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

On Mon, Jun 22, 2020 at 02:02:19PM +0200, Kurt Kanzenbach wrote:

On Fri Jun 19 2020, Andrew Lunn wrote:

quoted

quoted

quoted

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? 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.

     Andrew