[PATCH v4 1/4] drivers: usb: phy: add a new driver for usb part of control module

[mark.rutland@arm.com (Mark Rutland)]

On Fri, Jan 25, 2013 at 02:59:28PM +0000, Felipe Balbi wrote:
> Hi,
> 
> On Fri, Jan 25, 2013 at 12:29:43PM +0000, Mark Rutland wrote:
> > > > > +   depending upon omap4 or omap5.
> > > > > + - reg-names: The names of the register addresses corresponding to the registers
> > > > > +   filled in "reg".
> > > > > + - ti,type: This is used to differentiate whether the control module has
> > > > > +   usb mailbox or usb3 phy power. omap4 has usb mailbox in control module to
> > > > > +   notify events to the musb core and omap5 has usb3 phy power register to
> > > > > +   power on usb3 phy. Should be "1" if it has mailbox and "2" if it has usb3
> > > > > +   phy power.
> > > > 
> > > > Why not make this a string property, perhaps values "mailbox" or "register"?
> > > 
> > > NAK.
> > 
> > Can I ask what your objection to using a string property is?
> > 
> > As far as I can see, "ti,type" is only used by this driver, so there's no
> > common convention to stick to. Using a string makes the binding easier for
> > humans to read, and thus harder to mess up in a dts, and it decouples the
> > binding from kernel-side constants.
> 
> IIRC there is some work going on to add #define-like support for DT,
> which would allow us to match against integers while still having
> meaningful symbolic representations.

I was under the impression that the motivation for using the preprocessor on
the DT was to allow symbolic names for device/soc-specific values like
addresses, rather than what amounts to ABI values for the binding.

I don't see the point in building a binding that depends on future
functionality to be legible, especially as we can make it more readable,
robust, and just as extensible today, with a simple change to the proposed
binding.

Even ignoring the above, the driver isn't doing appropriate sanity checking.
If you use a string property, this sanity check is implicit in the parsing --
you've either matched a value you can handle or you haven't.

Thanks,
Mark.