Merge branch 'elevator-switch-6.19' into for-6.19/block

Merge elevator switching improvements from Nilay:

"This patchset reorganizes the elevator switch path used during both
 nr_hw_queues update and elv_iosched_store() operations to address a
 recently reported lockdep splat [1].

 The warning highlights a locking dependency between ->freeze_lock and
 ->elevator_lock on pcpu_alloc_mutex, triggered when the Kyber scheduler
 dynamically allocates its private scheduling data. The fix is to ensure
 that such allocations occur outside the locked sections, thus
 eliminating the dependency chain.

 While working on this, it also became evident that the nr_hw_queue
 update code maintains two disjoint xarrays—one for elevator tags and
 another for elevator type—both serving the same purpose. Unifying these
 into a single elv_change_ctx structure improves clarity and
 maintainability.

 This series therefore implements five patches:
 The first perparatory patch unifies elevator tags and type xarrays. It
 combines both xarrays into a single struct elv_change_ctx, simplifying
 per-queue elevator state management.

 The second patch is aimed to group together all elevator-related
 resources that share the same lifetime and as a first step we move the
 elevator tags pointer from struct elv_change_ctx into the newly
 introduced struct elevator_resources. The subsequent patch extends the
 struct elevator_resources to include other elevator-related data.

 The third patch introduce ->alloc_sched_data and ->free_sched_data
 elevator ops which could be then used to safely allocate and free
 scheduler data.

 The fourth patch now builds upon the previous patch and starts using
 the newly introduced alloc/free sched data methods in the earlier patch
 during elevator switch and nr_hw_queue update. And while doing so, it's
 ensured that sched data allocation and free happens before we acquire
 ->freeze_lock and ->elevator_lock thus preventing its dependency on
 pcpu_alloc_mutex.

 The last patch of this series converts Kyber scheduler to use the new
 methods inroduced in the previous patch. It hooks Kyber’s scheduler
 data allocation and teardown logic from ->init_sched and ->exit_sched
 into the new methods, ensuring memory operations are performed outside
 locked sections.

 Together, these changes simplify the elevator switch logic and prevent
 the reported lockdep splat."

Link: https://lore.kernel.org/linux-block/20251113090619.2030737-1-nilay@linux.ibm.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>

* elevator-switch-6.19:
  block: define alloc_sched_data and free_sched_data methods for kyber
  block: use {alloc|free}_sched data methods
  block: introduce alloc_sched_data and free_sched_data elevator methods
  block: move elevator tags into struct elevator_resources
  block: unify elevator tags and type xarrays into struct elv_change_ctx

7 files changed, 248 insertions, 102 deletions

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 97b69fbe26f6..e26898128a7e 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -427,11 +427,25 @@ void blk_mq_free_sched_tags(struct elevator_tags *et,
 	kfree(et);
 }
 
-void blk_mq_free_sched_tags_batch(struct xarray *et_table,
+void blk_mq_free_sched_res(struct elevator_resources *res,
+		struct elevator_type *type,
+		struct blk_mq_tag_set *set)
+{
+	if (res->et) {
+		blk_mq_free_sched_tags(res->et, set);
+		res->et = NULL;
+	}
+	if (res->data) {
+		blk_mq_free_sched_data(type, res->data);
+		res->data = NULL;
+	}
+}
+
+void blk_mq_free_sched_res_batch(struct xarray *elv_tbl,
 		struct blk_mq_tag_set *set)
 {
 	struct request_queue *q;
-	struct elevator_tags *et;
+	struct elv_change_ctx *ctx;
 
 	lockdep_assert_held_write(&set->update_nr_hwq_lock);
 
