BACKPORT: blk-mq: grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter

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 use-after-free(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.

Tested-by: John Garry <john.garry@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Ming Lei <ming.lei@redhat.com>

Bug: 197804811
Change-Id: Ib80fe8b9f1d76d2489e41f3365fbd12d68a3b097
(cherry picked from commit 2e315dc07df009c3e29d6926871f62a30cfae394)
[Pradeep: Resolved conflicts in block/blk-mq-tag.c]
Signed-off-by: Pradeep P V K <pragalla@codeaurora.org>

block/blk-mq-tag.c

@@ -212,6 +212,16 @@ struct bt_iter_data {
 	bool reserved;
 };
 
+static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags,
+		unsigned int bitnr)
+{
+	struct request *rq = tags->rqs[bitnr];
+
+	if (!rq || !refcount_inc_not_zero(&rq->ref))
+		return NULL;
+	return rq;
+}
+
 static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 {
 	struct bt_iter_data *iter_data = data;
@@ -219,18 +229,23 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	struct blk_mq_tags *tags = hctx->tags;
 	bool reserved = iter_data->reserved;
 	struct request *rq;
+	bool ret = true;
 
 	if (!reserved)
 		bitnr += tags->nr_reserved_tags;
-	rq = tags->rqs[bitnr];
 
 	/*
 	 * We can hit rq == NULL here, because the tagging functions
 	 * test and set the bit before assigning ->rqs[].
 	 */
-	if (rq && rq->q == hctx->queue)
-		return iter_data->fn(hctx, rq, iter_data->data, reserved);
+	rq = blk_mq_find_and_get_req(tags, bitnr);
+	if (!rq)
 		return true;
+
+	if (rq->q == hctx->queue && rq->mq_hctx == hctx)
+		ret = iter_data->fn(hctx, rq, iter_data->data, reserved);
+	blk_mq_put_rq_ref(rq);
+	return ret;
 }
 
 /**
@@ -273,6 +288,7 @@ 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->reserved;
 	struct request *rq;
+	bool ret = true;
 
 	if (!reserved)
 		bitnr += tags->nr_reserved_tags;
@@ -281,11 +297,13 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	 * We can hit rq == NULL here, because the tagging functions
 	 * test and set the bit before assining ->rqs[].
 	 */
-	rq = tags->rqs[bitnr];
-	if (rq && blk_mq_request_started(rq))
-		return iter_data->fn(rq, iter_data->data, reserved);
-
+	rq = blk_mq_find_and_get_req(tags, bitnr);
+	if (!rq)
 		return true;
+	if (blk_mq_request_started(rq))
+		ret = iter_data->fn(rq, iter_data->data, reserved);
+	blk_mq_put_rq_ref(rq);
+	return ret;
 }
 
 /**
@@ -342,6 +360,9 @@ static void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags,
  *		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.
  */
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv)

block/blk-mq.c

@@ -886,6 +886,14 @@ 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)
 {
@@ -919,11 +927,7 @@ 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;
 }
 

block/blk-mq.h

@@ -47,6 +47,7 @@ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 bool blk_mq_get_driver_tag(struct request *rq);
 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