From 232143b605387b372dee0ec7830f93b93df5f67d Mon Sep 17 00:00:00 2001 From: Nilay Shroff Date: Thu, 13 Nov 2025 14:28:18 +0530 Subject: [PATCH 1/5] block: unify elevator tags and type xarrays into struct elv_change_ctx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, the nr_hw_queues update path manages two disjoint xarrays — one for elevator tags and another for elevator type — both used during elevator switching. Maintaining these two parallel structures for the same purpose adds unnecessary complexity and potential for mismatched state. This patch unifies both xarrays into a single structure, struct elv_change_ctx, which holds all per-queue elevator change context. A single xarray, named elv_tbl, now maps each queue (q->id) in a tagset to its corresponding elv_change_ctx entry, encapsulating the elevator tags, type and name references. This unification simplifies the code, improves maintainability, and clarifies ownership of per-queue elevator state. Reviewed-by: Ming Lei Reviewed-by: Yu Kuai Signed-off-by: Nilay Shroff Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 78 +++++++++++++++++++++++++++++++++----------- block/blk-mq-sched.h | 3 ++ block/blk-mq.c | 50 ++++++++++++++++------------ block/blk.h | 7 ++-- block/elevator.c | 31 ++++-------------- block/elevator.h | 15 +++++++++ 6 files changed, 116 insertions(+), 68 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 97b69fbe26f6..7ba285a7759b 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -427,11 +427,11 @@ 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_tags_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); @@ -444,15 +444,49 @@ 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 || !ctx->et) { WARN_ON_ONCE(1); - else - blk_mq_free_sched_tags(et, set); + continue; + } + blk_mq_free_sched_tags(ctx->et, set); + ctx->et = NULL; } } } +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, unsigned int nr_hw_queues, unsigned int nr_requests) { @@ -497,12 +531,13 @@ struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set, return NULL; } -int blk_mq_alloc_sched_tags_batch(struct xarray *et_table, +int blk_mq_alloc_sched_tags_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); @@ -515,26 +550,31 @@ 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; - if (xa_insert(et_table, q->id, et, gfp)) - goto out_free_tags; + } + + ctx->et = blk_mq_alloc_sched_tags(set, nr_hw_queues, + blk_mq_default_nr_requests(set)); + if (!ctx->et) + goto out_unwind; + } } 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 && ctx->et) { + blk_mq_free_sched_tags(ctx->et, set); + ctx->et = NULL; + } } } - return -ENOMEM; + return ret; } /* caller must have a reference to @e, will grab another one if successful */ diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 8e21a6b1415d..2fddbc91a235 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -27,6 +27,9 @@ 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, 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, diff --git a/block/blk-mq.c b/block/blk-mq.c index b2fdeaac0efb..04c6356f0eb2 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_tags_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 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, /* 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 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, 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 #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..cd7bdff205c8 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); @@ -706,32 +693,28 @@ 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. */ - if (t && !ctx.new) - blk_mq_free_sched_tags(t, set); + if (ctx->et && !ctx->new) + blk_mq_free_sched_tags(ctx->et, set); } /* diff --git a/block/elevator.h b/block/elevator.h index c4d20155065e..bad43182361e 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -32,6 +32,21 @@ struct elevator_tags { struct blk_mq_tags *tags[]; }; +/* 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; + /* holds sched tags data */ + struct elevator_tags *et; +}; + struct elevator_mq_ops { int (*init_sched)(struct request_queue *, struct elevator_queue *); void (*exit_sched)(struct elevator_queue *); From 04728ce90966c54417fd8120a3820104d18ba68d Mon Sep 17 00:00:00 2001 From: Nilay Shroff Date: Thu, 13 Nov 2025 14:28:19 +0530 Subject: [PATCH 2/5] block: move elevator tags into struct elevator_resources This patch introduces a new structure, struct elevator_resources, to group together all elevator-related resources that share the same lifetime. As a first step, this change moves the elevator tag pointer from struct elv_change_ctx into the new struct elevator_resources. Additionally, rename blk_mq_alloc_sched_tags_batch() and