In NVMe's error handler, follows the typical steps of tearing down
hardware for recovering controller:
1) stop blk_mq hw queues
2) stop the real hw queues
3) cancel in-flight requests via
blk_mq_tagset_busy_iter(tags, cancel_request, ...)
cancel_request():
mark the request as abort
blk_mq_complete_request(req);
4) destroy real hw queues
However, there may be race between #3 and #4, because blk_mq_complete_request()
may run q->mq_ops->complete(rq) remotelly and asynchronously, and
->complete(rq) may be run after #4.
This patch introduces blk_mq_complete_request_sync() for fixing the
above race.
Cc: Keith Busch <kbusch@xxxxxxxxxx>
Cc: Sagi Grimberg <sagi@xxxxxxxxxxx>
Cc: Bart Van Assche <bvanassche@xxxxxxx>
Cc: James Smart <james.smart@xxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: linux-nvme@xxxxxxxxxxxxxxxxxxx
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
block/blk-mq.c | 7 +++++++
include/linux/blk-mq.h | 1 +
2 files changed, 8 insertions(+)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a9354835cf51..9516304a38ee 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -654,6 +654,13 @@ bool blk_mq_complete_request(struct request *rq)
}
EXPORT_SYMBOL(blk_mq_complete_request);
+void blk_mq_complete_request_sync(struct request *rq)
+{
+ WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
+ rq->q->mq_ops->complete(rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync);
+
int blk_mq_request_started(struct request *rq)
{
return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index cb2aa7ecafff..db29928de467 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -302,6 +302,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
bool blk_mq_complete_request(struct request *rq);
+void blk_mq_complete_request_sync(struct request *rq);
bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
struct bio *bio);
bool blk_mq_queue_stopped(struct request_queue *q);
--
2.9.5