@@ -444,13 +458,46 @@ void blk_mq_free_sched_tags_batch(struct xarray *et_table,
 		 * concurrently.
 		 */
 		if (q->elevator) {
-			et = xa_load(et_table, q->id);
-			if (unlikely(!et))
+			ctx = xa_load(elv_tbl, q->id);
+			if (!ctx) {
 				WARN_ON_ONCE(1);
-			else
-				blk_mq_free_sched_tags(et, set);
+				continue;
+			}
+			blk_mq_free_sched_res(&ctx->res, ctx->type, set);
+		}
+	}
+}
+
+void blk_mq_free_sched_ctx_batch(struct xarray *elv_tbl)
+{
+	unsigned long i;
+	struct elv_change_ctx *ctx;
+
+	xa_for_each(elv_tbl, i, ctx) {
+		xa_erase(elv_tbl, i);
+		kfree(ctx);
+	}
+}
+
+int blk_mq_alloc_sched_ctx_batch(struct xarray *elv_tbl,
+		struct blk_mq_tag_set *set)
+{
+	struct request_queue *q;
+	struct elv_change_ctx *ctx;
+
+	lockdep_assert_held_write(&set->update_nr_hwq_lock);
+
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		ctx = kzalloc(sizeof(struct elv_change_ctx), GFP_KERNEL);
+		if (!ctx)
+			return -ENOMEM;
+
+		if (xa_insert(elv_tbl, q->id, ctx, GFP_KERNEL)) {
+			kfree(ctx);
+			return -ENOMEM;
 		}
 	}
+	return 0;
 }
 
 struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set,
@@ -497,12 +544,33 @@ out:
 	return NULL;
 }
 
-int blk_mq_alloc_sched_tags_batch(struct xarray *et_table,
+int blk_mq_alloc_sched_res(struct request_queue *q,
+		struct elevator_type *type,
+		struct elevator_resources *res,
+		unsigned int nr_hw_queues)
+{
+	struct blk_mq_tag_set *set = q->tag_set;
+
+	res->et = blk_mq_alloc_sched_tags(set, nr_hw_queues,
+			blk_mq_default_nr_requests(set));
+	if (!res->et)
+		return -ENOMEM;
+
+	res->data = blk_mq_alloc_sched_data(q, type);
+	if (IS_ERR(res->data)) {
+		blk_mq_free_sched_tags(res->et, set);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int blk_mq_alloc_sched_res_batch(struct xarray *elv_tbl,
 		struct blk_mq_tag_set *set, unsigned int nr_hw_queues)
 {
+	struct elv_change_ctx *ctx;
 	struct request_queue *q;
-	struct elevator_tags *et;
-	gfp_t gfp = GFP_NOIO | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY;
+	int ret = -ENOMEM;
 
 	lockdep_assert_held_write(&set->update_nr_hwq_lock);
 
@@ -515,39 +583,44 @@ int blk_mq_alloc_sched_tags_batch(struct xarray *et_table,
 		 * concurrently.
 		 */
 		if (q->elevator) {
-			et = blk_mq_alloc_sched_tags(set, nr_hw_queues,
-					blk_mq_default_nr_requests(set));
-			if (!et)
+			ctx = xa_load(elv_tbl, q->id);
+			if (WARN_ON_ONCE(!ctx)) {
+				ret = -ENOENT;
+				goto out_unwind;
+			}
+
+			ret = blk_mq_alloc_sched_res(q, q->elevator->type,
+					&ctx->res, nr_hw_queues);
+			if (ret)
 				goto out_unwind;
-			if (xa_insert(et_table, q->id, et, gfp))
-				goto out_free_tags;
 		}
 	}
 	return 0;
-out_free_tags:
-	blk_mq_free_sched_tags(et, set);
+
 out_unwind:
 	list_for_each_entry_continue_reverse(q, &set->tag_list, tag_set_list) {
 		if (q->elevator) {
-			et = xa_load(et_table, q->id);
-			if (et)
-				blk_mq_free_sched_tags(et, set);
+			ctx = xa_load(elv_tbl, q->id);
+			if (ctx)
+				blk_mq_free_sched_res(&ctx->res,
+						ctx->type, set);
 		}
 	}
-	return -ENOMEM;
+	return ret;
 }
 
