netdev - Re: [PATCH v15 05/20] nvme-tcp: Add DDP offload control path

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <2531qevgwqh.fsf@nvidia.com>
Date: Mon, 18 Sep 2023 21:30:30 +0300
From: Aurelien Aptel <aaptel@...dia.com>
To: Sagi Grimberg <sagi@...mberg.me>, linux-nvme@...ts.infradead.org,
 netdev@...r.kernel.org, hch@....de, kbusch@...nel.org, axboe@...com,
 chaitanyak@...dia.com, davem@...emloft.net, kuba@...nel.org
Cc: Boris Pismenny <borisp@...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: Re: [PATCH v15 05/20] nvme-tcp: Add DDP offload control path

Sagi Grimberg <sagi@...mberg.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);
>> +     config.nvmeotcp.io_cpu = queue->sock->sk->sk_incoming_cpu;
>
> Please hide io_cpu inside the interface. There is no reason for
> the ulp to assign this. btw, is sk_incoming_cpu stable at this
> point?

We will move the assignemnt of io_cpu to the interface.
As you suggested we followed aRFS (and the NVMeTCP target) which uses
sk->sk_incoming_cpu.