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>
Link: https://lore.kernel.org/r/20210511152236.763464-3-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 2a37731..544edf2 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -199,6 +199,16 @@ 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;
@@ -206,18 +216,22 @@ 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 && rq->mq_hctx == hctx)
- return iter_data->fn(hctx, rq, iter_data->data, reserved);
- return true;
+ 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;
}
/**
@@ -264,6 +278,8 @@ 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 = true;
+ bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS);
if (!reserved)
bitnr += tags->nr_reserved_tags;
@@ -272,16 +288,19 @@ 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 assigning ->rqs[].
*/
- if (iter_data->flags & BT_TAG_ITER_STATIC_RQS)
+ if (iter_static_rqs)
rq = tags->static_rqs[bitnr];
else
- rq = tags->rqs[bitnr];
+ rq = blk_mq_find_and_get_req(tags, bitnr);
if (!rq)
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);
+
+ if (!(iter_data->flags & BT_TAG_ITER_STARTED) ||
+ blk_mq_request_started(rq))
+ ret = iter_data->fn(rq, iter_data->data, reserved);
+ if (!iter_static_rqs)
+ blk_mq_put_rq_ref(rq);
+ return ret;
}
/**
@@ -348,6 +367,9 @@ 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.
*/
void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
busy_tag_iter_fn *fn, void *priv)
