Re: [PATCHv4 1/5] net: dsa: Support internal phy on 'cpu' port

[Florian Fainelli]

On 01/22/2018 12:54 PM, Andrew Lunn wrote:
>> Note: there is still technically a misreprentation of how the PHY is
>> "attached" to the network device. In your DTSes, you have to have the
>> CPU port have a "phy-handle" to the internal PHY, while technically it
>> should be the i210 which has a "phy-handle" property to that PHY, and
>> even better, if the e1000e/idb drivers were PHYLIB capable, they could
>> manage it directly.
> 
> Hi Florian
> 
> Err, i don't think i agree. But maybe i'm missunderstanding.
> 
> We have two back-to-back PHYs. I would expect the i210 MAC to have a
> phy-handle pointing it its PHY. The CPU port would then point to the
> internal switch PHY.

Is it really a back-to-back PHY? If that is the case, ok, that can
indeed work without magnetics, but this is really an inefficient way to
connect a MAC to a switch, especially when you can do direct (R)GMII
without any PHY in between... If that is the case, then disregard my
comment.

> 
> Or are you suggesting the i210 has two phy-handles, its own and the
> switches?

Not suggesting that, that would be weird.

> 
> 	Andrew
> 


-- 
Florian