ops.sq.elevator_allow_bio_merge_fn(q, rq, bio);
 
 	return 1;
 }
@@ -224,7 +224,7 @@ int elevator_init(struct request_queue *q, char *name)
 		}
 	}
 
-	err = e->ops.elevator_init_fn(q, e);
+	err = e->ops.sq.elevator_init_fn(q, e);
 	if (err)
 		elevator_put(e);
 	return err;
@@ -234,8 +234,8 @@ EXPORT_SYMBOL(elevator_init);
 void elevator_exit(struct elevator_queue *e)
 {
 	mutex_lock(&e->sysfs_lock);
-	if (e->type->ops.elevator_exit_fn)
-		e->type->ops.elevator_exit_fn(e);
+	if (e->type->ops.sq.elevator_exit_fn)
+		e->type->ops.sq.elevator_exit_fn(e);
 	mutex_unlock(&e->sysfs_lock);
 
 	kobject_put(&e->kobj);
@@ -443,8 +443,8 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		return ELEVATOR_BACK_MERGE;
 	}
 
-	if (e->type->ops.elevator_merge_fn)
-		return e->type->ops.elevator_merge_fn(q, req, bio);
+	if (e->type->ops.sq.elevator_merge_fn)
+		return e->type->ops.sq.elevator_merge_fn(q, req, bio);
 
 	return ELEVATOR_NO_MERGE;
 }
@@ -495,8 +495,8 @@ void elv_merged_request(struct request_queue *q, struct request *rq, int type)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_merged_fn)
-		e->type->ops.elevator_merged_fn(q, rq, type);
+	if (e->type->ops.sq.elevator_merged_fn)
+		e->type->ops.sq.elevator_merged_fn(q, rq, type);
 
 	if (type == ELEVATOR_BACK_MERGE)
 		elv_rqhash_reposition(q, rq);
@@ -510,8 +510,8 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
 	struct elevator_queue *e = q->elevator;
 	const int next_sorted = next->rq_flags & RQF_SORTED;
 
-	if (next_sorted && e->type->ops.elevator_merge_req_fn)
-		e->type->ops.elevator_merge_req_fn(q, rq, next);
+	if (next_sorted && e->type->ops.sq.elevator_merge_req_fn)
+		e->type->ops.sq.elevator_merge_req_fn(q, rq, next);
 
 	elv_rqhash_reposition(q, rq);
 
@@ -528,8 +528,8 @@ void elv_bio_merged(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_bio_merged_fn)
-		e->type->ops.elevator_bio_merged_fn(q, rq, bio);
+	if (e->type->ops.sq.elevator_bio_merged_fn)
+		e->type->ops.sq.elevator_bio_merged_fn(q, rq, bio);
 }
 
 #ifdef CONFIG_PM
@@ -578,7 +578,7 @@ void elv_drain_elevator(struct request_queue *q)
 
 	lockdep_assert_held(q->queue_lock);
 
-	while (q->elevator->type->ops.elevator_dispatch_fn(q, 1))
+	while (q->elevator->type->ops.sq.elevator_dispatch_fn(q, 1))
 		;
 	if (q->nr_sorted && printed++ < 10) {
 		printk(KERN_ERR "%s: forced dispatching is broken "
@@ -653,7 +653,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 		 * rq cannot be accessed after calling
 		 * elevator_add_req_fn.
 		 */
-		q->elevator->type->ops.elevator_add_req_fn(q, rq);
+		q->elevator->type->ops.sq.elevator_add_req_fn(q, rq);
 		break;
 
 	case ELEVATOR_INSERT_FLUSH:
@@ -682,8 +682,8 @@ struct request *elv_latter_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_latter_req_fn)
-		return e->type->ops.elevator_latter_req_fn(q, rq);
+	if (e->type->ops.sq.elevator_latter_req_fn)
+		return e->type->ops.sq.elevator_latter_req_fn(q, rq);
 	return NULL;
 }
 
@@ -691,8 +691,8 @@ struct request *elv_former_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_former_req_fn)
-		return e->type->ops.elevator_former_req_fn(q, rq);
+	if (e->type->ops.sq.elevator_former_req_fn)
+		return e->type->ops.sq.elevator_former_req_fn(q, rq);
 	return NULL;
 }
 
@@ -701,8 +701,8 @@ int elv_set_request(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_set_req_fn)
-		return e->type->ops.elevator_set_req_fn(q, rq, bio, gfp_mask);
+	if (e->type->ops.sq.elevator_set_req_fn)
+		return e->type->ops.sq.elevator_set_req_fn(q, rq, bio, gfp_mask);
 	return 0;
 }
 
@@ -710,16 +710,16 @@ void elv_put_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_put_req_fn)
-		e->type->ops.elevator_put_req_fn(rq);
+	if (e->type->ops.sq.elevator_put_req_fn)
+		e->type->ops.sq.elevator_put_req_fn(rq);
 }
 
 int elv_may_queue(struct request_queue *q, unsigned int op)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_may_queue_fn)
-		return e->type->ops.elevator_may_queue_fn(q, op);
+	if (e->type->ops.sq.elevator_may_queue_fn)
+		return e->type->ops.sq.elevator_may_queue_fn(q, op);
 
 	return ELV_MQUEUE_MAY;
 }
@@ -734,8 +734,8 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]--;
 		if ((rq->rq_flags & RQF_SORTED) &&
-		    e->type->ops.elevator_completed_req_fn)
-			e->type->ops.elevator_completed_req_fn(q, rq);
+		    e->type->ops.sq.elevator_completed_req_fn)
+			e->type->ops.sq.elevator_completed_req_fn(q, rq);
 	}
 }
 
@@ -803,8 +803,8 @@ int elv_register_queue(struct request_queue *q)
 		}
 		kobject_uevent(&e->kobj, KOBJ_ADD);
 		e->registered = 1;
-		if (e->type->ops.elevator_registered_fn)
-			e->type->ops.elevator_registered_fn(q);
+		if (e->type->ops.sq.elevator_registered_fn)
+			e->type->ops.sq.elevator_registered_fn(q);
 	}
 	return error;
 }
@@ -912,7 +912,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	spin_unlock_irq(q->queue_lock);
 
 	/* allocate, init and register new elevator */
-	err = new_e->ops.elevator_init_fn(q, new_e);
+	err = new_e->ops.sq.elevator_init_fn(q, new_e);
 	if (err)
 		goto fail_init;
 
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index a163c487cf38..2d1b15d89b45 100644
--- a/block/noop-iosched.c
+++ b/block/noop-iosched.c
@@ -92,7 +92,7 @@ static void noop_exit_queue(struct elevator_queue *e)
 }
 
 static struct elevator_type elevator_noop = {
-	.ops = {
+	.ops.sq = {
 		.elevator_merge_req_fn		= noop_merged_requests,
 		.elevator_dispatch_fn		= noop_dispatch,
 		.elevator_add_req_fn		= noop_add_request,
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index b276e9ef0e0b..2a9e966eed03 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -94,7 +94,9 @@ struct elevator_type
 	struct kmem_cache *icq_cache;
 
 	/* fields provided by elevator implementation */
-	struct elevator_ops ops;
+	union {
+		struct elevator_ops sq;
+	} ops;
 	size_t icq_size;	/* see iocontext.h */
 	size_t icq_align;	/* ditto */
 	struct elv_fs_entry *elevator_attrs;
-- 
2.7.4

[PATCH 2/7] blk-mq: make mq_ops a const pointer

[Jens Axboe]

We never change it, make that clear.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c         | 2 +-
 include/linux/blk-mq.h | 2 +-
 include/linux/blkdev.h | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index d79fdc11b1ee..87b7eaa1cb74 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -639,7 +639,7 @@ struct blk_mq_timeout_data {
 
 void blk_mq_rq_timed_out(struct request *req, bool reserved)
 {
-	struct blk_mq_ops *ops = req->q->mq_ops;
+	const struct blk_mq_ops *ops = req->q->mq_ops;
 	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
 
 	/*
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 4a2ab5d99ff7..afc81d77e471 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -60,7 +60,7 @@ struct blk_mq_hw_ctx {
 
 struct blk_mq_tag_set {
 	unsigned int		*mq_map;
-	struct blk_mq_ops	*ops;
+	const struct blk_mq_ops	*ops;
 	unsigned int		nr_hw_queues;
 	unsigned int		queue_depth;	/* max hw supported */
 	unsigned int		reserved_tags;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 286b2a264383..7c40fb838b44 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -408,7 +408,7 @@ struct request_queue {
 	dma_drain_needed_fn	*dma_drain_needed;
 	lld_busy_fn		*lld_busy_fn;
 
-	struct blk_mq_ops	*mq_ops;
+	const struct blk_mq_ops	*mq_ops;
 
 	unsigned int		*mq_map;
 
-- 
2.7.4

Re: [PATCH 2/7] blk-mq: make mq_ops a const pointer

[Bart Van Assche]

On 12/15/2016 06:26 AM, Jens Axboe wrote:
> We never change it, make that clear.

Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>

[PATCH 3/7] block: move rq_ioc() to blk.h

[Jens Axboe]

We want to use it outside of blk-core.c.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c | 16 ----------------
 block/blk.h      | 16 ++++++++++++++++
 2 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 61ba08c58b64..92baea07acbc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1040,22 +1040,6 @@ static bool blk_rq_should_init_elevator(struct bio *bio)
 }
 
 /**
- * rq_ioc - determine io_context for request allocation
- * @bio: request being allocated is for this bio (can be %NULL)
- *
- * Determine io_context to use for request allocation for @bio.  May return
- * %NULL if %current->io_context doesn't exist.
- */
-static struct io_context *rq_ioc(struct bio *bio)
-{
-#ifdef CONFIG_BLK_CGROUP
-	if (bio && bio->bi_ioc)
-		return bio->bi_ioc;
-#endif
-	return current->io_context;
-}
-
-/**
  * __get_request - get a free request
  * @rl: request list to allocate from
  * @op: operation and flags
diff --git a/block/blk.h b/block/blk.h
index f46c0ac8ae3d..9a716b5925a4 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -264,6 +264,22 @@ void ioc_clear_queue(struct request_queue *q);
 int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node);
 
 /**
+ * rq_ioc - determine io_context for request allocation
+ * @bio: request being allocated is for this bio (can be %NULL)
+ *
+ * Determine io_context to use for request allocation for @bio.  May return
+ * %NULL if %current->io_context doesn't exist.
+ */
+static inline struct io_context *rq_ioc(struct bio *bio)
+{
+#ifdef CONFIG_BLK_CGROUP
+	if (bio && bio->bi_ioc)
+		return bio->bi_ioc;
+#endif
+	return current->io_context;
+}
+
+/**
  * create_io_context - try to create task->io_context
  * @gfp_mask: allocation mask
  * @node: allocation node
-- 
2.7.4

[PATCH 4/7] blk-mq: export some helpers we need to the scheduling framework

[Jens Axboe]

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c | 31 +++++++++++++++++--------------
 block/blk-mq.h | 25 +++++++++++++++++++++++++
 2 files changed, 42 insertions(+), 14 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 87b7eaa1cb74..8d1cec8e25d1 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -167,8 +167,8 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 }
 EXPORT_SYMBOL(blk_mq_can_queue);
 
