There is a problem that nbd_handle_reply() might access freed request:
1) At first, a normal io is submitted and completed with scheduler:
internel_tag = blk_mq_get_tag -> get tag from sched_tags
blk_mq_rq_ctx_init
sched_tags->rq[internel_tag] = sched_tag->static_rq[internel_tag]
...
blk_mq_get_driver_tag
__blk_mq_get_driver_tag -> get tag from tags
tags->rq[tag] = sched_tag->static_rq[internel_tag]
So, both tags->rq[tag] and sched_tags->rq[internel_tag] are pointing
to the request: sched_tags->static_rq[internal_tag]. Even if the
io is finished.
2) nbd server send a reply with random tag directly:
recv_work
nbd_handle_reply
blk_mq_tag_to_rq(tags, tag)
rq = tags->rq[tag]
3) if the sched_tags->static_rq is freed:
blk_mq_sched_free_requests
blk_mq_free_rqs(q->tag_set, hctx->sched_tags, i)
-> step 2) access rq before clearing rq mapping
blk_mq_clear_rq_mapping(set, tags, hctx_idx);
__free_pages() -> rq is freed here
4) Then, nbd continue to use the freed request in nbd_handle_reply
Fix the problem by get 'q_usage_counter' before blk_mq_tag_to_rq(),
thus request is ensured not to be freed because 'q_usage_counter' is
not zero.
Signed-off-by: Yu Kuai <yukuai3@xxxxxxxxxx>
---
block/blk-core.c | 1 +
drivers/block/nbd.c | 19 ++++++++++++++++++-
2 files changed, 19 insertions(+), 1 deletion(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 5454db2fa263..2008e6903166 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -489,6 +489,7 @@ void blk_queue_exit(struct request_queue *q)
{
percpu_ref_put(&q->q_usage_counter);
}
+EXPORT_SYMBOL(blk_queue_exit);
static void blk_queue_usage_counter_release(struct percpu_ref *ref)
{
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 9a7bbf8ebe74..f065afcc7586 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -824,6 +824,7 @@ static void recv_work(struct work_struct *work)
work);
struct nbd_device *nbd = args->nbd;
struct nbd_config *config = nbd->config;
+ struct request_queue *q = nbd->disk->queue;
struct nbd_sock *nsock;
struct nbd_cmd *cmd;
struct request *rq;
@@ -834,13 +835,29 @@ static void recv_work(struct work_struct *work)
if (nbd_read_reply(nbd, args->index, &reply))
break;
+ /*
+ * Get q_usage_counter can prevent accessing freed request
+ * through blk_mq_tag_to_rq() in nbd_handle_reply(). If
+ * q_usage_counter is zero, then no request is inflight, which
+ * means something is wrong since we expect to find a request to
+ * complete here.
+ */
+ if (!percpu_ref_tryget(&q->q_usage_counter)) {
+ dev_err(disk_to_dev(nbd->disk), "%s: no io inflight\n",
+ __func__);
+ break;
+ }
+
cmd = nbd_handle_reply(nbd, args->index, &reply);
- if (IS_ERR(cmd))
+ if (IS_ERR(cmd)) {
+ blk_queue_exit(q);
break;
+ }
rq = blk_mq_rq_from_pdu(cmd);
if (likely(!blk_should_fake_timeout(rq->q)))
blk_mq_complete_request(rq);
+ blk_queue_exit(q);
