[PATCH] nvme-tcp: return -EPROTO for a C2HData on a write

[Yehyeong Lee]

The direction check in nvme_tcp_handle_c2h_data() returns -EIO.  A
C2HData PDU naming a command that did not ask for data is a protocol
violation, and the check that rejects a PDU on those grounds a few
lines below it - SUCCESS set without LAST - returns -EPROTO.

No caller distinguishes the two, so this changes the error code alone.

Suggested-by: Sagi Grimberg <sagi at grimberg.me>
Signed-off-by: Yehyeong Lee <yhlee at isslab.korea.ac.kr>
---
Measured on the test target: a write answered with C2HData changes the
log line from "receive failed:  -5" to "-71", and the neighbouring
payload check still reports -5.  Three runs each way.

Applies on top of "nvme-tcp: check the data direction of a C2HData PDU"
in nvme-7.3; squash into it if you prefer.  No Fixes: tag because that
commit has no upstream hash yet.

 drivers/nvme/host/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index a62d6e48f7190..a865bd0688543 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -683,7 +683,7 @@ static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue,
 		dev_err(queue->ctrl->ctrl.device,
 			"queue %d tag %#x unexpected data for a write\n",
 			nvme_tcp_queue_id(queue), rq->tag);
-		return -EIO;
+		return -EPROTO;
 	}
 
 	req = blk_mq_rq_to_pdu(rq);
-- 
2.43.0