-static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			       struct request *rq, unsigned int op)
+void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
+			struct request *rq, unsigned int op)
 {
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* csd/requeue_work/fifo_time is initialized before use */
@@ -213,9 +213,10 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 
 	ctx->rq_dispatched[op_is_sync(op)]++;
 }
+EXPORT_SYMBOL_GPL(blk_mq_rq_ctx_init);
 
-static struct request *
-__blk_mq_alloc_request(struct blk_mq_alloc_data *data, unsigned int op)
+struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
+				       unsigned int op)
 {
 	struct request *rq;
 	unsigned int tag;
@@ -236,6 +237,7 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, unsigned int op)
 
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(__blk_mq_alloc_request);
 
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		unsigned int flags)
@@ -319,8 +321,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
 }
 EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
 
-static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
-				  struct blk_mq_ctx *ctx, struct request *rq)
+void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+			   struct request *rq)
 {
 	const int tag = rq->tag;
 	struct request_queue *q = rq->q;
@@ -803,7 +805,7 @@ static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
  * Process software queues that have been marked busy, splicing them
  * to the for-dispatch
  */
-static void flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
+void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 {
 	struct flush_busy_ctx_data data = {
 		.hctx = hctx,
@@ -812,6 +814,7 @@ static void flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 
 	sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data);
 }
+EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs);
 
 static inline unsigned int queued_to_index(unsigned int queued)
 {
@@ -922,7 +925,7 @@ static void blk_mq_process_rq_list(struct blk_mq_hw_ctx *hctx)
 	/*
 	 * Touch any software queue that has pending entries.
 	 */
-	flush_busy_ctxs(hctx, &rq_list);
+	blk_mq_flush_busy_ctxs(hctx, &rq_list);
 
 	/*
 	 * If we have previous entries on our dispatch list, grab them
@@ -1136,8 +1139,8 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
 		list_add_tail(&rq->queuelist, &ctx->rq_list);
 }
 
-static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
-				    struct request *rq, bool at_head)
+void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+			     bool at_head)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
@@ -1551,8 +1554,8 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	return cookie;
 }
 
-static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
-		struct blk_mq_tags *tags, unsigned int hctx_idx)
+void blk_mq_free_rq_map(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+			unsigned int hctx_idx)
 {
 	struct page *page;
 
@@ -1589,8 +1592,8 @@ static size_t order_to_size(unsigned int order)
 	return (size_t)PAGE_SIZE << order;
 }
 
-static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
-		unsigned int hctx_idx)
+struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
+				       unsigned int hctx_idx)
 {
 	struct blk_mq_tags *tags;
 	unsigned int i, j, entries_per_page, max_order = 4;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 63e9116cddbd..e59f5ca520a2 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -32,6 +32,21 @@ void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *, struct list_head *);
+void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
+
+/*
+ * Internal helpers for allocating/freeing the request map
+ */
+void blk_mq_free_rq_map(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+			unsigned int hctx_idx);
+struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
+					unsigned int hctx_idx);
+
+/*
+ * Internal helpers for request insertion into sw queues
+ */
+void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+				bool at_head);
 
 /*
  * CPU hotplug helpers
@@ -103,6 +118,16 @@ static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
 	data->hctx = hctx;
 }
 
+/*
+ * Internal helpers for request allocation/init/free
+ */
+void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
+			struct request *rq, unsigned int op);
+void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+				struct request *rq);
+struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
+					unsigned int op);
+
 static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
 {
 	return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
-- 
2.7.4

[PATCH 5/7] blk-mq-sched: add framework for MQ capable IO schedulers

[Jens Axboe]

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/Makefile           |   2 +-
 block/blk-core.c         |   7 +-
 block/blk-exec.c         |   3 +-
 block/blk-flush.c        |   7 +-
 block/blk-mq-sched.c     | 375 +++++++++++++++++++++++++++++++++++++++++++++++
 block/blk-mq-sched.h     | 190 ++++++++++++++++++++++++
 block/blk-mq-tag.c       |   1 +
 block/blk-mq.c           | 192 ++++++++++--------------
 block/blk-mq.h           |   3 +
 block/elevator.c         | 186 +++++++++++++++++------
 include/linux/blk-mq.h   |   3 +-
 include/linux/elevator.h |  29 ++++
 12 files changed, 833 insertions(+), 165 deletions(-)
 create mode 100644 block/blk-mq-sched.c
 create mode 100644 block/blk-mq-sched.h

diff --git a/block/Makefile b/block/Makefile
index a827f988c4e6..2eee9e1bb6db 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
-			blk-mq-sysfs.o blk-mq-cpumap.o ioctl.o \
+			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
 			badblocks.o partitions/
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 92baea07acbc..cb1e864cb23d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -39,6 +39,7 @@
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-sched.h"
 #include "blk-wbt.h"
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
@@ -1413,7 +1414,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 		return;
 
 	if (q->mq_ops) {
-		blk_mq_free_request(req);
+		blk_mq_sched_put_request(req);
 		return;
 	}
 
@@ -1449,7 +1450,7 @@ void blk_put_request(struct request *req)
 	struct request_queue *q = req->q;
 
 	if (q->mq_ops)
-		blk_mq_free_request(req);
+		blk_mq_sched_put_request(req);
 	else {
 		unsigned long flags;
 
@@ -2127,7 +2128,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
-		blk_mq_insert_request(rq, false, true, false);
+		blk_mq_sched_insert_request(rq, false, true, false);
 		return 0;
 	}
 
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 3ecb00a6cf45..86656fdfa637 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -9,6 +9,7 @@
 #include <linux/sched/sysctl.h>
 
 #include "blk.h"
+#include "blk-mq-sched.h"
 
 /*
  * for max sense size
@@ -65,7 +66,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_insert_request(rq, at_head, true, false);
+		blk_mq_sched_insert_request(rq, at_head, true, false);
 		return;
 	}
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 20b7c7a02f1c..6a7c29d2eb3c 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -74,6 +74,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
 
