From: Sagi Grimberg <sagi@grimberg.me>
To: Boris Pismenny <borisp@mellanox.com>,
kuba@kernel.org, davem@davemloft.net, saeedm@nvidia.com,
hch@lst.de, axboe@fb.com, kbusch@kernel.org,
viro@zeniv.linux.org.uk, edumazet@google.com
Cc: Yoray Zack <yorayz@mellanox.com>,
Ben Ben-Ishay <benishay@mellanox.com>,
boris.pismenny@gmail.com, linux-nvme@lists.infradead.org,
netdev@vger.kernel.org, Or Gerlitz <ogerlitz@mellanox.com>
Subject: Re: [PATCH net-next RFC v1 06/10] nvme-tcp: Add DDP data-path
Date: Thu, 8 Oct 2020 15:29:08 -0700 [thread overview]
Message-ID: <5a23d221-fd3e-5802-ce68-7edec55068bb@grimberg.me> (raw)
In-Reply-To: <20200930162010.21610-7-borisp@mellanox.com>
> bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags);
> +void nvme_tcp_ddp_teardown_done(void *ddp_ctx);
> const struct tcp_ddp_ulp_ops nvme_tcp_ddp_ulp_ops __read_mostly = {
> +
> .resync_request = nvme_tcp_resync_request,
> + .ddp_teardown_done = nvme_tcp_ddp_teardown_done,
> };
>
> +static
> +int nvme_tcp_teardown_ddp(struct nvme_tcp_queue *queue,
> + uint16_t command_id,
> + struct request *rq)
> +{
> + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
> + struct net_device *netdev = queue->ctrl->offloading_netdev;
> + int ret;
> +
> + if (unlikely(!netdev)) {
> + pr_info_ratelimited("%s: netdev not found\n", __func__);
dev_info_ratelimited
> + return -EINVAL;
> + }
> +
> + ret = netdev->tcp_ddp_ops->tcp_ddp_teardown(netdev, queue->sock->sk,
> + &req->ddp, rq);
> + sg_free_table_chained(&req->ddp.sg_table, SG_CHUNK_SIZE);
> + req->offloaded = false;
> + return ret;
> +}
> +
> +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, cpu_to_le16(req->status << 1), req->result))
> + nvme_complete_rq(rq);
> +}
> +
> +static
> +int nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue,
> + uint16_t command_id,
> + struct request *rq)
> +{
> + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
> + struct net_device *netdev = queue->ctrl->offloading_netdev;
> + int ret;
> +
> + req->offloaded = false;
> +
> + if (unlikely(!netdev)) {
> + pr_info_ratelimited("%s: netdev not found\n", __func__);
> + return -EINVAL;
> + }
> +
> + req->ddp.command_id = command_id;
> + 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;
newline here
> + req->ddp.nents = blk_rq_map_sg(rq->q, rq, req->ddp.sg_table.sgl);
> +
> + ret = netdev->tcp_ddp_ops->tcp_ddp_setup(netdev,
> + queue->sock->sk,
> + &req->ddp);
> + if (!ret)
> + req->offloaded = true;
> + return ret;
> +}
> +
> static
> int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue,
> struct nvme_tcp_config *config)
> @@ -351,6 +422,25 @@ bool nvme_tcp_resync_request(struct sock *sk, u32 seq, u32 flags)
>
> #else
>
> +static
> +int nvme_tcp_setup_ddp(struct nvme_tcp_queue *queue,
> + uint16_t command_id,
> + struct request *rq)
> +{
> + return -EINVAL;
> +}
> +
> +static
> +int nvme_tcp_teardown_ddp(struct nvme_tcp_queue *queue,
> + uint16_t command_id,
> + struct request *rq)
> +{
> + return -EINVAL;
> +}
> +
> +void nvme_tcp_ddp_teardown_done(void *ddp_ctx)
> +{}
> +
> static
> int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue,
> struct nvme_tcp_config *config)
> @@ -630,6 +720,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
> 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 = blk_mq_tag_to_rq(nvme_tcp_tagset(queue), cqe->command_id);
> @@ -641,8 +732,15 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
> return -EINVAL;
> }
>
> - if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
> - nvme_complete_rq(rq);
> + req = blk_mq_rq_to_pdu(rq);
> + if (req->offloaded) {
> + req->status = cqe->status;
> + req->result = cqe->result;
> + nvme_tcp_teardown_ddp(queue, cqe->command_id, rq);
> + } else {
> + if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
> + nvme_complete_rq(rq);
> + }
> queue->nr_cqe++;
>
> return 0;
> @@ -836,9 +934,18 @@ 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)
> {
> union nvme_result res = {};
> + 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;
>
> - if (!nvme_try_complete_req(rq, cpu_to_le16(status << 1), res))
> - nvme_complete_rq(rq);
> + if (req->offloaded) {
> + req->status = cpu_to_le16(status << 1);
> + req->result = res;
> + nvme_tcp_teardown_ddp(queue, pdu->command_id, rq);
> + } else {
> + if (!nvme_try_complete_req(rq, cpu_to_le16(status << 1), res))
> + nvme_complete_rq(rq);
> + }
> }
>
> static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
> @@ -1115,6 +1222,7 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
> bool inline_data = nvme_tcp_has_inline_data(req);
> u8 hdgst = nvme_tcp_hdgst_len(queue);
> int len = sizeof(*pdu) + hdgst - req->offset;
> + struct request *rq = blk_mq_rq_from_pdu(req);
> int flags = MSG_DONTWAIT;
> int ret;
>
> @@ -1123,6 +1231,10 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
> else
> flags |= MSG_EOR;
>
> + if (test_bit(NVME_TCP_Q_OFFLOADS, &queue->flags) &&
> + blk_rq_nr_phys_segments(rq) && rq_data_dir(rq) == READ)
> + nvme_tcp_setup_ddp(queue, pdu->cmd.common.command_id, rq);
I'd assume that this is something we want to setup in
nvme_tcp_setup_cmd_pdu. Why do it here?
