block: add new helper for disabling elevator switch when deleting disk

Add new helper disable_elv_switch() and new flag QUEUE_FLAG_NO_ELV_SWITCH
for disabling elevator switch before deleting disk:

- originally flag QUEUE_FLAG_REGISTERED is added for preventing elevator
switch during removing disk, but this flag has been used widely for
other purposes, so add one new flag for disabling elevator switch only

- for avoiding deadlock risk, we have to move elevator queue
register/unregister out of elevator lock and queue freeze, which will be
done in next patch. However, this way adds small race window between elevator
switch and deleting ->queue_kobj, in which elevator queue register/unregister
could be run concurrently. The added helper will be used for avoiding the race
in the following patch.

- drain in-progress elevator switch before deleting disk

Suggested-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Link: https://lore.kernel.org/r/20250505141805.2751237-21-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

4 files changed, 27 insertions, 3 deletions

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 2837a8ce8054..29b3540dd180 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -94,6 +94,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(HCTX_ACTIVE),
 	QUEUE_FLAG_NAME(SQ_SCHED),
 	QUEUE_FLAG_NAME(DISABLE_WBT_DEF),
+	QUEUE_FLAG_NAME(NO_ELV_SWITCH),
 };
 #undef QUEUE_FLAG_NAME
 
diff --git a/block/elevator.c b/block/elevator.c
index 2edaf84900fc..f7e333abefe3 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -680,6 +680,9 @@ void elevator_set_default(struct request_queue *q)
 	};
 	int err = 0;
 
+	/* now we allow to switch elevator */
+	blk_queue_flag_clear(QUEUE_FLAG_NO_ELV_SWITCH, q);
+
 	if (q->tag_set->flags & BLK_MQ_F_NO_SCHED_BY_DEFAULT)
 		return;
 
@@ -744,9 +747,13 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 	elv_iosched_load_module(ctx.name);
 
 	down_read(&set->update_nr_hwq_lock);
-	ret = elevator_change(q, &ctx);
-	if (!ret)
-		ret = count;
+	if (!blk_queue_no_elv_switch(q)) {
+		ret = elevator_change(q, &ctx);
+		if (!ret)
+			ret = count;
+	} else {
+		ret = -ENOENT;
+	}
 	up_read(&set->update_nr_hwq_lock);
 	return ret;
 }
diff --git a/block/genhd.c b/block/genhd.c
index f192fe4808b9..a8cb5607b6e3 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -764,6 +764,16 @@ static void __del_gendisk(struct gendisk *disk)
 		blk_unfreeze_release_lock(q);
 }
 
+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));
+
+	down_write(&set->update_nr_hwq_lock);
+	blk_queue_flag_set(QUEUE_FLAG_NO_ELV_SWITCH, q);
+	up_write(&set->update_nr_hwq_lock);
+}
+
 /**
  * del_gendisk - remove the gendisk
  * @disk: the struct gendisk to remove
@@ -792,6 +802,9 @@ void del_gendisk(struct gendisk *disk)
 		__del_gendisk(disk);
 	} else {
 		set = disk->queue->tag_set;
+
+		disable_elv_switch(disk->queue);
+
 		memflags = memalloc_noio_save();
 		down_read(&set->update_nr_hwq_lock);
 		__del_gendisk(disk);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c36d7a1c2cc0..3aa1fd637d57 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -642,6 +642,7 @@ enum {
 	QUEUE_FLAG_HCTX_ACTIVE,		/* at least one blk-mq hctx is active */
 	QUEUE_FLAG_SQ_SCHED,		/* single queue style io dispatch */
 	QUEUE_FLAG_DISABLE_WBT_DEF,	/* for sched to disable/enable wbt */
+	QUEUE_FLAG_NO_ELV_SWITCH,	/* can't switch elevator any more */
 	QUEUE_FLAG_MAX
 };
 
@@ -679,6 +680,8 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
 	((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE)
 #define blk_queue_disable_wbt(q)	\
 	test_bit(QUEUE_FLAG_DISABLE_WBT_DEF, &(q)->queue_flags)
+#define blk_queue_no_elv_switch(q)	\
+	test_bit(QUEUE_FLAG_NO_ELV_SWITCH, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);