Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Jinke Han <hanjinke.666@bytedance.com>
To:     axboe@kernel.dk, tj@kernel.org
Cc:     linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
        cgroups@vger.kernel.org, Jinke Han <hanjinke.666@bytedance.com>
Subject: [PATCH v2] block: don't allow the same type rq_qos add more than once
Date:   Tue, 19 Jul 2022 15:02:58 +0800
Message-Id: <20220719070258.25721-1-hanjinke.666@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Jinke Han <hanjinke.666@bytedance.com>

In our test of iocost, we encounttered some list add/del corrutions of
inner_walk list in ioc_timer_fn.

The reason can be descripted as follow:
cpu 0						cpu 1
ioc_qos_write					ioc_qos_write

ioc = q_to_ioc(bdev_get_queue(bdev));
if (!ioc) {
        ioc = kzalloc();			ioc = q_to_ioc(bdev_get_queue(bdev));
						if (!ioc) {
							ioc = kzalloc();
							...
							rq_qos_add(q, rqos);
						}
        ...
        rq_qos_add(q, rqos);
        ...
}

When the io.cost.qos file is written by two cpu concurrently, rq_qos may
be added to one disk twice. In that case, there will be two iocs enabled
and running on one disk. They own different iocgs on their active list.
In the ioc_timer_fn function, because of the iocgs from two ioc have the
same root iocg, the root iocg's walk_list may be overwritten by each
other and this lead to list add/del corrutions in building or destorying
the inner_walk list.

And so far, the blk-rq-qos framework works in case that one instance for
one type rq_qos per queue by default. This patch make this explicit and
also fix the crash above.

Signed-off-by: Jinke Han <hanjinke.666@bytedance.com>
---
 block/blk-iocost.c    | 19 ++++++++++++-------
 block/blk-iolatency.c |  6 +++++-
 block/blk-ioprio.c    |  5 +++++
 block/blk-rq-qos.h    | 11 ++++++++++-
 block/blk-wbt.c       |  8 +++++++-
 5 files changed, 39 insertions(+), 10 deletions(-)

diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 33a11ba971ea..e058b51a4e63 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2886,15 +2886,20 @@ static int blk_iocost_init(struct request_queue *q)
 	 * called before policy activation completion, can't assume that the
 	 * target bio has an iocg associated and need to test for NULL iocg.
 	 */
-	rq_qos_add(q, rqos);
+	ret = rq_qos_add(q, rqos);
+	if (ret)
+		goto err_free_ioc;
+
 	ret = blkcg_activate_policy(q, &blkcg_policy_iocost);
-	if (ret) {
-		rq_qos_del(q, rqos);
-		free_percpu(ioc->pcpu_stat);
-		kfree(ioc);
-		return ret;
-	}
+	if (ret)
+		goto err_del_qos;
 	return 0;
+err_del_qos:
+	rq_qos_del(q, rqos);
+err_free_ioc:
+	free_percpu(ioc->pcpu_stat);
+	kfree(ioc);
+	return ret;
 }
 
 static struct blkcg_policy_data *ioc_cpd_alloc(gfp_t gfp)
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 9568bf8dfe82..9a572439f326 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -773,7 +773,11 @@ int blk_iolatency_init(struct request_queue *q)
 	rqos->ops = &blkcg_iolatency_ops;
 	rqos->q = q;
 
-	rq_qos_add(q, rqos);
+	ret = rq_qos_add(q, rqos);
+	if (ret) {
+		kfree(blkiolat);
+		return ret;
+	}
 
 	ret = blkcg_activate_policy(q, &blkcg_policy_iolatency);
 	if (ret) {
diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c
index 79e797f5d194..931bffdf0cab 100644
--- a/block/blk-ioprio.c
+++ b/block/blk-ioprio.c
@@ -251,6 +251,11 @@ int blk_ioprio_init(struct request_queue *q)
 	 * rq-qos callbacks.
 	 */
 	rq_qos_add(q, rqos);
+	if (ret) {
+		blkcg_deactivate_policy(q, &ioprio_policy);
+		kfree(blkioprio_blkg);
+		return ret;
+	}
 
 	return 0;
 }
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 0e46052b018a..08b856570ad1 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -86,7 +86,7 @@ static inline void rq_wait_init(struct rq_wait *rq_wait)
 	init_waitqueue_head(&rq_wait->wait);
 }
 
-static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
+static inline int rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 {
 	/*
 	 * No IO can be in-flight when adding rqos, so freeze queue, which
@@ -98,6 +98,8 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 	blk_mq_freeze_queue(q);
 
 	spin_lock_irq(&q->queue_lock);
+	if (rq_qos_id(q, rqos->id))
+		goto ebusy;
 	rqos->next = q->rq_qos;
 	q->rq_qos = rqos;
 	spin_unlock_irq(&q->queue_lock);
@@ -109,6 +111,13 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 		blk_mq_debugfs_register_rqos(rqos);
 		mutex_unlock(&q->debugfs_mutex);
 	}
+
+	return 0;
+ebusy:
+	spin_unlock_irq(&q->queue_lock);
+	blk_mq_unfreeze_queue(q);
+	return -EBUSY;
+
 }
 
 static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 0c119be0e813..cc8f45929b31 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -820,6 +820,7 @@ int wbt_init(struct request_queue *q)
 {
 	struct rq_wb *rwb;
 	int i;
+	int ret;
 
 	rwb = kzalloc(sizeof(*rwb), GFP_KERNEL);
 	if (!rwb)
@@ -846,7 +847,12 @@ int wbt_init(struct request_queue *q)
 	/*
 	 * Assign rwb and add the stats callback.
 	 */
-	rq_qos_add(q, &rwb->rqos);
+	ret = rq_qos_add(q, &rwb->rqos);
+	if (ret) {
+		blk_stat_free_callback(rwb->cb);
+		kfree(rwb);
+		return ret;
+	}
 	blk_stat_add_callback(q, rwb->cb);
 
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
-- 
2.20.1