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:
- when it is called from adding disk, elevator switch isn't possible
because ->queue_kobj isn't added yet
- when it is called from deleting disk, disable_elv_switch() is
responsible for preventing new elevator switch and draining old
elevator switch.
- when it is called from blk_mq_update_nr_hw_queues(), adding/removing
disk and elevator switch can't be allowed or in-progress
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.
Reviewed-by: Hannes Reinecke <hare@xxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
block/blk-mq.c | 3 +--
block/elevator.c | 63 ++++++++++++++++++++++++++++++++++++++----------
block/genhd.c | 6 +++++
3 files changed, 57 insertions(+), 15 deletions(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b920eaedbaa9..a4bcfce4c4b9 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4997,11 +4997,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
blk_mq_debugfs_register_hctxs(q);
}
+ /* elv_update_nr_hw_queues() unfreeze queue for us */
list_for_each_entry(q, &set->tag_list, tag_set_list)
elv_update_nr_hw_queues(q);
- list_for_each_entry(q, &set->tag_list, tag_set_list)
- blk_mq_unfreeze_queue_nomemrestore(q);
memalloc_noio_restore(memflags);
/* Free the excess tags when nr_hw_queues shrink. */
diff --git a/block/elevator.c b/block/elevator.c
index 98a754f58de5..492a593160ae 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -49,6 +49,11 @@
struct elv_change_ctx {
const char *name;
bool no_uevent;
+
+ /* for unregistering old elevator */
+ struct elevator_queue *old;
+ /* for registering new elevator */
+ struct elevator_queue *new;
};
static DEFINE_SPINLOCK(elv_list_lock);
@@ -158,14 +163,14 @@ 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 inline void __elv_rqhash_del(struct request *rq)
@@ -466,8 +471,6 @@ 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;
@@ -494,8 +497,6 @@ 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);
@@ -586,7 +587,7 @@ static int elevator_switch(struct request_queue *q, struct elv_change_ctx *ctx)
blk_mq_quiesce_queue(q);
if (q->elevator) {
- elv_unregister_queue(q, q->elevator);
+ ctx->old = q->elevator;
elevator_exit(q);
}
@@ -594,11 +595,7 @@ static int elevator_switch(struct request_queue *q, struct elv_change_ctx *ctx)
ret = blk_mq_init_sched(q, new_e);
if (ret)
goto out_unfreeze;
- ret = elv_register_queue(q, q->elevator, !ctx->no_uevent);
- if (ret) {
- elevator_exit(q);
- goto out_unfreeze;
- }
+ ctx->new = q->elevator;
} else {
blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q);
q->elevator = NULL;
@@ -619,6 +616,38 @@ static int elevator_switch(struct request_queue *q, struct elv_change_ctx *ctx)
return ret;
}
+static void elv_exit_and_release(struct request_queue *q)
+{
+ struct elevator_queue *e;
+ unsigned memflags;
+
+ memflags = blk_mq_freeze_queue(q);
+ mutex_lock(&q->elevator_lock);
+ e = q->elevator;
+ elevator_exit(q);
+ mutex_unlock(&q->elevator_lock);
+ blk_mq_unfreeze_queue(q, memflags);
+ if (e)
+ kobject_put(&e->kobj);
+}
+
+static 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->no_uevent);
+ if (ret)
+ elv_exit_and_release(q);
+ }
+ return ret;
+}
+
/*
* Switch this queue to the given IO scheduler.
*/
@@ -645,6 +674,9 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx)
ret = elevator_switch(q, ctx);
mutex_unlock(&q->elevator_lock);
blk_mq_unfreeze_queue(q, memflags);
+ if (!ret)
+ ret = elevator_change_done(q, ctx);
+
return ret;
}
@@ -657,6 +689,7 @@ void elv_update_nr_hw_queues(struct request_queue *q)
struct elv_change_ctx ctx = {
.name = "none",
};
+ int ret = -ENODEV;
WARN_ON_ONCE(q->mq_freeze_depth == 0);
@@ -664,8 +697,12 @@ void elv_update_nr_hw_queues(struct request_queue *q)
if (q->elevator && !blk_queue_dying(q) && !blk_queue_registered(q))
ctx.name = q->elevator->type->elevator_name;
/* force to reattach elevator after nr_hw_queue is updated */
- elevator_switch(q, &ctx);
+ ret = elevator_switch(q, &ctx);
mutex_unlock(&q->elevator_lock);
+ blk_mq_unfreeze_queue_nomemrestore(q);
+
+ if (!ret)
+ WARN_ON_ONCE(elevator_change_done(q, &ctx));
}
/*
diff --git a/block/genhd.c b/block/genhd.c
index 0e64e7400fb4..59d9febd8c14 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -751,11 +751,17 @@ static void __del_gendisk(struct gendisk *disk)
static void disable_elv_switch(struct request_queue *q)
{
+ struct blk_mq_tag_set *set = q->tag_set;
+
WARN_ON_ONCE(!queue_is_mq(q));
mutex_lock(&q->elevator_lock);
blk_queue_flag_set(QUEUE_FLAG_NO_ELV_SWITCH, q);
mutex_unlock(&q->elevator_lock);
+
+ /* wait until in-progress elevator switch is done */
+ down_write(&set->update_nr_hwq_lock);
+ up_write(&set->update_nr_hwq_lock);
}
/**
--
2.47.0
