[PATCH v2 2/3] nvme: make keep-alive synchronous operation

[Nilay Shroff]

The nvme keep-alive operation, which executes at a periodic interval,
could potentially sneak in while shutting down a fabric controller.
This may lead to a race between the fabric controller admin queue
destroy code path (while shutting down controller) and the blk-mq
hw/hctx queuing from the keep-alive thread.

This fix helps avoid race by implementing keep-alive as a synchronous
operation so that admin queue-usage ref counter is decremented only
after keep-alive command finish execution and returns its status. This
would ensure that we don't inadvertently destroy the fabric admin queue
until we finish processing of nvme keep-alive request and its status and
hence it's safe to delete the queue.

Signed-off-by: Nilay Shroff <nilay at linux.ibm.com>
---
 drivers/nvme/host/core.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 02897f0564a3..736adbf65ef5 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1292,10 +1292,10 @@ static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
 	queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
 }
 
-static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
-						 blk_status_t status)
+static void nvme_keep_alive_finish(struct request *rq,
+				blk_status_t status,
+				struct nvme_ctrl *ctrl)
 {
-	struct nvme_ctrl *ctrl = rq->end_io_data;
 	unsigned long flags;
 	bool startka = false;
 	unsigned long rtt = jiffies - (rq->deadline - rq->timeout);
@@ -1313,13 +1313,11 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
 		delay = 0;
 	}
 
-	blk_mq_free_request(rq);
-
 	if (status) {
 		dev_err(ctrl->device,
 			"failed nvme_keep_alive_end_io error=%d\n",
 				status);
-		return RQ_END_IO_NONE;
+		return;
 	}
 
 	ctrl->ka_last_check_time = jiffies;
@@ -1331,7 +1329,6 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 	if (startka)
 		queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
-	return RQ_END_IO_NONE;
 }
 
 static void nvme_keep_alive_work(struct work_struct *work)
@@ -1340,6 +1337,7 @@ static void nvme_keep_alive_work(struct work_struct *work)
 			struct nvme_ctrl, ka_work);
 	bool comp_seen = ctrl->comp_seen;
 	struct request *rq;
+	blk_status_t status;
 
 	ctrl->ka_last_check_time = jiffies;
 
@@ -1362,9 +1360,9 @@ static void nvme_keep_alive_work(struct work_struct *work)
 	nvme_init_request(rq, &ctrl->ka_cmd);
 
 	rq->timeout = ctrl->kato * HZ;
-	rq->end_io = nvme_keep_alive_end_io;
-	rq->end_io_data = ctrl;
-	blk_execute_rq_nowait(rq, false);
+	status = blk_execute_rq(rq, false);
+	nvme_keep_alive_finish(rq, status, ctrl);
+	blk_mq_free_request(rq);
 }
 
 static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
-- 
2.45.2