block: don't allow the same type rq_qos add more than once

[ Upstream commit 14a6e2eb7df5c7897c15b109cba29ab0c4a791b6 ]

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

The reason can be described as follows:

cpu 0					cpu 1
ioc_qos_write				ioc_qos_write

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

When the io.cost.qos file is written by two cpus 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 iocs have the
same root iocg, the root iocg's walk_list may be overwritten by each other
and this leads to list add/del corruptions in building or destroying 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>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20220720093616.70584-1-hanjinke.666@bytedance.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 16705fbd0699132319b7060577bd9d130f95694d..a19f2db4eeb2ee0251641732d47052e76876c69e 100644 (file)
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2893,15 +2893,21 @@ 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 9568bf8dfe82b7545c0bd67137f98094e264153b..7845dca5fcfdb0ccb740dae63564fd10555994cc 100644 (file)
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -773,19 +773,23 @@ 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)
+               goto err_free;
        ret = blkcg_activate_policy(q, &blkcg_policy_iolatency);
-       if (ret) {
-               rq_qos_del(q, rqos);
-               kfree(blkiolat);
-               return ret;
-       }
+       if (ret)
+               goto err_qos_del;
 
        timer_setup(&blkiolat->timer, blkiolatency_timer_fn, 0);
        INIT_WORK(&blkiolat->enable_work, blkiolatency_enable_work_fn);
 
        return 0;
+
+err_qos_del:
+       rq_qos_del(q, rqos);
+err_free:
+       kfree(blkiolat);
+       return ret;
 }
 
 static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)

diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 0e46052b018a45222190d3084ec36bc48dcd67db..08b856570ad10a2e96f423c621593e610ed1be69 100644 (file)
--- 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 0c119be0e813316c28049e9d7a0c6cdc1eddf4f5..ae6ea0b5457991b193b4d5de6d45cdcc7a2cc90d 100644 (file)
--- 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 +847,10 @@ 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)
+               goto err_free;
+
        blk_stat_add_callback(q, rwb->cb);
 
        rwb->min_lat_nsec = wbt_default_latency_nsec(q);
@@ -855,4 +859,10 @@ int wbt_init(struct request_queue *q)
        wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 
        return 0;
+
+err_free:
+       blk_stat_free_callback(rwb->cb);
+       kfree(rwb);
+       return ret;
+
 }