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 <czhong@redhat.com>
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/all/CAGVVp+VNW4M-5DZMNoADp6o2VKFhi7KxWpTDkcnVyjO0=-D5+A@mail.gmail.com/
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Yu Kuai <yukuai@fnnas.com>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index 18efd6ef2a2b94bff0bc33469cc3c7173261a588..c1b36ffd19ceb43f1bf2a362b7de3725eb94f0fd 100644 (file)
--- 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,