netdev - Re: [RFC PATCH net-next 0/2] Configuring PFC stall prevention via ethtool

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]

Date:   Thu, 16 Nov 2017 14:03:21 +0200
From:   Eran Ben Elisha <eranlinuxmellanox@...il.com>
To:     Michal Kubecek <mkubecek@...e.cz>
Cc:     Eran Ben Elisha <eranbe@...lanox.com>,
        Linux Netdev List <netdev@...r.kernel.org>,
        "David S. Miller" <davem@...emloft.net>,
        "John W. Linville" <linville@...driver.com>,
        Saeed Mahameed <saeedm@...lanox.com>,
        Gal Pressman <galp@...lanox.com>,
        Ariel Almog <ariela@...lanox.com>,
        Inbar Karmy <inbark@...lanox.com>
Subject: Re: [RFC PATCH net-next 0/2] Configuring PFC stall prevention via ethtool

On Thu, Nov 16, 2017 at 10:44 AM, Michal Kubecek <mkubecek@...e.cz> wrote:
> On Wed, Nov 15, 2017 at 09:00:09PM +0200, Eran Ben Elisha wrote:
>> From: Inbar Karmy <inbark@...lanox.com>
>>
>> This RFC adds support for configuring PFC stall prevention through ethtool.
>>
>> In the event where the device unexpectedly becomes unresponsive for a long
>> period of time, flow control mechanism may propagate pause frames which will
>> cause congestion spreading to the entire network.
>>
>> To prevent this scenario, the device may implement a protection mechanism for
>> monitoring and resolving such state.  The following patches allow the user to
>> control the stall prevention functionality.
>>
>> PFC stall prevention configuration is done via ethtool -a (pause).
>> Two modes are introduced:
>> Default - current behavior per driver.
>> Auto - protection mechanism controlled automatically by the driver.
>> Due to lack of extension ability of ethtool_ops set_pauseparam, a new
>> ethtool_ops get_pfc_prevention_mode is introduced.
>
> I don't like adding another ethtool_ops callback tightly tied to the
> structures passed via ioctl() but when I started to think what to
> suggest as an alternative, I started to wonder if it is really necessary
> to add a new ethtool command at all. Couldn't this be handled as
> a tunable?
>
> Michal Kubecek

tunable seems as a good infrastructure to PHY tuning, however this
feature is not a PHY feature.
To me, it's looks fit to ethtool -a where pause operations are being controlled.
Unfortunately set/get_pauseparam is not extensible and need a new operation.

Eran.