From: Aurelien Aptel <aaptel@nvidia.com>
To: linux-nvme@lists.infradead.org, netdev@vger.kernel.org,
sagi@grimberg.me, hch@lst.de, kbusch@kernel.org, axboe@fb.com,
chaitanyak@nvidia.com, davem@davemloft.net, kuba@kernel.org
Cc: Aurelien Aptel <aaptel@nvidia.com>,
aurelien.aptel@gmail.com, smalin@nvidia.com, malin1024@gmail.com,
ogerlitz@nvidia.com, yorayz@nvidia.com, borisp@nvidia.com
Subject: [PATCH v11 08/25] nvme-tcp: Add DDP data-path
Date: Fri, 3 Feb 2023 15:26:48 +0200 [thread overview]
Message-ID: <20230203132705.627232-9-aaptel@nvidia.com> (raw)
In-Reply-To: <20230203132705.627232-1-aaptel@nvidia.com>
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>
---
drivers/nvme/host/tcp.c | 121 ++++++++++++++++++++++++++++++++++++++--
1 file changed, 116 insertions(+), 5 deletions(-)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index b350250bf8fb..533177971777 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -102,6 +102,13 @@ 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;
+ __le16 ddp_status;
+ union nvme_result result;
+#endif
};
enum nvme_tcp_queue_flags {
@@ -307,11 +314,75 @@ static bool nvme_tcp_ddp_query_limits(struct net_device *netdev,
return true;
}
+static int nvme_tcp_req_map_sg(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 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->offloading_netdev;
+ struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+
+ netdev->netdev_ops->ulp_ddp_ops->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->ddp_status, req->result))
+ nvme_complete_rq(rq);
+}
+
+static int nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue, u16 command_id,
+ struct request *rq)
+{
+ struct net_device *netdev = queue->ctrl->offloading_netdev;
+ struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+ int ret;
+
+ if (!(rq_data_dir(rq) == READ) ||
+ queue->ctrl->offload_io_threshold > blk_rq_payload_bytes(rq))
+ return 0;
+
+ req->ddp.command_id = command_id;
+ ret = nvme_tcp_req_map_sg(req, rq);
+ if (ret)
+ return -ENOMEM;
+
+ ret = netdev->netdev_ops->ulp_ddp_ops->setup(netdev, queue->sock->sk,
+ &req->ddp);
+ if (ret) {
+ sg_free_table_chained(&req->ddp.sg_table, SG_CHUNK_SIZE);
+ return ret;
+ }
+
+ /* if successful, sg table is freed in nvme_tcp_teardown_ddp() */
+ req->offloaded = true;
+ return 0;
+}
+
static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
{
struct net_device *netdev = queue->ctrl->offloading_netdev;
@@ -453,6 +524,12 @@ static inline bool is_netdev_ulp_offload_active(struct net_device *netdev)
return false;
}
+static int nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue, u16 command_id,
+ struct request *rq)
+{
+ return 0;
+}
+
static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
{
return 0;
@@ -740,6 +817,26 @@ 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)
+{
+#ifdef CONFIG_ULP_DDP
+ struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+
+ if (req->offloaded) {
+ req->ddp_status = status;
+ req->result = result;
+ nvme_tcp_teardown_ddp(req->queue, rq);
+ return;
+ }
+#endif
+
+ 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)
{
@@ -759,10 +856,9 @@ 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;
}
@@ -960,10 +1056,13 @@ 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,
@@ -1263,6 +1362,15 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
else
flags |= MSG_EOR;
+ if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags)) {
+ ret = nvme_tcp_setup_ddp(queue, pdu->cmd.common.command_id,
+ blk_mq_rq_from_pdu(req));
+ WARN_ONCE(ret, "ddp setup failed (queue 0x%x, cid 0x%x, ret=%d)",
+ nvme_tcp_queue_id(queue),
+ pdu->cmd.common.command_id,
+ ret);
+ }
+
if (queue->hdr_digest && !req->offset)
nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
