diff options
| author | Nilay Shroff <nilay@linux.ibm.com> | 2025-07-30 13:16:09 +0530 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2025-07-30 06:20:51 -0600 |
| commit | 04225d13aef11b2a539014def5e47d8c21fd74a5 (patch) | |
| tree | 322bda04c657a2aaee282737e32b35afa0be17e1 /block/elevator.c | |
| parent | f5a6604f7a4405450e4a1f54e5430f47290c500f (diff) | |
block: fix potential deadlock while running nr_hw_queue update
Move scheduler tags (sched_tags) allocation and deallocation outside
both the ->elevator_lock and ->freeze_lock when updating nr_hw_queues.
This change breaks the dependency chain from the percpu allocator lock
to the elevator lock, helping to prevent potential deadlocks, as
observed in the reported lockdep splat[1].
This commit introduces batch allocation and deallocation helpers for
sched_tags, which are now used from within __blk_mq_update_nr_hw_queues
routine while iterating through the tagset.
With this change, all sched_tags memory management is handled entirely
outside the ->elevator_lock and the ->freeze_lock context, thereby
eliminating the lock dependency that could otherwise manifest during
nr_hw_queues updates.
[1] https://lore.kernel.org/all/0659ea8d-a463-47c8-9180-43c719e106eb@linux.ibm.com/
Reported-by: Stefan Haberland <sth@linux.ibm.com>
Closes: https://lore.kernel.org/all/0659ea8d-a463-47c8-9180-43c719e106eb@linux.ibm.com/
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Link: https://lore.kernel.org/r/20250730074614.2537382-4-nilay@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block/elevator.c')
| -rw-r--r-- | block/elevator.c | 15 |
1 files changed, 6 insertions, 9 deletions
diff --git a/block/elevator.c b/block/elevator.c index e9dc837b7b70..fe96c6f4753c 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -705,7 +705,8 @@ 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) +void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e, + struct elevator_tags *t) { struct blk_mq_tag_set *set = q->tag_set; struct elv_change_ctx ctx = {}; @@ -715,25 +716,21 @@ void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e) if (e && !blk_queue_dying(q) && blk_queue_registered(q)) { ctx.name = e->elevator_name; - ctx.et = blk_mq_alloc_sched_tags(set, set->nr_hw_queues); - if (!ctx.et) { - WARN_ON_ONCE(1); - goto unfreeze; - } + ctx.et = t; + mutex_lock(&q->elevator_lock); /* force to reattach elevator after nr_hw_queue is updated */ ret = elevator_switch(q, &ctx); mutex_unlock(&q->elevator_lock); } -unfreeze: blk_mq_unfreeze_queue_nomemrestore(q); if (!ret) WARN_ON_ONCE(elevator_change_done(q, &ctx)); /* * Free sched tags if it's allocated but we couldn't switch elevator. */ - if (ctx.et && !ctx.new) - blk_mq_free_sched_tags(ctx.et, set); + if (t && !ctx.new) + blk_mq_free_sched_tags(t, set); } /* |