[PATCH] nvme-tcp: Do not reset transport on data digest errors

[Sagi Grimberg]

> 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. To fix this, keep track of the final status in the queue
> object and use it when completing the request.
> 
> The new member can be placed adjacent to the receive related members and
> fits in the cacheline as there is a 4 byte hole.
> 
> Signed-off-by: Daniel Wagner <dwagner at suse.de>
> ---
> 
> Hi,
> 
> I've tested this by modifying the receive path. Via the fault_inject
> interface I injecting wrong hash values. The request would then be
> completed with status != 0 and nvme_decide_disposition decices to
> retry the request. So this seems be in more sync with what the spec
> says on this topic.
> 
> Daniel
> 
>   drivers/nvme/host/tcp.c | 11 +++++++----
>   1 file changed, 7 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
> index 097f7dd10ed3..5253147df4c7 100644
> --- a/drivers/nvme/host/tcp.c
> +++ b/drivers/nvme/host/tcp.c
> @@ -89,6 +89,7 @@ struct nvme_tcp_queue {
>   	size_t			data_remaining;
>   	size_t			ddgst_remaining;
>   	unsigned int		nr_cqe;
> +	u16			status;

Why is this a queue member and not a request member?

>   
>   	/* send state */
>   	struct nvme_tcp_request *request;
> @@ -496,7 +497,8 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
>   		return -EINVAL;
>   	}
>   
> -	if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
> +	if (!nvme_try_complete_req(rq, queue->status ?
> +			queue->status : cqe->status, cqe->result))
>   		nvme_complete_rq(rq);
>   	queue->nr_cqe++;
>   
> @@ -676,6 +678,7 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
>   
>   	switch (hdr->type) {
>   	case nvme_tcp_c2h_data:
> +		queue->status = NVME_SC_SUCCESS;
>   		return nvme_tcp_handle_c2h_data(queue, (void *)queue->pdu);
>   	case nvme_tcp_rsp:
>   		nvme_tcp_init_recv_ctx(queue);
> @@ -758,7 +761,7 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
>   			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, queue->status);
>   				queue->nr_cqe++;
>   			}
>   			nvme_tcp_init_recv_ctx(queue);
> @@ -792,14 +795,14 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
>   			"data digest error: recv %#x expected %#x\n",
>   			le32_to_cpu(queue->recv_ddgst),
>   			le32_to_cpu(queue->exp_ddgst));
> -		return -EIO;
> +		queue->status = NVME_SC_DATA_XFER_ERROR;
>   	}
>   
>   	if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
>   		struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
>   					pdu->command_id);
>   
> -		nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
> +		nvme_tcp_end_request(rq, queue->status);
>   		queue->nr_cqe++;
>   	}
>   
>