 /* caller must have a reference to @e, will grab another one if successful */
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e,
-		struct elevator_tags *et)
+		struct elevator_resources *res)
 {
 	unsigned int flags = q->tag_set->flags;
+	struct elevator_tags *et = res->et;
 	struct blk_mq_hw_ctx *hctx;
 	struct elevator_queue *eq;
 	unsigned long i;
 	int ret;
 
-	eq = elevator_alloc(q, e, et);
+	eq = elevator_alloc(q, e, res);
 	if (!eq)
 		return -ENOMEM;
 
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 8e21a6b1415d..02c40a72e959 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -19,18 +19,52 @@ void __blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
 
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e,
-		struct elevator_tags *et);
+		struct elevator_resources *res);
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
 void blk_mq_sched_free_rqs(struct request_queue *q);
 
 struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set,
 		unsigned int nr_hw_queues, unsigned int nr_requests);
-int blk_mq_alloc_sched_tags_batch(struct xarray *et_table,
+int blk_mq_alloc_sched_res(struct request_queue *q,
+		struct elevator_type *type,
+		struct elevator_resources *res,
+		unsigned int nr_hw_queues);
+int blk_mq_alloc_sched_res_batch(struct xarray *elv_tbl,
 		struct blk_mq_tag_set *set, unsigned int nr_hw_queues);
+int blk_mq_alloc_sched_ctx_batch(struct xarray *elv_tbl,
+		struct blk_mq_tag_set *set);
+void blk_mq_free_sched_ctx_batch(struct xarray *elv_tbl);
 void blk_mq_free_sched_tags(struct elevator_tags *et,
 		struct blk_mq_tag_set *set);
-void blk_mq_free_sched_tags_batch(struct xarray *et_table,
+void blk_mq_free_sched_res(struct elevator_resources *res,
+		struct elevator_type *type,
+		struct blk_mq_tag_set *set);
+void blk_mq_free_sched_res_batch(struct xarray *et_table,
 		struct blk_mq_tag_set *set);
+/*
+ * blk_mq_alloc_sched_data() - Allocates scheduler specific data
+ * Returns:
+ *         - Pointer to allocated data on success
+ *         - NULL if no allocation needed
+ *         - ERR_PTR(-ENOMEM) in case of failure
+ */
+static inline void *blk_mq_alloc_sched_data(struct request_queue *q,
+		struct elevator_type *e)
+{
+	void *sched_data;
+
+	if (!e || !e->ops.alloc_sched_data)
+		return NULL;
+
+	sched_data = e->ops.alloc_sched_data(q);
+	return (sched_data) ?: ERR_PTR(-ENOMEM);
+}
+
+static inline void blk_mq_free_sched_data(struct elevator_type *e, void *data)
+{
+	if (e && e->ops.free_sched_data)
+		e->ops.free_sched_data(data);
+}
 
 static inline void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b2fdeaac0efb..0d38daaa4705 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4989,27 +4989,28 @@ struct elevator_tags *blk_mq_update_nr_requests(struct request_queue *q,
  * Switch back to the elevator type stored in the xarray.
  */
 static void blk_mq_elv_switch_back(struct request_queue *q,
-		struct xarray *elv_tbl, struct xarray *et_tbl)
+		struct xarray *elv_tbl)
 {
-	struct elevator_type *e = xa_load(elv_tbl, q->id);
-	struct elevator_tags *t = xa_load(et_tbl, q->id);
+	struct elv_change_ctx *ctx = xa_load(elv_tbl, q->id);
+
+	if (WARN_ON_ONCE(!ctx))
+		return;
 
 	/* The elv_update_nr_hw_queues unfreezes the queue. */
-	elv_update_nr_hw_queues(q, e, t);
+	elv_update_nr_hw_queues(q, ctx);
 
 	/* Drop the reference acquired in blk_mq_elv_switch_none. */
-	if (e)
-		elevator_put(e);
+	if (ctx->type)
+		elevator_put(ctx->type);
 }
 