blk_mq_free_sched_tags_batch() to blk_mq_alloc_sched_res_batch() and blk_mq_free_sched_res_batch(), respectively. Introduce two new wrapper helpers, blk_mq_alloc_sched_res() and blk_mq_free_sched_res(), around blk_mq_alloc_sched_tags() and blk_mq_free_sched_tags(). These changes pave the way for consolidating the allocation and freeing of elevator-specific resources into common helper functions. This refactoring improves encapsulation and prepares the code for future extensions, allowing additional elevator-specific data to be added to struct elevator_resources without cluttering struct elv_change_ctx. Subsequent patches will extend struct elevator_resources to include other elevator-related data. Reviewed-by: Ming Lei Reviewed-by: Yu Kuai Signed-off-by: Nilay Shroff Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 48 ++++++++++++++++++++++++++++++-------------- block/blk-mq-sched.h | 10 ++++++--- block/blk-mq.c | 2 +- block/elevator.c | 31 ++++++++++++++-------------- block/elevator.h | 9 +++++++-- 5 files changed, 64 insertions(+), 36 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 7ba285a7759b..32ae57518298 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -427,7 +427,16 @@ void blk_mq_free_sched_tags(struct elevator_tags *et, kfree(et); } -void blk_mq_free_sched_tags_batch(struct xarray *elv_tbl, +void blk_mq_free_sched_res(struct elevator_resources *res, + struct blk_mq_tag_set *set) +{ + if (res->et) { + blk_mq_free_sched_tags(res->et, set); + res->et = NULL; + } +} + +void blk_mq_free_sched_res_batch(struct xarray *elv_tbl, struct blk_mq_tag_set *set) { struct request_queue *q; @@ -445,12 +454,11 @@ void blk_mq_free_sched_tags_batch(struct xarray *elv_tbl, */ if (q->elevator) { ctx = xa_load(elv_tbl, q->id); - if (!ctx || !ctx->et) { + if (!ctx) { WARN_ON_ONCE(1); continue; } - blk_mq_free_sched_tags(ctx->et, set); - ctx->et = NULL; + blk_mq_free_sched_res(&ctx->res, set); } } } @@ -531,12 +539,24 @@ struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set, return NULL; } -int blk_mq_alloc_sched_tags_batch(struct xarray *elv_tbl, +int blk_mq_alloc_sched_res(struct request_queue *q, + 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; + + 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; int ret = -ENOMEM; lockdep_assert_held_write(&set->update_nr_hwq_lock); @@ -556,11 +576,10 @@ int blk_mq_alloc_sched_tags_batch(struct xarray *elv_tbl, goto out_unwind; } - ctx->et = blk_mq_alloc_sched_tags(set, nr_hw_queues, - blk_mq_default_nr_requests(set)); - if (!ctx->et) + ret = blk_mq_alloc_sched_res(q, &ctx->res, + nr_hw_queues); + if (ret) goto out_unwind; - } } return 0; @@ -568,10 +587,8 @@ int blk_mq_alloc_sched_tags_batch(struct xarray *elv_tbl, list_for_each_entry_continue_reverse(q, &set->tag_list, tag_set_list) { if (q->elevator) { ctx = xa_load(elv_tbl, q->id); - if (ctx && ctx->et) { - blk_mq_free_sched_tags(ctx->et, set); - ctx->et = NULL; - } + if (ctx) + blk_mq_free_sched_res(&ctx->res, set); } } return ret; @@ -579,9 +596,10 @@ int blk_mq_alloc_sched_tags_batch(struct xarray *elv_tbl, /* 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; diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 2fddbc91a235..1f8e58dd4b49 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -19,20 +19,24 @@ 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_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 blk_mq_tag_set *set); +void blk_mq_free_sched_res_batch(struct xarray *et_table, struct blk_mq_tag_set *set); 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 04c6356f0eb2..0d38daaa4705 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -5072,7 +5072,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, if (blk_mq_alloc_sched_ctx_batch(&elv_tbl, set) < 0) goto out_free_ctx; - if (blk_mq_alloc_sched_tags_batch(&elv_tbl, set, nr_hw_queues) < 0) + 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) { diff --git a/block/elevator.c b/block/elevator.c index cd7bdff205c8..cbec292a4af5 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -580,7 +580,7 @@ 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; @@ -604,7 +604,8 @@ static int elevator_switch(struct request_queue *q, struct elv_change_ctx *ctx) 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; @@ -616,7 +617,7 @@ 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, q->tag_set); kobject_put(&e->kobj); } } @@ -627,11 +628,12 @@ static int elevator_change_done(struct request_queue *q, int ret = 0; if (ctx->old) { + struct elevator_resources res = {.et = ctx->old->et}; 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, q->tag_set); kobject_put(&ctx->old->kobj); if (enable_wbt) wbt_enable_default(q->disk); @@ -639,7 +641,7 @@ 