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

[Sebastian Reichel]

Hi,

On Mon, Jan 22, 2018 at 12:56:44PM -0800, Florian Fainelli wrote:
> 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.

Right. For the i210 the internal phy is used, so there is no
phy-handle. It's basically a normal network card. It looks
like this:

i210.internal-phy <--- pcb lanes ---> switch.port4.internal-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

Attachment: signature.asc
Description: PGP signature