[V2,1/3] blk-mq: grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter

Commit Message

Ming Lei April 27, 2021, 1:45 a.m. UTC

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 <[e-mail]>
---
 block/blk-mq-tag.c | 23 +++++++++++++++++------
 block/blk-mq.c     | 14 +++++++++-----
 block/blk-mq.h     |  1 +
 3 files changed, 27 insertions(+), 11 deletions(-)

Comments

Bart Van Assche April 27, 2021, 2:28 a.m. UTC | #1

On 4/26/21 6:45 PM, Ming Lei wrote:
> + * 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.
              ^^^^^^^
              context?

> +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);
> +}

Will rq->end_io() be called twice when a tag iteration function
encounters a flush request?

Thanks,

Bart.

Ming Lei April 27, 2021, 2:45 a.m. UTC | #2

On Mon, Apr 26, 2021 at 07:28:18PM -0700, Bart Van Assche wrote:
> On 4/26/21 6:45 PM, Ming Lei wrote:
> > + * 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.
>               ^^^^^^^
>               context?
> 
> > +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);
> > +}
> 
> Will rq->end_io() be called twice when a tag iteration function
> encounters a flush request?

It could be, see flush_end_io():

static void flush_end_io(struct request *flush_rq, blk_status_t error)
{
		...
        spin_lock_irqsave(&fq->mq_flush_lock, flags);

        if (!refcount_dec_and_test(&flush_rq->ref)) {
                fq->rq_status = error;
                spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
				return;
		}
		...


Thanks,
Ming

Patch

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 2a37731e8244..100fa44d52a6 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -264,6 +264,8 @@  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;
+	bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS);
 
 	if (!reserved)
 		bitnr += tags->nr_reserved_tags;
@@ -272,16 +274,21 @@  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
+	else {
 		rq = tags->rqs[bitnr];
-	if (!rq)
-		return true;
+		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);
+	if (!iter_static_rqs)
+		blk_mq_put_rq_ref(rq);
+	return ret;
 }
 
 /**
@@ -348,6 +355,10 @@  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 927189a55575..4bd6c11bd8bc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -909,6 +909,14 @@  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)
 {
@@ -942,11 +950,7 @@  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