On Tue, 2019-04-16 at 12:12 +0200, Greg Kroah-Hartman wrote:
> On Wed, Apr 10, 2019 at 02:47:24PM +0800, Chunfeng Yun wrote:
> > Use devm_clk_get_optional() to get optional clock
> >
> > Signed-off-by: Chunfeng Yun <chunfeng.yun@xxxxxxxxxxxx>
> > ---
> > v2: no changes
> > ---
> > drivers/usb/host/xhci-mtk.c | 19 +++----------------
> > 1 file changed, 3 insertions(+), 16 deletions(-)
> >
> > diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c
> > index 60987c787e44..026fe18972d3 100644
> > --- a/drivers/usb/host/xhci-mtk.c
> > +++ b/drivers/usb/host/xhci-mtk.c
> > @@ -206,19 +206,6 @@ static int xhci_mtk_ssusb_config(struct xhci_hcd_mtk *mtk)
> > return xhci_mtk_host_enable(mtk);
> > }
> >
> > -/* ignore the error if the clock does not exist */
> > -static struct clk *optional_clk_get(struct device *dev, const char *id)
> > -{
> > - struct clk *opt_clk;
> > -
> > - opt_clk = devm_clk_get(dev, id);
> > - /* ignore error number except EPROBE_DEFER */
> > - if (IS_ERR(opt_clk) && (PTR_ERR(opt_clk) != -EPROBE_DEFER))
>
> Are you sure about this?
>
> devm_clk_get_optional() does not check for -EPROBE_DEFER, so you just
> changed the functionality of this code. Is that ok?
Yes, checking for -ENOENT covers more error cases than -EPROBE_DEFER,
and the original purpose also wants to ignore non-exist clock
> If so, please call
> it out explicitly in your changelog comment when you resend this.
I'll add it in next version
Thanks a lot
>
> thanks,
>
> greg k-h
