[PATCH v3] block: flush all throttled bios when deleting the cgroup

[Li Lingfeng <lilingfeng@huaweicloud.com>]

From: Li Lingfeng <lilingfeng3@huawei.com>

When a process migrates to another cgroup and the original cgroup is deleted,
the restrictions of throttled bios cannot be removed. If the restrictions
are set too low, it will take a long time to complete these bios.

Refer to the process of deleting a disk to remove the restrictions and
issue bios when deleting the cgroup.

This makes difference on the behavior of throttled bios:
Before: the limit of the throttled bios can't be changed and the bios will
complete under this limit;
Now: the limit will be canceled and the throttled bios will be flushed
immediately.

References:
[1] https://lore.kernel.org/r/20220318130144.1066064-4-ming.lei@redhat.com
[2] https://lore.kernel.org/all/da861d63-58c6-3ca0-2535-9089993e9e28@huaweicloud.com/

Signed-off-by: Li Lingfeng <lilingfeng3@huawei.com>
---
  v2->v3:
    Change "tg_cancel_bios" to "tg_flush_bios";
    Add reference of v2 to describe the background.
 block/blk-throttle.c | 68 ++++++++++++++++++++++++++++----------------
 1 file changed, 44 insertions(+), 24 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 6943ec720f39..cf7f4912c57a 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1526,6 +1526,42 @@ static void throtl_shutdown_wq(struct request_queue *q)
 	cancel_work_sync(&td->dispatch_work);
 }
 
+static void tg_flush_bios(struct throtl_grp *tg)
+{
+	struct throtl_service_queue *sq = &tg->service_queue;
+
+	if (tg->flags & THROTL_TG_CANCELING)
+		return;
+	/*
+	 * Set the flag to make sure throtl_pending_timer_fn() won't
+	 * stop until all throttled bios are dispatched.
+	 */
+	tg->flags |= THROTL_TG_CANCELING;
+
+	/*
+	 * Do not dispatch cgroup without THROTL_TG_PENDING or cgroup
+	 * will be inserted to service queue without THROTL_TG_PENDING
+	 * set in tg_update_disptime below. Then IO dispatched from
+	 * child in tg_dispatch_one_bio will trigger double insertion
+	 * and corrupt the tree.
+	 */
+	if (!(tg->flags & THROTL_TG_PENDING))
+		return;
+
+	/*
+	 * Update disptime after setting the above flag to make sure
+	 * throtl_select_dispatch() won't exit without dispatching.
+	 */
+	tg_update_disptime(tg);
+
+	throtl_schedule_pending_timer(sq, jiffies + 1);
+}
+
+static void throtl_pd_offline(struct blkg_policy_data *pd)
+{
+	tg_flush_bios(pd_to_tg(pd));
+}
+
 struct blkcg_policy blkcg_policy_throtl = {
 	.dfl_cftypes		= throtl_files,
 	.legacy_cftypes		= throtl_legacy_files,
@@ -1533,6 +1569,7 @@ struct blkcg_policy blkcg_policy_throtl = {
 	.pd_alloc_fn		= throtl_pd_alloc,
 	.pd_init_fn		= throtl_pd_init,
 	.pd_online_fn		= throtl_pd_online,
+	.pd_offline_fn		= throtl_pd_offline,
 	.pd_free_fn		= throtl_pd_free,
 };
 
@@ -1553,32 +1590,15 @@ void blk_throtl_cancel_bios(struct gendisk *disk)
 	 */
 	rcu_read_lock();
 	blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
-		struct throtl_grp *tg = blkg_to_tg(blkg);
-		struct throtl_service_queue *sq = &tg->service_queue;
-
-		/*
-		 * Set the flag to make sure throtl_pending_timer_fn() won't
-		 * stop until all throttled bios are dispatched.
-		 */
-		tg->flags |= THROTL_TG_CANCELING;
-
 		/*
-		 * Do not dispatch cgroup without THROTL_TG_PENDING or cgroup
-		 * will be inserted to service queue without THROTL_TG_PENDING
-		 * set in tg_update_disptime below. Then IO dispatched from
-		 * child in tg_dispatch_one_bio will trigger double insertion
-		 * and corrupt the tree.
+		 * disk_release will call pd_offline_fn to cancel bios.
+		 * However, disk_release can't be called if someone get
+		 * the refcount of device and issued bios which are
+		 * inflight after del_gendisk.
+		 * Cancel bios here to ensure no bios are inflight after
+		 * del_gendisk.
 		 */
-		if (!(tg->flags & THROTL_TG_PENDING))
-			continue;
-
-		/*
-		 * Update disptime after setting the above flag to make sure
-		 * throtl_select_dispatch() won't exit without dispatching.
-		 */
-		tg_update_disptime(tg);
-
-		throtl_schedule_pending_timer(sq, jiffies + 1);
+		tg_flush_bios(blkg_to_tg(blkg));
 	}
 	rcu_read_unlock();
 	spin_unlock_irq(&q->queue_lock);
-- 
2.39.2