1 files changed, 40 insertions, 27 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index a368eb6dc647..9e3fedbaa644 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -929,7 +929,7 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
 
 void blk_mq_put_rq_ref(struct request *rq)
 {
-	if (is_flush_rq(rq, rq->mq_hctx))
+	if (is_flush_rq(rq))
 		rq->end_io(rq, 0);
 	else if (refcount_dec_and_test(&rq->ref))
 		__blk_mq_free_request(rq);
@@ -941,34 +941,14 @@ static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 	unsigned long *next = priv;
 
 	/*
-	 * Just do a quick check if it is expired before locking the request in
-	 * so we're not unnecessarilly synchronizing across CPUs.
-	 */
-	if (!blk_mq_req_expired(rq, next))
-		return true;
-
-	/*
-	 * We have reason to believe the request may be expired. Take a
-	 * reference on the request to lock this request lifetime into its
-	 * currently allocated context to prevent it from being reallocated in
-	 * the event the completion by-passes this timeout handler.
-	 *
-	 * If the reference was already released, then the driver beat the
-	 * timeout handler to posting a natural completion.
-	 */
-	if (!refcount_inc_not_zero(&rq->ref))
-		return true;
-
-	/*
-	 * The request is now locked and cannot be reallocated underneath the
-	 * timeout handler's processing. Re-verify this exact request is truly
-	 * expired; if it is not expired, then the request was completed and
-	 * reallocated as a new request.
+	 * blk_mq_queue_tag_busy_iter() has locked the request, so it cannot
+	 * be reallocated underneath the timeout handler's processing, then
+	 * the expire check is reliable. If the request is not expired, then
+	 * it was completed and reallocated as a new request after returning
+	 * from blk_mq_check_expired().
 	 */
 	if (blk_mq_req_expired(rq, next))
 		blk_mq_rq_timed_out(rq, reserved);
-
-	blk_mq_put_rq_ref(rq);
 	return true;
 }
 
@@ -2609,16 +2589,49 @@ 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);