 /* FLUSH/FUA sequences */
 enum {
@@ -453,9 +454,9 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
-		if (q->mq_ops) {
-			blk_mq_insert_request(rq, false, true, false);
-		} else
+		if (q->mq_ops)
+			blk_mq_sched_insert_request(rq, false, true, false);
+		else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
 	}
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
new file mode 100644
index 000000000000..02ad17258666
--- /dev/null
+++ b/block/blk-mq-sched.c
@@ -0,0 +1,375 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/blk-mq.h>
+
+#include <trace/events/block.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-sched.h"
+#include "blk-mq-tag.h"
+#include "blk-wbt.h"
+
+/*
+ * Empty set
+ */
+static const struct blk_mq_ops mq_sched_tag_ops = {
+};
+
+void blk_mq_sched_free_requests(struct blk_mq_tags *tags)
+{
+	blk_mq_free_rq_map(NULL, tags, 0);
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_free_requests);
+
+struct blk_mq_tags *blk_mq_sched_alloc_requests(unsigned int depth,
+						unsigned int numa_node)
+{
+	struct blk_mq_tag_set set = {
+		.ops		= &mq_sched_tag_ops,
+		.nr_hw_queues	= 1,
+		.queue_depth	= depth,
+		.numa_node	= numa_node,
+	};
+
+	return blk_mq_init_rq_map(&set, 0);
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_alloc_requests);
+
+void blk_mq_sched_free_hctx_data(struct request_queue *q,
+				 void (*exit)(struct blk_mq_hw_ctx *))
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (exit)
+			exit(hctx);
+		kfree(hctx->sched_data);
+		hctx->sched_data = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
+
+int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
+				void (*init)(struct blk_mq_hw_ctx *))
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		hctx->sched_data = kmalloc_node(size, GFP_KERNEL, hctx->numa_node);
+		if (!hctx->sched_data)
+			goto error;
+
+		if (init)
+			init(hctx);
+	}
+
+	return 0;
+error:
+	blk_mq_sched_free_hctx_data(q, NULL);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data);
+
+struct request *blk_mq_sched_alloc_shadow_request(struct request_queue *q,
+						  struct blk_mq_alloc_data *data,
+						  struct blk_mq_tags *tags,
+						  atomic_t *wait_index)
+{
+	struct sbq_wait_state *ws;
+	DEFINE_WAIT(wait);
+	struct request *rq;
+	int tag;
+
+	tag = __sbitmap_queue_get(&tags->bitmap_tags);
+	if (tag != -1)
+		goto done;
+
+	if (data->flags & BLK_MQ_REQ_NOWAIT)
+		return NULL;
+
+	ws = sbq_wait_ptr(&tags->bitmap_tags, wait_index);
+	do {
+		prepare_to_wait(&ws->wait, &wait, TASK_UNINTERRUPTIBLE);
+
+		tag = __sbitmap_queue_get(&tags->bitmap_tags);
+		if (tag != -1)
+			break;
+
+		blk_mq_run_hw_queue(data->hctx, false);
+
+		tag = __sbitmap_queue_get(&tags->bitmap_tags);
+		if (tag != -1)
+			break;
+
+		blk_mq_put_ctx(data->ctx);
+		io_schedule();
+
+		data->ctx = blk_mq_get_ctx(data->q);
+		data->hctx = blk_mq_map_queue(data->q, data->ctx->cpu);
+		finish_wait(&ws->wait, &wait);
+		ws = sbq_wait_ptr(&tags->bitmap_tags, wait_index);
+	} while (1);
+
+	finish_wait(&ws->wait, &wait);
+done:
+	rq = tags->rqs[tag];
+	rq->tag = tag;
+	rq->rq_flags |= RQF_ALLOCED;
+	return rq;
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_alloc_shadow_request);
+
+void blk_mq_sched_free_shadow_request(struct blk_mq_tags *tags,
+				      struct request *rq)
+{
+	WARN_ON_ONCE(!(rq->rq_flags & RQF_ALLOCED));
+	sbitmap_queue_clear(&tags->bitmap_tags, rq->tag, rq->mq_ctx->cpu);
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_free_shadow_request);
+
+static void rq_copy(struct request *rq, struct request *src)
+{
+#define FIELD_COPY(dst, src, name)	((dst)->name = (src)->name)
+	FIELD_COPY(rq, src, cpu);
+	FIELD_COPY(rq, src, cmd_type);
+	FIELD_COPY(rq, src, cmd_flags);
+	rq->rq_flags |= (src->rq_flags & (RQF_PREEMPT | RQF_QUIET | RQF_PM | RQF_DONTPREP));
+	rq->rq_flags &= ~RQF_IO_STAT;
+	FIELD_COPY(rq, src, __data_len);
+	FIELD_COPY(rq, src, __sector);
+	FIELD_COPY(rq, src, bio);
+	FIELD_COPY(rq, src, biotail);
+	FIELD_COPY(rq, src, rq_disk);
+	FIELD_COPY(rq, src, part);
+	FIELD_COPY(rq, src, issue_stat);
+	src->issue_stat.time = 0;
+	FIELD_COPY(rq, src, nr_phys_segments);
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	FIELD_COPY(rq, src, nr_integrity_segments);
+#endif
+	FIELD_COPY(rq, src, ioprio);
+	FIELD_COPY(rq, src, timeout);
+
+	if (src->cmd_type == REQ_TYPE_BLOCK_PC) {
+		FIELD_COPY(rq, src, cmd);
+		FIELD_COPY(rq, src, cmd_len);
+		FIELD_COPY(rq, src, extra_len);
+		FIELD_COPY(rq, src, sense_len);
+		FIELD_COPY(rq, src, resid_len);
+		FIELD_COPY(rq, src, sense);
+		FIELD_COPY(rq, src, retries);
+	}
+
+	src->bio = src->biotail = NULL;
+}
+
+static void sched_rq_end_io(struct request *rq, int error)
+{
+	struct request *sched_rq = rq->end_io_data;
+
+	FIELD_COPY(sched_rq, rq, resid_len);
+	FIELD_COPY(sched_rq, rq, extra_len);
+	FIELD_COPY(sched_rq, rq, sense_len);
+	FIELD_COPY(sched_rq, rq, errors);
+	FIELD_COPY(sched_rq, rq, retries);
+
+	blk_account_io_completion(sched_rq, blk_rq_bytes(sched_rq));
+	blk_account_io_done(sched_rq);
+
+	if (sched_rq->end_io)
+		sched_rq->end_io(sched_rq, error);
+
+	blk_mq_free_request(rq);
+}
+
+struct request *
+blk_mq_sched_request_from_shadow(struct blk_mq_hw_ctx *hctx,
+				 struct request *(*get_sched_rq)(struct blk_mq_hw_ctx *))
+{
+	struct blk_mq_alloc_data data;
+	struct request *sched_rq, *rq;
+
+	data.q = hctx->queue;
+	data.flags = BLK_MQ_REQ_NOWAIT;
+	data.ctx = blk_mq_get_ctx(hctx->queue);
+	data.hctx = hctx;
+
+	rq = __blk_mq_alloc_request(&data, 0);
+	blk_mq_put_ctx(data.ctx);
+
+	if (!rq) {
+		blk_mq_stop_hw_queue(hctx);
+		return NULL;
+	}
+
+	sched_rq = get_sched_rq(hctx);
+
+	if (!sched_rq) {
+		blk_queue_enter_live(hctx->queue);
+		__blk_mq_free_request(hctx, data.ctx, rq);
+		return NULL;
+	}
+
+	WARN_ON_ONCE(!(sched_rq->rq_flags & RQF_ALLOCED));
+	rq_copy(rq, sched_rq);
+	rq->end_io = sched_rq_end_io;
+	rq->end_io_data = sched_rq;
+
+	return rq;
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_request_from_shadow);
+
+static void blk_mq_sched_assign_ioc(struct request_queue *q,
+				    struct request *rq, struct bio *bio)
+{
+	struct io_context *ioc = rq_ioc(bio);
+	struct io_cq *icq;
+
+	if (!ioc)
+		return;
+
+	spin_lock_irq(q->queue_lock);
+	icq = ioc_lookup_icq(ioc, q);
+	spin_unlock_irq(q->queue_lock);
+
+	if (!icq) {
+		if (ioc)
+			icq = ioc_create_icq(ioc, q, GFP_ATOMIC);
+		if (!icq) {
+fail:
+			printk_ratelimited("failed icq alloc\n");
+			return;
+		}
+	}
+
+	rq->elv.icq = icq;
+	if (blk_mq_sched_get_rq_priv(q, rq))
+		goto fail;
+
+	if (icq)
+		get_io_context(icq->ioc);
+}
+
+struct request *blk_mq_sched_get_request(struct request_queue *q,
+					 struct bio *bio,
+					 unsigned int op,
+					 struct blk_mq_alloc_data *data)
+{
+	struct elevator_queue *e = q->elevator;
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	struct request *rq;
+
+	blk_queue_enter_live(q);
+	ctx = blk_mq_get_ctx(q);
+	hctx = blk_mq_map_queue(q, ctx->cpu);
+
+	blk_mq_set_alloc_data(data, q, 0, ctx, hctx);
+
+	if (e && e->type->ops.mq.get_request)
+		rq = e->type->ops.mq.get_request(q, op, data);
+	else
+		rq = __blk_mq_alloc_request(data, op);
+
+	if (rq) {
+		rq->elv.icq = NULL;
+		if (e && e->type->icq_cache)
+			blk_mq_sched_assign_ioc(q, rq, bio);
+		data->hctx->queued++;
+		return rq;
+	}
+
+	blk_queue_exit(q);
+	return NULL;
+}
+
+void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
+{
+	struct elevator_queue *e = hctx->queue->elevator;
+	LIST_HEAD(rq_list);
+
+	if (unlikely(blk_mq_hctx_stopped(hctx)))
+		return;
+
+	hctx->run++;
+
+	/*
+	 * If we have previous entries on our dispatch list, grab them first for
+	 * more fair dispatch.
+	 */
+	if (!list_empty_careful(&hctx->dispatch)) {
+		spin_lock(&hctx->lock);
+		if (!list_empty(&hctx->dispatch))
+			list_splice_init(&hctx->dispatch, &rq_list);
+		spin_unlock(&hctx->lock);
+	}
+
+	/*
+	 * Only ask the scheduler for requests, if we didn't have residual
+	 * requests from the dispatch list. This is to avoid the case where
+	 * we only ever dispatch a fraction of the requests available because
+	 * of low device queue depth. Once we pull requests out of the IO
+	 * scheduler, we can no longer merge or sort them. So it's best to
+	 * leave them there for as long as we can. Mark the hw queue as
+	 * needing a restart in that case.
+	 */
+	if (list_empty(&rq_list)) {
+		if (e && e->type->ops.mq.dispatch_requests)
+			e->type->ops.mq.dispatch_requests(hctx, &rq_list);
+		else
+			blk_mq_flush_busy_ctxs(hctx, &rq_list);
+	} else
+		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+
+	blk_mq_dispatch_rq_list(hctx, &rq_list);
+}
+
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio)
+{
+	struct request *rq;
+	int ret;
+
+	ret = elv_merge(q, &rq, bio);
+	if (ret == ELEVATOR_BACK_MERGE) {
+		if (bio_attempt_back_merge(q, rq, bio)) {
+			if (!attempt_back_merge(q, rq))
+				elv_merged_request(q, rq, ret);
+			goto done;
+		}
+		ret = ELEVATOR_NO_MERGE;
+	} else if (ret == ELEVATOR_FRONT_MERGE) {
+		if (bio_attempt_front_merge(q, rq, bio)) {
+			if (!attempt_front_merge(q, rq))
+				elv_merged_request(q, rq, ret);
+			goto done;
+		}
+		ret = ELEVATOR_NO_MERGE;
+	}
+done:
+	return ret != ELEVATOR_NO_MERGE;
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
+
+bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.mq.bio_merge) {
+		struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
+		struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+
+		blk_mq_put_ctx(ctx);
+		return e->type->ops.mq.bio_merge(hctx, bio);
+	}
+
+	return false;
+}
+
+void blk_mq_sched_request_inserted(struct request *rq)
+{
+	trace_block_rq_insert(rq->q, rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
new file mode 100644
index 000000000000..b68dccc0190e
--- /dev/null
+++ b/block/blk-mq-sched.h
@@ -0,0 +1,190 @@
+#ifndef BLK_MQ_SCHED_H
+#define BLK_MQ_SCHED_H
+
+#include "blk-mq.h"
+
+struct blk_mq_tags *blk_mq_sched_alloc_requests(unsigned int depth, unsigned int numa_node);
+void blk_mq_sched_free_requests(struct blk_mq_tags *tags);
+
+int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
+				void (*init)(struct blk_mq_hw_ctx *));
+void blk_mq_sched_free_hctx_data(struct request_queue *q,
+				 void (*exit)(struct blk_mq_hw_ctx *));
+
+void blk_mq_sched_free_shadow_request(struct blk_mq_tags *tags,
+				      struct request *rq);
+struct request *blk_mq_sched_alloc_shadow_request(struct request_queue *q,
+						  struct blk_mq_alloc_data *data,
+						  struct blk_mq_tags *tags,
+						  atomic_t *wait_index);
+struct request *
+blk_mq_sched_request_from_shadow(struct blk_mq_hw_ctx *hctx,
+				 struct request *(*get_sched_rq)(struct blk_mq_hw_ctx *));
+
+struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bio, unsigned int op, struct blk_mq_alloc_data *data);
+
+void __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
+void blk_mq_sched_request_inserted(struct request *rq);
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio);
+bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
+
+void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
+
+static inline bool
+blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (!e || blk_queue_nomerges(q) || !bio_mergeable(bio))
+		return false;
+
+	return __blk_mq_sched_bio_merge(q, bio);
+}
+
+static inline int blk_mq_sched_get_rq_priv(struct request_queue *q,
+					   struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.get_rq_priv)
+		return e->type->ops.mq.get_rq_priv(q, rq);
+
+	return 0;
+}
+
+static inline void blk_mq_sched_put_rq_priv(struct request_queue *q,
+					    struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.put_rq_priv)
+		e->type->ops.mq.put_rq_priv(q, rq);
+}
+
+static inline void blk_mq_sched_put_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+	bool do_free = true;
+
+	if (rq->rq_flags & RQF_ELVPRIV) {
+		blk_mq_sched_put_rq_priv(rq->q, rq);
+		if (rq->elv.icq)
+			put_io_context(rq->elv.icq->ioc);
+	}
+
+	if (e && e->type->ops.mq.put_request)
+		do_free = !e->type->ops.mq.put_request(rq);
+	if (do_free)
+		blk_mq_free_request(rq);
+}
+
+static inline void
+blk_mq_sched_insert_request(struct request *rq, bool at_head, bool run_queue,
+			    bool async)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+
+	if (e && e->type->ops.mq.insert_requests) {
+		LIST_HEAD(list);
+
+		list_add(&rq->queuelist, &list);
+		e->type->ops.mq.insert_requests(hctx, &list, at_head);
+	} else {
+		spin_lock(&ctx->lock);
+		__blk_mq_insert_request(hctx, rq, at_head);
+		spin_unlock(&ctx->lock);
+	}
+
+	if (run_queue)
+		blk_mq_run_hw_queue(hctx, async);
+}
+
+static inline void
+blk_mq_sched_insert_requests(struct request_queue *q, struct blk_mq_ctx *ctx,
+			     struct list_head *list, bool run_queue_async)
+{
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (e && e->type->ops.mq.insert_requests)
+		e->type->ops.mq.insert_requests(hctx, list, false);
+	else
+		blk_mq_insert_requests(hctx, ctx, list);
+
+	blk_mq_run_hw_queue(hctx, run_queue_async);
+}
+
+static inline void
+blk_mq_sched_dispatch_shadow_requests(struct blk_mq_hw_ctx *hctx,
+				      struct list_head *rq_list,
+				      struct request *(*get_sched_rq)(struct blk_mq_hw_ctx *))
+{
+	do {
+		struct request *rq;
+
+		rq = blk_mq_sched_request_from_shadow(hctx, get_sched_rq);
+		if (!rq)
+			break;
+
+		list_add_tail(&rq->queuelist, rq_list);
+	} while (1);
+}
+
+static inline bool
+blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
+			 struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.allow_merge)
+		return e->type->ops.mq.allow_merge(q, rq, bio);
+
+	return true;
+}
+
+static inline void
+blk_mq_sched_completed_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
+{
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (e && e->type->ops.mq.completed_request)
+		e->type->ops.mq.completed_request(hctx, rq);
+
+	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
+		clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+		blk_mq_run_hw_queue(hctx, true);
+	}
+}
+
+static inline void blk_mq_sched_started_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.started_request)
+		e->type->ops.mq.started_request(rq);
+}
+
+static inline void blk_mq_sched_requeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.requeue_request)
+		e->type->ops.mq.requeue_request(rq);
+}
+
+static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (e && e->type->ops.mq.has_work)
+		return e->type->ops.mq.has_work(hctx);
+
+	return false;
+}
+#endif
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index dcf5ce3ba4bf..bbd494e23d57 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -12,6 +12,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
 
 bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
 {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 8d1cec8e25d1..d10a246a3bc7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -32,6 +32,7 @@
 #include "blk-mq-tag.h"
 #include "blk-stat.h"
 #include "blk-wbt.h"
+#include "blk-mq-sched.h"
 
 static DEFINE_MUTEX(all_q_mutex);
 static LIST_HEAD(all_q_list);
@@ -41,7 +42,8 @@ static LIST_HEAD(all_q_list);
  */
 static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
 {
-	return sbitmap_any_bit_set(&hctx->ctx_map);
+	return sbitmap_any_bit_set(&hctx->ctx_map) ||
+		blk_mq_sched_has_work(hctx);
 }
 
 /*
@@ -242,26 +244,21 @@ EXPORT_SYMBOL_GPL(__blk_mq_alloc_request);
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		unsigned int flags)
 {
-	struct blk_mq_ctx *ctx;
-	struct blk_mq_hw_ctx *hctx;
-	struct request *rq;
 	struct blk_mq_alloc_data alloc_data;
+	struct request *rq;
 	int ret;
 
 	ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT);
 	if (ret)
 		return ERR_PTR(ret);
 
-	ctx = blk_mq_get_ctx(q);
-	hctx = blk_mq_map_queue(q, ctx->cpu);
-	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw);
-	blk_mq_put_ctx(ctx);
+	rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
 
-	if (!rq) {
-		blk_queue_exit(q);
+	blk_mq_put_ctx(alloc_data.ctx);
+	blk_queue_exit(q);
+
+	if (!rq)
 		return ERR_PTR(-EWOULDBLOCK);
-	}
 
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
@@ -327,6 +324,8 @@ void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 	const int tag = rq->tag;
 	struct request_queue *q = rq->q;
 
+	blk_mq_sched_completed_request(hctx, rq);
+
 	if (rq->rq_flags & RQF_MQ_INFLIGHT)
 		atomic_dec(&hctx->nr_active);
 
@@ -364,8 +363,8 @@ inline void __blk_mq_end_request(struct request *rq, int error)
 		rq->end_io(rq, error);
 	} else {
 		if (unlikely(blk_bidi_rq(rq)))
-			blk_mq_free_request(rq->next_rq);
-		blk_mq_free_request(rq);
+			blk_mq_sched_put_request(rq->next_rq);
+		blk_mq_sched_put_request(rq);
 	}
 }
 EXPORT_SYMBOL(__blk_mq_end_request);
@@ -469,6 +468,8 @@ void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
+	blk_mq_sched_started_request(rq);
+
 	trace_block_rq_issue(q, rq);
 
 	rq->resid_len = blk_rq_bytes(rq);
@@ -517,6 +518,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 
 	trace_block_rq_requeue(q, rq);
 	wbt_requeue(q->rq_wb, &rq->issue_stat);
+	blk_mq_sched_requeue_request(rq);
 
 	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
 		if (q->dma_drain_size && blk_rq_bytes(rq))
@@ -551,13 +553,13 @@ static void blk_mq_requeue_work(struct work_struct *work)
 
 		rq->rq_flags &= ~RQF_SOFTBARRIER;
 		list_del_init(&rq->queuelist);
-		blk_mq_insert_request(rq, true, false, false);
+		blk_mq_sched_insert_request(rq, true, false, false);
 	}
 
 	while (!list_empty(&rq_list)) {
 		rq = list_entry(rq_list.next, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		blk_mq_insert_request(rq, false, false, false);
+		blk_mq_sched_insert_request(rq, false, false, false);
 	}
 
 	blk_mq_run_hw_queues(q, false);
@@ -763,8 +765,16 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 
 		if (!blk_rq_merge_ok(rq, bio))
 			continue;
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			break;
 
 		el_ret = blk_try_merge(rq, bio);
+		if (el_ret == ELEVATOR_NO_MERGE)
+			continue;
+
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			break;
+
 		if (el_ret == ELEVATOR_BACK_MERGE) {
 			if (bio_attempt_back_merge(q, rq, bio)) {
 				ctx->rq_merged++;
@@ -906,41 +916,6 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 	return ret != BLK_MQ_RQ_QUEUE_BUSY;
 }
 
-/*
- * Run this hardware queue, pulling any software queues mapped to it in.
- * Note that this function currently has various problems around ordering
- * of IO. In particular, we'd like FIFO behaviour on handling existing
- * items on the hctx->dispatch list. Ignore that for now.
- */
-static void blk_mq_process_rq_list(struct blk_mq_hw_ctx *hctx)
-{
-	LIST_HEAD(rq_list);
-	LIST_HEAD(driver_list);
-
-	if (unlikely(blk_mq_hctx_stopped(hctx)))
-		return;
-
-	hctx->run++;
-
-	/*
-	 * Touch any software queue that has pending entries.
-	 */
-	blk_mq_flush_busy_ctxs(hctx, &rq_list);
-
-	/*
-	 * If we have previous entries on our dispatch list, grab them
-	 * and stuff them at the front for more fair dispatch.
-	 */
-	if (!list_empty_careful(&hctx->dispatch)) {
-		spin_lock(&hctx->lock);
-		if (!list_empty(&hctx->dispatch))
-			list_splice_init(&hctx->dispatch, &rq_list);
-		spin_unlock(&hctx->lock);
-	}
-
-	blk_mq_dispatch_rq_list(hctx, &rq_list);
-}
-
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	int srcu_idx;
@@ -950,11 +925,11 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 
 	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
 		rcu_read_lock();
-		blk_mq_process_rq_list(hctx);
+		blk_mq_sched_dispatch_requests(hctx);
 		rcu_read_unlock();
 	} else {
 		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
-		blk_mq_process_rq_list(hctx);
+		blk_mq_sched_dispatch_requests(hctx);
 		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
 	}
 }
@@ -1148,32 +1123,10 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
-void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
-			   bool async)
-{
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	spin_lock(&ctx->lock);
-	__blk_mq_insert_request(hctx, rq, at_head);
-	spin_unlock(&ctx->lock);
-
-	if (run_queue)
-		blk_mq_run_hw_queue(hctx, async);
-}
-
-static void blk_mq_insert_requests(struct request_queue *q,
-				     struct blk_mq_ctx *ctx,
-				     struct list_head *list,
-				     int depth,
-				     bool from_schedule)
+void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+			    struct list_head *list)
 
 {
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	trace_block_unplug(q, depth, !from_schedule);
-
 	/*
 	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
 	 * offline now
@@ -1189,8 +1142,6 @@ static void blk_mq_insert_requests(struct request_queue *q,
 	}
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
-
-	blk_mq_run_hw_queue(hctx, from_schedule);
 }
 
 static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
@@ -1226,9 +1177,10 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		BUG_ON(!rq->q);
 		if (rq->mq_ctx != this_ctx) {
 			if (this_ctx) {
-				blk_mq_insert_requests(this_q, this_ctx,
-							&ctx_list, depth,
-							from_schedule);
+				trace_block_unplug(this_q, depth, from_schedule);
+				blk_mq_sched_insert_requests(this_q, this_ctx,
+								&ctx_list,
+								from_schedule);
 			}
 
 			this_ctx = rq->mq_ctx;
@@ -1245,8 +1197,9 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	 * on 'ctx_list'. Do those.
 	 */
 	if (this_ctx) {
-		blk_mq_insert_requests(this_q, this_ctx, &ctx_list, depth,
-				       from_schedule);
+		trace_block_unplug(this_q, depth, from_schedule);
+		blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
+						from_schedule);
 	}
 }
 
@@ -1289,41 +1242,27 @@ static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx,
 	}
 }
 
-static struct request *blk_mq_map_request(struct request_queue *q,
-					  struct bio *bio,
-					  struct blk_mq_alloc_data *data)
-{
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
-	struct request *rq;
-
-	blk_queue_enter_live(q);
-	ctx = blk_mq_get_ctx(q);
-	hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	trace_block_getrq(q, bio, bio->bi_opf);
-	blk_mq_set_alloc_data(data, q, 0, ctx, hctx);
-	rq = __blk_mq_alloc_request(data, bio->bi_opf);
-
-	data->hctx->queued++;
-	return rq;
-}
-
 static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
 {
-	int ret;
 	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
 	struct blk_mq_queue_data bd = {
 		.rq = rq,
 		.list = NULL,
 		.last = 1
 	};
-	blk_qc_t new_cookie = blk_tag_to_qc_t(rq->tag, hctx->queue_num);
+	struct blk_mq_hw_ctx *hctx;
+	blk_qc_t new_cookie;
+	int ret;
+
+	if (q->elevator)
+		goto insert;
 
+	hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
 	if (blk_mq_hctx_stopped(hctx))
 		goto insert;
 
+	new_cookie = blk_tag_to_qc_t(rq->tag, hctx->queue_num);
+
 	/*
 	 * For OK queue, we are done. For error, kill it. Any other
 	 * error (busy), just add it to our list as we previously
@@ -1345,7 +1284,7 @@ static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
 	}
 
 insert:
-	blk_mq_insert_request(rq, false, true, true);
+	blk_mq_sched_insert_request(rq, false, true, true);
 }
 
 /*
@@ -1378,9 +1317,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
 		return BLK_QC_T_NONE;
 
+	if (blk_mq_sched_bio_merge(q, bio))
+		return BLK_QC_T_NONE;
+
 	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
 
-	rq = blk_mq_map_request(q, bio, &data);
+	trace_block_getrq(q, bio, bio->bi_opf);
+
+	rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
 		__wbt_done(q->rq_wb, wb_acct);
 		return BLK_QC_T_NONE;
@@ -1442,6 +1386,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		goto done;
 	}
 
+	if (q->elevator) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_sched_insert_request(rq, false, true, true);
+		goto done;
+	}
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
 		/*
 		 * For a SYNC request, send it to the hardware immediately. For
@@ -1487,9 +1437,14 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	} else
 		request_count = blk_plug_queued_count(q);
 
+	if (blk_mq_sched_bio_merge(q, bio))
+		return BLK_QC_T_NONE;
+
 	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
 
