blk-mq: Defer freeing flush queue to SRCU callback

The freeing of the flush queue/request in blk_mq_exit_hctx() can race with
tag iterators that may still be accessing it. To prevent a potential
use-after-free, the deallocation should be deferred until after a grace
period. With this way, we can replace the big tags->lock in tags iterator
code path with srcu for solving the issue.

This patch introduces an SRCU-based deferred freeing mechanism for the
flush queue.

The changes include:
- Adding a `rcu_head` to `struct blk_flush_queue`.
- Creating a new callback function, `blk_free_flush_queue_callback`,
  to handle the actual freeing.
- Replacing the direct call to `blk_free_flush_queue()` in
  `blk_mq_exit_hctx()` with `call_srcu()`, using the `tags_srcu`
  instance to ensure synchronization with tag iterators.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index e1b44173029c807ec73606520d07f92c5f510724..1c3cdf17af79fb10daf09c169a0eb1e7817cac96 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3912,6 +3912,14 @@ static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags,
        spin_unlock_irqrestore(&tags->lock, flags);
 }
 
+static void blk_free_flush_queue_callback(struct rcu_head *head)
+{
+       struct blk_flush_queue *fq =
+               container_of(head, struct blk_flush_queue, rcu_head);
+
+       blk_free_flush_queue(fq);
+}
+
 /* hctx->ctxs will be freed in queue's release handler */
 static void blk_mq_exit_hctx(struct request_queue *q,
                struct blk_mq_tag_set *set,
@@ -3931,7 +3939,8 @@ static void blk_mq_exit_hctx(struct request_queue *q,
        if (set->ops->exit_hctx)
                set->ops->exit_hctx(hctx, hctx_idx);
 
-       blk_free_flush_queue(hctx->fq);
+       call_srcu(&set->tags_srcu, &hctx->fq->rcu_head,
+                       blk_free_flush_queue_callback);
        hctx->fq = NULL;
 
        xa_erase(&q->hctx_table, hctx_idx);

diff --git a/block/blk.h b/block/blk.h
index 46f566f9b1266c7cd7add6daf58c325363e7c27f..7d420c247d810b5336806ca7fe14601d3d171b4b 100644 (file)
--- a/block/blk.h
+++ b/block/blk.h
@@ -41,6 +41,7 @@ struct blk_flush_queue {
        struct list_head        flush_queue[2];
        unsigned long           flush_data_in_flight;
        struct request          *flush_rq;
+       struct rcu_head         rcu_head;
 };
 
 bool is_flush_rq(struct request *req);