diff options
author | Jianchao Wang <jianchao.w.wang@oracle.com> | 2018-08-21 10:15:03 +0300 |
---|---|---|
committer | Jens Axboe <axboe@kernel.dk> | 2018-08-21 18:02:55 +0300 |
commit | d48ece209f82c9ce07be942441b53d3fa3664936 (patch) | |
tree | ddf957d9d4edf1915558bc528fee6696cc02f1ed /block/blk-mq.c | |
parent | fcedba42d94ecdc14ca13d3797cba1ccbf743fa4 (diff) | |
download | linux-d48ece209f82c9ce07be942441b53d3fa3664936.tar.xz |
blk-mq: init hctx sched after update ctx and hctx mapping
Currently, when update nr_hw_queues, IO scheduler's init_hctx will
be invoked before the mapping between ctx and hctx is adapted
correctly by blk_mq_map_swqueue. The IO scheduler init_hctx (kyber)
may depend on this mapping and get wrong result and panic finally.
A simply way to fix this is that switch the IO scheduler to 'none'
before update the nr_hw_queues, and then switch it back after
update nr_hw_queues. blk_mq_sched_init_/exit_hctx are removed due
to nobody use them any more.
Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block/blk-mq.c')
-rw-r--r-- | block/blk-mq.c | 92 |
1 files changed, 84 insertions, 8 deletions
diff --git a/block/blk-mq.c b/block/blk-mq.c index 5efd789910e2..9c8c8c71a13f 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2147,8 +2147,6 @@ static void blk_mq_exit_hctx(struct request_queue *q, if (set->ops->exit_request) set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx); - blk_mq_sched_exit_hctx(q, hctx, hctx_idx); - if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); @@ -2216,12 +2214,9 @@ static int blk_mq_init_hctx(struct request_queue *q, set->ops->init_hctx(hctx, set->driver_data, hctx_idx)) goto free_bitmap; - if (blk_mq_sched_init_hctx(q, hctx, hctx_idx)) - goto exit_hctx; - hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size); if (!hctx->fq) - goto sched_exit_hctx; + goto exit_hctx; if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, node)) goto free_fq; @@ -2235,8 +2230,6 @@ static int blk_mq_init_hctx(struct request_queue *q, free_fq: kfree(hctx->fq); - sched_exit_hctx: - blk_mq_sched_exit_hctx(q, hctx, hctx_idx); exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); @@ -2898,10 +2891,81 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) return ret; } +/* + * request_queue and elevator_type pair. + * It is just used by __blk_mq_update_nr_hw_queues to cache + * the elevator_type associated with a request_queue. + */ +struct blk_mq_qe_pair { + struct list_head node; + struct request_queue *q; + struct elevator_type *type; +}; + +/* + * Cache the elevator_type in qe pair list and switch the + * io scheduler to 'none' + */ +static bool blk_mq_elv_switch_none(struct list_head *head, + struct request_queue *q) +{ + struct blk_mq_qe_pair *qe; + + if (!q->elevator) + return true; + + qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); + if (!qe) + return false; + + INIT_LIST_HEAD(&qe->node); + qe->q = q; + qe->type = q->elevator->type; + list_add(&qe->node, head); + + mutex_lock(&q->sysfs_lock); + /* + * After elevator_switch_mq, the previous elevator_queue will be + * released by elevator_release. The reference of the io scheduler + * module get by elevator_get will also be put. So we need to get + * a reference of the io scheduler module here to prevent it to be + * removed. + */ + __module_get(qe->type->elevator_owner); + elevator_switch_mq(q, NULL); + mutex_unlock(&q->sysfs_lock); + + return true; +} + +static void blk_mq_elv_switch_back(struct list_head *head, + struct request_queue *q) +{ + struct blk_mq_qe_pair *qe; + struct elevator_type *t = NULL; + + list_for_each_entry(qe, head, node) + if (qe->q == q) { + t = qe->type; + break; + } + + if (!t) + return; + + list_del(&qe->node); + kfree(qe); + + mutex_lock(&q->sysfs_lock); + elevator_switch_mq(q, t); + mutex_unlock(&q->sysfs_lock); +} + static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { struct request_queue *q; + LIST_HEAD(head); lockdep_assert_held(&set->tag_list_lock); @@ -2912,6 +2976,14 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue(q); + /* + * Switch IO scheduler to 'none', cleaning up the data associated + * with the previous scheduler. We will switch back once we are done + * updating the new sw to hw queue mappings. + */ + list_for_each_entry(q, &set->tag_list, tag_set_list) + if (!blk_mq_elv_switch_none(&head, q)) + goto switch_back; set->nr_hw_queues = nr_hw_queues; blk_mq_update_queue_map(set); @@ -2920,6 +2992,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, blk_mq_queue_reinit(q); } +switch_back: + list_for_each_entry(q, &set->tag_list, tag_set_list) + blk_mq_elv_switch_back(&head, q); + list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_unfreeze_queue(q); } |