diff options
| author | Nilay Shroff <nilay@linux.ibm.com> | 2025-03-04 15:52:33 +0530 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2025-03-10 07:30:18 -0600 |
| commit | 1bf70d08cc3b55abd1763e6dff5855cb8dd8318b (patch) | |
| tree | 11ec9cc9c02828e4b9416163102eff1eee5b5ae3 /block/blk-mq.c | |
| parent | d23977fee1ee838316fb1b00945064a146460843 (diff) | |
block: introduce a dedicated lock for protecting queue elevator updates
A queue's elevator can be updated either when modifying nr_hw_queues
or through the sysfs scheduler attribute. Currently, elevator switching/
updating is protected using q->sysfs_lock, but this has led to lockdep
splats[1] due to inconsistent lock ordering between q->sysfs_lock and
the freeze-lock in multiple block layer call sites.
As the scope of q->sysfs_lock is not well-defined, its (mis)use has
resulted in numerous lockdep warnings. To address this, introduce a new
q->elevator_lock, dedicated specifically for protecting elevator
switches/updates. And we'd now use this new q->elevator_lock instead of
q->sysfs_lock for protecting elevator switches/updates.
While at it, make elv_iosched_load_module() a static function, as it is
only called from elv_iosched_store(). Also, remove redundant parameters
from elv_iosched_load_module() function signature.
[1] https://lore.kernel.org/all/67637e70.050a0220.3157ee.000c.GAE@google.com/
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Link: https://lore.kernel.org/r/20250304102551.2533767-5-nilay@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block/blk-mq.c')
| -rw-r--r-- | block/blk-mq.c | 15 |
1 files changed, 7 insertions, 8 deletions
diff --git a/block/blk-mq.c b/block/blk-mq.c index 40490ac88045..5a2d63927525 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4467,7 +4467,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, unsigned long i, j; /* protect against switching io scheduler */ - mutex_lock(&q->sysfs_lock); + mutex_lock(&q->elevator_lock); for (i = 0; i < set->nr_hw_queues; i++) { int old_node; int node = blk_mq_get_hctx_node(set, i); @@ -4500,7 +4500,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, xa_for_each_start(&q->hctx_table, j, hctx, j) blk_mq_exit_hctx(q, set, hctx, j); - mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->elevator_lock); /* unregister cpuhp callbacks for exited hctxs */ blk_mq_remove_hw_queues_cpuhp(q); @@ -4933,10 +4933,9 @@ static bool blk_mq_elv_switch_none(struct list_head *head, if (!qe) return false; - /* q->elevator needs protection from ->sysfs_lock */ - mutex_lock(&q->sysfs_lock); + /* Accessing q->elevator needs protection from ->elevator_lock. */ + mutex_lock(&q->elevator_lock); - /* the check has to be done with holding sysfs_lock */ if (!q->elevator) { kfree(qe); goto unlock; @@ -4950,7 +4949,7 @@ static bool blk_mq_elv_switch_none(struct list_head *head, list_add(&qe->node, head); elevator_disable(q); unlock: - mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->elevator_lock); return true; } @@ -4980,11 +4979,11 @@ static void blk_mq_elv_switch_back(struct list_head *head, list_del(&qe->node); kfree(qe); - mutex_lock(&q->sysfs_lock); + mutex_lock(&q->elevator_lock); elevator_switch(q, t); /* drop the reference acquired in blk_mq_elv_switch_none */ elevator_put(t); - mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->elevator_lock); } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, |