 /*
- * Stores elevator type in xarray and set current elevator to none. It uses
- * q->id as an index to store the elevator type into the xarray.
+ * Stores elevator name and type in ctx and set current elevator to none.
  */
 static int blk_mq_elv_switch_none(struct request_queue *q,
 		struct xarray *elv_tbl)
 {
-	int ret = 0;
+	struct elv_change_ctx *ctx;
 
 	lockdep_assert_held_write(&q->tag_set->update_nr_hwq_lock);
 
@@ -5021,10 +5022,11 @@ static int blk_mq_elv_switch_none(struct request_queue *q,
 	 * can't run concurrently.
 	 */
 	if (q->elevator) {
+		ctx = xa_load(elv_tbl, q->id);
+		if (WARN_ON_ONCE(!ctx))
+			return -ENOENT;
 
-		ret = xa_insert(elv_tbl, q->id, q->elevator->type, GFP_KERNEL);
-		if (WARN_ON_ONCE(ret))
-			return ret;
+		ctx->name = q->elevator->type->elevator_name;
 
 		/*
 		 * Before we switch elevator to 'none', take a reference to
@@ -5035,9 +5037,14 @@ static int blk_mq_elv_switch_none(struct request_queue *q,
 		 */
 		__elevator_get(q->elevator->type);
 
+		/*
+		 * Store elevator type so that we can release the reference
+		 * taken above later.
+		 */
+		ctx->type = q->elevator->type;
 		elevator_set_none(q);
 	}
-	return ret;
+	return 0;
 }
 
 static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
@@ -5047,7 +5054,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	int prev_nr_hw_queues = set->nr_hw_queues;
 	unsigned int memflags;
 	int i;
-	struct xarray elv_tbl, et_tbl;
+	struct xarray elv_tbl;
 	bool queues_frozen = false;
 
 	lockdep_assert_held(&set->tag_list_lock);
@@ -5061,11 +5068,12 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	memflags = memalloc_noio_save();
 
-	xa_init(&et_tbl);
-	if (blk_mq_alloc_sched_tags_batch(&et_tbl, set, nr_hw_queues) < 0)
-		goto out_memalloc_restore;
-
 	xa_init(&elv_tbl);
+	if (blk_mq_alloc_sched_ctx_batch(&elv_tbl, set) < 0)
+		goto out_free_ctx;
+
+	if (blk_mq_alloc_sched_res_batch(&elv_tbl, set, nr_hw_queues) < 0)
+		goto out_free_ctx;
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_debugfs_unregister_hctxs(q);
@@ -5111,7 +5119,7 @@ switch_back:
 		/* switch_back expects queue to be frozen */
 		if (!queues_frozen)
 			blk_mq_freeze_queue_nomemsave(q);
-		blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl);
+		blk_mq_elv_switch_back(q, &elv_tbl);
 	}
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
@@ -5122,9 +5130,9 @@ switch_back:
 		blk_mq_add_hw_queues_cpuhp(q);
 	}
 
+out_free_ctx:
+	blk_mq_free_sched_ctx_batch(&elv_tbl);
 	xa_destroy(&elv_tbl);
-	xa_destroy(&et_tbl);
-out_memalloc_restore:
 	memalloc_noio_restore(memflags);
 
 	/* Free the excess tags when nr_hw_queues shrink. */
diff --git a/block/blk.h b/block/blk.h
index 4d809588b771..e4c433f62dfc 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -11,8 +11,7 @@
 #include <xen/xen.h>
 #include "blk-crypto-internal.h"
 
-struct elevator_type;
-struct elevator_tags;
+struct elv_change_ctx;
 
 /*
  * Default upper limit for the software max_sectors limit used for regular I/Os.
@@ -333,8 +332,8 @@ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
 
 bool blk_insert_flush(struct request *rq);
 
