Re: [RFC PATCH 9/9] dt-bindings: net: dsa: Add documentation for Hellcreek switches

From: Kurt Kanzenbach <kurt@linutronix.de>
To: Andrew Lunn <andrew@lunn.ch>
Cc: Vivien Didelot <vivien.didelot@gmail.com>,
	Florian Fainelli <f.fainelli@gmail.com>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	netdev@vger.kernel.org, Rob Herring <robh+dt@kernel.org>,
	devicetree@vger.kernel.org,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Richard Cochran <richardcochran@gmail.com>,
	Kamil Alkhouri <kamil.alkhouri@hs-offenburg.de>,
	ilias.apalodimas@linaro.org
Subject: Re: [RFC PATCH 9/9] dt-bindings: net: dsa: Add documentation for Hellcreek switches
Date: Tue, 23 Jun 2020 08:09:18 +0200	[thread overview]
Message-ID: <87eeq6nwj5.fsf@kurt> (raw)
In-Reply-To: <20200622134946.GM338481@lunn.ch>

[-- Attachment #1: Type: text/plain, Size: 1718 bytes --]

On Mon Jun 22 2020, Andrew Lunn wrote:
> On Mon, Jun 22, 2020 at 02:02:19PM +0200, Kurt Kanzenbach wrote:
>> 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.
>
> Hi Kurt
>
> Are there registers which allow you to determine the strapping?

No, there are not.

> There are phylib/phylink calls you can make to set the advertisement
> in the PHY. It would be good to do this in the DSA driver.

I will. All the chips currently available are configured to 100
Mbit/s. So, we can assume that for now.

Thanks,
Kurt

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 832 bytes --]