All of lore.kernel.org
 help / color / mirror / Atom feed
From: Aurelien Aptel <aaptel@nvidia.com>
To: Sagi Grimberg <sagi@grimberg.me>,
	linux-nvme@lists.infradead.org, netdev@vger.kernel.org,
	hch@lst.de, kbusch@kernel.org, axboe@fb.com,
	chaitanyak@nvidia.com, davem@davemloft.net, kuba@kernel.org
Cc: Boris Pismenny <borisp@nvidia.com>,
	aurelien.aptel@gmail.com, smalin@nvidia.com, malin1024@gmail.com,
	ogerlitz@nvidia.com, yorayz@nvidia.com, galshalom@nvidia.com,
	mgurtovoy@nvidia.com, brauner@kernel.org
Subject: Re: [PATCH v23 05/20] nvme-tcp: Add DDP offload control path
Date: Thu, 07 Mar 2024 17:43:24 +0200	[thread overview]
Message-ID: <253plw6ujxf.fsf@nvidia.com> (raw)
In-Reply-To: <7a2c3491-bd2a-4104-8371-f5b98bbd7355@grimberg.me>

Sagi Grimberg <sagi@grimberg.me> writes:
>> +
>> +static int nvme_tcp_offload_socket(struct nvme_tcp_queue *queue)
>> +{
>> +     struct ulp_ddp_config config = {.type = ULP_DDP_NVME};
>> +     int ret;
>> +
>> +     config.nvmeotcp.pfv = NVME_TCP_PFV_1_0;
>> +     config.nvmeotcp.cpda = 0;
>> +     config.nvmeotcp.dgst =
>> +             queue->hdr_digest ? NVME_TCP_HDR_DIGEST_ENABLE : 0;
>> +     config.nvmeotcp.dgst |=
>> +             queue->data_digest ? NVME_TCP_DATA_DIGEST_ENABLE : 0;
>> +     config.nvmeotcp.queue_size = queue->ctrl->ctrl.sqsize + 1;
>> +     config.nvmeotcp.queue_id = nvme_tcp_queue_id(queue);
>
> I forget, why is the queue_id needed? it does not travel the wire outside
> of the connect cmd.

You're right it is not needed, we will remove it.

>> +static void nvme_tcp_ddp_apply_limits(struct nvme_tcp_ctrl *ctrl)
>> +{
>> +     ctrl->ctrl.max_segments = ctrl->ddp_limits.max_ddp_sgl_len;
>> +     ctrl->ctrl.max_hw_sectors =
>> +             ctrl->ddp_limits.max_ddp_sgl_len << (ilog2(SZ_4K) - SECTOR_SHIFT);
>
> I think you can use NVME_CTRL_PAGE_SHIFT instead of ilog2(SZ_4K)?

Yes both seems to be 12. We will use NVME_CTRL_PAGE_SHIFT.

Thanks


  reply	other threads:[~2024-03-07 15:43 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-28 12:57 [PATCH v23 00/20] nvme-tcp receive offloads Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 01/20] net: Introduce direct data placement tcp offload Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 02/20] netlink: add new family to manage ULP_DDP enablement and stats Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 03/20] iov_iter: skip copy if src == dst for direct data placement Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 04/20] net/tls,core: export get_netdev_for_sock Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 05/20] nvme-tcp: Add DDP offload control path Aurelien Aptel
2024-03-07  9:06   ` Sagi Grimberg
2024-03-07 15:43     ` Aurelien Aptel [this message]
2024-02-28 12:57 ` [PATCH v23 06/20] nvme-tcp: Add DDP data-path Aurelien Aptel
2024-03-07  9:11   ` Sagi Grimberg
2024-03-07 15:44     ` Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 07/20] nvme-tcp: RX DDGST offload Aurelien Aptel
2024-03-07  9:18   ` Sagi Grimberg
2024-03-07 15:44     ` Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 08/20] nvme-tcp: Deal with netdevice DOWN events Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 09/20] Documentation: add ULP DDP offload documentation Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 10/20] net/mlx5e: Rename from tls to transport static params Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 11/20] net/mlx5e: Refactor ico sq polling to get budget Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 12/20] net/mlx5: Add NVMEoTCP caps, HW bits, 128B CQE and enumerations Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 13/20] net/mlx5e: NVMEoTCP, offload initialization Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 14/20] net/mlx5e: TCP flow steering for nvme-tcp acceleration Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 15/20] net/mlx5e: NVMEoTCP, use KLM UMRs for buffer registration Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 16/20] net/mlx5e: NVMEoTCP, queue init/teardown Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 17/20] net/mlx5e: NVMEoTCP, ddp setup and resync Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 18/20] net/mlx5e: NVMEoTCP, async ddp invalidation Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 19/20] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Aurelien Aptel
2024-02-28 12:57 ` [PATCH v23 20/20] net/mlx5e: NVMEoTCP, statistics Aurelien Aptel
2024-02-29 17:32 ` [PATCH v23 00/20] nvme-tcp receive offloads Jakub Kicinski
2024-03-01 12:09   ` Aurelien Aptel
2024-03-01 17:03     ` Jakub Kicinski

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=253plw6ujxf.fsf@nvidia.com \
    --to=aaptel@nvidia.com \
    --cc=aurelien.aptel@gmail.com \
    --cc=axboe@fb.com \
    --cc=borisp@nvidia.com \
    --cc=brauner@kernel.org \
    --cc=chaitanyak@nvidia.com \
    --cc=davem@davemloft.net \
    --cc=galshalom@nvidia.com \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=malin1024@gmail.com \
    --cc=mgurtovoy@nvidia.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.