-void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e,
-		struct elevator_tags *t);
+void elv_update_nr_hw_queues(struct request_queue *q,
+		struct elv_change_ctx *ctx);
 void elevator_set_default(struct request_queue *q);
 void elevator_set_none(struct request_queue *q);
 
diff --git a/block/elevator.c b/block/elevator.c
index e2ebfbf107b3..5b37ef44f52d 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -45,19 +45,6 @@
 #include "blk-wbt.h"
 #include "blk-cgroup.h"
 
-/* Holding context data for changing elevator */
-struct elv_change_ctx {
-	const char *name;
-	bool no_uevent;
-
-	/* for unregistering old elevator */
-	struct elevator_queue *old;
-	/* for registering new elevator */
-	struct elevator_queue *new;
-	/* holds sched tags data */
-	struct elevator_tags *et;
-};
-
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
 
@@ -134,7 +121,7 @@ static struct elevator_type *elevator_find_get(const char *name)
 static const struct kobj_type elv_ktype;
 
 struct elevator_queue *elevator_alloc(struct request_queue *q,
-		struct elevator_type *e, struct elevator_tags *et)
+		struct elevator_type *e, struct elevator_resources *res)
 {
 	struct elevator_queue *eq;
 
@@ -147,7 +134,8 @@ 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->et = et;
+	eq->et = res->et;
+	eq->elevator_data = res->data;
 
 	return eq;
 }
@@ -593,7 +581,7 @@ static int elevator_switch(struct request_queue *q, struct elv_change_ctx *ctx)
 	}
 
 	if (new_e) {
-		ret = blk_mq_init_sched(q, new_e, ctx->et);
+		ret = blk_mq_init_sched(q, new_e, &ctx->res);
 		if (ret)
 			goto out_unfreeze;
 		ctx->new = q->elevator;
@@ -617,7 +605,8 @@ out_unfreeze:
 	return ret;
 }
 
-static void elv_exit_and_release(struct request_queue *q)
+static void elv_exit_and_release(struct elv_change_ctx *ctx,
+		struct request_queue *q)
 {
 	struct elevator_queue *e;
 	unsigned memflags;
@@ -629,7 +618,7 @@ static void elv_exit_and_release(struct request_queue *q)
 	mutex_unlock(&q->elevator_lock);
 	blk_mq_unfreeze_queue(q, memflags);
 	if (e) {
-		blk_mq_free_sched_tags(e->et, q->tag_set);
+		blk_mq_free_sched_res(&ctx->res, ctx->type, q->tag_set);
 		kobject_put(&e->kobj);
 	}
 }
@@ -640,11 +629,15 @@ static int elevator_change_done(struct request_queue *q,
 	int ret = 0;
 
 	if (ctx->old) {
+		struct elevator_resources res = {
+			.et = ctx->old->et,
+			.data = ctx->old->elevator_data
+		};
 		bool enable_wbt = test_bit(ELEVATOR_FLAG_ENABLE_WBT_ON_EXIT,
 				&ctx->old->flags);
 
 		elv_unregister_queue(q, ctx->old);
-		blk_mq_free_sched_tags(ctx->old->et, q->tag_set);
+		blk_mq_free_sched_res(&res, ctx->old->type, q->tag_set);
 		kobject_put(&ctx->old->kobj);
 		if (enable_wbt)
 			wbt_enable_default(q->disk);
@@ -652,7 +645,7 @@ static int elevator_change_done(struct request_queue *q,
 	if (ctx->new) {
 		ret = elv_register_queue(q, ctx->new, !ctx->no_uevent);
 		if (ret)
-			elv_exit_and_release(q);
+			elv_exit_and_release(ctx, q);
 	}
 	return ret;
 }
@@ -669,10 +662,10 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx)
 	lockdep_assert_held(&set->update_nr_hwq_lock);
 
 	if (strncmp(ctx->name, "none", 4)) {
-		ctx->et = blk_mq_alloc_sched_tags(set, set->nr_hw_queues,
-				blk_mq_default_nr_requests(set));
-		if (!ctx->et)
-			return -ENOMEM;
+		ret = blk_mq_alloc_sched_res(q, ctx->type, &ctx->res,
+				set->nr_hw_queues);
+		if (ret)
+			return ret;
 	}
 