@@ -2594,6 +2702,9 @@ 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;
--
2.31.1
next prev parent reply other threads:[~2023-02-03 13:28 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-03 13:26 [PATCH v11 00/25] nvme-tcp receive offloads Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 01/25] net: Introduce direct data placement tcp offload Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 02/25] net/ethtool: add new stringset ETH_SS_ULP_DDP_{CAPS,STATS} Aurelien Aptel
2023-02-04 3:42 ` Jakub Kicinski
2023-02-03 13:26 ` [PATCH v11 03/25] net/ethtool: add ULP_DDP_{GET,SET} operations for caps and stats Aurelien Aptel
2023-02-04 3:46 ` Jakub Kicinski
2023-02-03 13:26 ` [PATCH v11 04/25] Documentation: document netlink ULP_DDP_GET/SET messages Aurelien Aptel
2023-02-04 3:41 ` Jakub Kicinski
2023-02-06 9:48 ` Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 05/25] iov_iter: skip copy if src == dst for direct data placement Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 06/25] net/tls,core: export get_netdev_for_sock Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 07/25] nvme-tcp: Add DDP offload control path Aurelien Aptel
2023-02-03 13:26 ` Aurelien Aptel [this message]
2023-02-03 13:26 ` [PATCH v11 09/25] nvme-tcp: RX DDGST offload Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 10/25] nvme-tcp: Deal with netdevice DOWN events Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 11/25] nvme-tcp: Add modparam to control the ULP offload enablement Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 12/25] Documentation: add ULP DDP offload documentation Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 13/25] net/mlx5e: Rename from tls to transport static params Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 14/25] net/mlx5e: Refactor ico sq polling to get budget Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 15/25] net/mlx5e: Have mdev pointer directly on the icosq structure Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 16/25] net/mlx5e: Refactor doorbell function to allow avoiding a completion Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 17/25] net/mlx5: Add NVMEoTCP caps, HW bits, 128B CQE and enumerations Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 18/25] net/mlx5e: NVMEoTCP, offload initialization Aurelien Aptel
2023-02-03 13:26 ` [PATCH v11 19/25] net/mlx5e: TCP flow steering for nvme-tcp acceleration Aurelien Aptel
2023-02-03 13:27 ` [PATCH v11 20/25] net/mlx5e: NVMEoTCP, use KLM UMRs for buffer registration Aurelien Aptel
2023-02-03 13:27 ` [PATCH v11 21/25] net/mlx5e: NVMEoTCP, queue init/teardown Aurelien Aptel
2023-02-03 13:27 ` [PATCH v11 22/25] net/mlx5e: NVMEoTCP, ddp setup and resync Aurelien Aptel
2023-02-03 13:27 ` [PATCH v11 23/25] net/mlx5e: NVMEoTCP, async ddp invalidation Aurelien Aptel
2023-02-03 13:27 ` [PATCH v11 24/25] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Aurelien Aptel
2023-02-03 13:27 ` [PATCH v11 25/25] net/mlx5e: NVMEoTCP, statistics Aurelien Aptel
2023-02-23 15:33 ` [PATCH v11 00/25] nvme-tcp receive offloads Sagi Grimberg
2023-03-01 19:13 ` Shai Malin
2023-03-07 10:11 ` Sagi Grimberg
2023-03-22 10:19 ` Shai Malin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230203132705.627232-9-aaptel@nvidia.com \
--to=aaptel@nvidia.com \
--cc=aurelien.aptel@gmail.com \
--cc=axboe@fb.com \
--cc=borisp@nvidia.com \
--cc=chaitanyak@nvidia.com \
--cc=davem@davemloft.net \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=kuba@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=malin1024@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@nvidia.com \
--cc=sagi@grimberg.me \
--cc=smalin@nvidia.com \
--cc=yorayz@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).