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; } @@ -656,10 +658,9 @@ 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->res, set->nr_hw_queues); + if (ret) + return ret; } memflags = blk_mq_freeze_queue(q); @@ -681,10 +682,10 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx) 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, set); return ret; } @@ -711,10 +712,10 @@ void elv_update_nr_hw_queues(struct request_queue *q, if (!ret) 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 (ctx->et && !ctx->new) - blk_mq_free_sched_tags(ctx->et, set); + if (!ctx->new) + blk_mq_free_sched_res(&ctx->res, set); } /* diff --git a/block/elevator.h b/block/elevator.h index bad43182361e..621a63597249 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -32,6 +32,11 @@ struct elevator_tags { struct blk_mq_tags *tags[]; }; +struct elevator_resources { + /* holds elevator tags */ + struct elevator_tags *et; +}; + /* Holding context data for changing elevator */ struct elv_change_ctx { const char *name; @@ -43,8 +48,8 @@ struct elv_change_ctx { struct elevator_queue *new; /* store elevator type */ struct elevator_type *type; - /* holds sched tags data */ - struct elevator_tags *et; + /* store elevator resources */ + struct elevator_resources res; }; struct elevator_mq_ops { From 61019afdf6ac17c8e8f9c42665aa1fa82f04a3e2 Mon Sep 17 00:00:00 2001 From: Nilay Shroff Date: Thu, 13 Nov 2025 14:28:20 +0530 Subject: [PATCH 3/5] block: introduce alloc_sched_data and free_sched_data elevator methods The recent lockdep splat [1] highlights a potential deadlock risk involving ->elevator_lock and ->freeze_lock dependencies on -pcpu_alloc_ mutex. The trace shows that the issue occurs when the Kyber scheduler allocates dynamic memory for its elevator data during initialization. To address this, introduce two new elevator operation callbacks: ->alloc_sched_data and ->free_sched_data. The subsequent patch would build upon these newly introduced methods to suppress lockdep splat[1]. [1] https://lore.kernel.org/all/CAGVVp+VNW4M-5DZMNoADp6o2VKFhi7KxWpTDkcnVyjO0=-D5+A@mail.gmail.com/ Signed-off-by: Nilay Shroff Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq-sched.h | 24 ++++++++++++++++++++++++ block/elevator.h | 2 ++ 2 files changed, 26 insertions(+) diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 1f8e58dd4b49..4e1b86e85a8a 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -38,6 +38,30 @@ void blk_mq_free_sched_res(struct elevator_resources *res, 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/elevator.h b/block/elevator.h index 621a63597249..e34043f6da26 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -58,6 +58,8 @@ struct elevator_mq_ops { 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); From 0315476e78c050048e80f66334a310e5581b46bb Mon Sep 17 00:00:00 2001 From: Nilay Shroff Date: Thu, 13 Nov 2025 14:28:21 +0530 Subject: [PATCH 4/5] block: use {alloc|free}_sched data methods The previous patch introduced ->alloc_sched_data and ->free_sched_data methods. This patch builds upon that by now using these methods during elevator switch and nr_hw_queue update. It's also ensured that scheduler-specific data is allocated and freed through the new callbacks outside of the ->freeze_lock and ->elevator_lock locking contexts, thereby preventing any dependency on pcpu_alloc_mutex. Reviewed-by: Ming Lei Reviewed-by: Yu Kuai Signed-off-by: Nilay Shroff Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 27 +++++++++++++++++++++------ block/blk-mq-sched.h | 5 ++++- block/elevator.c | 34 ++++++++++++++++++++++------------ block/elevator.h | 4 +++- 4 files changed, 50 insertions(+), 20 deletions(-) diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 32ae57518298..e26898128a7e 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -428,12 +428,17 @@ void blk_mq_free_sched_tags(struct elevator_tags *et, } 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, @@ -458,7 +463,7 @@ void blk_mq_free_sched_res_batch(struct xarray *elv_tbl, WARN_ON_ONCE(1); continue; } - blk_mq_free_sched_res(&ctx->res, set); + blk_mq_free_sched_res(&ctx->res, ctx->type, set); } } } @@ -540,7 +545,9 @@ struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set, } int blk_mq_alloc_sched_res(struct request_queue *q, - struct elevator_resources *res, unsigned int nr_hw_queues) + struct elevator_type *type, + struct elevator_resources *res, + unsigned int nr_hw_queues) { struct blk_mq_tag_set *set = q->tag_set; @@ -549,6 +556,12 @@ int blk_mq_alloc_sched_res(struct request_queue *q, 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; } @@ -576,19 +589,21 @@ int blk_mq_alloc_sched_res_batch(struct xarray *elv_tbl, goto out_unwind; } - ret = blk_mq_alloc_sched_res(q, &ctx->res, - nr_hw_queues); + ret = blk_mq_alloc_sched_res(q, q->elevator->type, + &ctx->res, nr_hw_queues); if (ret) goto out_unwind; } } return 0; + out_unwind: list_for_each_entry_continue_reverse(q, &set->tag_list, tag_set_list) { if (q->elevator) { ctx = xa_load(elv_tbl, q->id); if (ctx) - blk_mq_free_sched_res(&ctx->res, set); + blk_mq_free_sched_res(&ctx->res, + ctx->type, set); } } return ret; @@ -605,7 +620,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e, 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 4e1b86e85a8a..02c40a72e959 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -26,7 +26,9 @@ 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_res(struct request_queue *q, - struct elevator_resources *res, unsigned int nr_hw_queues); + 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, @@ -35,6 +37,7 @@ 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_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); diff --git a/block/elevator.c b/block/elevator.c index cbec292a4af5..5b37ef44f52d 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -121,7 +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; @@ -134,7 +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; } @@ -617,7 +618,7 @@ static void elv_exit_and_release(struct elv_change_ctx *ctx, mutex_unlock(&q->elevator_lock); blk_mq_unfreeze_queue(q, memflags); if (e) { - blk_mq_free_sched_res(&ctx->res, q->tag_set); + blk_mq_free_sched_res(&ctx->res, ctx->type, q->tag_set); kobject_put(&e->kobj); } } @@ -628,12 +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}; + 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_res(&res, 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); @@ -658,7 +662,8 @@ 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)) { - ret = blk_mq_alloc_sched_res(q, &ctx->res, set->nr_hw_queues); + ret = blk_mq_alloc_sched_res(q, ctx->type, &ctx->res, + set->nr_hw_queues); if (ret) return ret; } @@ -681,11 +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 resource if it's allocated but we couldn't switch elevator. */ if (!ctx->new) - blk_mq_free_sched_res(&ctx->res, set); + blk_mq_free_sched_res(&ctx->res, ctx->type, set); return ret; } @@ -711,11 +717,12 @@ void elv_update_nr_hw_queues(struct request_queue *q, blk_mq_unfreeze_queue_nomemrestore(q); if (!ret) WARN_ON_ONCE(elevator_change_done(q, ctx)); + /* * Free sched resource if it's allocated but we couldn't switch elevator. */ if (!ctx->new) - blk_mq_free_sched_res(&ctx->res, set); + blk_mq_free_sched_res(&ctx->res, ctx->type, set); } /* @@ -729,7 +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); @@ -742,8 +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 || @@ -753,7 +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) @@ -802,6 +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)) { @@ -812,6 +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 e34043f6da26..3ee1d494f48a 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -33,6 +33,8 @@ struct elevator_tags { }; struct elevator_resources { + /* holds elevator data */ + void *data; /* holds elevator tags */ struct elevator_tags *et; }; @@ -185,7 +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. From d4c3ef56a1618cb7d55a4be74a09cda09165745a Mon Sep 17 00:00:00 2001 From: Nilay Shroff Date: Thu, 13 Nov 2025 14:28:22 +0530 Subject: [PATCH 5/5] block: define alloc_sched_data and free_sched_data methods for kyber Currently, the Kyber elevator allocates its private data dynamically in ->init_sched and frees it in ->exit_sched. However, since ->init_sched is invoked during elevator switch after acquiring both ->freeze_lock and ->elevator_lock, it may trigger the lockdep splat [1] due to dependency on pcpu_alloc_mutex. To resolve this, move the elevator data allocation and deallocation logic from ->init_sched and ->exit_sched into the newly introduced ->alloc_sched_data and ->free_sched_data methods. These callbacks are invoked before acquiring ->freeze_lock and ->elevator_lock, ensuring that memory allocation happens safely without introducing additional locking dependencies. This change breaks the dependency chain involving pcpu_alloc_mutex and prevents the reported lockdep warning. [1] https://lore.kernel.org/all/CAGVVp+VNW4M-5DZMNoADp6o2VKFhi7KxWpTDkcnVyjO0=-D5+A@mail.gmail.com/ Reported-by: Changhui Zhong Reported-by: Yi Zhang Closes: https://lore.kernel.org/all/CAGVVp+VNW4M-5DZMNoADp6o2VKFhi7KxWpTDkcnVyjO0=-D5+A@mail.gmail.com/ Tested-by: Yi Zhang Reviewed-by: Ming Lei Reviewed-by: Yu Kuai Signed-off-by: Nilay Shroff Signed-off-by: Jens Axboe --- block/kyber-iosched.c | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) 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,