From c43332fe028c252a2a28e46be70a530f64fc3c9d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 8 Feb 2023 07:35:14 +0100
Subject: [PATCH] blk-cgroup: delay calling blkcg_exit_disk until disk_release
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
While del_gendisk ensures there is no outstanding I/O on the queue,
it can't prevent block layer users from building new I/O.
This leads to a NULL ->root_blkg reference in bio_associate_blkg when
allocating a new bio on a shut down file system. Delay freeing the
blk-cgroup subsystems from del_gendisk until disk_release to make
sure the blkg and throttle information is still avaÑ–lable for bio
submitters, even if those bios will immediately fail.
This now can cause a case where disk_release is called on a disk
that hasn't been added. That's mostly harmless, except for a case
in blk_throttl_exit that now needs to check for a NULL ->td pointer.
Fixes: 178fa7d49815 ("blk-cgroup: delay blk-cgroup initialization until add_disk")
Reported-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230208063514.171485-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/blk-throttle.c | 3 ++-
block/genhd.c | 4 ++--
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 902203bdddb4b..e7bd7050d6840 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2411,7 +2411,8 @@ void blk_throtl_exit(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
- BUG_ON(!q->td);
+ if (!q->td)
+ return;
del_timer_sync(&q->td->service_queue.pending_timer);
throtl_shutdown_wq(q);
blkcg_deactivate_policy(disk, &blkcg_policy_throtl);
diff --git a/block/genhd.c b/block/genhd.c
index 7e031559bf514..65373738c70b0 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -668,8 +668,6 @@ void del_gendisk(struct gendisk *disk)
rq_qos_exit(q);
blk_mq_unquiesce_queue(q);
- blkcg_exit_disk(disk);
-
/*
* If the disk does not own the queue, allow using passthrough requests
* again. Else leave the queue frozen to fail all I/O.
@@ -1166,6 +1164,8 @@ static void disk_release(struct device *dev)
might_sleep();
WARN_ON_ONCE(disk_live(disk));
+ blkcg_exit_disk(disk);
+
/*
* To undo the all initialization from blk_mq_init_allocated_queue in
* case of a probe failure where add_disk is never called we have to
--
GitLab