Hi,
On Fri, Feb 08, 2013 at 06:04:03PM +0300, Sergei Shtylyov wrote:
> Hello.
>
> On 02/08/2013 04:02 PM, Felipe Balbi wrote:
>
> > this will make sure that request_memory_region() will
> > be called and that we don't need to manually call
> > iounmap() on ->remove().
>
> > Signed-off-by: Felipe Balbi <balbi@xxxxxx>
> > ---
> > drivers/usb/musb/musb_core.c | 11 ++---------
> > 1 file changed, 2 insertions(+), 9 deletions(-)
>
> > diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
> > index a68ff27..48609ea 100644
> > --- a/drivers/usb/musb/musb_core.c
> > +++ b/drivers/usb/musb/musb_core.c
> > @@ -2014,7 +2014,6 @@ static int musb_probe(struct platform_device *pdev)
> > {
> > struct device *dev = &pdev->dev;
> > int irq = platform_get_irq_byname(pdev, "mc");
> > - int status;
> > struct resource *iomem;
> > void __iomem *base;
> >
> > @@ -2022,24 +2021,19 @@ static int musb_probe(struct platform_device *pdev)
> > if (!iomem || irq <= 0)
> > return -ENODEV;
> >
> > - base = ioremap(iomem->start, resource_size(iomem));
> > + base = devm_ioremap_resource(dev, iomem);
>
> devm_ioremap_resource() is not in mainline yet, AFAIK. Maybe we should call
I'm not sending this patch for v3.9 anyway...
> devm_request_mem_region() in the glue layers instead? I'm preparing a patch that
better not since that's being deprecated.
> will only pass MUSB register subrange to the MUSB core from the glue layers
that'll be one nice patch to have.
> (have long promised it but musbhsdma.c part turned out to be not ready for prime
> time and I have to find a time to finish it).
>
> > if (!base) {
>
> devm_ioremap_resource() returns error pointer, not NULL, AFAIR.
>
> > dev_err(dev, "ioremap failed\n");
>
> devm_ioremap_resource() prints the error message itself.
>
> > return -ENOMEM;
>
> You should pass up what devm_ioremap_resource() returned.
right, good point.
--
balbi
Attachment:
signature.asc
Description: Digital signature