-	rq = blk_mq_map_request(q, bio, &data);
+	trace_block_getrq(q, bio, bio->bi_opf);
+
+	rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
 		__wbt_done(q->rq_wb, wb_acct);
 		return BLK_QC_T_NONE;
@@ -1539,6 +1494,12 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		return cookie;
 	}
 
+	if (q->elevator) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_sched_insert_request(rq, false, true, true);
+		goto done;
+	}
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
 		/*
 		 * For a SYNC request, send it to the hardware immediately. For
@@ -1551,6 +1512,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	blk_mq_put_ctx(data.ctx);
+done:
 	return cookie;
 }
 
@@ -1559,7 +1521,7 @@ void blk_mq_free_rq_map(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 {
 	struct page *page;
 
-	if (tags->rqs && set->ops->exit_request) {
+	if (tags->rqs && set && set->ops->exit_request) {
 		int i;
 
 		for (i = 0; i < tags->nr_tags; i++) {
@@ -2267,10 +2229,10 @@ static int blk_mq_queue_reinit_dead(unsigned int cpu)
  * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list
  * and set bit0 in pending bitmap as ctx1->index_hw is still zero.
  *
- * And then while running hw queue, flush_busy_ctxs() finds bit0 is set in
- * pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
- * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list
- * is ignored.
+ * And then while running hw queue, blk_mq_flush_busy_ctxs() finds bit0 is set
+ * in pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
+ * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list is
+ * ignored.
  */
 static int blk_mq_queue_reinit_prepare(unsigned int cpu)
 {
diff --git a/block/blk-mq.h b/block/blk-mq.h
index e59f5ca520a2..a5ddc860b220 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -47,6 +47,9 @@ struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
  */
 void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				bool at_head);
+void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+				struct list_head *list);
+void blk_mq_process_sw_list(struct blk_mq_hw_ctx *hctx);
 
 /*
  * CPU hotplug helpers
diff --git a/block/elevator.c b/block/elevator.c
index 022a26830297..6d39197768c1 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -40,6 +40,7 @@
 #include <trace/events/block.h>
 
 #include "blk.h"
+#include "blk-mq-sched.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
@@ -58,7 +59,9 @@ static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.sq.elevator_allow_bio_merge_fn)
+	if (e->uses_mq && e->type->ops.mq.allow_merge)
+		return e->type->ops.mq.allow_merge(q, rq, bio);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_allow_bio_merge_fn)
 		return e->type->ops.sq.elevator_allow_bio_merge_fn(q, rq, bio);
 
 	return 1;
@@ -163,6 +166,7 @@ struct elevator_queue *elevator_alloc(struct request_queue *q,
 	kobject_init(&eq->kobj, &elv_ktype);
 	mutex_init(&eq->sysfs_lock);
 	hash_init(eq->hash);
+	eq->uses_mq = e->uses_mq;
 
 	return eq;
 }
@@ -219,12 +223,19 @@ int elevator_init(struct request_queue *q, char *name)
 		if (!e) {
 			printk(KERN_ERR
 				"Default I/O scheduler not found. " \
-				"Using noop.\n");
+				"Using noop/none.\n");
+			if (q->mq_ops) {
+				elevator_put(e);
+				return 0;
+			}
 			e = elevator_get("noop", false);
 		}
 	}
 
-	err = e->ops.sq.elevator_init_fn(q, e);
+	if (e->uses_mq)
+		err = e->ops.mq.init_sched(q, e);
+	else
+		err = e->ops.sq.elevator_init_fn(q, e);
 	if (err)
 		elevator_put(e);
 	return err;
@@ -234,7 +245,9 @@ EXPORT_SYMBOL(elevator_init);
 void elevator_exit(struct elevator_queue *e)
 {
 	mutex_lock(&e->sysfs_lock);
-	if (e->type->ops.sq.elevator_exit_fn)
+	if (e->uses_mq && e->type->ops.mq.exit_sched)
+		e->type->ops.mq.exit_sched(e);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn)
 		e->type->ops.sq.elevator_exit_fn(e);
 	mutex_unlock(&e->sysfs_lock);
 
@@ -253,6 +266,7 @@ void elv_rqhash_del(struct request_queue *q, struct request *rq)
 	if (ELV_ON_HASH(rq))
 		__elv_rqhash_del(rq);
 }
+EXPORT_SYMBOL_GPL(elv_rqhash_del);
 
 void elv_rqhash_add(struct request_queue *q, struct request *rq)
 {
@@ -262,6 +276,7 @@ void elv_rqhash_add(struct request_queue *q, struct request *rq)
 	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
 	rq->rq_flags |= RQF_HASHED;
 }
+EXPORT_SYMBOL_GPL(elv_rqhash_add);
 
 void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
 {
@@ -443,7 +458,9 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		return ELEVATOR_BACK_MERGE;
 	}
 
-	if (e->type->ops.sq.elevator_merge_fn)
+	if (e->uses_mq && e->type->ops.mq.request_merge)
+		return e->type->ops.mq.request_merge(q, req, bio);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_merge_fn)
 		return e->type->ops.sq.elevator_merge_fn(q, req, bio);
 
 	return ELEVATOR_NO_MERGE;
@@ -462,6 +479,9 @@ static bool elv_attempt_insert_merge(struct request_queue *q,
 	struct request *__rq;
 	bool ret;
 
+	if (WARN_ON_ONCE(q->elevator && q->elevator->uses_mq))
+		return false;
+
 	if (blk_queue_nomerges(q))
 		return false;
 
@@ -495,7 +515,9 @@ void elv_merged_request(struct request_queue *q, struct request *rq, int type)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.sq.elevator_merged_fn)
+	if (e->uses_mq && e->type->ops.mq.request_merged)
+		e->type->ops.mq.request_merged(q, rq, type);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_merged_fn)
 		e->type->ops.sq.elevator_merged_fn(q, rq, type);
 
 	if (type == ELEVATOR_BACK_MERGE)
@@ -508,10 +530,15 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
 			     struct request *next)
 {
 	struct elevator_queue *e = q->elevator;
-	const int next_sorted = next->rq_flags & RQF_SORTED;
-
-	if (next_sorted && e->type->ops.sq.elevator_merge_req_fn)
-		e->type->ops.sq.elevator_merge_req_fn(q, rq, next);
+	bool next_sorted = false;
+
+	if (e->uses_mq && e->type->ops.mq.requests_merged)
+		e->type->ops.mq.requests_merged(q, rq, next);
+	else if (e->type->ops.sq.elevator_merge_req_fn) {
+		next_sorted = next->rq_flags & RQF_SORTED;
+		if (next_sorted)
+			e->type->ops.sq.elevator_merge_req_fn(q, rq, next);
+	}
 
 	elv_rqhash_reposition(q, rq);
 
@@ -528,6 +555,9 @@ void elv_bio_merged(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
 	if (e->type->ops.sq.elevator_bio_merged_fn)
 		e->type->ops.sq.elevator_bio_merged_fn(q, rq, bio);
 }
@@ -682,8 +712,11 @@ struct request *elv_latter_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.sq.elevator_latter_req_fn)
+	if (e->uses_mq && e->type->ops.mq.next_request)
+		return e->type->ops.mq.next_request(q, rq);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_latter_req_fn)
 		return e->type->ops.sq.elevator_latter_req_fn(q, rq);
+
 	return NULL;
 }
 
@@ -691,7 +724,9 @@ struct request *elv_former_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.sq.elevator_former_req_fn)
+	if (e->uses_mq && e->type->ops.mq.former_request)
+		return e->type->ops.mq.former_request(q, rq);
+	if (!e->uses_mq && e->type->ops.sq.elevator_former_req_fn)
 		return e->type->ops.sq.elevator_former_req_fn(q, rq);
 	return NULL;
 }
@@ -701,6 +736,9 @@ int elv_set_request(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
+	if (WARN_ON_ONCE(e->uses_mq))
+		return 0;
+
 	if (e->type->ops.sq.elevator_set_req_fn)
 		return e->type->ops.sq.elevator_set_req_fn(q, rq, bio, gfp_mask);
 	return 0;
@@ -710,6 +748,9 @@ void elv_put_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
 	if (e->type->ops.sq.elevator_put_req_fn)
 		e->type->ops.sq.elevator_put_req_fn(rq);
 }
@@ -718,6 +759,9 @@ int elv_may_queue(struct request_queue *q, unsigned int op)
 {
 	struct elevator_queue *e = q->elevator;
 
+	if (WARN_ON_ONCE(e->uses_mq))
+		return 0;
+
 	if (e->type->ops.sq.elevator_may_queue_fn)
 		return e->type->ops.sq.elevator_may_queue_fn(q, op);
 
@@ -728,6 +772,9 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
 	/*
 	 * request is released from the driver, io must be done
 	 */
@@ -803,7 +850,7 @@ int elv_register_queue(struct request_queue *q)
 		}
 		kobject_uevent(&e->kobj, KOBJ_ADD);
 		e->registered = 1;
-		if (e->type->ops.sq.elevator_registered_fn)
+		if (!e->uses_mq && e->type->ops.sq.elevator_registered_fn)
 			e->type->ops.sq.elevator_registered_fn(q);
 	}
 	return error;
@@ -891,9 +938,14 @@ EXPORT_SYMBOL_GPL(elv_unregister);
 static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 {
 	struct elevator_queue *old = q->elevator;
-	bool registered = old->registered;
+	bool old_registered = false;
 	int err;
 
+	if (q->mq_ops) {
+		blk_mq_freeze_queue(q);
+		blk_mq_quiesce_queue(q);
+	}
+
 	/*
 	 * Turn on BYPASS and drain all requests w/ elevator private data.
 	 * Block layer doesn't call into a quiesced elevator - all requests
@@ -901,32 +953,52 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 * using INSERT_BACK.  All requests have SOFTBARRIER set and no
 	 * merge happens either.
 	 */
-	blk_queue_bypass_start(q);
+	if (old) {
+		old_registered = old->registered;
 
-	/* unregister and clear all auxiliary data of the old elevator */
-	if (registered)
-		elv_unregister_queue(q);
+		if (!q->mq_ops)
+			blk_queue_bypass_start(q);
 
-	spin_lock_irq(q->queue_lock);
-	ioc_clear_queue(q);
-	spin_unlock_irq(q->queue_lock);
+		/* unregister and clear all auxiliary data of the old elevator */
+		if (old_registered)
+			elv_unregister_queue(q);
+
+		spin_lock_irq(q->queue_lock);
+		ioc_clear_queue(q);
+		spin_unlock_irq(q->queue_lock);
+	}
 
 	/* allocate, init and register new elevator */
-	err = new_e->ops.sq.elevator_init_fn(q, new_e);
-	if (err)
-		goto fail_init;
+	if (new_e) {
+		if (new_e->uses_mq)
+			err = new_e->ops.mq.init_sched(q, new_e);
+		else
+			err = new_e->ops.sq.elevator_init_fn(q, new_e);
+		if (err)
+			goto fail_init;
 
-	if (registered) {
 		err = elv_register_queue(q);
 		if (err)
 			goto fail_register;
-	}
+	} else
+		q->elevator = NULL;
 
