Re: [PATCH v23 06/20] nvme-tcp: Add DDP data-path

[Sagi Grimberg <sagi@grimberg.me>]

On 28/02/2024 14:57, Aurelien Aptel wrote:
> From: Boris Pismenny <borisp@nvidia.com>
>
> Introduce the NVMe-TCP DDP data-path offload.
> Using this interface, the NIC hardware will scatter TCP payload directly
> to the BIO pages according to the command_id in the PDU.
> To maintain the correctness of the network stack, the driver is expected
> to construct SKBs that point to the BIO pages.
>
> The data-path interface contains two routines: setup/teardown.
> The setup provides the mapping from command_id to the request buffers,
> while the teardown removes this mapping.
>
> For efficiency, we introduce an asynchronous nvme completion, which is
> split between NVMe-TCP and the NIC driver as follows:
> NVMe-TCP performs the specific completion, while NIC driver performs the
> generic mq_blk completion.
>
> Signed-off-by: Boris Pismenny <borisp@nvidia.com>
> Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
> Signed-off-by: Or Gerlitz <ogerlitz@nvidia.com>
> Signed-off-by: Yoray Zack <yorayz@nvidia.com>
> Signed-off-by: Shai Malin <smalin@nvidia.com>
> Signed-off-by: Aurelien Aptel <aaptel@nvidia.com>
> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
> Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com>
> ---
>   drivers/nvme/host/tcp.c | 135 ++++++++++++++++++++++++++++++++++++++--
>   1 file changed, 130 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
> index 86a9ad9f679b..b7cfe14661d6 100644
> --- a/drivers/nvme/host/tcp.c
> +++ b/drivers/nvme/host/tcp.c
> @@ -120,6 +120,10 @@ struct nvme_tcp_request {
>   	struct llist_node	lentry;
>   	__le32			ddgst;
>   
> +	/* ddp async completion */
> +	__le16			nvme_status;
> +	union nvme_result	result;
> +
>   	struct bio		*curr_bio;
>   	struct iov_iter		iter;
>   
> @@ -127,6 +131,11 @@ struct nvme_tcp_request {
>   	size_t			offset;
>   	size_t			data_sent;
>   	enum nvme_tcp_send_state state;
> +
> +#ifdef CONFIG_ULP_DDP
> +	bool			offloaded;
> +	struct ulp_ddp_io	ddp;
> +#endif
>   };
>   
>   enum nvme_tcp_queue_flags {
> @@ -333,6 +342,25 @@ static inline size_t nvme_tcp_pdu_last_send(struct nvme_tcp_request *req,
>   
>   #ifdef CONFIG_ULP_DDP
>   
> +static bool nvme_tcp_is_ddp_offloaded(const struct nvme_tcp_request *req)
> +{
> +	return req->offloaded;
> +}
> +
> +static int nvme_tcp_ddp_alloc_sgl(struct nvme_tcp_request *req, struct request *rq)
> +{
> +	int ret;
> +
> +	req->ddp.sg_table.sgl = req->ddp.first_sgl;
> +	ret = sg_alloc_table_chained(&req->ddp.sg_table,
> +				     blk_rq_nr_phys_segments(rq),
> +				     req->ddp.sg_table.sgl, SG_CHUNK_SIZE);
> +	if (ret)
> +		return -ENOMEM;
> +	req->ddp.nents = blk_rq_map_sg(rq->q, rq, req->ddp.sg_table.sgl);
> +	return 0;
> +}
> +
>   static struct net_device *
>   nvme_tcp_get_ddp_netdev_with_limits(struct nvme_tcp_ctrl *ctrl)
>   {
> @@ -366,10 +394,68 @@ nvme_tcp_get_ddp_netdev_with_limits(struct nvme_tcp_ctrl *ctrl)
>   }
>   
>   static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags);
> +static void nvme_tcp_ddp_teardown_done(void *ddp_ctx);
>   static const struct ulp_ddp_ulp_ops nvme_tcp_ddp_ulp_ops = {
>   	.resync_request		= nvme_tcp_resync_request,
