Move elv_register[unregister]_queue out of ->elevator_lock & queue freezing,
so we can kill many lockdep warnings.
elv_register[unregister]_queue() is serialized, and just dealing with sysfs/
debugfs things, no need to be done with queue frozen.
With this change, elevator's ->exit() is called before calling
elv_unregister_queue, then user may call into ->show()/store() of elevator's
sysfs attributes, and we have covered this issue by adding `ELEVATOR_FLAG_DYNG`.
For blk-mq debugfs, hctx->sched_tags is always checked with ->elevator_lock by
debugfs code, meantime hctx->sched_tags is updated with ->elevator_lock, so
there isn't such issue.
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
block/blk-mq.c | 9 ++++----
block/blk.h | 1 +
block/elevator.c | 58 ++++++++++++++++++++++++++++++++++--------------
block/elevator.h | 5 +++++
4 files changed, 52 insertions(+), 21 deletions(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1a287c2e791c..9a361a173a8e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4993,16 +4993,17 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
.force = true,
.uevent = true,
};
+ int ret = -ENODEV;
mutex_lock(&q->elevator_lock);
if (q->elevator && !blk_queue_dying(q))
ctx.name = q->elevator->type->elevator_name;
- __elevator_change(q, &ctx);
+ ret = __elevator_change(q, &ctx);
mutex_unlock(&q->elevator_lock);
- }
-
- list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_unfreeze_queue_nomemrestore(q);
+ if (!ret)
+ WARN_ON_ONCE(elevator_change_done(q, &ctx));
+ }
memalloc_noio_restore(memflags);
/* Free the excess tags when nr_hw_queues shrink. */
diff --git a/block/blk.h b/block/blk.h
index 0e19c09009ed..48cf6b1c36fe 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -323,6 +323,7 @@ bool blk_insert_flush(struct request *rq);
int __elevator_change(struct request_queue *q, struct elv_change_ctx *ctx);
void elevator_set_default(struct request_queue *q);
void elevator_set_none(struct request_queue *q);
+int elevator_change_done(struct request_queue *q, struct elv_change_ctx *ctx);
ssize_t part_size_show(struct device *dev, struct device_attribute *attr,
char *buf);
diff --git a/block/elevator.c b/block/elevator.c
index 16171ea92f80..8652fe45a2db 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -151,18 +151,24 @@ static void elevator_release(struct kobject *kobj)
kfree(e);
}
-static void elevator_exit(struct request_queue *q)
+static void __elevator_exit(struct request_queue *q)
{
struct elevator_queue *e = q->elevator;
+ lockdep_assert_held(&q->elevator_lock);
+
ioc_clear_queue(q);
blk_mq_sched_free_rqs(q);
mutex_lock(&e->sysfs_lock);
blk_mq_exit_sched(q, e);
mutex_unlock(&e->sysfs_lock);
+}
- kobject_put(&e->kobj);
+static void elevator_exit(struct request_queue *q)
+{
+ __elevator_exit(q);
+ kobject_put(&q->elevator->kobj);
}
static inline void __elv_rqhash_del(struct request *rq)
@@ -467,8 +473,6 @@ static int elv_register_queue(struct request_queue *q,
{
int error;
- lockdep_assert_held(&q->elevator_lock);
-
error = kobject_add(&e->kobj, &q->disk->queue_kobj, "iosched");
if (!error) {
const struct elv_fs_entry *attr = e->type->elevator_attrs;
@@ -495,8 +499,6 @@ static int elv_register_queue(struct request_queue *q,
static void elv_unregister_queue(struct request_queue *q,
struct elevator_queue *e)
{
- lockdep_assert_held(&q->elevator_lock);
-
if (e && test_and_clear_bit(ELEVATOR_FLAG_REGISTERED, &e->flags)) {
kobject_uevent(&e->kobj, KOBJ_REMOVE);
kobject_del(&e->kobj);
@@ -640,19 +642,15 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e,
blk_mq_quiesce_queue(q);
if (q->elevator) {
- elv_unregister_queue(q, q->elevator);
- elevator_exit(q);
+ ctx->old = q->elevator;
+ __elevator_exit(q);
}
ret = blk_mq_init_sched(q, new_e);
if (ret)
goto out_unfreeze;
- ret = elv_register_queue(q, q->elevator, ctx->uevent);
- if (ret) {
- elevator_exit(q);
- goto out_unfreeze;
- }
+ ctx->new = q->elevator;
blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
out_unfreeze:
@@ -666,15 +664,16 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e,
return ret;
}
-static void elevator_disable(struct request_queue *q)
+static void elevator_disable(struct request_queue *q,
+ struct elv_change_ctx *ctx)
{
WARN_ON_ONCE(q->mq_freeze_depth == 0);
lockdep_assert_held(&q->elevator_lock);
blk_mq_quiesce_queue(q);
- elv_unregister_queue(q, q->elevator);
- elevator_exit(q);
+ ctx->old = q->elevator;
+ __elevator_exit(q);
blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q);
q->elevator = NULL;
q->nr_requests = q->tag_set->queue_depth;
@@ -683,6 +682,28 @@ static void elevator_disable(struct request_queue *q)
blk_mq_unquiesce_queue(q);
}
+int elevator_change_done(struct request_queue *q, struct elv_change_ctx *ctx)
+{
+ int ret = 0;
+
+ if (ctx->old) {
+ elv_unregister_queue(q, ctx->old);
+ kobject_put(&ctx->old->kobj);
+ }
+ if (ctx->new) {
+ ret = elv_register_queue(q, ctx->new, ctx->uevent);
+ if (ret) {
+ unsigned memflags = blk_mq_freeze_queue(q);
+
+ mutex_lock(&q->elevator_lock);
+ elevator_exit(q);
+ mutex_unlock(&q->elevator_lock);
+ blk_mq_unfreeze_queue(q, memflags);
+ }
+ }
+ return 0;
+}
+
/*
* Switch this queue to the given IO scheduler.
*/
@@ -698,7 +719,7 @@ int __elevator_change(struct request_queue *q, struct elv_change_ctx *ctx)
if (!strncmp(elevator_name, "none", 4)) {
if (q->elevator)
- elevator_disable(q);
+ elevator_disable(q, ctx);
return 0;
}
@@ -742,6 +763,9 @@ static int elevator_change(struct request_queue *q,
ret = __elevator_change(q, ctx);
mutex_unlock(&q->elevator_lock);
blk_mq_unfreeze_queue(q, memflags);
+ if (!ret)
+ ret = elevator_change_done(q, ctx);
+
exit:
srcu_read_unlock(&set->update_nr_hwq_srcu, idx);
return ret;
diff --git a/block/elevator.h b/block/elevator.h
index 16d8888fa2b2..486be0690499 100644
--- a/block/elevator.h
+++ b/block/elevator.h
@@ -129,6 +129,11 @@ struct elv_change_ctx {
bool force;
bool uevent;
bool init;
+
+ /* for unregistering old elevator */
+ struct elevator_queue *old;
+ /* for registering new elevator */
+ struct elevator_queue *new;
};
/*
--
2.47.0