 	memflags = blk_mq_freeze_queue(q);
@@ -693,11 +686,12 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx)
 	blk_mq_unfreeze_queue(q, memflags);
 	if (!ret)
 		ret = elevator_change_done(q, ctx);
+
 	/*
-	 * Free sched tags if it's allocated but we couldn't switch elevator.
+	 * Free sched resource if it's allocated but we couldn't switch elevator.
 	 */
-	if (ctx->et && !ctx->new)
-		blk_mq_free_sched_tags(ctx->et, set);
+	if (!ctx->new)
+		blk_mq_free_sched_res(&ctx->res, ctx->type, set);
 
 	return ret;
 }
@@ -706,32 +700,29 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx)
  * The I/O scheduler depends on the number of hardware queues, this forces a
  * reattachment when nr_hw_queues changes.
  */
-void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e,
-		struct elevator_tags *t)
+void elv_update_nr_hw_queues(struct request_queue *q,
+		struct elv_change_ctx *ctx)
 {
 	struct blk_mq_tag_set *set = q->tag_set;
-	struct elv_change_ctx ctx = {};
 	int ret = -ENODEV;
 
 	WARN_ON_ONCE(q->mq_freeze_depth == 0);
 
-	if (e && !blk_queue_dying(q) && blk_queue_registered(q)) {
-		ctx.name = e->elevator_name;
-		ctx.et = t;
-
+	if (ctx->type && !blk_queue_dying(q) && blk_queue_registered(q)) {
 		mutex_lock(&q->elevator_lock);
 		/* force to reattach elevator after nr_hw_queue is updated */
-		ret = elevator_switch(q, &ctx);
+		ret = elevator_switch(q, ctx);
 		mutex_unlock(&q->elevator_lock);
 	}
 	blk_mq_unfreeze_queue_nomemrestore(q);
 	if (!ret)
-		WARN_ON_ONCE(elevator_change_done(q, &ctx));
+		WARN_ON_ONCE(elevator_change_done(q, ctx));
+
 	/*
-	 * Free sched tags if it's allocated but we couldn't switch elevator.
+	 * Free sched resource if it's allocated but we couldn't switch elevator.
 	 */
-	if (t && !ctx.new)
-		blk_mq_free_sched_tags(t, set);
+	if (!ctx->new)
+		blk_mq_free_sched_res(&ctx->res, ctx->type, set);
 }
 
 /*
@@ -745,7 +736,6 @@ void elevator_set_default(struct request_queue *q)
 		.no_uevent = true,
 	};
 	int err;
-	struct elevator_type *e;
 
 	/* now we allow to switch elevator */
 	blk_queue_flag_clear(QUEUE_FLAG_NO_ELV_SWITCH, q);
@@ -758,8 +748,8 @@ void elevator_set_default(struct request_queue *q)
 	 * have multiple queues or mq-deadline is not available, default
 	 * to "none".
 	 */
-	e = elevator_find_get(ctx.name);
-	if (!e)
+	ctx.type = elevator_find_get(ctx.name);
+	if (!ctx.type)
 		return;
 
 	if ((q->nr_hw_queues == 1 ||
@@ -769,7 +759,7 @@ void elevator_set_default(struct request_queue *q)
 			pr_warn("\"%s\" elevator initialization, failed %d, falling back to \"none\"\n",
 					ctx.name, err);
 	}
-	elevator_put(e);
+	elevator_put(ctx.type);
 }
 
 void elevator_set_none(struct request_queue *q)
@@ -818,6 +808,7 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 	ctx.name = strstrip(elevator_name);
 
 	elv_iosched_load_module(ctx.name);
+	ctx.type = elevator_find_get(ctx.name);
 
 	down_read(&set->update_nr_hwq_lock);
 	if (!blk_queue_no_elv_switch(q)) {
@@ -828,6 +819,9 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 		ret = -ENOENT;
 	}
 	up_read(&set->update_nr_hwq_lock);
+
+	if (ctx.type)
+		elevator_put(ctx.type);
 	return ret;
 }
 
diff --git a/block/elevator.h b/block/elevator.h
index c4d20155065e..3ee1d494f48a 100644
--- a/block/elevator.h
+++ b/block/elevator.h
@@ -32,12 +32,36 @@ struct elevator_tags {
 	struct blk_mq_tags *tags[];
 };
 
