[PATCH 7/8] blk-mq: grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter

[Ming Lei <ming.lei@redhat.com>]

Grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter(), and
this way will prevent the request from being re-used when ->fn is
running. The approach is same as what we do during handling timeout.

Fix request UAF related with completion race or queue releasing:

- If one rq is referred before rq->q is frozen, then queue won't be
frozen before the request is released during iteration.

- If one rq is referred after rq->q is frozen, refcount_inc_not_zero()
will return false, and we won't iterate over this request.

However, still one request UAF not covered: refcount_inc_not_zero() may
read one freed request, and it will be handled in next patch.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-mq-tag.c | 14 +++++++++++---
 block/blk-mq.c     | 14 +++++++++-----
 block/blk-mq.h     |  1 +
 3 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 2a37731e8244..489d2db89856 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -264,6 +264,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	struct blk_mq_tags *tags = iter_data->tags;
 	bool reserved = iter_data->flags & BT_TAG_ITER_RESERVED;
 	struct request *rq;
+	bool ret;
 
 	if (!reserved)
 		bitnr += tags->nr_reserved_tags;
@@ -276,12 +277,15 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 		rq = tags->static_rqs[bitnr];
 	else
 		rq = tags->rqs[bitnr];
-	if (!rq)
+	if (!rq || !refcount_inc_not_zero(&rq->ref))
 		return true;
 	if ((iter_data->flags & BT_TAG_ITER_STARTED) &&
 	    !blk_mq_request_started(rq))
-		return true;
-	return iter_data->fn(rq, iter_data->data, reserved);
+		ret = true;
+	else
+		ret = iter_data->fn(rq, iter_data->data, reserved);
+	blk_mq_put_rq_ref(rq);
+	return ret;
 }
 
 /**
@@ -348,6 +352,10 @@ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
  *		indicates whether or not @rq is a reserved request. Return
  *		true to continue iterating tags, false to stop.
  * @priv:	Will be passed as second argument to @fn.
+ *
+ * We grab one request reference before calling @fn and release it after
+ * @fn returns. So far we don't support to pass the request reference to
+ * one new conetxt in @fn.
  */
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e3d1067b10c3..9a4d520740a1 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -925,6 +925,14 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
 	return false;
 }
 
+void blk_mq_put_rq_ref(struct request *rq)
+{
+	if (is_flush_rq(rq, rq->mq_hctx))
+		rq->end_io(rq, 0);
+	else if (refcount_dec_and_test(&rq->ref))
+		__blk_mq_free_request(rq);
+}
+
 static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		struct request *rq, void *priv, bool reserved)
 {
@@ -958,11 +966,7 @@ static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 	if (blk_mq_req_expired(rq, next))
 		blk_mq_rq_timed_out(rq, reserved);
 
-	if (is_flush_rq(rq, hctx))
-		rq->end_io(rq, 0);
-	else if (refcount_dec_and_test(&rq->ref))
-		__blk_mq_free_request(rq);
-
+	blk_mq_put_rq_ref(rq);
 	return true;
 }
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 3616453ca28c..143afe42c63a 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -47,6 +47,7 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start);
+void blk_mq_put_rq_ref(struct request *rq);
 
 /*
  * Internal helpers for allocating/freeing the request map
-- 
2.29.2