blk-mq: clearing flush request reference in tags->rqs[]

Before we free request queue, clearing flush request reference in
tags->rqs[], so that potential UAF can be avoided.

Based on one patch written by David Jeffery.

Tested-by: John Garry <john.garry@huawei.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: David Jeffery <djeffery@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20210511152236.763464-5-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 34 insertions, 1 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index dd371f321d35..fbb165393790 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2643,16 +2643,49 @@ static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
 					    &hctx->cpuhp_dead);
 }
 
+/*
+ * Before freeing hw queue, clearing the flush request reference in
+ * tags->rqs[] for avoiding potential UAF.
+ */
+static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags,
+		unsigned int queue_depth, struct request *flush_rq)
+{
+	int i;
+	unsigned long flags;
+
+	/* The hw queue may not be mapped yet */
+	if (!tags)
+		return;
+
+	WARN_ON_ONCE(refcount_read(&flush_rq->ref) != 0);
+
+	for (i = 0; i < queue_depth; i++)
+		cmpxchg(&tags->rqs[i], flush_rq, NULL);
+
+	/*
+	 * Wait until all pending iteration is done.
+	 *
+	 * Request reference is cleared and it is guaranteed to be observed
+	 * after the ->lock is released.
+	 */
+	spin_lock_irqsave(&tags->lock, flags);
+	spin_unlock_irqrestore(&tags->lock, flags);
+}
+
 /* 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,
 		struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 {
+	struct request *flush_rq = hctx->fq->flush_rq;
+
 	if (blk_mq_hw_queue_mapped(hctx))
 		blk_mq_tag_idle(hctx);
 
+	blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx],
+			set->queue_depth, flush_rq);
 	if (set->ops->exit_request)
-		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
+		set->ops->exit_request(set, flush_rq, hctx_idx);
 
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);