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
