In blk_mq_update_nr_hw_queues(), nr_hw_queues changes and elevator data
depends on it, so elevator has to be reattached.
Now elevator switch isn't allowed during blk_mq_update_nr_hw_queues(), so
we can simply call elevator_change() to reattach elevator sched tags after
nr_hw_queues is updated.
Add elv_update_nr_hw_queues() for blk_mq_update_nr_hw_queues() to
reattach elevator.
Reviewed-by: Nilay Shroff <nilay@xxxxxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
block/blk-mq.c | 90 +-----------------------------------------------
block/blk.h | 3 +-
block/elevator.c | 32 +++++++++++++----
3 files changed, 28 insertions(+), 97 deletions(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1ed2d183f912..3afcddd21586 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4943,88 +4943,10 @@ 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;
-
- qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
- if (!qe)
- return false;
-
- /* Accessing q->elevator needs protection from ->elevator_lock. */
- mutex_lock(&q->elevator_lock);
-
- if (!q->elevator) {
- kfree(qe);
- goto unlock;
- }
-
- INIT_LIST_HEAD(&qe->node);
- qe->q = q;
- qe->type = q->elevator->type;
- /* keep a reference to the elevator module as we'll switch back */
- __elevator_get(qe->type);
- list_add(&qe->node, head);
- elevator_disable(q);
-unlock:
- mutex_unlock(&q->elevator_lock);
-
- return true;
-}
-
-static struct blk_mq_qe_pair *blk_lookup_qe_pair(struct list_head *head,
- struct request_queue *q)
-{
- struct blk_mq_qe_pair *qe;
-
- list_for_each_entry(qe, head, node)
- if (qe->q == q)
- return qe;
-
- return NULL;
-}
-
-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;
-
- qe = blk_lookup_qe_pair(head, q);
- if (!qe)
- return;
- t = qe->type;
- list_del(&qe->node);
- kfree(qe);
-
- 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->elevator_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);
int prev_nr_hw_queues = set->nr_hw_queues;
unsigned int memflags;
int i;
@@ -5042,15 +4964,6 @@ 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_nomemsave(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;
-
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_debugfs_unregister_hctxs(q);
blk_mq_sysfs_unregister_hctxs(q);
@@ -5084,9 +4997,8 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
blk_mq_debugfs_register_hctxs(q);
}
-switch_back:
list_for_each_entry(q, &set->tag_list, tag_set_list)
- blk_mq_elv_switch_back(&head, q);
+ elv_update_nr_hw_queues(q);
list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_unfreeze_queue_nomemrestore(q);
diff --git a/block/blk.h b/block/blk.h
index 006e3be433d2..2969f4427996 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -319,8 +319,7 @@ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
bool blk_insert_flush(struct request *rq);
-int elevator_switch(struct request_queue *q, struct elevator_type *new_e);
-void elevator_disable(struct request_queue *q);
+void elv_update_nr_hw_queues(struct request_queue *q);
void elevator_exit(struct request_queue *q);
int elv_register_queue(struct request_queue *q, bool uevent);
void elv_unregister_queue(struct request_queue *q);
diff --git a/block/elevator.c b/block/elevator.c
index 56da6ab7691a..5705f7056516 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -621,7 +621,7 @@ void elevator_init_mq(struct request_queue *q)
* If switching fails, we are most likely running out of memory and not able
* to restore the old io scheduler, so leaving the io scheduler being none.
*/
-int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
+static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
{
int ret;
@@ -657,7 +657,7 @@ int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
return ret;
}
-void elevator_disable(struct request_queue *q)
+static void elevator_disable(struct request_queue *q)
{
WARN_ON_ONCE(q->mq_freeze_depth == 0);
lockdep_assert_held(&q->elevator_lock);
@@ -677,7 +677,8 @@ void elevator_disable(struct request_queue *q)
/*
* Switch this queue to the given IO scheduler.
*/
-static int elevator_change(struct request_queue *q, const char *elevator_name)
+static int __elevator_change(struct request_queue *q,
+ const char *elevator_name)
{
struct elevator_type *e;
int ret;
@@ -692,9 +693,6 @@ static int elevator_change(struct request_queue *q, const char *elevator_name)
return 0;
}
- if (q->elevator && elevator_match(q->elevator->type, elevator_name))
- return 0;
-
e = elevator_find_get(elevator_name);
if (!e)
return -EINVAL;
@@ -703,6 +701,28 @@ static int elevator_change(struct request_queue *q, const char *elevator_name)
return ret;
}
+static int elevator_change(struct request_queue *q, const char *elevator_name)
+{
+ if (!q->elevator || !elevator_match(q->elevator->type, elevator_name))
+ return __elevator_change(q, elevator_name);
+ return 0;
+}
+
+/*
+ * 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)
+{
+ const char *name = "none";
+
+ mutex_lock(&q->elevator_lock);
+ if (q->elevator && !blk_queue_dying(q))
+ name = q->elevator->type->elevator_name;
+ __elevator_change(q, name);
+ mutex_unlock(&q->elevator_lock);
+}
+
static void elv_iosched_load_module(char *elevator_name)
{
struct elevator_type *found;
--
2.47.0