 	/* done, kill the old one and finish */
-	elevator_exit(old);
-	blk_queue_bypass_end(q);
+	if (old) {
+		elevator_exit(old);
+		if (!q->mq_ops)
+			blk_queue_bypass_end(q);
+	}
+
+	if (q->mq_ops) {
+		blk_mq_unfreeze_queue(q);
+		blk_mq_start_stopped_hw_queues(q, true);
+	}
 
-	blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+	if (new_e)
+		blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+	else
+		blk_add_trace_msg(q, "elv switch: none");
 
 	return 0;
 
@@ -934,9 +1006,16 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	elevator_exit(q->elevator);
 fail_init:
 	/* switch failed, restore and re-register old elevator */
-	q->elevator = old;
-	elv_register_queue(q);
-	blk_queue_bypass_end(q);
+	if (old) {
+		q->elevator = old;
+		elv_register_queue(q);
+		if (!q->mq_ops)
+			blk_queue_bypass_end(q);
+	}
+	if (q->mq_ops) {
+		blk_mq_unfreeze_queue(q);
+		blk_mq_start_stopped_hw_queues(q, true);
+	}
 
 	return err;
 }
@@ -949,8 +1028,11 @@ static int __elevator_change(struct request_queue *q, const char *name)
 	char elevator_name[ELV_NAME_MAX];
 	struct elevator_type *e;
 
-	if (!q->elevator)
-		return -ENXIO;
+	/*
+	 * Special case for mq, turn off scheduling
+	 */
+	if (q->mq_ops && !strncmp(name, "none", 4))
+		return elevator_switch(q, NULL);
 
 	strlcpy(elevator_name, name, sizeof(elevator_name));
 	e = elevator_get(strstrip(elevator_name), true);
@@ -959,11 +1041,23 @@ static int __elevator_change(struct request_queue *q, const char *name)
 		return -EINVAL;
 	}
 
-	if (!strcmp(elevator_name, q->elevator->type->elevator_name)) {
+	if (q->elevator &&
+	    !strcmp(elevator_name, q->elevator->type->elevator_name)) {
 		elevator_put(e);
 		return 0;
 	}
 
+	if (!e->uses_mq && q->mq_ops) {
+		printk(KERN_ERR "blk-mq-sched: elv %s does not support mq\n", elevator_name);
+		elevator_put(e);
+		return -EINVAL;
+	}
+	if (e->uses_mq && !q->mq_ops) {
+		printk(KERN_ERR "blk-mq-sched: elv %s is for mq\n", elevator_name);
+		elevator_put(e);
+		return -EINVAL;
+	}
+
 	return elevator_switch(q, e);
 }
 
@@ -985,7 +1079,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 {
 	int ret;
 
-	if (!q->elevator)
+	if (!q->mq_ops || q->request_fn)
 		return count;
 
 	ret = __elevator_change(q, name);
@@ -999,24 +1093,34 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 ssize_t elv_iosched_show(struct request_queue *q, char *name)
 {
 	struct elevator_queue *e = q->elevator;
-	struct elevator_type *elv;
+	struct elevator_type *elv = NULL;
 	struct elevator_type *__e;
 	int len = 0;
 
-	if (!q->elevator || !blk_queue_stackable(q))
+	if (!blk_queue_stackable(q))
 		return sprintf(name, "none\n");
 
-	elv = e->type;
+	if (!q->elevator)
+		len += sprintf(name+len, "[none] ");
+	else
+		elv = e->type;
 
 	spin_lock(&elv_list_lock);
 	list_for_each_entry(__e, &elv_list, list) {
-		if (!strcmp(elv->elevator_name, __e->elevator_name))
+		if (elv && !strcmp(elv->elevator_name, __e->elevator_name)) {
 			len += sprintf(name+len, "[%s] ", elv->elevator_name);
-		else
+			continue;
+		}
+		if (__e->uses_mq && q->mq_ops)
+			len += sprintf(name+len, "%s ", __e->elevator_name);
+		else if (!__e->uses_mq && !q->mq_ops)
 			len += sprintf(name+len, "%s ", __e->elevator_name);
 	}
 	spin_unlock(&elv_list_lock);
 
+	if (q->mq_ops && q->elevator)
+		len += sprintf(name+len, "none");
+
 	len += sprintf(len+name, "\n");
 	return len;
 }
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index afc81d77e471..73b58b5be6e0 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -22,6 +22,7 @@ struct blk_mq_hw_ctx {
 
 	unsigned long		flags;		/* BLK_MQ_F_* flags */
 
+	void			*sched_data;
 	struct request_queue	*queue;
 	struct blk_flush_queue	*fq;
 
@@ -156,6 +157,7 @@ enum {
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
+	BLK_MQ_S_SCHED_RESTART	= 2,
 
 	BLK_MQ_MAX_DEPTH	= 10240,
 
@@ -179,7 +181,6 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
-void blk_mq_insert_request(struct request *, bool, bool, bool);
 void blk_mq_free_request(struct request *rq);
 void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 2a9e966eed03..0cbf30a00186 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -77,6 +77,32 @@ struct elevator_ops
 	elevator_registered_fn *elevator_registered_fn;
 };
 
+struct blk_mq_alloc_data;
+struct blk_mq_hw_ctx;
+
+struct elevator_mq_ops {
+	int (*init_sched)(struct request_queue *, struct elevator_type *);
+	void (*exit_sched)(struct elevator_queue *);
+
+	bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
+	bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);
+	int (*request_merge)(struct request_queue *q, struct request **, struct bio *);
+	void (*request_merged)(struct request_queue *, struct request *, int);
+	void (*requests_merged)(struct request_queue *, struct request *, struct request *);
+	struct request *(*get_request)(struct request_queue *, unsigned int, struct blk_mq_alloc_data *);
+	bool (*put_request)(struct request *);
+	void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
+	void (*dispatch_requests)(struct blk_mq_hw_ctx *, struct list_head *);
+	bool (*has_work)(struct blk_mq_hw_ctx *);
+	void (*completed_request)(struct blk_mq_hw_ctx *, struct request *);
+	void (*started_request)(struct request *);
+	void (*requeue_request)(struct request *);
+	struct request *(*former_request)(struct request_queue *, struct request *);
+	struct request *(*next_request)(struct request_queue *, struct request *);
+	int (*get_rq_priv)(struct request_queue *, struct request *);
+	void (*put_rq_priv)(struct request_queue *, struct request *);
+};
+
 #define ELV_NAME_MAX	(16)
 
 struct elv_fs_entry {
@@ -96,12 +122,14 @@ struct elevator_type
 	/* fields provided by elevator implementation */
 	union {
 		struct elevator_ops sq;
+		struct elevator_mq_ops mq;
 	} ops;
 	size_t icq_size;	/* see iocontext.h */
 	size_t icq_align;	/* ditto */
 	struct elv_fs_entry *elevator_attrs;
 	char elevator_name[ELV_NAME_MAX];
 	struct module *elevator_owner;
+	bool uses_mq;
 
 	/* managed by elevator core */
 	char icq_cache_name[ELV_NAME_MAX + 5];	/* elvname + "_io_cq" */
@@ -125,6 +153,7 @@ struct elevator_queue
 	struct kobject kobj;
 	struct mutex sysfs_lock;
 	unsigned int registered:1;
+	unsigned int uses_mq:1;
 	DECLARE_HASHTABLE(hash, ELV_HASH_BITS);
 };
 
-- 
2.7.4

Re: [PATCH 5/7] blk-mq-sched: add framework for MQ capable IO schedulers

[Omar Sandoval]

Hey, Jens, a couple of minor nits below.

One bigger note: adding the blk_mq_sched_*() helpers and keeping the
blk_mq_*() helpers that they replaced seems risky. For example,
blk_mq_free_request() is superseded by blk_mq_sched_put_request(), but
we kept blk_mq_free_request(). There are definitely some codepaths that
are still using blk_mq_free_request() that are now wrong
(__nvme_submit_user_cmd() is the most obvious one I saw).

Can we get rid of the old, non-sched functions? Or maybe even make old
interface do the sched stuff instead of adding blk_mq_sched_*()?

On Wed, Dec 14, 2016 at 10:26:06PM -0700, Jens Axboe wrote:
> Signed-off-by: Jens Axboe <axboe@fb.com>
> ---
>  block/Makefile           |   2 +-
>  block/blk-core.c         |   7 +-
>  block/blk-exec.c         |   3 +-
>  block/blk-flush.c        |   7 +-
>  block/blk-mq-sched.c     | 375 +++++++++++++++++++++++++++++++++++++++++++++++
>  block/blk-mq-sched.h     | 190 ++++++++++++++++++++++++
>  block/blk-mq-tag.c       |   1 +
>  block/blk-mq.c           | 192 ++++++++++--------------
>  block/blk-mq.h           |   3 +
>  block/elevator.c         | 186 +++++++++++++++++------
>  include/linux/blk-mq.h   |   3 +-
>  include/linux/elevator.h |  29 ++++
>  12 files changed, 833 insertions(+), 165 deletions(-)
>  create mode 100644 block/blk-mq-sched.c
>  create mode 100644 block/blk-mq-sched.h
> 

[snip]

> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index 8d1cec8e25d1..d10a246a3bc7 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -2267,10 +2229,10 @@ static int blk_mq_queue_reinit_dead(unsigned int cpu)
>   * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list
>   * and set bit0 in pending bitmap as ctx1->index_hw is still zero.
>   *
> - * And then while running hw queue, flush_busy_ctxs() finds bit0 is set in
> - * pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
> - * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list
> - * is ignored.
> + * And then while running hw queue, blk_mq_flush_busy_ctxs() finds bit0 is set
> + * in pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
> + * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list is
> + * ignored.
>   */

This belongs in patch 4 where flush_busy_ctxs() got renamed.

>  static int blk_mq_queue_reinit_prepare(unsigned int cpu)
>  {
> diff --git a/block/blk-mq.h b/block/blk-mq.h
> index e59f5ca520a2..a5ddc860b220 100644
> --- a/block/blk-mq.h
> +++ b/block/blk-mq.h
> @@ -47,6 +47,9 @@ struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
>   */
>  void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
>  				bool at_head);
> +void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
> +				struct list_head *list);
> +void blk_mq_process_sw_list(struct blk_mq_hw_ctx *hctx);

Looks like the declaration of blk_mq_process_sw_list() survived a rebase
even though it doesn't exist anymore.

[snip]

Re: [PATCH 5/7] blk-mq-sched: add framework for MQ capable IO schedulers

[Jens Axboe]

On Thu, Dec 15 2016, Omar Sandoval wrote:
> Hey, Jens, a couple of minor nits below.
> 
> One bigger note: adding the blk_mq_sched_*() helpers and keeping the
> blk_mq_*() helpers that they replaced seems risky. For example,
> blk_mq_free_request() is superseded by blk_mq_sched_put_request(), but
> we kept blk_mq_free_request(). There are definitely some codepaths that
> are still using blk_mq_free_request() that are now wrong
> (__nvme_submit_user_cmd() is the most obvious one I saw).
> 
> Can we get rid of the old, non-sched functions? Or maybe even make old
> interface do the sched stuff instead of adding blk_mq_sched_*()?