> +	.ddp_teardown_done	= nvme_tcp_ddp_teardown_done,
>   };
>   
> +static void nvme_tcp_teardown_ddp(struct nvme_tcp_queue *queue,
> +				  struct request *rq)
> +{
> +	struct net_device *netdev = queue->ctrl->ddp_netdev;
> +	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
> +
> +	ulp_ddp_teardown(netdev, queue->sock->sk, &req->ddp, rq);
> +	sg_free_table_chained(&req->ddp.sg_table, SG_CHUNK_SIZE);
> +}
> +
> +static void nvme_tcp_ddp_teardown_done(void *ddp_ctx)
> +{
> +	struct request *rq = ddp_ctx;
> +	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
> +
> +	if (!nvme_try_complete_req(rq, req->nvme_status, req->result))
> +		nvme_complete_rq(rq);
> +}
> +
> +static void nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue,
> +			       struct request *rq)
> +{
> +	struct net_device *netdev = queue->ctrl->ddp_netdev;
> +	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
> +	int ret;
> +
> +	if (rq_data_dir(rq) != READ ||
> +	    queue->ctrl->ddp_threshold > blk_rq_payload_bytes(rq))
> +		return;
> +
> +	/*
> +	 * DDP offload is best-effort, errors are ignored.
> +	 */
> +
> +	req->ddp.command_id = nvme_cid(rq);
> +	ret = nvme_tcp_ddp_alloc_sgl(req, rq);
> +	if (ret)
> +		goto err;
> +
> +	ret = ulp_ddp_setup(netdev, queue->sock->sk, &req->ddp);
> +	if (ret) {
> +		sg_free_table_chained(&req->ddp.sg_table, SG_CHUNK_SIZE);
> +		goto err;
> +	}
> +
> +	/* if successful, sg table is freed in nvme_tcp_teardown_ddp() */
> +	req->offloaded = true;
> +
> +	return;
> +err:
> +	WARN_ONCE(ret, "ddp setup failed (queue 0x%x, cid 0x%x, ret=%d)",
> +		  nvme_tcp_queue_id(queue),
> +		  nvme_cid(rq),
> +		  ret);
> +}
> +
>   static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
>   {
>   	struct ulp_ddp_config config = {.type = ULP_DDP_NVME};
> @@ -473,6 +559,11 @@ static bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags)
>   
>   #else
>   
> +static bool nvme_tcp_is_ddp_offloaded(const struct nvme_tcp_request *req)
> +{
> +	return false;
> +}
> +
>   static struct net_device *
>   nvme_tcp_get_ddp_netdev_with_limits(struct nvme_tcp_ctrl *ctrl)
>   {
> @@ -490,6 +581,14 @@ static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
>   static void nvme_tcp_unoffload_socket(struct nvme_tcp_queue *queue)
>   {}
>   
> +static void nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue,
> +			       struct request *rq)
> +{}
> +
> +static void nvme_tcp_teardown_ddp(struct nvme_tcp_queue *queue,
> +				  struct request *rq)
> +{}
> +
>   static void nvme_tcp_resync_response(struct nvme_tcp_queue *queue,
>   				     struct sk_buff *skb, unsigned int offset)
>   {}
> @@ -765,6 +864,24 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
>   	queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work);
>   }
>   
> +static void nvme_tcp_complete_request(struct request *rq,
> +				      __le16 status,
> +				      union nvme_result result,
> +				      __u16 command_id)
> +{
> +	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
> +
> +	if (nvme_tcp_is_ddp_offloaded(req)) {
> +		req->nvme_status = status;

this can just be called req->status I think.

> +		req->result = result;

I think it will be cleaner to always capture req->result and req->status
regardless of ddp offload.