Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Thu, 22 Sep 2022 19:23:13 -0700
From:   Jakub Kicinski <kuba@kernel.org>
To:     Guangbin Huang <huangguangbin2@huawei.com>
Cc:     <jiri@mellanox.com>, <moshe@mellanox.com>, <davem@davemloft.net>,
        <idosch@nvidia.com>, <edumazet@google.com>, <pabeni@redhat.com>,
        <netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        <lipeng321@huawei.com>, <chenhao418@huawei.com>
Subject: Re: [PATCH net-next 2/2] net: hns3: PF add support setting
 parameters of congestion control algorithm by devlink param
Message-ID: <20220922192313.628470a6@kernel.org>
In-Reply-To: <20220923013818.51003-3-huangguangbin2@huawei.com>
References: <20220923013818.51003-1-huangguangbin2@huawei.com>
        <20220923013818.51003-3-huangguangbin2@huawei.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Precedence: bulk

On Fri, 23 Sep 2022 09:38:18 +0800 Guangbin Huang wrote:
> Some new devices support dynamiclly configuring parameters of congestion
> control algorithm, this patch implement it by devlink param.
> 
> Examples of read and set command are as follows:
> 
> $ devlink dev param set pci/0000:35:00.0 name algo_param value \
>   "type@dcqcn_alp@30_f@35_tmp@11_tkp@11_ai@60_maxspeed@17_g@11_al@19_cnptime@20" \
>   cmode runtime
> 
> $ devlink dev param show pci/0000:35:00.0 name algo_param
> pci/0000:35:00.0:
>   name algo_param type driver-specific
>     values:
>       cmode runtime value type@dcqcn_ai@60_f@35_tkp@11_tmp@11_alp@30_maxspeed@17_g@11_al@19_cnptime@20

Please put your RDMA params to the RDMA subsystem.
It's not what devlink is for. In general 95% of the time devlink params
are not the answer upstream.