_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
next prev parent reply other threads:[~2020-10-08 22:29 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-30 16:20 [PATCH net-next RFC v1 00/10] nvme-tcp receive offloads Boris Pismenny
2020-09-30 16:20 ` [PATCH net-next RFC v1 01/10] iov_iter: Skip copy in memcpy_to_page if src==dst Boris Pismenny
2020-10-08 23:05 ` Sagi Grimberg
2020-09-30 16:20 ` [PATCH net-next RFC v1 02/10] net: Introduce direct data placement tcp offload Boris Pismenny
2020-10-08 21:47 ` Sagi Grimberg
2020-10-11 14:44 ` Boris Pismenny
2020-09-30 16:20 ` [PATCH net-next RFC v1 03/10] net: Introduce crc offload for tcp ddp ulp Boris Pismenny
2020-10-08 21:51 ` Sagi Grimberg
2020-10-11 14:58 ` Boris Pismenny
2020-09-30 16:20 ` [PATCH net-next RFC v1 04/10] net/tls: expose get_netdev_for_sock Boris Pismenny
2020-10-08 21:56 ` Sagi Grimberg
2020-09-30 16:20 ` [PATCH net-next RFC v1 05/10] nvme-tcp: Add DDP offload control path Boris Pismenny
2020-10-08 22:19 ` Sagi Grimberg
2020-10-19 18:28 ` Boris Pismenny
[not found] ` <PH0PR18MB3845430DDF572E0DD4832D06CCED0@PH0PR18MB3845.namprd18.prod.outlook.com>
2020-11-08 6:51 ` Shai Malin
2020-11-09 23:23 ` Sagi Grimberg
2020-11-11 5:12 ` FW: " Shai Malin
2020-11-11 5:43 ` Shai Malin
2020-09-30 16:20 ` [PATCH net-next RFC v1 06/10] nvme-tcp: Add DDP data-path Boris Pismenny
2020-10-08 22:29 ` Sagi Grimberg [this message]
2020-10-08 23:00 ` Sagi Grimberg
2020-11-08 13:59 ` Boris Pismenny
2020-11-08 9:44 ` Boris Pismenny
2020-11-09 23:18 ` Sagi Grimberg
2020-09-30 16:20 ` [PATCH net-next RFC v1 07/10] nvme-tcp : Recalculate crc in the end of the capsule Boris Pismenny
2020-10-08 22:44 ` Sagi Grimberg
[not found] ` <PH0PR18MB3845764B48FD24C87FA34304CCED0@PH0PR18MB3845.namprd18.prod.outlook.com>
[not found] ` <PH0PR18MB38458FD325BD77983D2623D4CCEB0@PH0PR18MB3845.namprd18.prod.outlook.com>
2020-11-08 6:59 ` Shai Malin
2020-11-08 7:28 ` Boris Pismenny
2020-11-08 14:46 ` Boris Pismenny
2020-09-30 16:20 ` [PATCH net-next RFC v1 08/10] nvme-tcp: Deal with netdevice DOWN events Boris Pismenny
2020-10-08 22:47 ` Sagi Grimberg
2020-10-11 6:54 ` Or Gerlitz
2020-09-30 16:20 ` [PATCH net-next RFC v1 09/10] net/mlx5e: Add NVMEoTCP offload Boris Pismenny
2020-09-30 16:20 ` [PATCH net-next RFC v1 10/10] net/mlx5e: NVMEoTCP, data-path for DDP offload Boris Pismenny
2020-10-09 0:08 ` [PATCH net-next RFC v1 00/10] nvme-tcp receive offloads Sagi Grimberg
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=5a23d221-fd3e-5802-ce68-7edec55068bb@grimberg.me \
--to=sagi@grimberg.me \
--cc=axboe@fb.com \
--cc=benishay@mellanox.com \
--cc=boris.pismenny@gmail.com \
--cc=borisp@mellanox.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=kuba@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@mellanox.com \
--cc=saeedm@nvidia.com \
--cc=viro@zeniv.linux.org.uk \
--cc=yorayz@mellanox.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).