[PATCH 20/21] phy: Add support for Qualcomm's USB HSIC phy

[stephen.boyd@linaro.org (Stephen Boyd)]

Quoting Neil Armstrong (2016-06-29 02:16:51)
> On 06/28/2016 11:58 PM, Stephen Boyd wrote:
> > Quoting Neil Armstrong (2016-06-28 01:49:37)
> >> On 06/26/2016 09:28 AM, Stephen Boyd wrote:
> >>> +     uphy->cal_sleep_clk = clk = devm_clk_get(&ulpi->dev, "cal_sleep");
> >>> +     if (IS_ERR(clk))
> >>> +             return PTR_ERR(clk);
> >>
> >> Hi Stephen,
> >>
> >> In the bindings the cal_sleep is marked optional, and I think should be since AFAIK
> >> it's not present on MDM9615 for example.
> > 
> > The cal_sleep clk is just the sleep clk then (should be a board clk in
> > DT). Sometimes there's a gate in GCC to allow us to turn it off, other
> > times there isn't. Either way, it's always wired there so I'll update
> > the binding to say it isn't optional.
> 
> Sorry I don't understand !
> What should I do if GCC does not provide a gate here ? And looking at the driver, it could be optional.

You should set the property to point to &sleep_clk which should be under
the "clocks" node at the root of the OF tree. For example, see the
sleep_clk node in arch/arm/boot/dts/qcom-apq8064.dtsi.