Re: [PATCH v2 05/11] net: stmmac: dwmac-rk: Add internal phy support

[Corentin Labbe <clabbe.montjoie@gmail.com>]

On Thu, Jul 27, 2017 at 09:54:01AM -0700, Florian Fainelli wrote:
> On 07/27/2017 06:48 AM, Andrew Lunn wrote:
> > On Thu, Jul 27, 2017 at 09:02:16PM +0800, David Wu wrote:
> >> To make internal phy work, need to configure the phy_clock,
> >> phy cru_reset and related registers.
> >>
> >> Signed-off-by: David Wu <david.wu@rock-chips.com>
> >> ---
> >> changes in v2:
> >>  - Use the standard "phy-mode" property for internal phy. (Florian)
> > 
> > I think we need to discuss this. This PHY appears to be on an MDIO
> > bus, it uses a standard PHY driver, and it appears to be using an RMII
> > interface. So it is just an ordinary PHY.
> 
> First, the fact that the internal PHY also appears through MDIO is
> orthogonal to the fact that it is internal or external. Plenty of
> designs have internal PHYs exposed through MDIO because that is
> convenient. What matters though is how the data/clock lines are wired
> internally, which is what "phy-mode" describes.
> 
> > 
> > Internal is supposed to be something which is not ordinary, does not
> > use one of the standard phy modes, needs something special to make it
> > work.
> > 
> > Florain, it appears to be your suggestion to use internal. What do you
> > say?
> 
> phy-mode = "internal" really means that it is not a standard MII variant
> to connect the data/clock lines between the Ethernet MAC and the PHY,
> and this can happen in some designs (although quite unlikely). So from
> there we could do several things depending on the requirements:
> 
> - if you can have your Ethernet MAC driver perform the necessary
> configuration *after* you have been able to bind the PHY device with its
> PHY driver, then the PHY driver should have PHY_IS_INTERNAL in its
> flags, and you can use phy_is_internal() from PHYLIB to tell you that
> and we could imagine using: phy-mode = "rmii" because that would not too
> much of a stretch
> 
> - if you need knowledge about this PHY connection type prior to binding
> the PHY device and its driver (that is, before of_phy_connect()) we
> could add a boolean property e.g: "phy-is-internal" that allows us to
> know that, or we can have a new phy-mode value, e.g: "internal-rmii"
> which describes that, either way would probably be fine, but the former
> scales better
> 

Hello

We have the same problem on Allwinner SoCs for dwmac-sun8i, we need to set a syscon for chossing between internal/external PHY.
Having this phy-is-internal would be very helpfull. (adding internal-xmii will add too many flags in our case)

Thanks
Regards
Corentin Labbe