[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87imfjtik4.fsf@kurt>
Date: Mon, 22 Jun 2020 14:02:19 +0200
From: Kurt Kanzenbach <kurt@...utronix.de>
To: Andrew Lunn <andrew@...n.ch>
Cc: Vivien Didelot <vivien.didelot@...il.com>,
Florian Fainelli <f.fainelli@...il.com>,
"David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>, netdev@...r.kernel.org,
Rob Herring <robh+dt@...nel.org>, devicetree@...r.kernel.org,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Richard Cochran <richardcochran@...il.com>,
Kamil Alkhouri <kamil.alkhouri@...offenburg.de>,
ilias.apalodimas@...aro.org
Subject: Re: [RFC PATCH 9/9] dt-bindings: net: dsa: Add documentation for Hellcreek switches
On Fri Jun 19 2020, Andrew Lunn wrote:
>> > The switch is 100/100Mbps right? The MAC is only Fast ethernet. Do you
>> > need some properties in the port@0 node to tell the switch to only use
>> > 100Mbps? I would expect it to default to 1G. Not looked at the code
>> > yet...
>>
>> No, that is not needed. That is a hardware configuration and AFAIK
>> cannot be changed at run time.
>
> I was wondering about that in general. I did not spot any code in the
> driver dealing with results from the PHY auto-neg. So you are saying
> the CPU is fixed speed, by strapping? But what about the other ports?
> Does the MAC need to know the PHY has negotiated 10Half, not 1G? Would
> that not make a difference to your TSN?
Indeed, that does make a difference. I've checked with the vendor. The
current version of the switch IP does not support configuring the speed
etc. at run time. It is hard wired to 100 Mbit/s or 1000 Mbit/s for
now. Later versions of the chip might support setting the speed etc. via
configuration registers. As a result the PHYs at the front ports should
be programmed to only advertise 100 Mbit/s or 1G depending on the
hardware setup.
Thanks,
Kurt
Download attachment "signature.asc" of type "application/pgp-signature" (833 bytes)
Powered by blists - more mailing lists