[12/14] block: move blk_exit_queue into disk_release

Commit Message

Christoph Hellwig March 4, 2022, 4:03 p.m. UTC

From: Ming Lei <[e-mail]>

There can't be FS IO in disk_release(), so move blk_exit_queue() there.

We still need to freeze queue here since the request is freed after the
bio is completed and passthrough request rely on scheduler tags as well.

The disk can be released before or after queue is cleaned up, and we have
to free the scheduler request pool before blk_cleanup_queue returns,
while the static request pool has to be freed before exiting the
I/O scheduler.

Signed-off-by: Ming Lei <[e-mail]>
[hch: rebased]
Signed-off-by: Christoph Hellwig <[e-mail]>
---
 block/blk-sysfs.c | 16 ----------------
 block/genhd.c     | 32 +++++++++++++++++++++++++++++++-
 2 files changed, 31 insertions(+), 17 deletions(-)

Comments

Bart Van Assche March 6, 2022, 9:21 p.m. UTC | #1

On 3/4/22 08:03, Christoph Hellwig wrote:
> From: Ming Lei <[e-mail]>
> 
> There can't be FS IO in disk_release(), so move blk_exit_queue() there.
> 
> We still need to freeze queue here since the request is freed after the
> bio is completed and passthrough request rely on scheduler tags as well.
> 
> The disk can be released before or after queue is cleaned up, and we have
> to free the scheduler request pool before blk_cleanup_queue returns,
> while the static request pool has to be freed before exiting the
> I/O scheduler.

The above explains why it is safe to make this change but not why this 
change is made. Please add an explanation of why this change is made. 
Anyway:

Reviewed-by: Bart Van Assche <[e-mail]>

Patch

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index af5a6d86073f1..85c4ba006671d 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -739,20 +739,6 @@  static void blk_free_queue_rcu(struct rcu_head *rcu_head)
 	kmem_cache_free(blk_get_queue_kmem_cache(blk_queue_has_srcu(q)), q);
 }
 
-/* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */
-static void blk_exit_queue(struct request_queue *q)
-{
-	/*
-	 * Since the I/O scheduler exit code may access cgroup information,
-	 * perform I/O scheduler exit before disassociating from the block
-	 * cgroup controller.
-	 */
-	if (q->elevator) {
-		ioc_clear_queue(q);
-		elevator_exit(q);
-	}
-}
-
 /**
  * blk_release_queue - releases all allocated resources of the request_queue
  * @kobj: pointer to a kobject, whose container is a request_queue
@@ -786,8 +772,6 @@  static void blk_release_queue(struct kobject *kobj)
 		blk_stat_remove_callback(q, q->poll_cb);
 	blk_stat_free_callback(q->poll_cb);
 
-	blk_exit_queue(q);
-
 	blk_free_queue_stats(q->stats);
 	kfree(q->poll_stat);
 
diff --git a/block/genhd.c b/block/genhd.c
index 073e93f2fc40b..73705a749ea92 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -29,6 +29,7 @@ 
 #include "blk.h"
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
+#include "blk-cgroup.h"
 
 static struct kobject *block_depr;
 
@@ -1097,6 +1098,34 @@  static const struct attribute_group *disk_attr_groups[] = {
 	NULL
 };
 
+static void disk_release_mq(struct request_queue *q)
+{
+	blk_mq_cancel_work_sync(q);
+
+	/*
+	 * There can't be any non non-passthrough bios in flight here, but
+	 * requests stay around longer, including passthrough ones so we
+	 * still need to freeze the queue here.
+	 */
+	blk_mq_freeze_queue(q);
+
+	/*
+	 * Since the I/O scheduler exit code may access cgroup information,
+	 * perform I/O scheduler exit before disassociating from the block
+	 * cgroup controller.
+	 */
+	if (q->elevator) {
+		ioc_clear_queue(q);
+
+		mutex_lock(&q->sysfs_lock);
+		blk_mq_sched_free_rqs(q);
+		elevator_exit(q);
+		mutex_unlock(&q->sysfs_lock);
+	}
+
+	__blk_mq_unfreeze_queue(q, true);
+}
+
 /**
  * disk_release - releases all allocated resources of the gendisk
  * @dev: the device representing this disk
@@ -1118,7 +1147,8 @@  static void disk_release(struct device *dev)
 	might_sleep();
 	WARN_ON_ONCE(disk_live(disk));
 
-	blk_mq_cancel_work_sync(disk->queue);
+	if (queue_is_mq(disk->queue))
+		disk_release_mq(disk->queue);
 
 	blkcg_exit_queue(disk->queue);