You are right, that is a concern. I'll think of some ways to lessen that
risk, it's much better to have build time breakage than runtime.

> > diff --git a/block/blk-mq.c b/block/blk-mq.c
> > index 8d1cec8e25d1..d10a246a3bc7 100644
> > --- a/block/blk-mq.c
> > +++ b/block/blk-mq.c
> > @@ -2267,10 +2229,10 @@ static int blk_mq_queue_reinit_dead(unsigned int cpu)
> >   * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list
> >   * and set bit0 in pending bitmap as ctx1->index_hw is still zero.
> >   *
> > - * And then while running hw queue, flush_busy_ctxs() finds bit0 is set in
> > - * pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
> > - * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list
> > - * is ignored.
> > + * And then while running hw queue, blk_mq_flush_busy_ctxs() finds bit0 is set
> > + * in pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
> > + * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list is
> > + * ignored.
> >   */
> 
> This belongs in patch 4 where flush_busy_ctxs() got renamed.

Fixed, thanks!

> >  static int blk_mq_queue_reinit_prepare(unsigned int cpu)
> >  {
> > diff --git a/block/blk-mq.h b/block/blk-mq.h
> > index e59f5ca520a2..a5ddc860b220 100644
> > --- a/block/blk-mq.h
> > +++ b/block/blk-mq.h
> > @@ -47,6 +47,9 @@ struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
> >   */
> >  void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
> >  				bool at_head);
> > +void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
> > +				struct list_head *list);
> > +void blk_mq_process_sw_list(struct blk_mq_hw_ctx *hctx);
> 
> Looks like the declaration of blk_mq_process_sw_list() survived a rebase
> even though it doesn't exist anymore.

Indeed, now killed.

-- 
Jens Axboe

Re: [PATCH 5/7] blk-mq-sched: add framework for MQ capable IO schedulers

[Jens Axboe]

On 12/15/2016 12:29 PM, Omar Sandoval wrote:
> Hey, Jens, a couple of minor nits below.
> 
> One bigger note: adding the blk_mq_sched_*() helpers and keeping the
> blk_mq_*() helpers that they replaced seems risky. For example,
> blk_mq_free_request() is superseded by blk_mq_sched_put_request(), but
> we kept blk_mq_free_request(). There are definitely some codepaths that
> are still using blk_mq_free_request() that are now wrong
> (__nvme_submit_user_cmd() is the most obvious one I saw).
> 
> Can we get rid of the old, non-sched functions? Or maybe even make old
> interface do the sched stuff instead of adding blk_mq_sched_*()?

I fixed this up. blk_mq_free_request() is now what we still use as an
exported interface, and that just calls blk_mq_sched_put_request().  The
old (__)blk_mq_free_request() are now (__)blk_mq_finish_request() and
internal only.

-- 
Jens Axboe

[PATCH 6/7] mq-deadline: add blk-mq adaptation of the deadline IO scheduler

[Jens Axboe]

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/Kconfig.iosched |   6 +
 block/Makefile        |   1 +
 block/mq-deadline.c   | 638 ++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 645 insertions(+)
 create mode 100644 block/mq-deadline.c

diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 421bef9c4c48..490ef2850fae 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -32,6 +32,12 @@ 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
diff --git a/block/Makefile b/block/Makefile
index 2eee9e1bb6db..3ee0abd7205a 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
+obj-$(CONFIG_MQ_IOSCHED_DEADLINE)	+= mq-deadline.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
new file mode 100644
index 000000000000..6114779cdc68
--- /dev/null
+++ b/block/mq-deadline.c
@@ -0,0 +1,638 @@
+/*
+ *  MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler,
+ *  for the blk-mq scheduling framework
+ *
+ *  Copyright (C) 2016 Jens Axboe <axboe@kernel.dk>
+ */
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/elevator.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <linux/sbitmap.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
+
+static inline bool dd_rq_is_shadow(struct request *rq)
+{
+	return rq->rq_flags & RQF_ALLOCED;
+}
+
+/*
+ * See Documentation/block/deadline-iosched.txt
+ */
+static const int read_expire = HZ / 2;  /* max time before a read is submitted. */
+static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
+static const int writes_starved = 2;    /* max times reads can starve a write */
+static const int fifo_batch = 16;       /* # of sequential requests treated as one
+				     by the above parameters. For throughput. */
+
+struct deadline_data {
+	/*
+	 * run time data
+	 */
+
+	/*
+	 * requests (deadline_rq s) are present on both sort_list and fifo_list
+	 */
+	struct rb_root sort_list[2];
+	struct list_head fifo_list[2];
+
+	/*
+	 * next in sort order. read, write or both are NULL
+	 */
+	struct request *next_rq[2];
+	unsigned int batching;		/* number of sequential requests made */
+	unsigned int starved;		/* times reads have starved writes */
+
+	/*
+	 * settings that change how the i/o scheduler behaves
+	 */
+	int fifo_expire[2];
+	int fifo_batch;
+	int writes_starved;
+	int front_merges;
+
+	spinlock_t lock;
+	struct list_head dispatch;
+	struct blk_mq_tags *tags;
+	atomic_t wait_index;
+};
+
+static inline struct rb_root *
+deadline_rb_root(struct deadline_data *dd, struct request *rq)
+{
+	return &dd->sort_list[rq_data_dir(rq)];
+}
+
+/*
+ * get the request after `rq' in sector-sorted order
+ */
+static inline struct request *
+deadline_latter_request(struct request *rq)
+{
+	struct rb_node *node = rb_next(&rq->rb_node);
+
+	if (node)
+		return rb_entry_rq(node);
+
+	return NULL;
+}
+
+static void
+deadline_add_rq_rb(struct deadline_data *dd, struct request *rq)
+{
+	struct rb_root *root = deadline_rb_root(dd, rq);
+
+	elv_rb_add(root, rq);
+}
+
+static inline void
+deadline_del_rq_rb(struct deadline_data *dd, struct request *rq)
+{
+	const int data_dir = rq_data_dir(rq);
+
+	if (dd->next_rq[data_dir] == rq)
+		dd->next_rq[data_dir] = deadline_latter_request(rq);
+
+	elv_rb_del(deadline_rb_root(dd, rq), rq);
+}
+
+/*
+ * remove rq from rbtree and fifo.
+ */
+static void deadline_remove_request(struct request_queue *q, struct request *rq)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	list_del_init(&rq->queuelist);
+	deadline_del_rq_rb(dd, rq);
+
+	elv_rqhash_del(q, rq);
+	if (q->last_merge == rq)
+		q->last_merge = NULL;
+}
+
+static void dd_request_merged(struct request_queue *q, struct request *req,
+			      int type)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	/*
+	 * if the merge was a front merge, we need to reposition request
+	 */
+	if (type == ELEVATOR_FRONT_MERGE) {
+		elv_rb_del(deadline_rb_root(dd, req), req);
+		deadline_add_rq_rb(dd, req);
+	}
+}
+
+static void dd_merged_requests(struct request_queue *q, struct request *req,
+			       struct request *next)
+{
+	/*
+	 * if next expires before rq, assign its expire time to rq
+	 * and move into next position (next will be deleted) in fifo
+	 */
+	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
+		if (time_before((unsigned long)next->fifo_time,
+				(unsigned long)req->fifo_time)) {
+			list_move(&req->queuelist, &next->queuelist);
+			req->fifo_time = next->fifo_time;
+		}
+	}
+
+	/*
+	 * kill knowledge of next, this one is a goner
+	 */
+	deadline_remove_request(q, next);
+}
+
+/*
+ * move an entry to dispatch queue
+ */
+static void
+deadline_move_request(struct deadline_data *dd, struct request *rq)
+{
+	const int data_dir = rq_data_dir(rq);
+
+	dd->next_rq[READ] = NULL;
+	dd->next_rq[WRITE] = NULL;
+	dd->next_rq[data_dir] = deadline_latter_request(rq);
+
+	/*
+	 * take it off the sort and fifo list
+	 */
+	deadline_remove_request(rq->q, rq);
+}
+
+/*
+ * deadline_check_fifo returns 0 if there are no expired requests on the fifo,
+ * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
+ */
+static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
+{
+	struct request *rq = rq_entry_fifo(dd->fifo_list[ddir].next);
+
+	/*
+	 * rq is expired!
+	 */
+	if (time_after_eq(jiffies, (unsigned long)rq->fifo_time))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * deadline_dispatch_requests selects the best request according to
+ * read/write expire, fifo_batch, etc
+ */
+static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+	struct request *rq;
+	bool reads, writes;
+	int data_dir;
+
+	spin_lock(&dd->lock);
+
+	if (!list_empty(&dd->dispatch)) {
+		rq = list_first_entry(&dd->dispatch, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		goto done;
+	}
+
+	reads = !list_empty(&dd->fifo_list[READ]);
+	writes = !list_empty(&dd->fifo_list[WRITE]);
+
+	/*
+	 * batches are currently reads XOR writes
+	 */
+	if (dd->next_rq[WRITE])
+		rq = dd->next_rq[WRITE];
+	else
+		rq = dd->next_rq[READ];
+
+	if (rq && dd->batching < dd->fifo_batch)
+		/* we have a next request are still entitled to batch */
+		goto dispatch_request;
+
+	/*
+	 * at this point we are not running a batch. select the appropriate
+	 * data direction (read / write)
+	 */
+
+	if (reads) {
+		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ]));
+
+		if (writes && (dd->starved++ >= dd->writes_starved))
+			goto dispatch_writes;
+
+		data_dir = READ;
+
+		goto dispatch_find_request;
+	}
+
+	/*
+	 * there are either no reads or writes have been starved
+	 */
+
+	if (writes) {
+dispatch_writes:
+		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[WRITE]));
+
+		dd->starved = 0;
+
+		data_dir = WRITE;
+
+		goto dispatch_find_request;
+	}
+
+	spin_unlock(&dd->lock);
+	return NULL;
+
+dispatch_find_request:
+	/*
+	 * we are not running a batch, find best request for selected data_dir
+	 */
+	if (deadline_check_fifo(dd, data_dir) || !dd->next_rq[data_dir]) {
+		/*
+		 * A deadline has expired, the last request was in the other
+		 * direction, or we have run out of higher-sectored requests.
+		 * Start again from the request with the earliest expiry time.
+		 */
+		rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+	} else {
+		/*
+		 * The last req was the same dir and we have a next request in
+		 * sort order. No expired requests so continue on from here.
+		 */
+		rq = dd->next_rq[data_dir];
+	}
+
+	dd->batching = 0;
+
+dispatch_request:
+	/*
+	 * rq is the selected appropriate request.
+	 */
+	dd->batching++;
+	deadline_move_request(dd, rq);
+done:
+	rq->rq_flags |= RQF_STARTED;
+	spin_unlock(&dd->lock);
+	return rq;
+}
+
+static void dd_dispatch_requests(struct blk_mq_hw_ctx *hctx,
+				 struct list_head *rq_list)
+{
+	blk_mq_sched_dispatch_shadow_requests(hctx, rq_list, __dd_dispatch_request);
+}
+
+static void dd_exit_queue(struct elevator_queue *e)
+{
+	struct deadline_data *dd = e->elevator_data;
+
+	BUG_ON(!list_empty(&dd->fifo_list[READ]));
+	BUG_ON(!list_empty(&dd->fifo_list[WRITE]));
+
+	blk_mq_sched_free_requests(dd->tags);
+	kfree(dd);
+}
+
+/*
+ * initialize elevator private data (deadline_data).
+ */
+static int dd_init_queue(struct request_queue *q, struct elevator_type *e)
+{
+	struct deadline_data *dd;
+	struct elevator_queue *eq;
+
+	eq = elevator_alloc(q, e);
+	if (!eq)
+		return -ENOMEM;
+
+	dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
+	if (!dd) {
+		kobject_put(&eq->kobj);
+		return -ENOMEM;
+	}
+	eq->elevator_data = dd;
+
+	dd->tags = blk_mq_sched_alloc_requests(256, q->node);
+	if (!dd->tags) {
+		kfree(dd);
+		kobject_put(&eq->kobj);
+		return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&dd->fifo_list[READ]);
+	INIT_LIST_HEAD(&dd->fifo_list[WRITE]);
+	dd->sort_list[READ] = RB_ROOT;
+	dd->sort_list[WRITE] = RB_ROOT;
+	dd->fifo_expire[READ] = read_expire;
+	dd->fifo_expire[WRITE] = write_expire;
+	dd->writes_starved = writes_starved;
+	dd->front_merges = 1;
+	dd->fifo_batch = fifo_batch;
+	spin_lock_init(&dd->lock);
+	INIT_LIST_HEAD(&dd->dispatch);
+	atomic_set(&dd->wait_index, 0);
+
+	q->elevator = eq;
+	return 0;
+}
+
+static int dd_request_merge(struct request_queue *q, struct request **rq,
+			    struct bio *bio)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+	sector_t sector = bio_end_sector(bio);
+	struct request *__rq;
+
+	if (!dd->front_merges)
+		return ELEVATOR_NO_MERGE;
+
+	__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
+	if (__rq) {
+		BUG_ON(sector != blk_rq_pos(__rq));
+
+		if (elv_bio_merge_ok(__rq, bio)) {
+			*rq = __rq;
+			return ELEVATOR_FRONT_MERGE;
+		}
+	}
+
+	return ELEVATOR_NO_MERGE;
+}
+
+static bool dd_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
+{
+	struct request_queue *q = hctx->queue;
+	struct deadline_data *dd = q->elevator->elevator_data;
+	int ret;
+
+	spin_lock(&dd->lock);
+	ret = blk_mq_sched_try_merge(q, bio);
+	spin_unlock(&dd->lock);
+
+	return ret;
+}
+
+/*
+ * add rq to rbtree and fifo
+ */
+static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+			      bool at_head)
+{
+	struct request_queue *q = hctx->queue;
+	struct deadline_data *dd = q->elevator->elevator_data;
+	const int data_dir = rq_data_dir(rq);
+
+	blk_mq_sched_request_inserted(rq);
+
+	/*
+	 * If we're trying to insert a real request, just send it directly
+	 * to the hardware dispatch list. This only happens for a requeue,
+	 * or FUA/FLUSH requests.
+	 */
+	if (!dd_rq_is_shadow(rq)) {
+		spin_lock(&hctx->lock);
+		list_add_tail(&rq->queuelist, &hctx->dispatch);
+		spin_unlock(&hctx->lock);
+		return;
+	}
+
+	if (at_head || rq->cmd_type != REQ_TYPE_FS) {
+		if (at_head)
+			list_add(&rq->queuelist, &dd->dispatch);
+		else
+			list_add_tail(&rq->queuelist, &dd->dispatch);
+	} else {
+		deadline_add_rq_rb(dd, rq);
+
+		if (rq_mergeable(rq)) {
+			elv_rqhash_add(q, rq);
+			if (!q->last_merge)
+				q->last_merge = rq;
+		}
+
+		/*
+		 * set expire time and add to fifo list
+		 */
+		rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
+		list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]);
+	}
+}
+
+static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
+			       struct list_head *list, bool at_head)
+{
+	struct request_queue *q = hctx->queue;
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	spin_lock(&dd->lock);
+	while (!list_empty(list)) {
+		struct request *rq;
+
+		rq = list_first_entry(list, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		dd_insert_request(hctx, rq, at_head);
+	}
+	spin_unlock(&dd->lock);
+}
+
+static struct request *dd_get_request(struct request_queue *q, unsigned int op,
+				      struct blk_mq_alloc_data *data)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+	struct request *rq;
+
+	/*
+	 * The flush machinery intercepts before we insert the request. As
+	 * a work-around, just hand it back a real request.
+	 */
+	if (unlikely(op & (REQ_PREFLUSH | REQ_FUA)))
+		rq = __blk_mq_alloc_request(data, op);
+	else {
+		rq = blk_mq_sched_alloc_shadow_request(q, data, dd->tags, &dd->wait_index);
+		if (rq)
+			blk_mq_rq_ctx_init(q, data->ctx, rq, op);
+	}
+
+	return rq;
+}
+
+static bool dd_put_request(struct request *rq)
+{
+	/*
+	 * If it's a real request, we just have to free it. For a shadow
+	 * request, we should only free it if we haven't started it. A
+	 * started request is mapped to a real one, and the real one will
+	 * free it. We can get here with request merges, since we then
+	 * free the request before we start/issue it.
+	 */
+	if (!dd_rq_is_shadow(rq))
+		return false;
+
+	if (!(rq->rq_flags & RQF_STARTED)) {
+		struct request_queue *q = rq->q;
+		struct deadline_data *dd = q->elevator->elevator_data;
+
+		/*
+		 * IO completion would normally do this, but if we merge
+		 * and free before we issue the request, drop both the
+		 * tag and queue ref
+		 */
+		blk_mq_sched_free_shadow_request(dd->tags, rq);
+		blk_queue_exit(q);
+	}
+
+	return true;
+}
+
+static void dd_completed_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
+{
+	struct request *sched_rq = rq->end_io_data;
+
+	/*
+	 * sched_rq can be NULL, if we haven't setup the shadow yet
+	 * because we failed getting one.
+	 */
+	if (sched_rq) {
+		struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+
+		blk_mq_sched_free_shadow_request(dd->tags, sched_rq);
+		blk_mq_start_stopped_hw_queue(hctx, true);
+	}
+}
+
+static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+
+	return !list_empty_careful(&dd->dispatch) ||
+		!list_empty_careful(&dd->fifo_list[0]) ||
+		!list_empty_careful(&dd->fifo_list[1]);
+}
+
+/*
+ * sysfs parts below
+ */
+static ssize_t
+deadline_var_show(int var, char *page)
+{
+	return sprintf(page, "%d\n", var);
+}
+
+static ssize_t
+deadline_var_store(int *var, const char *page, size_t count)
+{
+	char *p = (char *) page;
+
+	*var = simple_strtol(p, &p, 10);
+	return count;
+}
+
+#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct deadline_data *dd = e->elevator_data;			\
+	int __data = __VAR;						\
+	if (__CONV)							\
+		__data = jiffies_to_msecs(__data);			\
+	return deadline_var_show(__data, (page));			\
+}
+SHOW_FUNCTION(deadline_read_expire_show, dd->fifo_expire[READ], 1);
+SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1);
+SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0);
+SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 0);
+SHOW_FUNCTION(deadline_fifo_batch_show, dd->fifo_batch, 0);
+#undef SHOW_FUNCTION
+
+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct deadline_data *dd = e->elevator_data;			\
+	int __data;							\
+	int ret = deadline_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	if (__CONV)							\
+		*(__PTR) = msecs_to_jiffies(__data);			\
+	else								\
+		*(__PTR) = __data;					\
+	return ret;							\
+}
+STORE_FUNCTION(deadline_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0);
+STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0);
+STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
+#undef STORE_FUNCTION
+
+#define DD_ATTR(name) \
+	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
+				      deadline_##name##_store)
+
+static struct elv_fs_entry deadline_attrs[] = {
+	DD_ATTR(read_expire),
+	DD_ATTR(write_expire),
+	DD_ATTR(writes_starved),
+	DD_ATTR(front_merges),
+	DD_ATTR(fifo_batch),
+	__ATTR_NULL
+};
+
+static struct elevator_type mq_deadline = {
+	.ops.mq = {
+		.get_request		= dd_get_request,
+		.put_request		= dd_put_request,
+		.insert_requests	= dd_insert_requests,
+		.dispatch_requests	= dd_dispatch_requests,
+		.completed_request	= dd_completed_request,
+		.next_request		= elv_rb_latter_request,
+		.former_request		= elv_rb_former_request,
+		.bio_merge		= dd_bio_merge,
+		.request_merge		= dd_request_merge,
+		.requests_merged	= dd_merged_requests,
+		.request_merged		= dd_request_merged,
+		.has_work		= dd_has_work,
+		.init_sched		= dd_init_queue,
+		.exit_sched		= dd_exit_queue,
+	},
+
+	.uses_mq	= true,
+	.elevator_attrs = deadline_attrs,
+	.elevator_name = "mq-deadline",
+	.elevator_owner = THIS_MODULE,
+};
+
+static int __init deadline_init(void)
+{
+	return elv_register(&mq_deadline);
+}
+
+static void __exit deadline_exit(void)
+{
+	elv_unregister(&mq_deadline);
+}
+
+module_init(deadline_init);
+module_exit(deadline_exit);
+
+MODULE_AUTHOR("Jens Axboe");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MQ deadline IO scheduler");
-- 
2.7.4

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

[Jens Axboe]

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/Kconfig.iosched   | 43 +++++++++++++++++++++++++++++++++++++------
 block/blk-mq-sched.c    | 19 +++++++++++++++++++
 block/blk-mq-sched.h    |  2 ++
 block/blk-mq.c          |  3 +++
 block/elevator.c        |  5 ++++-
 drivers/nvme/host/pci.c |  1 +
 include/linux/blk-mq.h  |  1 +
 7 files changed, 67 insertions(+), 7 deletions(-)

diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 490ef2850fae..96216cf18560 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
+
+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.
+
 endmenu
 
 endif
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 02ad17258666..606d519b42ee 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -373,3 +373,22 @@ void blk_mq_sched_request_inserted(struct request *rq)
 	trace_block_rq_insert(rq->q, rq);
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
+
+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 b68dccc0190e..e398412d3fcf 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -28,6 +28,8 @@ void blk_mq_sched_request_inserted(struct request *rq);
 bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio);
 bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
 
+int blk_mq_sched_init(struct request_queue *q);
+
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
 
 static inline bool
diff --git a/block/blk-mq.c b/block/blk-mq.c
index d10a246a3bc7..48c28e1cb42a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2101,6 +2101,9 @@ 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 6d39197768c1..7ad906689833 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 d6e6bce93d0c..063410d9b3cc 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1188,6 +1188,7 @@ 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 73b58b5be6e0..5fffccf3b95f 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