On Tue, Sep 09, 2014 at 12:59:29PM -0700, Nicolin Chen wrote:
> On Tue, Sep 09, 2014 at 02:37:42PM -0500, Timur Tabi wrote:
> > On 09/09/2014 01:38 PM, Nicolin Chen wrote:
> > >make sure to have the call for imx only because it seems that
> > >the other platforms do not depend on the clock.
> >
> > Although I doubt anyone will every add support for clocks to PowerPC "side"
> > of this driver, I would prefer to avoid IMX-specific changes. Instead, the
> > code should check if a clock is available. That's why I suggested this
> > change:
> >
> > - if (ssi_private->soc->imx)
> > + if (!IS_ERR(ssi_private->clk))
>
> Hmm.... I think the following change may be better?
>
> probe() {
> ....
> + /*
> + * Initially mark the clock to NULL for all platforms so that later
> + * clk_prepare_enable() will ignore and return 0 for non-clock cases.
> + */
> + ssi_private->clk = NULL;
> .....
> fsl_ssi_imx_probe();
> }
ssi_private is initialized to zero in beginning of probe. I think no need to
add this change here.
wang shengjiu
>
> In this way, all platforms, not confined to imx any more, will be able
> to call clk_prepare_enable(). Then we don't need an extra platform check
> before calling it.
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