+struct elevator_resources {
+	/* holds elevator data */
+	void *data;
+	/* holds elevator tags */
+	struct elevator_tags *et;
+};
+
+/* Holding context data for changing elevator */
+struct elv_change_ctx {
+	const char *name;
+	bool no_uevent;
+
+	/* for unregistering old elevator */
+	struct elevator_queue *old;
+	/* for registering new elevator */
+	struct elevator_queue *new;
+	/* store elevator type */
+	struct elevator_type *type;
+	/* store elevator resources */
+	struct elevator_resources res;
+};
+
 struct elevator_mq_ops {
 	int (*init_sched)(struct request_queue *, struct elevator_queue *);
 	void (*exit_sched)(struct elevator_queue *);
 	int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int);
 	void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
 	void (*depth_updated)(struct request_queue *);
+	void *(*alloc_sched_data)(struct request_queue *);
+	void (*free_sched_data)(void *);
 
 	bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
 	bool (*bio_merge)(struct request_queue *, struct bio *, unsigned int);
@@ -163,7 +187,7 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *page, size_t count);
 
 extern bool elv_bio_merge_ok(struct request *, struct bio *);
 struct elevator_queue *elevator_alloc(struct request_queue *,
-		struct elevator_type *, struct elevator_tags *);
+		struct elevator_type *, struct elevator_resources *);
 
 /*
  * Helper functions.
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index 18efd6ef2a2b..c1b36ffd19ce 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -409,30 +409,42 @@ static void kyber_depth_updated(struct request_queue *q)
 
 static int kyber_init_sched(struct request_queue *q, struct elevator_queue *eq)
 {
-	struct kyber_queue_data *kqd;
-
-	kqd = kyber_queue_data_alloc(q);
-	if (IS_ERR(kqd))
-		return PTR_ERR(kqd);
-
 	blk_stat_enable_accounting(q);
 
 	blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q);
 
-	eq->elevator_data = kqd;
 	q->elevator = eq;
 	kyber_depth_updated(q);
 
 	return 0;
 }
 
+static void *kyber_alloc_sched_data(struct request_queue *q)
+{
+	struct kyber_queue_data *kqd;
+
+	kqd = kyber_queue_data_alloc(q);
+	if (IS_ERR(kqd))
+		return NULL;
+
+	return kqd;
+}
+
 static void kyber_exit_sched(struct elevator_queue *e)
 {
 	struct kyber_queue_data *kqd = e->elevator_data;
-	int i;
 
 	timer_shutdown_sync(&kqd->timer);
 	blk_stat_disable_accounting(kqd->q);
+}
+
+static void kyber_free_sched_data(void *elv_data)
+{
+	struct kyber_queue_data *kqd = elv_data;
+	int i;
+
+	if (!kqd)
+		return;
 
 	for (i = 0; i < KYBER_NUM_DOMAINS; i++)
 		sbitmap_queue_free(&kqd->domain_tokens[i]);
@@ -1004,6 +1016,8 @@ static struct elevator_type kyber_sched = {
 		.exit_sched = kyber_exit_sched,
 		.init_hctx = kyber_init_hctx,
 		.exit_hctx = kyber_exit_hctx,
+		.alloc_sched_data = kyber_alloc_sched_data,
+		.free_sched_data = kyber_free_sched_data,
 		.limit_depth = kyber_limit_depth,
 		.bio_merge = kyber_bio_merge,
 		.prepare_request = kyber_prepare_request,