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@xxxxxxxxxxxxxx> > >> --- > >> 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 -- To unsubscribe from this list: send the line "unsubscribe devicetree" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
