There is a race between cpu hotplug handling and adding/deleting
gendisk for blk-mq, where both are trying to register and unregister
the same sysfs entries.
null_add_dev
--> blk_mq_init_queue
--> blk_mq_init_allocated_queue
--> add to 'all_q_list' (*)
--> add_disk
--> blk_register_queue
--> blk_mq_register_disk (++)
null_del_dev
--> del_gendisk
--> blk_unregister_queue
--> blk_mq_unregister_disk (--)
--> blk_cleanup_queue
--> blk_mq_free_queue
--> del from 'all_q_list' (*)
blk_mq_queue_reinit
--> blk_mq_sysfs_unregister (-)
--> blk_mq_sysfs_register (+)
While the request queue is added to 'all_q_list' (*),
blk_mq_queue_reinit() can be called for the queue anytime by CPU
hotplug callback. But blk_mq_sysfs_unregister (-) and
blk_mq_sysfs_register (+) in blk_mq_queue_reinit must not be called
before blk_mq_register_disk (++) and after blk_mq_unregister_disk (--)
is finished. Because '/sys/block/*/mq/' is not exists.
There has already been BLK_MQ_F_SYSFS_UP flag in hctx->flags which can
be used to track these sysfs stuff, but it is only fixing this issue
partially.
In order to fix it completely, we just need per-queue flag instead of
per-hctx flag with appropriate locking. So this introduces
q->mq_sysfs_init_done which is properly protected with all_q_mutex.
Also, we need to ensure that blk_mq_map_swqueue() is called with
all_q_mutex is held. Since hctx->nr_ctx is reset temporarily and
updated in blk_mq_map_swqueue(), so we should avoid
blk_mq_register_hctx() seeing the temporary hctx->nr_ctx value
in CPU hotplug handling or adding/deleting gendisk .
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Cc: Ming Lei <tom.leiming@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
struct blk_mq_ctx *ctx;
int i;
struct blk_mq_ctx *ctx;
int i;
- if (!hctx->nr_ctx || !(hctx->flags & BLK_MQ_F_SYSFS_UP))
return;
hctx_for_each_ctx(hctx, ctx, i)
return;
hctx_for_each_ctx(hctx, ctx, i)
struct blk_mq_ctx *ctx;
int i, ret;
struct blk_mq_ctx *ctx;
int i, ret;
- if (!hctx->nr_ctx || !(hctx->flags & BLK_MQ_F_SYSFS_UP))
return 0;
ret = kobject_add(&hctx->kobj, &q->mq_kobj, "%u", hctx->queue_num);
return 0;
ret = kobject_add(&hctx->kobj, &q->mq_kobj, "%u", hctx->queue_num);
struct blk_mq_ctx *ctx;
int i, j;
struct blk_mq_ctx *ctx;
int i, j;
+ blk_mq_disable_hotplug();
+
queue_for_each_hw_ctx(q, hctx, i) {
blk_mq_unregister_hctx(hctx);
queue_for_each_hw_ctx(q, hctx, i) {
blk_mq_unregister_hctx(hctx);
kobject_put(&q->mq_kobj);
kobject_put(&disk_to_dev(disk)->kobj);
kobject_put(&q->mq_kobj);
kobject_put(&disk_to_dev(disk)->kobj);
+
+ q->mq_sysfs_init_done = false;
+ blk_mq_enable_hotplug();
}
static void blk_mq_sysfs_init(struct request_queue *q)
}
static void blk_mq_sysfs_init(struct request_queue *q)
struct blk_mq_hw_ctx *hctx;
int ret, i;
struct blk_mq_hw_ctx *hctx;
int ret, i;
+ blk_mq_disable_hotplug();
+
blk_mq_sysfs_init(q);
ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
if (ret < 0)
blk_mq_sysfs_init(q);
ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
if (ret < 0)
kobject_uevent(&q->mq_kobj, KOBJ_ADD);
queue_for_each_hw_ctx(q, hctx, i) {
kobject_uevent(&q->mq_kobj, KOBJ_ADD);
queue_for_each_hw_ctx(q, hctx, i) {
- hctx->flags |= BLK_MQ_F_SYSFS_UP;
ret = blk_mq_register_hctx(hctx);
if (ret)
break;
}
ret = blk_mq_register_hctx(hctx);
if (ret)
break;
}
blk_mq_unregister_disk(disk);
blk_mq_unregister_disk(disk);
+ else
+ q->mq_sysfs_init_done = true;
+out:
+ blk_mq_enable_hotplug();
}
EXPORT_SYMBOL_GPL(blk_mq_register_disk);
}
EXPORT_SYMBOL_GPL(blk_mq_register_disk);
struct blk_mq_hw_ctx *hctx;
int i;
struct blk_mq_hw_ctx *hctx;
int i;
+ if (!q->mq_sysfs_init_done)
+ return;
+
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_unregister_hctx(hctx);
}
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_unregister_hctx(hctx);
}
struct blk_mq_hw_ctx *hctx;
int i, ret = 0;
struct blk_mq_hw_ctx *hctx;
int i, ret = 0;
+ if (!q->mq_sysfs_init_done)
+ return ret;
+
queue_for_each_hw_ctx(q, hctx, i) {
ret = blk_mq_register_hctx(hctx);
if (ret)
queue_for_each_hw_ctx(q, hctx, i) {
ret = blk_mq_register_hctx(hctx);
if (ret)
goto err_hctxs;
mutex_lock(&all_q_mutex);
goto err_hctxs;
mutex_lock(&all_q_mutex);
- list_add_tail(&q->all_q_node, &all_q_list);
- mutex_unlock(&all_q_mutex);
+ list_add_tail(&q->all_q_node, &all_q_list);
blk_mq_add_queue_tag_set(set, q);
blk_mq_add_queue_tag_set(set, q);
+ mutex_unlock(&all_q_mutex);
+
BLK_MQ_F_SHOULD_MERGE = 1 << 0,
BLK_MQ_F_TAG_SHARED = 1 << 1,
BLK_MQ_F_SG_MERGE = 1 << 2,
BLK_MQ_F_SHOULD_MERGE = 1 << 0,
BLK_MQ_F_TAG_SHARED = 1 << 1,
BLK_MQ_F_SG_MERGE = 1 << 2,
- BLK_MQ_F_SYSFS_UP = 1 << 3,
BLK_MQ_F_DEFER_ISSUE = 1 << 4,
BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
BLK_MQ_F_ALLOC_POLICY_BITS = 1,
BLK_MQ_F_DEFER_ISSUE = 1 << 4,
BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
BLK_MQ_F_ALLOC_POLICY_BITS = 1,
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
struct bio_set *bio_split;
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
struct bio_set *bio_split;
+
+ bool mq_sysfs_init_done;
};
#define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */
};
#define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */