On Thu, Jul 27, 2017 at 07:31:52PM +0200, Corentin Labbe wrote: > 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 > > 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) In our case, we'll always have a phy node, so we can have a compatible that will give you the same information. Maxime -- Maxime Ripard, Free Electrons Embedded Linux and Kernel engineering http://free-electrons.com
Attachment:
signature.asc
Description: PGP signature
