From: Daniel Wagner <dwagner@suse.de>
Date: Mon, 30 Aug 2021 15:36:26 +0200
Subject: nvme-tcp: Do not reset transport on data digest errors
Patch-mainline: v5.15-rc1
Git-commit: 1ba2e507f55c5b0cbde8c0fbfe0d9e39612a3e52
References: bsc#1190569 bsc#1188418

The spec says

  7.4.6.1 Digest Error handling

  When a host detects a data digest error in a C2HData PDU, that host
  shall continue processing C2HData PDUs associated with the command and
  when the command processing has completed, if a successful status was
  returned by the controller, the host shall fail the command with a
  non-fatal transport error.

Currently the transport is reseted when a data digest error is
detected. Instead, when a digest error is detected, mark the final
status as NVME_SC_DATA_XFER_ERROR and let the upper layer handle
the error.

In order to keep track of the final result maintain a status field in
nvme_tcp_request object and use it to overwrite the completion queue
status (which might be successful even though a digest error has been
detected) when completing the request.

Signed-off-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/tcp.c |   22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -45,6 +45,7 @@ struct nvme_tcp_request {
 	u32			pdu_len;
 	u32			pdu_sent;
 	u16			ttag;
+	__le16			status;
 	struct list_head	entry;
 	struct llist_node	lentry;
 	__le32			ddgst;
@@ -485,6 +486,7 @@ static void nvme_tcp_error_recovery(stru
 static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 		struct nvme_completion *cqe)
 {
+	struct nvme_tcp_request *req;
 	struct request *rq;
 
 	rq = nvme_find_rq(nvme_tcp_tagset(queue), cqe->command_id);
@@ -496,7 +498,11 @@ static int nvme_tcp_process_nvme_cqe(str
 		return -EINVAL;
 	}
 
-	if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
+	req = blk_mq_rq_to_pdu(rq);
+	if (req->status == cpu_to_le16(NVME_SC_SUCCESS))
+		req->status = cqe->status;
+
+	if (!nvme_try_complete_req(rq, req->status, cqe->result))
 		nvme_complete_rq(rq);
 	queue->nr_cqe++;
 
@@ -758,7 +764,8 @@ static int nvme_tcp_recv_data(struct nvm
 			queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH;
 		} else {
 			if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
-				nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
+				nvme_tcp_end_request(rq,
+						le16_to_cpu(req->status));
 				queue->nr_cqe++;
 			}
 			nvme_tcp_init_recv_ctx(queue);
@@ -788,18 +795,24 @@ static int nvme_tcp_recv_ddgst(struct nv
 		return 0;
 
 	if (queue->recv_ddgst != queue->exp_ddgst) {
+		struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
+					pdu->command_id);
+		struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+
+		req->status = cpu_to_le16(NVME_SC_DATA_XFER_ERROR);
+
 		dev_err(queue->ctrl->ctrl.device,
 			"data digest error: recv %#x expected %#x\n",
 			le32_to_cpu(queue->recv_ddgst),
 			le32_to_cpu(queue->exp_ddgst));
-		return -EIO;
 	}
 
 	if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
 		struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
 					pdu->command_id);
+		struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
-		nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
+		nvme_tcp_end_request(rq, le16_to_cpu(req->status));
 		queue->nr_cqe++;
 	}
 
@@ -2293,6 +2306,7 @@ static blk_status_t nvme_tcp_setup_cmd_p
 		return ret;
 
 	req->state = NVME_TCP_SEND_CMD_PDU;
+	req->status = cpu_to_le16(NVME_SC_SUCCESS);
 	req->offset = 0;
 	req->data_sent = 0;
 	req->pdu_len = 0;