[PATCH] block: prevent elevator switch during updating nr_hw_queues

[Ming Lei <ming.lei@xxxxxxxxxx>]

updating nr_hw_queues is usually used for error handling code, when it
doesn't make sense to allow blk-mq elevator switching, since nr_hw_queues
may change, and elevator tags depends on nr_hw_queues.

Prevent elevator switch during updating nr_hw_queues by setting flag of
BLK_MQ_F_UPDATE_HW_QUEUES, and use srcu to fail elevator switch during
the period.

Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
 block/blk-mq-debugfs.c |  1 +
 block/blk-mq.c         | 32 ++++++++++++++++++++------------
 block/elevator.c       | 12 +++++++++++-
 include/linux/blk-mq.h |  9 ++++++++-
 4 files changed, 40 insertions(+), 14 deletions(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index c308699ded58..27f984311bb7 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -180,6 +180,7 @@ static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(BLOCKING),
 	HCTX_FLAG_NAME(TAG_RR),
 	HCTX_FLAG_NAME(NO_SCHED_BY_DEFAULT),
+	HCTX_FLAG_NAME(UPDATE_HW_QUEUES),
 };
 #undef HCTX_FLAG_NAME
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index d7a103dc258b..c1e7e1823369 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4776,14 +4776,12 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
 		set->nr_hw_queues = nr_cpu_ids;
 
-	if (set->flags & BLK_MQ_F_BLOCKING) {
-		set->srcu = kmalloc(sizeof(*set->srcu), GFP_KERNEL);
-		if (!set->srcu)
-			return -ENOMEM;
-		ret = init_srcu_struct(set->srcu);
-		if (ret)
-			goto out_free_srcu;
-	}
+	set->srcu = kmalloc(sizeof(*set->srcu), GFP_KERNEL);
+	if (!set->srcu)
+		return -ENOMEM;
+	ret = init_srcu_struct(set->srcu);
+	if (ret)
+		goto out_free_srcu;
 
 	ret = -ENOMEM;
 	set->tags = kcalloc_node(set->nr_hw_queues,
@@ -4864,10 +4862,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 
 	kfree(set->tags);
 	set->tags = NULL;
-	if (set->flags & BLK_MQ_F_BLOCKING) {
-		cleanup_srcu_struct(set->srcu);
-		kfree(set->srcu);
-	}
+
+	cleanup_srcu_struct(set->srcu);
+	kfree(set->srcu);
 }
 EXPORT_SYMBOL(blk_mq_free_tag_set);
 
@@ -5081,7 +5078,18 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 {
 	mutex_lock(&set->tag_list_lock);
+	/*
+	 * Mark us in updating nr_hw_queues for preventing switching
+	 * elevator
+	 *
+	 * Elevator switch code can _not_ acquire ->tag_list_lock
+	 */
+	set->flags |= BLK_MQ_F_UPDATE_HW_QUEUES;
+	synchronize_srcu(set->srcu);
+
 	__blk_mq_update_nr_hw_queues(set, nr_hw_queues);
+
+	set->flags &= BLK_MQ_F_UPDATE_HW_QUEUES;
 	mutex_unlock(&set->tag_list_lock);
 }
 EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
diff --git a/block/elevator.c b/block/elevator.c
index cf48613c6e62..e50e04ed15a0 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -718,9 +718,10 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 {
 	char elevator_name[ELV_NAME_MAX];
 	char *name;
-	int ret;
+	int ret, idx;
 	unsigned int memflags;
 	struct request_queue *q = disk->queue;
+	struct blk_mq_tag_set *set = q->tag_set;
 
 	/*
 	 * If the attribute needs to load a module, do it before freezing the
@@ -732,6 +733,13 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 
 	elv_iosched_load_module(name);
 
+	idx = srcu_read_lock(set->srcu);
+
+	if (set->flags & BLK_MQ_F_UPDATE_HW_QUEUES) {
+		ret = -EBUSY;
+		goto exit;
+	}
+
 	memflags = blk_mq_freeze_queue(q);
 	mutex_lock(&q->elevator_lock);
 	ret = elevator_change(q, name);
@@ -739,6 +747,8 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 		ret = count;
 	mutex_unlock(&q->elevator_lock);
 	blk_mq_unfreeze_queue(q, memflags);
+exit:
+	srcu_read_unlock(set->srcu, idx);
 	return ret;
 }
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 8eb9b3310167..71e05245af9d 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -681,7 +681,14 @@ enum {
 	 */
 	BLK_MQ_F_NO_SCHED_BY_DEFAULT	= 1 << 6,
 
-	BLK_MQ_F_MAX = 1 << 7,
+	/*
+	 * True when updating nr_hw_queues is in-progress
+	 *
+	 * tag_set only flag, not usable for hctx
+	 */
+	BLK_MQ_F_UPDATE_HW_QUEUES	= 1 << 7,
+
+	BLK_MQ_F_MAX = 1 << 8,
 };
 
 #define BLK_MQ_MAX_DEPTH	(10240)
-- 
2.44.0


--1HVwzvZ8lKiJPGhS--