Re: [PATCH 09/10] watchdog: xilinx: Add missing binding

[Arnd Bergmann <arnd@arndb.de>]

On Monday 03 February 2014, Michal Simek wrote:
> On 02/03/2014 04:32 PM, Arnd Bergmann wrote:
> > On Monday 03 February 2014 16:13:47 Michal Simek wrote:
> >> Intention wasn't to fix binding but document current one
> >> which is in mainline for a long time.
> > 
> > Ok, I see.
> > 
> >> Apart of this - yes, wdt-enable-once is nowayout and wdt-interval should be timeout
> >> is seconds, and clock-frequency should go out and use CCF for getting clock.
> > 
> > Could we make a common binding then, and document that the xilinx
> > watchdog can optionally provide either one?
> 
> Do you mean to have 2 DT bindings?
> 
> This binding is used from 2011-07.
> It means it was generated for all hw designs at least from this time.
> I would say from DT usage on Microblaze because it is not special case
> in our dt generator.

I certainly wasn't suggesting to break the binding, quite the contrary.
What I tried to say is that the properties look like they should be
useful for different kinds of watchdogs, not just xilinx, so it would
be good to have a common definition using generic strings.

The xilinx driver would definitely have to keep supporting the traditional
property names, but it could also support the generic names in the
future.

> xlnx,XXX are XXX parameters which you have to setup in tools
> and get synthesized. This is valid for all xilinx IPs. We have full
> IP description by generating xlnx,XXX parameters directly from tools
> because we know all variants which can happen.
>
> Just back to your previous post:
> "I'm not sure about the enable-once flag, which seems to just map to the
> "nowayout" watchdog option that is not a hardware feature at all"
> this is hw feature which you can select in tools because this is fpga. :-)

Ah, so you mean the properties are not settings that the driver
programs into the hardware, but they are hardware properties that the
driver reports to user space?

	Arnd