netdev - Re: [PATCH] net: ftgmac100: Request clock and set speed

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] [day] [month] [year] [list]

Message-ID: <CACPK8Xd6CPfXJ3UnfCJxRPYq7CYXSt=2uS9N8sVt60e04GuB2w@mail.gmail.com>
Date:   Thu, 12 Oct 2017 11:02:10 +0800
From:   Joel Stanley <joel@....id.au>
To:     Benjamin Herrenschmidt <benh@...nel.crashing.org>
Cc:     "David S . Miller" <davem@...emloft.net>, netdev@...r.kernel.org,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Andrew Jeffery <andrew@...id.au>
Subject: Re: [PATCH] net: ftgmac100: Request clock and set speed

On Tue, Oct 10, 2017 at 4:14 PM, Benjamin Herrenschmidt
<benh@...nel.crashing.org> wrote:
> On Tue, 2017-10-10 at 15:19 +1030, Joel Stanley wrote:
>> According to the ASPEED datasheet, gigabit speeds require a clock of
>> 100MHz or higher. Other speeds require 25MHz or higher.
>
> Did you try "live" changing by either using ethtool or plugging into
> switches/hubs at different speed ?
>
> Also this is aspeed'isms, we should probably keep that under an
> is_aspeed test.
>
> My assumption is that we wouldn't bother, and just leave the freq
> set based on whether there's a physical gigabit capable connection or
> not (ie, real gigabit PHY vs. NC-SI really). But if it can help save a
> few milliwatts..

I didn't try changing the link speed at runtime. I don't have a setup
that lets me precisely measure power consumption, so it's hard to know
what the benefits are. In the future I can revisit this and do those
measurements.

I'll change it to be as you suggest; 100MHz for PHY and 50MHz for NC-SI.

Cheers,

Joel