Message-Id: <20240228125733.299384-7-aaptel@nvidia.com>
Date: Wed, 28 Feb 2024 12:57:19 +0000
From: Aurelien Aptel <aaptel@...dia.com>
To: linux-nvme@...ts.infradead.org,
	netdev@...r.kernel.org,
	sagi@...mberg.me,
	hch@....de,
	kbusch@...nel.org,
	axboe@...com,
	chaitanyak@...dia.com,
	davem@...emloft.net,
	kuba@...nel.org
Cc: Boris Pismenny <borisp@...dia.com>,
	aaptel@...dia.com,
	aurelien.aptel@...il.com,
	smalin@...dia.com,
	malin1024@...il.com,
	ogerlitz@...dia.com,
	yorayz@...dia.com,
	galshalom@...dia.com,
	mgurtovoy@...dia.com
Subject: [PATCH v23 06/20] nvme-tcp: Add DDP data-path

From: Boris Pismenny <borisp@...dia.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@...dia.com>
Signed-off-by: Ben Ben-Ishay <benishay@...dia.com>
Signed-off-by: Or Gerlitz <ogerlitz@...dia.com>
Signed-off-by: Yoray Zack <yorayz@...dia.com>
Signed-off-by: Shai Malin <smalin@...dia.com>
Signed-off-by: Aurelien Aptel <aaptel@...dia.com>
Reviewed-by: Chaitanya Kulkarni <kch@...dia.com>
Reviewed-by: Max Gurtovoy <mgurtovoy@...dia.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;
+		req->result = result;
+		nvme_tcp_teardown_ddp(req->queue, rq);
+		return;
+	}
+
+	if (!nvme_try_complete_req(rq, status, result))
+		nvme_complete_rq(rq);
+}
+
 static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 		struct nvme_completion *cqe)
 {
@@ -784,10 +901,9 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 	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);
+	nvme_tcp_complete_request(rq, req->status, cqe->result,
+				  cqe->command_id);
 	queue->nr_cqe++;
-
 	return 0;
 }
 
@@ -985,10 +1101,13 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 
 static inline void nvme_tcp_end_request(struct request *rq, u16 status)
 {
+	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_tcp_queue *queue = req->queue;
+	struct nvme_tcp_data_pdu *pdu = (void *)queue->pdu;
 	union nvme_result res = {};
 
-	if (!nvme_try_complete_req(rq, cpu_to_le16(status << 1), res))
-		nvme_complete_rq(rq);
+	nvme_tcp_complete_request(rq, cpu_to_le16(status << 1), res,
+				  pdu->command_id);
 }
 
 static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
@@ -2734,6 +2853,9 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
 	if (ret)
 		return ret;
 
+#ifdef CONFIG_ULP_DDP
+	req->offloaded = false;
+#endif
 	req->state = NVME_TCP_SEND_CMD_PDU;
 	req->status = cpu_to_le16(NVME_SC_SUCCESS);
 	req->offset = 0;
@@ -2772,6 +2894,9 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
 		return ret;
 	}
 
+	if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags))
+		nvme_tcp_setup_ddp(queue, rq);
+
 	return 0;
 }
 
-- 
2.34.1

Powered by blists - more mailing lists