block: properly protect the 'queue' kobj in blk_unregister_queue

The original commit e9a823fb34a8b (block: fix warning when I/O elevator
is changed as request_queue is being removed) is pretty conflated.
"conflated" because the resource being protected by q->sysfs_lock isn't
the queue_flags (it is the 'queue' kobj).

q->sysfs_lock serializes __elevator_change() (via elv_iosched_store)
from racing with blk_unregister_queue():
1) By holding q->sysfs_lock first, __elevator_change() can complete
before a racing blk_unregister_queue().
2) Conversely, __elevator_change() is testing for QUEUE_FLAG_REGISTERED
in case elv_iosched_store() loses the race with blk_unregister_queue(),
it needs a way to know the 'queue' kobj isn't there.

Expand the scope of blk_unregister_queue()'s q->sysfs_lock use so it is
held until after the 'queue' kobj is removed.

To do so blk_mq_unregister_dev() must not also take q->sysfs_lock.  So
rename __blk_mq_unregister_dev() to blk_mq_unregister_dev().

Also, blk_unregister_queue() should use q->queue_lock to protect against
any concurrent writes to q->queue_flags -- even though chances are the
queue is being cleaned up so no concurrent writes are likely.

Fixes: e9a823fb34a8b ("block: fix warning when I/O elevator is changed as request_queue is being removed")
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 79969c3c234fd9db3f76f2186d3f7080e9f1e321..a54b4b070f1c7a61c03a2d4ca84c6d5e8a7930dc 100644 (file)
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -248,7 +248,7 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
        return ret;
 }
 
-static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
+void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 {
        struct blk_mq_hw_ctx *hctx;
        int i;
@@ -265,13 +265,6 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
        q->mq_sysfs_init_done = false;
 }
 
-void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
-{
-       mutex_lock(&q->sysfs_lock);
-       __blk_mq_unregister_dev(dev, q);
-       mutex_unlock(&q->sysfs_lock);
-}
-
 void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
 {
        kobject_init(&hctx->kobj, &blk_mq_hw_ktype);

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 870484eaed1f64b586ccb0fd4dd34c3f9462a29d..9272452ff456daddb93723f130a635909947d40f 100644 (file)
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -929,12 +929,17 @@ void blk_unregister_queue(struct gendisk *disk)
        if (WARN_ON(!q))
                return;
 
+       /*
+        * Protect against the 'queue' kobj being accessed
+        * while/after it is removed.
+        */
        mutex_lock(&q->sysfs_lock);
-       queue_flag_clear_unlocked(QUEUE_FLAG_REGISTERED, q);
-       mutex_unlock(&q->sysfs_lock);
 
-       wbt_exit(q);
+       spin_lock_irq(q->queue_lock);
+       queue_flag_clear(QUEUE_FLAG_REGISTERED, q);
+       spin_unlock_irq(q->queue_lock);
 
+       wbt_exit(q);
 
        if (q->mq_ops)
                blk_mq_unregister_dev(disk_to_dev(disk), q);
@@ -946,4 +951,6 @@ void blk_unregister_queue(struct gendisk *disk)
        kobject_del(&q->kobj);
        blk_trace_remove_sysfs(disk_to_dev(disk));
        kobject_put(&disk_to_dev(disk)->kobj);
+
+       mutex_unlock(&q->sysfs_lock);
 }