@@ -2087,8 +2087,6 @@ 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);
@@ -2155,12 +2153,9 @@ 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;
@@ -2174,8 +2169,6 @@ 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);
@@ -2860,6 +2853,21 @@ 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 NULL to clean up the data in it.
+ * will get it back after update mapping between cpu and hw queues.
+ */
+ list_for_each_entry(q, &set->tag_list, tag_set_list) {
+ if (!q->elevator) {
+ q->elv_type = NULL;
+ continue;
+ }
+ q->elv_type = q->elevator->type;
+ mutex_lock(&q->sysfs_lock);
+ elevator_switch_mq(q, NULL);
+ mutex_unlock(&q->sysfs_lock);
+ }
+
set->nr_hw_queues = nr_hw_queues;
blk_mq_update_queue_map(set);
list_for_each_entry(q, &set->tag_list, tag_set_list) {
@@ -2867,6 +2875,14 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
blk_mq_queue_reinit(q);
}
+ list_for_each_entry(q, &set->tag_list, tag_set_list) {
+ if (!q->elv_type)
+ continue;
+
+ mutex_lock(&q->sysfs_lock);
+ elevator_switch_mq(q, q->elv_type);
+ mutex_unlock(&q->sysfs_lock);
+ }
list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_unfreeze_queue(q);
}
@@ -233,6 +233,8 @@ static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq
int elevator_init(struct request_queue *);
int elevator_init_mq(struct request_queue *q);
+int elevator_switch_mq(struct request_queue *q,
+ struct elevator_type *new_e);
void elevator_exit(struct request_queue *, struct elevator_queue *);
int elv_register_queue(struct request_queue *q);
void elv_unregister_queue(struct request_queue *q);
@@ -933,16 +933,13 @@ void elv_unregister(struct elevator_type *e)
}
EXPORT_SYMBOL_GPL(elv_unregister);
-static int elevator_switch_mq(struct request_queue *q,
+int elevator_switch_mq(struct request_queue *q,
struct elevator_type *new_e)
{
int ret;
lockdep_assert_held(&q->sysfs_lock);
- blk_mq_freeze_queue(q);
- blk_mq_quiesce_queue(q);
-
if (q->elevator) {
if (q->elevator->registered)
elv_unregister_queue(q);
@@ -968,8 +965,6 @@ static int elevator_switch_mq(struct request_queue *q,
blk_add_trace_msg(q, "elv switch: none");
out:
- blk_mq_unquiesce_queue(q);
- blk_mq_unfreeze_queue(q);
return ret;
}
@@ -1021,8 +1016,17 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
lockdep_assert_held(&q->sysfs_lock);
- if (q->mq_ops)
- return elevator_switch_mq(q, new_e);
+ if (q->mq_ops) {
+ blk_mq_freeze_queue(q);
+ blk_mq_quiesce_queue(q);
+
+ err = elevator_switch_mq(q, new_e);
+
+ blk_mq_unquiesce_queue(q);
+ blk_mq_unfreeze_queue(q);
+
+ return err;
+ }
/*
* Turn on BYPASS and drain all requests w/ elevator private data.
@@ -439,6 +439,9 @@ struct request_queue {
struct list_head queue_head;
struct request *last_merge;
struct elevator_queue *elevator;
+
+ /* used when update nr_hw_queues */
+ struct elevator_type *elv_type;
int nr_rqs[2]; /* # allocated [a]sync rqs */
int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */
Kyber depends on the mapping between cpu and nr_hw_queues. When update nr_hw_queues, elevator_type->ops.mq.init_hctx will be invoked before the mapping is adapted correctly, this would cause terrible result. A simply way to fix this is switch the io scheduler to none before update the nr_hw_queues, and then get it back after update nr_hw_queues. To achieve this, we add a new member elv_type in request_queue to save the original elevator and adapt and export elevator_switch_mq. Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com> --- block/blk-mq.c | 32 ++++++++++++++++++++++++-------- block/blk.h | 2 ++ block/elevator.c | 20 ++++++++++++-------- include/linux/blkdev.h | 3 +++ 4 files changed, 41 insertions(+), 16 deletions(-)